Entity attribute extraction method, system and device based on dictionary and sequence labeling model

A technology of sequence labeling and entity attributes, applied in character and pattern recognition, electrical digital data processing, instruments, etc., to achieve the effect of improving computing speed

Active Publication Date: 2020-09-01
北京智通云联科技有限公司
View PDF12 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to provide a method, system and device for extracting entity attributes based on a dictionary and sequence labeling model, aiming to solve the above-mentioned problems in the prior art

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
  • Entity attribute extraction method, system and device based on dictionary and sequence labeling model
  • Entity attribute extraction method, system and device based on dictionary and sequence labeling model
  • Entity attribute extraction method, system and device based on dictionary and sequence labeling model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] An embodiment of the present invention provides an entity attribute extraction device based on a dictionary and a sequence annotation model, such as Figure 4 As shown, it includes: a memory 40, a processor 42, and a computer program stored on the memory 40 and operable on the processor 42. When the computer program is executed by the processor 42, the following method steps are realized:

[0086] It should be noted that, in the embodiment of the present invention, before performing the following step 101, it is necessary to create an entity dictionary, an attribute name-to-entity dictionary, and an attribute value dictionary, wherein, as shown in Table 1, the entity dictionary is used to manage industrial For all entities in the domain, as shown in Table 2, the attribute name-to-entity dictionary is used to manage the one-to-one correspondence between the attribute name of the entity and the entity. As shown in Table 3, the attribute value dictionary is used to manage a...

Embodiment 2

[0108] An embodiment of the present invention provides a computer-readable storage medium, on which a program for realizing information transmission is stored, and when the program is executed by the processor 42, the following method steps are implemented:

[0109] It should be noted that, in the embodiment of the present invention, before performing the following step 101, it is necessary to create an entity dictionary, an attribute name-to-entity dictionary, and an attribute value dictionary, wherein, as shown in Table 1, the entity dictionary is used to manage industrial For all entities in the domain, as shown in Table 2, the attribute name-to-entity dictionary is used to manage the one-to-one correspondence between the attribute name of the entity and the entity. As shown in Table 3, the attribute value dictionary is used to manage all enumerable attribute values.

[0110] In addition, it is also necessary to train a sequence labeling model, such as figure 2 As shown, i...

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 an entity attribute extraction method, system and device based on a dictionary and a sequence labeling model. The method comprises the steps of performing word segmentation processing on an input text according to a pre-created dictionary to obtain a text after word segmentation, obtaining attribute names in the text after word segmentation and entities corresponding to theattribute names, and creating one or more data nodes containing the entities and the attribute names; sequentially extracting the attribute name in each data node, defining the label of the attributename as a key; defining labels of other attribute names as NN, combining the label of the defined attribute name, inputting the text after word segmentation into a pre-trained sequence labeling modelto obtain labels corresponding to all words in the text after word segmentation, determining attribute values corresponding to the attribute names according to specific meanings of the labels corresponding to all words, and further obtaining all final entity attribute results containing the entities, the attribute names and the attribute values in the input text.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method, system and device for extracting entity attributes based on a dictionary and a sequence labeling model. Background technique [0002] In the prior art, an entity is usually an object described in a text, such as a person name, a place name, an organization name, etc., and an attribute refers to an attribute or a component in an entity, such as gender, name, age, etc. Entity attribute extraction refers to extracting <entity, attribute name, attribute value> information pair from the text. There are three commonly used methods at present. [0003] Method 1: template-based extraction, first specify the entity attribute information to be extracted, and create a template file; then create extraction rules. This method has poor portability and is only suitable for semi-structured text, such as web pages whose content changes at any time, but the struct...

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): G06F40/289G06F40/295G06F40/30G06K9/62
CPCG06F40/30G06F40/295G06F40/289G06F18/214Y02P90/30
Inventor 么新新张学龙谭培波刘弦弦
Owner 北京智通云联科技有限公司
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