Cognitive Convergence Engine for Multi-Channel Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enterprise organizations face challenges in efficiently prioritizing and distributing service requests across multiple geographical locations due to complex decision-making processes and inadequate information availability, leading to prolonged queuing and increased administrative work.
Innovation Solution
A multi-layer, cloud-based artificial intelligence integrated architecture that aggregates service requests, evaluates their eligibility for bot processing, and identifies the best fit resource using a polylithic cognitive optimizer and IoT data to optimize computational instances for seamless resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual resource allocation and evaluation processes are used across multiple geographical locations, then decision-making can be customized and adaptable to local conditions, but the processing time increases and productivity decreases due to prolonged queuing and increased administrative work
Solution Approach 1:
The system segments the resource allocation process into multiple independent evaluation layers (bot eligibility evaluation, computational instance evaluation, resource scoring) that can process requests in parallel. Each layer handles specific aspects of evaluation independently, allowing simultaneous processing of multiple requests across different geographical locations while maintaining customized decision-making criteria for each region.
Solution Approach 2:
The patent introduces an intermediary AI-based evaluation system that acts as a mediator between manual resource allocation processes and final request assignment. This intermediary automatically evaluates requests through multiple computational instances, scores available resources, and recommends optimal assignments, thereby reducing administrative work while preserving the ability to customize decision-making parameters for different geographical locations.
2Adaptability or versatility
If multiple channels are used to receive service requests, then customer service coverage and adaptability improve, but information availability becomes inadequate and queuing time increases due to the complexity of managing multiple channels
Solution Approach 1:
The system merges multiple service request channels into a unified processing architecture where all requests (regardless of origin channel) are evaluated by the same AI-based evaluation system. This consolidation maintains the ability to accept requests through diverse channels while eliminating the inefficiencies of separate processing queues, thereby reducing overall queuing time while preserving service coverage.
Solution Approach 2:
The patent implements a universal evaluation system that handles requests from multiple channels through a single multi-functional platform. The system can process loan applications, account openings, and other service requests through various channels (online, mobile, in-branch) using the same AI evaluation infrastructure, eliminating the need for channel-specific processing and reducing information gaps.
3Productivity
If computational instances are increased to handle higher request volume, then processing capacity and productivity improve, but system complexity and resource management difficulty increase
Solution Approach 1:
The system implements dynamic computational instance management where the number and configuration of computational instances automatically adjust based on real-time request volume and complexity. The AI evaluation system dynamically allocates computational resources, creating or decommissioning instances as needed, which maintains high processing capacity while reducing the burden of manual resource management and system complexity.
Data Source
AI summary
Arrangements for using a cognitive convergence engine for resource optimization are provided. Requests for service, such as a loan, an account, or the like, may be received via different communication channels. The requests for service may be aggregated based on type of request and transferred to a cloud environment for evaluation. A request may be evaluated to determine whether it is eligible for bot processing. If so, the request may be transferred to a bot server for processing. If not, the request may be evaluated to identify a best fit resource for processing. Identifying the best fit resource may include scores computed by a plurality of computational instances or virtual machines configured to process the computations. A number of computational instances may be determined based on a volume of requests. The computational instances may then be deployed to determine a best fit resource for the first request.