Model reasoning method and device and computing equipment

By tracing and matching non-text data in real time within RAG technology to enhance its correlation with text data, the problems of insufficient usability, accuracy, and diversity of output content in existing technologies are solved, thereby improving the user experience.

CN121638433APending Publication Date: 2026-03-10HUAWEI CLOUD COMPUTING TECHNOLOGIES CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202411194563.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2026-03-10

AI Technical Summary

Technical Problem

Existing RAG technology lacks usability, accuracy, and diversity in its output content for knowledge base question answering scenarios, and the insertion of non-text modal data does not support streaming generation, resulting in a poor user experience.

Method used

After generating text data, the system traces back to the original text segment it references in real time, matches and inserts relevant non-text data from it, and achieves streaming output, enhancing the correlation between non-text data and text data and reducing user waiting time.

Benefits of technology

It improves the usability, accuracy, and diversity of output content, enhances the user experience, and reduces user waiting time.

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

Abstract

The invention provides a model reasoning method. The method comprises the steps that information input by a user is acquired; a first text related to the information input by the user is output, and the first text comprises at least one sentence of text data; determining at least one piece of non-text data related to the at least one sentence of text data in a target original text segment, the target original text segment being an original text segment referenced by the at least one sentence of text data, and the target original text segment being included in a user knowledge base; determining target non-text data matched with the at least one sentence of text data from the at least one non-text data; and outputting the target non-text data. According to the scheme, the understandability, correctness and diversity of the output content can be improved, and the waiting time of the user is shortened, so that the use experience of the user is improved.
Need to check novelty before this filing date? Find Prior Art