Automated Entity Search Scoring for Incomplete Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data aggregation techniques require significant experience and skill, and struggle with comprehensive searches for entities with dispersed information, often resulting in limited obvious hits and incomplete information due to the use of false or incomplete identification data.
Innovation Solution
A computing system configured to search multiple data sources, automatically filter and structure information, and generate additional searches to aggregate data on an entity of interest, using seed entities, related entities, and various search queries to uncover hidden connections and properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional search techniques are used to search for information about an entity, then the search process is simple and quick, but the search results are limited and incomplete when the entity uses false or incomplete identification information
Solution Approach 1:
The system introduces an intermediary automated assistance layer between the analyst and the search tools. This intermediary automatically generates and executes search queries based on entity properties, transforming the complex multi-step search process into a simplified automated workflow that maintains completeness without requiring analyst expertise in advanced search techniques
Solution Approach 2:
The system performs preliminary actions by automatically generating search queries and executing searches before the analyst needs to review results. The automated assistance pre-processes the information gathering by conducting searches across multiple data sources using entity properties, so that when the analyst reviews results, the comprehensive search work has already been completed
2Productivity
If an automated system is used to generate and execute search queries, then the completeness of information discovery is improved, but the complexity of the system increases
Solution Approach 1:
The automated assistance system is designed as a universal multi-functional tool that can work with any entity type and any data source. It performs multiple functions including generating search queries, executing searches, collecting results, and presenting findings to analysts. This universal design improves productivity across different use cases while managing complexity through a unified interface rather than requiring separate complex systems for each function
Solution Approach 2:
The system implements self-service by automatically generating search queries and executing searches without requiring manual intervention from the analyst. The automated assistance takes entity properties as input, autonomously conducts comprehensive searches across multiple data sources, and delivers results to the analyst, freeing the analyst from the complex task of manually constructing and executing search queries
3Loss of information
If multiple data sources are searched with various queries to find dispersed information, then the comprehensiveness of results improves, but the time and effort required increases significantly
Solution Approach 1:
The system ensures continuity of useful action by automatically executing multiple search queries across different data sources without interruption. Rather than requiring the analyst to sequentially search each source, the automated assistance continuously conducts searches using entity properties, maintaining productive action throughout the information gathering process and reducing total time while maintaining completeness
Solution Approach 2:
The system performs preliminary search actions by automatically generating and executing search queries before the analyst needs the results. By pre-conducting comprehensive searches across multiple data sources using entity properties, the system prepares the information in advance, reducing the time the analyst spends on search activities while ensuring complete information is available
Data Source
AI summary
Systems and methods are provided for identifying relevant information for an entity, referred to as a seed entity. A plurality of search queries can be generated each comprising a property of a seed entity or one of the entities associated with the seed entity (seed-linked entities). Preferably, a collection of search queries includes ones representing different properties of the seed entity and properties of different seed-linked entities. Optionally, the collection of search queries is optimized to reduce search burden. Searches can then be conducted with the search queries in one or more data sources to obtain a plurality of search results, wherein each search result comprises a hit entity and one or more entities associated with the hit entity (hit-linked entity). For each of the search results, a score can be determined taking as input (a) likelihood of match between the seed entity and the hit entity or between a seed-linked entity and a hit-linked entity, (b) presence of a new entity in the search result not present in the search queries or a difference between the new entity and an entity present in the search queries, and (c) characteristic of the new entity in the search result. Based on the scores, high priority search results can be presented a user for further analysis.