Information-enhanced meta-learning method for relieving cold start problem of recommended user

Abstract

The invention discloses an information-enhanced meta-learning method for relieving a recommended user cold start problem. The method comprises the following steps: constructing a user-article bipartite graph according to a comment relationship of user articles; using the user neighborhood information and the article description text as the source of node information, performing random sampling on the constructed bipartite graph, and constructing meta-learning tasks, wherein each task represents a new user to carry out cold start recommendation to simulate a scene for realizing recommendation for the new user; using a bert method to perform feature extraction work of text data for each meta-learning task to obtain preference information; and using the global parameters of the preference information guide element for generating local parameters of an embedded generation function of each user, inputting element learning tasks into a recommendation model to obtain predicted scores of the users on articles, updating element learning parameters, and directly applying the trained parameters to untrained new users. According to the method, the problem that preference recommendation inaccuracy cannot be evaluated due to less new user interaction is relieved.

Description

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

AI Technical Summary

Benefits of technology

This technology helps recommend models based on past experiences or preferences from multiple people who have similar comments about things like food they eat at home over time. It can learn more accurate parameters such as how many neighbors are connected together within one node (their owners) while still being able to provide relevant suggestions to other members around them. Additionally, it allows users to gradually adjust their behavior without having to stop working altogether due to poorly understood issues related to recommending content too hot up). Overall, this technology improves overall performance across all types of scenarios where users' opinions may be affected negatively.

Problems solved by technology

This patented technical issue addressed by this patents relates to recommender systems used over internet shops where individuals frequently purchase things from their favorite websites without having enough contact details about them. Current models require significant amounts of time to adjust and generate suggestions, while newer ones may lack sufficient detail compared to older versions. Additionally, these conventional solutions suffer from weaknesses like predictability issues caused by noise levels during network communication.

Images