Speech Command Processing for Multi-Device Function Execution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems require multiple user speeches to execute multiple functions on devices, leading to user inconvenience and potential unawareness of available functions to address a request.

Innovation Solution

An information processing apparatus that acquires a single user speech to specify multiple devices and functions, enabling them to execute the requested functions simultaneously.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If multiple speeches are required to execute multiple functions on devices, then each function can be executed accurately, but user convenience deteriorates and operation complexity increases

Engineering Contradiction:
Improveuser convenienceVSAvoidoperation complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent merges multiple separate speech recognition processes into a single integrated processing flow. The speech recognition apparatus processes one speech input to simultaneously identify multiple devices and multiple functions, then executes all identified functions in coordination. This combining of multiple operations into a single speech-based command directly improves ease of operation while managing system complexity through unified processing logic.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The speech recognition apparatus is designed with multi-functionality to handle diverse operations through a single interface. It can identify different types of devices (audio output devices, display devices, etc.) and various functions (playback, display, control) from one speech input, making the system universally applicable to multiple scenarios without requiring separate specialized processes for each function type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Productivity

If multiple speeches are used to control devices, then precise control is achieved, but time consumption increases and productivity decreases

Engineering Contradiction:
Improveoperation efficiencyVSAvoidtime consumption
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent combines multiple sequential speech-based control operations into a single parallel processing operation. By identifying multiple devices and functions from one speech input and executing them simultaneously, the system eliminates the time loss associated with multiple sequential speeches, thereby improving operation efficiency and reducing time consumption.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The speech recognition apparatus performs preliminary identification of all required devices and functions in advance during the single speech processing stage. This preliminary action allows the system to prepare and execute multiple functions without requiring additional time for subsequent identification steps, thus improving productivity while minimizing time loss.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If one speech executes only one function, then control precision is maintained, but versatility and adaptability of the system deteriorate

Engineering Contradiction:
Improvesystem versatilityVSAvoidfunction awareness
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The speech recognition apparatus is designed to handle multiple function types (audio playback, display output, device control) and multiple device types through a single unified processing framework. This multi-functional design enhances system versatility by allowing one speech to trigger diverse operations across different devices, while the comprehensive identification process ensures no function awareness is lost.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system provides feedback to the user by displaying identified devices and functions before execution. This feedback mechanism ensures that users are aware of all functions that will be executed from their single speech input, preventing loss of function awareness while maintaining the versatility to execute multiple diverse operations simultaneously.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS12586588B2Information processing apparatus, information processing method, and non-transitory storage medium
Publication Date: 2026.03.24 TOYOTA JIDOSHA KK
  • US12586588B2 patent drawing
  • US12586588B2 patent drawing
  • US12586588B2 patent drawing

AI summary

A control unit of an information processing apparatus is configured to acquire a speech including a request of a user. The control unit of the information processing apparatus is configured to specify one or multiple devices and at least two functions to be executed by the one or multiple devices, for realizing the request of the user based on the acquired speech of the user. The control unit of the information processing apparatus is configured to cause the one or multiple devices to execute the at least two functions.