CN112801745A - Big data platform based online comment validity recommendation method - Google Patents
Big data platform based online comment validity recommendation method Download PDFInfo
- Publication number
- CN112801745A CN112801745A CN202110140738.8A CN202110140738A CN112801745A CN 112801745 A CN112801745 A CN 112801745A CN 202110140738 A CN202110140738 A CN 202110140738A CN 112801745 A CN112801745 A CN 112801745A
- Authority
- CN
- China
- Prior art keywords
- comment
- publication
- comments
- keywords
- big data
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
-
- 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
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
Abstract
The invention belongs to the technical field of electronic commerce application, and relates to a recommendation method for online comment validity based on a big data platform. Extracting corresponding keywords according to the questions of consumers in the similar products to the products; formulating a comment set of the commodity according to the keywords and all comments of the extracted keywords on a certain commodity; assigning a time to publication for each comment, wherein publication within three days is 1, publication within one week is 0.9, publication within two weeks is 0.8, publication within three weeks is 0.7, publication within one month is 0.6, publication within three months is 0.5, publication within half a year is 0.3, publication within one year is 0.1; according to the formula:wherein, CgFor the recommended value of a certain comment of the commodity, T is the time value of the comment, k is all keywords contained in the comment, TC is the total number of the comment of the commodity, and KCiThe number of comments for a certain keyword; and finally, recommending according to the magnitude of the recommended value obtained by calculation in the order from large to small.
Description
Technical Field
The invention belongs to the technical field of electronic commerce application, and particularly relates to a recommendation method for online comment validity based on a big data platform.
Background
With the rapid development of society and economy, especially the unprecedented prosperity of internet technology, the life style of people is changed, and more consumers tend to shop online. Electronic commerce websites such as Taobao, Jingdong, Shuduo, Amazon and the like are rapidly expanded, and the number of commodities and the scale of users are in an explosive growth trend. Meanwhile, with the rapid development of the internet and information technology, the original electronic commerce mode taking the enterprise as a center is changed into social electronic commerce taking consumers as the center, the consumers can actively transmit information instead of passively receiving product information released by enterprises, and the data shows an explosive growth trend when entering a big data era globally. Consumers and enterprises enjoy abundant network information to bring convenience, and meanwhile suffer from the trouble caused by the problem of information overload.
In the face of the full-line commodities on the existing e-commerce websites, countless users make countless comments aiming at the feelings of the users, and 'information overload' of comment information is caused. In the face of such a thick information gold mine, the existing e-commerce website expects to efficiently extract valuable comments from the information gold mine and present the comments to the user, so as to help the user to know commodity information and shorten the purchasing decision time of the user. Meanwhile, as the security and convenience of mobile payment are greatly improved, more and more users shop through mobile terminals, and the user wants to acquire more commodity information by browsing as few comments as possible in consideration of the limitations of actual scenes and screen sizes, so that if the optimal comments are recommended to the user, the recommendation of the optimal comments becomes the direction of the current e-commerce website key research.
Disclosure of Invention
Aiming at the technical problems existing in the overload of the comment information, the invention provides the recommendation method based on the online comment validity of the big data platform, which has the advantages of reasonable design and simple method and can effectively recommend the optimal comment.
In order to achieve the purpose, the invention adopts the technical scheme that the invention provides a recommendation method of online comment validity based on a big data platform, which comprises the following effective steps:
A. firstly, extracting corresponding keywords according to questions of consumers in the similar products to the products;
B. formulating a comment set of the commodity according to the keywords and all comments of the extracted keywords on a certain commodity;
C. assigning a time to publication for each comment, wherein publication within three days is 1, publication within one week is 0.9, publication within two weeks is 0.8, publication within three weeks is 0.7, publication within one month is 0.6, publication within three months is 0.5, publication within half a year is 0.3, publication within one year is 0.1;
D. according to the formula:
wherein, CgFor the recommended value of a certain comment of the commodity, T is the time value of the comment, k is all keywords contained in the comment, TC is the total number of the comment of the commodity, and KCiThe number of comments for a certain keyword;
E. and finally, recommending according to the magnitude of the recommended value obtained by calculation in the order from large to small.
Preferably, in the step B, the comment includes an initial comment and an additional comment.
Preferably, in the step C, when one comment has an additional comment, the additional comment is assigned with the posting time of the additional comment.
Preferably, in the step D, k is all keywords except the logistics information in the review.
Preferably, in the step E, comments with less consistent keywords and less scores in the comments are removed in a collaborative filtering manner, and the comments with scores later are referred to.
Preferably, in the step E, comments with the same keyword in the comments are removed in a collaborative filtering manner, and only the first five comments with higher scores are included.
Compared with the prior art, the invention has the advantages and positive effects that,
1. the invention provides a recommendation method for online comment validity based on a big data platform, which analyzes the validity of comments by taking the information of questions asked by a consumer to a merchant as a keyword through consideration from the perspective of the consumer, further solves the problems of the existing comments, and is simple, safe, reliable and suitable for large-scale popularization and use.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, the present invention will be further described with reference to the following examples. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and thus the present invention is not limited to the specific embodiments of the present disclosure.
Embodiment 1, this embodiment provides a recommendation method for online review validity based on a big data platform,
firstly, extracting corresponding keywords according to questions of consumers to the products in the same kind of products, in order to reduce unnecessary disputes, the electronic commerce website increases the question function of the customers to the products, the purpose of reducing the comments watched by the consumers is achieved by customer service or the answers of the consumers to the questions, the problems of brand problems or prices and the like are considered, the problems belong to special problems of the products, the special problems are probably not mainly reflected in the comments of some consumers, the problems are probably of different meanings to other consumers, therefore, the keywords of all the problems of the same kind of products are extracted, the products can be more comprehensively displayed, and the consumers can learn the products from the perspective of the consumers.
And then, establishing a comment set of the commodity according to all comments of the extracted keywords to the certain commodity and the keywords, wherein the main purpose of establishing the comment set is to determine the proportion of the keywords in the commodity, if one keyword appears in a plurality of comments, the keyword belongs to the point which is intended by a consumer for the commodity, and certainly, one comment may appear in different comment sets.
Considering that the updating of some commodities is fast, therefore, the influence of the reviews with the closer publication time on consumers is larger, and therefore, the publication time of each review is assigned, wherein the publication time within three days is 1, the publication time within one week is 0.9, the publication time within two weeks is 0.8, the publication time within three weeks is 0.7, the publication time within one month is 0.6, the publication time within three months is 0.5, the publication time within half year is 0.3, and the publication time within one year is 0.1.
Then, calculating a recommended value of a certain comment of the commodity according to a formula:
wherein, CgFor the recommended value of a certain comment of the commodity, T is the time value of the comment, k is all keywords contained in the comment, TC is the total number of the comment of the commodity, and KCiConsidering that logistics may be the most concerned problem of consumers in electronic commerce transactions, the logistics percentage is the highest among all reviews, and thus some excellent reviews which do not record logistics information may have errors, and k is all keywords excluding logistics information in the reviews. Thus, given the removal of the logistic score, the recommendation for a good will have a time and review proportion.
And finally, recommending according to the order from large to small according to the size of the recommended value obtained by calculation, considering that the comments with the same keyword are possibly many, and all the comments displayed in the ranking recommendation mode are the same type of comments. Collaborative filtering recommendations are rapidly becoming a very popular technology in information filtering and information systems. Different from the traditional recommendation based on content filtering and direct content analysis, the method is characterized in that the interest of the user is analyzed through collaborative filtering, similar (interested) users of the specified user are found in the user group, and the preference degree prediction of the specified user on the information is formed through the evaluation of the similar users on the information. Therefore, similar comments can be selected through the collaborative filtering algorithm, then the ranked similar comments are not ranked any more, and other comments in the later place are forwarded, so that the comprehensiveness of the comments is facilitated.
Considering that the comment of the same user may have additional comments, for this reason, the comment includes the initial comment and the additional comment. When one comment has an additional comment, the additional comment is assigned with the posting time of the additional comment. In the comment recommendation value calculation, the initial comment and the additional comment are determined as the entire comment.
Through the arrangement, the keywords are extracted from the viewpoint of the consumer, the incompleteness of extracting the keywords by the existing merchants is solved, the calculation complexity of extracting the keywords from all the comments is solved, in addition, the scores obtained by adding time assignment to the percentage scores of the keywords in all the comments are determined to be the recommended value of a certain comment, the accuracy and the comprehensiveness of the recommended value are further ensured, and the effectiveness of online comment recommendation is guaranteed.
The above description is only a preferred embodiment of the present invention, and not intended to limit the present invention in other forms, and any person skilled in the art may apply the above modifications or changes to the equivalent embodiments with equivalent changes, without departing from the technical spirit of the present invention, and any simple modification, equivalent change and change made to the above embodiments according to the technical spirit of the present invention still belong to the protection scope of the technical spirit of the present invention.
Claims (6)
1. A recommendation method for online comment validity based on a big data platform is characterized by comprising the following effective steps:
A. firstly, extracting corresponding keywords according to questions of consumers in the similar products to the products;
B. formulating a comment set of the commodity according to the keywords and all comments of the extracted keywords on a certain commodity;
C. assigning a time to publication for each comment, wherein publication within three days is 1, publication within one week is 0.9, publication within two weeks is 0.8, publication within three weeks is 0.7, publication within one month is 0.6, publication within three months is 0.5, publication within half a year is 0.3, publication within one year is 0.1;
D. according to the formula:
wherein, CgFor the recommended value of a certain comment of the commodity, T is the time value of the comment, k is all keywords contained in the comment, TC is the total number of the comment of the commodity, and KCiThe number of comments for a certain keyword;
E. and finally, recommending according to the magnitude of the recommended value obtained by calculation in the order from large to small.
2. The big data platform-based recommendation method for online comment validity according to claim 1, wherein in the step B, the comments comprise initial comments and additional comments.
3. The big data platform-based online comment validity recommendation method according to claim 2, wherein in the step C, in the case that one comment has an additional comment, the additional comment is assigned with the posting time of the additional comment.
4. The big data platform-based recommendation method for online comment validity according to claim 3, wherein in the step D, k is all keywords except logistics information contained in the comment.
5. The big data platform-based online comment validity recommendation method according to claim 4, wherein in the step E, comments with consistent keywords and low scores in the comments are removed in a collaborative filtering manner, and the comments with low scores later are promoted.
6. The big data platform-based online comment validity recommendation method according to claim 5, wherein in the step E, comments with consistent keywords in the comments are removed in a collaborative filtering manner, and only the first five comments with higher scores are included.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110140738.8A CN112801745A (en) | 2021-02-02 | 2021-02-02 | Big data platform based online comment validity recommendation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110140738.8A CN112801745A (en) | 2021-02-02 | 2021-02-02 | Big data platform based online comment validity recommendation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112801745A true CN112801745A (en) | 2021-05-14 |
Family
ID=75813650
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110140738.8A Pending CN112801745A (en) | 2021-02-02 | 2021-02-02 | Big data platform based online comment validity recommendation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112801745A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893350A (en) * | 2016-03-31 | 2016-08-24 | 重庆大学 | Evaluating method and system for text comment quality in electronic commerce |
CN107577759A (en) * | 2017-09-01 | 2018-01-12 | 安徽广播电视大学 | User comment auto recommending method |
CN109408726A (en) * | 2018-11-09 | 2019-03-01 | 大连海事大学 | Question answering person's recommended method in question and answer website |
CN110362662A (en) * | 2018-04-09 | 2019-10-22 | 北京京东尚科信息技术有限公司 | Data processing method, device and computer readable storage medium |
CN111242729A (en) * | 2020-01-07 | 2020-06-05 | 西北工业大学 | Serialization recommendation method based on long-term and short-term interests |
CN111666413A (en) * | 2020-06-09 | 2020-09-15 | 重庆邮电大学 | Commodity comment recommendation method based on reviewer reliability regression prediction |
CN112052401A (en) * | 2020-08-26 | 2020-12-08 | 南京邮电大学 | Recommendation method based on user comments |
-
2021
- 2021-02-02 CN CN202110140738.8A patent/CN112801745A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893350A (en) * | 2016-03-31 | 2016-08-24 | 重庆大学 | Evaluating method and system for text comment quality in electronic commerce |
CN107577759A (en) * | 2017-09-01 | 2018-01-12 | 安徽广播电视大学 | User comment auto recommending method |
CN110362662A (en) * | 2018-04-09 | 2019-10-22 | 北京京东尚科信息技术有限公司 | Data processing method, device and computer readable storage medium |
CN109408726A (en) * | 2018-11-09 | 2019-03-01 | 大连海事大学 | Question answering person's recommended method in question and answer website |
CN111242729A (en) * | 2020-01-07 | 2020-06-05 | 西北工业大学 | Serialization recommendation method based on long-term and short-term interests |
CN111666413A (en) * | 2020-06-09 | 2020-09-15 | 重庆邮电大学 | Commodity comment recommendation method based on reviewer reliability regression prediction |
CN112052401A (en) * | 2020-08-26 | 2020-12-08 | 南京邮电大学 | Recommendation method based on user comments |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Durmaz et al. | Travel from traditional marketing to digital marketing | |
Cheng et al. | Personalized click prediction in sponsored search | |
Makki et al. | Understanding the effects of social media and mobile usage on e-commerce: an exploratory study in Saudi Arabia | |
CN103246980B (en) | Information output method and server | |
CN104463630A (en) | Product recommendation method and system based on characteristics of online shopping insurance products | |
US20150254714A1 (en) | Systems and methods for keyword suggestion | |
CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
Cherqi et al. | Analysis of hacking related trade in the darkweb | |
CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
Lin et al. | A consumer review-driven recommender service for web e-commerce | |
Wu et al. | Keyword extraction for contextual advertisement | |
Bang et al. | Product recommendation system based on user purchase priority | |
Kumar et al. | Cuisine prediction based on ingredients using tree boosting algorithms | |
Zhao et al. | Tourism e-commerce recommender system based on web data mining | |
He et al. | Understanding Users' Coupon Usage Behaviors in E-Commerce Environments | |
CN112801745A (en) | Big data platform based online comment validity recommendation method | |
TWM633789U (en) | Matching system | |
CN113807896A (en) | Big data user mining method based on people shaking e-commerce platform | |
CN114155057A (en) | Commodity recommendation system for electronic commerce platform | |
CN113254775A (en) | Credit card product recommendation method based on client browsing behavior sequence | |
Kamepalli et al. | Weighted Based Frequent and Infrequent Pattern Mining Model for Real-Time E-Commerce Databases | |
Ming | Application research of customer big data analysis for online shop based on smart cloud platform tools | |
Shah et al. | A methodology for brand name hierarchical clustering based on social media data | |
Wu et al. | Clustering technology application in e-commerce recommendation system | |
Rajapaksha et al. | Recommendations to Increase the Customer Interaction of E-commerce Applications with Web Usage Mining |
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 |
Application publication date: 20210514 |
|
RJ01 | Rejection of invention patent application after publication |