Entity Search Using Classifier Correlation and Smoothing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current entity search methods rely on keyword-based matching, which results in a low matching rate and accuracy due to the conceptual gap between different user expressions, leading to poor user experience.
Innovation Solution
The method determines correlations between classifiers in query information and candidate entities using multiple matchers, including core words and modifiers, and applies context association and correlation smoothing algorithms to improve matching accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If keyword-based matching search method is used, then the search process is simple and fast, but the matching rate and accuracy are low due to conceptual gap between different user expressions
Solution Approach 1:
The patent introduces an entity library as an intermediary between the query and candidate entities. The entity library stores pre-defined entity information with multiple expressions and attributes, serving as a mediator that bridges the conceptual gap between different user expressions and standard entity representations, thereby improving matching accuracy without significantly increasing system complexity
Solution Approach 2:
The patent changes the matching parameters from simple keyword comparison to multi-dimensional entity attribute comparison. By evaluating multiple attributes (such as entity type, modifiers, and contextual features) rather than relying solely on exact keyword matches, the system achieves higher matching accuracy while managing complexity through structured attribute evaluation
2Reliability
If multiple classifiers and correlations are used to improve matching accuracy, then the matching success rate increases, but the computational complexity increases
Solution Approach 1:
The patent segments the matching process into distinct stages: first determining the entity type classifier, then determining the attribute classifier, and finally calculating correlations. This segmentation allows the system to handle complex multi-classifier matching by breaking it down into manageable steps, improving reliability while controlling computational complexity through progressive evaluation
Solution Approach 2:
The patent performs preliminary classification of entities into types and attributes before conducting the actual matching. By pre-determining classifiers and organizing entity information in advance, the system reduces the computational burden during the matching phase, achieving high matching success rates without excessive computational complexity
Data Source
AI summary
An entity search method, a related device, and a computer storage medium are provided. The method includes: determining a first classifier and a second classifier that are included in query information; determining, based on a first entity library and the first classifier and the second classifier that are included in the query information, s correlations corresponding to each of w candidate entities, wherein information about the candidate entity includes a third classifier and a fourth classifier, and the correlation indicates a correlation between the classifiers in the query information and the classifiers in the candidate entity; and determining, based on the s correlations corresponding to each of the w candidate entities, information about a target entity corresponding to the query information, wherein the target entity is an entity in the w candidate entities.