Multi-Dimensional Entity Tag Mining via Syntax Templates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for mining entity description tags are limited to specific fields and have a single tag dimension, making them ineffective for extracting entity description tag data from multiple dimensions.
Innovation Solution
A method that involves acquiring core words and syntax-dependent templates for each field, performing matching on data sources to determine description tags, recognizing entities in larger data sources, and correlating them to generate entity description tags across multiple dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If instructed extraction way is used to generate description tags, then the extraction process is simple and direct, but the method is only applicable to a special field and has a single tag dimension
Solution Approach 1:
The patent applies universality by designing a multi-dimensional tag extraction framework that can handle multiple fields simultaneously. The system uses multiple syntax templates (subject-predicate-object, attribute-value, etc.) and processes both structured and unstructured data sources, making it adaptable to different domains while maintaining a unified extraction architecture.
Solution Approach 2:
The patent transitions from single-dimension tag extraction to multi-dimensional tag extraction by introducing multiple syntax templates, multiple data sources (structured and unstructured), and multiple processing dimensions (field-level tags and entity-level tags). This dimensional expansion enables the system to capture diverse entity characteristics across different fields.
2Measurement precision
If multiple data sources and multi-dimensional tagging are implemented, then the coverage and accuracy of entity description tag mining is improved, but the system complexity increases
Solution Approach 1:
The patent segments the complex tag extraction task into distinct components: field-level description tag extraction using syntax templates, entity recognition in unstructured data, and correlation matching between entities and tags. This segmentation allows each component to be processed independently with appropriate methods, reducing overall system complexity while maintaining multi-dimensional capabilities.
Solution Approach 2:
The patent introduces an intermediary correlation matching mechanism that bridges the field-level description tags and entity-level recognition results. This intermediary layer computes matching degrees and correlates entities with appropriate tags, managing the complexity of integrating multiple data sources while improving accuracy.
3Ease of operation
If instructed extraction way is used, then the extraction process is straightforward, but the confidence and relevance of mining results are limited
Solution Approach 1:
The patent merges multiple extraction approaches: instructed extraction using syntax templates for structured data and entity recognition methods for unstructured data. By combining these different approaches and correlating results across multiple dimensions, the system enhances the confidence and relevance of mining results while maintaining operational straightforwardness through a unified processing framework.
Data Source
AI summary
The present disclosure provides a method, a terminal device and a storage medium for mining an entity description tag. The method includes: acquiring a group of one or more core words corresponding to each field and a first syntax dependent template corresponding to each core word; performing a matching on each data in a first data source by using the first syntax dependent template to determine a first description tag set in each field; performing a recognition on each data in a second data source to determine an entity set; determining a second description tag set based on a matching degree between each description tag in the description tag set of each field and each data in the second data source; and determining an entity description tag set based on a correlation between each entity in the entity set and each description tag in the second descriptive tag set.