A recommendation method based on the influence of multiple interests of neighbor users
A neighbor user and recommendation method technology, applied in the field of recommendation based on user interests, can solve the problem of not being able to consider neighbor users in a fine-grained manner, and achieve the effect of improving the recommendation effect and accuracy
Active Publication Date: 2021-10-29
NORTHEASTERN UNIV LIAONING
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of the deficiencies in the prior art above, the purpose of this application is to provide a recommendation method based on the influence of multiple interests of neighboring users, aiming to solve the problem that the existing recommendation system cannot fine-grainedly consider the influence of interests among neighboring users in social networks. question
Method used
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
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0054] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Preferred embodiments of the application are shown in the accompanying drawings. However, the present application can be embodied in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the application more thorough and comprehensive.
[0055] In order to solve the problem that the existing recommendation system cannot fine-grainedly consider the influence of the interests of neighboring users in social networks, the solution provided by this application is: a recommendation method based on multiple interests of neighboring users. The neighbors of each user are randomly sampled to obtain K interest-aware graphs, and each interest-aware graph represents an interest-influence relationship betwe...
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 PUM
Login to View More Abstract
The invention discloses a recommendation method based on the influence of multiple interests of neighboring users, and belongs to the technical field of recommendation methods based on user interests. Randomly sample each user’s neighbors according to the social relationship graph to obtain K interest-aware graphs; perform graph convolution operations on each interest-aware graph to aggregate the mutual influence of a single interest among users; in the user-item interaction graph Through the graph convolution operation, the project information that the user has interacted with and the user information that the project has been interacted with are aggregated; the results obtained by the above two aggregation steps are elementally spliced to obtain the result of the first convolutional layer; the above-mentioned iterations are repeated multiple times Graph convolution operation; the results of multiple convolutional layers are fused with attention to obtain the final embedding vector of the user and the item, and the probability that the user may interact with the item is obtained through the vector inner product, and then the recommendation list is obtained. This method enables the recommendation system to make full use of the influence of social networks and improve the recommendation effect.
Description
technical field [0001] The present invention relates to a recommendation method based on user interests, more specifically to a recommendation method based on the influence of multiple interests of neighboring users. Background technique [0002] In recent years, online social networks have gradually become popular in our lives, and more and more people like to express their interests and preferences on social platforms, which can provide reliable information for users' follow-up demand analysis and recommended items for users. basis. Therefore, we can use the social relationship between users to alleviate the data sparsity problem in the recommendation system. In the existing recommendation system, in order to accurately recommend items that users may like, the recommendation system needs to fully explore the mutual influence of multiple interests among users according to the characteristics of interests among users, and finally improve the recommendation system. accuracy...
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 Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/9536G06Q50/00G06N3/04
CPCG06F16/9536G06Q50/01G06N3/048G06N3/045
Inventor 于瑞云汪志鸿张碧耘
Owner NORTHEASTERN UNIV LIAONING