CNN-based social niche user tag mining and similar user recommendation method
A recommendation method and user technology, applied in the field of social network technology processing, can solve problems such as difficulty in finding common users, difficulties in representative labels, etc.
Active Publication Date: 2022-07-12
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, niche users use fewer tags than active users and provide less personal information, which brings great difficulties to extract representative tags of common niche users
Since the information provided by ordinary niche users is relatively small, it is difficult to find groups that ordinary users are interested in
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
[0048] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0049] figure 1 This is the overall method flow chart of the embodiment of the present invention. A representative label recommendation method for ordinary niche users in social networks based on personalized CNN, figure 2 It is a schematic diagram of the improved personalized CNN model of the present invention. On the basis of the original CNN model, user personalized attribute features are added, including but not limited to the ...
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 relates to the field of social network technology processing, in particular to a method for tag mining of social niche users and recommendation of similar users based on CNN, comprising: obtaining original content data published by users on social software, preprocessing; obtaining through a word2vec model Word vector feature; input the preprocessed content data into the word embedding layer, take the position of each word in word2vec, find the word vector corresponding to each word; obtain the user's personal attribute feature vector info, and put the word vector The feature is combined with the personal attribute feature vector info to form an input matrix; the input matrix is input into the CNN model to obtain the user's hashtag; the social network graph is constructed through the clustering algorithm, and the groups similar to the user or the groups of interest to the user are output; Recommend hashtags and groups to users. The present invention solves the problem of topic recommendation and related group recommendation for users with less information on the social network.
Description
technical field [0001] The invention relates to the field of social network technology processing, in particular to a CNN-based social niche user tag mining and similar user recommendation method. Background technique [0002] With the development of society, social software has become one of the popular platforms for people to communicate, expand interpersonal relationships, and share their lives. Some people who use social software know how to show others about themselves and topics they are interested in. Others can find them through the system or platform, and the system can also recommend content that users may like based on their personal information and historical data, as well as those related to the system. User's other users with similar interests. However, most users do not show their interests on social networks. These users have only a small number of followers and fans. They do not know what topics they are interested in, and they do not often post news on soc...
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): G06F16/9536G06F16/33G06K9/62G06N3/04G06N3/08G06Q50/00
CPCG06F16/9536G06F16/3335G06F16/3344G06N3/08G06Q50/01G06N3/047G06N3/048G06N3/045G06F18/241G06F18/2415
Inventor 陈贤罗朗王豪
Owner CHONGQING UNIV OF POSTS & TELECOMM