Unique Character Recognition Method Based on Temporal Semantic Path Similarity in Heterogeneous Networks

A similarity, temporal technology, used in special data processing applications, instruments, electrical digital data processing, etc.

Inactive Publication Date: 2016-08-17
CENT SOUTH UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can accurately and efficiently identify the same person object in a social relationship network with large data scale and high network complexity, and can effectively solve the problem of unique person identification in the relationship network

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
  • Unique Character Recognition Method Based on Temporal Semantic Path Similarity in Heterogeneous Networks
  • Unique Character Recognition Method Based on Temporal Semantic Path Similarity in Heterogeneous Networks
  • Unique Character Recognition Method Based on Temporal Semantic Path Similarity in Heterogeneous Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] The present invention example provides a kind of calculation method based on heterogeneous network structure temporal semantic path similarity, main steps are as follows:

[0046] 101 Establishment of Heterogeneous Social Networks

[0047] First, read the relationship and the basic attribute information of the relationship object in the transaction activity record database, and convert them into the start node name, end node name, relationship name, relationship start time and end time, and save them in the network topology-based in the graph database. In a graph database, all characters and relationships are stored in the database in the form of "objects". Both characters and relationship objects have their own basic attribute information. For example, character objects generally have basic attributes such as name, gender, and age. Relational objects generally have basic attributes such as start node name, end node name, start time and end time. After importing the d...

Embodiment 2

[0098] This embodiment provides a method for uniquely identifying a person based on a heterogeneous social network, and the specific steps are as follows:

[0099] 201 Establishment of Heterogeneous Social Networks

[0100] First, read the data from the Excel data table. In the data table, the basic attribute information of the person object is divided into: name, gender, date of birth, and the basic attribute information of the relationship object is divided into: start node name, start node name, start time, end time. The data extracted from the relational data table is saved in the form of graph in the graph database based on the network topology. In a graph database, all characters and relationships are stored in the database in the form of "objects". Both characters and relationship objects have their own basic attribute information. For example, character objects generally have basic attributes such as name, gender, and age. Relational objects generally have basic attr...

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 figure uniqueness recognition method based on heterogeneous network temporal semantic path similarity. The method comprises the steps of firstly establishing a heterogeneous social relationship network, namely extracting the relationship from a figure social activity transaction database and establishing a heterogeneous relationship network with time attributes; conducting searching on a temporal semantic path between figure objects according to a network structure, meanwhile, conducting measurement on the path similarity of the figure objects in the network according to the heterogeneous social relationship network characteristics and the temporal semantic path, sorting the figure objects according to the similarity value, conducting filtering according to similarity threshold values set by the network characteristics and the application requirements, and therefore recognizing the figure objects with the uniqueness characteristics. The method can accurately and efficiently measure the similarity of the figure objects in the large-scale and high-complexity social relationship network, effectively solve the problem of the figure uniqueness recognition in the relationship network, and improve the effectiveness of the relationship network analysis and mining processes.

Description

technical field [0001] The invention belongs to the technical field of computer applications, and relates to a method for uniquely identifying characters based on temporal semantic path similarity of a heterogeneous network structure. technical background [0002] Extracting semantic relational network from massive text information is an important research topic of social relational network modeling and mining. Usually, when extracting large-scale social relational networks from Web pages, electronic document libraries, transactional databases, and relational databases, due to time differences in transactional information, incomplete information, and differences in information patterns and structures, the relationship between characters in the network will be confused. , which makes it difficult to determine the uniqueness of characters. This problem has become a key problem to be solved in the process of social network analysis. [0003] Traditional social relationship net...

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 Patents(China)
IPC IPC(8): G06F17/27G06F17/30
Inventor 黄芳朱磊
Owner CENT SOUTH UNIV
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