Contextual Topic Description Selection for Enterprise Knowledge

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Modern enterprises face inefficiencies in disseminating curated enterprise knowledge due to manual curation and sharing methods, leading to inappropriate and inefficient dissemination of information, with descriptive materials often becoming trapped or irrelevant to recipients.

Innovation Solution

A system utilizing machine learning models to extract and rank topic descriptions from enterprise computing resources, selecting contextually appropriate descriptions for individual recipients based on their roles, access permissions, and document contexts, thereby ensuring relevant and secure knowledge dissemination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual curation and sharing methods are used to disseminate enterprise knowledge, then knowledge can be shared among employees, but the dissemination becomes inefficient and inappropriately scoped

Engineering Contradiction:

Improveknowledge dissemination efficiencyVSAvoidappropriateness of knowledge scope

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system enables self-service by automatically extracting topic descriptions from enterprise documents and serving them to relevant employees based on their roles and access permissions, eliminating the need for manual curation and distribution while ensuring appropriate scoping

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual process of curating and distributing knowledge with an automated computer-based system that uses machine learning models to extract, rank, and distribute topic descriptions, significantly improving efficiency while maintaining appropriateness

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If descriptive materials are widely disseminated to all employees, then more people can access the information, but the materials become trapped in individual accounts or are inappropriately scoped for recipients

Engineering Contradiction:

Improveaccessibility of knowledgeVSAvoidtime wasted on inappropriate information

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system applies local quality by tailoring the scope and detail of topic descriptions to each recipient's specific role, department, and access permissions, ensuring that each employee receives information appropriately scoped for their needs rather than a uniform distribution to all

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system performs preliminary action by pre-processing enterprise documents to extract and rank topic descriptions before they are needed, storing them in a structured format that enables rapid, context-appropriate retrieval and delivery to employees without manual intervention

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If multiple descriptions of a topic are provided for different purposes, then comprehensive coverage is achieved, but recipients receive descriptions that are inappropriately scoped for their need-to-know basis

Engineering Contradiction:

Improvecomprehensiveness of topic coverageVSAvoidrelevance to recipient context

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system implements dynamics by making the selection of topic descriptions adaptive and dynamic based on recipient context, using machine learning models to automatically determine which pre-extracted descriptions are most appropriate for each employee's role, department, and access level rather than using static distribution rules

Inventive Principle:

Principle #15Dynamics

4Productivity

If automated machine learning models are used to extract and rank topic descriptions, then manual curation efforts are reduced, but the system complexity increases

Engineering Contradiction:

Improvecuration efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies universality by designing a multi-functional system where the machine learning models perform multiple tasks including extracting topic descriptions, ranking them by relevance, filtering based on access permissions, and delivering to appropriate recipients, consolidating what would otherwise require multiple separate systems into one unified solution

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12164529B2Extracting and surfacing contextually relevant topic descriptions

Publication Date: 2024.12.10 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Techniques for extracting and ranking multiple topic descriptions based on source contexts and subsequently selecting individual topic descriptions to surface based on recipient contexts. More specifically, a mining platform may extract, from a set of source documents making up a corpus, topic descriptions for various topics that are relevant to an enterprise. The mining platform may further rank the extracted topic descriptions based on a source context of those documents from which individual topic descriptions are extracted. Subsequently, when users access enterprise documents including term-usage instances of topics for which one or more topic descriptions have been extracted and ranked, a description serving module may select a topic description that is contextually appropriate for a recipient view the enterprise documents.