CN111667337A - Commodity evaluation ordering method and system - Google Patents
Commodity evaluation ordering method and system Download PDFInfo
- Publication number
- CN111667337A CN111667337A CN202010350718.9A CN202010350718A CN111667337A CN 111667337 A CN111667337 A CN 111667337A CN 202010350718 A CN202010350718 A CN 202010350718A CN 111667337 A CN111667337 A CN 111667337A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- commodity
- characters
- picture
- emotion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 289
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012163 sequencing technique Methods 0.000 claims abstract description 29
- 238000000556 factor analysis Methods 0.000 claims abstract description 12
- 230000008451 emotion Effects 0.000 claims description 54
- 238000004458 analytical method Methods 0.000 claims description 48
- 239000013598 vector Substances 0.000 claims description 18
- 230000002996 emotional effect Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 230000007935 neutral effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 9
- 238000013441 quality evaluation Methods 0.000 abstract description 7
- 238000012821 model calculation Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0627—Directed, with specific intent or strategy using item specifications
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity evaluation sequencing method and a commodity evaluation sequencing system, wherein the commodity evaluation sequencing method comprises the following steps: determining the demand of a user on commodity evaluation and an influence factor related to the demand on evaluation sequencing, analyzing the influence factor by using a factor analysis method, and constructing an evaluation weight model; acquiring the evaluation data of a user on a commodity, extracting evaluation characters and an evaluation picture from the evaluation data, and respectively scoring the evaluation characters and the evaluation picture; and carrying out numerical value sorting on the total scores of the evaluation characters and the evaluation pictures through the evaluation weight model, and corresponding the numerical value sorting to the evaluation sorting of the commodities. The embodiment of the invention shows the high-quality evaluation of the commodity characteristics to the consumers through the picture and character recognition and model calculation of commodity evaluation, improves the conversion rate of the commodity and simultaneously reduces the operation cost of the e-commerce.
Description
Technical Field
The invention relates to the field of e-commerce operation, in particular to a commodity evaluation sequencing method and a commodity evaluation sequencing system.
Background
The evaluation is a starting point in a shopping link of a user and is a key element influencing commodity conversion. As a consumer, the user demand starting point is as follows: the method has the advantages of seeing the real evaluation, rich evaluation content and strong commodity-related evaluation. As a merchant or platform, the merchant needs the starting point: it is desirable that the evaluation describing positive emotion, high evaluation star rating, and highlighting the quality characteristics of the commodity is preferentially shown to the consumer. However, in order to meet the common requirements of consumers and merchant platforms, different strategy algorithms are set for evaluation and sorting in the current electronic merchant platform, and the existing sorting algorithm has the problems that evaluation content text information is disordered, evaluation display of large sections of invalid texts is in front, and picture quality is unclear. On the other hand, due to the fact that part of sellers have multiple types of commodities, the possible number of evaluations of each commodity is small, and a plurality of sellers manually select the commodity in sequence, the manual selection, evaluation and sequencing method can improve labor cost, increase the operation cost of the e-commerce, and show real and reasonable evaluations to consumers while reducing the operation cost of the e-commerce, so that the desire of converting the commodities of the sellers into buyers for purchase is improved, namely the problem of commodity conversion rate is solved, and further technical innovation is needed.
Disclosure of Invention
In order to solve the problems in the prior art, the embodiment of the invention provides a commodity evaluation sequencing method and a commodity evaluation sequencing system, and the high-quality evaluation of commodity characteristics is displayed to consumers through picture and character recognition and model calculation of commodity evaluation, so that the conversion rate of commodities is improved, and the operation cost of an e-commerce is reduced.
In order to solve the technical problems, the invention adopts the technical scheme that:
in a first aspect, an embodiment of the present invention provides a method for ordering commodity evaluations, including the following steps:
determining the demand of a user on commodity evaluation and an influence factor related to the demand on evaluation sequencing, analyzing the influence factor by using a factor analysis method, and constructing an evaluation weight model;
acquiring the evaluation data of a user on a commodity, extracting evaluation characters and an evaluation picture from the evaluation data, and respectively scoring the evaluation characters and the evaluation picture;
and carrying out numerical value sorting on the total scores of the evaluation characters and the evaluation pictures through the evaluation weight model, and corresponding the numerical value sorting to the evaluation sorting of the commodities.
Further, scoring the evaluation text comprises: and firstly, respectively analyzing the semantic emotional tendency and the content richness of the evaluation characters, and then carrying out numerical operation on the semantic emotional tendency and the content richness to obtain the final scores of the evaluation characters.
Further, the semantic emotion tendency analysis distinguishes positive, negative and neutral emotion polarities by judging the confidence degree of the emotion polarity type of the evaluation character, and counts the number of negative evaluation values of the emotion polarity type.
Further, the analysis of the content richness comprises the steps of extracting emotion opinions related to the evaluation emotion word library in the evaluation characters through an evaluation emotion word library with three dimensions of goods, logistics and services to obtain two polarity comment opinion labels of good comment and bad comment.
Further, scoring the evaluation screen includes: and respectively identifying the feature vectors of the evaluation picture and the main picture of the shop commodity, obtaining the Euclidean distance of the feature vectors as similar scores, and calculating the final score of the evaluation picture through the similar scores.
On the other hand, the embodiment of the invention also provides a commodity evaluation sequencing system, which comprises:
the evaluation construction module is used for determining the demand of the user on commodity evaluation and the influence factor of the demand related to the evaluation sequence, analyzing the influence factor by using a factor analysis method and constructing an evaluation weight model;
the evaluation processing module is used for acquiring the evaluation data of the user on the commodity, extracting evaluation characters and an evaluation picture from the evaluation data, and respectively scoring the evaluation characters and the evaluation picture;
and the evaluation ranking module is used for performing numerical value ranking on the total scores of the evaluation characters and the evaluation pictures through the evaluation weight model, and the numerical value ranking corresponds to the evaluation ranking of the commodities.
Furthermore, the evaluation processing module comprises an evaluation character analysis unit, and the evaluation character analysis unit is used for respectively analyzing the semantic emotional tendency and the content richness of the evaluation characters, and then carrying out numerical operation on the semantic emotional tendency and the content richness to obtain the final score of the evaluation characters.
Further, the evaluation character analysis unit comprises an emotion analysis subunit, and the emotion analysis subunit is used for judging the confidence degree of the emotion polarity type of the evaluation character, so as to distinguish positive, negative and neutral emotion polarities, and count the number of evaluations that the emotion polarity type is negative.
Furthermore, the evaluation character analysis unit further comprises a content analysis subunit, and the content analysis subunit is used for extracting emotion opinions related to the evaluation emotion word stock in the evaluation characters through an evaluation emotion word stock in three dimensions of goods, logistics and services to obtain two polar comment opinion labels of good comment and bad comment.
Further, the evaluation processing module further comprises an evaluation picture analysis unit, wherein the evaluation picture analysis unit is used for respectively identifying the evaluation picture and the feature vector of the main store commodity picture, obtaining the Euclidean distance of the feature vector as a similar score, and calculating the final score of the evaluation picture through the similar score.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the embodiment of the invention discloses a commodity evaluation sequencing method and a commodity evaluation sequencing system, wherein in the process of evaluating and sequencing an e-commerce, influence factors of evaluation sequencing of buyers in the e-commerce are considered in many aspects, the evaluation content is emphasized, the quality of characters and pictures/videos is evaluated, and the influence on the evaluation sequencing is analyzed on the aspect of evaluating the characters, namely, the character expression emotion tendency, the content richness and the commodity relevancy are analyzed through a semantic analysis technology; on the aspect of evaluating the pictures, commodity relevancy, definition and similarity of the pictures and historical pictures are analyzed through a picture recognition technology, and an evaluation sequencing model is constructed through a factor analysis method, so that high-quality evaluation of commodity characteristics is displayed to consumers, and the conversion rate of commodities is improved. In addition, the operation cost of manually evaluating the commodities is obviously reduced by automatically identifying the commodity evaluation and carrying out automatic evaluation sequencing.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for ranking merchandise evaluations according to an embodiment of the present invention;
fig. 2 is a logic diagram of text scoring in the method for ranking commodity evaluations disclosed in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
as shown in fig. 1, the present embodiment provides a method for sorting commodity evaluations, including the following steps:
s1: determining the demand of a user on commodity evaluation and an influence factor related to the demand on evaluation sequencing, analyzing the influence factor by using a factor analysis method, and constructing an evaluation weight model;
s2: acquiring the evaluation data of a user on a commodity, extracting evaluation characters and an evaluation picture from the evaluation data, and respectively scoring the evaluation characters and the evaluation picture;
s3: and carrying out numerical value sorting on the total scores of the evaluation characters and the evaluation pictures through the evaluation weight model, and corresponding the numerical value sorting to the evaluation sorting of the commodities.
The intelligent ranking of the evaluations through automatic grading of characters and pictures is based on inherent attribute dimensions (evaluation characters, evaluation pictures, evaluation time and evaluation star levels) of evaluation contents and inherent attribute dimensions (membership levels) of users, an evaluation weight model is established by using a factor analysis method, each evaluation is calculated to obtain a weight value, and the weight values are displayed in a descending order on an evaluation list page. Specifically, in the process of evaluating and sequencing the e-commerce, influence factors of evaluation and sequencing of buyers in the e-commerce are considered in many aspects, the evaluation content is emphasized, the quality of characters and pictures/videos is evaluated, and the character expression emotional tendency, the content richness and the commodity relevancy are analyzed through a semantic analysis technology on the aspect of evaluating the character; on the aspect of evaluating the pictures, commodity relevancy, definition and similarity of the pictures and historical pictures are analyzed through a picture recognition technology, and an evaluation sequencing model is constructed through a factor analysis method, so that high-quality evaluation of commodity characteristics is displayed to consumers, and the conversion rate of commodities is improved. In addition, the operation cost of manually evaluating the commodities is obviously reduced by automatically identifying the commodity evaluation and carrying out automatic evaluation sequencing. The influence factors on the purchasing desire of the user in the evaluation are analyzed through big data and researched by the user, the influence factors on the influence factors of the user on the shopping emotion bias, the content richness, the commodity strong correlation degree, the correlation between the user published picture and the commodity and the picture definition in the evaluation are firstly found out, and then the character pictures in the evaluation are further separated through the influence factors, so that the representativeness and the accuracy of the subsequent scoring are improved.
Preferably, the scoring of the evaluation letter includes: and firstly, respectively analyzing the semantic emotional tendency and the content richness of the evaluation characters, and then carrying out numerical operation on the semantic emotional tendency and the content richness to obtain the final scores of the evaluation characters. Further, the semantic emotion tendency analysis distinguishes positive, negative and neutral emotion polarities by judging the confidence degree of the emotion polarity type of the evaluation character, and counts the number of negative evaluation values of the emotion polarity type. Further, the analysis of the content richness comprises the steps of extracting emotion opinions related to the evaluation emotion word library in the evaluation characters through an evaluation emotion word library with three dimensions of goods, logistics and services to obtain two polarity comment opinion labels of good comment and bad comment. The operation on the final score of the evaluation character in this embodiment is as follows: the final evaluation text score is positive label count-negative label count-T0, where positive label count indicates the number of good-rated viewpoint labels, negative label count indicates the number of bad-rated viewpoint labels, and T0 indicates the number of negative evaluations for the emotion polarity category. The calculation scoring is obtained by analyzing big data after the requirements of the evaluation display sequence are sorted and sorted according to documents and the influence factors of the evaluation display sequence related to the requirements of users (consumers and merchants), and the optimal mode of finding out the operation rule of the character scoring after a large amount of automatic sequencing can realize the technical problem solved by the invention, can well show the high-quality evaluation of the commodity characteristics to the consumers through actual verification, and improves the conversion rate of the commodity.
As shown in the logic diagram of text scoring in the commodity evaluation ordering method shown in fig. 2, the whole text evaluation process can be seen through the data call flow and the interface in all the evaluation systems from beginning to end, the newly added evaluation data of the buyer is pushed first, the evaluation of the buyer is updated in real time, then the next flow is entered for analyzing the evaluation data, the analysis process is the analysis of the semantic emotion tendency of the evaluation text and the analysis of the content richness of the evaluation text, and then the analyzed score is transmitted to the next flow for final calculation of text scoring.
Preferably, the scoring of the evaluation screen includes: and respectively identifying the feature vectors of the evaluation picture and the main picture of the shop commodity, obtaining the Euclidean distance of the feature vectors as similar scores, and calculating the final score of the evaluation picture through the similar scores. In this embodiment, the image feature vectors of the user evaluation image and the 5 main commodity images are calculated by using an image recognition model, then the euclidean distances between the feature vector of each user evaluation image and the feature vectors of the main commodity images of 5 main commodities, that is, the similarity scores, are calculated respectively, finally the highest value of the 5 similarity scores is taken as the similarity score of the user evaluation image, the number of good images and difference books in the evaluation image are counted, the definition of the image in evaluation is improved, and finally the evaluation image score is scored through the calculation model, wherein the image score calculated through the similarity scores can be calculated through the following algorithm:
example two:
the embodiment further provides a commodity evaluation ordering system, which includes:
the evaluation construction module is used for determining the demand of the user on commodity evaluation and the influence factor of the demand related to the evaluation sequence, analyzing the influence factor by using a factor analysis method and constructing an evaluation weight model;
the evaluation processing module is used for acquiring the evaluation data of the user on the commodity, extracting evaluation characters and an evaluation picture from the evaluation data, and respectively scoring the evaluation characters and the evaluation picture;
and the evaluation ranking module is used for performing numerical value ranking on the total scores of the evaluation characters and the evaluation pictures through the evaluation weight model, and the numerical value ranking corresponds to the evaluation ranking of the commodities.
The intelligent ranking of the evaluations through automatic grading of characters and pictures is based on inherent attribute dimensions (evaluation characters, evaluation pictures, evaluation time and evaluation star levels) of evaluation contents and inherent attribute dimensions (membership levels) of users, an evaluation weight model is established by using a factor analysis method, each evaluation is calculated to obtain a weight value, and the weight values are displayed in a descending order on an evaluation list page. Specifically, when the evaluation ordering is carried out through the ordering system for commodity evaluation, influence factors of buyer evaluation ordering in electronic commerce are considered in many aspects, the evaluation content is emphasized, the quality of characters and pictures/videos is evaluated, and the influence on the evaluation ordering is analyzed through a semantic analysis technology on the level of the evaluation characters, so that the character expression emotion tendency, the content richness and the commodity relevancy are analyzed; on the aspect of evaluating the pictures, commodity relevancy, definition and similarity of the pictures and historical pictures are analyzed through a picture recognition technology, and an evaluation sequencing model is constructed through a factor analysis method, so that high-quality evaluation of commodity characteristics is displayed to consumers, and the conversion rate of commodities is improved. In addition, the operation cost of manually evaluating the commodities is obviously reduced by automatically identifying the commodity evaluation and carrying out automatic evaluation sequencing.
Preferably, the evaluation processing module includes an evaluation character analysis unit, and the evaluation character analysis unit is configured to perform semantic emotion tendency analysis and content richness analysis on the evaluation characters, and then perform numerical operation on the semantic emotion tendency and the content richness to obtain a final score of the evaluation characters. Further, the evaluation character analysis unit comprises an emotion analysis subunit, and the emotion analysis subunit is used for judging the confidence degree of the emotion polarity type of the evaluation character, so as to distinguish positive, negative and neutral emotion polarities, and count the number of evaluations that the emotion polarity type is negative. Furthermore, the evaluation character analysis unit further comprises a content analysis subunit, and the content analysis subunit is used for extracting emotion opinions related to the evaluation emotion word stock in the evaluation characters through an evaluation emotion word stock in three dimensions of goods, logistics and services to obtain two polar comment opinion labels of good comment and bad comment. The emotion analysis subunit and the content analysis subunit mainly perform analysis and scoring from the evaluated emotion and content, and in the scoring process, the evaluation text score is positive label number-negative label number-T0, wherein the positive label number represents the number of good-rated viewpoint labels, the negative label number represents the number of bad-rated viewpoint labels, and T0 represents the number of evaluations that the emotion polarity category is negative. The calculation scoring is obtained by analyzing big data after the requirements of the evaluation display sequence are sorted and sorted according to documents and the influence factors of the evaluation display sequence related to the requirements of users (consumers and merchants), and the optimal mode of finding out the operation rule of the character scoring after a large amount of automatic sequencing can realize the technical problem solved by the invention, can well show the high-quality evaluation of the commodity characteristics to the consumers through actual verification, and improves the conversion rate of the commodity.
Preferably, the evaluation processing module further comprises an evaluation picture analysis unit, and the evaluation picture analysis unit is configured to identify feature vectors of the evaluation picture and the main store commodity picture, respectively, obtain a euclidean distance of the feature vectors as a similarity score, and calculate a final score of the evaluation picture through the similarity score. Calculating the characteristic vectors of the user evaluation pictures and the pictures of the 5 main commodity pictures by using the picture recognition model, respectively calculating the Euclidean distance between the characteristic vector of each user evaluation picture and the characteristic vector of the main commodity picture of 5, namely the similarity score, finally taking the highest value of the 5 similarity scores as the similarity score of the user evaluation picture, and finally scoring the evaluation picture score through the calculation model. And finally, identifying the quality of the user comments by the character scores and the picture scores, expressing the quality of the contents in a numerical form, and sequencing the contents at the same time.
All the above-mentioned optional technical solutions can be combined arbitrarily to form the optional embodiments of the present invention, and are not described herein again.
It should be noted that: in the above embodiment, when ranking the evaluation of the e-commerce, the ranking system for commodity evaluation provided in the above embodiment is only illustrated by dividing the functional modules, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the ranking system for commodity evaluation may be divided into different functional modules to complete all or part of the functions described above. In addition, the commodity evaluation ranking system provided by the above embodiment and the commodity evaluation ranking method embodiment belong to the same concept, and specific implementation processes thereof are detailed in the method embodiment and are not described herein again.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A commodity evaluation ranking method is characterized by comprising the following steps:
determining the demand of a user on commodity evaluation and an influence factor related to the demand on evaluation sequencing, analyzing the influence factor by using a factor analysis method, and constructing an evaluation weight model;
acquiring the evaluation data of a user on a commodity, extracting evaluation characters and an evaluation picture from the evaluation data, and respectively scoring the evaluation characters and the evaluation picture;
and carrying out numerical value sorting on the total scores of the evaluation characters and the evaluation pictures by using the evaluation weight model, and corresponding the numerical value sorting to the evaluation sorting of the commodities.
2. The method of claim 1, wherein scoring the evaluation script comprises: and respectively analyzing the semantic emotional tendency and the content richness of the evaluation characters, and then carrying out numerical operation on the semantic emotional tendency and the content richness to obtain the final score of the evaluation characters.
3. The method as claimed in claim 2, wherein the analysis of semantic emotion tendencies distinguishes positive, negative and neutral emotion polarities by judging confidence of emotion polarity categories of the evaluation characters, and counts the number of negative evaluations of emotion polarity categories.
4. The method for ranking commodity evaluations according to claim 2, wherein the analysis of the content richness includes extracting emotional opinions related to the evaluation emotional lexicon in the evaluation text through an evaluation emotional lexicon in three dimensions of commodity, logistics and service to obtain two polar comment opinion labels of good comment and bad comment.
5. The method of claim 1, wherein scoring the evaluation screen comprises: and respectively identifying the feature vectors of the evaluation picture and the main picture of the shop commodity, obtaining the Euclidean distance of the feature vectors as similar scores, and calculating the final score of the evaluation picture through the similar scores.
6. A system for ranking merchandise evaluations, comprising:
the evaluation construction module is used for determining the demand of the user on commodity evaluation and the influence factor of the demand related to the evaluation sequence, analyzing the influence factor by using a factor analysis method and constructing an evaluation weight model;
the evaluation processing module is used for acquiring the evaluation data of the user on the commodity, extracting evaluation characters and an evaluation picture from the evaluation data, and respectively scoring the evaluation characters and the evaluation picture;
and the evaluation ranking module is used for performing numerical value ranking on the total scores of the evaluation characters and the evaluation pictures through the evaluation weight model, and the numerical value ranking corresponds to the evaluation ranking of the commodities.
7. The system of claim 6, wherein the evaluation processing module comprises an evaluation character analysis unit, and the evaluation character analysis unit is configured to perform semantic emotion tendency analysis and content richness analysis on the evaluation characters respectively, and perform numerical operation on the semantic emotion tendency and the content richness to obtain a final score of the evaluation characters.
8. The system of claim 7, wherein the evaluation text analysis unit comprises an emotion analysis subunit, and the emotion analysis subunit is configured to determine the confidence level of the emotion polarity type of the evaluation text, so as to distinguish positive, negative, and neutral emotion polarities, and count the number of negative evaluations in the emotion polarity type.
9. The system according to claim 7, wherein the evaluation text analysis unit further comprises a content analysis subunit, and the content analysis subunit is configured to extract emotional views related to the evaluation emotion lexicon from the evaluation text through an evaluation emotion lexicon with three dimensions of goods, logistics, and services, so as to obtain two polar comment view tags, namely good comment and bad comment.
10. The system according to claim 6, wherein the evaluation processing module further comprises an evaluation picture analysis unit configured to identify feature vectors of the evaluation picture and the main store product picture, respectively, obtain euclidean distances of the feature vectors as similarity scores, and calculate final scores of the evaluation pictures from the similarity scores.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010350718.9A CN111667337A (en) | 2020-04-28 | 2020-04-28 | Commodity evaluation ordering method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010350718.9A CN111667337A (en) | 2020-04-28 | 2020-04-28 | Commodity evaluation ordering method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111667337A true CN111667337A (en) | 2020-09-15 |
Family
ID=72382903
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010350718.9A Pending CN111667337A (en) | 2020-04-28 | 2020-04-28 | Commodity evaluation ordering method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111667337A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112395324A (en) * | 2020-11-09 | 2021-02-23 | 艾迪安逊教育科技发展(广州)有限公司 | Big data storage system for online education platform |
CN112927034A (en) * | 2021-01-28 | 2021-06-08 | 长沙市到家悠享网络科技有限公司 | Information processing method and device |
CN114202389A (en) * | 2021-10-27 | 2022-03-18 | 杭州拼便宜网络科技有限公司 | User evaluation control method and device, electronic equipment and storage medium |
CN114387009A (en) * | 2021-12-10 | 2022-04-22 | 北京卓思天成数据咨询股份有限公司 | Customer demand determination method, device, equipment and computer readable storage medium |
CN115526690A (en) * | 2022-10-21 | 2022-12-27 | 鹏展万国电子商务(深圳)有限公司 | Commodity ordering system and method based on artificial intelligence |
CN115983873A (en) * | 2022-12-29 | 2023-04-18 | 珠海蓝度科技有限公司 | Big data based user data analysis management system and method |
CN116308684A (en) * | 2023-05-18 | 2023-06-23 | 和元达信息科技有限公司 | Online shopping platform store information pushing method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017051425A1 (en) * | 2015-09-23 | 2017-03-30 | Devanathan Giridhari | A computer-implemented method and system for analyzing and evaluating user reviews |
CN108960944A (en) * | 2017-05-17 | 2018-12-07 | 北京京东尚科信息技术有限公司 | User's evaluation processing method and processing device, computer-readable medium, electronic equipment |
CN109377080A (en) * | 2018-11-13 | 2019-02-22 | 平安科技(深圳)有限公司 | Commodity evaluation method, device, computer equipment and storage medium |
CN110766502A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Commodity evaluation method and system |
-
2020
- 2020-04-28 CN CN202010350718.9A patent/CN111667337A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017051425A1 (en) * | 2015-09-23 | 2017-03-30 | Devanathan Giridhari | A computer-implemented method and system for analyzing and evaluating user reviews |
CN108960944A (en) * | 2017-05-17 | 2018-12-07 | 北京京东尚科信息技术有限公司 | User's evaluation processing method and processing device, computer-readable medium, electronic equipment |
CN110766502A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Commodity evaluation method and system |
CN109377080A (en) * | 2018-11-13 | 2019-02-22 | 平安科技(深圳)有限公司 | Commodity evaluation method, device, computer equipment and storage medium |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112395324A (en) * | 2020-11-09 | 2021-02-23 | 艾迪安逊教育科技发展(广州)有限公司 | Big data storage system for online education platform |
CN112927034A (en) * | 2021-01-28 | 2021-06-08 | 长沙市到家悠享网络科技有限公司 | Information processing method and device |
CN114202389A (en) * | 2021-10-27 | 2022-03-18 | 杭州拼便宜网络科技有限公司 | User evaluation control method and device, electronic equipment and storage medium |
CN114387009A (en) * | 2021-12-10 | 2022-04-22 | 北京卓思天成数据咨询股份有限公司 | Customer demand determination method, device, equipment and computer readable storage medium |
CN114387009B (en) * | 2021-12-10 | 2023-08-04 | 北京卓思天成数据咨询股份有限公司 | Customer demand determining method, apparatus, device and computer readable storage medium |
CN115526690A (en) * | 2022-10-21 | 2022-12-27 | 鹏展万国电子商务(深圳)有限公司 | Commodity ordering system and method based on artificial intelligence |
CN115983873A (en) * | 2022-12-29 | 2023-04-18 | 珠海蓝度科技有限公司 | Big data based user data analysis management system and method |
CN116308684A (en) * | 2023-05-18 | 2023-06-23 | 和元达信息科技有限公司 | Online shopping platform store information pushing method and system |
CN116308684B (en) * | 2023-05-18 | 2023-08-11 | 和元达信息科技有限公司 | Online shopping platform store information pushing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111667337A (en) | Commodity evaluation ordering method and system | |
CN107861972B (en) | Method and equipment for displaying full commodity result after user inputs commodity information | |
CN107391493B (en) | Public opinion information extraction method and device, terminal equipment and storage medium | |
CN107833082B (en) | Commodity picture recommendation method and device | |
CN111260437B (en) | Product recommendation method based on commodity-aspect-level emotion mining and fuzzy decision | |
CN110489457B (en) | Commodity information analysis method and system based on image recognition and storage medium | |
CN109584006B (en) | Cross-platform commodity matching method based on deep matching model | |
CN112015721A (en) | E-commerce platform storage database optimization method based on big data | |
CN107832338B (en) | Method and system for recognizing core product words | |
CN109101553B (en) | Purchasing user evaluation method and system for industry of non-beneficiary party of purchasing party | |
US11599927B1 (en) | Artificial intelligence system using deep neural networks for pairwise character-level text analysis and recommendations | |
CN112884542A (en) | Commodity recommendation method and device | |
CN111324698B (en) | Deep learning method, evaluation viewpoint extraction method, device and system | |
CN111310038A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
CN114997956B (en) | Mother and infant product intelligent recommendation system based on big data | |
US10445793B2 (en) | Review text output system and review text output method | |
CN116579351B (en) | Analysis method and device for user evaluation information | |
CN112949322A (en) | E-commerce opinion mining recommendation system driven by online text comments | |
CN113744019A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium | |
CN111639184A (en) | Detection system for tendency inconsistency of scores and comment contents | |
CN108009726B (en) | Object evaluation system combining user comments | |
CN114155057A (en) | Commodity recommendation system for electronic commerce platform | |
US20240062264A1 (en) | Ai- backed e-commerce for all the top rated products on a single platform | |
CN115659961A (en) | Method, apparatus and computer storage medium for extracting text viewpoints | |
CN115131108A (en) | E-commerce commodity screening system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200915 |