Construction method of healthy diet knowledge network based on neural network and graph structure

A technology of neural network and knowledge network, applied in biological neural network model, neural architecture, unstructured text data retrieval, etc., which can solve problems such as low degree of automation and obvious field restrictions

Inactive Publication Date: 2020-04-28
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a method for constructing a healthy diet knowledge network based on a neural network and a graph structure. The traditional healthy diet knowledge base is not highly automated and has obvious field limitations, which greatly reduces the construction and maintenance costs of the healthy diet knowledge base. Fully automatic linking and labeling of the relationship between diseases and food entities, and no specific field restrictions

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
  • Construction method of healthy diet knowledge network based on neural network and graph structure
  • Construction method of healthy diet knowledge network based on neural network and graph structure
  • Construction method of healthy diet knowledge network based on neural network and graph structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] The database used by the healthy diet knowledge network in this embodiment is the NoSQL map database Neo4J. Compared with the relational database used in the traditional knowledge base, the map database can store entities and the relationship between entities in a richer form, and at the same time provide more It is a convenient and fast query method.

[0073] Such as figure 1 As shown, the present embodiment provides a method for constructing a health knowledge network based on a neural network and a map structure, and the method includes the following steps:

[0074] (1) Carry out word vector modeling on all text corpus participating in learning and training

[0075] The "word vector" in this embodiment refers to the neural network word embedding modeling algorithm and its supporting modeling tool word2vec proposed by Google in 2013. Physique Description These text corpora are input into the word vector tool word2vec, and the word vector modeling is performed on it....

Embodiment 2

[0116] This embodiment is a specific application example, which is called by relevant researchers and application developers in the form of middleware, and is composed of the following components: 1) Graph database maintenance component P01, including querying the graph database, adding and deleting nodes and edges , security backup and other functions; 2) word vector operation component P02; 3) association detection and representation component P03; 4) neural network relationship classification component P04; 5) auxiliary function component P05, including text preprocessing, text original data management, stage Functions such as result cache management. The overall architecture of the method described in the invention is as follows Figure 6 As shown, the specific functions and usage techniques of each component are shown in Table 1 below.

[0117]

[0118] Table 1 Specific functions and usage technical table of each component

[0119] The text data processed by the meth...

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 constructing a healthy diet knowledge network based on a neural network and a map structure, comprising: performing word vector modeling on a text corpus, so that each non-stop word in the text corpus corresponds to a word vector of a fixed length; Use the cosine similarity between two word vectors to measure the degree of association between the entities corresponding to the two word vectors; extract food and disease entity nodes, treat these two entity nodes as entity nodes in the topology, and construct The edge relationship between entity nodes forms a graph structure, so that the edge relationship between entity nodes is described by a set of tokens; the vector representation corresponding to each token is arranged to obtain the representation of the edge relationship between entity nodes matrix; design a classification framework based on a deep neural network, input a representation matrix, and classify the polarity of the edge relationship between entity nodes. The invention effectively solves the problems of low automation degree of traditional healthy diet knowledge base, obvious field limitation and the like.

Description

technical field [0001] The invention relates to a method for constructing a healthy diet knowledge network, in particular to a method for constructing a healthy diet knowledge network based on a neural network and a map structure, and belongs to the technical field of knowledge representation and knowledge base construction. Background technique [0002] With the improvement of people's living standards, more and more people begin to pay attention to their own dietary health issues. Since ancient times, traditional Chinese medicine has been emphasizing that "medicine is not as good as food", and "medicine is three-point poison". Naturally, medicine cannot be taken frequently in daily life. Reasonable and healthy diet and combination are a good way to maintain a healthy life. However, in the fast-paced and stressful modern society, it is difficult for people to have time to consult doctors or nutritionists. It is an urgent need for people to get accurate and effective healthy...

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): G16H20/60G16H70/00G06F40/295G06F16/33G06F16/36G06F16/901G06N3/04
CPCG06F16/3344G06F16/367G06F16/9024G06F40/295G06N3/045
Inventor 文贵华胡杨
Owner SOUTH CHINA UNIV OF TECH
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