Triad prediction model generation method and relationship triad extraction method and device

A predictive model and technology of triples, applied in the field of data processing, can solve problems such as the limitation of the number of relational triples, the type of relational triples, and the impact on data analysis.

Pending Publication Date: 2020-12-11
BEIJING SINOVOICE TECH CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing extraction methods of relational triples are usually limited to a fixed field, resulting in the limitation of the number of relational triplets that can be extracted and the relationship types of relational triplets, which affects subsequent data analysis

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
  • Triad prediction model generation method and relationship triad extraction method and device
  • Triad prediction model generation method and relationship triad extraction method and device
  • Triad prediction model generation method and relationship triad extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0060] refer to figure 1 , which shows a flow chart of the steps of an embodiment of a method for generating a triplet prediction model according to the present invention, which may specifically include the following steps:

[0061] Step 101, obtaining training texts containing preset relational triples; the relational triples include main entity words, relational words, and sub-entity words; the training texts contain the main entities corresponding to the relational triplets words, subentity words and relative words;

[0062] In the embodiment of the present invention, several relational triples may be preset, and the relational triples include a main entity word, a subsidiary entity word, and a relationship indicating the rela...

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 a triad prediction model generation method, a relationship triad extraction method and device. The triad prediction model generation method comprises the stepsof obtaining a training text containing a preset relationship triad; wherein the relationship triad comprises a main entity word, a relationship word and an auxiliary entity word; wherein the training text has auxiliary entity word annotation information and relationship word annotation information corresponding to the relationship triad; and training a preset model by taking the training text and the main entity words in the relationship triad as model input and taking the auxiliary entity word annotation information and the relationship word annotation information as model output to generate a triad prediction model. Therefore, relationship triples obtained through prediction can contain various different relation types, the number of the relationship triads which can be extracted by the triad prediction model and the relationship types are expanded, and extraction of the relation triads in the open field is achieved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a method for generating a triple prediction model, a method for extracting a relational triple, a device for generating a triple prediction model, and a relational triple extraction device. Background technique [0002] In the existing technology, in order to meet the needs of data analysis, information retrieval, and establishment of question answering systems for massive data, several relational triples can be obtained, and knowledge graphs can be further constructed based on the relational triples, or massive data analysis can be performed. However, the existing methods for extracting relational triples are usually limited to a fixed field, resulting in the limitation of the number of relational triples that can be extracted and the relationship types of the relational triples, and affects subsequent data analysis. Contents of the invention [0003] In view ...

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): G06F40/295G06F16/36G06F16/33
CPCG06F16/3344G06F16/367G06F40/295
Inventor 胡洪兵李健武卫东
Owner BEIJING SINOVOICE TECH CO LTD
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