Project recommendation method and device, medium and computer equipment

By constructing project sequential transfer graphs and semantic transfer graphs, combining adjacent project transformations and semantic correlation patterns, and adjusting diffusion models, the shortcomings of existing recommendation systems in dealing with noise and semantic correlation modeling between sequences are solved, and the accuracy of project recommendations is significantly improved.

CN119719486AActive Publication Date: 2025-03-28CHANGSHU INSTITUTE OF TECHNOLOGY
10 Cites 2 Cited by

Patent Information

Application Number
CN202411724741.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-28
Publication Date
2025-03-28
Estimated Expiration
2044-11-28

AI Technical Summary

Technical Problem

Existing recommendation systems are difficult to effectively combine adjacent project transformations and semantic correlation project transformation patterns in user behavior, resulting in limited sequence recommendation performance, especially in dealing with inter-sequence noise and semantic correlation modeling.

Method used

By constructing project sequence transfer graphs and project semantic transfer graphs, fuse adjacent project transformation and semantic correlation project transformation patterns, determine conditional signals based on these graphs, and adjust the diffusion model to deal with noise problems between sequences and within sequences.

Benefits of technology

It significantly improves the accuracy of project recommendations, effectively deals with noise problems between sequences and within sequences, and improves the personalization and accuracy of the recommendation system.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a project recommendation method and device, a medium and computer equipment, and relates to the technical field of recommendation systems.The method comprises the steps that a user behavior sequence set is obtained, a project set is determined based on the user behavior sequence set, and a project embedding matrix is constructed based on the project set; determining a user-item embedding vector corresponding to each user behavior sequence based on the item embedding matrix; respectively constructing a project sequence transfer graph and a project semantic transfer graph based on the user behavior sequence set; determining a condition signal corresponding to each user behavior sequence based on a project sequence transfer graph and the project semantic transfer graph; and for the recommendation demand of any user, adjusting a pre-trained diffusion model based on the condition signal corresponding to the user behavior sequence of any user, and determining a target recommendation item corresponding to any user based on the adjusted diffusion model. According to the embodiment, the accuracy of project recommendation is improved.
Need to check novelty before this filing date? Find Prior Art