Natural Language Query Modeling With User Confirmation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice-based user interaction systems for devices such as PCs, PDAs, and smartphones are often inaccurate, imprecise, and unreliable, requiring time-consuming voice training, which limits their adoption and use in applications like e-commerce and e-learning.

Innovation Solution

A system and method that allows users to input natural language queries, which are modeled and presented to the user for confirmation before execution, enabling modification, and executed to extract data from databases, with user identity-based access and adaptive learning to improve accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice-based user interaction systems are implemented, then user interaction convenience is improved, but accuracy and reliability deteriorate

Engineering Contradiction:
Improveuser interaction convenienceVSAvoidaccuracy and reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary actions by presenting the modeled query to the user before execution. This allows the user to review and verify the interpreted query, ensuring accuracy before it is submitted to the database, thus resolving the contradiction between convenience and reliability.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by displaying the modeled query back to the user for confirmation. This feedback loop allows the user to detect and correct any misinterpretations, improving accuracy while maintaining the convenience of voice-based interaction.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If voice training is implemented to improve accuracy, then measurement precision is improved, but loss of time increases

Engineering Contradiction:
Improvevoice recognition accuracyVSAvoidtraining time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system uses self-service by automatically modeling the query from the user's voice input without requiring external training. The query modeling engine processes the speech input and generates a structured query automatically, eliminating the need for time-consuming voice training while maintaining accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary query modeling and presentation before execution, allowing accurate query interpretation without requiring prior voice training. This preliminary processing step ensures precision while avoiding the time loss associated with training procedures.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If query modeling and user confirmation are implemented, then reliability is improved, but loss of time increases

Engineering Contradiction:
Improvequery accuracyVSAvoidquery processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs the query modeling and user confirmation as a preliminary action before query execution. By presenting the modeled query to the user beforehand, the system ensures reliability and accuracy while minimizing time loss, as the user only needs to review and confirm rather than manually construct the entire query.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12487997B1System and method for modeling a search query
Publication Date: 2025.12.02 UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)
  • US12487997B1 patent drawing
  • US12487997B1 patent drawing
  • US12487997B1 patent drawing

AI summary

A computer method and system for providing information results in response to a natural language information request. The system and method include receiving a natural language information request from a user and compiling a computer executable query from the natural language information request from a user wherein the query is formatted to extract data from one or more computer databases. The query is then presented to the user prior to execution of the query so as to enable the user to change the query prior to its execution. The query is then executed to extract data from one or more computer databases whereby extracted data is presented to the user in a certain presentation format.