Personalized recommendation method and system based on connection matrix
A technology of connection matrix and recommendation method, applied in instruments, data processing applications, business, etc., can solve the problem of loss of semantic relationship of NRL algorithm, achieve good application prospects, improve prediction accuracy and personalized recommendation performance.
Active Publication Date: 2021-08-10
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004]
To this end, the present invention provides a method and system for personalized recommendation based on connection matrix, which solves the problem of loss of semantic relationship based on meta-path NRL algorithm in HIN, and optimizes the performance of personalized recommendation
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
[0031] In order to make the purpose, technical solution and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and technical solutions.
[0032] How to use the user's social information and product relationship information to build a prediction model and improve the performance of prediction is a difficult and hot topic in the field of recommendation system research. An embodiment of the present invention provides a connection matrix-based personalized recommendation method, see figure 1 As shown, it contains the following content:
[0033] S101. Construct a user relationship network and a product relationship network based on user social data, product category data, and user rating data on products;
[0034] S102. Obtain user feature representation vectors and commodity feature representation vectors in the user relationship network and commodity relati...
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 belongs to the technical field of personalized recommendation, and particularly relates to a personalized recommendation method and system based on a connection matrix, and the method comprises the steps: constructing a user relation network and a commodity relation network according to user social data, commodity category data and the decibel of user-to-commodity score data; obtaining a user feature representation vector and a commodity feature representation vector in the user relation network and the commodity relation network by using a network representation learning algorithm; constructing a score prediction model, taking a user feature representation vector and a commodity feature representation vector as model input, fitting the user feature representation vector and the commodity feature representation vector through a connection matrix, taking an inner product of the three as a prediction score output by the model, and training the model by a stochastic gradient descent algorithm; and utilizing the trained score prediction model to obtain a predicted score of an unknown user on the commodity. The problem of semantic relationship loss based on the meta-path NRL algorithm in the HIN can be solved, the personalized recommendation performance is optimized, and the invention has a good application prospect.
Description
technical field [0001] The invention belongs to the technical field of personalized recommendation, and in particular relates to a connection matrix-based personalized recommendation method and system. Background technique [0002] As a tool to cope with information overload, the Recommender System is widely used in various platforms such as shopping, social networking, and content sharing. The recommendation system can help users obtain the content they are interested in from massive data and improve user experience. In the early recommendation methods, the interaction data (such as ratings) between users and products was often regarded as a bipartite graph, and the task of the recommendation system was to predict the unknown links in the bipartite graph. In fact, commercial platforms usually contain richer auxiliary information. For example, in Yelp, there are interaction information between users, information on types of products, and so on. These data information desc...
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 Applications(China)
IPC IPC(8): G06F16/9535G06F16/9536G06F17/16G06Q30/06G06Q50/00
CPCG06F16/9535G06F16/9536G06F17/16G06Q30/0631G06Q50/01
Inventor 李震宇徐金卯陶荣华巩道福王益伟谭磊刘粉林卢昊宇彭帅衡王艺龙杜少勇刘峰张李潇
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU