Expert Knowledge Platform for Automated Subject Matter Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying subject matter experts within an organization is challenging due to the large number of experts across various subject areas, and existing technologies lack effective methods to analyze communications and extract relevant entities and topics.
Innovation Solution
A system utilizing machine learning and natural language processing to analyze electronic communications, extract named entities and topics, and classify experts based on relationship scores, generating visual representations and updating knowledge bases for efficient expert identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used to identify experts in an organization, then the process is simple to implement, but it becomes difficult and time-consuming when the organization includes many experts in different subject areas
Solution Approach 1:
The patent replaces manual expert identification processes with automated machine learning systems that analyze electronic communication data. The system uses natural language processing and entity recognition models to automatically extract topics and named entities from communications, classify experts based on relationship scores, and generate visual representations, eliminating the need for time-consuming manual searches through organizational directories.
Solution Approach 2:
The system enables self-service expert identification by allowing users to input topic keywords and automatically receiving expert recommendations. The machine learning models continuously learn from communication data to improve expert identification accuracy over time, making the system increasingly autonomous and reducing reliance on manual curation of expert directories.
2Measurement precision
If comprehensive communication data is analyzed to accurately identify experts, then expert identification accuracy improves, but system complexity and processing requirements increase
Solution Approach 1:
The patent segments the expert identification system into distinct functional modules: an entity recognition model for extracting topics and named entities from communications, an expert classifier for calculating relationship scores and identifying experts, and a visualization component for displaying results. This modular architecture improves accuracy while managing complexity by allowing each component to be optimized independently.
Solution Approach 2:
The system introduces intermediate processing layers including topic extraction from communications and relationship score calculation as mediators between raw communication data and final expert identification. These intermediate steps transform unstructured communication data into structured insights, improving accuracy while making the overall system more manageable through staged processing.
Data Source
AI summary
An expert system processes communication data to extract entities and topics. The expert system generates relationship graphs and relationship scores between the entities and topics. The system can identify entities that are expert in a given topic. The expert system uses a knowledge engine to provide different services and applications.