Question Answering Disambiguation via Contextual Concept Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Question-answering systems often return a large number of search results with varying relevance, making it difficult for users to identify the most relevant answers due to ambiguity in query responses, as multiple answers may be associated with the same concept but have different values.

Innovation Solution

A question-answering system that identifies concepts associated with answer results and determines disambiguation information through contextual analysis and user interaction, allowing for the elimination of less relevant answers by obtaining clarification information from users to resolve ambiguity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a question-answering system returns multiple search results to ensure comprehensive coverage, then the completeness of information is improved, but the difficulty of identifying relevant answers increases due to ambiguity

Engineering Contradiction:

Improvecompleteness of informationVSAvoiddifficulty of identifying relevant answers

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent introduces disambiguation information as an intermediary element between the query and search results. This mediator provides contextual clarification that helps users distinguish relevant answers from irrelevant ones, thereby maintaining comprehensive result coverage while reducing the difficulty of identifying relevant information.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the search result presentation by introducing distinct disambiguation information components that separate and clarify different aspects of ambiguous results. This segmentation allows users to process information in organized chunks rather than facing a undifferentiated mass of results.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If exhaustive metadata is captured to improve disambiguation accuracy, then the precision of search results is improved, but the complexity of the system increases

Engineering Contradiction:

Improveprecision of search resultsVSAvoidcomplexity of metadata capture

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies partial action by capturing only the specific metadata elements necessary for disambiguation rather than attempting to capture all possible metadata. This selective approach achieves sufficient precision for resolving ambiguity without incurring the complexity of comprehensive metadata capture.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent changes the parameter of metadata capture from exhaustive to selective, focusing on capturing only those parameters (contextual elements) that are relevant for disambiguation. This parameter change reduces system complexity while maintaining the precision needed for effective result differentiation.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If disambiguation information is obtained through user interaction to improve answer relevance, then the accuracy of selected answers is improved, but the time required to obtain results increases

Engineering Contradiction:

Improveaccuracy of selected answersVSAvoidtime required to obtain results

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary action by pre-computing and storing disambiguation information during the indexing phase, before actual search queries are executed. This preliminary preparation allows the system to quickly retrieve and apply disambiguation data during search operations, improving accuracy without significantly increasing query response time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements self-service by having the system automatically generate and apply disambiguation information without requiring manual user input or interaction. The system serves itself by autonomously resolving ambiguities using pre-computed contextual data, thereby maintaining high accuracy while minimizing time loss.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20230205824A1Contextual Clarification and Disambiguation for Question Answering Processes

Publication Date: 2023.06.29 PRYON INC

AI summary

Disclosed are methods, systems, devices, apparatus, media, and other implementations, including a method that includes receiving query data representative of a question relating to source content of one or more source documents, and causing a search of a data repository maintaining data portions relating to the one or more source documents to determine a set of multiple matches between the query data and the data portions. The method additionally includes identifying one or more concepts associated with the set of multiple matches, with at least one of the identified concepts being associated with at least some of the multiple matches and including different respective values associated those some of the multiple matches, obtaining disambiguation information relevant to the at least one of the identified concepts, and selecting at least one of the multiple matches based on the obtained disambiguation information.