Label system accurate recommendation method based on user comment analysis

Abstract

The invention provides a label system accurate recommendation method based on user comment analysis. The interest model is constructed according to the user-commodity-label ternary relation, the accurate recommendation method more suitable for the label system is obtained, and in view of the problems that label information data of users in the label system generally has data sparseness and the user similarity calculated by using sparse data is low in accuracy, user comment data is creatively introduced, text analysis on user comment information is carried out, Chinese word segmentation and keyword extraction on the comment information are carried out, the extracted keywords are taken as pseudo tags, user labels are extracted, the label information data is expanded, the problem of label information data sparseness is solved, meanwhile, based on the fact that user comment information contains user preferences, value assignment calculation is conducted on emotion words in the comment information, the score value of a user for a commodity is obtained from user comments, the obtained score value information is used for further improving a label algorithm, and the accuracy of a recommendation result is improved.

Description

technical field [0001] The invention relates to a customized and precise recommendation method for commodities, in particular to a precise recommendation method for a label system based on analysis of user comments, and belongs to the technical field of commodity customization and recommendation. Background technique [0002] With the rapid popularization and development of the Internet, especially the mobile Internet, people can obtain massive resources from the Internet. However, the continuous increase of resources on the Internet also makes it more and more difficult for people to obtain the resources they need. Although search engines can solve part of the information overload problem, the accuracy of search results is largely based on the keywords entered by users. At present, the display area of ​​many systems is very limited, and it is necessary to display as many information resources that users are interested in as possible within the limited area in order to bett...

AI Technical Summary

Problems solved by technology

[0015] Improve the collaborative filtering recommendation method based on the label system, add the user comment information in the label system to the recommendation process, perform Chinese word segmentation and keyword extraction on the comment information, and use the extracted keywords as pseudo-labels to solve the problem of labeling. For the problem of sparse information data, assign and calculate the emotional words in the comment information, obtain the user's rating value for the product from the user comment, and use the obtained rating value information to further improve the labeling algorithm;

Images