CN113495909A - Customer complaint single quantity early warning method and device, electronic equipment and storage medium - Google Patents
Customer complaint single quantity early warning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113495909A CN113495909A CN202010262313.XA CN202010262313A CN113495909A CN 113495909 A CN113495909 A CN 113495909A CN 202010262313 A CN202010262313 A CN 202010262313A CN 113495909 A CN113495909 A CN 113495909A
- Authority
- CN
- China
- Prior art keywords
- customer complaint
- early warning
- data
- historical
- complaint event
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Fuzzy Systems (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a customer complaint single quantity early warning method and device, electronic equipment and a storage medium, and relates to the technical field of information processing. The method comprises the steps of obtaining historical single quantity data of a customer complaint event, cleaning abnormal data in the historical single quantity data, carrying out resetting random sampling on the cleaned historical single quantity data to obtain a new single quantity data set of the customer complaint event, obtaining current single quantity data of the customer complaint event, and judging whether the historical single quantity data of the customer complaint event conforms to normal distribution or not, so that the calculation mode of the early warning probability of the current single quantity data of the customer complaint event in the new single quantity data set of the customer complaint event is determined; and calculating corresponding early warning probability according to the determined calculation mode, displaying the early warning probability in a thermodynamic diagram form through conversion, and accurately early warning the current single data of the customer complaint event, so that customer complaint handling work can be reasonably arranged by customer service personnel, and the customer complaint service satisfaction degree is improved.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a customer complaint single quantity early warning method and device, electronic equipment and a storage medium.
Background
At present, with the demand of people for service quality becoming higher and higher, in order to improve the service satisfaction of users, service providers generally record the feedback of users to customer service staff by a customer complaint system and record customer complaints events in the form of work orders.
In the prior art, there are two technical schemes: one technical scheme is that the customer complaint event single quantity at the current moment is compared with the customer complaint event single quantity at the historical moment, and an alarm is given when a certain threshold value is exceeded. The other technical scheme is that whether early warning is needed or not is judged according to a 3sigma criterion of the event single quantity at the current moment.
However, the early warning threshold value is determined empirically by the first technical solution, false judgments such as false alarm and false negative alarm are easily generated, and the premise of the second technical solution is to comply with normal distribution, and the standard deviation σ of the judgment criterion is also fixed, so that reasonable early warning cannot be accurately given.
Disclosure of Invention
The invention provides a method and a device for early warning the single customer complaint amount, electronic equipment and a storage medium, which can accurately early warn the current single customer complaint amount of the event, thereby facilitating the customer service staff to reasonably arrange the customer complaint handling work and further improving the satisfaction degree of the customer complaint service.
In a first aspect, an embodiment of the present invention provides a customer complaint single quantity early warning method, where the method includes:
acquiring historical single data of a customer complaint event, and cleaning abnormal data in the historical single data;
carrying out resetting random sampling on the washed historical single data to obtain a new single data set of the customer complaint event;
determining the early warning probability of the current single data of the customer complaint event in a new single data set of the customer complaint event according to the type of the historical single data of the customer complaint event;
and carrying out early warning prompt through thermodynamic diagrams according to the early warning probability.
Optionally, the step of determining the early warning probability of the current single volume data of the customer complaint event in the new single volume data set of the customer complaint event according to the type of the historical single volume data of the customer complaint event may specifically include:
judging whether the historical single data accords with normal distribution;
if the historical single data accords with normal distribution, acquiring the mean value and the standard deviation of a new data set of the customer complaint event, and normally standardizing the current single data of the customer complaint event based on the mean value and the standard deviation to obtain standardized single data;
and calculating the early warning probability of the normalized single data in a new single data set of the customer complaint event according to a preset normal integral function.
Optionally, after determining whether the historical single amount data conforms to the normal distribution, the customer complaint single amount early warning method further includes:
and if the historical single data does not accord with normal distribution, acquiring the data proportion of a new data set smaller than the current single data, and determining the early warning probability of the current single data of the customer complaint event in the historical single data.
Optionally, the performing an early warning prompt through thermodynamic diagrams according to the early warning probability includes:
calculating the early warning probability according to a preset thermodynamic conversion function to obtain a thermodynamic display value corresponding to the early warning probability;
and acquiring a corresponding early warning color according to the thermal display value to perform early warning prompt.
In a second aspect, an embodiment of the present invention provides a customer complaint single-quantity warning device, where the device includes:
and the cleaning module is used for acquiring historical single-quantity data of the customer complaint event and cleaning abnormal data in the historical single-quantity data.
And the resampling module is used for carrying out resetting random sampling on the washed historical single data to obtain a new single data set of the customer complaint event.
And the processing module is used for determining the early warning probability of the current single data of the customer complaint event in the new single data set of the customer complaint event according to the type of the historical single data of the customer complaint event.
And the early warning module is used for carrying out early warning prompt through thermodynamic diagrams according to the early warning probability.
Optionally, the processing module comprises:
the judging module is used for judging whether the historical single data accords with normal distribution;
the first calculation module is used for acquiring the mean value and the standard deviation of a new data set of the customer complaint event if the historical single data accords with the normal distribution, and carrying out normal standardization on the current single data of the customer complaint event based on the mean value and the standard deviation to obtain the standardized single data;
and calculating the early warning probability of the standardized new single data set of the customer complaint event according to a preset normal integral function.
Optionally, the processing module further comprises:
and the second calculation module is used for acquiring the data proportion of a new data set smaller than the current single data set if the historical single data is not in accordance with normal distribution, and determining the early warning probability of the current single data of the customer complaint event in the historical single data.
Optionally, the early warning module comprises:
the conversion module is used for calculating the early warning probability according to a preset thermodynamic conversion function to obtain a corresponding thermodynamic display value;
and the prompt module is used for acquiring the corresponding early warning color according to the thermal display value to perform early warning prompt.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the customer complaint single-quantity early warning method comprises a processor, a storage medium and a bus, wherein the storage medium stores machine readable instructions executable by the processor, when the electronic device runs, the processor and the storage medium are communicated through the bus, and the processor executes the machine readable instructions to execute the customer complaint single-quantity early warning method according to the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a storage medium, where the storage medium stores a computer program, and the computer program is executed by a processor to perform the customer complaint order early warning method according to the first aspect.
The invention has the beneficial effects that:
the method comprises the steps of obtaining historical single quantity data of a customer complaint event, cleaning abnormal data in the historical single quantity data, carrying out resetting random sampling on the cleaned historical single quantity data to obtain a new single quantity data set of the customer complaint event, obtaining current single quantity data of the customer complaint event, and judging whether the historical single quantity data of the customer complaint event conforms to normal distribution or not, so that the calculation mode of the early warning probability of the current single quantity data of the customer complaint event in the new single quantity data set of the customer complaint event is determined; and calculating corresponding early warning probability according to the determined calculation mode, displaying the early warning probability in a thermodynamic diagram form through conversion, and accurately early warning the current single data of the customer complaint event, so that customer complaint handling work can be reasonably arranged by customer service personnel, and the customer complaint service satisfaction degree is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flow chart of a customer complaint single-quantity early warning method provided by an embodiment of the invention;
FIG. 2 is a schematic flow chart illustrating a customer complaint single-quantity warning method according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a customer complaint single-quantity warning method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a thermodynamic conversion function of a customer complaint single-quantity early warning method provided by an embodiment of the invention;
FIG. 5 is a schematic flow chart illustrating a customer complaint single-quantity warning method according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a customer complaint single-quantity early warning device provided by an embodiment of the invention;
FIG. 7 is a schematic structural diagram of a customer complaint single-quantity warning device provided in the embodiment of the present invention;
FIG. 8 is a schematic structural diagram of a customer complaint single-quantity warning device provided in the embodiment of the present invention;
FIG. 9 is a schematic structural diagram of a customer complaint single-quantity warning device provided by an embodiment of the invention;
fig. 10 shows a schematic structural diagram of a customer complaint single-quantity early warning device provided by an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The embodiment of the invention provides a customer complaint single quantity early warning method which can be applied to a customer complaint system, and can accurately give out reasonable early warning prompts, improve the handling efficiency of customer complaints and improve the service experience of users by early warning the customer complaint single quantity through the customer complaint single quantity early warning method. The execution subject of the method may be a server or a computer of the customer complaint system, or may also be one or more processors in the server or the computer, and the invention is not limited thereto.
Fig. 1 shows a flow chart of a customer complaint single quantity early warning method provided by an embodiment of the invention.
As shown in fig. 1, the customer complaint single-amount early warning method may include:
s101, obtaining historical single-quantity data of the customer complaint event, and cleaning abnormal data in the historical single-quantity data.
The customer service system can obtain single data of the customer complaint events in a historical period of time, such as: the customer complaint event single data can comprise statistical time, name of customer service center and customer complaint single quantity; the specific data pattern is shown in table 1 below:
TABLE 1 customer complaint event single quantity data sheet
If there may be some abnormal data in the historical single amount of data, the historical single amount of data needs to be cleaned to remove the abnormal data, for example, a Box diagram Box-plot may be taken, which may be specifically processed by the following formula (1):
{ Q1-1.5 (Q3-Q1), Q3+1.5 (Q3-Q1) } formula (1)
Wherein, quantiles of Q1 and Q3: arranging the historical single quantity data from small to large, wherein the historical single quantity data at the position of 25% is a quantile Q1; the historical single-quantity data at the 75% position is Q3 quantile, 1.5 is a cleaning coefficient, and the cleaned historical single-quantity data can be obtained after the processing of the formula (1). The customer complaint event is a work document generated by the customer service system for the received customer service appeal, for example: the customer complaint list, the customer demand list, and the like may be specifically configured according to actual conditions, but are not limited thereto.
Related abnormal values are eliminated through the quantiles, so that data (for example, holidays) at some special time points are avoided being directly eliminated.
It should be noted that, when processing an abnormal value, besides the above quantile, a method such as a 3sigma principle may be used, but when testing 3sigma, it is found that the 3sigma method is likely to receive interference of abnormal data, and affects variance, thereby affecting the quality of removing the abnormal value.
And S102, carrying out resetting random sampling on the washed historical single data to obtain a new single data set of the customer complaint event.
Alternatively, it is assumed that after the first step of data outlier cleaning processing, the single amount of historical data of the customer service center a customer complaint event is (n) { n1, n2, n3, … …, n100}, 100 pieces of data. Because the data volume is small, the real distribution of the parent is difficult to reflect really, which causes difficulty for subsequent analysis, 1000 times of bootstrap boot-pulling method sampling can be carried out on the historical single-volume data to obtain a new single-volume data set of the customer complaint event, so that the finally obtained data can reflect the distribution of the parent per se. The specific method comprises the following steps: randomly extracting 100 pieces of data from the historical single data (N) to obtain a data set N1, and then continuing the same processing mode to obtain a data set N2. By analogy, 1000 times of extraction are carried out, and 1000 data sets { N1, N2, N3, … …, N1000} are obtained. Finally, these 1000 data sets are combined to obtain a new data set N with a magnitude sufficient to reflect the distribution of customer complaint events, where the new data set N is of the order of 1000 x 100.
S103, determining the early warning probability of the current single data of the customer complaint event in a new single data set of the customer complaint event according to the type of the historical single data of the customer complaint event.
Optionally, a calculation mode of the early warning probability corresponding to the current single volume data of the customer complaint event can be determined according to whether the type of the historical single volume data conforms to normal distribution, if so, the current single volume data of the customer complaint event is subjected to data standardization processing to calculate a corresponding early warning probability value, and if not, the current single volume data of the customer complaint event is calculated at the quantile point of a new single volume data set of the customer complaint event to obtain a corresponding early warning probability value.
And S104, carrying out early warning prompt through thermodynamic diagrams according to the early warning probability.
Optionally, the early warning probability is calculated according to a preset thermal conversion function to obtain a thermal display value corresponding to the early warning probability, the thermal display value is a number between 0 and 1, when the thermal display value is larger, the color can be set to be darker, and finally early warning prompt is performed according to the corresponding early warning color.
In the embodiment, historical single quantity data of a customer complaint event is obtained, abnormal data in the historical single quantity data is cleaned, the cleaned historical single quantity data is subjected to resetting random sampling to obtain a new single quantity data set of the customer complaint event, current single quantity data of the customer complaint event is obtained, whether the historical single quantity data of the customer complaint event conforms to normal distribution or not is judged, and therefore a calculation mode of early warning probability of the current single quantity data of the customer complaint event in the new single quantity data set of the customer complaint event is determined; and calculating corresponding early warning probability according to the determined calculation mode, displaying the early warning probability in a thermodynamic diagram form through conversion, and accurately early warning the current single data of the customer complaint event, so that customer complaint handling work can be reasonably arranged by customer service personnel, and the customer complaint service satisfaction degree is improved.
Fig. 2 shows another flow chart of the customer complaint single-quantity early warning method provided by the embodiment of the invention.
Optionally, as shown in fig. 2, in another embodiment, the step of determining the early warning probability of the current single volume data of the customer complaint event in the new single volume data set of the customer complaint event according to the type of the historical single volume data of the customer complaint event may specifically include:
s201, judging whether the historical single data accords with normal distribution.
S202, if the historical single data accords with normal distribution, acquiring the mean value and the standard deviation of a new data set of the customer complaint event, and normally standardizing the current single data of the customer complaint event based on the mean value and the standard deviation to obtain standardized single data.
S203, calculating the early warning probability of the normalized single data in a new single data set of the customer complaint event according to a preset normal integral function.
Optionally, when the historical single amount data of the customer complaint event is obtained, it may be determined whether the historical single amount data conforms to normal distribution, that is, the historical single amount data before being subjected to the cleaning processing is not obtained, if the historical single amount data conforms to normal distribution, the illustrated example of the embodiment is continued, a mean value and a standard deviation of a new data set N of the customer complaint event are obtained, that is, m and sigma, respectively, when the customer service center a has a new customer complaint event single amount a, normal normalization may be performed on the data a based on the new data set N according to the formula (2), so as to obtain normalized data x, specifically, as follows:
x ═ a-m)/sigma equation (2)
The normalized data is distributed from the standard positive space, and then x is substituted into the normal integral function, i.e. formula (3), for calculation, as follows:
where μ is 0 and σ is 1, the integration range is negative infinity to the value x, and then a probability P between 0 and 1 can be calculated.
In S201, the step of determining whether the historical single amount data conforms to the normal distribution may be performed only after the historical single amount data is acquired, and the step is not limited to the step of this embodiment.
Optionally, after determining whether the historical single amount data conforms to the normal distribution, the customer complaint single amount early warning method further includes:
and if the historical single data does not accord with normal distribution, acquiring the data proportion of a new data set smaller than the current single data, and determining the early warning probability of the current single data of the customer complaint event in the historical single data.
Optionally, assuming that the current single data of the customer appeal event is a, calculating a data proportion of the new data set N smaller than the current single data a, and determining the early warning probability of the current single data of the customer appeal event in the historical single data according to the data proportion.
Fig. 3 shows another flow chart of the customer complaint single-quantity early warning method provided by the embodiment of the invention.
Optionally, as shown in fig. 3, the performing an early warning prompt through thermodynamic diagrams according to the early warning probability includes:
s301, calculating the early warning probability according to a preset thermal conversion function to obtain a thermal display value corresponding to the early warning probability;
s302, acquiring a corresponding early warning color according to the thermal display value to perform early warning prompt.
Optionally, the early warning probability calculated according to the current single amount of the customer-complaint event can be displayed through a thermodynamic diagram, according to the service requirement of the customer-complaint event, when the real-time single amount of the customer-complaint event is in the first 20% of the historical single amount data, the thermodynamic color change rate is increased to indicate that the early warning degree is higher, and when the real-time single amount of the customer-complaint event is in the last 80% of the historical single amount data set, the thermodynamic color change rate is reduced to indicate that the early warning degree is lower.
Fig. 4 shows a schematic diagram of a thermodynamic conversion function of a customer complaint single-quantity early warning method provided by an embodiment of the invention. Alternatively, as shown in fig. 4, in order to achieve this, a thermodynamic conversion function f is needed to numerically convert the result early warning probability, the thermodynamic conversion function is shown in formula (4),
function f ═ ((2x-1) ^3)/2+0.5 formula (4)
When the function f is [0,1] in the domain of definition, its value domain is also [0,1 ]. As shown in fig. 4, when x is greater than 0.8, the corresponding value range change rate is significantly higher than when x is less than 0.8. Meets the requirement of the thermodynamic conversion function f.
After the early warning probability is converted by the thermal conversion function, a thermal display value y can be obtained, wherein y can be a number between 0 and 1. When y is larger, the color on the thermodynamic diagram is darker, and the single customer complaint event early warning degree representing the customer service center is higher.
The customer complaint single-quantity early warning method provided by the embodiment of the invention is explained in a specific implementation manner as follows:
fig. 5 shows another flow chart of the customer complaint single-quantity early warning method provided by the embodiment of the invention.
As shown in fig. 5, in this embodiment, the customer complaint single quantity warning method may include:
s501, obtaining historical single data of customer complaint events of the customer complaint center.
S502, judging whether the historical single data accords with normal distribution.
If yes, sequentially executing steps S503, S504, S505, S506 and S507, and then executing steps S509 and S510; if not, steps S503, S504, S505, S508, and S509 are sequentially executed, and then steps S509 and S510 are executed.
S503, removing abnormal data in the historical single data through the Box diagram Box-plot.
And S504, cleaning the null values in the historical single data.
And S505, carrying out 1000 times of reset random sampling on the washed historical single data to obtain a new single data set of the customer complaint event.
And S506, standardizing the current single data of the customer complaint event.
And S507, calculating early warning probability according to the current single data and the new single data set after standardization processing.
And S508, calculating the data occupation ratio of the new data set smaller than the current single data as early warning probability.
And S509, calculating to obtain a thermal display value with the abnormal degree between 0 and 1 by taking the calculated early warning probability as an input value of a thermal conversion function.
And S510, inputting the thermodynamic display value into a thermodynamic diagram for displaying.
In this embodiment, the customer complaint single-quantity early warning method described in the foregoing embodiment has the same beneficial effects as the customer complaint single-quantity early warning method described in the foregoing embodiment, and details are not repeated herein.
Based on the customer complaint single quantity early warning method in the foregoing method embodiment, an embodiment of the present invention further provides a customer complaint single quantity early warning device, and fig. 6 shows a schematic structural diagram of the customer complaint single quantity early warning device provided in the embodiment of the present invention.
As shown in fig. 6, the customer complaint single-amount warning device may include:
and the cleaning module 10 is used for acquiring historical single-quantity data of the customer complaint event and cleaning abnormal data in the historical single-quantity data.
And the resampling module 20 is configured to perform resetting random sampling on the washed historical single data to obtain a new single data set of the customer complaint event.
And the processing module 30 is configured to determine, according to the type of the historical single data of the customer complaint event, an early warning probability of the current single data of the customer complaint event in a new single data set of the customer complaint event.
And the early warning module 40 is used for carrying out early warning prompt through thermodynamic diagrams according to the early warning probability.
Fig. 7 shows another schematic structural diagram of a customer complaint single-quantity early warning device provided by an embodiment of the invention.
Alternatively, as shown in fig. 7, the processing module 30 includes:
the judging module 31 is configured to judge whether the historical single amount data conforms to normal distribution;
the first calculation module 32 is configured to, if the historical single amount data conforms to normal distribution, obtain a mean value and a standard deviation of a new data set of the customer complaint event, and normally standardize the current single amount data of the customer complaint event based on the mean value and the standard deviation to obtain standardized single amount data;
and calculating the normalized early warning probability of the new single data set of the customer complaint event according to a preset normal integral function.
Fig. 8 shows another schematic structural diagram of the customer complaint single-quantity early warning device provided by the embodiment of the invention.
Optionally, as shown in fig. 8, the processing module 30 further includes:
and the second calculating module 33 is configured to, if the historical single amount data does not conform to the normal distribution, obtain a data proportion of the new data set smaller than the current single amount data, and determine an early warning probability of the current single amount data of the customer complaint event in the historical single amount data.
Fig. 9 shows another schematic structural diagram of a customer complaint single-quantity early warning device provided by the embodiment of the invention.
Optionally, as shown in fig. 9, the early warning module 40 includes:
the conversion module 41 is configured to calculate the early warning probability according to a preset thermodynamic conversion function to obtain a corresponding thermodynamic display value;
and the prompt module 42 is used for acquiring a corresponding early warning color according to the thermal display value to perform early warning prompt.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process of the method in the foregoing method embodiment, and is not described in detail herein.
The customer complaint single-quantity early warning device provided by the embodiment of the invention corresponds to the customer complaint single-quantity early warning method in the method embodiment, so that the customer complaint single-quantity early warning device in the device embodiment has all the beneficial effects of the customer complaint single-quantity early warning method in the embodiment, and details are not repeated here.
An embodiment of the present invention further provides an electronic device, which may be a background server, a computer, or the like of a customer complaint system, and fig. 10 shows a schematic structural diagram of the electronic device provided in the embodiment of the present invention.
As shown in fig. 10, the electronic device may include: the storage medium 200 stores machine-readable instructions executable by the processor 100, and when the electronic device is operated, the processor 100 communicates with the storage medium 200 via the bus, and the processor 100 executes the machine-readable instructions to perform the customer complaint single-amount warning method as described in the foregoing method embodiment. The specific implementation and technical effects are similar, and are not described herein again.
For ease of illustration, only one processor is described in the above electronic device. However, it should be noted that the electronic device in the present invention may also comprise a plurality of processors, and thus the steps performed by one processor described in the present invention may also be performed by a plurality of processors in combination or individually. For example, the processor of the electronic device executes step a and step B, it should be understood that step a and step B may also be executed by two different processors together or separately in one processor. For example, a first processor performs step a and a second processor performs step B, or the first processor and the second processor perform steps a and B together, etc.
In some embodiments, a processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set computer (Reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.
The embodiment of the present invention further provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the customer complaint single quantity early warning method described in the foregoing method embodiment is executed. The specific implementation and technical effects are similar, and are not described herein again.
Alternatively, the storage medium may be a U disk, a removable hard disk, a ROM, a RAM, a magnetic or optical disk, or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A customer complaint single quantity early warning method is characterized by comprising the following steps:
acquiring historical single data of a customer complaint event, and cleaning abnormal data in the historical single data;
carrying out resetting random sampling on the washed historical single data to obtain a new single data set of the customer complaint event;
determining the early warning probability of the current single data of the customer complaint event in a new single data set of the customer complaint event according to the type of the historical single data of the customer complaint event;
and carrying out early warning prompt through thermodynamic diagrams according to the early warning probability.
2. The customer complaint single-volume early warning method of claim 1, wherein determining the early warning probability of the current single-volume data of the customer complaint event in a new single-volume data set of the customer complaint event according to the type of the historical single-volume data of the customer complaint event comprises:
judging whether the historical single data accords with normal distribution;
if the historical single data accords with normal distribution, acquiring a mean value and a standard deviation of a new data set of the customer complaint event, and normally standardizing the current single data of the customer complaint event based on the mean value and the standard deviation to obtain standardized single data;
and calculating the normalized early warning probability of the new single data set of the customer complaint event according to a preset normal integral function.
3. The customer complaint single-quantity early warning method according to claim 2, wherein after judging whether the historical single-quantity data conforms to normal distribution, the method further comprises:
and if the historical single data does not accord with normal distribution, acquiring the data occupation ratio of the new data set smaller than the current single data, and determining the early warning probability of the current single data of the customer complaint event in the historical single data.
4. The method of claim 1, wherein performing early warning prompting via thermodynamic diagrams according to the early warning probability comprises:
calculating the early warning probability according to a preset thermal conversion function to obtain a thermal display value corresponding to the early warning probability;
and acquiring a corresponding early warning color according to the thermal display value to perform early warning prompt.
5. A customer complaint single-amount early warning device, characterized in that the device comprises:
the cleaning module is used for acquiring historical single-quantity data of the customer complaint event and cleaning abnormal data in the historical single-quantity data;
the resampling module is used for carrying out resetting random sampling on the washed historical single data to obtain a new single data set of the customer complaint event;
the processing module is used for determining the early warning probability of the current single data of the customer complaint event in the new single data set of the customer complaint event according to the type of the historical single data of the customer complaint event;
and the early warning module is used for carrying out early warning prompt through thermodynamic diagrams according to the early warning probability.
6. The apparatus of claim 5, wherein the processing module comprises:
the judging module is used for judging whether the historical single data accords with normal distribution;
the first calculation module is used for acquiring a mean value and a standard deviation of a new data set of the customer complaint event if the historical single quantity data conforms to normal distribution, and normally standardizing the current single quantity data of the customer complaint event based on the mean value and the standard deviation to obtain standardized single quantity data;
and calculating the normalized early warning probability of the new single data set of the customer complaint event according to a preset normal integral function.
7. The apparatus of claim 5, wherein the processing module further comprises:
and the second calculation module is used for acquiring the data proportion of the new data set smaller than the current single-quantity data if the historical single-quantity data does not conform to normal distribution, and determining the early warning probability of the current single-quantity data of the customer complaint event in the historical single-quantity data.
8. The apparatus of claim 5, wherein the early warning module comprises:
the conversion module is used for calculating the early warning probability according to a preset thermodynamic conversion function to obtain a corresponding thermodynamic display value;
and the prompt module is used for acquiring a corresponding early warning color according to the thermal display value to perform early warning prompt.
9. An electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the electronic device is operated, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to execute the customer complaint single-dose early warning method according to any one of claims 1-4.
10. A storage medium having stored thereon a computer program which, when executed by a processor, performs the customer complaint single-volume warning method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010262313.XA CN113495909A (en) | 2020-04-06 | 2020-04-06 | Customer complaint single quantity early warning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010262313.XA CN113495909A (en) | 2020-04-06 | 2020-04-06 | Customer complaint single quantity early warning method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113495909A true CN113495909A (en) | 2021-10-12 |
Family
ID=77995226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010262313.XA Pending CN113495909A (en) | 2020-04-06 | 2020-04-06 | Customer complaint single quantity early warning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113495909A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101267362A (en) * | 2008-05-16 | 2008-09-17 | 亿阳信通股份有限公司 | A dynamic identification method and its device for normal fluctuation range of performance normal value |
| CN103200039A (en) * | 2012-01-09 | 2013-07-10 | 阿里巴巴集团控股有限公司 | Data monitoring method and device |
| CN104572391A (en) * | 2013-10-16 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Monitoring alarm strategy collocation method and device and monitoring alarm method and device |
| CN104866922A (en) * | 2015-05-22 | 2015-08-26 | 中国联合网络通信集团有限公司 | User off-network prediction method and apparatus |
| CN105279257A (en) * | 2015-10-15 | 2016-01-27 | 珠海世纪鼎利科技股份有限公司 | Normal distribution-based internet big data mining method and system |
| CN105868845A (en) * | 2016-03-24 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Risk pre-warning method and apparatus |
| US20170017760A1 (en) * | 2010-03-31 | 2017-01-19 | Fortel Analytics LLC | Healthcare claims fraud, waste and abuse detection system using non-parametric statistics and probability based scores |
| CN106921507A (en) * | 2015-12-25 | 2017-07-04 | 株式会社日立制作所 | The method and apparatus being predicted to customer complaint within a wireless communication network |
| CN106971310A (en) * | 2017-03-16 | 2017-07-21 | 国家电网公司 | A kind of customer complaint quantitative forecasting technique and device |
| CN107992609A (en) * | 2017-12-15 | 2018-05-04 | 广东电网有限责任公司信息中心 | A kind of complaint tendency determination methods based on Text Classification and decision tree |
| CN109325059A (en) * | 2018-12-03 | 2019-02-12 | 枘熠集成电路（上海）有限公司 | A kind of data comparing method and device |
| WO2019037202A1 (en) * | 2017-08-24 | 2019-02-28 | 平安科技（深圳）有限公司 | Method and apparatus for recognising target customer, electronic device and medium |
| CN109542740A (en) * | 2017-09-22 | 2019-03-29 | 阿里巴巴集团控股有限公司 | Method for detecting abnormality and device |
| CN109961248A (en) * | 2017-12-25 | 2019-07-02 | 顺丰科技有限公司 | Waybill complains prediction technique, device, equipment and its storage medium |
| CN110503249A (en) * | 2019-08-07 | 2019-11-26 | 国网河北省电力有限公司 | One kind complaining prediction technique caused by having a power failure |
-
2020
- 2020-04-06 CN CN202010262313.XA patent/CN113495909A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101267362A (en) * | 2008-05-16 | 2008-09-17 | 亿阳信通股份有限公司 | A dynamic identification method and its device for normal fluctuation range of performance normal value |
| US20170017760A1 (en) * | 2010-03-31 | 2017-01-19 | Fortel Analytics LLC | Healthcare claims fraud, waste and abuse detection system using non-parametric statistics and probability based scores |
| CN103200039A (en) * | 2012-01-09 | 2013-07-10 | 阿里巴巴集团控股有限公司 | Data monitoring method and device |
| CN104572391A (en) * | 2013-10-16 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Monitoring alarm strategy collocation method and device and monitoring alarm method and device |
| CN104866922A (en) * | 2015-05-22 | 2015-08-26 | 中国联合网络通信集团有限公司 | User off-network prediction method and apparatus |
| CN105279257A (en) * | 2015-10-15 | 2016-01-27 | 珠海世纪鼎利科技股份有限公司 | Normal distribution-based internet big data mining method and system |
| CN106921507A (en) * | 2015-12-25 | 2017-07-04 | 株式会社日立制作所 | The method and apparatus being predicted to customer complaint within a wireless communication network |
| CN105868845A (en) * | 2016-03-24 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | Risk pre-warning method and apparatus |
| CN106971310A (en) * | 2017-03-16 | 2017-07-21 | 国家电网公司 | A kind of customer complaint quantitative forecasting technique and device |
| WO2019037202A1 (en) * | 2017-08-24 | 2019-02-28 | 平安科技（深圳）有限公司 | Method and apparatus for recognising target customer, electronic device and medium |
| CN109542740A (en) * | 2017-09-22 | 2019-03-29 | 阿里巴巴集团控股有限公司 | Method for detecting abnormality and device |
| CN107992609A (en) * | 2017-12-15 | 2018-05-04 | 广东电网有限责任公司信息中心 | A kind of complaint tendency determination methods based on Text Classification and decision tree |
| CN109961248A (en) * | 2017-12-25 | 2019-07-02 | 顺丰科技有限公司 | Waybill complains prediction technique, device, equipment and its storage medium |
| CN109325059A (en) * | 2018-12-03 | 2019-02-12 | 枘熠集成电路（上海）有限公司 | A kind of data comparing method and device |
| CN110503249A (en) * | 2019-08-07 | 2019-11-26 | 国网河北省电力有限公司 | One kind complaining prediction technique caused by having a power failure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110191094B (en) | Abnormal data monitoring method and device, storage medium and terminal | |
| CN111444060A (en) | Anomaly detection model training method, anomaly detection method and related device | |
| CN114662953A (en) | Internet of things equipment operation and maintenance method, device, equipment and medium | |
| CN113495909A (en) | Customer complaint single quantity early warning method and device, electronic equipment and storage medium | |
| CN113468021A (en) | Method, device, equipment and storage medium for monitoring performance data | |
| CN113393325A (en) | Transaction detection method, intelligent device and computer storage medium | |
| US11656613B2 (en) | Information processing device and information processing method | |
| CN111275466A (en) | Method and device for early warning of overdue single quantity | |
| JP6048119B2 (en) | Abnormal cause estimation program, abnormal cause estimation apparatus, and abnormal cause estimation method | |
| CN111258585A (en) | Attendance calculation method, system and equipment | |
| CN116167854A (en) | Quotation display analysis method, system, equipment and medium | |
| CN112487039B (en) | Data processing method, device, equipment and readable storage medium | |
| CN115686411A (en) | Physical examination guiding method, device, equipment and storage medium | |
| CN115526431A (en) | Data analysis method based on industrial Internet and related device | |
| CN113988188A (en) | Fault diagnosis method, fault diagnosis device, electronic equipment and storage medium | |
| CN112926108A (en) | Industrial component visual customization method and device and storage medium | |
| CN112329982B (en) | Geological disaster prediction method and system based on K-line graph | |
| CN112422333A (en) | Distribution network condition determining method, system and related device | |
| CN116991684B (en) | Alarm information processing method, device, equipment and medium | |
| CN111178780A (en) | Operation and maintenance strategy setting method and device, storage medium and electronic equipment | |
| CN116991620B (en) | Solution determining method, device, equipment and medium | |
| JP6879330B2 (en) | Goal non-achievement information presentation system and goal non-achievement information presentation program | |
| CN112989555B (en) | Time sequence data processing method, device, equipment and computer medium | |
| CN116308215B (en) | Method and device for generating batch outgoing information and related equipment | |
| CN117421325A (en) | Associated alarm recognition method and device based on database |
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 |