Query Response Synthesis Using Progressive AI Query Decomposition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to accurately and efficiently generate responses to client-specific queries in questionnaires due to the nuances and complexities involved, leading to incomplete, vague, or inaccurate answers that compromise the integrity of client reviews and regulatory compliance.

Innovation Solution

A system utilizing a generative AI model for query interface response synthesis via machine learning and progressive query data decomposition, which decomposes queries into sub-queries of increasing complexity, generates successive responses, and collates them into accurate collated data, eliminating manual input and reducing resource usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If comprehensive questionnaires are manually completed to track client-specific circumstances, then accuracy and completeness of responses improve, but time consumption and resource usage increase substantially

Engineering Contradiction:

Improveaccuracy of questionnaire responsesVSAvoidtime to complete questionnaires

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system segments complex questionnaire queries into smaller sub-queries that can be processed independently. The query decomposition module breaks down each questionnaire question into multiple sub-queries, allowing parallel processing and faster retrieval of relevant information from client interaction data.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-processing and storing client interaction data in structured formats before questionnaire completion is needed. Historical interactions are already organized and indexed, enabling rapid retrieval during questionnaire generation without requiring manual research at the time of completion.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If manual research and data collection are performed for each questionnaire, then response accuracy improves, but productivity and processing speed decrease

Engineering Contradiction:

Improveresponse accuracyVSAvoidquestionnaire processing speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system replaces manual mechanical processes with automated AI-based processing. The generative AI model automatically synthesizes questionnaire responses by processing decomposed sub-queries and retrieving relevant data, eliminating the need for manual research while maintaining high accuracy through systematic data analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically generating complete questionnaire responses without human intervention. The AI model independently retrieves client interaction data, processes it through query decomposition, and synthesizes accurate responses, making the entire questionnaire completion process autonomous and highly efficient.

Inventive Principle:

Principle #25Self-service

3Loss of information

If detailed client interaction data is processed through multiple research steps, then completeness of responses improves, but network resource consumption and processing overhead increase

Engineering Contradiction:

Improvecompleteness of client informationVSAvoidnetwork resource consumption

Core Design Contradiction:

Loss of informationVSLoss of energy

Solution Approach 1:

The system segments client interaction data into organized categories and processes only relevant portions for each questionnaire. By decomposing queries into sub-queries, the system retrieves only the specific data needed for each question rather than processing entire datasets, reducing network resource consumption while maintaining information completeness.

Inventive Principle:

Principle #1Segmentation

4Device complexity

If traditional query processing methods are used without decomposition, then system complexity remains low, but response quality and tailoring to client needs deteriorate

Engineering Contradiction:

Improvesystem structure simplicityVSAvoidresponse quality

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system applies segmentation by breaking down complex client-specific queries into manageable sub-queries. This decomposition allows the AI model to systematically process different aspects of client interactions separately and synthesize comprehensive responses, significantly improving response quality while maintaining reasonable system complexity through modular architecture.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12517901B1System and method for query interface response synthesis via machine learning and progressive query data decomposition

Publication Date: 2026.01.06 BANK OF AMERICA CORP

AI summary

Systems, computer program products, and methods are described herein for query interface response synthesis via machine learning and progressive query data decomposition. The present disclosure includes receiving a document, parsing retrievable text in the document to identify a query in the retrievable text, decomposing the query, using a generative AI model comprising a large language model, into a sub-query sequence, wherein the sub-query sequence comprises a plurality of sub-queries, the plurality of sub-queries within the sub-query sequence successively increasing in complexity, retrieving, using a retriever, data records corresponding with a user identifier, transmitting the data records to the generative AI model, generating, within a first persistent dialogue session of the generative AI model, successive responses according to the sub-query sequence, and collating the successive responses into collated response data.