Dynamic Expertise Ranking via Document Involvement Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for identifying and ranking experts and their areas of expertise in organizations are limited, as they rely on static skill definitions and similarity-based searches, failing to accurately reflect expertise based on document involvement and relevance.
Innovation Solution
A method that identifies identities and topics from documents, assigning scores based on features like location and typographical properties, and uses these scores to rank experts and their expertise dynamically, merging aliases and updating expertise in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If similarity-based search is used to find experts, then the search process is simple and fast, but the accuracy of identifying true expertise is poor
Solution Approach 1:
The system transitions from static skill definitions to dynamic expertise scoring that continuously updates based on document involvement. Expertise scores are recalculated as new documents are added or modified, allowing the system to adapt to changing organizational knowledge without manual intervention.
Solution Approach 2:
The system automatically extracts expertise information from documents without requiring manual input from administrators. By analyzing document metadata, authorship, and content, the system self-updates expertise profiles and rankings based on actual organizational activities and contributions.
2Reliability
If static skill definitions are used, then the system is easy to maintain, but it fails to reflect current expertise based on document involvement
Solution Approach 1:
The expertise ranking system operates continuously in the background, automatically updating expertise scores as documents are added or modified. This continuous operation ensures expertise information remains current without requiring periodic manual updates or system interventions.
Solution Approach 2:
The system pre-calculates and stores expertise scores and document associations, enabling rapid retrieval and ranking when queries are submitted. By preparing expertise data in advance through automated analysis, the system responds quickly to user requests without real-time computation delays.
3Adaptability or versatility
If manual directory maintenance is used, then expertise information is structured and organized, but it is not up-to-date with current organizational activities
Solution Approach 1:
The system automatically extracts and updates expertise information from organizational documents without requiring manual directory maintenance. By analyzing document metadata, authorship patterns, and content relationships, the system self-maintains current expertise profiles that reflect actual organizational activities.
Solution Approach 2:
The system serves multiple functions simultaneously: it indexes documents for retrieval, identifies expertise areas, ranks experts by relevance, and updates profiles automatically. This multi-functionality eliminates the need for separate manual directory maintenance while providing comprehensive expertise information.
Data Source
AI summary
Methods, systems and apparatus, including computer program products, for ranking expertise. In some implementations a method is provided that includes identifying a plurality of identities, and identifying a plurality of topics using one or more documents in a repository. For a document in a corpus of documents identifying one or more occurrences of any identity in the plurality of identities and one or more occurrences of any topic in the plurality of topics, determining an association between the identities occurring in the document and the document including deriving an identity score for each unique identity occurring in the document, determining an association between the topics occurring in the document and the document including deriving a topic score for each unique topic occurring in the document, and using the determined associations to derive a score of the document with respect to identities and topics occurring in the document.