Knowledge graph-based knowledge credibility measurement method

A technology of knowledge graph and credibility, which is applied in special data processing applications, unstructured text data retrieval, instruments, etc., and can solve problems such as wrong knowledge and wrong decision-making

Pending Publication Date: 2021-05-28
SOUTHEAST UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, although automated construction technology saves a lot of manpower and can supplement new knowledge in a timely manner, such an approach will inevitably introduce a lot of wrong knowledge
At present, knowledge graphs are widely used in the fields of question answering, recommendation, and search, and these applications based on knowledge graphs assume that the knowledge in the knowledge graph is correct, which will inevitably have some potential problems, such as in auxiliary decision-making. knowledge can lead to wrong decisions with serious consequences

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
  • Knowledge graph-based knowledge credibility measurement method
  • Knowledge graph-based knowledge credibility measurement method
  • Knowledge graph-based knowledge credibility measurement method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Embodiment 1: in combination with figure 1 , the present invention is a method for measuring the credibility of knowledge based on knowledge graphs, the method comprising the following steps:

[0027] The first step is relationship credibility measurement. There are many knowledge representation learning algorithms. In a specific embodiment of the present invention, the TransE algorithm is used to obtain the vector representation of entities and relationships. The calculation process of relationship credibility is attached figure 2 shown, including the following steps:

[0028] Step 1: Manually build a standard set of relationships, use the TransE algorithm to train entities and relationships, and embed entities and relationships in the knowledge map into a low-dimensional vector space.

[0029] Step 2, using the energy function to calculate the credibility of each triplet relationship. Calculated as follows:

[0030] E(h, r, t) = ||h+r-t||

[0031] Among them, h...

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 knowledge graph-based knowledge credibility measurement method, which comprises the following steps of: firstly, vectorizing entities and relationships in a knowledge graph by utilizing a knowledge representation learning algorithm, and performing calculating by utilizing an energy function and a sigmoid function to obtain relationship credibility; then, according to the attribute standard set, evaluating entity attribute values in the knowledge graph, and obtaining the attribute value credibility through calculation in a mode of combining lexical similarity and editing distance; then, constructing a question-answering system, and performing question solving credibility calculation on the knowledge in the knowledge graph by using the question-answering system and the question-answering standard set; and finally, in combination with the relationship credibility, the attribute value credibility and the problem solving credibility, performing weighted summation according to different weights to obtain the credibility of the knowledge graph. According to the method, error knowledge in the knowledge graph can be corrected, and the accuracy of the knowledge in the knowledge graph is improved.

Description

technical field [0001] The invention relates to knowledge graph knowledge credibility measurement in the field of knowledge graph improvement, in particular to a knowledge graph-based knowledge credibility measurement method. Background technique [0002] After Google proposed the concept of "knowledge graph" in 2012, knowledge graphs have been widely used in fields such as semantic search, intelligent question answering, and decision-making assistance. Use the knowledge graph to recommend search results, etc. [0003] Early knowledge graphs were basically constructed manually, which was not only very labor-intensive, but also unable to update new knowledge in the real world in a timely manner. Therefore, many researchers have been working on how to automatically extract knowledge from unstructured data, so that knowledge can be continuously obtained from the network to complement the existing knowledge graph. However, although automated construction technology saves a lot...

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): G06F16/36G06F40/35G06F40/186
CPCG06F16/367G06F40/186G06F40/35
Inventor 李必信方文跃李吟
Owner SOUTHEAST 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