Image search method, device, intelligent agent, electronic device and storage medium
By using large models for semantic analysis and image-text analysis, generating question-answer pairs and comparing answer information, the problem of semantic deviation in image search is solved, achieving higher image search accuracy and speed.
CN119597955BActive Publication Date: 2025-09-09BEIJING BAIDU NETCOM SCI & TECH CO LTD
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202411764757.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-03
- Publication Date
- 2025-09-09
- Estimated Expiration
- 2044-12-03
AI Technical Summary
Technical Problem
Existing image search technologies have deviations in details and complex semantic relationships at the semantic level, resulting in low accuracy between images and input information.
Method used
The first model is used to perform semantic analysis on the input text information to generate question-answer pairs, and the second model is used to perform image-text analysis. By comparing the first answer information and the second answer information, the target image that matches the image search requirements is screened out.
Benefits of technology
It improves the accuracy of image search, ensures that the image matches the input information in terms of details and complex semantic relationships, and improves the overall accuracy and speed of image search.
✦ Generated by Eureka AI based on patent content.
Abstract
The present disclosure provides an image search method, apparatus, intelligent agent, electronic device, and storage medium, relating to the field of artificial intelligence technology, particularly computer vision, deep learning, large models, image search, and other technical fields, and can be applied to scenarios such as AIGC-based content generation based on artificial intelligence. The method includes: obtaining at least one first candidate image that matches input text information; using a first large model to perform semantic analysis on the input text information to generate at least one question-answer pair, the question-answer pair including question information and first answer information; using a second large model to perform graphic analysis on the at least one question information and at least one first candidate image to generate second answer information for each question information; and determining, based on a comparison result between the at least one first answer information and the at least one second answer information, at least one target image that matches the image search requirement from the at least one first candidate image.
Need to check novelty before this filing date? Find Prior Art