Method and device for determining user similarity based on multi-category information
A technology of user similarity and category information, applied in the field of user similarity determination method and device based on multi-category information, can solve the problems of low accuracy of user similarity, waste of resources, inaccurate information recommendation, etc.
Active Publication Date: 2021-03-23
TSINGHUA UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in the process of realizing the present invention, the inventor found that the above-mentioned methods in the related art have at least the following technical problems: the above-mentioned methods all rely solely on one type of data for user similarity calculation, and the accuracy of the determined user similarity The accuracy is not high, which leads to inaccurate information recommendation and waste of resources
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
[0027] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.
[0028] In the description of the present invention, it should be understood that the term "plurality" refers to two or more than two; sex.
[0029] In related technologies, when calculating user similarity, it usually relies solely on one type of data to calculate user similarity, and the accuracy of the determined user similarity is not high, which in turn leads to inaccurate information recommendation and resource shortage. waste.
[0030] To this end, this application proposes a user similarity determination method based on multi-ca...
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 present invention proposes a user similarity determination method and device based on multi-category information, wherein the method includes: after obtaining different categories of information in a unified form in the extended adjacency matrix, using the first extended adjacency matrix to obtain the first user The row vector of the second user and the row vector of the second user, and the improved deep autoencoder network performs feature extraction on the data, and generates a highly abstract feature representation for the first user and the second user. Subsequently, the pre-trained improved Siamese neural network model is used to learn the difference between highly abstract features to determine the similarity between the first user and the second user. Thus, through the complementary advantages of different categories, combined with the information of different categories of users, the similarity between users is accurately calculated, which lays the foundation for accurate information recommendation to users in the future.
Description
technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for determining user similarity based on multi-category information. Background technique [0002] With the rapid development of mobile Internet technology, mobile Internet-based applications have sprung up like mushrooms after rain. Therefore, the mobile Internet has accumulated a large amount of data, including online social relationship data between users, location data added by Moments, pictures and texts shared by Weibo, and other data. In fact, these data reflect the user's behavior habits and personality preferences to a certain extent. The information hidden behind the data can be used for friend recommendation in social networks, personalized product recommendation in e-commerce platforms, and information flow advertising. Precise advertising recommendation. This can not only create better revenue for service providers, but also improve user exper...
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): G06K9/62G06F16/9535G06Q30/06G06Q30/02
CPCG06F16/9535G06Q30/0631G06Q30/0251G06F18/22
Inventor 徐恪赵乙
Owner TSINGHUA UNIV