A dynamic recommendation method based on user interest adaptive evolution

A technology of user interests and recommendation methods, applied in the field of dynamic recommendation based on the adaptive evolution of user interests, can solve the problems of decreased recommendation accuracy, lower recommendation accuracy, and ignore changes in the interests of recommendation subjects, and achieve the effect of increasing accuracy
CN109933720AActive Publication Date: 2019-06-25SHANTOU UNIV
4 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHANTOU UNIV
Publication Date
2019-06-25

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a dynamic recommendation method based on user interest adaptive evolution, which comprises the following steps: firstly establishing a user interest model of each user, then segmenting user interest vectors according to a time sequence, calculating the similarity among the users, screening out a plurality of to-be-recommended users, and fully considering the characteristicthat the user interest is changed along with time; Based on historical comment records of the target user and the to-be-recommended user, obtaining a recommendation result; constructing a historical interest sequence matrix His; and performing interest evolution iteration for preset times through a PSO (Particle Swarm Optimization) algorithm to obtain a recommendation priority sequence of the target user and each user in the to-be-recommended user set, and finally recommending the users which are screened out from the to-be-recommended user set and ranked in front to the target user. By the adoption of the technical scheme, the stability of the recommendation result is controlled, meanwhile, the interest change of the user is reasonably simulated, and the recommendation accuracy, predictability and comprehensiveness are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical field

[0001] The invention relates to the field of computer technology, in particular to a dynamic recommendation method based on the adaptive evolution of user interests. Background technique

[0002] The recommendation system changes the passive mode of search engines to the mode of actively pushing information to users, while also providing users with a different, convenient and comfortable experience and effective information. Most current recommendation models tend to recommend resources that meet their interests, preferences or needs, such as web pages, movies, commodities, tags, and so on. Since the recommendation system of each platform is designed according to the characteristics of their respective platforms, they are very different in terms of their recommendation targets and purposes. Therefore, it is necessary to design suitable friend recommendations based on the actual situation and characteristics of the question-and-answer social network Algorithm. [0...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More