User classification method and device, computer equipment, storage medium and program product

By constructing a multi-dimensional evaluation index system and fuzzy hierarchical analysis method, combining customer group classification model, using convolutional neural network and gated recurrent unit network, the user group is classified, and the problem of long classification time and inaccurate results in traditional methods is solved. , realizes efficient and accurate classification of user groups.

CN118940084APending Publication Date: 2024-11-12BANK OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410929790.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-11
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Traditional methods take a lot of time to classify user groups and the results are not accurate and comprehensive enough to effectively meet the needs of financial institutions for subdividing user groups and personalized service.

Method used

The user evaluation data is obtained by using a multi-dimensional evaluation index system and fuzzy hierarchical analysis method, and the user group is classified through the customer group classification model, and the convolutional neural network and the gated recurrent unit network are used to classify the user group.

Benefits of technology

It realizes comprehensive and accurate classification of user groups, ensures the objectivity, comprehensiveness, accuracy and feasibility of user evaluation data, and improves the accuracy of the classification process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940084A_ABST
    Figure CN118940084A_ABST
Patent Text Reader

Abstract

The invention relates to a user classification method and device, computer equipment, a storage medium and a program product which can be applied to the technical field of finance and other technical fields. The method comprises the following steps: constructing a multi-dimensional evaluation index system for a target product according to product characteristics of the target product; based on a fuzzy analytic hierarchy process, according to the multi-dimensional evaluation index system, obtaining user evaluation data of each user in the user group of the target product on the target product; and based on a customer group classification model, classifying the user group according to the user evaluation data. By adopting the method, the users in the user group can be comprehensively and accurately classified.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a user classification method, apparatus, computer equipment, storage medium and program product, which can be applied to the field of financial technology and other technical fields. Background Art

[0002] With the rapid development of the financial industry, financial institutions have gradually acquired a large and complex user group. In order to manage the user group in an orderly manner and provide personalized services, as well as to improve service quality, it is necessary to segment the user group.

[0003] At present, the traditional method classifies users in a user group according to their attributes. However, this classification method requires a lot of time to analyze the basic attributes of customers, and the classification results obtained are not accurate and comprehensive enough. Summary of the invention

[0004] Based on this, it is necessary to provide a user classification method, apparatus, computer equipment, storage medium and program product to address the above technical issues, which can comprehensively and accurately classify users in a user group.

[0005] In a first aspect, the present application provides a user classification method, comprising:

[0006] According to the product characteristics of the target product, a multi-dimensional evaluation index system for the target product is constructed;

[0007] Based on the fuzzy analytic hierarchy process, according to the multidimensional evaluation index system, obtaining user evaluation data of the target product by each user in the user group of the target product;

[0008] Based on the customer group classification model, the user group is classified according to the user evaluation data.

[0009] In one embodiment, the multi-dimensional evaluation index system for the target product is constructed according to the product characteristics of the target product, including:

[0010] Determine, according to the product characteristics of the target product, each user evaluation index of the target product and the evaluation target corresponding to each user evaluation index;

[0011] According to each user evaluation index and the corresponding evaluation target, a multi-dimensional evaluation index system for the target product is constructed.

[0012] In one embodiment, the method of obtaining user evaluation data of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system based on the fuzzy hierarchical analysis method includes:

[0013] According to the multidimensional evaluation index system, obtaining the user evaluation results of the target product by each user in the user group of the target product; wherein the user evaluation results include the evaluation values ​​corresponding to each user evaluation index in the multidimensional evaluation index system;

[0014] Based on the fuzzy hierarchical analysis method, the user evaluation data of the target product by each user in the user group of the target product is determined according to the user evaluation results.

[0015] In one embodiment, obtaining the user evaluation results of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system includes:

[0016] Generate evaluation collection information for a target product according to the multi-dimensional evaluation index system, and send the evaluation collection information to each user in a user group of the target product;

[0017] Receive user evaluation results for the target product fed back by each user in the user group.

[0018] In one embodiment, the method of determining the user evaluation data of the target product by each user in the user group of the target product according to the user evaluation result based on the fuzzy hierarchical analysis method includes:

[0019] Determining the importance of each user evaluation indicator according to the evaluation value corresponding to each user evaluation indicator in the user evaluation result;

[0020] According to the importance of each user evaluation index, a fuzzy judgment matrix of the user group is constructed;

[0021] Based on the fuzzy analytic hierarchy process, the fuzzy judgment matrix is ​​converted into a fuzzy consistency matrix;

[0022] According to the fuzzy consistency matrix, user evaluation data of the target product by each user in the user group of the target product is determined.

[0023] In one embodiment, the user group is classified based on the customer group classification model according to the user evaluation data, including:

[0024] Inputting the user evaluation data into a convolutional neural network of a customer group classification model to obtain a spatial feature vector of the user evaluation data;

[0025] The spatial feature vector is input into the gated recurrent unit network of the customer group classification model to obtain the classification result of each user in the user group.

[0026] In a second aspect, the present application further provides a user classification device, including:

[0027] A system construction module, used to construct a multi-dimensional evaluation index system for the target product according to the product characteristics of the target product;

[0028] A data acquisition module, used for acquiring user evaluation data of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system based on the fuzzy hierarchical analysis method;

[0029] The user classification module is used to classify the user group based on the customer group classification model and according to the user evaluation data.

[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] According to the product characteristics of the target product, a multi-dimensional evaluation index system for the target product is constructed;

[0032] Based on the fuzzy analytic hierarchy process, according to the multidimensional evaluation index system, obtaining user evaluation data of the target product by each user in the user group of the target product;

[0033] Based on the customer group classification model, the user group is classified according to the user evaluation data.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0035] According to the product characteristics of the target product, a multi-dimensional evaluation index system for the target product is constructed;

[0036] Based on the fuzzy analytic hierarchy process, according to the multidimensional evaluation index system, obtaining user evaluation data of the target product by each user in the user group of the target product;

[0037] Based on the customer group classification model, the user group is classified according to the user evaluation data.

[0038] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0039] According to the product characteristics of the target product, a multi-dimensional evaluation index system for the target product is constructed;

[0040] Based on the fuzzy analytic hierarchy process, according to the multidimensional evaluation index system, obtaining user evaluation data of the target product by each user in the user group of the target product;

[0041] Based on the customer group classification model, the user group is classified according to the user evaluation data.

[0042] The above user classification method, device, computer equipment, storage medium and program product construct a multidimensional evaluation index system for the target product according to the product characteristics of the target product, and based on the fuzzy hierarchical analysis method, obtain the user evaluation data of the target product from each user in the user group of the target product according to the multidimensional evaluation index system; further, based on the customer group classification model, classify the user group according to the user evaluation data. The above scheme ensures the objectivity, comprehensiveness, accuracy and feasibility of the obtained user evaluation data by constructing a multidimensional evaluation index system for the target product, and based on the multidimensional evaluation index system and the fuzzy hierarchical analysis method; in addition, the introduction of the customer group classification model ensures the accuracy of the user group classification process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] FIG1 is a schematic diagram of a flow chart of a user classification method in one embodiment;

[0045] FIG2 is a schematic diagram of a process for constructing a multidimensional evaluation index system in one embodiment;

[0046] FIG3 is a schematic diagram of a process for obtaining user evaluation data in one embodiment;

[0047] FIG4 is a schematic diagram of a process for obtaining user evaluation results in one embodiment;

[0048] FIG5 is a schematic diagram of a process for obtaining user evaluation data in another embodiment;

[0049] FIG6 is a schematic diagram of a process for classifying user groups according to an embodiment;

[0050] FIG7 is a schematic diagram of a flow chart of a user classification method in another embodiment;

[0051] FIG8 is a structural block diagram of a user classification device in one embodiment;

[0052] FIG. 9 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] The user classification method provided in the embodiment of the present application can be applied in an application environment for classifying user groups of financial institutions. The user classification method provided in the embodiment of the present application can be executed by a computer device, which can be a server or a terminal with powerful computing capabilities. In one embodiment, as shown in FIG1 , a user classification method is provided, which is described by taking the application of the method to a server as an example, and specifically includes the following steps:

[0055] S101, construct a multi-dimensional evaluation index system for the target product according to the product characteristics of the target product.

[0056] The target product can be any financial product of a financial institution. Product characteristics characterize the characteristics of the target product. If the target product is an application of a financial institution, the product characteristics can be home page rendering time, average response time, and system stability. The multidimensional evaluation index system is a multidimensional system constructed by user evaluation indicators of the target product; in the embodiment of the present application, the user evaluation indicators can be product satisfaction, recommendation level, stability, etc.

[0057] Optionally, user evaluation indicators for the target product may be selected according to the product characteristics of the target product and based on expert experience; it should be noted that user evaluation indicators should also pay more attention to individual user satisfaction and the degree of external recommendation, and may also add evaluation indicators such as satisfaction and ease of use.

[0058] Furthermore, based on the selected user evaluation indicators, a multi-dimensional evaluation indicator system for the target product is constructed.

[0059] S102, based on the fuzzy analytic hierarchy process and the multi-dimensional evaluation index system, obtaining user evaluation data of the target product from each user in the user group of the target product.

[0060] Among them, the user evaluation data is data generated based on the user's evaluation of the target product; in the embodiment of the present application, the user evaluation data includes the evaluation data of each user, and the user evaluation data is presented in the form of a matrix, wherein the evaluation data of each user constitutes a row in the matrix.

[0061] Optionally, based on a multidimensional evaluation index system, evaluation information of the target product by each user in the user group of the target product can be obtained; further, based on the fuzzy hierarchical analysis method, the evaluation information can be analyzed to generate user evaluation data of the target product by each user in the user group of the target product.

[0062] S103, based on the customer group classification model and according to the user evaluation data, classify the user groups.

[0063] Among them, the customer group classification model is a model for classifying each user in a user group; in an embodiment of the present application, the customer group classification model is a combination model of a convolutional neural network and a gated recurrent unit network.

[0064] Optionally, the user evaluation data is input into a customer group classification model so that the convolutional neural network and the gated recurrent unit network in the customer group classification model perform computational analysis on the user evaluation data, classify the user groups, and output the classification results for each user in the user group.

[0065] In the above user classification method, a multidimensional evaluation index system for the target product is constructed according to the product characteristics of the target product, and based on the fuzzy hierarchical analysis method, the user evaluation data of the target product by each user in the user group of the target product is obtained according to the multidimensional evaluation index system; further, based on the customer group classification model, the user group is classified according to the user evaluation data. The above scheme ensures the objectivity, comprehensiveness, accuracy and feasibility of the obtained user evaluation data by constructing a multidimensional evaluation index system for the target product, and based on the multidimensional evaluation index system and the fuzzy hierarchical analysis method; in addition, the introduction of the customer group classification model ensures the accuracy of the user group classification process.

[0066] Optionally, in order to ensure the accuracy of the constructed multidimensional evaluation index system, in one embodiment, as shown in FIG2 , a method for constructing a multidimensional evaluation index system is provided, which specifically includes the following steps:

[0067] S201, determining each user evaluation index of the target product and an evaluation target corresponding to each user evaluation index according to product characteristics of the target product.

[0068] Among them, the user evaluation index is an index for measuring the user's evaluation of the target product; and the evaluation target is the target for evaluating the user evaluation index.

[0069] Optionally, the product characteristics of the target product may be analyzed to determine user evaluation indicators that can evaluate the target product, and based on expert experience, the evaluation target of each user evaluation indicator may be determined.

[0070] S202: Construct a multi-dimensional evaluation index system for the target product based on each user evaluation index and the corresponding evaluation target.

[0071] Optionally, a tool or model may be built based on the indicator system to construct a multi-dimensional evaluation indicator system for the target product according to each user's evaluation indicator and the corresponding evaluation target.

[0072] In this embodiment, by introducing various user evaluation indicators of the target product and the evaluation targets corresponding to the various user evaluation indicators, the comprehensiveness and accuracy of the multi-dimensional evaluation indicator system constructed for the target product are guaranteed.

[0073] Optionally, in order to ensure the accuracy of the acquired user evaluation data, in one embodiment, as shown in FIG3 , a method for acquiring user evaluation data is provided, which specifically includes the following steps:

[0074] S301, obtaining user evaluation results of the target product from each user in the user group of the target product according to the multi-dimensional evaluation index system.

[0075] The user evaluation results include the evaluation values ​​corresponding to each user evaluation indicator in the multi-dimensional evaluation indicator system.

[0076] Optionally, based on the multidimensional evaluation index system, the evaluation results of each user in the user group of the target product for each user evaluation index in the multidimensional evaluation index system can be collected, and the collected evaluation results can be used as the user evaluation results of each user in the user group of the target product for the target product.

[0077] S302, based on the fuzzy analytic hierarchy process and according to the user evaluation results, determining the user evaluation data of the target product by each user in the user group of the target product.

[0078] Optionally, based on the fuzzy analytic hierarchy process, a statistical analysis is performed on the user evaluation results to obtain the user evaluation data of the target product by each user in the user group of the target product.

[0079] In this embodiment, by introducing the user evaluation results of the target product by each user in the user group of the target product and based on the fuzzy hierarchical analysis method, the accuracy and comprehensiveness of the obtained user evaluation data are guaranteed.

[0080] Optionally, in order to ensure the accuracy of the obtained user evaluation results, based on the above embodiment, in one embodiment, as shown in FIG4 , a method for obtaining user evaluation results is provided, which specifically includes the following steps:

[0081] S401, generating evaluation collection information for a target product according to a multi-dimensional evaluation index system, and sending the evaluation collection information to each user in a user group of the target product.

[0082] The evaluation collection information is the collection information for evaluating each user evaluation index in the multi-dimensional evaluation index system; in the embodiment of the present application, the evaluation collection information can be presented in the form of a questionnaire.

[0083] Optionally, based on a multi-dimensional evaluation index system, a questionnaire can be generated according to the evaluation indicators of each user and the corresponding evaluation targets, and the generated questionnaire can be used as evaluation collection information for the target product; further, the evaluation collection information can be sent to the terminal held by each user in the user group in the form of text messages, and can also be sent to the terminal held by each user in the user group through an application under a financial institution, so that the users can fill in and provide feedback on the evaluation collection information.

[0084] S402, receiving user evaluation results for the target product fed back by each user in the user group.

[0085] Optionally, after the user fills in and provides feedback on the evaluation collection information, the server can obtain the user evaluation results for the target product provided by each user in the user group.

[0086] In this embodiment, by introducing the evaluation collection information and sending the evaluation collection information to each user, the accuracy and comprehensiveness of the determined user evaluation results are guaranteed, and a method for obtaining the user evaluation results is provided.

[0087] Optionally, in order to ensure the accuracy of the acquired user evaluation data, in one embodiment, as shown in FIG5 , a method for acquiring user evaluation data is provided, which specifically includes the following steps:

[0088] S501, determining the importance of each user evaluation indicator according to the evaluation value corresponding to each user evaluation indicator in the user evaluation result.

[0089] Optionally, the evaluation values ​​corresponding to the user evaluation indicators in the user evaluation results may be compared and analyzed in pairs to obtain the importance between the user evaluation indicators. Exemplarily, the importance between the user evaluation indicators may be represented by a numerical value, such as a numerical value between 0.1 and 0.9, where a higher numerical value indicates a greater importance; and correspondingly, a lower numerical value indicates a lower importance.

[0090] S502: construct a fuzzy judgment matrix of the user group according to the importance of each user evaluation index.

[0091] Optionally, according to the importance of each user evaluation index, each user evaluation index can be used as a row and a column, and the importance values ​​of each user evaluation index can be filled in at the corresponding position to construct a fuzzy judgment matrix of the user group.

[0092] S503, based on the fuzzy analytic hierarchy process, converting the fuzzy judgment matrix into a fuzzy consistency matrix.

[0093] Optionally, based on the hierarchical analysis method, the fuzzy judgment matrix is ​​subjected to consistency check, that is, the fuzzy consistency processing is performed on it, and after the processing is completed, the fuzzy consistency matrix can be obtained.

[0094] S504: Determine user evaluation data of the target product by each user in the user group of the target product according to the fuzzy consistency matrix.

[0095] Optionally, according to the fuzzy consistency matrix, the weight of each user evaluation index is calculated layer by layer, and according to the weight of each user evaluation index, the user evaluation data of the target product by each user in the user group of the target product is determined.

[0096] In this embodiment, a method for acquiring user evaluation data is provided by introducing a fuzzy judgment matrix and a fuzzy consistency matrix, thereby ensuring the accuracy and comprehensiveness of the acquired user evaluation data.

[0097] Optionally, in order to ensure the accuracy of the classification result, in one embodiment, as shown in FIG6 , a method for classifying user groups is provided, which specifically includes the following steps:

[0098] S601, input the user evaluation data into the convolutional neural network of the customer group classification model to obtain the spatial feature vector of the user evaluation data.

[0099] Among them, the convolutional neural network is used to extract feature vectors from user evaluation data; in an embodiment of the present application, the convolutional neural network includes a first convolutional layer, a second convolutional layer and a fully connected layer.

[0100] Optionally, the user evaluation data is input into the convolutional neural network of the customer group classification model, so that the first convolutional layer and the second convolutional layer of the convolutional neural network extract abstract features of the user evaluation data, and the features extracted by the first convolutional layer and the second convolutional layer are integrated through the fully connected layer to obtain the spatial feature vector of the user evaluation data.

[0101] It should be noted that the activation function of the first convolutional layer is the ReLU function; the activation function of the second convolutional layer is the SwiGLU function; and the activation function of the fully connected layer is the SwiGLU function.

[0102] S602, inputting the spatial feature vector into the gated recurrent unit network of the customer group classification model to obtain the classification result of each user in the user group.

[0103] Optionally, the spatial feature vector is input into a gated recurrent unit network of a customer group classification model, so that the gated recurrent unit network uses the spatial feature extraction vector to obtain a classification result for each user in the user group.

[0104] It should be noted that the activation function of the gated recurrent unit network is the TANH function.

[0105] In this embodiment, by introducing a convolutional neural network and a gated recurrent unit network, and performing feature extraction through the convolutional neural network, the accuracy of the extracted features is ensured; further, by using the gated recurrent unit network, the accuracy of the determined classification results is ensured.

[0106] FIG7 is a flow chart of a user classification method in another embodiment. Based on the above embodiment, this embodiment provides an optional example of a user classification method. In conjunction with FIG7 , the specific implementation process is as follows:

[0107] S701, determining each user evaluation index of the target product and an evaluation target corresponding to each user evaluation index according to the product characteristics of the target product.

[0108] S702: Construct a multi-dimensional evaluation index system for the target product according to each user evaluation index and the corresponding evaluation target.

[0109] S703, obtaining user evaluation results of the target product from each user in the user group of the target product according to the multi-dimensional evaluation index system.

[0110] The user evaluation results include the evaluation values ​​corresponding to each user evaluation indicator in the multi-dimensional evaluation indicator system.

[0111] Optionally, based on the multi-dimensional evaluation index system, evaluation collection information for the target product is generated, and the evaluation collection information is sent to each user in the user group of the target product; and user evaluation results for the target product fed back by each user in the user group are received.

[0112] S704, determining the importance of each user evaluation indicator according to the evaluation value corresponding to each user evaluation indicator in the user evaluation result.

[0113] S705: construct a fuzzy judgment matrix of the user group according to the importance of each user evaluation index.

[0114] S706, based on the fuzzy analytic hierarchy process, converting the fuzzy judgment matrix into a fuzzy consistency matrix.

[0115] S707, determining user evaluation data of the target product by each user in the user group of the target product according to the fuzzy consistency matrix.

[0116] S708, input the user evaluation data into the convolutional neural network of the customer group classification model to obtain the spatial feature vector of the user evaluation data.

[0117] S709, inputting the spatial feature vector into the gated recurrent unit network of the customer group classification model to obtain the classification result of each user in the user group.

[0118] The specific process of the above S701-S709 can be found in the description of the above method embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0119] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0120] Based on the same inventive concept, the embodiment of the present application also provides a user classification device for implementing the user classification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more user classification device embodiments provided below can refer to the limitations on the user classification method above, and will not be repeated here.

[0121] In one embodiment, as shown in FIG8 , a user classification device 80 is provided, comprising: a system construction module 10, a data acquisition module 20 and a user classification module 30, wherein:

[0122] The system construction module 10 is used to construct a multi-dimensional evaluation index system for the target product according to the product characteristics of the target product.

[0123] The data acquisition module 20 is used to acquire user evaluation data of the target product from each user in the user group of the target product based on the fuzzy hierarchical analysis method and the multi-dimensional evaluation index system.

[0124] The user classification module 30 is used to classify user groups based on the customer group classification model and according to user evaluation data.

[0125] The user classification device constructs a multidimensional evaluation index system for the target product according to the product characteristics of the target product, and obtains the user evaluation data of the target product from each user in the user group of the target product based on the fuzzy hierarchical analysis method and the multidimensional evaluation index system; further, based on the customer group classification model, the user group is classified according to the user evaluation data. The above scheme ensures the objectivity, comprehensiveness, accuracy and feasibility of the obtained user evaluation data by constructing a multidimensional evaluation index system for the target product and based on the multidimensional evaluation index system and the fuzzy hierarchical analysis method; in addition, the introduction of the customer group classification model ensures the accuracy of the user group classification process.

[0126] In one embodiment, the system building module 10 is specifically used for:

[0127] According to the product characteristics of the target product, determine each user evaluation index of the target product and the evaluation target corresponding to each user evaluation index; according to each user evaluation index and the corresponding evaluation target, build a multidimensional evaluation index system for the target product.

[0128] In one embodiment, the data acquisition module 20 includes:

[0129] The result acquisition unit is used to acquire the user evaluation results of the target product by each user in the user group of the target product according to the multidimensional evaluation index system; wherein the user evaluation results include the evaluation values ​​corresponding to each user evaluation index in the multidimensional evaluation index system.

[0130] The data acquisition unit is used to determine the user evaluation data of the target product by each user in the user group of the target product according to the user evaluation results based on the fuzzy hierarchical analysis method.

[0131] In one embodiment, the result acquisition unit is specifically used for:

[0132] Based on the multi-dimensional evaluation index system, evaluation collection information for the target product is generated, and the evaluation collection information is sent to each user in the user group of the target product; and user evaluation results for the target product fed back by each user in the user group are received.

[0133] In one embodiment, the data acquisition unit is specifically used for:

[0134] According to the evaluation value corresponding to each user evaluation indicator in the user evaluation results, the importance of each user evaluation indicator is determined; according to the importance of each user evaluation indicator, a fuzzy judgment matrix of the user group is constructed; based on the fuzzy hierarchical analysis method, the fuzzy judgment matrix is ​​converted into a fuzzy consistency matrix; according to the fuzzy consistency matrix, the user evaluation data of each user in the user group of the target product on the target product is determined.

[0135] In one embodiment, the user classification module 30 is specifically used for:

[0136] The user evaluation data is input into the convolutional neural network of the customer group classification model to obtain the spatial feature vector of the user evaluation data; the spatial feature vector is input into the gated recurrent unit network of the customer group classification model to obtain the classification results of each user in the user group.

[0137] Each module in the above user classification device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0138] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a user classification method is implemented.

[0139] Those skilled in the art will understand that the structure shown in FIG. 9 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0140] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0141] According to the product characteristics of the target product, a multi-dimensional evaluation index system is constructed for the target product;

[0142] Based on the fuzzy hierarchical analysis method and the multi-dimensional evaluation index system, the user evaluation data of the target product by each user in the user group of the target product is obtained;

[0143] Based on the customer classification model, user groups are classified according to user evaluation data.

[0144] In one embodiment, when the processor executes the computer program to construct a multi-dimensional evaluation index system for the target product according to the product characteristics of the target product, the processor further implements the following steps:

[0145] According to the product characteristics of the target product, determine each user evaluation index of the target product and the evaluation target corresponding to each user evaluation index; according to each user evaluation index and the corresponding evaluation target, build a multidimensional evaluation index system for the target product.

[0146] In one embodiment, when the processor executes the computer program to obtain user evaluation data of the target product by each user in the user group of the target product based on the fuzzy hierarchical analysis method and the multi-dimensional evaluation index system, the following steps are also implemented:

[0147] According to the multidimensional evaluation index system, the user evaluation results of the target product by each user in the user group of the target product are obtained; wherein the user evaluation results include the evaluation values ​​corresponding to each user evaluation index in the multidimensional evaluation index system; based on the fuzzy hierarchical analysis method, the user evaluation data of the target product by each user in the user group of the target product is determined according to the user evaluation results.

[0148] In one embodiment, when the processor executes the computer program to obtain the user evaluation results of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system, the processor further implements the following steps:

[0149] Based on the multi-dimensional evaluation index system, evaluation collection information for the target product is generated, and the evaluation collection information is sent to each user in the user group of the target product; and user evaluation results for the target product fed back by each user in the user group are received.

[0150] In one embodiment, when the processor executes the computer program to determine the user evaluation data of the target product by each user in the user group of the target product based on the fuzzy hierarchical analysis method according to the user evaluation results, the processor further implements the following steps:

[0151] According to the evaluation value corresponding to each user evaluation indicator in the user evaluation results, the importance of each user evaluation indicator is determined; according to the importance of each user evaluation indicator, a fuzzy judgment matrix of the user group is constructed; based on the fuzzy hierarchical analysis method, the fuzzy judgment matrix is ​​converted into a fuzzy consistency matrix; according to the fuzzy consistency matrix, the user evaluation data of each user in the user group of the target product on the target product is determined.

[0152] In one embodiment, when the processor executes the computer program to classify the user groups based on the customer group classification model and the user evaluation data, the following steps are also implemented:

[0153] The user evaluation data is input into the convolutional neural network of the customer group classification model to obtain the spatial feature vector of the user evaluation data; the spatial feature vector is input into the gated recurrent unit network of the customer group classification model to obtain the classification results of each user in the user group.

[0154] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0155] According to the product characteristics of the target product, a multi-dimensional evaluation index system is constructed for the target product;

[0156] Based on the fuzzy hierarchical analysis method and the multi-dimensional evaluation index system, the user evaluation data of the target product by each user in the user group of the target product is obtained;

[0157] Based on the customer classification model, user groups are classified according to user evaluation data.

[0158] In one embodiment, when the processor executes the computer program to construct a multi-dimensional evaluation index system for the target product according to the product characteristics of the target product, the processor further implements the following steps:

[0159] According to the product characteristics of the target product, determine each user evaluation index of the target product and the evaluation target corresponding to each user evaluation index; according to each user evaluation index and the corresponding evaluation target, build a multidimensional evaluation index system for the target product.

[0160] In one embodiment, when the processor executes the computer program to obtain user evaluation data of the target product by each user in the user group of the target product based on the fuzzy hierarchical analysis method and the multi-dimensional evaluation index system, the following steps are also implemented:

[0161] According to the multidimensional evaluation index system, the user evaluation results of the target product by each user in the user group of the target product are obtained; wherein the user evaluation results include the evaluation values ​​corresponding to each user evaluation index in the multidimensional evaluation index system; based on the fuzzy hierarchical analysis method, the user evaluation data of the target product by each user in the user group of the target product is determined according to the user evaluation results.

[0162] In one embodiment, when the processor executes the computer program to obtain the user evaluation results of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system, the processor further implements the following steps:

[0163] Based on the multi-dimensional evaluation index system, evaluation collection information for the target product is generated, and the evaluation collection information is sent to each user in the user group of the target product; and user evaluation results for the target product fed back by each user in the user group are received.

[0164] In one embodiment, when the processor executes the computer program to determine the user evaluation data of the target product by each user in the user group of the target product based on the fuzzy hierarchical analysis method according to the user evaluation results, the processor further implements the following steps:

[0165] According to the evaluation value corresponding to each user evaluation indicator in the user evaluation results, the importance of each user evaluation indicator is determined; according to the importance of each user evaluation indicator, a fuzzy judgment matrix of the user group is constructed; based on the fuzzy hierarchical analysis method, the fuzzy judgment matrix is ​​converted into a fuzzy consistency matrix; according to the fuzzy consistency matrix, the user evaluation data of each user in the user group of the target product on the target product is determined.

[0166] In one embodiment, when the processor executes the computer program to classify the user groups based on the customer group classification model and the user evaluation data, the following steps are also implemented:

[0167] The user evaluation data is input into the convolutional neural network of the customer group classification model to obtain the spatial feature vector of the user evaluation data; the spatial feature vector is input into the gated recurrent unit network of the customer group classification model to obtain the classification results of each user in the user group.

[0168] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0169] According to the product characteristics of the target product, a multi-dimensional evaluation index system is constructed for the target product;

[0170] Based on the fuzzy hierarchical analysis method and the multi-dimensional evaluation index system, the user evaluation data of the target product by each user in the user group of the target product is obtained;

[0171] Based on the customer classification model, user groups are classified according to user evaluation data.

[0172] In one embodiment, when the processor executes the computer program to construct a multi-dimensional evaluation index system for the target product according to the product characteristics of the target product, the processor further implements the following steps:

[0173] According to the product characteristics of the target product, determine each user evaluation index of the target product and the evaluation target corresponding to each user evaluation index; according to each user evaluation index and the corresponding evaluation target, build a multidimensional evaluation index system for the target product.

[0174] In one embodiment, when the processor executes the computer program to obtain user evaluation data of the target product by each user in the user group of the target product based on the fuzzy hierarchical analysis method and the multi-dimensional evaluation index system, the following steps are also implemented:

[0175] According to the multidimensional evaluation index system, the user evaluation results of the target product by each user in the user group of the target product are obtained; wherein the user evaluation results include the evaluation values ​​corresponding to each user evaluation index in the multidimensional evaluation index system; based on the fuzzy hierarchical analysis method, the user evaluation data of the target product by each user in the user group of the target product is determined according to the user evaluation results.

[0176] In one embodiment, when the processor executes the computer program to obtain the user evaluation results of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system, the processor further implements the following steps:

[0177] Based on the multi-dimensional evaluation index system, evaluation collection information for the target product is generated, and the evaluation collection information is sent to each user in the user group of the target product; and user evaluation results for the target product fed back by each user in the user group are received.

[0178] In one embodiment, when the processor executes the computer program to determine the user evaluation data of the target product by each user in the user group of the target product based on the fuzzy hierarchical analysis method according to the user evaluation results, the processor further implements the following steps:

[0179] According to the evaluation value corresponding to each user evaluation indicator in the user evaluation results, the importance of each user evaluation indicator is determined; according to the importance of each user evaluation indicator, a fuzzy judgment matrix of the user group is constructed; based on the fuzzy hierarchical analysis method, the fuzzy judgment matrix is ​​converted into a fuzzy consistency matrix; according to the fuzzy consistency matrix, the user evaluation data of each user in the user group of the target product on the target product is determined.

[0180] In one embodiment, when the processor executes the computer program to classify the user groups based on the customer group classification model and the user evaluation data, the following steps are also implemented:

[0181] The user evaluation data is input into the convolutional neural network of the customer group classification model to obtain the spatial feature vector of the user evaluation data; the spatial feature vector is input into the gated recurrent unit network of the customer group classification model to obtain the classification results of each user in the user group.

[0182] It should be noted that the user information (including but not limited to user evaluation data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0183] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0184] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A user classification method, characterized in that: The method comprises: According to the product characteristics of the target product, a multi-dimensional evaluation index system for the target product is constructed; Based on the fuzzy analytic hierarchy process, according to the multidimensional evaluation index system, obtaining user evaluation data of the target product by each user in the user group of the target product; Based on the customer group classification model, the user group is classified according to the user evaluation data.

2. The method according to claim 1, characterized in that According to the product characteristics of the target product, a multi-dimensional evaluation index system for the target product is constructed, including: Determine, according to the product characteristics of the target product, each user evaluation index of the target product and the evaluation target corresponding to each user evaluation index; According to each user evaluation index and the corresponding evaluation target, a multi-dimensional evaluation index system for the target product is constructed.

3. The method according to claim 1, characterized in that The method of obtaining user evaluation data of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system based on the fuzzy hierarchical analysis method includes: According to the multidimensional evaluation index system, obtaining the user evaluation results of the target product by each user in the user group of the target product; wherein the user evaluation results include the evaluation values ​​corresponding to each user evaluation index in the multidimensional evaluation index system; Based on the fuzzy hierarchical analysis method, the user evaluation data of the target product by each user in the user group of the target product is determined according to the user evaluation results.

4. The method according to claim 3, characterized in that The step of obtaining user evaluation results of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system includes: Generate evaluation collection information for a target product according to the multi-dimensional evaluation index system, and send the evaluation collection information to each user in a user group of the target product; Receive user evaluation results for the target product fed back by each user in the user group.

5. The method according to claim 3, characterized in that: The method of determining the user evaluation data of the target product by each user in the user group of the target product according to the user evaluation result based on the fuzzy hierarchical analysis method includes: Determining the importance of each user evaluation indicator according to the evaluation value corresponding to each user evaluation indicator in the user evaluation result; According to the importance of each user evaluation index, a fuzzy judgment matrix of the user group is constructed; Based on the fuzzy analytic hierarchy process, the fuzzy judgment matrix is ​​converted into a fuzzy consistency matrix; According to the fuzzy consistency matrix, user evaluation data of the target product by each user in the user group of the target product is determined.

6. The method according to claim 1, characterized in that The method of classifying user groups based on the customer group classification model according to the user evaluation data includes: Inputting the user evaluation data into a convolutional neural network of a customer group classification model to obtain a spatial feature vector of the user evaluation data; The spatial feature vector is input into the gated recurrent unit network of the customer group classification model to obtain the classification result of each user in the user group.

7. A user classification device, characterized in that: The device comprises: A system construction module, used to construct a multi-dimensional evaluation index system for the target product according to the product characteristics of the target product; A data acquisition module, used for acquiring user evaluation data of the target product by each user in the user group of the target product according to the multi-dimensional evaluation index system based on the fuzzy hierarchical analysis method; The user classification module is used to classify the user group based on the customer group classification model and according to the user evaluation data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.