Chinese classical garden knowledge graph completion and cognitive reasoning method

A technology of knowledge graph and reasoning method, which is applied in the fields of knowledge graph completion and cognitive reasoning in Chinese classical gardens, and can solve problems such as difficulty in explaining neural network models.

Pending Publication Date: 2021-03-09
中国园林博物馆北京筹备办公室 +1
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the knowledge graph reasoning task, the problem that the neural network model is difficult to explain still exists, and how to explain the reasoning ability of the neural network is worth studying

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
  • Chinese classical garden knowledge graph completion and cognitive reasoning method
  • Chinese classical garden knowledge graph completion and cognitive reasoning method
  • Chinese classical garden knowledge graph completion and cognitive reasoning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0116] A Chinese classical garden knowledge map completion and cognitive reasoning method, comprising the following steps:

[0117] 1. Execute the function of system 1 in the dual-channel theory of cognitive science, that is, the function of the perception system, and realize the information extraction of entities and relationships.

[0118] Step 1 includes 4 small steps: step 1.1, calculate the word vector embedding sequence according to the input, step 1.2, perform Bi-LSTM encoding on the sequence, that is, two-way long short-term memory encoding, step 1.3, perform state transition, first judge if When the state reaches the final state, the entity and relationship have been extracted, and the end is over; otherwise, according to the probability calculation, go to the next step, step 1.4, select an entity extraction state transition action, or select a relationship extraction state transition action, after execution Both return to step 1.3, and finally complete the entity and...

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 Chinese classical garden knowledge graph completion and cognitive reasoning method, which comprises the following steps of: 1, executing the function of a system 1, namely a perception system, in a recognition science double-channel theory, and realizing information extraction of entities and relationships; and 2, executing the system 2 in the acknowledged scientific double-channel theory, namely analyzing the function of the system, performing reasoning, firstly judging whether knowledge graph completion is continuously performed or not, and if completion is completed, stopping the algorithm flow. The method of the invention mainly has the following technical advantages: 1, the method has the capability of third-generation artificial intelligence cognitive reasoning; 2, the utilization rate and the execution efficiency of information are improved; and 3, the method can be widely applied to national classical gardens.

Description

technical field [0001] The invention relates to the technical field of processing natural language data and information retrieval and its database structure, in particular to a method for complementing and cognitive reasoning of Chinese classical garden knowledge maps. Background technique [0002] Chinese classical gardens are world-renowned for their exquisite gardening skills and profound cultural connotations, and are an important part of Chinese traditional culture. Applying modern information technology to build a knowledge map of Chinese classical gardens has important practical significance for its protection and inheritance. [0003] The knowledge graph represents a collection of factual information in the form of relational triples. Each relational triple can be expressed as (e 1 ,r,e 2 ), where e 1 and e 2 is entity, r is e 1 and e 2 The relationship between. The most common knowledge graph representation is a multi-relationship graph, each triplet (r, e ...

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): G06F16/36G06F16/33G06F16/335G06N3/04
CPCG06F16/367G06F16/3344G06F16/335G06N3/044G06N3/045
Inventor 陈进勇王亚弟张宝鑫费晓飞刘冰谢帅
Owner 中国园林博物馆北京筹备办公室
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