CN109979568B - Mental health early warning method, server, family member terminal and system - Google Patents
Mental health early warning method, server, family member terminal and system Download PDFInfo
- Publication number
- CN109979568B CN109979568B CN201910229694.9A CN201910229694A CN109979568B CN 109979568 B CN109979568 B CN 109979568B CN 201910229694 A CN201910229694 A CN 201910229694A CN 109979568 B CN109979568 B CN 109979568B
- Authority
- CN
- China
- Prior art keywords
- mental health
- user
- content
- family
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 230000004630 mental health Effects 0.000 title claims abstract description 198
- 238000000034 method Methods 0.000 title claims abstract description 124
- 238000004458 analytical method Methods 0.000 claims abstract description 172
- 230000008451 emotion Effects 0.000 claims abstract description 166
- 230000000474 nursing effect Effects 0.000 claims description 34
- 238000010801 machine learning Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 6
- 230000018109 developmental process Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000007635 classification algorithm Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 238000004891 communication Methods 0.000 claims 2
- 230000008569 process Effects 0.000 description 38
- 230000006870 function Effects 0.000 description 14
- 238000012544 monitoring process Methods 0.000 description 10
- 238000013459 approach Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 8
- 230000006996 mental state Effects 0.000 description 8
- 208000020016 psychiatric disease Diseases 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 4
- 238000003909 pattern recognition Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008909 emotion recognition Effects 0.000 description 3
- 230000002996 emotional effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000003340 mental effect Effects 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000009098 adjuvant therapy Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Hospice & Palliative Care (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Child & Adolescent Psychology (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Acoustics & Sound (AREA)
- Probability & Statistics with Applications (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Developmental Disabilities (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
Abstract
The invention provides a mental health early warning method, which comprises the following steps: receiving the content of the user terminal; performing sentiment analysis on the content; judging the mental health level according to the emotion analysis result; and sending early warning information to the family terminal according to the mental health level. The invention also provides a mental health early warning server, a terminal and a system, which solve the problem that the mental health state cannot be tracked in time in the prior art, and can realize timely tracking and warning through emotion analysis.
Description
Technical Field
The invention relates to the technical field of psychological assessment, in particular to a mental health early warning method, a server, a family terminal and a system.
Background
The increase of life pressure and other reasons, the increase of patients suffering from psychological diseases such as depression continues. Traditional mental health levels need to be assessed by a physician seeking face-to-face assistance from the patient to a mental hospital. In fact, many patients do not actively visit the hospital and are difficult to track the mental health level in time. For people with poor mental health, family adjuvant therapy is especially absent. Most of rehabilitation lives of patients with psychological diseases are spent at home, and the mental health level of the patients can be improved through scientific family care, so that psychological intervention can be performed on the patients in time. However, the general family has difficulty in making professional judgment on the mental health level of the depression patient, does not have professional knowledge, and cannot take psychological auxiliary nursing and intervention according to the mental health level of the depression patient.
Aiming at the problem that the mental health state cannot be tracked in time in the prior art, an effective solution is not provided at present.
Disclosure of Invention
The present invention aims to solve the above technical problem at least to some extent.
The embodiment of the invention provides a mental health early warning method, a server, a family member terminal and a system, which aim to solve the problem that the prior art cannot track the mental health state in time.
According to an aspect of an embodiment of the present invention, there is provided a mental health early warning method, including:
receiving the content of the user terminal;
performing sentiment analysis on the content;
judging the mental health level according to the emotion analysis result;
and sending early warning information to the family terminal according to the mental health level.
According to an aspect of an embodiment of the present invention, there is provided a mental health early warning method, including:
receiving early warning information sent by a server according to the mental health level;
generating an early warning interface according to the early warning information, wherein the early warning interface displays the early warning information through one or more of characters, images, audios or videos
According to still another aspect of an embodiment of the present invention, there is provided a mental health warning server, including:
the receiving module is used for receiving the content of the user terminal, wherein the content is the content input by the user terminal in the user input method or the content of a webpage currently browsed by a user;
the analysis module is used for carrying out emotion analysis on the content;
the judging module is used for judging the mental health level according to the emotion analysis result;
and the early warning module is used for sending early warning information to the family terminal according to the mental health level.
According to another aspect of the embodiments of the present invention, there is provided a mental health early warning family terminal, including:
the third receiving module is used for receiving early warning information sent by the server according to the mental health level;
and the generation module is used for generating an early warning interface according to the early warning information, and the early warning interface displays the early warning information through one or more combinations of characters, images, audios or videos.
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides a mental health early warning method, a server, a family terminal and a system which can realize timely tracking and warning through emotion analysis.
Drawings
Fig. 1 is a flowchart of a mental health early warning method according to an embodiment of the present invention.
Fig. 2 is a flowchart of the emotion analysis step performed on the content by the mental health early warning method according to the embodiment of the present invention.
Fig. 3 is a flowchart illustrating the emotion analyzing step for the content according to a mental health warning method according to another embodiment of the present invention.
Fig. 4 is a flowchart of emotion steps of selecting an emotion analysis tool corresponding to the character type to analyze the content according to the mental health early warning method in the embodiment of the present invention.
Fig. 5 is a flowchart illustrating a method for mental health early warning according to the emotion analysis result to determine the mental health level according to an embodiment of the present invention.
Fig. 6 is a flowchart illustrating a data synchronization frequency setting procedure of a mental health warning method according to an embodiment of the present invention.
Fig. 7 is a flowchart illustrating a mental health warning method according to another embodiment of the present invention, wherein the mental health level is used to set a data synchronization frequency.
Fig. 8 is a flowchart of steps of inquiring matched family member assistant nursing knowledge points by using a mental health early warning method according to an embodiment of the present invention.
Fig. 9 is a flowchart of a mental health warning method according to yet another embodiment of the present invention.
Fig. 10 is a flowchart of a mental health warning method according to another embodiment of the present invention.
Fig. 11 is a flowchart of a mental health warning method according to another embodiment of the present invention.
Fig. 12 is a flowchart illustrating a mental health warning method according to yet another embodiment of the present invention.
Fig. 13 is a schematic structural diagram of a mental health warning server according to an embodiment of the present invention.
Fig. 14 is a schematic structural diagram of a mental health early warning user terminal according to an embodiment of the present invention.
Fig. 15 is a schematic structural diagram of a mental health early warning family terminal according to an embodiment of the present invention.
Fig. 16 is a schematic structural diagram of a mental health warning system according to an embodiment of the present invention.
Wherein: 100. a server; 101. a first receiving module; 102. an analysis module; 103. a judgment module; 104. an early warning module; 105. a selection module; 106. a statistical module; 107. a calculation module; 108. setting a module; 109. a first sending module; 110. a query module; 200. a user terminal; 201. a second detection module; 202. an acquisition module; 203. a second sending module; 204. a second receiving module; 300. a family terminal; 301. a third receiving module; 302. a generation module; 303. a third detection module; 304. and a display module.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1, according to an aspect of an embodiment of the present invention, there is provided a mental health early warning method, including:
s110: receiving the content of a user terminal, wherein the content is the content input by a user terminal acquisition user input method or the content of a webpage browsed by a user currently;
s120: performing sentiment analysis on the content;
s130: judging the mental health level according to the emotion analysis result;
s140: and sending early warning information to the family terminal according to the mental health level.
In a specific implementation process, a server receives content of a user terminal sent by the user terminal, wherein the content is content which is acquired by the user terminal and input by a user in an input method or webpage content currently browsed by the user; the server analyzes the emotion of the content; the server judges the mental health level according to the emotion analysis result; and the server sends early warning information to the family terminal according to the mental health level.
The method comprises the steps of actively collecting the content input or browsed by a user in a user terminal held by the user, carrying out emotion analysis on the content, judging the mental health level of the user according to the emotion analysis result, and tracking the mental health level of the user in real time under the condition that the user does not need to go to a hospital for inquiry.
Due to the adoption of the mode of actively analyzing the user content, the problem that psychological medical resources are in short supply because the psychological state of the user can be known only by one-to-one manual inquiry in the prior art is solved, and thus, psychologists can service the psychological medical resources in one-to-many ways.
The server sends early warning information to the family terminals held by the families according to the mental health level, so that the families can perform psychological monitoring and intervention on the user in time, and the negative emotion of the user can be relieved.
As shown in fig. 2, in a specific implementation process, the step of performing sentiment analysis on the content includes:
s121: judging the type of the content, wherein the type comprises a text, a picture or a voice;
s122: and selecting a corresponding emotion analysis mode according to the type of the content, wherein the emotion analysis mode comprises text analysis, picture analysis and voice analysis.
Specifically, the server judges the type of the content, wherein the type comprises a text, a picture or a voice; and the server selects a corresponding emotion analysis mode according to the type of the content, wherein the emotion analysis mode comprises text analysis, picture analysis and voice analysis.
Specifically, if the type is a picture, the server selects an image emotion analysis technology to perform image emotion recognition on the content. The image emotion analysis is to analyze and extract emotional features from an image, perform calculation on the emotional features by using a pattern recognition and machine learning method, and further understand human emotion. The main pattern recognition technology in image emotion analysis comprises the following steps: template matching pattern recognition, fuzzy pattern recognition, pattern recognition of support vector machines, and deep learning based on artificial neural networks. The specific method of image emotion analysis is prior art and is not described in detail herein.
Specifically, if the type is voice, the server selects a voice emotion analysis technology to perform image emotion recognition on the content. The speech emotion analysis is to analyze and process the speech signal to obtain the emotional state of the person. The main speech emotion recognition algorithm comprises a Gaussian mixture model, a support vector machine, K nearest neighbor, a hidden Markov model, a spectrogram + convolution cyclic neural network and a manual feature + convolution cyclic neural network. The specific method of speech emotion analysis is prior art and is not described in detail herein.
Some users prefer to input voice or pictures, and select a corresponding emotion analysis mode according to the type of the content, so that emotion analysis can be performed when the users input rich media content, such as pictures, voice and other content.
In a specific implementation process, the step of selecting a corresponding emotion analysis mode according to the type of the content comprises the following steps: and if the content is a text, analyzing the emotion of the content.
Specifically, if the content is text, the server analyzes the emotion of the content. The method and algorithm for realizing the text emotion analysis comprise a rule-based automatic system and a mixing system. Rule-based methods define a set of rules through a script that identify subjectivity, polarity, or opinion subjects. The rules may use various inputs. For example, classical NLP techniques such as stemming, notation, part-of-speech tagging and parsing. In addition, rules may also use dictionaries (i.e., lists of words and expressions). The main steps of the rule-based algorithm include: defining two lists of polarized words (e.g., negative words such as bad, worst, ugly, etc., and positive words such as good, best, beauty, etc.); the number of active words present in the text in the content is calculated. The number of negative words present in the text is calculated. A positive emotion is returned if the number of positive occurrences is greater than the number of negative word occurrences and, conversely, a negative emotion is returned. Otherwise, return to neutral. Automated methods rely on machine learning. The sentiment analysis task is typically modeled as a classification problem, with the text of the content being input to a classifier and then returned to the corresponding category, e.g., positive, negative or neutral (if polarity analysis is being performed).
In an exemplary embodiment, if the content is text, the algorithm for analyzing the emotion of the content includes a training unit and an analyzing unit. The implementation of the training unit is: using the development set; training the training set in the machine learning classification algorithm to obtain a machine learning model classifier; classifying the development set by using a machine learning model classifier, and finally obtaining a text classification result; manually intervening by utilizing a corpus to label data of the text, and giving the accurate accuracy of the machine learning classifier; obtaining an algorithm and a characteristic dimension; and obtaining a test set, and testing the established machine learning. The analysis unit is implemented as: calling a trained Bayes model; saving the final model; loading a final Bayesian model; word segmentation and word stop operation; reading in active text and passive text; calling a Bayes model training method; calling a handle method in the sentent class; calling a classfy method in a Bayes class; the classsify method in bayes is called.
As shown in fig. 3, in a specific implementation process, if the content is a text, the step of performing emotion analysis on the content includes:
s123: judging the character type of the content, wherein the character type comprises one or more combinations of Chinese, English and other characters;
s124: and selecting an emotion analysis tool corresponding to the character type to analyze the emotion of the content.
Specifically, the server judges the character type of the content, wherein the character type comprises one or more combinations of Chinese, English and other characters; and the server selects an emotion analysis tool corresponding to the character type to analyze the emotion of the content. If the character type is English, the server selects English text sentiment analysis tools including Natural Language Toolkit (NLTK), scinit-left, spaCy, Textacy, Tensorflow, Theano, fastText, TextBlob. If the character type is Chinese, the server selects Chinese text emotion analysis tools including SnowNLP, BosonNLP and Tencent AI emotion analysis.
And selecting a corresponding emotion analysis tool by judging the character type, so that the method can be applied to the use in various language environments.
As shown in fig. 4, in a specific implementation process, the selecting an emotion analysis tool corresponding to the character type to analyze the emotion of the content includes:
s124 a: counting character types in the content;
s124 b: if the character types comprise two or more than two languages, counting the number of characters corresponding to each character type;
s124 c: calculating the proportion of the number of characters of each character type to the total number of text characters;
s124 d: and calculating the emotion analysis result of the content according to the proportion of each character type.
Specifically, the step of selecting an emotion analysis tool corresponding to the character type to analyze the emotion of the content includes: the server counts character types in the content; if the character types contain two or more languages, the server counts the number of characters corresponding to each character type; the server calculates the proportion of the number of characters of each character type to the total number of text characters; and the server calculates the emotion analysis result of the content according to the proportion of each character type.
In practical circumstances, some users prefer to express the same sentence in multiple languages, such as a hybrid Chinese-English sentence. And calculating the emotion analysis result of the content according to the proportion of each character type, so that the emotion analysis problem that a plurality of languages are mixed in the same sentence can be effectively solved.
In a specific implementation process, the step of calculating the emotion analysis result of the content according to the proportion of each character type includes:
and calculating an emotion analysis result formula of the content as follows:
wherein, PLiThe emotion analysis result is the ith character;
KLithe ratio of the number of the ith characters to the total number of the text characters
And P is the emotion analysis result of the content.
Specifically, P is a number between 0 and 1, and is more positive as approaching 1 and more negative as approaching 0.
As shown in fig. 5, in a specific implementation process, the step of determining the mental health level according to the emotion analysis result further includes:
s131: counting historical emotion analysis results;
s132: and judging the mental health level according to the difference between the historical emotion analysis result and the current emotion analysis result.
Specifically, the step of judging the mental health level according to the emotion analysis result further includes: the server counts historical emotion analysis results; and the server judges the mental health level according to the difference between the historical emotion analysis result and the current emotion analysis result. In particular, the historical sentiment analysis results may include historical sentiment analysis results for different periods, such as a previous day, a previous week, a previous month, a previous quarter, a previous year, or historical sentiment analysis results since use.
In a specific implementation process, the step of judging the mental health level according to the difference between the historical emotion analysis result and the current emotion analysis result comprises the following steps:
the mental health level calculation formula is as follows:
wherein, beta is a mental health level value;
and the current emotion analysis result is the average value of the last m emotion analysis results.
Specifically, the average value of the historical emotion analysis results is compared with the current emotion analysis results, so that the change of the emotion value variation can be monitored. When the change in the beta emotion value is large and positive, the larger beta, the worse the mental health level, and the more negative the mental state. When beta is negative, the mental health level is high, and the mental state is more positive than the historical emotion. As β approaches 0, it indicates less psychological fluctuation.
In a specific implementation process, the mental health level calculation formula is as follows:
wherein, beta is a mental health level value;
and the current emotion analysis result is the average value of the last m emotion analysis results.
specifically, the closer to the period of the current time, the larger the time correlation coefficient. The sum of the time correlation coefficients is 1. In a specific embodiment, the ith cycle time correlation coefficient may be set as:
the 1 st period is the previous day, the time correlation coefficient K of the previous dayβ1=0.4;
The 2 nd period is the previous week, the time correlation coefficient K of the previous weekβ2=0.3;
The 3 rd period is the previous month, the time correlation coefficient K of the previous monthβ3=0.15;
The 4 th period is the previous season, and the time correlation coefficient K of the previous seasonβ4=0.10;
The 5 th cycle is the previous year and the time correlation coefficient K of the previous yearβ5=0.05。
Specifically, the longer the historical emotion analysis result is from the current time, the smaller the reference degree of the difference value of the current emotion analysis result is. And a time correlation coefficient is added, so that the mental health level value can reflect the difference value of mental change. When the change in the beta emotion value is large and positive, the larger beta, the worse the mental health level, and the more negative the mental state. When beta is negative, the mental health level is high, and the mental state is more positive than the historical emotion. As β approaches 0, it indicates less psychological fluctuation.
In one exemplary embodiment, the mental health level can be divided into five levels of very positive, medium, negative, severe negative, etc., and the mental health level value is equal to the emotion analysis result. The step of judging the mental health level according to the emotion analysis result may be implemented such that the server judges whether the emotion analysis result is lower than a first threshold; if below the first threshold, the mental health level is severely negative. If the first threshold is preset to 0.2, the mental health level is severely negative if the sentiment analysis result is 0.1.
The mental health level is judged through the emotion variation and the absolute value of emotion analysis, and the recent health level condition of the user can be comprehensively reflected.
As shown in fig. 6, in a specific implementation process, after the step of sending the warning information to the family terminal according to the mental health level, the method further includes:
s150: and setting a data synchronization frequency according to the mental health level, wherein the data synchronization frequency is the frequency of sending the user content to the server by the user terminal.
Specifically, the server sets a data synchronization frequency according to the mental health level, wherein the data synchronization frequency is a frequency at which the user terminal sends the user content to the server in the current time period
As shown in fig. 7, in an implementation, the step of setting a data synchronization frequency according to the mental health level includes:
s151: setting data synchronization times according to the input frequency and the mental health level of the user content, wherein the data synchronization times are the times of submitting the user content to a server in the time period;
s152: and sending the data synchronization times to the user terminal.
Specifically, the formula of the number of data synchronization times in the time period is
UT=FT×IT
UTThe number of data synchronization times, namely the number of times of submitting the user content to the server in the time period;
ITinputting times for the user in the time period;
FTthe data synchronization frequency is the proportion of the number of times of synchronizing the user content to the server in the current time period and the number of times of inputting the user, and the calculation formula is as follows:
wherein, FT-1The frequency is synchronized for the data of the previous time period.
Specifically, F0 is set to 1, i.e., the terminal synchronizes the input content to the server every time the user inputs it.
When the beta approaches to 1, the more negative the psychology is, the more frequent the data synchronization frequency is, the higher the monitoring strength is, and the problem of the terminal user can be found in time. When beta is less than or equal to 0, the psychology is more positive, the monitoring frequency is reduced, the energy consumption of the mobile phone is reduced, and the consumption of the performance of the mobile phone is reduced.
As shown in fig. 8, in a specific implementation process, after the step of sending the warning information to the family terminal according to the mental health level, the method further includes:
s160: according to the user information and the mental health level, matched family auxiliary nursing knowledge points are inquired from a family auxiliary knowledge base, and the family auxiliary knowledge base stores knowledge points related to family auxiliary nursing assistance;
s170: and sending the family auxiliary nursing knowledge points to the family corresponding to the user.
In a specific implementation process, the step of querying the matched mental health knowledge from the family member auxiliary knowledge base further comprises the following steps:
inquiring the family members corresponding to the user and the relationship between the family members and the user;
and inquiring matched family auxiliary nursing knowledge points from a family auxiliary knowledge base according to the relationship between the family and the user.
In the specific implementation process, the step of inquiring the matched mental health knowledge from the family member auxiliary knowledge base further comprises
Calculating the correlation degree of the knowledge points of the family auxiliary knowledge base and the knowledge of the user;
selecting the previous N knowledge points according to the knowledge correlation degree from big to small;
and sending the knowledge points and the knowledge correlation degrees thereof to a family terminal, and displaying the knowledge points by the family terminal according to the knowledge correlation degrees.
In the specific implementation process, the knowledge correlation degree is related to the age, the sex, the mental health level, the mental disease type and the relationship between the family members and the user of the user. And setting the attributes of the knowledge points in the family auxiliary knowledge base, wherein the attributes comprise the age, the sex, the mental health level, the type of mental diseases and the relationship between the family and the user of the user. And respectively calculating the correlation degrees of the corresponding attributes of the user and the knowledge points, and adding all the attributes, namely the knowledge correlation degrees of the user and the knowledge points. The relevance of the user to the corresponding attributes of the knowledge points can be calculated through semantic similarity.
The knowledge correlation formula is as follows:
n is knowledge point relevance;
Kyiis the weight of the ith attribute;
kc (i) is the ith attribute of a knowledge point;
user (i) is the ith attribute of the user;
yu [ kc (i), user (i) ] refers to the semantic relatedness of kc (i) and user (i).
Through knowledge correlation, the literature closest to the user is found and pushed to the family members, so that the family members can carry out family member auxiliary nursing more scientifically and pertinently.
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides a mental health early warning method which can realize timely tracking and warning through emotion analysis.
Example 2
As shown in fig. 9, according to another aspect of an embodiment of the present invention, there is provided a mental health warning method, including:
s210: detecting an input state or a browsing state of a user terminal;
s220: acquiring the input or browsed content;
s230: and sending the input or browsed content to a server so as to be judged by the server and send out early warning according to the mental health level of the user.
In an exemplary embodiment, the user terminal operating system is an android, and the step of acquiring the input content when the input is completed is specifically implemented as: InputMethodService function: the function is called when the input method is started for the first time and is used for setting initialization; connecting the input method with another client by calling an onBindlnput interface function; calling an InputMethodManager module as an input method manager to manage the interaction of each part; obtaining the current input end through an onFinishnputO function; the endstroy () function is called when the input method is closed.
In a specific implementation process, the step of sending the input or browsed content to the server includes:
receiving a data synchronization frequency;
and transmitting the input content to a server according to the data synchronization frequency.
Specifically, the step of transmitting the inputted or browsed content to the server is implemented as: the user terminal receives data synchronization frequency or data synchronization times sent by the server according to the mental health level; and the user terminal sends the input content to a server according to the data synchronization frequency or the data synchronization times.
Different data synchronization frequencies or data synchronization times are set according to the mental health level, when beta approaches to 1, the more negative the psychology is, the more frequent the data synchronization frequency is, the monitoring strength is increased, and the problem of a terminal user can be found in time. When beta is less than or equal to 0, the psychology is more positive, the monitoring frequency is reduced, the energy consumption of the mobile phone is reduced, and the consumption of the performance of the mobile phone is reduced.
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides a mental health early warning method which can realize timely tracking and warning through emotion analysis.
Example 3
As shown in fig. 10, according to still another aspect of an embodiment of the present invention, there is provided a mental health warning method, including:
s310: receiving early warning information sent by a server according to the mental health level;
s320: and generating an early warning interface according to the early warning information, wherein the early warning interface displays the early warning information through one or more combinations of characters, images, audios or videos.
As shown in fig. 11, in a specific implementation process, the early warning interface includes a first information control, and after the step of generating the early warning interface according to the early warning information, the method further includes:
s330: detecting an event in an early warning interface;
s340: in response to a selection event for the first information control, presenting user detailed information, the user detailed information including a historical mental health level, a current mental health level.
As shown in fig. 12, in a specific implementation process, the early warning interface includes a second information control, and after the step of generating the early warning interface according to the early warning information, the method further includes:
s330: detecting an event in an early warning interface;
s350: in response to a selection event for the second information control, displaying a family assisted care knowledge list, the family assisted care knowledge list displaying family assisted care knowledge points that are appropriate for a current mental health level.
In a specific implementation process, the step of displaying the family assistant nursing knowledge list further comprises the following steps:
detecting events in the family auxiliary nursing knowledge list;
in response to a selection event for a knowledge point in the list of family assisted care knowledge, presenting the corresponding family assisted care knowledge point.
In an exemplary embodiment, the mental health warning method may be implemented as:
the user terminal detects the input state or the browsing state of the user terminal;
the user terminal acquires the input or browsed content; wherein the step of obtaining the input content is implemented as: calling an InputMethodService function when the input method is started for the first time, and setting initialization; connecting with the input method by calling an onBindlnput interface function; calling an InputMethodManager module as an input method manager to manage the interaction of each part; obtaining the current input end through an onFinishnputO function; calling an onDestroy () function when the input method is closed;
the user terminal sends the input or browsed content to the server;
the server receives the content of the user terminal, wherein the content is the content input by the user terminal in the user input method or the content of a webpage currently browsed by a user;
the server analyzes the emotion of the content; wherein, the step of the server performing sentiment analysis on the content comprises the following steps: judging the type of the content, wherein the type comprises a text, a picture or a voice; selecting a corresponding emotion analysis mode according to the type of the content, wherein the emotion analysis mode comprises text analysis, picture analysis and voice analysis; if the type is a text, judging the character type of the content, wherein the character type comprises one or a combination of Chinese, English and other characters; selecting an emotion analysis tool corresponding to the character type to analyze the emotion of the content; counting character types in the content; if the character types comprise two or more than two languages, counting the number of characters corresponding to each character type; calculating the proportion of the number of characters of each character type to the total number of text characters; calculating the emotion analysis result of the content according to the proportion of each character type;
the server judges the mental health level according to the emotion analysis result; the step of judging the mental health level according to the emotion analysis result further comprises the following steps: counting historical emotion analysis results; judging the mental health level according to the difference between the historical emotion analysis result and the current emotion analysis result; the historical emotion analysis result can comprise historical emotion analysis results of different periods;
the server sends early warning information to the family terminal according to the mental health level;
the family terminal receives early warning information sent by the server according to the mental health level;
the family terminal generates an early warning interface according to the early warning information, and the early warning interface displays the early warning information through one or more of characters, images, audios or videos
The server inquires the family corresponding to the user and the relationship between the family and the user according to the user information;
the server inquires matched family auxiliary nursing knowledge points from a family auxiliary knowledge base, wherein the family auxiliary knowledge base stores knowledge points related to auxiliary nursing of the family; wherein the knowledge correlation degree is related to the age, sex, mental health level, mental disease type and relationship between family members and the user of the user; setting attributes of knowledge points in an auxiliary family knowledge base, wherein the attributes comprise the age, the sex, the mental health level, the type of mental diseases and the relationship between the family and the user of the user; respectively calculating the correlation degrees of the corresponding attributes of the user and the knowledge points, and adding all the attributes, namely the knowledge correlation degrees of the user and the knowledge points; the step of searching matched family auxiliary nursing knowledge points from the family auxiliary knowledge base by calculating the correlation degree of the corresponding attributes of the user and the knowledge points through semantic similarity further comprises the following steps of: calculating the correlation degree of the knowledge points of the family auxiliary knowledge base and the knowledge of the user; selecting the previous N knowledge points according to the knowledge correlation degree from big to small; sending the knowledge points and the knowledge correlation degrees thereof to a family terminal, and displaying the knowledge points by the family terminal according to the knowledge correlation degrees;
the server sends the family auxiliary nursing knowledge points to the family corresponding to the user;
detecting an event in an early warning interface by a family terminal, wherein the early warning interface comprises a first information control;
the family terminal responds to a selection event aiming at the first information control and displays user detailed information, wherein the user detailed information comprises historical mental health level and current mental health level;
the early warning interface further comprises a second information control, the family terminal responds to a selection event aiming at the second information control and displays a family auxiliary nursing knowledge list, and the family auxiliary nursing knowledge list displays family auxiliary nursing knowledge points adaptive to the current mental health level;
detecting an event in the family auxiliary nursing knowledge list by the family terminal;
the family terminal responds to the selection event aiming at the knowledge points in the family auxiliary nursing knowledge list and displays the corresponding family auxiliary nursing knowledge points
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides a mental health early warning method which can realize timely tracking and warning through emotion analysis.
Example 4
As shown in fig. 13, according to an aspect of an embodiment of the present invention, there is provided a mental health warning server 100, the server 100 including:
the receiving module 101 is configured to receive content of a user terminal, where the content is content input by a user input method collected by the user terminal or content of a webpage currently browsed by a user;
an analysis module 102, configured to perform emotion analysis on the content;
the judging module 103 is used for judging the mental health level according to the emotion analysis result;
and the early warning module 104 is used for sending early warning information to the family terminal according to the mental health level.
In a specific implementation process, a server receives content of a user terminal sent by the user terminal, wherein the content is content which is acquired by the user terminal and input by a user in an input method or browsed in a browser; the server analyzes the emotion of the content; the server judges the mental health level according to the emotion analysis result; and the server sends early warning information to the family terminal according to the mental health level.
The method comprises the steps of actively acquiring the content input by a user in a user terminal held by the user or the mode of browsing the content, carrying out emotion analysis on the content, judging the mental health level of the user according to the emotion analysis result, and tracking the mental health level of the user in real time under the condition that the user does not need to go to a hospital for inquiry.
Due to the adoption of the mode of actively analyzing the input content or browsing the content of the user, the problem that the psychological medical resources are in short supply because the psychological state of the user can be known only by one-to-one manual inquiry in the prior art is solved, and thus, a psychologist can serve a plurality of places.
The server sends early warning information to the family terminals held by the families according to the mental health level, so that the families can perform psychological monitoring and intervention on the user in time, and the negative emotion of the user can be relieved.
In a specific implementation process, the server 100 further includes:
the judging module 103 is further configured to judge a type of the content, where the type includes a text, a picture, or a voice;
and the selecting module 105 is configured to select a corresponding emotion analysis mode according to the type of the content, where the emotion analysis mode includes text analysis, picture analysis, and voice analysis.
Specifically, the server judges the type of the content, wherein the type comprises a text, a picture or a voice; and the server selects a corresponding emotion analysis mode according to the type of the content, wherein the emotion analysis mode comprises text analysis, picture analysis and voice analysis.
Some users prefer to input voice or pictures, and select a corresponding emotion analysis mode according to the type of the content, so that emotion analysis can be performed when the users input rich media content, such as pictures, voice and other content.
In a specific implementation process, the server further includes:
the analysis module 102 is further configured to analyze the emotion of the content if the content is a text.
In a specific implementation process, the server 100 further includes:
the judging module 103 is further configured to judge a character type of the content, where the character type includes one or a combination of more than one of chinese, english, and other characters;
the selecting module 105 is further configured to select an emotion analysis tool corresponding to the character type to analyze the emotion of the content.
And selecting a corresponding emotion analysis tool by judging the character type, so that the method can be applied to the use in various language environments.
In a specific implementation process, the server 100 further includes:
a statistic module 106, configured to count character types in the content;
the counting module 106 is further configured to count the number of characters corresponding to each character type if the character type includes two or more languages;
a calculating module 107, configured to calculate a ratio of the number of characters of each character type to the total number of text characters;
the calculating module 107 is further configured to calculate an emotion analysis result of the content according to the percentage of each character type.
Specifically, the step of selecting an emotion analysis tool corresponding to the character type to analyze the emotion of the content includes: the server counts character types in the content; if the character types contain two or more languages, the server counts the number of characters corresponding to each character type; the server calculates the proportion of the number of characters of each character type to the total number of text characters; and the server calculates the emotion analysis result of the content according to the proportion of each character type.
In practical circumstances, some users prefer to express the same sentence in multiple languages, such as a hybrid Chinese-English sentence. And calculating the emotion analysis result of the content according to the proportion of each character type, so that the emotion analysis problem that a plurality of languages are mixed in the same sentence can be effectively solved.
In a specific implementation process, the emotion analysis result formula for calculating the content is as follows:
wherein, PLiThe emotion analysis result is the ith character;
KLithe ratio of the number of the ith characters to the total number of the text characters
And P is the emotion analysis result of the content.
Specifically, P is a number between 0 and 1, and is more positive as approaching 1 and more negative as approaching 0.
In a specific implementation process, the server 100 further includes:
the statistic module 106 is further configured to count a historical emotion analysis result;
the judging module 103 is further configured to judge the mental health level according to a difference between the historical emotion analysis result and the current emotion analysis result.
In particular, the historical sentiment analysis results may include historical sentiment analysis results for different periods, such as a previous day, a previous week, a previous month, a previous quarter, a previous year, or historical sentiment analysis results since use.
In a specific implementation process, the server 100 includes:
the mental health level calculation formula is as follows:
wherein, beta is a mental health level value;
and the current emotion analysis result is the average value of the last m emotion analysis results.
Specifically, the average value of the historical emotion analysis results is compared with the current emotion analysis results, so that the change of the emotion value variation can be monitored. When the change in the beta emotion value is large and positive, the larger beta, the worse the mental health level, and the more negative the mental state. When beta is negative, the mental health level is high, and the mental state is more positive than the historical emotion. As β approaches 0, it indicates less psychological fluctuation.
In a specific implementation process, the mental health level calculation formula is as follows:
wherein, beta is a mental health level value;
and the current emotion analysis result is the average value of the last m emotion analysis results.
specifically, the closer to the period of the current time, the larger the time correlation coefficient. The sum of the time correlation coefficients is 1. In a specific embodiment, the ith cycle time correlation coefficient may be set as:
the 1 st period is the previous day, the time correlation coefficient K of the previous dayβ1=0.4;
The 2 nd period is the previous week, the time correlation coefficient K of the previous weekβ2=0.3;
The 3 rd period is the previous month, the time correlation coefficient K of the previous monthβ3=0.15;
The 4 th period is the previous season, and the time correlation coefficient K of the previous seasonβ4=0.10;
The 5 th cycle is the previous year and the time correlation coefficient K of the previous yearβ5=0.05。
Specifically, the longer the historical emotion analysis result is from the current time, the smaller the reference degree of the difference value of the current emotion analysis result is. And a time correlation coefficient is added, so that the mental health level value can reflect the difference value of mental change. When the change in the beta emotion value is large and positive, the larger beta, the worse the mental health level, and the more negative the mental state. When beta is negative, the mental health level is high, and the mental state is more positive than the historical emotion. As β approaches 0, it indicates less psychological fluctuation.
In one exemplary embodiment, the mental health level can be divided into five levels of very positive, medium, negative, severe negative, etc., and the mental health level value is equal to the emotion analysis result. The step of judging the mental health level according to the emotion analysis result may be implemented such that the server judges whether the emotion analysis result is lower than a first threshold; if below the first threshold, the mental health level is severely negative. If the first threshold is preset to 0.2, the mental health level is severely negative if the sentiment analysis result is 0.1.
In a specific implementation process, the server 100 further includes:
a setting module 108, configured to set a data synchronization frequency according to the mental health level, where the data synchronization frequency is a frequency at which the user terminal sends the user content to the server.
Specifically, the server sets a data synchronization frequency according to the mental health level, wherein the data synchronization frequency is a frequency at which the user terminal sends the user content to the server in the current time period
In a specific implementation process, the step of setting a data synchronization frequency according to the mental health level comprises:
the setting module 108 is further configured to set data synchronization times according to the input frequency of the user content and the mental health level, where the data synchronization times are times of submitting the user content to the server in the current time period;
a first sending module 109, configured to send the data synchronization times to the user terminal.
Specifically, the formula of the number of data synchronization times in the time period is
UT=FT×IT
UTFor the number of data synchronizations, i.e. the present timeThe number of times the user content is submitted to the server within the segment;
ITinputting times for the user in the time period;
FTthe data synchronization frequency is the proportion of the number of times of synchronizing the user content to the server in the current time period and the number of times of inputting the user, and the calculation formula is as follows:
wherein, FT-1The frequency is synchronized for the data of the previous time period.
Specifically, F0 is set to 1, i.e., the terminal synchronizes the input content to the server every time the user inputs it.
When the beta approaches to 1, the more negative the psychology is, the more frequent the data synchronization frequency is, the higher the monitoring strength is, and the problem of the terminal user can be found in time. When beta is less than or equal to 0, the psychology is more positive, the monitoring frequency is reduced, the energy consumption of the mobile phone is reduced, and the consumption of the performance of the mobile phone is reduced.
In a specific implementation process, the server 100 further includes:
the query module 110 is configured to query matched family auxiliary nursing knowledge points from a family auxiliary knowledge base according to the user information and the mental health level, where the family auxiliary knowledge base stores knowledge points related to family auxiliary nursing assistance;
the first sending module 109 is further configured to send the family-assisted care knowledge point to the family corresponding to the user.
In a specific implementation process, the server 100 further includes:
the query module 110 is further configured to query the family members corresponding to the user and the relationship between the family members and the user;
the query module 110 is further configured to query the matched family auxiliary care knowledge points from the family auxiliary knowledge base according to the relationship between the family and the user.
In a specific implementation process, the server 100 further includes:
the calculating module 107 is further configured to calculate a knowledge correlation between the knowledge point of the family auxiliary knowledge base and the knowledge of the user;
the selection module 105 is further configured to select the previous N knowledge points according to the knowledge correlation degree from large to small;
the first sending module 109 is further configured to send the knowledge point and the knowledge correlation thereof to a family terminal, so that the family terminal displays the knowledge point according to the knowledge correlation.
In the specific implementation process, the knowledge correlation degree is related to the age, the sex, the mental health level, the mental disease type and the relationship between the family members and the user of the user. And setting the attributes of the knowledge points in the family auxiliary knowledge base, wherein the attributes comprise the age, the sex, the mental health level, the type of mental diseases and the relationship between the family and the user of the user. And respectively calculating the correlation degrees of the corresponding attributes of the user and the knowledge points, and adding all the attributes, namely the knowledge correlation degrees of the user and the knowledge points. The relevance of the user to the corresponding attributes of the knowledge points can be calculated through semantic similarity.
The knowledge correlation formula is as follows:
n is knowledge point relevance;
Kyiis the weight of the ith attribute;
kc (i) is the ith attribute of a knowledge point;
user (i) is the ith attribute of the user;
yu [ kc (i), user (i) ] refers to the semantic relatedness of kc (i) and user (i).
Through knowledge correlation, the literature closest to the user is found and pushed to the family members, so that the family members can carry out family member auxiliary nursing more scientifically and pertinently.
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides a mental health early warning method which can realize timely tracking and warning through emotion analysis.
Example 5
As shown in fig. 14, according to another aspect of the embodiment of the present invention, there is provided a mental health warning user terminal 200, where the user terminal 200 includes:
a second detecting module 201, configured to detect an input state or a browsing state of the user terminal;
a second obtaining module 202, configured to obtain the input or browsed content;
and the second sending module 203 is used for sending the input or browsed content to the server so as to be judged by the server and send out early warning according to the mental health level of the user.
In an exemplary embodiment, the user terminal operating system is an android, and the step of acquiring the input content when the input is completed is specifically implemented as: InputMethodService function: the function is called when the input method is started for the first time and is used for setting initialization; connecting the input method with another client by calling an onBindlnput interface function; calling an InputMethodManager module as an input method manager to manage the interaction of each part; obtaining the current input end through an onFinishnputO function; the endstroy () function is called when the input method is closed.
In a specific implementation process, the user terminal 200 further includes:
a second receiving module 204, configured to receive a data synchronization frequency;
the second sending module 203 is further configured to send the input content to a server according to the data synchronization frequency.
Specifically, the step of transmitting the inputted or browsed content to the server is implemented as: the user terminal receives data synchronization frequency or data synchronization times sent by the server according to the mental health level; and the user terminal sends the input content to a server according to the data synchronization frequency or the data synchronization times.
Different data synchronization frequencies or data synchronization times are set according to the mental health level, when beta approaches to 1, the more negative the psychology is, the more frequent the data synchronization frequency is, the monitoring strength is increased, and the problem of a terminal user can be found in time. When beta is less than or equal to 0, the psychology is more positive, the monitoring frequency is reduced, the energy consumption of the mobile phone is reduced, and the consumption of the performance of the mobile phone is reduced.
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides a mental health early warning user terminal which can realize timely tracking and warning through emotion analysis.
Example 6
As shown in fig. 15, according to still another aspect of an embodiment of the present invention, there is provided a mental health early warning family terminal 300, the family terminal 300 including:
a third receiving module 301, configured to receive warning information sent by the server according to the mental health level;
a generating module 302, configured to generate an early warning interface according to the early warning information, where the early warning interface displays the early warning information through one or more combinations of characters, images, audios, and videos.
In a specific implementation process, the family terminal 300 further includes:
a third detecting module 303, configured to detect an event in the early warning interface;
a presentation module 304 for presenting user details including historical mental health levels, current mental health levels in response to a selection event for the first information control.
In a specific implementation process, the family terminal 300 further includes:
the display module 304 is further configured to display a family-assisted nursing knowledge list in response to a selection event for the second information control, where the family-assisted nursing knowledge list displays family-assisted nursing knowledge points that are adapted to the current mental health level.
In a specific implementation process, the family terminal 300 further includes:
the third detecting module 303 is further configured to detect an event in the family-assisted care knowledge list;
the display module 304 is further configured to display the corresponding family member assistant nursing knowledge points in response to a selection event for the knowledge points in the family member assistant nursing knowledge list.
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides the mental health early warning family terminal which can realize timely tracking and warning through emotion analysis.
Example 7
As shown in fig. 16, according to still another aspect of an embodiment of the present invention, there is provided a mental health early warning system, which includes a mental health early warning server 100, a user terminal 200, and a family terminal 300. The user terminal 200 is communicatively connected to the server 100. The family terminal 300 is communicatively connected to the server 100.
The server 100 includes a memory and a processor coupled to the memory, the processor being configured to execute the mental health warning method according to embodiment 1 of the present disclosure based on instructions stored in the memory. The memory may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), a database, and other programs.
The user terminal 200 includes a memory and a processor coupled to the memory, and the processor is configured to execute the mental health warning method according to embodiment 2 of the present disclosure based on instructions stored in the memory. The memory may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), a database, and other programs.
The family terminal 300 includes a memory and a processor coupled to the memory, and the processor is configured to execute the mental health warning method according to embodiment 3 of the present disclosure based on instructions stored in the memory. The memory may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), a database, and other programs.
The invention solves the problem that the mental health state cannot be tracked in time in the prior art, and provides a mental health early warning system which can realize timely tracking and warning through emotion analysis.
The present disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the mental health warning method of any of the preceding embodiments.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
So far, the mental health early warning method, the server, the family member terminal and the system according to the present disclosure have been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A mental health warning method, comprising:
receiving the content of the user terminal;
performing sentiment analysis on the content;
judging the mental health level according to the emotion analysis result;
sending early warning information to the family terminal according to the mental health level;
if the content is a text, the algorithm for analyzing the emotion of the content comprises a training unit and an analyzing unit; the implementation of the training unit is: using the development set; training the training set in the machine learning classification algorithm to obtain a machine learning model classifier; classifying the development set by using a machine learning model classifier, and finally obtaining a text classification result; manually intervening by utilizing a corpus to label data of the text, and giving the accurate accuracy of the machine learning classifier; obtaining an algorithm and a characteristic dimension; obtaining a test set, and testing the established machine learning; the analysis unit is implemented as: calling a trained Bayes model; saving the final model; loading a final Bayes model; word segmentation and word stop operation; reading in active text and passive text; calling a Bayes model training method; calling a handle method in the sentent class; calling a classfy method in a Bayes class;
the step of sending early warning information to the family terminal according to the mental health level further comprises the following steps:
setting a data synchronization frequency according to the mental health level, wherein the data synchronization frequency is the frequency of the user terminal for sending the user content to a server;
the step of setting a data synchronization frequency according to the mental health level comprises:
setting data synchronization times according to the input frequency and the mental health level of the user content, wherein the data synchronization times are the times of submitting the user content to a server in the time period;
sending the data synchronization times to the user terminal;
wherein, the formula of the data synchronization times in the time period is
UT=FT×IT
UTThe number of data synchronization times, namely the number of times of submitting the user content to the server in the time period;
ITinputting times for the user in the time period;
FTthe data synchronization frequency is the proportion of the number of times of synchronizing the user content to the server in the current time period and the number of times of inputting the user, and the calculation formula is as follows:
FT=1,(1+β)×FT-1≥1
FT=(1+β)×FT-1,1>(1+β)×FT-1;
FT=0,(1+β)×FT-1≤0
wherein, FT-1Synchronizing frequency for data in the previous time period;
wherein, beta is a mental health level value;
2. The mental health warning method of claim 1, further comprising, after the step of sending warning information according to the mental health level:
according to the user information and the mental health level, matched family auxiliary nursing knowledge points are inquired from a family auxiliary knowledge base, and the family auxiliary knowledge base stores knowledge points related to family auxiliary nursing assistance;
and sending the family auxiliary nursing knowledge points to the family corresponding to the user.
3. The mental health warning method of claim 2, wherein the step of querying the matched mental health knowledge from the family member auxiliary knowledge base further comprises:
inquiring the family members corresponding to the user and the relationship between the family members and the user;
inquiring matched family auxiliary nursing knowledge points from a family auxiliary knowledge base according to the relationship between the family and the user;
wherein, the step of inquiring the matched mental health knowledge from the family auxiliary knowledge base further comprises the following steps:
calculating the correlation degree of the knowledge points of the family auxiliary knowledge base and the knowledge of the user;
selecting the previous N knowledge points according to the knowledge correlation degree from big to small;
sending the knowledge points and the knowledge correlation degrees thereof to a family terminal, and displaying the knowledge points by the family terminal according to the knowledge correlation degrees;
the knowledge correlation formula is as follows:
n is knowledge point relevance;
Kyiis the weight of the ith attribute;
kc (i) is the ith attribute of a knowledge point;
user (i) is the ith attribute of the user;
yu [ kc (i), user (i) ] refers to the semantic relatedness of kc (i) and user (i).
4. The mental health warning method of claim 3, wherein the method comprises:
receiving early warning information sent by a server according to the mental health level;
and generating an early warning interface according to the early warning information, wherein the early warning interface displays the early warning information through one or more combinations of characters, images, audios or videos.
5. The mental health warning method of claim 4, wherein the warning interface includes a first information control, and the step of generating the warning interface according to the warning information further comprises:
detecting an event in an early warning interface;
in response to a selection event for the first information control, presenting user detailed information, the user detailed information including a historical mental health level, a current mental health level.
6. The mental health warning method of claim 5, wherein the warning interface includes a first information control, and the step of generating the warning interface according to the warning information further comprises:
detecting an event in an early warning interface;
and in response to a selection event for the second information control, displaying a family auxiliary nursing knowledge list, wherein the family auxiliary nursing knowledge list displays family auxiliary nursing knowledge points adaptive to the current mental health level.
7. A mental health warning server, the server further comprising:
the receiving module is used for receiving the content of the user terminal, wherein the content is the content input by the user terminal in the user input method or the content of a webpage currently browsed by a user;
the analysis module is used for carrying out emotion analysis on the content;
the judging module is used for judging the mental health level according to the emotion analysis result;
the early warning module is used for sending early warning information to the family terminal according to the mental health level;
if the content is a text, the algorithm for analyzing the emotion of the content comprises a training unit and an analyzing unit; the implementation of the training unit is: using the development set; training the training set in the machine learning classification algorithm to obtain a machine learning model classifier; classifying the development set by using a machine learning model classifier, and finally obtaining a text classification result; manually intervening by utilizing a corpus to label data of the text, and giving the accurate accuracy of the machine learning classifier; obtaining an algorithm and a characteristic dimension; obtaining a test set, and testing the established machine learning; the analysis unit is implemented as: calling a trained Bayes model; saving the final model; loading a final Bayes model; word segmentation and word stop operation; reading in active text and passive text; calling a Bayes model training method; calling a handle method in the sentent class; calling a classfy method in a Bayes class;
the setting module is used for setting data synchronization frequency according to the mental health level, wherein the data synchronization frequency is the frequency of the user terminal for sending the user content to a server;
the server further comprises:
the setting module is further used for setting data synchronization times according to the input frequency and the mental health level of the user content, wherein the data synchronization times are the times of submitting the user content to the server in the time period;
a first sending module, configured to send the data synchronization times to the user terminal;
the formula of the data synchronization times in the time period is as follows:
UT=FT×IT
UTthe number of data synchronization times, namely the number of times of submitting the user content to the server in the time period;
ITinputting times for the user in the time period;
FTthe data synchronization frequency is the proportion of the number of times of synchronizing the user content to the server in the current time period and the number of times of inputting the user, and the calculation formula is as follows:
FT=1,(1+β)×FT-1≥1
FT=(1+β)×FT-1,1>(1+β)×FT-1
FT=0,(1+β)×FT-1≤0;
wherein, FT-1Synchronizing frequency for data in the previous time period;
wherein, beta is a mental health level value;
8. The utility model provides a mental health early warning family member terminal which characterized in that, family member terminal includes:
a third receiving module, configured to receive warning information sent by the server according to the mental health level according to claim 7;
and the generation module is used for generating an early warning interface according to the early warning information, and the early warning interface displays the early warning information through one or more combinations of characters, images, audios or videos.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the mental health warning method according to one of claims 1 to 6.
10. A mental health warning system, the system comprising:
a user terminal, a family terminal according to claim 8, a server according to claim 7; the user terminal is in communication connection with the server; the family terminal is in communication connection with the server;
wherein the user terminal comprises: the second detection module is used for detecting the input state or the browsing state of the user terminal; the second acquisition module is used for acquiring the input or browsed content; and the second sending module is used for sending the input or browsed content to the server so as to be judged by the server and send out early warning according to the mental health level of the user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910229694.9A CN109979568B (en) | 2019-03-25 | 2019-03-25 | Mental health early warning method, server, family member terminal and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910229694.9A CN109979568B (en) | 2019-03-25 | 2019-03-25 | Mental health early warning method, server, family member terminal and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109979568A CN109979568A (en) | 2019-07-05 |
CN109979568B true CN109979568B (en) | 2021-08-24 |
Family
ID=67080459
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910229694.9A Expired - Fee Related CN109979568B (en) | 2019-03-25 | 2019-03-25 | Mental health early warning method, server, family member terminal and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109979568B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110600104A (en) * | 2019-08-30 | 2019-12-20 | 深圳智慧林网络科技有限公司 | Mental health correction plan generation method and device and readable storage medium thereof |
CN111370113A (en) * | 2020-03-03 | 2020-07-03 | 淮安信息职业技术学院 | Remote psychological counseling system and method based on Internet of things cloud |
CN113055746B (en) * | 2021-04-19 | 2022-09-30 | 广州欢网科技有限责任公司 | Old people monitoring method, device, server and system based on television watching behaviors |
CN115631772A (en) * | 2022-10-27 | 2023-01-20 | 四川大学华西医院 | Method and device for evaluating risk of suicide injury, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009110490A (en) * | 2007-10-31 | 2009-05-21 | Think Project:Kk | System for diagnosing and managing mental health of family members using internet |
CN106570327A (en) * | 2016-11-04 | 2017-04-19 | 奚红娟 | Condition management system for babies with eczema |
CN106708805A (en) * | 2016-12-30 | 2017-05-24 | 深圳天珑无线科技有限公司 | Text statistics-based psychoanalysis method and device |
CN108937972A (en) * | 2018-06-08 | 2018-12-07 | 青岛大学附属医院 | A kind of medical user emotion monitoring method of multiple features fusion |
-
2019
- 2019-03-25 CN CN201910229694.9A patent/CN109979568B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009110490A (en) * | 2007-10-31 | 2009-05-21 | Think Project:Kk | System for diagnosing and managing mental health of family members using internet |
CN106570327A (en) * | 2016-11-04 | 2017-04-19 | 奚红娟 | Condition management system for babies with eczema |
CN106708805A (en) * | 2016-12-30 | 2017-05-24 | 深圳天珑无线科技有限公司 | Text statistics-based psychoanalysis method and device |
CN108937972A (en) * | 2018-06-08 | 2018-12-07 | 青岛大学附属医院 | A kind of medical user emotion monitoring method of multiple features fusion |
Also Published As
Publication number | Publication date |
---|---|
CN109979568A (en) | 2019-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yazdavar et al. | Semi-supervised approach to monitoring clinical depressive symptoms in social media | |
US12001964B2 (en) | Artificial intelligence advisory systems and methods for behavioral pattern matching and language generation | |
US9146987B2 (en) | Clustering based question set generation for training and testing of a question and answer system | |
CN109979568B (en) | Mental health early warning method, server, family member terminal and system | |
US9275115B2 (en) | Correlating corpus/corpora value from answered questions | |
US9336485B2 (en) | Determining answers in a question/answer system when answer is not contained in corpus | |
US9230009B2 (en) | Routing of questions to appropriately trained question and answer system pipelines using clustering | |
US9621601B2 (en) | User collaboration for answer generation in question and answer system | |
EP3895178A1 (en) | System and method for providing health information | |
US20150161230A1 (en) | Generating an Answer from Multiple Pipelines Using Clustering | |
US20210035661A1 (en) | Methods and systems for relating user inputs to antidote labels using artificial intelligence | |
Carberry et al. | Access to multimodal articles for individuals with sight impairments | |
CN108363699A (en) | A kind of netizen's school work mood analysis method based on Baidu's mhkc | |
CN117390145A (en) | Automatic text dialogue method, device, equipment and medium for clinical test | |
CN109979592A (en) | Mental health method for early warning, user terminal, server and system | |
CN116453674A (en) | Intelligent medical system | |
US20140012853A1 (en) | Search device, search method, search program, and computer-readable memory medium for recording search program | |
CN109994207B (en) | Mental health early warning method, server and system | |
Zafari et al. | Chatsum: an intelligent medical chat summarization tool | |
EP3901875A1 (en) | Topic modelling of short medical inquiries | |
CN114201613B (en) | Test question generation method, test question generation device, electronic device, and storage medium | |
Narimatsu et al. | Collision Probability Matching Loss for Disentangling Epistemic Uncertainty from Aleatoric Uncertainty | |
Taj et al. | Leveraging Natural Language Processing for In-Depth Analysis and Insights from Hospital Patient Feedback Data | |
CN111512395A (en) | Learning and applying background similarity between entities | |
US20240242732A1 (en) | System and method for determining a users emotions and increasing the users emotional intelligence and self-awareness utilizing the users voice samples |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210824 |