AI Orchestration Platform for Automated Request Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Responding to customer requests, such as insurance-related inquiries, is a time-consuming and error-prone process, especially when numerous requests are received through various channels, requiring different types of processing and handling.

Innovation Solution

An artificial intelligence orchestration platform automatically determines the intent of electronic records, extracts requisite entity identifiers, and processes requests using a robotic automation platform, enabling efficient and accurate responses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual processing methods are used to handle customer requests, then flexibility in handling different request types is maintained, but processing time and error rates increase significantly

Engineering Contradiction:

Improverequest processing speedVSAvoidresponse accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system enables automated self-processing of customer requests through AI-driven intent recognition and entity extraction. The robotic automation platform independently handles request routing, information validation, and response generation without requiring manual human intervention for each request, thereby increasing both speed and accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processing (human analysts reviewing and responding to requests) with an automated digital system. The AI orchestration platform uses natural language processing and machine learning algorithms to automatically determine request intent, extract relevant entities, and route requests appropriately, eliminating human error and acceleration processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated processing systems are implemented to increase processing speed, then productivity improves, but system complexity increases

Engineering Contradiction:

Improverequest processing throughputVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system is divided into distinct functional modules: an AI orchestration platform for intent recognition, an entity extraction platform for information retrieval, and a robotic automation platform for request processing. Each module performs a specific function, making the overall complex system manageable through clear separation of concerns and specialized processing at each stage

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The AI orchestration platform serves as an intermediary layer between incoming requests and the entity extraction/platform processing systems. It automatically determines request intent and prepares structured information before passing to downstream systems, simplifying their processing requirements and reducing overall system complexity through standardized interfaces

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If multiple request channels are supported to improve customer service coverage, then adaptability increases, but difficulty in managing and processing requests from different channels increases

Engineering Contradiction:

Improvechannel support capabilityVSAvoidrequest management simplicity

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The robotic automation platform is designed with universal processing capabilities that can handle requests from multiple channels (email, web forms, telephony, etc.) through a single unified system. The AI orchestration layer abstracts channel-specific details, allowing the core processing logic to remain consistent across different input sources, thereby maintaining ease of operation while supporting high adaptability

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20190266254A1System to process electronic records using a request orchestration platform

Publication Date: 2019.08.29 HARTFORD FIRE INSURANCE CO

AI summary

According to some embodiments, an artificial intelligence orchestration platform may automatically determine an intent of an electronic record (e.g., an email message, text, translated voice channel request, etc.) associated with a request (e.g., by communicating with a classification platform service or analyzing the electronic record). Based on an indication of intent, an entity extraction platform may extract at least one requisite entity identifier from the electronic record in accordance with a transaction requirement. A robotic automation platform may then process the request utilizing the indication of intent and the extracted requisite entity identifier. For example, the robotic automation platform may transmit a complete response to the request, pre-populate data in a template provided to a human knowledge worker, determine additional information associated with the request, etc.