Construction method and identification method of automatic electronic product named entity identification system

A technology for automatic identification systems and electronic products, applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problem of low recall rate and achieve the effect of high recall rate, diverse forms, and fast change

Inactive Publication Date: 2011-04-27
HARBIN INST OF TECH
View PDF1 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for constructing an automatic recognition system for named entities of electronic products, so as to solve the problem that the rule-based recognition system has a low recall rate during recognition, while the recognition system based on machine learning needs to manually mark a large amount of training corpus. question

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
  • Construction method and identification method of automatic electronic product named entity identification system
  • Construction method and identification method of automatic electronic product named entity identification system
  • Construction method and identification method of automatic electronic product named entity identification system

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0010] Specific Embodiment One: The construction method of the electronic product named entity automatic recognition system of the present embodiment includes the following steps: 1. Collect various genres of electronic product webpage information from the Internet by using download software, and extract the text of the webpage information, thereby Form the knowledge base of the original corpus; use the part-of-speech tagging tool to segment the original corpus (separate the words in the sentence from the space) and part-of-speech tagging (mark the part of speech of each word), and then name the entity according to the electronic product The definition of the corpus after word segmentation and part-of-speech tagging is carried out to entity tagging, and a tagging corpus is constructed; the definition of the electronic product named entity refers to distinguishing electronic products according to the brand name, series name and model of an electronic product named entity. Named ...

specific Embodiment approach 2

[0011] Embodiment 2: The difference between this embodiment and Embodiment 1 is: the resources in the knowledge base are all automatically obtained from the Internet by using web crawler technology and information extraction technology; the knowledge base includes: A brand name dictionary constructed with information characteristics; a series name dictionary constructed for the series of electronic products under a brand; or a specific word knowledge base constructed for some phrases with specific meanings.

specific Embodiment approach 3

[0012] Specific embodiment three: The identification method of the electronic product named entity automatic identification system based on the first embodiment of the present embodiment includes the following steps: 1. Input the free text used for identification into the electronic product named entity automatic identification system ; 2. The system first uses the feature template to extract features, and then uses the conditional random field model to obtain the weight corresponding to each feature, and uses the conditional random field method to calculate these weights to obtain the final recognition result.

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 construction method and an identification method of an automatic electronic product named entity identification system, relates to a construction method and an identification method of a named entity identification system in natural language processing and belongs to a technique for automatically identifying names of electronic products from related information. The invention is used for identifying the names of the electronic products and solves the problems that a rule-based identification system has low recall rate during identification and a machine learning-based identification system needs to manually label a great deal of training language database during identification. The construction method comprises the following steps of: forming a knowledge base of the original linguistic data; constructing a label language database; and performing electronic product named entity identification on the basis of a conditional random field method. The identification method comprises the following steps that: a free text is input into the automatic electronic product named entity identification system; and the system extracts characteristics by using a characteristic template, acquires each weight corresponding to each characteristic by using a conditional random field model and calculates the weights by the conditional random field method to acquire an identification result.

Description

technical field [0001] The invention relates to a construction method and a recognition method of a named entity recognition system in natural language processing, and belongs to the technology of automatically recognizing the names of electronic products from related information. Background technique [0002] Things that exist objectively and can be distinguished from each other are called entities. Entities can be concrete people, things and things, or abstract concepts or connections. The task of named entity recognition refers to the recognition of entities with specific meaning in text. As human society enters the digital age, more and more electronic products have entered people's lives. Various reports about electronic products appear in large numbers in electronic documents. The Internet is full of advertisements, usage methods and user reviews about electronic products. Electronic Product Named Entity Recognition technology can help people to better query and ma...

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): G06F17/30
Inventor 孙承杰林磊梅丰王晓龙刘远超刘秉权
Owner HARBIN INST 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