Product Recommendation Method Based on Selective Neighborhood Information

Abstract

The invention discloses a product recommendation method based on selective neighborhood information. The method includes: obtaining the interest preference of the target user; obtaining the attribute characteristics of the product; obtaining all users who have historical scoring records with the product, and using all users as Neighborhood information of the target user under the product and determine their interest preferences; determine the similarity of the interest preferences of the target user and each user in the neighborhood information; fuse the interest preferences of the neighborhood information to obtain the neighborhood characteristics of the target user information; determine the availability of neighborhood feature information; obtain target user feature information based on neighborhood information; obtain the target user's predicted score for the product; select several products with the largest predicted score to recommend to the target user. The method of the present invention regards neighborhood information as a kind of auxiliary information, automatically filters out similar neighborhood information, and captures the consistency of interest preferences between users and their neighborhood information, which can effectively alleviate the problem of data sparsity and significantly improve recommendation accuracy.

Description

technical field [0001] The invention relates to the technical field of commodity recommendation systems, in particular to a commodity recommendation method based on selective neighborhood information. Background technique [0002] Personalized recommendation technology mainly analyzes the behavior of different users, guesses user interests, and actively recommends resources to users, thereby alleviating the contradiction between the Internet information explosion and users' rapid acquisition of information, and also making up for the weak ability of general search engines to provide personalized feedback results. shortcoming. [0003] With the continuous development of e-commerce and the continuous expansion of the scale, the number and types of goods are also increasing rapidly, which makes customers spend a lot of time in selecting the goods they need, and buy products that suit them in a short period of time. Commodities have become the development direction of online sh...

AI Technical Summary

Problems solved by technology

[0006] Although the existing recommendation methods can improve the recommendation effect by using the neighborhood information as auxiliary information; however, the existing recommendation methods introduce the neighborhood information into the recommendation process indiscriminately, ignoring the impact of the neighborhood information on the user. There are individual differences in the usability of the user. Because some users' interest preferences do not depend on the user's neighborhood information, the neighborhood information is introduced without distinction. On the contrary, it introduces interference information into the recommendation process, affects the recommendation performance, and makes the recommendation In addition, when the existing recommendation method introduces neighborhood information, it does not explicitly model the semantic similarity between the user and the user's neighborhood, resulting in the inability to efficiently capture the user's relationship with the user. The similarity between the neighbors, the recommendation effect is not good

Images