Expert Matching via Workload Intelligence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing live support systems face challenges in efficiently matching customers with experts due to inadequate consideration of expert workload capacity and limited attributes, often resulting in ineffective and inefficient matches.
Innovation Solution
A method utilizing workload intelligence, where a machine learning model predicts completion times based on historical data and expert attributes to determine match scores, ensuring efficient expert allocation for support engagements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing techniques select the next available expert or use limited attributes for matching, then the matching process is simple and fast, but the match quality is low and inefficiency occurs
Solution Approach 1:
The patent transforms the matching process from simple attribute comparison to a comprehensive evaluation by introducing multiple parameters including predicted completion times, workload capacities, and various expert and customer attributes. This allows the system to assess match quality more precisely by considering how each parameter affects the overall matching outcome.
Solution Approach 2:
The patent introduces an intermediary matching system that acts as a mediator between customers and experts. This intermediary evaluates multiple attributes and predicted completion times to determine optimal matches, rather than relying on direct simple pairing or manual intervention.
2Measurement precision
If manual matching is performed in real-time by professionals, then match quality improves, but dedicated personnel are required and scalability is limited
Solution Approach 1:
The patent implements a self-service automated matching system that performs the functions previously requiring manual professional intervention. The system automatically evaluates customer requests, assesses expert attributes and workload capacities, predicts completion times, and determines optimal matches without requiring dedicated personnel, thereby enabling scalability.
Solution Approach 2:
The patent replaces the mechanical system of manual matching by professionals with an automated computational system. The automated system uses algorithms to evaluate attributes, predict completion times, and determine matches, substituting human manual processes with machine-based automation that can scale indefinitely.
3Reliability
If existing techniques do not consider expert workload capacity in advance, then the matching process is simple, but experts cannot effectively handle customer requests due to overload
Solution Approach 1:
The patent performs preliminary assessment of expert workload capacities before making matches. The system calculates predicted completion times and evaluates current workload statuses in advance, ensuring that experts are not overloaded before assigning new customer requests. This preliminary action prevents ineffective matches before they occur.
4Measurement precision
If limited customer and expert attributes are considered in matching, then the matching process is fast and simple, but match quality is low
Solution Approach 1:
The patent comprehensively evaluates multiple customer and expert attributes including skills, experience, availability, and historical performance metrics. By considering a wide range of parameters rather than limited attributes, the system achieves higher match quality through more comprehensive evaluation of compatibility between customers and experts.
Data Source
AI summary
Aspects of the present disclosure provide techniques for expert matching though workload intelligence. Embodiments include receiving a request for a support engagement. Embodiments include receiving workload data of a plurality of experts. Embodiments include determining a workload capacity of each respective expert based on the respective workload data for the respective expert. Embodiments include determining a respective estimated completion time for the support engagement for each of the plurality of experts using a machine learning model. Embodiments include determining match scores for the support engagement and each of the plurality of experts based on the estimated completion times and the workload capacities. Embodiments include selecting a given expert of the plurality of experts to handle the support engagement based on the match scores.