AI Interaction Orchestration for Missing Data Retrieval

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current AI applications face challenges in handling incomplete and ambiguous data, leading to inaccurate responses, frustration, and resource wastage, and are inflexible in dynamic interactions, requiring complex and costly BPM processes and lacking the ability to retrieve missing information from users or API calls.

Innovation Solution

A system that dynamically loads required functions based on user intent, using AI agents to process messages, query APIs and secondary sources, and request clarification through natural language processing to ensure accurate responses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If BPM processes are used to manage dialogue between AI application and user, then reliability of data handling is improved, but device complexity and cost increase significantly

Engineering Contradiction:

Improvedata handling reliabilityVSAvoidprocess management complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an interactive orchestration server as an intermediary component that mediates between the AI agent and external systems. This server contains an execution engine that dynamically generates and executes computational graphs, serving as a flexible mediator that reduces the need for rigid BPM processes while maintaining reliable data handling through structured execution of AI-generated plans.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically generates computational graphs based on user inputs and AI reasoning, rather than relying on pre-defined static BPM processes. The execution engine adapts the execution plan in real-time based on available data and user interactions, allowing the system to maintain reliability while reducing complexity through dynamic adaptation.

Inventive Principle:

Principle #15Dynamics

2Measurement precision

If comprehensive BPM processes are implemented, then accuracy of responses is improved, but loss of time in processing increases

Engineering Contradiction:

Improveresponse accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-defining API specifications and data validation rules in the API repository. The execution engine prepares computational graphs in advance based on AI-generated plans, allowing data validation and processing steps to be ready before actual user queries are processed, thus maintaining accuracy while reducing processing time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The execution engine maintains continuous processing by dynamically executing computational graphs that flow data through multiple processing stages without interruption. The system continuously validates data, calls APIs, and generates responses in an uninterrupted pipeline, improving response accuracy while minimizing processing time through continuous operation.

Inventive Principle:

Principle #20Continuity of useful action

3Reliability

If AI application requests clarification for incomplete data, then reliability of responses is improved, but loss of time in interaction increases

Engineering Contradiction:

Improveresponse reliabilityVSAvoidinteraction time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system implements feedback mechanisms where the execution engine continuously monitors data completeness and quality during the computational graph execution. When incomplete data is detected, the system provides targeted feedback to the user through the AI agent, requesting only the specific missing information needed to complete the task, thus maintaining reliability while minimizing interaction time through precise feedback.

Inventive Principle:

Principle #23Feedback

4Adaptability or versatility

If dynamic function loading is implemented, then adaptability to user intent is improved, but device complexity increases

Engineering Contradiction:

Improveadaptability to user intentVSAvoidsystem configuration complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments functions into modular API specifications stored in the API repository, organized by function, description, parameters, and expected outputs. The execution engine dynamically loads and executes only the relevant API specifications needed for each user query, rather than loading all functions at once. This segmentation enables adaptability to user intent while managing complexity through modular organization.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20260057262A1Systems and methods for orchestrating interaction with an artificial intelligence application

Publication Date: 2026.02.26 THE BANK OF NEW YORK MELLON

AI summary

Systems and methods for orchestrating interaction with an AI application include receiving a message from a user via an AI agent and generating an initial computational inference process based on the message. The system queries an API repository to determine whether all required information to execute the process is available. If available, the system executes the inference process, generates a reply based on the process and the API repository, and sends the reply to the user via the AI agent. If information is missing, the system determines whether secondary sources provide the necessary information. If available, the system executes the inference process, generates the reply, and sends it via the AI agent. If required information is not available through the API repository or secondary sources, the system generates a query requesting the missing information from the user and sends the query via the AI agent.