Interactive Entity Disambiguation via User Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current text analytic tools cannot confirm the true identity of entities like 'Mike Smith' and do not allow users to participate in the selection of intended entities, leading to potential incorrect selections from a plurality of entities stored in their databases.

Innovation Solution

A computer program product enables users to disambiguate entities in electronic documents by providing a list of potential entities related to the user-provided entity, allowing users to select the correct one, and incorporating metadata associated with the selected entity into the document, with the option to add, delete, or edit metadata.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If text analytic tools automatically select entities from their databases, then processing speed is improved, but accuracy of entity identification deteriorates because users cannot confirm the true identity

Engineering Contradiction:

Improveprocessing speedVSAvoidaccuracy of entity identification

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system provides feedback to the user by presenting a list of potential entities with metadata, allowing the user to review and confirm the selected entity. This feedback mechanism enables users to verify accuracy while maintaining efficient processing through automated suggestion.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system serves itself by automatically extracting entities and providing suggestions, but allows the user to take control when needed. The user can quickly confirm or correct entity selections without manual analysis of all possibilities, maintaining both speed and accuracy.

Inventive Principle:

Principle #25Self-service

2Loss of time

If text analytic tools make assumptions about entity properties from context, then processing time is reduced, but reliability of entity information deteriorates

Engineering Contradiction:

Improveprocessing timeVSAvoidreliability of entity information

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The system performs preliminary action by automatically extracting entities and gathering metadata before user review. This pre-processing reduces processing time while the user's confirmation ensures reliability, as the system prepares information in advance but relies on user validation for accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system provides feedback showing the assumed entity properties and metadata for user confirmation. This allows the system to maintain efficient automated processing while giving users the ability to correct any inaccuracies, ensuring both speed and reliability.

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If multiple entities with similar names are stored in the database, then comprehensive coverage is improved, but difficulty in selecting the correct entity increases

Engineering Contradiction:

Improvecomprehensive coverageVSAvoidease of selecting correct entity

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system segments the selection process into two stages: automated entity extraction and user confirmation. This segmentation maintains comprehensive coverage by keeping all similar entities in the database while simplifying user interaction through structured presentation and selection guidance.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary layer between the database and the user interface. This intermediary presents filtered and organized entity lists with metadata, making it easier for users to identify and select the correct entity from multiple similar names without requiring them to search through the entire database.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Measurement precision

If users manually verify each entity selection, then accuracy is improved, but productivity deteriorates due to time-consuming verification

Engineering Contradiction:

Improveaccuracy of entity selectionVSAvoiddocument creation speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system applies partial action by requiring user verification only for entity selections that need confirmation, rather than mandating manual verification of all entities. This maintains accuracy where needed while allowing rapid acceptance of confident automated selections, preserving overall productivity.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system serves itself by providing intelligent automated entity extraction and metadata gathering, reducing the burden on users. Users only need to confirm or correct selections rather than perform complete manual verification, maintaining both accuracy and high productivity.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS8949241B2Systems and methods for interactive disambiguation of data

Publication Date: 2015.02.03 REFINITIV US ORGANIZATION LLC

AI summary

Systems, methods and computer program products residing on a computer readable medium for use in and capable of storing computer instructions therein for enabling a computer to perform a computer-implemented and user assisted process for disambiguating entities in an electronic document that includes: (a) creating, by the user, an electronic document; (b) providing, by the computer, a list to the user of potential entities related to an entity provided by the user in the electronic document; and (c) selecting, by the user, an entity provided in the computer provided list.