Context-Specific Generative Answers via Structured User Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current generative models struggle to provide satisfactory answers to context-specific queries, failing to utilize both general and user-specific information effectively.

Innovation Solution

A method and system that create a computer-readable data structure with context-specific features and user values, applying a generative model to generate tailored answers by combining general and user-specific data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a generative model is used to answer user queries, then general questions can be answered, but specific context-specific questions cannot be answered satisfactorily

Engineering Contradiction:

Improveability to answer general questionsVSAvoidability to answer context-specific questions

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system segments the query processing into distinct components: identifying context-specific queries versus general queries, extracting relevant features, retrieving user-specific data, and generating tailored responses. This segmentation allows the system to handle different query types with appropriate methods, resolving the contradiction between general adaptability and specific reliability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-identifying context-specific features and pre-retrieving user-specific data before generating the final answer. This preliminary preparation ensures that when a context-specific query is received, all necessary personalized information is already available, improving the reliability of specific answers while maintaining general capabilities.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If user-specific data is incorporated into the query processing, then context-specific answers can be generated, but system complexity increases

Engineering Contradiction:

Improveaccuracy of context-specific answersVSAvoidsystem architecture complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system introduces an intermediary layer that manages the complexity of user-specific data retrieval and integration. This intermediary component handles the coordination between the generative model and user data repositories, shielding the core generative process from complexity while enabling accurate context-specific answers through structured data mediation.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250217424A1Method and system for context-specific generative model answers from context-specific queries

Publication Date: 2025.07.03 INTUIT INC

AI summary

A method including receiving a context-specific query, specific to the user, from a user device of a user. The method also includes creating a computer-readable data structure for storing data. The computer-readable data structure is specific to the context-specific query. The method also includes determining a feature related to the context-specific query. The method also includes retrieving a user value for the feature. The user value is retrieved from a data repository storing user-specific data that includes the user value. The method also includes modifying the computer-readable data structure to generate a modified computer-readable data structure by adding the feature and the user value for the feature to the computer-readable data structure. The method also includes applying a generative model to the modified computer-readable data structure to generate an output. The output includes a context-specific answer to the context-specific query. The method also includes returning the output.