Entity Resolution System for Investigative Data Compilation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The scattered nature of digital records across different databases, lack of centralized management, and varying data structures and ontologies make it challenging to collect and analyze information about an entity effectively for investigative purposes.

Innovation Solution

A method involving search queries across multiple data sources with known characteristics of an entity, merging matching records into unified records, and enabling user annotation and ranking to present comprehensive information for investigation, while allowing for iterative searches and data enrichment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If digital records are stored across multiple separate databases with different structures, then data can be maintained by individual organizations, but it becomes difficult to collect and analyze complete information about an entity

Engineering Contradiction:
Improvedata storage flexibilityVSAvoiddata collection complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a centralized entity resolution system that acts as an intermediary between multiple distributed databases and the user. This system receives search queries, automatically searches across multiple data sources with different structures, resolves entity identities across databases, and returns unified results. The intermediary handles the complexity of data collection and integration, allowing individual databases to maintain their independence while enabling comprehensive entity analysis.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Quantity of substance

If records from multiple databases are collected, then more information about an entity can be obtained, but the data becomes redundant and difficult to manage

Engineering Contradiction:
Improveinformation completenessVSAvoiddata management complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent implements an entity resolution process that merges multiple records about the same entity into a single unified view. The system collects records from multiple databases, identifies that they refer to the same entity through resolution techniques, and combines them into consolidated results. This merging process eliminates redundancy while preserving complete information, presenting unified entity data to users rather than scattered duplicate records.

Inventive Principle:
Principle #5Merging (Combining)

3Productivity

If automated search and compilation processes are implemented, then information retrieval efficiency is improved, but the system complexity increases

Engineering Contradiction:
Improveinformation retrieval efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements self-service automation where the entity resolution system automatically performs search queries across multiple databases, resolves entity identities, compiles results, and presents unified information without requiring manual intervention. The system services itself by managing the complex tasks of data collection, resolution, and compilation automatically, improving retrieval efficiency while encapsulating system complexity within the automated process.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS11475031B2Identification and compiling of information relating to an entity
Publication Date: 2022.10.18 PALANTIR TECHNOLOGIES INC
  • US11475031B2 patent drawing
  • US11475031B2 patent drawing
  • US11475031B2 patent drawing

AI summary

Systems and methods are provided for identifying and compiling information relating to an entity for investigative analysis. The system may comprise one or more processors and a memory storing instructions that, when executed by the one or more processors, cause the system to search, in one or more data sources, with a plurality of known characteristics of an entity to obtain a first plurality of records, identify from the first plurality of records a subset of records that match the known characteristics with a substantial confidence, compile the subset of records to form a unified record representing the entity and conduct a second search with information from the unified record to obtain a second plurality of search results.