Document information extraction method and system based on text classification and reading understanding
A technology for reading comprehension and text classification, applied in the field of information content processing, can solve the problems of shortening training and prediction time, difficult model training, low extraction accuracy, etc., to improve prediction accuracy, solve entity nesting, and strong versatility Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0075] Such as figure 2 As shown, the present invention provides a document information extraction method based on text classification and reading comprehension, including the following steps;
[0076] S1, inputting a document, parsing and identifying the document, and converting the document into a plain text format;
[0077] S2, preprocessing the text content in the document to obtain input data;
[0078] S3, generating corresponding word vectors, word vectors and context vectors according to the input data in step S2, and splicing the word vectors, word vectors and context vectors to obtain spliced vectors;
[0079] S4, if the spliced vector is an answerable type, then use the entity text question corresponding to the spliced vector as the input of the next step;
[0080] S5, using the reading comprehension model to obtain the position of the most matching long label data corresponding to the entity text question through calculation;
[0081] S6. Obtain the long t...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com