Neural network-based Chinese named entity recognition method, device, equipment and storage medium

A named entity recognition and neural network technology, applied in the field of Chinese language processing and recognition, can solve problems such as unusable information, flawed recognition effect, and limited recognition rate improvement, achieving high recognition rate, easy implementation, and speed of judgment. The effect of high accuracy

Pending Publication Date: 2020-01-21
北京爱医博通信息技术有限公司
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the existing character-based Chinese named entity recognition method cannot use the information of the words in the sentence, which leads to flaws in the recognition effect and limits the improvement of the recognition rate, the purpose of the present invention is to provide a neural network-based Chinese named entity recognition method, device, equipment and storage medium

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
  • Neural network-based Chinese named entity recognition method, device, equipment and storage medium
  • Neural network-based Chinese named entity recognition method, device, equipment and storage medium
  • Neural network-based Chinese named entity recognition method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as Figure 1~2 As shown, the neural network-based Chinese named entity recognition method provided in this embodiment may, but is not limited to, include the following steps.

[0056] S101. Preprocess the training data to obtain the character feature identification vector and character position identification vector of each sentence, wherein the character feature identification vector contains the unique ID number of the character feature of each word in the corresponding sentence, and the character position The identification vector contains the unique ID number of the character position of each word in the corresponding sentence.

[0057] In the step S101, the data to be trained can be composed of various document data provided by the user or collected by existing collection software, wherein the document data can be but not limited to title, abstract, keywords, text, attachments Part or several fields in the title, attachment content and author information, etc...

Embodiment 2

[0074] Such as image 3 As shown, this embodiment provides a hardware device for implementing the neural network-based Chinese named entity recognition method described in Embodiment 1, including a data preprocessing module, a model training module, and an entity labeling module that are sequentially connected by communication; the data The preprocessing module is used to preprocess the training data to obtain the character feature identification vector and the character position identification vector of each sentence, wherein the character feature identification vector includes the unique ID number of the character feature of each word in the corresponding sentence, The character position identification vector includes the character position unique ID number of each word in the corresponding sentence; the model training module is used to use the character feature identification vector and the character position identification vector of each sentence as a training sample, Impo...

Embodiment 3

[0077] Such as Figure 4 As shown, this embodiment provides a hardware device for realizing the neural network-based Chinese named entity recognition method described in Embodiment 1, including a memory and a processor connected by communication, wherein the memory is used to store computer programs, and the The processor is configured to execute the computer program to realize the steps of the neural network-based Chinese named entity recognition method described in Embodiment 1.

[0078] For the working process, working details and technical effects of the Chinese named entity recognition device provided in this embodiment, please refer to Embodiment 1, which will not be repeated here.

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 the technical field of Chinese language processing and recognition, and discloses a neural network-based Chinese named entity recognition method, a device, equipment and a storage medium. According to the invention, through the invention, the invention provides a new method for improving the recognition rate of Chinese named entities by comprehensively utilizing charactersand word characteristics to carry out deep learning based on a neural network. That is to say, before model training, the method comprises the steps of preprocessing to-be-trained data; wherein the training sample comprises a character position recognition vector serving as word boundary information; therefore, the Chinese named entity recognition model obtained by training is ensured to have anextremely high recognition rate; the recognition model can convert the input text into the named entity label, so that the problems that the recognition effect is defective and the improvement of therecognition rate is limited due to the fact that the information of words in sentences cannot be utilized in the prior art can be solved, and actual application and popularization are facilitated. Inaddition, the Chinese named entity recognition method is easy to implement and low in development and operation cost.

Description

technical field [0001] The invention belongs to the technical field of Chinese language processing and recognition, and in particular relates to a neural network-based Chinese named entity recognition method, device, equipment and storage medium. Background technique [0002] Named Entity Recognition (NER) is a basic task of natural language processing, the purpose is to identify proper nouns and phrases in natural language processing and classify them. As more and more researchers propose a variety of model structures in the NEP field, it has become a major trend to use neural networks or deep learning to deal with NER problems. [0003] The current character-based method and the word-based method are two mainstream processing methods. Among them, the word-based method requires the use of word segmentation tools, but the effect of word segmentation tools is not perfect. Once the word segmentation is wrong, it will directly affect the prediction of entity boundaries. lead t...

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): G06F40/295G06N3/08
CPCG06N3/08Y02D10/00
Inventor 黄浩
Owner 北京爱医博通信息技术有限公司
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