Personalized training course generation method, system and device and medium

By using generative large language models and user portrait data in the personalized training system, personalized training courses are generated in real time, and personalized training courses are solved. The problem of personalized training in the existing technology is difficult to achieve, efficient and personalized training course generation is achieved, and operation and maintenance costs are reduced.

CN119722397APending Publication Date: 2025-03-28HUADIAN ELECTRIC POWER SCI INST CO LTD
5 Cites 0 Cited by

Patent Information

Application Number
CN202411583887.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-07
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

The prior art is difficult to effectively use generative large language models for personalized training, and there is a problem of high operating calculation costs.

Method used

By matching and filtering out the target content from the pre-stored personalized question bank based on the user portrait data of the pre-stored personalized question bank, and using the trained generative model to generate incremental content in real time. If the generated content is insufficient, supplement the pre-set content to form a personalized training course.

Benefits of technology

Incrementally generating a large number of topics to be selected and pre-stored, reducing the number of real-time requests for large models, improving the personalization and efficiency of training courses, and at the same time, training large models through redundant power, reducing operation and maintenance costs.

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

Abstract

The invention relates to a personalized training course generation method, system and device and a medium, and the method comprises the steps: carrying out the matching and screening of a first target content from a pre-stored personalized question bank containing the safety course questions of a power station based on the user portrait data of a preset user; based on the user portrait data and the user scale of the preset user and the question number of the personalized question bank, second target content is generated in real time through a trained generative large model; and on the basis of the first target content and / or the second target content, completing generation of a personalized training course of the preset user. According to the method and the device, a large number of to-be-selected questions are generated in an incremental manner and are pre-stored, so that a large number of materials are provided for the generation of training courses for personalized distribution, the number of real-time requests for a large model can be reduced, and the problem of how to perform personalized training by using a generative large language model is solved.
Need to check novelty before this filing date? Find Prior Art