Case-reasoning-based personalized recommendation method for E-commerce website commodity

Abstract

The invention relates to a case-reasoning-based personalized recommendation method for an E-commerce website commodity. An objective problem is constructed according to a feature and an access behavior of a current access user and an original case is established according to features, historical access behaviors, and purchase records of other users; a fuzzy clustering way is used for carrying out clustering according to a target case feature, cases with high similarity levels of user features and interests and the like are classified into the same class and the class is identified, and a high-similarity-level case base is established; and a resolved case set most similar to the target user case is recommended by using a user case similarity retrieval and an improved fuzzy mean clustering algorithm and then is corrected and reused, and a dynamic case base is also updated. According to the invention, the system real-time performance is enhanced; and a problem that the previous recommendation system relies too much on commodity evaluation by users can be solved.

Description

technical field [0001] The invention belongs to the field of computer technology, and relates to e-commerce personalized recommendation technology, in particular to a case-based reasoning method for personalized recommendation of commodities on an e-commerce website. , Background technique [0002] In the "big data network environment", e-commerce companies are required to use big data processing systems to track consumers from unconscious website browsing to product purchases and post-purchase behaviors, and to make more real-time and more personalized solutions for the individual needs of different consumers. recommended. Conventional personalized recommendation technology learns user interests and behaviors by collecting and analyzing user information, and it is difficult to update in real time and actively provide fine personalized recommendation information to users. At the same time, the system collects high-dimensional sparsity of user information and behaviors, and...

AI Technical Summary

Problems solved by technology

Conventional personalized recommendation technology learns user interests and behaviors by collecting and analyzing user information, and it is difficult to update in real time and proactively provide fine personalized recommendation information to users

At the same time, the system collects high-dimensional sparsity of user information and behaviors, and it is difficult to use these scarce information to provide accurate recommendations for other users. With the increase of users, the information becomes more and more abundant. In order to better provide personalized How to quickly and effectively utilize these user preferences and historical purchase behaviors has become a very important issue

[0003] The current personalized recommendation can make personalized recommendations for users based on the known user characteristics and massive information on product evaluations. evaluation and provide more real-time personalized recommendations, which cannot be achieved by current recommendation schemes

Images