Robot active inquiry method based on traditional Chinese medicine clinical knowledge graph

A technology of knowledge map and robot, which is applied in the field of robot active consultation based on clinical knowledge map of traditional Chinese medicine, which can solve the problems of complexity and difficulty of artificial intelligence consultation

Active Publication Date: 2020-02-25
广州西思数字科技有限公司
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention aims to provide a robot active consultation method based

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
  • Robot active inquiry method based on traditional Chinese medicine clinical knowledge graph
  • Robot active inquiry method based on traditional Chinese medicine clinical knowledge graph
  • Robot active inquiry method based on traditional Chinese medicine clinical knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0134] This embodiment provides a process of establishing a TCM clinical knowledge graph.

[0135] The establishment of a TCM clinical knowledge map mainly includes the steps of knowledge modeling, setting knowledge sources, knowledge extraction, and knowledge fusion;

[0136] 1.1. Knowledge modeling: disease, disease location, nicknames, syndromes, symptoms, treatment rules, prescriptions, and Chinese medicinal materials are entities, and the entities are related to each other; every two entities are connected by a line to form a ternary Group, ie ; for example, represe , The first such as wrapped>;

[0137] 1.2. Set knowledge sources; in this embodiment, the knowledge sources include TCM clinical terminology system, TCM internal medicine knowledge base, TCM expert summary processing, online TCM-related Q&A and consultation on the Internet, encyclopedia knowledge on the Internet, Ancient medical records, medical records, etc.;

[0138] 1.3. Knowledge extraction: Knowledge extractio...

Embodiment 2

[0160] This embodiment provides a predictive reasoning model M based on the TCM clinical knowledge graph obtained by using the method described in embodiment 1. transH The specific steps are:

[0161] 2.1. The TCM clinical knowledge map KG obtained from the method in Example 1 tcm Three files are output in the file, the first file is the entity code file, which represents the digital code of the entity; the second file is the relation code file, which represents the digital code of the entity; the third file is the knowledge triple data after the encoding;

[0162] 2.2. According to the knowledge triple data, use a random strategy to generate negative sample data Δ', and positive sample data is expressed as Δ;

[0163] 2.3. Introduce TransH to train the TCM clinical knowledge map; suppose a fact (h, r, t), r represents the relationship vector, d r Through r through vector w r ∈R is obtained by projection, h and t represent entity vectors, and the score that defines the r relationship...

Embodiment 3

[0175] This embodiment provides a TCM syndrome identification process based on the TCM clinical knowledge graph. The robot's consultation process is essentially collecting patient information about symptoms. Suppose that the current robot collects the patient's symptom information set S, and the robot compares the set S with the knowledge of the TCM clinical knowledge map to diagnose the syndrome type and disease of the disease. The expected diagnosis result is the syndrome type distribution, such as figure 2 As shown, the specific steps are:

[0176] 3.1. From the TCM clinical knowledge map KG tcm Acquire knowledge points of Chinese medicine and convert them into sx , Card type KR s >The record form, denoted as KR ssx ;

[0177] 3.2, from KR ssx Extract msx , Card type KR s >The record is marked as KR mssx ;

[0178] 3.3, put KR sx , KR msx The two sets are vectorized separately:

[0179] 3.3.1. Find out KG of TCM clinical knowledge graph tcm Symptom Collection S tcm , Remembe...

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 robot active inquiry method based on a traditional Chinese medicine clinical knowledge graph. In the inquiry process, the robot has the initiative right of the knowledge graph, the information of a patient is collected through multiple times of inquiry, diagnosis and iteration are conducted to complete an inquiry task, and then final diagnosis is conducted. The method relates to the knowledge graph, knowledge expression learning, knowledge reasoning technology and a syndrome type diagnosis iteration model. According to the invention, the problems of high complexity and big difficulty of artificial intelligence traditional Chinese medicine inquiry can be solved.

Description

Technical field [0001] The invention relates to the technical field of artificial intelligence, and in particular to a method for robot active questioning based on a TCM clinical knowledge graph. Background technique [0002] Traditional Chinese medicine is a treasure of the Chinese nation's culture. It is a medical science that has been gradually developed by the people of all ethnic groups in our country in the course of thousands of years of production and life practices and the struggle against diseases. Whether in the treatment of diseases or in the prevention and health care, it has significant characteristics and advantages, and has become an important part of my country's health service. Traditional Chinese medicine continues to innovate and develop, the theoretical system is becoming more and more sophisticated, and the technical methods are more abundant, forming distinctive features. [0003] "Wearing, hearing, asking and cutting" is a characteristic diagnosis method of...

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): G16H50/30G16H80/00G06F16/332G06F16/36
CPCG16H50/30G16H80/00G06F16/3329G06F16/367
Inventor 梁锐秦建增
Owner 广州西思数字科技有限公司
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