Voice Input Intent Recognition via Intermediary Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies face challenges in accurately grasping user intentions from voice inputs and providing appropriate feedback, leading to a demand for a system that can effectively recommend substitute operations or destinations based on analyzed voice inputs.

Innovation Solution

A device equipped with a processor and microphone that uses machine learning algorithms, specifically deep learning, to analyze voice inputs, determine user intentions, and generate response messages recommending substitute operations or destinations by obtaining association information related to the user's context and intentions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If speech recognition technology is used to enable voice input operations, then user convenience is improved, but the system cannot accurately grasp user intentions

Engineering Contradiction:
Improvevoice input convenienceVSAvoidintention recognition accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary processing layer between voice input and system response. This layer includes intention analysis modules that interpret the meaning behind voice commands, context understanding components that consider user history and situation, and decision-making algorithms that determine appropriate substitute operations when original intentions cannot be fulfilled. This intermediary processing transforms simple speech recognition into comprehensive intention understanding.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If the system attempts to provide comprehensive feedback for voice inputs, then user experience improves, but the complexity of the system increases

Engineering Contradiction:
Improvefeedback appropriatenessVSAvoidsystem structure complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent dynamically adjusts system parameters based on input confidence levels and context availability. When voice inputs are clear and unambiguous, the system provides direct responses with minimal processing. When intentions are unclear or context is insufficient, the system automatically increases processing depth by activating additional analysis modules and requesting clarifying information. This parameter-based adaptation allows comprehensive feedback when needed while maintaining simplicity for routine operations.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If machine learning algorithms are used to understand user intentions, then recognition accuracy improves, but processing time increases

Engineering Contradiction:
Improveintention recognition accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements preliminary action through pre-trained machine learning models and pre-computed context databases. User profiles, historical behavior patterns, and common intention scenarios are pre-analyzed and stored during off-peak times. When a voice input is received, the system quickly retrieves relevant pre-computed information rather than performing full analysis in real-time. This allows complex machine learning-based intention recognition to occur with minimal user-perceivable delay.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11501766B2Device and method for providing response message to voice input of user
Publication Date: 2022.11.15 SAMSUNG ELECTRONICS CO LTD
  • US11501766B2 patent drawing
  • US11501766B2 patent drawing
  • US11501766B2 patent drawing

AI summary

Provided are a device and a method for providing a response message to a voice input of a user. The method, performed by a device, of providing a response message to a voice input of a user includes: receiving the voice input of the user; determining a destination of the user and an intention of the user, by analyzing the received voice input; obtaining association information related to the destination; generating the response message that recommends a substitute destination related to the intention of the user, based on the obtained association information; and displaying the generated response message.