Recommendation method and device based on longitudinal federated learning

Abstract

The embodiment of the invention provides a recommendation method and device based on longitudinal federated learning. A third-party user side sends a determination message to a recruitment platform side and an enterprise user side when judging that a position weight vector and a user weight vector meet a preset convergence condition; and when it is judged that the position weight vector and the user weight vector do not meet the preset convergence condition, a first iteration parameter vector and a second iteration parameter vector are sent to a recruitment platform side and an enterprise user side respectively. The enterprise user side updates the position weight vector according to the second iteration parameter vector, and sends a target position weight vector to the recruitment platform side when receiving a determination message. And the recruitment platform side updates the user weight vector according to the first iteration parameter vector, and recommends to a specified job seeker and the enterprise user side based on a target user feature vector, a target position feature vector, a target position weight vector and a target user weight vector when receiving the determination message, so as to protect the privacy information of the job seeker. And the recommendation effectiveness of the recruitment platform is improved.

Description

technical field [0001] The invention relates to the field of network technology, in particular to a recommendation method and device based on longitudinal federated learning. Background technique [0002] The recruitment platform provides a convenient communication channel for enterprise users and job seekers. For example, enterprise users can select job seekers who meet the recruitment requirements from the job seekers provided by the recruitment platform; Among the recruitment positions provided by each enterprise user, select the recruitment position that meets the job-seeking requirements. [0003] In the prior art, the recruitment platform end can send information to the personal client terminal used by the job seeker based on the job seeker's job requirements (such as salary, job position, work location, etc.) Recommended job openings. In addition, the recruitment platform can also recommend job seekers to the enterprise client used by the enterprise user based on th...

AI Technical Summary

Problems solved by technology

[0004] However, in order to protect the privacy information of job seekers, enterprise users will not provide the final feedback information of enterprise users to job seekers to the recruitment platform, resulting in the failure of the recruitment platform to combine the final feedback information of enterprise users to job seekers and provide the information used by job seekers Personal and enterprise clients make recommendations, which in turn makes it impossible to improve the effectiveness of recommendations on the recruitment platform

Images