Expert Directory via Message Graph Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large organizations face productivity losses due to informational silos, where expertise is concentrated within specific teams, making it difficult for other teams to find relevant experts, and traditional systems fail to maintain comprehensive and up-to-date directories of subject-matter experts.
Innovation Solution
A computer-implemented method that collects electronic messages within an organization, creates a message graph, extracts topics, annotates the graph, and identifies experts by analyzing the annotated graph to determine vertices representing subject-matter experts, thereby creating a comprehensive and constantly updated directory without manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional manual directories of subject-matter experts are created, then expertise information can be organized, but the directories quickly become out of date and require considerable effort to maintain
Solution Approach 1:
The system automatically updates the expert directory by analyzing electronic message data without requiring manual intervention. The processor continuously collects message data, updates the graph structure, and identifies experts based on topic correlations, allowing the directory to self-maintain and stay current with organizational expertise dynamics
Solution Approach 2:
The system performs preliminary analysis of electronic message data to pre-identify expertise relationships before they are needed. By continuously analyzing message patterns and topic correlations in advance, the system prepares the expert directory proactively, ensuring expertise information is ready when queried without requiring reactive updates
2Loss of information
If traditional manual directories are assembled, then some expertise can be captured, but the directories are often not comprehensive because directors must determine which subjects to cover and some experts may evade inclusion
Solution Approach 1:
The system replaces the manual mechanical process of directory assembly with automated computational analysis. The processor analyzes electronic message data patterns to objectively identify experts based on actual communication behavior and topic correlations, eliminating the need for human judgment about which subjects to cover and preventing experts from evading inclusion through selective non-participation
Solution Approach 2:
The system uses electronic message data as an intermediary to indirectly identify expertise relationships. Rather than directly asking individuals to self-identify or manually assessing expertise, the system analyzes communication patterns in electronic messages as a mediator to objectively determine who possesses expertise in which topics based on actual organizational interactions
3Reliability
If expertise is concentrated in specific teams, then deep knowledge can be maintained, but informational silos form and other teams cannot find relevant experts
Solution Approach 1:
The system creates a universal expert directory that serves the entire organization regardless of team boundaries. By analyzing electronic message data across all teams and identifying expertise based on topic correlations rather than organizational structure, the system makes concentrated expertise accessible organization-wide, allowing any team to find experts in any topic while preserving the depth of knowledge within specialized teams
Data Source
AI summary
The disclosed computer-implemented method for identifying subject-matter experts may include (i) collecting, by the computing device, a plurality of electronic messages transmitted within an organization, (ii) creating a message graph for the organization, (iii) extracting a plurality of topics from the plurality of electronic messages transmitted within the organization, (iv) annotating the message graph by correlating each topic within the plurality of topics with each edge of the message graph that represents an electronic message related to the topic, and (v) identifying, based on an analysis of the annotated message graph, at least one vertex that represents an expert on at least one topic from the plurality of topics. Various other methods, systems, and computer-readable media are also disclosed.