Product mutual identification mining method and device, equipment and storage medium

Abstract

The invention relates to the technical field of financial science and technology, in particular to a product mutual authentication mining method and device, equipment and a storage medium, and the method comprises the steps: obtaining hot list products in a target software market, and determining the product information of the hot list products; based on the product information and to-be-optimized product information, determining similar products from the products in the hot list; determining competitive products from the similar products based on the product information of the similar products; and performing theme clustering on the product information of the competitive product to obtain a theme classification result. According to the invention, the optimization design effect of the bank APP product can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a product mutual identification mining method, device, equipment and storage medium. Background Art

[0002] In order to meet the users' needs for online business processing, banks generally develop corresponding bank APP products. In order to continuously improve the user experience of using bank APP products, they generally continue to optimize the design of bank APP products, thereby achieving the sustainable development of corresponding bank APP products.

[0003] At present, the way banks continuously optimize the design of bank APP products is: obtain user feedback on the use of bank APP products through questionnaires or telephone inquiries, and then determine the direction of product improvement based on the usage feedback, and finally optimize the design of bank APP products based on the product improvement direction.

[0004] However, obtaining user feedback on the use of bank APP products through questionnaires or telephone inquiries will disturb users and give them a bad experience, resulting in poor quality of user feedback through questionnaires or telephone inquiries; in addition, the efficiency of obtaining usage feedback through the above methods is also poor; ultimately resulting in poor optimization design effects of bank APP products. Summary of the invention

[0005] In order to facilitate the improvement of the optimized design effect of bank APP products, this application provides a product mutual identification mining method, device, equipment and storage medium.

[0006] In a first aspect, the present application provides a product mutual identification mining method, comprising:

[0007] Obtaining hot list products in the target software market and determining product information of the hot list products;

[0008] Determine similar products from the hot list products based on the product information and the product information to be optimized;

[0009] Determine competing products from the similar products based on the product information of the similar products;

[0010] The product information of the competing products is clustered by subject to obtain a subject classification result.

[0011] Through the above implementation, the product information of competing products corresponding to the product to be optimized can be determined from each target software market, and then the product information of each competing product can be subject-categorized to obtain the corresponding subject classification results. This makes it easy for developers to determine the improvement direction of the product to be optimized based on the subject classification results. In this process, zero disturbance to users can be achieved, and the efficiency of obtaining product information of competing products can be greatly improved. This can facilitate the improvement of the optimization design effect of banking APP products.

[0012] Preferably, the product mutual identification mining method provided by the present application further includes:

[0013] The product information of the competing product is classified according to evaluation tendency to obtain an evaluation tendency classification result.

[0014] Through the above implementation, on the basis of subject classification, the product information of competing products can be further classified on the dimension of evaluation tendency classification, so as to facilitate developers to grasp the evaluation tendency of competing products' product information, so as to facilitate developers to determine the direction of improvement from the evaluation tendency classification results, thereby further improving the optimization design effect of banking APP products.

[0015] Preferably, determining similar products from the hot list products based on the product information and the product information to be optimized includes:

[0016] Calculating the similarity between the product information and the product information to be optimized to obtain a similarity value;

[0017] Based on the similarity value and a preset similarity threshold, similar products are determined from the hot list products.

[0018] Through the above implementation, the similarity between the product information and the product information to be optimized is calculated, so that it is convenient to determine similar products based on the similarity, thereby facilitating improving the accuracy of determining similar products.

[0019] Preferably, the calculating the similarity between the product information and the product information to be optimized to obtain a similarity value includes:

[0020] Inputting the category label in the product information and the product label to be optimized in the product information to be optimized into a preset semantic model for processing, respectively, to obtain a first label semantic corresponding to the product label to be optimized and a second label semantic corresponding to the category label;

[0021] The first label semantics and the second label semantics are input into a similarity calculation model for processing to obtain a similarity value.

[0022] Through the above implementation, the category labels in the product information and the product labels to be optimized in the product information to be optimized are processed by the semantic model, and then the semantic similarity is calculated by the similarity calculation model, so that it is easy to determine whether the hot list product corresponding to the product information belongs to the same category as the product to be optimized.

[0023] Preferably, the performing evaluation tendency classification on the product information of the competing product to obtain the evaluation tendency classification result includes:

[0024] Segmenting the product reviews in the product information of the competing product to obtain a primary word set;

[0025] Removing stop words from the primary word set to obtain a target word set;

[0026] The target word set is input into a preset evaluation tendency dictionary for processing to obtain an evaluation tendency classification result.

[0027] Through the above implementation, by segmenting the product evaluations in the product information and processing the segmented words through the evaluation tendency dictionary, it is easy to obtain the evaluation tendency classification corresponding to the product evaluations in the product information of the competing product.

[0028] Preferably, the performing evaluation tendency classification on the product information of the competing product to obtain the evaluation tendency classification result includes:

[0029] Convert the product evaluation in the product information of the competing product into a corresponding feature vector;

[0030] The feature vector is input into a preset classifier for processing to obtain an evaluation tendency classification result.

[0031] Through the above implementation, the feature vectors corresponding to the product evaluations in the product information of the competing product are processed by the classifier, so as to obtain the evaluation tendency classification corresponding to the product evaluations in the product information of the competing product.

[0032] In a second aspect, the present application provides a product mutual identification mining device, comprising:

[0033] An information determination module, used to obtain hot list products in the target software market and determine product information of the hot list products;

[0034] A similar determination module, used to determine similar products from the hot list products based on the product information and the product information to be optimized;

[0035] A competing product determination module, used to determine competing products from the same type of products based on the product information of the same type of products;

[0036] The topic classification module is used to perform topic clustering on the product information of the competing products to obtain topic classification results.

[0037] Through the above implementation, the product information of competing products corresponding to the product to be optimized can be determined from each target software market, and then the product information of each competing product can be subject-categorized to obtain the corresponding subject classification results. This makes it easy for developers to determine the improvement direction of the product to be optimized based on the subject classification results. In this process, zero disturbance to users can be achieved, and the efficiency of obtaining product information of competing products can be greatly improved. This can facilitate the improvement of the optimization design effect of banking APP products.

[0038] In a third aspect, the present application provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method when executing the computer program.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above method when executed by a processor.

[0040] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0041] The above-mentioned product mutual learning mining method, device, equipment and storage medium determine the product information of the hot-list products by acquiring the hot-list products in the target software market; determine similar products from the hot-list products based on the product information and the information of the products to be optimized; determine competing products from the similar products based on the product information of the similar products; and subject-cluster the product information of the competing products to obtain a subject classification result; through the above-mentioned implementation, the product information of the competing products corresponding to the product to be optimized can be determined from each target software market, and then the product information of each competing product can be subject-classified to obtain the corresponding subject classification result, so that it is convenient for developers to determine the improvement direction of the product to be optimized according to the subject classification result. In this process, zero disturbance to users can be achieved, and the efficiency of obtaining product information of competing products can be greatly improved. In this way, it is convenient to improve the optimization design effect of bank APP products.

[0042] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A flowchart of a product mutual identification mining method provided in an embodiment of the present application;

[0045] Figure 2 A flowchart of another product mutual identification mining method provided in an embodiment of the present application;

[0046] Figure 3 A schematic diagram of the structure of a product mutual identification mining device provided in an embodiment of the present application;

[0047] Figure 4 A schematic diagram of the structure of another product mutual identification mining device provided in an embodiment of the present application;

[0048] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0049] Figure 6 This is a diagram of the internal structure of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present disclosure more clear, the present disclosure 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 disclosure and are not used to limit the present disclosure.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0052] In this article, the term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship.

[0053] Embodiment 1

[0054] Figure 1 This is a flowchart of a product mutual identification mining method provided in Example 1 of this application, refer to Figure 1 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0055] S110: Acquire hot list products in the target software market, and determine product information of the hot list products.

[0056] Among them, the target software market is the software download APPs of various smart device brands on the market or third parties used on smart devices. The hot list products are APP products with high download volume in the target software market. High download volume means that the download volume exceeds a certain download volume threshold; product information includes the product name, product category label, product rating, product evaluation, product evaluation time and product evaluation quantity of the corresponding APP product.

[0057] Specifically, taking a target software market as an example, all APP products with high download volume in the target software market are obtained as hot list products; then the product information of each hot list product is obtained.

[0058] S120: Determine similar products from the hot list products based on the product information and the product information to be optimized.

[0059] Among them, the products to be optimized are the bank APP products that the bank needs to continuously optimize, the product information to be optimized is the product information of the products to be optimized, and the product information of the products to be optimized specifically includes: the name of the product to be optimized, the category label of the product to be optimized, the score of the product to be optimized, the evaluation of the product to be optimized, the evaluation time of the product to be optimized and the number of evaluations of the product to be optimized, etc.; similar products are the APP products in each hot list product with similar functions to the products to be optimized. For example, similar products are bank APP products of other banks; by comparing the product information of each hot list product with the product information to be optimized, similar products to the products to be optimized can be determined from each hot list product.

[0060] Specifically, the product information of each hot list product is compared with the information of the product to be optimized, so as to determine the same products as the product to be optimized from each hot list product.

[0061] S130: Determine competing products from the similar products based on the product information of the similar products.

[0062] It should be noted that although some similar products belong to the hot list products, their users may have a low number of product evaluations for the similar products in the target software market, which results in the similar products being unable to provide effective information for the subsequent improvement of the products to be optimized; in order to facilitate the efficiency of the subsequent improvement of the products to be optimized, the number of product evaluations in the product information of the similar products can be determined first, and then it can be determined whether the number of product evaluations is not less than the preset evaluation number threshold; if so, it means that the similar products are easy to provide effective information for the improvement of the products to be optimized due to the high number of product evaluations. In this case, the similar products can be regarded as competing products; otherwise, it is clear that the similar products are difficult to provide effective information for the improvement of the products to be optimized due to the low number of product evaluations. In this case, the similar products are not regarded as competing products. In other embodiments, competing products can also be determined from each similar product according to the product scores in the product information of the similar products; if the product score of the similar products is higher than the preset score threshold, the similar products are regarded as competing products, otherwise, the similar products are not regarded as competing products.

[0063] Specifically, competing products are identified from similar products based on product information of similar products.

[0064] S140, performing topic clustering on the product information of the competing product to obtain a topic classification result.

[0065] Among them, there are generally a large number of product evaluations in the product information of competing products, and the types of evaluation content are relatively complicated. In order to facilitate subsequent developers to summarize the advantages and disadvantages of competing products based on the product evaluations in the product information of competing products, and to determine the improvement direction of the products to be optimized, it is necessary to organize the product evaluations in the product information of competing products. One way of organizing is to subject-cluster the product information of competing products. Subject clustering is to cluster the products of competing products into corresponding subject categories. The categories of subject classification in this embodiment include product complaints, problem feedback, optimization suggestions, and other categories; the subject classification results are the collection of product evaluations of competing products under each subject category.

[0066] It should be noted that in order to facilitate intuitive display of the subject classification results, the subject classification results can be displayed in the form of tables and / or statistical graphs.

[0067] Specifically, the product information of the competing products is clustered by topics to obtain topic classification results.

[0068] It should be noted that this embodiment determines the product information of the hot-listed products by acquiring the hot-listed products in the target software market; determines similar products from the hot-listed products based on the product information and the information of the products to be optimized; determines competing products from the similar products based on the product information of the similar products; and the product information of the competing products is thematically clustered to obtain a thematic classification result; through the above implementation, the product information of the competing products corresponding to the product to be optimized can be determined from each target software market, and then the product information of each competing product is thematically classified to obtain the corresponding thematic classification result, which makes it easy for developers to determine the improvement direction of the product to be optimized based on the thematic classification result. In this process, zero disturbance to users can be achieved, and the efficiency of obtaining the product information of competing products can be greatly improved. In this way, the optimization design effect of the bank APP product can be improved.

[0069] It should also be noted that the implementation of the above method can study and analyze the user's comments on similar, popular and well-received APP products, such as the shortcomings, needs and recognition content, to explore the user's real needs and expectations, and provide important reference and guidance for product design. In the future, developers can combine user feedback and market demand to continuously optimize product design, improve user experience, and achieve sustainable development and optimization of products.

[0070] Embodiment 2

[0071] Figure 2 This is a flowchart of a product mutual identification mining method provided in Example 2 of this application, refer to Figure 2 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0072] S210: Acquire hot list products in the target software market, and determine product information of the hot list products.

[0073] S220: Determine similar products from the hot list products based on the product information and the product information to be optimized.

[0074] S230: Determine competing products from the similar products based on the product information of the similar products.

[0075] S240: Perform topic clustering on the product information of the competing product to obtain a topic classification result.

[0076] S250: classify the product information of the competing product by evaluation tendency to obtain an evaluation tendency classification result.

[0077] It should be noted that the topic clustering of the product information of competing products is a way to classify the product evaluations of competing products. In addition, the product information of competing products can also be classified according to the evaluation tendency. The product evaluations of competing products can be classified based on the evaluation tendency dimension, thereby enriching the way of classifying product evaluations and obtaining classification results in different dimensions, so as to provide developers with rich classification results, thereby facilitating the improvement of the optimization design effect of banking APP products.

[0078] Among them, the evaluation tendency classification is to classify the product evaluations of competing products into corresponding evaluation tendency classifications. In this embodiment, the types of evaluation tendency classifications include: positive evaluation, neutral evaluation and negative evaluation. The evaluation tendency classification result is the collection of product evaluations of competing products under each evaluation tendency classification.

[0079] Specifically, evaluation tendency classification is performed on product evaluations in product information of competing products to obtain evaluation tendency classification results.

[0080] It should be noted that in order to facilitate the intuitive display of the evaluation tendency classification results, the evaluation tendency classification results can be displayed in the form of tables and / or statistical graphs.

[0081] Embodiment 3

[0082] A product mutual identification mining method is provided in the third embodiment of the present application. The method optimizes the "determining similar products from the hot list products based on the product information and the product information to be optimized" in the first embodiment. It should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments. The method includes:

[0083] S310: Acquire hot list products in the target software market, and determine product information of the hot list products.

[0084] S321. Calculate the similarity between the product information and the product information to be optimized to obtain a similarity value.

[0085] The similarity calculation is to respectively compare the similarity between the product information of each hot list product and the product information to be optimized, so as to obtain the similarity value corresponding to each hot list product.

[0086] Specifically, the similarity between the product information of each hot list product and the product information to be optimized is compared respectively, and the similarity value corresponding to each hot list product is obtained respectively.

[0087] S322: Determine similar products from the hot list products based on the similarity value and a preset similarity threshold.

[0088] Among them, the preset similarity threshold is used to compare with the similarity value to determine whether the similarity value is high. If the similarity value is high, the hot list product corresponding to the similarity value is used as a similar product to the product to be optimized.

[0089] Specifically, taking one of the hot list products as an example, the product information of the hot list product is obtained, and then the similarity between the product information of the hot list product and the product information to be optimized is compared to obtain a corresponding similarity value, and then the similarity value is compared to see whether it is greater than a preset similarity threshold. If so, the hot list product corresponding to the similarity value is used as a similar product of the product to be optimized.

[0090] S330: Determine competing products from the similar products based on the product information of the similar products.

[0091] S340: Perform topic clustering on the product information of the competing product to obtain a topic classification result.

[0092] Embodiment 4

[0093] A product mutual identification mining method is provided in the fourth embodiment of the present application. The method optimizes the "calculating the similarity between the product information and the product information to be optimized to obtain a similarity value" in the third embodiment. It should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments. The method includes:

[0094] S410: Acquire hot list products in the target software market, and determine product information of the hot list products.

[0095] S4211. Input the category label in the product information and the product label to be optimized in the product information to be optimized into a preset semantic model for processing, and obtain the first label semantics corresponding to the product label to be optimized and the second label semantics corresponding to the category label.

[0096] Among them, the product information of the hot list products includes a category label, which is used to characterize the field to which the corresponding hot list products belong, where the types of fields include life, finance, social, etc.; the product information to be optimized includes the product label to be optimized, and the product label to be optimized is used to characterize the field to which the product to be optimized belongs; the preset semantic model adopts a natural language model in this embodiment, and the semantic model is used to process the category label and the product label to be optimized input therein respectively, and output the first label semantics corresponding to the product label to be optimized and the second label semantics corresponding to the category label.

[0097] Specifically, taking a hot-list product as an example, the category label in the product information of the hot-list product is obtained, and the category label and the product label to be optimized in the product information to be optimized are respectively input into the preset semantic model for processing. The semantic model outputs the first label semantics corresponding to the product label to be optimized and the second label semantics corresponding to the category label.

[0098] S4212: Input the first label semantics and the second label semantics into a similarity calculation model for processing to obtain a similarity value.

[0099] The similarity calculation model is used to calculate the similarity between the first label semantics and the second label semantics, and input a similarity value corresponding to the similarity.

[0100] Specifically, the first label semantics and the second label semantics are input into a similarity calculation model for calculation to obtain a similarity value.

[0101] S422: Determine similar products from the hot list products based on the similarity value and a preset similarity threshold.

[0102] S430: Determine competing products from the similar products based on the product information of the similar products.

[0103] S440: Perform topic clustering on the product information of the competing product to obtain a topic classification result.

[0104] Embodiment 5

[0105] A product mutual learning mining method is provided in the fifth embodiment of the present application. The method optimizes the "classifying the product information of the competitive product by evaluation tendency to obtain the evaluation tendency classification result" in the second embodiment. It should be noted that for the part not described in detail in the present embodiment, reference can be made to the description of other embodiments. The method includes:

[0106] S510: Acquire hot list products in the target software market, and determine product information of the hot list products.

[0107] S520: Determine similar products from the hot list products based on the product information and the product information to be optimized.

[0108] S530: Determine competing products from the similar products based on the product information of the similar products.

[0109] S540: Perform topic clustering on the product information of the competing product to obtain a topic classification result.

[0110] S551. Segment the product evaluation in the product information of the competing product to obtain a primary word set.

[0111] Among them, the product evaluation is a piece of text, and word segmentation means splitting this text into multiple words. The primary word set is the result obtained by performing word segmentation on the product evaluation in the product information of the competing product; Exemplarily, the primary word set is: 'wealth management', 'fund', '-','small and micro', 'of', '-', 'finance', '.', 'provide', 'has', 'inclusive', 'characteristics','services'.

[0112] Specifically, perform word segmentation on the product evaluation in the product information of the competing product to obtain the primary word set.

[0113] S552. Remove the stop words in the primary word set to obtain the target word set.

[0114] It should be noted that the purpose of obtaining the primary word set is to perform evaluation tendency classification based on the words in the primary word set subsequently. However, some stop words in the primary word set contribute little to the subsequent evaluation tendency classification and will affect the accuracy and efficiency of the evaluation tendency classification. To facilitate improving the accuracy and efficiency of the evaluation tendency classification, before performing the evaluation tendency classification, it is also necessary to remove the stop words in the primary word set. Stop words are words such as 'of', 'has', modal particles, and punctuation marks in the primary word set. The target word set is the result obtained by removing the stop words from the primary word set.

[0115] Specifically, remove the stop words in the primary word set to obtain the target word set.

[0116] S553. Input the target word set into a preset evaluation tendency dictionary for processing to obtain an evaluation tendency classification result.

[0117] Among them, the evaluation tendency dictionary determines the evaluation tendency classification corresponding to the target word set, and classifies the product evaluations corresponding to the target word sets belonging to the same evaluation tendency classification under this evaluation tendency classification, so as to obtain the evaluation tendency classification result.

[0118] Embodiment Six

[0119] A product mutual reference mining method provided by Embodiment Six of this application optimizes 'performing evaluation tendency classification on the product information of the competing product to obtain an evaluation tendency classification result' in Embodiment Two; It should be noted that for parts not detailed in this embodiment, reference can be made to the descriptions of other embodiments. This method includes:

[0120] S610. Obtain the hot products in the target software market and determine the product information of the hot products.

[0121] S620. Determine the similar products from the hot products based on the product information and the product information to be optimized.

[0122] S630: Determine competing products from the similar products based on the product information of the similar products.

[0123] S640: Perform topic clustering on the product information of the competing product to obtain a topic classification result.

[0124] S651. Convert the product evaluation in the product information of the competing product into a corresponding feature vector.

[0125] Among them, the feature vector is a vector corresponding to the product evaluation in the product information of the competing product. The product evaluation can be converted into the corresponding feature vector through a preset conversion tool.

[0126] Specifically, the product evaluation in the product information of the competing product is converted into a corresponding feature vector through a preset conversion tool.

[0127] S652: Input the feature vector into a preset classifier for processing to obtain an evaluation tendency classification result.

[0128] Among them, the classifier is used to determine the evaluation tendency classification corresponding to the feature vector input therein, that is, to determine the evaluation tendency classification of the product evaluation corresponding to the feature vector; the product evaluations corresponding to the target word set belonging to the same evaluation tendency classification are classified into the evaluation tendency classification, so that the evaluation tendency classification result can be obtained.

[0129] 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.

[0130] Embodiment 7

[0131] Based on the same inventive concept, this embodiment also provides a product mutual identification mining device for implementing the product mutual identification mining method involved in the above embodiment 1. 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 product mutual identification mining device embodiments provided below can refer to the limitations of the product mutual identification mining method above, and will not be repeated here.

[0132] In this embodiment, Figure 3 As shown, a product mutual identification mining device is provided, comprising:

[0133] An information determination module, used to obtain hot list products in the target software market and determine product information of the hot list products;

[0134] A similar determination module, used to determine similar products from the hot list products based on the product information and the product information to be optimized;

[0135] A competing product determination module, used to determine competing products from the same type of products based on the product information of the same type of products;

[0136] The topic classification module is used to perform topic clustering on the product information of the competing products to obtain topic classification results.

[0137] Embodiment 8

[0138] Based on the same inventive concept, this embodiment also provides a product mutual identification mining device for implementing the product mutual identification mining method involved in the above embodiment 2. 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 product mutual identification mining device embodiments provided below can refer to the limitations of the product mutual identification mining method above, and will not be repeated here.

[0139] In this embodiment, Figure 4 As shown, a product mutual identification mining device is provided, comprising:

[0140] An information determination module, used to obtain hot list products in the target software market and determine product information of the hot list products;

[0141] A similar determination module, used to determine similar products from the hot list products based on the product information and the product information to be optimized;

[0142] A competing product determination module, used to determine competing products from the same type of products based on the product information of the same type of products;

[0143] A topic classification module, used to perform topic clustering on the product information of the competing product to obtain a topic classification result;

[0144] The evaluation tendency classification module is used to classify the product information of the competing product by evaluation tendency to obtain an evaluation tendency classification result.

[0145] Each module in the above-mentioned product mutual identification mining device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0146] It should be noted that this embodiment determines the product information of the hot-listed products by acquiring the hot-listed products in the target software market; determines similar products from the hot-listed products based on the product information and the information of the products to be optimized; determines competing products from the similar products based on the product information of the similar products; and the product information of the competing products is thematically clustered to obtain a thematic classification result; through the above implementation, the product information of the competing products corresponding to the product to be optimized can be determined from each target software market, and then the product information of each competing product is thematically classified to obtain the corresponding thematic classification result, which makes it easy for developers to determine the improvement direction of the product to be optimized based on the thematic classification result. In this process, zero disturbance to users can be achieved, and the efficiency of obtaining the product information of competing products can be greatly improved. In this way, the optimization design effect of the bank APP product can be improved.

[0147] Embodiment 9

[0148] In this embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, 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 database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a product mutual identification mining method is implemented.

[0149] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0150] Embodiment 10

[0151] In this embodiment, a computer readable storage medium is provided. Figure 6As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0152] Embodiment 11

[0153] In this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0155] 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 by the present disclosure 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 by the present disclosure 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 thereto. The processor involved in each embodiment provided by the present disclosure 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 thereto.

[0156] 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.

[0157] The above-described embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out 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 disclosure, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the attached claims.

Claims

1. A product mutual identification mining method, characterized in that: include: Obtaining hot list products in the target software market and determining product information of the hot list products; Determine similar products from the hot list products based on the product information and the product information to be optimized; Determine competing products from the similar products based on the product information of the similar products; The product information of the competing products is clustered by subject to obtain a subject classification result.

2. The method according to claim 1, characterized in that Also includes: The product information of the competing product is classified according to evaluation tendency to obtain an evaluation tendency classification result.

3. The method according to claim 1, characterized in that The determining of similar products from the hot list products based on the product information and the product information to be optimized includes: Calculating the similarity between the product information and the product information to be optimized to obtain a similarity value; Based on the similarity value and a preset similarity threshold, similar products are determined from the hot list products.

4. The method according to claim 3, characterized in that: The calculating the similarity between the product information and the product information to be optimized to obtain a similarity value includes: Inputting the category label in the product information and the product label to be optimized in the product information to be optimized into a preset semantic model for processing, respectively, to obtain a first label semantic corresponding to the product label to be optimized and a second label semantic corresponding to the category label; The first label semantics and the second label semantics are input into a similarity calculation model for processing to obtain a similarity value.

5. The method according to claim 2, characterized in that: The performing evaluation tendency classification on the product information of the competitive product to obtain the evaluation tendency classification result includes: Segmenting the product reviews in the product information of the competing product to obtain a primary word set; Removing stop words from the primary word set to obtain a target word set; The target word set is input into a preset evaluation tendency dictionary for processing to obtain an evaluation tendency classification result.

6. The method according to claim 2, characterized in that The performing evaluation tendency classification on the product information of the competitive product to obtain the evaluation tendency classification result includes: Convert the product evaluation in the product information of the competing product into a corresponding feature vector; The feature vector is input into a preset classifier for processing to obtain an evaluation tendency classification result.

7. A product mutual identification mining device, characterized in that: The device comprises: An information determination module, used to obtain hot list products in the target software market and determine product information of the hot list products; A similar determination module, used to determine similar products from the hot list products based on the product information and the product information to be optimized; A competing product determination module, used to determine competing products from the same type of products based on the product information of the same type of products; The topic classification module is used to perform topic clustering on the product information of the competing products to obtain topic classification results.

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.

Images