Text processing feedback system and method based on multi-modal data

By designing a text processing feedback system based on multimodal data, the multimodal data fusion problem in the prior art is solved, and the generation of high-quality and diverse text content is achieved to meet the personalized needs of users.

CN119691155AInactive Publication Date: 2025-03-25JIANGSU HOPERUN SOFTWARE CO LTD
6 Cites 1 Cited by

Patent Information

Application Number
CN202510196331.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-21
Publication Date
2025-03-25
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art is difficult to efficiently fuse multimodal data, resulting in the limitation of the accuracy and diversity of text-generated content and cannot meet the personalized needs of users.

Method used

A text processing feedback system based on multimodal data is designed. Through the multimodal data input module, text semantic feature extraction module, multi-scale feature extraction module, image understanding module, multi-modal requirement expression matrix generation module, feature correction module and text generation optimization module, the fusion and correction of text and image features are realized to generate high-quality text content that meets user needs.

Benefits of technology

Through the fusion and correction of multimodal data, the system can effectively generate high-quality and diverse text content, meet the needs of different scenarios, and improve the comprehensive ability and personalization of text generation.

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

Abstract

The invention relates to the technical field of multi-modal data, and discloses a text processing feedback system and method based on multi-modal data, and the method comprises the steps: processing text data input by a user through a context encoder containing an embedded layer, and obtaining semantic feature vectors of a plurality of texts; arranging the plurality of semantic feature vectors into a one-dimensional feature vector; the method comprises the following steps: processing image data provided by a user through a convolutional neural network, and extracting a key feature vector in an image; calculating the product between the transpose of the image understanding feature vector and the text understanding feature vector to obtain a multi-modal demand expression matrix; adjusting each characteristic value in the matrix through a characteristic correction mechanism based on the characteristic value of each position in the multi-modal demand expression matrix; and inputting the corrected multi-modal demand expression matrix into a multi-label classifier for processing. The method has the advantage of improving the comprehensive text generation capability.
Need to check novelty before this filing date? Find Prior Art