Check patentability & draft patents in minutes with Patsnap Eureka AI!

Fishery standard knowledge graph construction method fusing rules and deep learning

A technology of deep learning and knowledge graph, applied in the direction of neural learning methods, neural architecture, semantic tool creation, etc., can solve problems such as complex and diverse sentence structure, uneven quality, no construction, etc., and achieve the effect of simplifying the complexity of work

Pending Publication Date: 2022-01-18
DALIAN OCEAN UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at this stage, there are problems such as uneven quality and complex and diverse sentence structures in fishery standard texts, so far there has been no report on the construction of fishery standard knowledge graphs.

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
  • Fishery standard knowledge graph construction method fusing rules and deep learning
  • Fishery standard knowledge graph construction method fusing rules and deep learning
  • Fishery standard knowledge graph construction method fusing rules and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] A method for constructing a fishery standard knowledge map that integrates rules and deep learning of the present invention is characterized in that it proceeds in accordance with the following steps:

[0039] Step 1. Collect the standard texts of fishery production and aquaculture, and preprocess the fishery standard texts: collect more than 100 fishery standard texts from 1998 to 2019, with 360,000 characters, through book scanning, crawler technology, and platform downloads; The collected fishery standard texts are pre-processed such as format conversion and data cleaning. Since most of the fishery standard texts exist in the form of books, PDF files, pictures, etc., after converting them into Word format, manual cleaning is required to delete typos, add Omit words and remove irrelevant words;

[0040] Step 2. Manually label the preprocessed fishery standard text and augment the data set according to the labeling rules:

[0041] The labeling rules are as follows:

...

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 fishery standard knowledge graph construction method fusing rules and deep learning. The fishery standard knowledge graph construction method comprises the steps of collecting a fishery standard text and preprocessing a fishery standard data set; marking the fishery standard text and augmenting a comparison relation entity pair; establishing a rule base and constructing and training a deep learning model; and according to a rule base and a trained BERT-BiLSTM-CRF model, continuously carrying out entity and relation recognition and extraction on a training set to obtain a relation triple, storing the relation triple in a graph database, and completing construction of the fishery standard knowledge graph. The complexity of graph construction work is greatly simplified.

Description

technical field [0001] The invention relates to the field of graph construction, in particular to a method for constructing a fishery standard knowledge graph that integrates rules and deep learning. Background technique [0002] Knowledge map construction is a mainstream method to improve the utilization rate of domain knowledge, and it is widely used in agriculture, medicine and other fields. The essence of a knowledge graph is a high-quality knowledge base, and its main knowledge expression method is an entity-relationship triplet, that is, the data structure of the knowledge graph is usually expressed in the form of a "triple". Fishery standard texts contain a large amount of aquaculture knowledge, which can be used to guide and regulate fishery production. With the rapid development of fishery standardization, the number of fishery standard texts has also increased rapidly. However, at this stage, there are problems such as uneven quality and complex and diverse senten...

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): G06F16/36G06F16/35G06Q50/02G06N3/04G06N3/08
CPCG06F16/367G06Q50/02G06F16/35G06N3/08G06N3/044G06N3/045
Inventor 于红孙哲涛杨惠宁邵立铭杨鹤刘巨升张思佳孙华王梓铭喻文甫
Owner DALIAN OCEAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com