Knowledge Graph Construction for Artwork Data Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The dispersion of knowledge related to art works makes user inquiries difficult, with important information often being omitted, thereby affecting the searching experience.
Innovation Solution
A method for building a knowledge graph that involves acquiring source data related to preset keywords, cleaning it using a data dictionary and error information table, extracting entities and relationships, and fusing this information into data triples for storage in a graph database, specifically designed for the field of arts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If knowledge related to art works is dispersed across multiple sources, then the quantity of information available increases, but user inquiry difficulty increases and important information is often omitted
Solution Approach 1:
The patent merges dispersed knowledge about art works from multiple sources into a unified knowledge graph structure. Entities such as painters, paintings, and museums are integrated with their relationships and attributes organized in a centralized graph database, allowing users to access comprehensive information through single queries rather than searching across scattered sources.
Solution Approach 2:
The knowledge graph acts as an intermediary layer between dispersed art work information and user inquiries. It processes and structures raw data from multiple sources into organized entities and relationships, mediating between the complexity of dispersed information and the simplicity of user search requirements.
2Quantity of substance
If knowledge related to art works is dispersed across multiple sources, then the quantity of information available increases, but information completeness decreases due to omitted important information
Solution Approach 1:
By merging data from multiple sources into a unified knowledge graph, the system ensures that all important information about art works, painters, and museums is captured and stored in one place, preventing information loss that occurs when data remains dispersed across separate sources.
Solution Approach 2:
The system performs preliminary data collection and integration by building the knowledge graph in advance, organizing all relevant entities and relationships before user inquiries occur. This preliminary structuring ensures that complete information is ready for retrieval, preventing omission of important details during user searches.
3Quantity of substance
If data is collected from multiple sources including semi-structured and structured data, then the coverage of art-related information increases, but data processing complexity increases
Solution Approach 1:
The patent segments data processing into distinct stages: data collection from multiple sources, cleaning and preprocessing, entity extraction, relationship identification, and graph construction. This segmentation handles the complexity of processing both semi-structured and structured data by breaking it into manageable steps, while maintaining comprehensive coverage of art-related information.
4Measurement precision
If data cleaning and entity extraction are performed using preset data dictionaries and error information tables, then data accuracy improves, but processing time increases
Solution Approach 1:
The system performs data cleaning and entity extraction in advance during knowledge graph construction, using preset data dictionaries and error information tables to ensure high accuracy. By completing these time-consuming processing steps beforehand, the system maintains data accuracy while enabling fast retrieval during user inquiries.
Data Source
AI summary
The present disclosure relates to a method for building a knowledge graph, an electronic apparatus and a non-transitory computer-readable storage medium. The method for building a knowledge graph includes following steps: acquiring source data related to preset keywords according to the preset keywords; cleaning the source data according to a preset data dictionary and an error information table; extracting entities, attribute information of the entities and relationship information among the entities from the cleaned source data according to the preset data dictionary and an entity relationship; fusing the entities, the attribute information of the entities and the relationship information among the entities to obtain data triples, and taking the data triples as a built knowledge graph; and storing the knowledge graph into a preset graph database.