Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for predicting a target node of a knowledge graph based on user feedback information

A target node and feedback information technology, which is applied in digital data information retrieval, special data processing applications, unstructured text data retrieval, etc., can solve problems such as lack of interpretability, and achieve a clear and clear detection process

Pending Publication Date: 2020-05-12
EAST CHINA NORMAL UNIVERSITY
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] Although the effect of the deep learning model is remarkable, because the model automatically extracts features through big data, the process is not interpretable. In practical applications, only the final judgment result of the model can be seen

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
  • Method for predicting a target node of a knowledge graph based on user feedback information
  • Method for predicting a target node of a knowledge graph based on user feedback information
  • Method for predicting a target node of a knowledge graph based on user feedback information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] refer to figure 1 , this embodiment specifically includes the following steps:

[0032] In order to better represent the relationship between data, a knowledge graph (Knowledge Graph, KG) is constructed first. In the graph, the label of the sample is defined as the target node, and the characteristic data appearing in the sample is defined as the observation node. If the observation If the node appears in the sample where the target node is located, it is considered that the observed node has a relationship with the target node, and a relationship edge (Edge) is established. Calculate the conditional probability P target node observation node and the conditional probability P observation node target node of the relevant nodes on each relationship edge:

[0033]

[0034]

[0035] According to the user's input information, find relevant observation nodes in the graph to construct a known node set (KnownNode Set, KN-Set), and use the algorithm BN-local to calculate ...

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 method for predicting a target node of a knowledge graph based on user feedback information, and the method comprises the following steps: 1) constructing the knowledge graphaccording to sample data, defining the target node and an observation node, and carrying out the statistics of related probability data; 2) based on user input information, designing a BN _ local algorithm to predict the probability of each target node; and 3) designing a vn _ DQN model, judging whether prediction is completed or not according to the probability state of the current target node,if so, outputting a prediction result to complete prediction, otherwise, recommending related observation nodes to inquire a user, and optimizing a decision path. According to the knowledge graph target node prediction method based on the user feedback information provided by the invention, target prediction can be effectively and interpretably carried out, and a decision path is optimized.

Description

technical field [0001] The present invention relates to the problem of node prediction in knowledge graphs, specifically mining the feature information in target events to construct entities and the relationship between entities, and using these information to predict targets, that is, a method for predicting target nodes in knowledge graphs based on user feedback information method. Background technique [0002] The definition of artificial intelligence is very broad. With the deduction of time and technological progress, artificial intelligence technology will continue to evolve. With the existing technology and large data reserves, this technology has made great achievements in many fields such as security, medical treatment, and transportation. Eye-catching effect. The main problems in these fields can be transformed into a target detection problem. For example, emergencies in security problems can be used as a detection target, diagnosed diseases in medical problems ca...

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
IPC IPC(8): G06F16/36G06F16/2455G16H10/60
CPCG06F16/367G06F16/24564G16H10/60
Inventor 杨燕李芸陈成才贺樑庄建林陈培华杜玉清郑琪霍沛
Owner EAST CHINA NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com