CN113704407A - Complaint amount analysis method, device, equipment and storage medium based on category analysis - Google Patents

Complaint amount analysis method, device, equipment and storage medium based on category analysis Download PDF

Info

Publication number
CN113704407A
CN113704407A CN202111006941.2A CN202111006941A CN113704407A CN 113704407 A CN113704407 A CN 113704407A CN 202111006941 A CN202111006941 A CN 202111006941A CN 113704407 A CN113704407 A CN 113704407A
Authority
CN
China
Prior art keywords
complaint
text
amount
preset
category
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.)
Granted
Application number
CN202111006941.2A
Other languages
Chinese (zh)
Other versions
CN113704407B (en
Inventor
李骁
赖众程
王亮
高洪喜
许海金
张宇川
张舒婷
陈杭
邱文涛
吴鹏召
海洋
李会璟
李兴辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Bank Co Ltd
Original Assignee
Ping An Bank Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Bank Co Ltd filed Critical Ping An Bank Co Ltd
Priority to CN202111006941.2A priority Critical patent/CN113704407B/en
Publication of CN113704407A publication Critical patent/CN113704407A/en
Application granted granted Critical
Publication of CN113704407B publication Critical patent/CN113704407B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/12—Use of codes for handling textual entities
    • G06F40/126—Character encoding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to an artificial intelligence technology, and discloses a complaint amount analysis method based on category analysis, which comprises the following steps: the method comprises the steps of counting complaint quantities in a plurality of preset time intervals from complaint quantity data of preset services, respectively calculating correlation coefficients between a plurality of operation indexes and the complaint quantities, collecting the operation indexes of which the correlation coefficients are larger than a preset threshold value as characteristic indexes, generating a text matrix of a complaint text of each complaint, determining the complaint class of each complaint according to the text matrix, calculating the proportion weight of each complaint class, analyzing the complaint quantities to obtain the complaint quantities in the future preset time period, and calculating the complaint quantities of different complaint classes in the future preset time period according to the proportion weight and the complaint quantities in the future preset time period. In addition, the invention also relates to a block chain technology, and complaint amount data can be stored in the nodes of the block chain. The invention also provides a complaint quantity analysis device, equipment and medium based on the category analysis. The invention can improve the accuracy of complaint quantity analysis.

Description

Complaint amount analysis method, device, equipment and storage medium based on category analysis
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a complaint amount analysis method and device based on category analysis, electronic equipment and a computer-readable storage medium.
Background
With the increasingly fierce competition of duration, more and more companies and enterprises pay attention to the service level of users, the complaint volume becomes an important index for measuring the quality and quickness of a service, and when the complaint volume of a certain service is too high, the service has a large number of defects, so that the user experience is poor. Therefore, the complaint amount is reasonably analyzed and predicted, and the improvement of business realization of enterprises is facilitated.
Most of the existing complaint quantity prediction methods are regression analysis based on historical complaint quantity, namely, the complaint quantity in a future time period is predicted according to the complaint quantity in a certain time period in the history. However, in this method, other factors related to the service are ignored, and the complaint percentage of each type in a large number of customer complaints cannot be known, so that the accuracy of the complaint amount obtained by performing regression analysis only using the historical complaint amount is low.
Disclosure of Invention
The invention provides a complaint amount analysis method and device based on category analysis and a computer-readable storage medium, and mainly aims to solve the problem of low accuracy in complaint amount analysis.
In order to achieve the above object, the present invention provides a complaint amount analysis method based on category analysis, including:
the method comprises the steps of obtaining complaint quantity data of a preset service, and counting the complaint quantity of each time interval in a plurality of preset time intervals according to the complaint quantity data;
acquiring a plurality of operation indexes of the preset service in each time interval, respectively calculating a correlation coefficient between each operation index and the complaint amount, and collecting the operation indexes of which the correlation coefficients are greater than a preset threshold value as characteristic indexes;
obtaining a complaint text of each complaint of the preset service, and performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text;
respectively calculating the relative probability between each text matrix and a preset complaint category, determining the complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculating the proportion weight of each complaint category in the complaint text according to the complaint category;
and analyzing the complaint amount according to the complaint amount of each time interval and the characteristic index by utilizing a pre-constructed time sequence prediction model to obtain the complaint amount of a future preset time period, and calculating the complaint amount of each complaint category in the future preset time period according to the proportion weight and the complaint amount of the future preset time period.
Optionally, the counting the complaint amount of each time interval in a plurality of preset time intervals according to the complaint amount data includes:
extracting a time data expression format in the complaint amount data;
compiling preset characters into regular expressions according to the time data expression format;
extracting complaint time of each complaint from the complaint quantity data by using the regular expression;
classifying the complaint quantity data into a plurality of preset time intervals according to the complaint time;
and counting the number of the complaint amount data in each time interval to obtain the complaint amount in each time interval.
Optionally, the calculating a correlation coefficient between each business index and the complaint amount respectively includes:
converting the plurality of operation indexes of the preset service in each time interval into index vectors respectively;
selecting one of the time intervals from the preset time intervals one by one, selecting one of the vectors from the index vectors of the selected time interval one by one as a target vector, and calculating the association degree between the target vector and the complaint amount of the selected time interval;
and summing the relevance between the target vector and the complaint amount of each time interval to obtain a correlation coefficient between the operation index corresponding to the target vector and the complaint amount.
Optionally, the calculating a correlation between the target vector and the complaint amount of the selected time interval includes:
calculating the relevance between the target vector and the complaint amount of the selected time interval by using a relevance algorithm as follows:
Figure BDA0003237375520000021
wherein, Px,yIs the degree of correlation between the target vector and the complaint volume for the selected time interval, x is the modulo length of the target vector,
Figure BDA0003237375520000031
is the mean of the modular lengths of all the index vectors, y is the complaint volume in the selected time interval,
Figure BDA0003237375520000032
the average value of the complaint amount in all time intervals is shown.
Optionally, the performing numerical matrix conversion on the complaint texts to obtain a text matrix of each complaint text includes:
selecting one text from the complaint texts one by one as a target text;
performing word segmentation processing on the target text to obtain text word segmentation;
counting the position information of each text participle in the target text, and carrying out vector coding on the position information to obtain a position vector;
converting each text word into a word vector, and splicing a position code corresponding to each text word and the word vector of the text word into a code vector;
and splicing the coding vectors of all text word segmentation as row vectors to obtain a text matrix of the target text.
Optionally, the obtaining the text matrix of the target text by splicing the coding vectors of all text participles as row vectors includes:
counting the vector length of each vector in the coding vectors, and determining the maximum vector length as a target length;
utilizing preset parameters to extend the vector length of each vector in the coding vectors to the target length;
and selecting the extended coding vectors as row vectors one by one for splicing to obtain a text matrix of the target text.
Optionally, the analyzing, by using a pre-established time sequence prediction model, the complaint amount according to the complaint amount of each time interval and the characteristic index to obtain the complaint amount of the future preset time period includes:
collecting the complaint amount and the characteristic index of each time interval as characteristic data;
mapping the characteristic data to a preset characteristic space by using a pre-constructed time sequence detection model, and counting the space coordinate of each characteristic data in the preset characteristic space;
performing curve fitting on the space coordinate to obtain a fitting function;
and substituting the future preset time period as a parameter into the fitting function to obtain the complaint amount of the future preset time period.
In order to solve the above problem, the present invention also provides a complaint amount analysis device based on category analysis, the device including:
the complaint quantity counting module is used for acquiring complaint quantity data of a preset service and counting the complaint quantity of each time interval in a plurality of preset time intervals according to the complaint quantity data;
the index calculation module is used for acquiring a plurality of operation indexes of the preset service in each time interval, calculating a correlation coefficient between each operation index and the complaint amount respectively, and collecting the operation indexes of which the correlation coefficients are larger than a preset threshold value as characteristic indexes;
the text matrix generation module is used for acquiring the complaint text of each complaint of the preset service, and performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text;
the weight calculation module is used for respectively calculating the relative probability between each text matrix and a preset complaint category, determining the complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculating the proportion weight of each complaint category in the complaint text according to the complaint category;
and the complaint quantity prediction module is used for analyzing the complaint quantity according to the complaint quantity of each time interval and the characteristic index by utilizing a pre-constructed time sequence prediction model to obtain the complaint quantity of a future preset time period, and calculating the complaint quantity of each complaint category in the future preset time period according to the percentage weight and the complaint quantity of the future preset time period.
In order to solve the above problem, the present invention also provides an electronic device, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method for complaint volume analysis based on category analysis described above.
In order to solve the above problem, the present invention also provides a computer-readable storage medium having at least one computer program stored therein, the at least one computer program being executed by a processor in an electronic device to implement the complaint amount analysis method based on category analysis described above.
The method and the device can screen out the operation indexes related to the complaint amount in the service, and predict the complaint amount in the future preset time period based on the complaint amount in the historical preset time period and the screened operation indexes, wherein the numerical value of the complaint amount and the factors of the operation indexes related to the service are considered; and according to the proportion of each type of complaint amount in the history, numerical values of the complaint amounts of different types in a future preset time period are predicted, so that the complaint amounts of different types are predicted, and the accuracy of complaint amount prediction is improved. Therefore, the complaint amount analysis method, the complaint amount analysis device, the complaint amount analysis electronic equipment and the computer-readable storage medium based on the category analysis can solve the problem of low accuracy in recommending products.
Drawings
FIG. 1 is a schematic flow chart of a complaint quantity analysis method based on category analysis according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a process of calculating correlation coefficients according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of generating a text matrix according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a complaint quantity analysis apparatus based on category analysis according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for implementing the complaint quantity analysis method based on category analysis according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a complaint amount analysis method based on category analysis. The main body of the complaint quantity analysis method based on the category analysis includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the complaint amount analysis method based on the category analysis may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Referring to fig. 1, a schematic flow chart of a complaint quantity analysis method based on category analysis according to an embodiment of the present invention is shown. In this embodiment, the method for analyzing the complaint amount based on the category analysis includes:
s1, obtaining the complaint amount data of the preset service, and counting the complaint amount of each time interval in a plurality of preset time intervals according to the complaint amount data.
In the embodiment of the present invention, the preset service may be any product, service, or benefit, and the complaint amount data includes data such as time and frequency of complaints performed by at least one user on the preset service.
In detail, the remaining stored complaint amount data may be crawled from pre-constructed storage areas, including but not limited to databases, blockchain nodes, network caches, using computer statements with data crawling functionality (e.g., java statements, python statements, etc.).
In the embodiment of the invention, the complaint amount data can be analyzed to obtain the complaint amount of each time interval in a plurality of preset time intervals.
In detail, a regular expression can be constructed, the regular expression is used for extracting the time of each complained time from the complaining amount data, and then the complaining amount of each time interval in the preset time intervals is determined according to the complaining time.
In particular, the regular expression may be used to extract fields in data having a particular format.
In an embodiment of the present invention, the counting the complaint amount of each time interval in a plurality of preset time intervals according to the complaint amount data includes:
extracting a time data expression format in the complaint amount data;
compiling preset characters into regular expressions according to the time data expression format;
extracting complaint time of each complaint from the complaint quantity data by using the regular expression;
classifying the complaint quantity data into a plurality of preset time intervals according to the complaint time;
and counting the number of the complaint amount data in each time interval to obtain the complaint amount in each time interval.
In detail, the time data expression format refers to a data format of data for expressing time in the complaint amount data, for example, time expressed in the form of "xx/xx/xx", or time expressed in the form of "xx month xx day" in xx years, and the like.
Specifically, a preset compiler may be utilized to compile preset characters into a regular expression according to the actual data expression format, and then extract the complaint time of each complaint from the data volume data by using the compiled regular expression, where the compiler includes but is not limited to: visual Studio compiler, Dev C + + compiler.
In the embodiment of the invention, after the complaint time of each complaint is extracted, the complaint amount data can be classified into a plurality of preset time intervals according to the complaint time, and the number of the complaint amount data in each time interval is counted to obtain the complaint amount in each time interval.
S2, obtaining a plurality of operation indexes of the preset service in each time interval, respectively calculating a correlation coefficient between each operation index and the complaint amount, and collecting the operation indexes of which the correlation coefficients are larger than a preset threshold value as characteristic indexes.
In the embodiment of the invention, the operation indexes refer to indexes such as money amount and user number of the preset service in the operation process.
In detail, the step of obtaining the multiple operation indexes of the preset service in each time interval is consistent with the step of obtaining the complaint amount data of the preset service in S1, and is not described herein again.
In the embodiment of the invention, because the number of the operation indexes is possibly very large, but not every operation index has a relatively obvious relationship with the complaint amount, in order to improve the efficiency and the accuracy of the subsequent analysis of the complaint amount, the correlation coefficient between every operation index and the complaint amount can be respectively calculated, so that the operation index which is relatively obviously related to the complaint amount can be screened out according to the correlation coefficient.
In the embodiment of the present invention, referring to fig. 2, the calculating the correlation coefficient between each business index and the complaint amount respectively includes:
s21, converting the plurality of operation indexes of the preset service in each time interval into index vectors respectively;
s22, selecting one of the time intervals from the preset time intervals one by one, selecting one of the vectors from the index vectors of the selected time interval one by one as a target vector, and calculating the association degree between the target vector and the complaint amount of the selected time interval;
and S23, summing the relevance between the target vector and the complaint amount in each time interval to obtain a correlation coefficient between the business index corresponding to the target vector and the complaint amount.
In detail, a plurality of business indicators of the preset business in each time interval may be respectively converted into indicator vectors by using a preset artificial intelligence Model with a vector conversion function, where the artificial intelligence Model includes, but is not limited to, an NLP (Natural Language Processing) Model, an HMM (Hidden Markov Model).
Specifically, the calculating a correlation degree between the target vector and the complaint amount of the selected time interval includes:
calculating the relevance between the target vector and the complaint amount of the selected time interval by using a relevance algorithm as follows:
Figure BDA0003237375520000081
wherein, Px,yIs the degree of correlation between the target vector and the complaint volume for the selected time interval, x is the modulo length of the target vector,
Figure BDA0003237375520000082
is the mean of the modular lengths of all the index vectors, y is the complaint volume in the selected time interval,
Figure BDA0003237375520000083
the average value of the complaint amount in all time intervals is shown.
In the embodiment of the present invention, since there are a plurality of preset time intervals, but the correlation between the operation index corresponding to the target vector obtained by the calculation and the complaint amount in the time interval in which the target vector is located is the same, the correlation between the operation index corresponding to the target vector and the complaint amount in each time interval can be summed to obtain the correlation coefficient between the operation index corresponding to the target vector and the overall complaint amount, and the operation index having the correlation coefficient greater than the preset threshold value is selected as the characteristic index.
S3, obtaining the complaint text of each complaint of the preset service, and performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text.
In the embodiment of the present invention, the complaint text is a text of complaint opinions generated by the user for the preset service when the preset service is complaint by the user.
In detail, the step of obtaining the complaint text of the preset service each time the preset service is complained is the same as the step of obtaining the complaint amount data of the preset service in S1, and is not described herein again.
In the embodiment of the invention, because the complaint text is in a text form, in order to reduce the occupation of computing resources when the complaint text is analyzed, the numerical matrix conversion can be performed on the complaint text to obtain a text matrix corresponding to the complaint text.
In the embodiment of the present invention, referring to fig. 3, the performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text includes:
s31, selecting one text from the complaint texts one by one as a target text;
s32, performing word segmentation processing on the target text to obtain text word segmentation;
s33, counting the position information of each text participle in the target text, and carrying out vector coding on the position information to obtain a position vector;
s34, converting each text word into a word vector, and splicing the position code corresponding to each text word and the word vector of the text word into a code vector;
and S35, splicing the coding vectors of all text word segmentation as row vectors to obtain a text matrix of the target text.
In detail, the target text can be subjected to word segmentation processing by using an artificial intelligence model with a word segmentation processing function, such as a preset word2vec model and a bert model, so as to obtain text word segmentation.
In the embodiment of the present invention, the steps of performing vector coding on the location information and converting each text word into a word vector are the same as the step of converting the plurality of operation indexes of the preset service into the index vectors in each time interval in S2, which is not described herein again.
In the embodiment of the invention, the position information of the text participle is coded, and the position vector obtained by coding the position information is added into the word vector of the text participle, so that the position information of the word can be embedded into the word vector, and the accuracy of the finally generated text matrix is improved.
In the embodiment of the present invention, the obtaining of the text matrix of the target text by splicing the coding vectors of all text participles as row vectors includes:
counting the vector length of each vector in the coding vectors, and determining the maximum vector length as a target length;
utilizing preset parameters to extend the vector length of each vector in the coding vectors to the target length;
and selecting the extended coding vectors as row vectors one by one for splicing to obtain a text matrix of the target text.
In detail, since the encoding vectors are obtained by quantity concatenation of word vectors of different text segments and position lines of each text segment, the lengths of the vectors of different encoding vectors may be different, which is not favorable for subsequent concatenation into a text matrix, and further, the lengths of the vectors of each of the encoding vectors can be extended to a uniform length by using preset parameters.
For example, there is a code vector a: (10,33), code vector B: (22,35,55) and code vector C: (1,42,5,76), it is statistically known that the vector length of the code vector C is the largest (4), and when the preset parameter is 0, the preset parameter can be used to extend the vector lengths of the code vector a and the code vector B to 4, so as to obtain an extended code vector a: (10,33,0,0), and the extended coded vector B: (22,35,55,0), and further selecting the extended coding vectors one by one as row vectors to splice to obtain the following text matrix:
Figure BDA0003237375520000091
s4, respectively calculating the relative probability between each text matrix and a preset complaint category, determining the complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculating the proportion weight of each complaint category in the complaint text according to the complaint category
In the embodiment of the present invention, the relative probability refers to a probability value of which kind of complaint category the complaint text corresponding to each text matrix belongs to, for example, when the relative probability value between the text matrix and the preset complaint category a is 80, it indicates that the probability value of the complaint text corresponding to the text matrix belonging to the preset complaint category a is eighty percent.
In the embodiment of the present invention, the calculating the relative probability between each text matrix and the preset complaint category includes:
respectively calculating the relative probability between each text matrix and a preset complaint category by using the following relative probability algorithm:
Figure BDA0003237375520000101
wherein F is the relative probability, a is the text matrix, bkIs the kth preset complaint category.
In detail, the complaint texts corresponding to each text matrix can be classified into the preset complaint categories with the maximum relative probability with the text matrix according to the relative probability.
For example, a text matrix a and a text matrix B exist, the preset complaint category includes a category x and a category y, where a relative probability between the text matrix a and the category x is 80, a relative probability between the text matrix a and the category y is 30, a relative probability between the text matrix B and the category x is 50, and a relative probability between the text matrix B and the category y is 90, it can be determined that the complaint text corresponding to the text matrix a belongs to the category x, and the complaint text corresponding to the text matrix B belongs to the text matrix y.
In the embodiment of the present invention, after the complaint category of the complaint text corresponding to each text matrix is determined, the number of the complaint texts in each preset complaint category can be counted, and the proportion weight of each complaint category in the complaint is calculated.
In detail, the calculating a proportion weight of each complaint category in the complaint text according to the complaint category includes:
calculating the proportion weight of each complaint category in the complaint text by using the following weight algorithm:
Figure BDA0003237375520000102
wherein, WjFor the proportional weight of the jth complaint category, MjFor the number of complaint texts in the jth complaint category, N is the total number of all complaint texts.
S5, analyzing the complaint amount according to the complaint amount of each time interval and the characteristic index by using a pre-constructed time sequence prediction model to obtain the complaint amount of a future preset time period, and calculating the complaint amount of each complaint category in the future preset time period according to the proportion weight and the complaint amount of the future preset time period.
In the embodiment of the present invention, the time sequence prediction model is an artificial intelligence model with numerical regression analysis, and the time sequence prediction model includes, but is not limited to, a LightGBM model and an LSTM (Long short-term memory) model.
In the embodiment of the present invention, the analyzing the complaint amount according to the complaint amount and the characteristic index of each time interval by using the pre-established time sequence prediction model to obtain the complaint amount of the future preset time period includes:
collecting the complaint amount and the characteristic index of each time interval as characteristic data;
mapping the characteristic data to a preset characteristic space by using a pre-constructed time sequence detection model, and counting the space coordinate of each characteristic data in the preset characteristic space;
performing curve fitting on the space coordinate to obtain a fitting function;
and substituting the future preset time period as a parameter into the fitting function to obtain the complaint amount of the future preset time period.
In detail, the time sequence detection model may map the feature data to a preset feature space by using a preset mapping function, and further determine a spatial coordinate of each feature data in the preset feature space, where the mapping function includes, but is not limited to, a gaussian function and a map function.
Specifically, the spatial coordinates of each feature data in the preset feature space may be connected by using a smooth curve to obtain a fitting function of the spatial coordinates.
In the embodiment of the invention, after the fitting function is obtained, the future preset time period can be used as a parameter to be substituted into the fitting function for solving, so that the complaint amount of the future preset time period is obtained.
Further, the corresponding complaint amount of each preset complaint type in the complaint amounts can be calculated according to the proportion weight.
For example, the duty ratio weights include: the preset proportion weight of the complaint type A is 0.4, the preset proportion weight of the complaint type B is 0.6, when the complaint amount in the future preset time period is 100, the complaint amount of the preset complaint type A is 40 according to the proportion weight, and the complaint amount of the preset complaint type B is 60.
The method and the device can screen out the operation indexes related to the complaint amount in the service, and predict the complaint amount in the future preset time period based on the complaint amount in the historical preset time period and the screened operation indexes, wherein the numerical value of the complaint amount and the factors of the operation indexes related to the service are considered; and according to the proportion of each type of complaint amount in the history, numerical values of the complaint amounts of different types in a future preset time period are predicted, so that the complaint amounts of different types are predicted, and the accuracy of complaint amount prediction is improved. Therefore, the complaint quantity analysis method based on the category analysis can solve the problem of low precision in product recommendation.
Fig. 4 is a functional block diagram of a complaint amount analysis device based on category analysis according to an embodiment of the present invention.
The complaint amount analysis device 100 based on the category analysis according to the present invention can be incorporated in an electronic apparatus. According to the realized functions, the complaint amount analysis device 100 based on the category analysis may include a complaint amount statistic module 101, an index calculation module 102, a text matrix generation module 103, a weight calculation module 104, and a complaint amount prediction module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the complaint quantity counting module 101 is configured to obtain complaint quantity data of a preset service, and count complaint quantities of each time interval in a plurality of preset time intervals according to the complaint quantity data;
the index calculation module 102 is configured to obtain a plurality of operation indexes of the preset service in each time interval, calculate a correlation coefficient between each operation index and the complaint amount, and collect operation indexes, of which the correlation coefficients are greater than a preset threshold, as feature indexes;
the text matrix generation module 103 is configured to obtain a complaint text of each complaint of the preset service, and perform numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text;
the weight calculation module 104 is configured to calculate a relative probability between each text matrix and a preset complaint category, determine a complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculate a proportion weight of each complaint category in the complaint text according to the complaint category;
the complaint quantity prediction module 105 is configured to perform complaint quantity analysis according to the complaint quantity and the characteristic index of each time interval by using a pre-constructed time sequence prediction model to obtain a complaint quantity of a future preset time period, and calculate the complaint quantity of each complaint category in the future preset time period according to the percentage weight and the complaint quantity of the future preset time period.
In detail, each module in the complaint quantity analysis apparatus 100 based on category analysis according to the embodiment of the present invention adopts the same technical means as the complaint quantity analysis method based on category analysis described in fig. 1 to 3, and can produce the same technical effect, and details are not repeated here.
Fig. 5 is a schematic structural diagram of an electronic device for implementing a complaint quantity analysis method based on category analysis according to an embodiment of the present invention.
The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as a complaint volume analysis program based on category analysis, stored in the memory 11 and executable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory 11 (for example, executing a complaint amount analysis program based on category analysis, etc.), and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of complaint amount analysis programs based on category analysis, etc., but also to temporarily store data that has been output or is to be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
Fig. 5 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The complaint quantity analysis program based on category analysis stored in the memory 11 of the electronic device 1 is a combination of a plurality of instructions, and when running in the processor 10, can realize:
the method comprises the steps of obtaining complaint quantity data of a preset service, and counting the complaint quantity of each time interval in a plurality of preset time intervals according to the complaint quantity data;
acquiring a plurality of operation indexes of the preset service in each time interval, respectively calculating a correlation coefficient between each operation index and the complaint amount, and collecting the operation indexes of which the correlation coefficients are greater than a preset threshold value as characteristic indexes;
obtaining a complaint text of each complaint of the preset service, and performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text;
respectively calculating the relative probability between each text matrix and a preset complaint category, determining the complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculating the proportion weight of each complaint category in the complaint text according to the complaint category;
and analyzing the complaint amount according to the complaint amount of each time interval and the characteristic index by utilizing a pre-constructed time sequence prediction model to obtain the complaint amount of a future preset time period, and calculating the complaint amount of each complaint category in the future preset time period according to the proportion weight and the complaint amount of the future preset time period.
Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
the method comprises the steps of obtaining complaint quantity data of a preset service, and counting the complaint quantity of each time interval in a plurality of preset time intervals according to the complaint quantity data;
acquiring a plurality of operation indexes of the preset service in each time interval, respectively calculating a correlation coefficient between each operation index and the complaint amount, and collecting the operation indexes of which the correlation coefficients are greater than a preset threshold value as characteristic indexes;
obtaining a complaint text of each complaint of the preset service, and performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text;
respectively calculating the relative probability between each text matrix and a preset complaint category, determining the complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculating the proportion weight of each complaint category in the complaint text according to the complaint category;
and analyzing the complaint amount according to the complaint amount of each time interval and the characteristic index by utilizing a pre-constructed time sequence prediction model to obtain the complaint amount of a future preset time period, and calculating the complaint amount of each complaint category in the future preset time period according to the proportion weight and the complaint amount of the future preset time period.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A complaint amount analysis method based on category analysis, characterized by comprising:
the method comprises the steps of obtaining complaint quantity data of a preset service, and counting the complaint quantity of each time interval in a plurality of preset time intervals according to the complaint quantity data;
acquiring a plurality of operation indexes of the preset service in each time interval, respectively calculating a correlation coefficient between each operation index and the complaint amount, and collecting the operation indexes of which the correlation coefficients are greater than a preset threshold value as characteristic indexes;
obtaining a complaint text of each complaint of the preset service, and performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text;
respectively calculating the relative probability between each text matrix and a preset complaint category, determining the complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculating the proportion weight of each complaint category in the complaint text according to the complaint category;
and analyzing the complaint amount according to the complaint amount of each time interval and the characteristic index by utilizing a pre-constructed time sequence prediction model to obtain the complaint amount of a future preset time period, and calculating the complaint amount of each complaint category in the future preset time period according to the proportion weight and the complaint amount of the future preset time period.
2. The method for analyzing the amount of complaint based on the category analysis as claimed in claim 1, wherein said counting the amount of complaint for each of a plurality of preset time intervals based on the complaint amount data comprises:
extracting a time data expression format in the complaint amount data;
compiling preset characters into regular expressions according to the time data expression format;
extracting complaint time of each complaint from the complaint quantity data by using the regular expression;
classifying the complaint quantity data into a plurality of preset time intervals according to the complaint time;
and counting the number of the complaint amount data in each time interval to obtain the complaint amount in each time interval.
3. The method for analyzing the complaint amount based on the category analysis as claimed in claim 1, wherein the calculating of the correlation coefficient between each of the business indexes and the complaint amount, respectively, comprises:
converting the plurality of operation indexes of the preset service in each time interval into index vectors respectively;
selecting one of the time intervals from the preset time intervals one by one, selecting one of the vectors from the index vectors of the selected time interval one by one as a target vector, and calculating the association degree between the target vector and the complaint amount of the selected time interval;
and summing the relevance between the target vector and the complaint amount of each time interval to obtain a correlation coefficient between the operation index corresponding to the target vector and the complaint amount.
4. The method for analyzing the complaint quantity based on the category analysis as claimed in claim 3, wherein the calculating the correlation between the target vector and the complaint quantity of the selected time interval comprises:
calculating the relevance between the target vector and the complaint amount of the selected time interval by using a relevance algorithm as follows:
Figure FDA0003237375510000021
wherein, Px,yIs the degree of correlation between the target vector and the complaint volume for the selected time interval, x is the modulo length of the target vector,
Figure FDA0003237375510000022
is the mean of the modular lengths of all the index vectors, y is the complaint volume in the selected time interval,
Figure FDA0003237375510000023
the average value of the complaint amount in all time intervals is shown.
5. The method for analyzing the complaint volume based on the category analysis as claimed in claim 1, wherein the subjecting the complaint texts to the numerical matrix conversion to obtain the text matrix of each complaint text comprises:
selecting one text from the complaint texts one by one as a target text;
performing word segmentation processing on the target text to obtain text word segmentation;
counting the position information of each text participle in the target text, and carrying out vector coding on the position information to obtain a position vector;
converting each text word into a word vector, and splicing a position code corresponding to each text word and the word vector of the text word into a code vector;
and splicing the coding vectors of all text word segmentation as row vectors to obtain a text matrix of the target text.
6. The complaint quantity analysis method based on category analysis as claimed in claim 5, wherein the step of splicing the code vectors of all text participles as row vectors to obtain a text matrix of the target text comprises:
counting the vector length of each vector in the coding vectors, and determining the maximum vector length as a target length;
utilizing preset parameters to extend the vector length of each vector in the coding vectors to the target length;
and selecting the extended coding vectors as row vectors one by one for splicing to obtain a text matrix of the target text.
7. The method for analyzing the amount of complaint based on the category analysis according to any one of claims 1 to 6, wherein the analyzing the amount of complaint based on the amount of complaint and the characteristic index for each time interval by using a pre-constructed time-series prediction model to obtain the amount of complaint for a preset time period in the future comprises:
collecting the complaint amount and the characteristic index of each time interval as characteristic data;
mapping the characteristic data to a preset characteristic space by using a pre-constructed time sequence detection model, and counting the space coordinate of each characteristic data in the preset characteristic space;
performing curve fitting on the space coordinate to obtain a fitting function;
and substituting the future preset time period as a parameter into the fitting function to obtain the complaint amount of the future preset time period.
8. A complaint amount analysis device based on category analysis, characterized by comprising:
the complaint quantity counting module is used for acquiring complaint quantity data of a preset service and counting the complaint quantity of each time interval in a plurality of preset time intervals according to the complaint quantity data;
the index calculation module is used for acquiring a plurality of operation indexes of the preset service in each time interval, calculating a correlation coefficient between each operation index and the complaint amount respectively, and collecting the operation indexes of which the correlation coefficients are larger than a preset threshold value as characteristic indexes;
the text matrix generation module is used for acquiring the complaint text of each complaint of the preset service, and performing numerical matrix conversion on the complaint text to obtain a text matrix of each complaint text;
the weight calculation module is used for respectively calculating the relative probability between each text matrix and a preset complaint category, determining the complaint category of the complaint text corresponding to each text matrix according to the relative probability, and calculating the proportion weight of each complaint category in the complaint text according to the complaint category;
and the complaint quantity prediction module is used for analyzing the complaint quantity according to the complaint quantity of each time interval and the characteristic index by utilizing a pre-constructed time sequence prediction model to obtain the complaint quantity of a future preset time period, and calculating the complaint quantity of each complaint category in the future preset time period according to the percentage weight and the complaint quantity of the future preset time period.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the complaint volume analysis method based on the category analysis of any one of claims 1-7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the complaint quantity analysis method based on the category analysis of any one of claims 1 to 7.
CN202111006941.2A 2021-08-30 2021-08-30 Complaint volume analysis method, device, equipment and storage medium based on category analysis Active CN113704407B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111006941.2A CN113704407B (en) 2021-08-30 2021-08-30 Complaint volume analysis method, device, equipment and storage medium based on category analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111006941.2A CN113704407B (en) 2021-08-30 2021-08-30 Complaint volume analysis method, device, equipment and storage medium based on category analysis

Publications (2)

Publication Number Publication Date
CN113704407A true CN113704407A (en) 2021-11-26
CN113704407B CN113704407B (en) 2023-08-25

Family

ID=78657040

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111006941.2A Active CN113704407B (en) 2021-08-30 2021-08-30 Complaint volume analysis method, device, equipment and storage medium based on category analysis

Country Status (1)

Country Link
CN (1) CN113704407B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115134260A (en) * 2022-07-12 2022-09-30 北京东土拓明科技有限公司 User perception improving method and device, computing equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050010541A1 (en) * 2003-07-07 2005-01-13 Rietman Edward A. Method and system for computing categories and prediction of categories utilizing time-series classification data
JP5933863B1 (en) * 2015-05-22 2016-06-15 株式会社Ｕｂｉｃ Data analysis system, control method, control program, and recording medium
CN106971310A (en) * 2017-03-16 2017-07-21 国家电网公司 A kind of customer complaint quantitative forecasting technique and device
CN110347840A (en) * 2019-07-18 2019-10-18 携程计算机技术（上海）有限公司 Complain prediction technique, system, equipment and the storage medium of text categories
CN112699099A (en) * 2020-12-30 2021-04-23 广州杰赛科技股份有限公司 Method, device and storage medium for expanding user complaint database

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050010541A1 (en) * 2003-07-07 2005-01-13 Rietman Edward A. Method and system for computing categories and prediction of categories utilizing time-series classification data
JP5933863B1 (en) * 2015-05-22 2016-06-15 株式会社Ｕｂｉｃ Data analysis system, control method, control program, and recording medium
CN106971310A (en) * 2017-03-16 2017-07-21 国家电网公司 A kind of customer complaint quantitative forecasting technique and device
CN110347840A (en) * 2019-07-18 2019-10-18 携程计算机技术（上海）有限公司 Complain prediction technique, system, equipment and the storage medium of text categories
CN112699099A (en) * 2020-12-30 2021-04-23 广州杰赛科技股份有限公司 Method, device and storage medium for expanding user complaint database

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115134260A (en) * 2022-07-12 2022-09-30 北京东土拓明科技有限公司 User perception improving method and device, computing equipment and storage medium

Also Published As

Publication number Publication date
CN113704407B (en) 2023-08-25

Similar Documents

Publication Publication Date Title
CN115391669B (en) Intelligent recommendation method and device and electronic equipment
CN115423535B (en) Product purchasing method, device, equipment and medium based on market priori big data
CN114612194A (en) Product recommendation method and device, electronic equipment and storage medium
CN113516417A (en) Service evaluation method and device based on intelligent modeling, electronic equipment and medium
CN114663198A (en) Product recommendation method, device and equipment based on user portrait and storage medium
CN113868529A (en) Knowledge recommendation method and device, electronic equipment and readable storage medium
CN114399212A (en) Ecological environment quality evaluation method and device, electronic equipment and storage medium
CN114398560B (en) Marketing interface setting method, device, equipment and medium based on WEB platform
CN113706322A (en) Service distribution method, device, equipment and storage medium based on data analysis
CN114781832A (en) Course recommendation method and device, electronic equipment and storage medium
CN114186132A (en) Information recommendation method and device, electronic equipment and storage medium
CN113837631B (en) Employee evaluation method and device, electronic equipment and readable storage medium
CN113627160B (en) Text error correction method and device, electronic equipment and storage medium
CN113704407A (en) Complaint amount analysis method, device, equipment and storage medium based on category analysis
CN114708073B (en) Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium
CN113139129B (en) Virtual reading trajectory graph generation method and device, electronic equipment and storage medium
CN115641186A (en) Intelligent analysis method, device and equipment for preference of live broadcast product and storage medium
CN112561500B (en) Salary data generation method, device, equipment and medium based on user data
CN114187096A (en) Risk assessment method, device and equipment based on user portrait and storage medium
CN113657546A (en) Information classification method and device, electronic equipment and readable storage medium
CN113706204B (en) Deep learning-based rights issuing method, device, equipment and storage medium
CN113793037B (en) Service distribution method, device, equipment and storage medium based on data analysis
CN116991364B (en) Software development system management method based on big data
CN113706019B (en) Service capability analysis method, device, equipment and medium based on multidimensional data
CN114723488B (en) Course recommendation method and device, electronic equipment and storage medium

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