Expert Identification System Using ML Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In distributed organizations, individuals face inefficiencies and costs due to difficulty in locating colleagues with specific undocumented knowledge, often resulting in suboptimal assistance from less knowledgeable individuals.
Innovation Solution
A computer system that identifies users with requested expertise by extracting keywords from user inputs, generating search requests, aggregating user interaction data, and using machine learning to rank potential experts among software application users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual searching for experts is performed in distributed organizations, then individuals can locate colleagues with specific knowledge, but it results in wasted time and inefficient resource utilization
Solution Approach 1:
The patent introduces an intermediary system that acts as a mediator between users seeking expertise and potential experts in the organization. This system automatically analyzes user queries, searches through aggregated data from multiple sources including software applications and communication platforms, and returns ranked lists of suitable experts, thereby eliminating the need for manual searching and significantly reducing time loss.
Solution Approach 2:
The patent replaces the mechanical manual searching process with an automated computational system. Instead of individuals manually browsing contacts or asking around, the system uses natural language processing, machine learning algorithms, and automated data aggregation to identify and rank potential experts, substituting human effort with intelligent automation.
2Reliability
If manual searching for experts is performed, then individuals can find assistance, but the quality of assistance may be compromised as less knowledgeable individuals may be selected
Solution Approach 1:
The intermediary system performs comprehensive analysis of user profiles, expertise indicators, and interaction histories to identify true experts. It aggregates data from multiple sources including software application usage patterns, communication platform interactions, and project participation records to create a reliable ranking that reflects actual expertise levels, ensuring high-quality assistance is provided.
Solution Approach 2:
The system performs preliminary actions by pre-aggregating and analyzing data about all organization members' expertise and capabilities before search queries are submitted. This includes continuously monitoring software application usage, communication patterns, and project contributions to maintain up-to-date expertise profiles, so that when a search is performed, the system can quickly return accurate results without compromising quality.
3Productivity
If automated systems are implemented to identify experts, then time and efficiency are improved, but the system complexity increases
Solution Approach 1:
The patent implements a universal system that performs multiple functions through a single integrated platform: data aggregation from various sources, natural language processing of queries, expertise profile analysis, ranking algorithm execution, and result presentation. This multi-functional approach consolidates what would otherwise require multiple separate systems into one cohesive solution, managing complexity while maintaining high productivity.
Solution Approach 2:
The system incorporates self-service mechanisms where the automated expert identification system manages its own operations including data collection, processing, and updating without requiring manual intervention. The system automatically adapts to new data sources, learns from user feedback, and maintains its own expertise databases, reducing the operational complexity burden on users while sustaining high efficiency.
Data Source
AI summary
Systems and methods for identifying individuals with a user-requested expertise are provided. For example, the system can include a processor configured to receive a user input and extract one or more keywords from the input. The processor can generate search requests based upon the one or more keywords, each search request identifying at least one application programming interface (API) call configured to invoke at least one API function as exposed by a software application. The processor can transmit the search requests to the software applications and receive search responses. The processor can determine a plurality of software application users and a set of associated evidence, each set of associated evidence including user interactions with each of the software applications. The processor can aggregate the evidence into an aggregated data set and configure the aggregated data set as an input to a machine learning classifier for ranking the sets of evidence.