Machine Learning Expertise Directory Across Organizational Data Silos
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In large organizations, finding the right person with expertise on a specific topic can be difficult and time-consuming, often resulting in wasted time and frustration due to the isolation of data silos and lack of efficient directory assistance.
Innovation Solution
A machine learning model is trained using digital data from various sources within the organization to identify and locate experts by associating keywords with members, utilizing a deep learning neural network and Natural Language Processing, and providing assistance through a chatbot.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual searching methods are used to find experts in large organizations, then the system complexity remains low, but the time required to locate experts increases significantly
Solution Approach 1:
The system automatically indexes digital data from multiple sources and trains machine learning models to identify experts without requiring manual intervention. The model continuously learns from organizational data to improve its ability to locate experts, eliminating the need for manual directory searches while maintaining manageable system complexity through automated processes
Solution Approach 2:
The patent replaces manual mechanical searching processes with machine learning algorithms that automatically analyze digital data. The system uses NLP and classification models to process information from emails, documents, and collaboration tools, substituting human search efforts with intelligent automated systems that scale efficiently
2Loss of information
If data is stored in isolated data silos across multiple departments, then data security and departmental autonomy are maintained, but the ability to find experts across departments becomes difficult
Solution Approach 1:
The machine learning model acts as an intermediary that bridges isolated data silos. It processes and analyzes data from multiple departmental sources without requiring direct integration between them, maintaining data security while enabling cross-departmental expert search through centralized intelligent processing
Solution Approach 2:
The system creates a universal search mechanism that operates across all data silos simultaneously. The machine learning model is trained to recognize patterns and keywords across different departmental data sources, providing unified access to expert information regardless of which data silo contains the relevant information
3Measurement precision
If multiple employees are interrupted to determine their expertise, then accurate expert identification is achieved, but productivity decreases due to interruptions
Solution Approach 1:
The system performs preliminary analysis of employee expertise by continuously indexing digital data and training machine learning models in advance. When an expert search is needed, the pre-trained model can immediately provide accurate results without requiring employees to be interrupted for assessment
Solution Approach 2:
The machine learning model autonomously evaluates and identifies experts by analyzing organizational data patterns, eliminating the need for manual employee assessments. The system self-updates its knowledge base continuously, maintaining high accuracy without requiring employee time or attention
Data Source
AI summary
Systems and methods for providing directory support in an organization are described. A method, according to one implementation, includes gathering digital data from multiple sources within an organization. The method also includes indexing the digital data in a table that includes at least a first column including names of a plurality of members of the organization and a second column including keywords attributed to the plurality of members. Also, the method includes training a Machine Learning (ML) model by data crawling through the digital data, assigning weights to the keywords, and storing the weights in a third column in the table. In response to receiving an inquiry from a user, the ML model is configured during inference to use information in the table to provide an output to the user identifying a member in the organization who demonstrates expertise on a specific topic.