Association Inference Model for Indirect Relationship Discovery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Practitioners face significant challenges in discovering new domains of interest and determining relevant methods for specific problems, as existing automated tools lack robustness and accuracy in identifying relationships between concepts, especially in areas with scarce literature and expert guidance.

Innovation Solution

A data management component (DMC) employs AI techniques to analyze information from documents and external sources, generating an association inference model that embeds entities and relationships into a common representation, allowing for the prediction of indirect relationships between concepts and providing relatedness scores, thereby facilitating knowledge discovery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated tools are used to identify relationships between concepts, then productivity is improved, but measurement precision and reliability deteriorate

Engineering Contradiction:

Improveefficiency in discovering new domainsVSAvoidaccuracy in identifying relationships between concepts

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary evaluation component that acts as a mediator between the AI component and the final output. This intermediary uses multiple evaluation metrics (precision, recall, F1-score) and configurable thresholds to assess the reliability of AI-generated relationships before they are finalized, thereby maintaining productivity while improving measurement precision

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback mechanisms where evaluation results are used to adjust thresholds and parameters for subsequent processing. The evaluation component provides feedback on the quality of relationships identified by the AI component, allowing the system to iteratively improve its accuracy while maintaining high productivity through automated adjustment

Inventive Principle:

Principle #23Feedback

2Measurement precision

If manual literature review and expert consultation are used, then measurement precision is improved, but loss of time increases

Engineering Contradiction:

Improveaccuracy in domain discoveryVSAvoidtime spent in vetting and discovering new domains

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary automated analysis using the AI component to identify potential relationships and generate hypotheses before human experts intervene. This preliminary action filters and prioritizes candidates, so that when experts do review literature or provide input, they focus only on the most promising areas, thereby maintaining precision while reducing time loss

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies partial automation where the AI component handles the bulk of relationship identification (excessive action in terms of volume), while human experts perform selective verification on a subset of results (partial action). This division allows the system to process large volumes of data quickly while maintaining high accuracy through targeted human review

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If AI techniques are employed to analyze information and generate association models, then productivity is improved, but reliability deteriorates due to bias and accuracy issues

Engineering Contradiction:

Improveefficiency in knowledge discoveryVSAvoidrobustness and accuracy of relationship identification

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The evaluation component serves as an intermediary that independently assesses the output of the AI component using multiple metrics and thresholds. This intermediary layer provides a check on AI-generated relationships, filtering out unreliable results and flagging those requiring human review, thereby improving reliability without sacrificing the productivity benefits of AI

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically adjusts parameters such as confidence thresholds, evaluation metrics weights, and filtering criteria based on the specific domain and data characteristics. By changing these parameters adaptively, the system optimizes the balance between productivity and reliability for different knowledge discovery tasks

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20230022673A1Knowledge discovery based on indirect inference of association

Publication Date: 2023.01.26 AT&T INTELLECTUAL PROPERTY I L P

AI summary

Techniques for knowledge discovery based on indirect inference of association are presented. A data management component (DMC) can determine and extract, in a structured format, entities, relationships between entities, and concepts relating thereto in documents, based on analysis of information in the documents and/or keywords relating to concepts, to generate an association inference model. Using artificial intelligence techniques, DMC can embed the entities and relationships to a common representation to generate and train a scoring model that can be used to evaluate and score similarity strength between entities, including entities that do not have a known relationship, and can predict or infer relationships, including indirect relationships, between entities or between concepts. In that regard, DMC or user can evaluate concept-level scores to determine a level of relationship between concepts. DMC can feedback information from the scoring model or evaluation to update the association inference model.