Entity Identification System Using Multi-Attribute Relevancy Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines face difficulties in identifying content related to a specific person due to the prevalence of shared names, as they rely on keyword recognition which is not effective in distinguishing between individuals with similar or same names.
Innovation Solution
A method is developed to identify entities by generating sets of candidate identity attributes and calculating relevancy scores based on entity attributes specified in documents, allowing for the accurate identification of individuals by processing metadata and content analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If search engines use keyword recognition to identify content related to a name, then the search process is simple and fast, but the accuracy of identifying content related to a specific person deteriorates due to shared names
Solution Approach 1:
The patent segments the identification task into multiple independent processes, each generating candidate identity attributes (such as name, location, affiliation, date of birth) from different sources. This segmentation allows the system to evaluate multiple attributes simultaneously rather than relying on a single keyword match, thereby improving identification accuracy while maintaining efficiency through parallel processing.
Solution Approach 2:
The system changes the identification parameters from simple keyword matching to a multi-dimensional attribute comparison framework. By evaluating multiple identity attributes (name, location, affiliation, date of birth) with weighted relevancy scores, the system transforms the identification process from a single-parameter search to a multi-parameter evaluation, significantly improving accuracy for distinguishing individuals with similar names.
2Measurement precision
If multiple processes generate candidate identity attributes to improve identification accuracy, then the identification precision improves, but the system complexity increases
Solution Approach 1:
The patent implements a universal identification framework where multiple processes perform the same function of generating candidate identity attributes but from different data sources and methodologies. This multi-functionality allows the system to maintain a standardized output format (candidate attributes with relevancy scores) across diverse input sources, managing complexity through uniform processing interfaces while leveraging diverse identification approaches.
Solution Approach 2:
The system introduces an intermediary layer that consolidates candidate identity attributes from multiple processes. This intermediary component receives attributes from various sources, standardizes their format, calculates综合 relevancy scores, and presents a unified set of candidates for selection. This intermediary structure manages system complexity by providing a single point of integration rather than requiring direct coordination between all processes.
3Measurement precision
If the system processes multiple candidate identity attributes with relevancy scores, then the accuracy of distinguishing individuals with similar names improves, but the processing time increases
Solution Approach 1:
The system applies partial action by focusing computational resources on the most promising candidate attributes first. By calculating relevancy scores and prioritizing candidates based on their likelihood of being correct, the system processes only the necessary subset of attributes in detail rather than exhaustively analyzing all possible candidates, thus reducing processing time while maintaining high accuracy through targeted evaluation.
Data Source
AI summary
Some embodiments provide a program that identifies an entity having an entity attribute. The program receives, from each method of several methods, a set of candidate identity attributes that are each for identifying a particular entity having the entity attribute specified in the document. Each method of the several methods generates the corresponding set of candidate identity attributes based on the entity attribute specified in a document. The program calculates a score for each candidate identity attribute in the sets of candidate identity attributes. The program identifies, based on the sets of scores, an identity attribute from the sets of candidate identity attributes that identifies the entity having the entity attribute specified in the document.