Voice Control via Sensor Fusion for Ambiguous Location

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing display control systems struggle to provide natural voice-based instructions for controlling location-specific interactions without specifying a location, and they fail to consider scenarios where voice commands lack explicit location information.

Innovation Solution

An information processing device that acquires voice utterances, determines locations using environment sensing data from multiple sensors, and issues control commands based on this determination, even when specific location names are absent, by utilizing sensors like cameras and microphones to interpret demonstrative pronouns and user gestures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice-based control is used without explicit location names, then ease of operation is improved, but reliability deteriorates due to ambiguity in location determination

Engineering Contradiction:
Improveease of voice instructionVSAvoidlocation determination accuracy
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent introduces environmental sensing data from multiple sensors as an intermediary to bridge the gap between ambiguous voice commands and precise location determination. The sensors (cameras, microphones, other detection devices) capture environmental information that serves as a mediator to resolve the uncertainty in location interpretation, enabling both natural voice input and accurate location identification

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system employs multiple types of sensors with different functions to determine location. The control unit integrates data from cameras, microphones, and other detection devices, allowing the system to use various sensing modalities universally to resolve location ambiguity, thereby maintaining reliability while enabling natural voice-based control

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

2Measurement precision

If multiple sensors are used for environment sensing, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvelocation determination precisionVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies multi-functionality by using multiple sensor types (cameras, microphones, other detection devices) that can serve various sensing purposes. This universal approach allows the system to achieve high measurement precision for location determination while managing device complexity through integrated multi-functional sensing capabilities

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

Solution Approach 2:

The control unit automatically processes and integrates data from multiple sensors without requiring manual intervention or complex external processing systems. The system self-services by autonomously combining sensor inputs to determine location, thereby achieving high precision while minimizing the complexity burden of having multiple sensors

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS11373650B2Information processing device and information processing method
Publication Date: 2022.06.28 SONY GROUP CORP
  • US11373650B2 patent drawing
  • US11373650B2 patent drawing
  • US11373650B2 patent drawing

AI summary

[Problem] Provided are an information processing device, an information processing method, and a program which are capable of giving an instruction for control relating to a location in a space even in voice utterance that does not include the name of a specific location. [Solution] The information processing device includes a control unit that acquires voice utterance corresponding to a processing command of control relating to a location in a space, determines the location in the space in the processing command on the basis of a result of environment sensing processing of the space by a plurality of kinds of sensors in a case where the acquired voice utterance does not include a word that specifies the location in the space, and performs control of issuing a processing command of control relating to the location in the space on the basis of the determined location.