Alarm information hierarchical element recognition method and computer

A technology for identifying methods and elements, applied in computing, neural learning methods, semantic analysis, etc., can solve the problems of reduced model identification ability, inability to accurately obtain key information of the police situation, and difficulty in extracting elements.

Pending Publication Date: 2021-09-21
苏州智汇谷科技服务有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is difficult to accurately extract these elements through only one layer of entity recognition model
When the granularity of the element category is coarse, it is impossible to accurately obtain the key information of the alarm situation. When the granularity of the element category is fine, the recognition ability of the model will decrease as the category increases.

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
  • Alarm information hierarchical element recognition method and computer
  • Alarm information hierarchical element recognition method and computer
  • Alarm information hierarchical element recognition method and computer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the associated drawings. Preferred embodiments of the invention are shown in the accompanying drawings. However, the present invention can be embodied in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0033] The embodiment of the present invention adopts a brand-new hierarchical alarm element recognition model, which extracts and identifies key information in the alarm text from two levels of coarse-grained elements and fine-grained elements respectively, and according to various elements The relevant features are used to complete the information extraction and recognition of each task through the entity recognition model and the reading comprehension model...

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 embodiment of the invention provides an alarm information hierarchical element recognition method and a computer. The method comprises the following steps: extracting coarse-grained alarm elements of coarse-grained element categories from alarm information by using an entity identification model; and utilizing the reading understanding model to extract the fine-grained alarm condition elements of the fine-grained element category from the coarse-grained alarm condition elements. Through entity identification and reading understanding of a hierarchical element identification model, fine-grained alarm condition element information can be accurately and efficiently extracted from an alarm condition text.

Description

technical field [0001] The invention relates to the field of public security management, in particular to a method for identifying layered elements of police information and a computer. Background technique [0002] The task of police element recognition is to extract key element information from massive police texts. For example, the people involved in the police case, the time and place when the police incident occurred, and the items, tools and related amounts involved in the police case. Extracting these information is not only helpful to the classification of police cases, but also plays a key role in identifying the relationship between various police cases. However, the traditional manual analysis method has problems such as low efficiency and high error rate. With the development of machine learning and deep neural network technology, relevant technologies in the field of natural language processing can well assist police officers in extracting and analyzing inform...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/295G06F40/30G06N3/04G06N3/08G06F16/35G06Q50/26
CPCG06F40/295G06F40/30G06N3/08G06F16/35G06Q50/26G06N3/044G06N3/045
Inventor 吴瑞萦何莹李直旭陈耀玲
Owner 苏州智汇谷科技服务有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap