E-commerce platform user comment analysis system

Abstract

The invention relates to the technical field of e-commerce platforms, and discloses an e-commerce platform user comment analysis system comprising the following systems: a collection module used for collecting user comments in an e-commerce platform; and the preferential extraction module is used for extracting the user evaluation for collecting the newly-collected e-commerce evaluation when the table is prepared to be made. According to the invention, when the information with poor evaluation is judged through the screening module, the information is classified into the service attitude, the product quality and the logistics speed according to the evaluation content of the user, and when the information is not in the service attitude, the product quality and the logistics speed, the information is judged again; and if not in the service attitude, the product quality and the logistics speed, classifying the data into others, and performing statistics based on the number of the data with better evaluation and the number of the data with poorer evaluation in the classification module so as to make a histogram.

Description

Technical Field

[0001] The present invention belongs to the technical field of e-commerce platforms, and in particular, relates to an e-commerce platform user review analysis system. Background Art

[0002] With the rapid development of e-commerce, the number of user reviews on e-commerce platforms has exploded. These user reviews contain rich information, such as product quality, service attitude, logistics speed, etc. However, traditional manual analysis methods are difficult to cope with such a large amount of review data, so an efficient automated analysis system is needed to mine valuable information from these reviews.

[0003] However, when analyzing user reviews, the existing methods often separate the good and bad information to observe the information with poor user reviews. When there is less information about poor user reviews, it is easy to be ignored. At the same time, when observing poor user reviews, the existing methods cannot remember which aspects of the reviews are about, and for the poor reviews in each aspect, it is not known which aspects to prioritize for improvement.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] In order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0006] An e-commerce platform user review analysis system, including the following systems:

[0007] S1, collection module: the collection module is used to collect user evaluations on the e-commerce platform;

[0008] S2. Priority extraction module: The priority extraction module extracts user evaluations collected from newly collected e-commerce evaluations when preparing to make a table;

[0009] S3, processing module: the processing module processes the user evaluations in the above-mentioned collection module and priority extraction module;

[0010] S4, extraction module: the extraction module extracts the user evaluations in the collection module;

[0011] S5, classification module: the classification module classifies the extracted user reviews;

[0012] S6, screening module: the screening module is to classify the content based on the poor user evaluation in the classification module;

[0013] S7, production module: the production module is used to sort out the total quantity and single quantity in the classification module and the screening module to produce a bar chart.

[0014] As a preferred embodiment of the present invention, the specific collection system based on the above-mentioned collection module includes: the collection module collects evaluations generated by users through the e-commerce platform, wherein the collected user evaluations include those with good evaluations and those with poor evaluations, so as to obtain the total number of user evaluations.

[0015] As a preferred embodiment of the present invention, the specific priority extraction system based on the above-mentioned S2 priority extraction module includes: the priority extraction system is based on the information screening and classification of the first total quantity in the processing module, extraction module, classification module and screening module in the above-mentioned S1 and the bar chart after the completion. At this time, the e-commerce platform collects new user evaluations. At this time, the collected new user evaluations can be directly classified and screened through the processing module, so that they can be directly integrated into the bar chart that has been prepared, and the revised bar chart can be revised.

[0016] As a preferred embodiment of the present invention, a specific processing system based on the above-mentioned S3 processing module includes: when the processing module is used by the collection module and the detected priority extraction module, it can process them so that they can enter the corresponding working program.

[0017] As a preferred embodiment of the present invention, the specific extraction system based on the above S4 extraction module includes: the extraction module collects the user evaluations collected in the collection module through the processing module, and extracts the user evaluations in the collection module through the extraction module.

[0018] As a preferred embodiment of the present invention, the specific classification system based on the above S5 classification module includes: the classification module classifies the user evaluations in the extraction module and the priority extraction module:

[0019] The specific classification in the extraction module is to preferentially filter out the bad information in the user evaluation through the extracted overall user evaluation, and classify the information into the poor evaluation; at the same time, the classification module can also perform secondary screening, and when performing secondary screening, it mainly further screens the user evaluation that was not originally screened, so as to filter out the bad information missed in the user evaluation, and classify it into the poor evaluation, while the remaining user evaluation information can be judged as good, and thus be classified into the good evaluation;

[0020] The specific classification in the priority extraction module is to directly judge the user awards contained in the priority extraction module to determine whether they are well-rated. If they are well-rated, they are directly entered into the category of well-rated. If they are not well-rated, they are directly entered into the category of poorly-rated.

[0021] As a preferred embodiment of the present invention, the specific screening system based on the above S6 screening module includes: the screening module judges the information judged to be poorly evaluated, and specifically, the poorly evaluated information can be divided into service attitude, product quality and logistics speed:

[0022] When judging the information with poor evaluation, it is divided into service attitude, product quality and logistics speed according to the content of user evaluation. When encountering a situation that is not in the service attitude, product quality and logistics speed, it will be judged again. If it is still not in the service attitude, product quality and logistics speed, it will be classified into others.

[0023] As a preferred embodiment of the present invention, the specific production system based on the above-mentioned S7 production module includes: making statistics based on the number of products with good and poor evaluations in the above-mentioned classification module to produce a bar chart; and at the same time, making statistics based on the respective numbers of service attitude, product quality and logistics speed among the poor numbers to produce a bar chart.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The present invention, when judging the information with poor evaluation through the screening module, classifies it into service attitude, product quality and logistics speed according to the content of the user evaluation. When encountering a situation that is not in the service attitude, product quality and logistics speed, it will be judged again at this time. If it is still not in the service attitude, product quality and logistics speed, it will be classified into others. At the same time, statistics are made based on the number of good evaluations and poor evaluations in the above classification modules, so as to produce a bar chart; at the same time, statistics are made based on the respective numbers of service attitude, product quality and logistics speed in the poor number, so as to produce a bar chart. At the same time, when the collection module receives new user evaluations at this time, the collected new user evaluations are directly classified and screened through the processing module, so that they can be directly integrated into the already produced bar chart, and the already revised bar chart is revised.

[0026] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In the attached picture:

[0028] Figure 1This is a system diagram of an e-commerce platform user review analysis system;

[0029] Figure 2 It is a specific system diagram of a user review analysis system for an e-commerce platform;

[0030] Figure 3 A schematic diagram of a priority extraction module of a user review analysis system for an e-commerce platform;

[0031] Figure 4 This is a bar chart of the extraction module of a user review analysis system for an e-commerce platform;

[0032] Figure 5 A histogram of the priority extraction modules of a user review analysis system for an e-commerce platform. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention.

[0034] like Figures 1 to 5 As shown, an e-commerce platform user review analysis system includes the following systems:

[0035] S1, collection module: the collection module is used to collect user evaluations on the e-commerce platform;

[0036] S2. Priority extraction module: The priority extraction module extracts user evaluations collected from newly collected e-commerce evaluations when preparing to make a table;

[0037] S3, processing module: the processing module processes the user evaluations in the above-mentioned collection module and priority extraction module;

[0038] S4, extraction module: the extraction module extracts the user evaluations in the collection module;

[0039] S5, classification module: the classification module classifies the extracted user reviews;

[0040] S6, screening module: the screening module is to classify the content based on the poor user evaluation in the classification module;

[0041] S7, production module: the production module is used to sort out the total quantity and single quantity in the classification module and the screening module to produce a bar chart.

[0042] In a specific implementation, the specific collection system based on the above-mentioned collection module includes: the collection module collects evaluations generated by users through the e-commerce platform, wherein the collected user evaluations include those with good evaluations and those with poor evaluations, thereby being able to obtain the total number of user evaluations.

[0043] Furthermore, based on the specific priority extraction system in the above-mentioned S2 priority extraction module, the priority extraction system includes: the priority extraction system is based on the information screening and classification of the first total quantity in the processing module, extraction module, classification module and screening module in the above-mentioned S1 and the bar chart after the completion. At this time, the e-commerce platform collects new user evaluations. At this time, the collected new user evaluations can be directly classified and screened through the processing module, so that they can be directly integrated into the bar chart that has been produced, and the revised bar chart can be revised.

[0044] Furthermore, a specific processing system based on the above S3 processing module includes: when the processing module is used by the collection module and the detected priority extraction module, it can process them so that they can enter the corresponding working procedures.

[0045] Furthermore, the specific extraction system based on the above S4 extraction module includes: the extraction module collects the user evaluations collected in the collection module through the processing module, and extracts the user evaluations in the collection module through the extraction module.

[0046] Furthermore, the specific classification system based on the above S5 classification module includes: the classification module is to classify the user evaluations in the extraction module and the priority extraction module:

[0047] The specific classification in the extraction module is to preferentially filter out the bad information in the user evaluation through the extracted overall user evaluation, and classify the information into the poor evaluation; at the same time, the classification module can also perform secondary screening, and when performing secondary screening, it mainly further screens the user evaluation that was not originally screened, so as to filter out the bad information missed in the user evaluation, and classify it into the poor evaluation, while the remaining user evaluation information can be judged as good, and thus be classified into the good evaluation;

[0048] The specific classification in the priority extraction module is to directly judge the user awards contained in the priority extraction module to determine whether they are well-rated. If they are well-rated, they are directly entered into the category of well-rated. If they are not well-rated, they are directly entered into the category of poorly-rated.

[0049] Furthermore, the specific screening system based on the above S6 screening module includes: the screening module is to judge the information judged to be poorly evaluated, and the poorly evaluated information can be specifically divided into service attitude, product quality and logistics speed:

[0050] When judging the information with poor evaluation, it is divided into service attitude, product quality and logistics speed according to the content of user evaluation. When encountering a situation that is not in the service attitude, product quality and logistics speed, it will be judged again. If it is still not in the service attitude, product quality and logistics speed, it will be classified into others.

[0051] Furthermore, the specific production system based on the above S7 production module includes: making statistics based on the number of good and poor evaluations in the above classification module to produce a bar chart; and at the same time, making statistics based on the respective numbers of service attitude, product quality and logistics speed among the poor numbers to produce a bar chart.

[0052] The implementation principle of the e-commerce platform user review analysis system of this embodiment is as follows:

[0053] The evaluations generated by users are collected through the e-commerce platform, wherein the collected user evaluations include those with good evaluations and those with poor evaluations, so that the total number of user evaluations can be obtained; the collection module is processed by the processing module so that it can enter the corresponding work procedure, the extraction module collects the user evaluations collected in the collection module, and the user evaluations in the collection module are extracted by the extraction module; and the specific classification in the extraction module is performed by the classification module, that is, the extracted overall user evaluations are used to preferentially filter out the bad information in the user evaluations, and the information is classified into the poor evaluation; at the same time, the classification module can also perform a secondary screening, and when performing the secondary screening, it is mainly to further screen the user evaluations that were not originally screened, so as to filter out the bad information missed in the user evaluations, and classify them into the poor evaluation, while the remaining user evaluation information can be judged as good, and thus classified into the good evaluation; at this time, the screening module is used again. When the block judges the information with poor evaluation, it will be divided into service attitude, product quality and logistics speed according to the content of the user evaluation. When encountering a situation that is not in the service attitude, product quality and logistics speed, it will be judged again at this time. If it is still not in the service attitude, product quality and logistics speed, it will be classified into others. At the same time, statistics are made based on the number of good and poor evaluations in the above classification modules to make a bar chart; at the same time, statistics are made based on the respective numbers of service attitude, product quality and logistics speed in the poor number to make a bar chart. At the same time, when the collection module receives new user evaluations at this time, the new user evaluations collected are directly classified and screened through the processing module, so that they can be directly merged into the already made bar chart, and the revised bar chart can be revised. At the same time, the specific aspects of the poor evaluation in the user evaluation can be intuitively observed through the bar chart, and priority improvements can be made based on the specific aspects, thereby optimizing and improving.

Claims

1. An e-commerce platform user review analysis system, characterized in that: Includes the following systems: S1, collection module: the collection module is used to collect user evaluations on the e-commerce platform; S2. Priority extraction module: The priority extraction module extracts user evaluations collected from newly collected e-commerce evaluations when preparing to make a table; S3, processing module: the processing module processes the user evaluations in the above-mentioned collection module and priority extraction module; S4, extraction module: the extraction module extracts the user evaluations in the collection module; S5, classification module: the classification module classifies the extracted user reviews; S6, screening module: the screening module is to classify the content based on the poor user evaluation in the classification module; S7, production module: the production module is used to sort out the total quantity and single quantity in the classification module and the screening module to produce a bar chart.

2. The e-commerce platform user review analysis system according to claim 1, characterized in that: The specific collection system based on the above-mentioned collection module includes: the collection module collects the evaluations generated by users through the e-commerce platform, wherein the collected user evaluations include those with good evaluations and those with poor evaluations, so as to obtain the total number of user evaluations.

3. The e-commerce platform user review analysis system according to claim 1, characterized in that: The specific priority extraction system based on the above-mentioned S2 priority extraction module includes: the priority extraction system is based on the information screening and classification of the first total quantity in the processing module, extraction module, classification module and screening module in the above-mentioned S1 and the bar chart after the completion. At this time, the e-commerce platform collects new user evaluations. At this time, the collected new user evaluations can be directly classified and screened through the processing module, so that they can be directly integrated into the bar chart that has been produced, and the revised bar chart can be revised.

4. The e-commerce platform user review analysis system according to claim 1, characterized in that: The specific processing system based on the above S3 processing module includes: when the processing module is used by the collection module and the detected priority extraction module, it can process them so that they can enter the corresponding working program.

5. The e-commerce platform user review analysis system according to claim 1, characterized in that: The specific extraction system based on the above S4 extraction module includes: the extraction module collects the user evaluations collected in the collection module through the processing module, and extracts the user evaluations in the collection module through the extraction module.

6. The e-commerce platform user review analysis system according to claim 1, characterized in that: The specific classification system based on the above S5 classification module includes: the classification module classifies the user evaluations in the extraction module and the priority extraction module: The specific classification in the extraction module is to preferentially filter out the bad information in the user evaluation through the extracted overall user evaluation, and classify the information into the poor evaluation; at the same time, the classification module can also perform secondary screening, and when performing secondary screening, it mainly further screens the user evaluation that was not originally screened, so as to filter out the bad information missed in the user evaluation, and classify it into the poor evaluation, while the remaining user evaluation information can be judged as good, and thus be classified into the good evaluation; The specific classification in the priority extraction module is to directly judge the user awards contained in the priority extraction module to determine whether they are well-rated. If they are well-rated, they are directly entered into the category of well-rated. If they are not well-rated, they are directly entered into the category of poorly-rated.

7. The e-commerce platform user review analysis system according to claim 1, characterized in that: The specific screening system based on the above S6 screening module includes: the screening module judges the information judged to be poorly evaluated, and specifically, the poorly evaluated information can be divided into service attitude, product quality and logistics speed: When judging the information with poor evaluation, it is divided into service attitude, product quality and logistics speed according to the content of user evaluation. When encountering a situation that is not in the service attitude, product quality and logistics speed, it will be judged again. If it is still not in the service attitude, product quality and logistics speed, it will be classified into others.

8. The e-commerce platform user review analysis system according to claim 1, characterized in that: The specific production system based on the above S7 production module includes: making statistics based on the number of good and poor evaluations in the above classification module to produce a bar chart; and making statistics based on the various numbers of service attitude, product quality and logistics speed among the poor numbers to produce a bar chart.

Images