Voice Input Parameter Formatting for Multi-App Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current speech recognition services incorrectly determine user intent and enter incorrect parameters into application input fields, often due to mismatched formats, leading to errors in processing user inputs across multiple applications.

Innovation Solution

An electronic apparatus with a processor, touchscreen display, microphone, and wireless communication circuit that receives user inputs, transmits data to an external server, and processes responses to match parameters with the attributes of input fields, ensuring accurate parameter entry and preventing errors by converting text formats as needed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If speech recognition service displays only the result according to user input, then the service is simple to operate, but it cannot process user inputs to request execution of multiple applications

Engineering Contradiction:
Improvespeech recognition service operationVSAvoidprocessing capability for multiple applications
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The user input is segmented into multiple distinct utterances (first utterance and second utterance), where each utterance corresponds to a different application or function. The system processes each segmented utterance separately to execute multiple applications sequentially, enabling complex multi-application control while maintaining simple voice-based operation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from processing a single-dimensional user input to handling multi-dimensional inputs by introducing temporal sequencing. Multiple utterances are processed in a specific order (first utterance triggering first application, second utterance triggering second application), adding a time-based dimension to the speech recognition process that enables multi-application control.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Speed

If speech recognition service directly enters parameters from user voice, then the processing speed is fast, but it incorrectly determines user intent and enters wrong parameters with mismatched formats

Engineering Contradiction:
Improveparameter entry speedVSAvoidparameter determination accuracy
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

An intermediary processing step is introduced between voice input and parameter entry. The system receives the first text from speech recognition, validates it against the expected format of the target input field, and performs format conversion if necessary. This intermediary validation and conversion process ensures parameter accuracy while maintaining relatively fast processing speed.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary format validation and conversion before entering the parameter into the input field. By checking whether the first text matches the required format in advance and converting it if needed, the system prevents incorrect parameter entry while maintaining efficient processing through automated preliminary checks.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If speech recognition service enters parameters without format validation, then the processing is simple and fast, but parameters with different formats are incorrectly entered into input fields

Engineering Contradiction:
Improveparameter entry efficiencyVSAvoidparameter format accuracy
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The system performs self-service format validation and conversion by automatically comparing the first text against the required input field format and converting it if necessary. This self-service approach maintains high productivity through automated processing while ensuring manufacturing precision by correcting format mismatches without requiring manual intervention.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system implements feedback by comparing the first text against the expected format of the input field and using this comparison result to determine whether conversion is needed. This feedback mechanism ensures that parameters are entered with correct formatting while maintaining efficient automated processing through conditional conversion based on format mismatch detection.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3610479B1Electronic apparatus for processing user utterance
Publication Date: 2024.02.28 SAMSUNG ELECTRONICS CO LTD
  • EP3610479B1 patent drawingFigure 1
  • EP3610479B1 patent drawingFigure 2
  • EP3610479B1 patent drawingFigure 3

AI summary

An electronic apparatus is provided. The electronic apparatus includes a housing, a touchscreen display positioned inside the housing and exposed through a first area of the housing, a microphone positioned inside the housing and exposed through a second area of the housing, at least one speaker positioned inside the housing and exposed through a third area of the housing, a wireless communication circuit positioned inside the housing, a processor positioned inside the housing and electrically connected to the touchscreen display, the microphone, the at least one speaker, and the wireless communication circuit, and a memory positioned in the housing and electrically connected with the processor.