Self-learning event extraction method and application thereof

An event extraction, self-learning technology, applied in special data processing applications, natural language data processing, instruments, etc., can solve problems such as error-prone, poor coverage and portability, cumbersome process, etc., to achieve effective decision-making, accurate structure The effect of interpretation

Active Publication Date: 2020-11-03
GUANGDONG UNIV OF TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to obtain accurate trigger word recognition, a large number of trigger word tags are required. In the existing technology, most of them are realized through manual tagging, which is not only cumbersome, error-prone, but also poor in coverage and portability.

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
  • Self-learning event extraction method and application thereof
  • Self-learning event extraction method and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0098] During model training, for the input, set the maximum number of sentences and the maximum sentence length to 64 and 128 respectively, use the Adam optimizer, the learning rate is 1e-4, and train for a maximum of 100 iterations, and select the best model according to the verification score on the development set. good number of iterations.

[0099] Through the trained model, interpret the following exception logs according to the above specific implementation method:

[0100] On July 5, 2015, at 10am, there was insufficient supply of aluminum alloy in the milling machine workshop, and the workshop was suspended for halfa day without fulfilling the required indicators.

[0101] In the process of S1 data preprocessing:

[0102] First, refer to disambiguation through stanford corenlp, and get the following log content after disambiguation:

[0103] On July 5, 2015, at 10am, there was insufficient supply of aluminum alloy in the milling machine workshop, and milling machin...

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 discloses a self-learning event extraction method and application thereof. The event extraction method comprises the steps that candidate words are subjected to self-learning screening through sentence vectors of event information and candidate word role mapping contained in each sentence vector, and a trigger word set is obtained; according to the invention, industrial production abnormal logs and other information can be quickly and accurately interpreted, and an appropriate decision is further made.

Description

technical field [0001] The present invention relates to the technical field of event extraction. Background technique [0002] Production anomalies refer to schedule delays or production shutdowns that occur during the production process, and generally include planning anomalies, material anomalies, equipment anomalies, process quality anomalies, design process anomalies, water and electricity anomalies, and other forms. Abnormal production will cause production waste and seriously affect the production capacity of the enterprise, which is an urgent problem to be overcome in production. In the solution to this problem, a common method is that decision makers interpret the abnormal logs of the industrial production process to find out information related to the abnormality, such as the cause, development process, etc., and make effective decisions based on this information. Reduce production exceptions. [0003] In the prior art, the interpretation of event information such...

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): G06F16/33G06F16/35G06F40/211G06F40/289
CPCG06F16/3344G06F16/35G06F40/211G06F40/289Y02P90/30
Inventor 朱远发张伟文王德培赖泰驱
Owner GUANGDONG UNIV OF TECH
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