Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Judicial text classification method and system based on attention mechanism

A text classification and attention technology, applied in text database clustering/classification, unstructured text data retrieval, special data processing applications, etc., can solve problems such as insufficient deep semantic expression, and achieve the effect of rapid classification

Active Publication Date: 2019-11-05
ENJOYOR COMPANY LIMITED
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention adopts a multi-head self-attention mechanism, expands the ability of the model to pay attention to different positions, solves the problem of multi-themes and insufficient deep semantic expression of Chinese text, and makes the semantic information represented by Chinese text more accurate and rich; at the same time, it saves time and cost

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Judicial text classification method and system based on attention mechanism
  • Judicial text classification method and system based on attention mechanism
  • Judicial text classification method and system based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] Embodiment: a kind of judicial text classification system based on attention mechanism, comprises data collection module, feature extraction module, feature fine-tuning module, network training module; Described data collection module is used for collecting the question-and-answer data of judicial field, and collects The obtained questions and answers are preprocessed by data cleaning, word segmentation and stop word removal to form answer datasets and question datasets; the feature extraction module uses the self-attention mechanism to extract question data features and answer data features; the feature fine-tuning module uses The collaborative attention mechanism fine-tunes the question features according to the answer features, and updates the question features; the network training module uses the lstm long short memory network for classification training to obtain the final classification model.

[0046] Such as figure 1 As shown, a judicial text classification met...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a judicial text classification method and system based on an attention mechanism. The judicial text classification method mainly comprises the steps of data preprocessing operation, data vectorization processing, self-learning by utilizing a self-attention mechanism, defining intention of a problem by utilizing a collaborative attention mechanism, and training a text classification model by utilizing lstm. A multi-head self-attention mechanism is adopted, the ability of a model to pay attention to different positions is expanded, the problem that deep semantic expression of multiple themes and Chinese texts is not comprehensive enough is solved, and semantic information expressed by the Chinese texts is more accurate and richer; meanwhile, the time cost is saved.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a judicial text classification method and system based on an attention mechanism. Background technique [0002] Search engine technology is a new technology that has emerged in the development of the Internet in recent years. The purpose of its application is to help Internet users quickly find and display the information they need in the vast amount of information. With the rapid growth of network information, search engines have become an essential tool for modern people to access information online. Legal search is a complex, systematic, and cumbersome project or task. How to find the desired content from thousands of judgment documents requires careful arrangement and design. The legal search engine can help users quickly find and display the information they need in the massive judicial library. For example, there are tens of millions of judgment documents on the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/35
CPCG06F16/353G06F16/355
Inventor 金佳佳丁锴蒋立靓陈涛李建元
Owner ENJOYOR COMPANY LIMITED
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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