WO2019006642A1

WO2019006642A1 - System for identifying quality of comment for product in electronic commerce

Info

Publication number: WO2019006642A1
Application number: PCT/CN2017/091592
Authority: WO
Inventors: 陈钦鹏
Original assignee: 深圳齐心集团股份有限公司
Priority date: 2017-07-04
Filing date: 2017-07-04
Publication date: 2019-01-10

Abstract

The present invention provides a system for identifying the quality of a comment for a product in electronic commerce. The system comprises a comment file construction module, a similar comment screening module, a similar ID extraction module, and a comment quality identification module. The comment file construction module is used for capturing comment data and classifying the comment data according to the categories of commodities, so as to construct product comment files corresponding to the commodities. The similar comment screening module is used to sifting out similar comments in the product comment files. The similar ID extraction module is used for extracting similar IDs from the product comment files. The comment quality identification module is used for matching the selected similar comments with the extracted similar IDs according to the product comment files, capturing product comments with similar IDs and comments according to the matching results, marking the captured product comments with the similar IDs and the similar comments as fake comments, and marking the IDs corresponding to the fake comments as fake comment IDs. Fake comments in target product comments can be identified, and the reliability of the determining results is high.

Description

E-commerce product review quality identification system

Technical field

The invention belongs to the field of electronic commerce, and in particular relates to an e-commerce product review quality identification system.

Background technique

In the modern era, with the popularity of the Internet, e-commerce has become a widely used form of commercial trade. The buyers and sellers mainly conduct trading activities through the e-commerce webpage or software. Since e-commerce does not have a traditional physical storefront, the number of sales personnel is not high, so it is more controllable than the traditional transaction mode, so it has a greater price advantage. However, there are many unscrupulous merchants who hire professional brush evaluation teams to create a large number of false comments to make false advertisements about their products in order to increase their sales, thereby deceiving consumers to improve their real sales.

At present, the development of e-commerce is rapid and huge, and there are many sellers in the e-commerce environment. It is difficult for users to judge the authenticity of the product description when making the purchase decision, and the dependence on the product evaluation is very high, which is caused by the seller’s evaluation cheating. The loss of buyer's interest caused by the high performance of the product's performance is serious. Under such circumstances, how to identify and judge the cheating behavior of merchants in e-commerce is an urgent problem to be solved in the process of e-commerce development; how to improve the accuracy of judgment in the process of judging false comments and avoid the occurrence of misjudgment It is also a very important consideration factor; at present, there is still a lack of accurate and effective related equipment in the prior art to realize the identification of product review quality.

technical problem

The embodiment of the invention provides an e-commerce product review quality identification system, which aims to solve the problem that the prior art lacks accurate and effective related equipment to realize product identification quality identification.

Technical solution

The embodiment of the present invention is implemented as follows: an e-commerce product review quality authentication system, comprising: a comment document construction module, a similar comment screening module, a similar ID extraction module, and a comment quality authentication module; wherein the comment document construction module, For extracting comment data, and classifying the review data by product category to construct a product review document corresponding to the product; the similar comment screening module, for filtering out similar comments from the product review document; the similar ID extraction Module for extracting similar IDs from product review documents The comment quality identification module is configured to match the filtered similar comments with the extracted similar IDs according to the product review document, and capture product reviews with similar IDs and reviews according to the matching results, and capture the captured products. The product review identifiers whose IDs and comments are similar are identified as false comments, and the ID corresponding to the fake comments is identified as a fake comment ID.

Preferably, the comment document construction module output is respectively connected to the input of the similar comment screening module and the similar ID extraction module; the comment quality authentication module and the display comment screening module respectively, the similar ID The output of the extraction module is connected.

Preferably, the comment quality authentication module comprises:

a receiving unit, configured to receive a similar comment filtered by a similar comment screening module and a similar ID extracted by a similar ID extraction module;

a matching unit, configured to match the filtered similar comments with the extracted similar IDs according to the product review document;

a false comment identification unit, configured to capture product reviews having similar IDs and comments according to the matching result, and identify the product reviews with similar captured IDs and comments as false comments, and ID identifiers corresponding to the fake comments A false comment ID.

Preferably, the system further includes: an identifier start time entry module, configured to enter an identifier start time for the fake ID identified in the comment quality authentication module.

Preferably, the system further comprises: a storage module, configured to store the identified fake ID.

Preferably, the system further includes: a fake ID timing deletion module, configured to calculate a time value stored in the storage module according to the identifier start time and the current system time entered by the fake ID, and the time value is The preset time threshold is compared. When the time value is greater than the preset time threshold, the fake ID is deleted from the storage module.

Preferably, the time threshold is 30 to 60 days.

Preferably, the system further includes: a data redundancy judging module, connected to the comment quality discriminating module and the fake ID storage module, configured to determine a false ID identified in the comment quality discriminating module and a false stored in the storage module Is the ID the same?

Preferably, the system further includes: a same fake ID deletion module, configured to delete the fake ID identified in the comment quality authentication module when the fake ID identified in the comment quality authentication module is the same as the fake ID stored in the storage module.

Beneficial effect

The e-commerce product review quality authentication system provided by the embodiment of the present invention captures the comment data by the comment document building module, classifies the comment data according to the product category, and constructs a product review document corresponding to the product; and filters the module through the similar comment screening module. A similar comment is filtered out in the comment document; a similar ID extraction module extracts a similar ID from the product review document Finally, through the comment quality identification module, the selected similar comments are matched with the extracted similar IDs according to the product review document, and the product reviews with similar IDs and comments are captured according to the matching results, and the captured IDs and comments are extracted. The similar product reviews are identified as false comments, and the ID corresponding to the false comments is identified as a false comment ID, which can identify false comments in the target product evaluation, and the determination result is highly reliable.

DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below. Obviously, the drawings in the following description are Some embodiments of the present invention may also be used to obtain other drawings based on these drawings without departing from the art.

The following drawings are only intended to illustrate and explain the present invention, and do not limit the scope of the invention.

1 is a schematic structural diagram of an e-commerce product review quality authentication system according to an embodiment of the present invention;

2 is a schematic structural diagram of a comment quality authentication module according to an embodiment of the present invention;

3 is a schematic structural diagram of another e-commerce product review quality authentication system according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of still another e-commerce product review quality authentication system according to an embodiment of the present invention.

Embodiments of the invention

The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

As shown in FIG. 1 , in an embodiment of the present invention, an e-commerce product review quality authentication system 100 includes: a comment document construction module 110, a similar comment screening module 120, a similar ID extraction module 130, and a comment quality authentication module 140; The comment document construction module 110 is configured to capture the comment data, and classify the comment data by the product category to construct a product review document corresponding to the product; the similar comment screening module 120 is configured to review the document from the product. Similar comments are filtered out; the similar ID extraction module 130 is configured to extract a similar ID from the product review document The comment quality discriminating module 140 is configured to match the filtered similar comments and the extracted similar IDs according to the product review document, and capture product reviews with similar IDs and reviews according to the matching results, and grab the products The product review identifiers whose IDs and comments are similar are identified as false comments, and the ID corresponding to the fake comments is identified as a fake comment ID. It is possible to identify false comments in the evaluation of the target product, and the judgment result is highly reliable.

In the embodiment of the present invention, the output of the comment document construction module 110 is respectively connected to the input of the similar comment screening module 120 and the similar ID extraction module 130; the comment quality identification module 140 and the display respectively The comment screening module 120 and the output of the similar ID extraction module 130 are connected.

In the embodiment of the present invention, as shown in FIG. 2, the comment quality discriminating module 140 includes: a receiving unit 141, configured to receive a similar comment filtered by a similar comment screening module and a similar ID extracted by a similar ID extraction module; The matching unit 142 is configured to match the filtered similar comments and the extracted similar IDs according to the product review document, and the fake comment identifying unit 143, configured to capture the product reviews with similar IDs and comments according to the matching result, and The product reviews with similar IDs and comments are identified as false comments, and the ID corresponding to the fake comments is identified as a fake comment ID.

In the embodiment of the present invention, as shown in FIG. 3, the system 100 further includes: an identifier start time entry module 150, a storage module 160, and a fake ID timing deletion module 170. The identifier start time entry module 150 is configured to enter an identifier start time for the fake ID identified in the comment quality authentication module. The storage module 160 is configured to store the identified fake ID. The fake ID timing deletion module 170 is configured to calculate a time value stored in the storage module according to the identifier start time and the current system time entered by the fake ID, and set the time value to a preset time threshold. The comparison is performed. When the time value is greater than the preset time threshold, the fake ID is deleted from the storage module.

In this embodiment, the time threshold may be 30 to 60 days. For example, when the time threshold is 30 days, the identifier start time entry module enters the identifier start time of a fake ID identifier in the comment quality authentication module as 2011-06-06, and the current system time is 2011-077. -06, the fake ID timing deletion module deletes the modified false ID stored in the storage module; for example, when the time threshold is 45 days, the identifier start time entry module identifies the identifier in the comment quality authentication module. The initial ID of the fake ID entry is 2011-06-06, and the current system time is 2011-07-21. The fake ID timing deletion module deletes the modified false ID stored in the storage module; The time threshold is 60 days. The identifier start time entry module enters the identifier ID of the fake ID ID in the comment quality authentication module. The start time is 2011-06-06, and the current system time is 2011-08-06. The fake ID timing deletion module deletes the modified fake ID stored in the storage module.

In the embodiment of the present invention, as shown in FIG. 4, the system 100 further includes: a data redundancy judging module 180 and an identical fake ID deleting module 190. The data redundancy judging module 180 is connected to the comment quality discriminating module and the fake ID storage module, and is configured to determine whether the fake ID identified in the comment quality discriminating module is the same as the spurious ID stored in the storage module. The same fake ID deletion module 190 is configured to delete the fake ID identified in the comment quality authentication module when the fake ID identified in the comment quality authentication module is the same as the fake ID stored in the storage module. For example, when the storage module stores a fake ID of 123456, and the database redundancy module identifies that the fake ID identified in the comment quality authentication module is 123456, the same fake ID deletion module will comment on the false ID identified in the quality authentication module. The fake ID with the ID 123456 is deleted.

The e-commerce product review quality authentication system provided by the above embodiment of the invention captures the comment data by the comment document building module, classifies the comment data by the product category, and constructs a product review document corresponding to the product; and filters the module from the product through the similar comment screening module. A similar comment is filtered out in the comment document; a similar ID extraction module extracts a similar ID from the product review document Finally, through the comment quality identification module, the selected similar comments are matched with the extracted similar IDs according to the product review document, and the product reviews with similar IDs and comments are captured according to the matching results, and the captured IDs and comments are extracted. The similar product reviews are identified as false comments, and the ID corresponding to the false comments is identified as a false comment ID, which can identify false comments in the target product evaluation, and the determination result is highly reliable.

The above is only the preferred embodiment of the present invention, and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. Within the scope.

Claims

An e-commerce product review quality authentication system, comprising: a comment document construction module, a similar comment screening module, a similar ID extraction module, and a comment quality authentication module; wherein the comment document construction module is configured to capture a comment Data, while classifying the review data by product category to construct a product review document corresponding to the product; the similar comment screening module for filtering out similar comments from the product review document; the similar ID extraction module for A similar ID is extracted from the product review document The comment quality identification module is configured to match the filtered similar comments with the extracted similar IDs according to the product review document, and capture product reviews with similar IDs and reviews according to the matching results, and capture the captured products. The product review identifiers whose IDs and comments are similar are identified as false comments, and the ID corresponding to the fake comments is identified as a fake comment ID.
The e-commerce product review quality authentication system according to claim 1, wherein the comment document construction module output is respectively connected to the input of the similar comment screening module and the similar ID extraction module; The quality authentication module is respectively connected to the output of the display comment screening module and the similar ID extraction module.
The e-commerce product review quality authentication system according to claim 1, wherein the comment quality authentication module comprises:

a receiving unit, configured to receive a similar comment filtered by a similar comment screening module and a similar ID extracted by a similar ID extraction module;

a matching unit, configured to match the filtered similar comments with the extracted similar IDs according to the product review document;

a false comment identification unit, configured to capture product reviews having similar IDs and comments according to the matching result, and identify the product reviews with similar captured IDs and comments as false comments, and ID identifiers corresponding to the fake comments A false comment ID.
The e-commerce product review quality authentication system according to claim 3, further comprising: an identification start time entry module, configured to enter an identification start time for the fake ID identified in the comment quality authentication module.
The e-commerce product review quality authentication system according to claim 4, further comprising: a storage module, configured to store the identified fake ID.
The e-commerce product review quality authentication system according to claim 5, further comprising: a fake ID timing deletion module, configured to calculate the false ID according to the identifier start time and the current system time entered by the fake ID The time value stored in the storage module is compared with a preset time threshold. When the time value is greater than the preset time threshold, the fake ID is deleted from the storage module.
The e-commerce product review quality authentication system according to claim 6, wherein the time threshold is 30 to 60 days.
The e-commerce product review quality authentication system according to claim 7, further comprising: a data redundancy judging module, coupled to the comment quality discriminating module and the fake ID storage module, for judging the quality of the comment. The fake ID identified in the module is the same as the fake ID stored in the storage module.
The e-commerce product review quality authentication system according to claim 8, further comprising: a same fake ID deletion module, configured to: when the fake ID identified in the comment quality authentication module is the same as the fake ID stored in the storage module , delete the fake ID identified in the comment quality authentication module.