Question and answer processing method and device, computer device, and storage medium
By acquiring question text features and initial information features, using an association evaluation model to filter relevant features, and combining image and text processing sub-models to generate answers, the problem of insufficient accuracy in existing question answering technologies is solved, and the accuracy of multimodal question answering is improved.
CN115757725BActive Publication Date: 2026-05-29CHINA PING AN PROPERTY INSURANCE CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA PING AN PROPERTY INSURANCE CO LTD
- Filing Date
- 2022-11-15
- Publication Date
- 2026-05-29
AI Technical Summary
Technical Problem
Existing question-answering technologies lack accuracy when answers are represented by both text and images.
Method used
By acquiring question text features and multiple initial information features, a correlation evaluation model is used to filter relevant initial information features, construct question-answer features, and use the image processing sub-model and text processing sub-model in the question-answer model to generate multimodal answer information.
Benefits of technology
It improves the accuracy of multimodal question answering, enables the simultaneous generation of text and image answers, and enhances the overall accuracy of question answering.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115757725B_ABST
Abstract
The embodiment of the application belongs to the field of artificial intelligence, and relates to a question and answer processing method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a question and answer request carrying question text features, wherein the question text features are generated based on a question text; obtaining a plurality of initial information features, wherein the initial information features are image features or text features; screening the initial information features related to the question text to obtain a plurality of recall information features; constructing a question and answer feature according to the question text features and each recall information feature and inputting the question and answer feature into a question and answer model, so as to generate image answer information by processing the image features in the question and answer feature based on an image processing submodel in the question and answer model, and generate text answer information by processing the text features in the question and answer feature based on a text processing submodel in the question and answer model, thereby obtaining answer information. The application also relates to blockchain technology, and the initial information features can be stored in the blockchain. The application improves the accuracy of multi-modal question and answer.
Need to check novelty before this filing date? Find Prior Art