Knowledge-Enriched Item Set Expansion via Rule-Based Inference

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current item set expansion methods fail to achieve high precision and recall due to their agnosticism towards specific application-domain knowledge, relying mainly on probabilistic methods and machine learning techniques without incorporating rule-based inference or comprehensive entity semantics, leading to limited practical use.

Innovation Solution

The proposed solution combines statistical evaluations with rule-based knowledge processing using a knowledge base that includes domain-specific facts and rules, along with an inference engine to select items that co-occur with seed items in documents, improving both precision and recall by enforcing domain-specific conditions and disambiguating user intent.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If probabilistic methods and machine learning techniques are used for item set expansion, then the system can process data automatically, but the precision and recall remain limited due to lack of domain-specific knowledge

Engineering Contradiction:

Improveautomatic processingVSAvoidprecision and recall

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The patent combines probabilistic methods and machine learning techniques with rule-based inference and domain-specific knowledge bases. This merging integrates automatic processing capabilities with precision-enhancing domain expertise, allowing the system to benefit from both automation and specialized knowledge to improve precision and recall simultaneously

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces a knowledge base as an intermediary component that stores domain-specific facts and rules. This intermediary bridges the gap between automatic processing and domain expertise, allowing the system to consult specialized knowledge during item set expansion without sacrificing automation

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If general probabilistic methods are used, then the system has broad applicability, but it fails to achieve high precision in specific application domains

Engineering Contradiction:

Improvebroad applicabilityVSAvoidprecision in specific domains

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent makes the system dynamic by allowing it to adapt its behavior based on the application domain. The knowledge base can be customized with domain-specific facts and rules, enabling the system to switch between general probabilistic processing and domain-specific rule-based inference as needed, thus maintaining both versatility and precision

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent applies local quality by allowing different parts of the system to use different methods depending on the domain. In general domains, probabilistic methods are used for broad applicability, while in specific domains, rule-based inference with domain-specific knowledge is applied to achieve high precision

Inventive Principle:

Principle #3Local quality

3Measurement precision

If rule-based inference with domain-specific knowledge is added, then precision and recall improve, but the system complexity increases

Engineering Contradiction:

Improveprecision and recallVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the system into distinct modular components: a probabilistic processing module, a knowledge base module, and a rule-based inference module. This segmentation allows each component to be developed and maintained independently, reducing overall system complexity while enabling the integration of domain-specific knowledge to improve precision and recall

Inventive Principle:

Principle #1Segmentation

4Manufacturing precision

If domain-specific knowledge bases and inference engines are integrated, then item selection accuracy improves, but the computational resources and processing time increase

Engineering Contradiction:

Improveitem selection accuracyVSAvoidprocessing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary action by pre-processing and storing domain-specific knowledge in a structured knowledge base before actual item set expansion. This allows the inference engine to quickly retrieve and apply relevant rules during processing, reducing computational overhead and processing time while maintaining high item selection accuracy

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11734365B1Knowledge-enriched item set expansion system and method

Publication Date: 2023.08.22 UNLIMIDATA LTD

AI summary

A computer-implemented method and a corresponding system for expanding an initially given input list of items from an application domain by similar or related items. The method operates on a computer-retrievable document repository containing a plurality of electronic documents. The method computes an expanded list of items from the initially given seed list by combining (i) methods for extracting candidate items that co-occur with already established items in selected lists contained in documents retrieved from said document store with (ii) knowledge-based inference tasks involving domain-specific logical facts and, in some embodiments also at least one domain-specific logical rule related to said application domain. By this combination, an improved item set expansion is obtained, which takes the particularities of the application domain into account, and which leads to a list expansion that may better fit a user's expectation.