Character relation classifying method and device

A technology for character relationship and classification method is applied in the field of character relationship classification method and device to achieve the effects of improving efficiency, eliminating noise, and reducing consumption and waste.

Active Publication Date: 2017-05-31
NETPOSA TECH
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the embodiments of the present invention is to provide a method and device for character relationship classification, which expands the label vector set through the robust path similarity measure, and eliminates the influence of noise and isolated points through the robust effect, reducing the Manual labeling of corpus reduces the consumption and waste of human resources, solves the bottleneck problem of manual labeling of corpus when massive labeling is required, and applies regularized semi-supervised classification algorithms to character relationship extraction, improving the efficiency of character relationship classification

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
  • Character relation classifying method and device
  • Character relation classifying method and device
  • Character relation classifying method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] An embodiment of the present invention provides a method for classifying personal relationships.

[0059] Character relationship refers to the relationship that exists and arises between characters and others within their specific social scope. According to the degree of familiarity and intimacy between people, the relationship between characters can be divided into six categories: family relationship, work relationship, friend relationship, teacher-student relationship, cooperative relationship and co-occurrence relationship. Among them, the co-occurrence relationship refers to the situation that the relationship between two characters cannot be accurately classified through the features in the sentence during the analysis process. Text information usually includes character relationship information, and the method provided by the embodiment of the present invention can classify the character relationship in the text.

[0060] see figure 1 , the method specifically i...

Embodiment 2

[0135] see Figure 4 An embodiment of the present invention provides a device for classifying personal relationships, which is configured to implement the method for classifying personal relationships provided in Embodiment 1 above. The unit includes:

[0136] An acquisition module 201, configured to acquire a labeled vector set, an unlabeled vector set, and a candidate relationship test set;

[0137] An expansion module 202, configured to expand the labeled vector set through a robust path similarity measure according to the labeled vector set and the unlabeled vector set;

[0138] The training and learning module 203 is used to train and learn the expanded label vector set through a non-linear semi-supervised classification function to obtain a character relationship classification model;

[0139] The classification module 204 is configured to classify the relationship between persons on the test set of candidate relations through the classification model of person relatio...

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 provides a character relation classifying method and device. The method comprises the following steps: acquiring a labeled vector set, a unlabeled vector set and a candidate relation test set; expanding the labeled vector set according to the labeled vector set and the unlabeled vector through robust path similarity measurement; carrying out training study on the expanded labeled vector set by a nonlinear semi-supervised classifying function to obtain a character relation classifying model; and carrying out character relation classification on the candidate relation test set by the character relation classifying model. The labeled vector set is expanded by the robust path similarity measurement, influence of noises and isolated points is eliminated by the effect of robustness, manually annotated corpus is reduced, consumption and waste of manpower resources are reduced, the bottleneck problem of manually labeled corpus when a large amount of labeling is required is solved, a regularized semi-supervised classification algorithm is applied to character relation extraction, and the character relation classification efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of information extraction, in particular, to a method and device for classifying person relationships. Background technique [0002] At present, in the fields of social public opinion analysis and social network analysis, it is often necessary to analyze the social relationship of characters. Text information usually contains information about character relationships, and character relationships include various types such as family relationships and colleague relationships. Before identifying the relationship, it is necessary to classify the character relationship in the text information. [0003] Currently, related technologies provide a method for character relationship classification based on supervised machine learning, including: manually labeling a large number of texts, labeling the relationship between characters in the text, training and learning the manually labeled text, and establishing ...

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): G06K9/62G06F17/27
CPCG06F40/211G06F40/284G06F18/22G06F18/214
Inventor 蔡磊师少飞
Owner NETPOSA 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