Intelligent question-answering method and device based on tool matching, equipment, medium and program product

By preprocessing long videos and selecting appropriate tools, dynamically adjusting the sampling interval, filtering suitable content parsing tools, extracting fine-grained information, and performing large language model inference, the problem of inaccurate answers to complex questions in long videos has been solved, thereby improving the accuracy and effectiveness of intelligent question answering.

CN122157106APending Publication Date: 2026-06-05CHINA MOBILE JIUTIAN ARTIFICIAL INTELLIGENCE TECHNOLOGY (BEIJING) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA MOBILE JIUTIAN ARTIFICIAL INTELLIGENCE TECHNOLOGY (BEIJING) CO LTD
Filing Date
2026-03-05
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Traditional end-to-end models struggle to extract fine-grained features from long videos, leading to inaccurate and unreliable answers to complex user questions.

Method used

By receiving long video files and user questions, preprocessing is performed, the sampling interval is dynamically adjusted for frame sampling and compression, and matching content parsing tools such as automatic speech recognition, text recognition, face recognition and target tracking tools are selected to extract fine-grained key information, and a large language model is used for reasoning to generate answers.

Benefits of technology

It improves the accuracy and reliability of intelligent question answering in long video scenarios, makes up for the lack of targeted information extraction in traditional models, and achieves improved accuracy and effectiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122157106A_ABST
    Figure CN122157106A_ABST
Patent Text Reader

Abstract

The application provides an intelligent question and answer method and device based on tool matching, equipment, medium and program product, relating to the technical field of artificial intelligence, the method comprises: receiving a long video file input by a user and a user question; preprocessing the long video file to obtain video information; determining a content analysis tool matched with the user question based on the video information, wherein the content analysis tool comprises at least one of an automatic speech recognition tool, a text recognition tool, a face recognition tool and a target tracking tool; extracting fine-grained key information from the video information through the content analysis tool; and reasoning the user question through a large language model based on the video information, the fine-grained key information and the user question to generate an answer text. The application can give more accurate and reliable answers.
Need to check novelty before this filing date? Find Prior Art