Multi-Modal Input Processing for Small Terminals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current information processing apparatuses, such as smartphones, often rely solely on gesture-based operations, which do not cover all functional or application-related operations, necessitating the integration of additional operation methods like voice and button operations to enhance usability.
Innovation Solution
An information processing system that combines gesture, voice, and button operations, allowing users to perform various functions by utilizing a small-size terminal with sensors and a cell-phone connected via short-distance wireless communication, where the system activates sensors appropriately based on application notifications to reduce power consumption and enable multiple operation methods in parallel.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If gesture-based operations are used, then the device can be operated without physical contact, but the coverage of functional operations is insufficient
Solution Approach 1:
The patent integrates multiple operation methods (gesture recognition, voice recognition, and button operation recognition) into a single information processing apparatus, enabling the device to handle diverse operational tasks through a unified multi-functional framework that adapts to different user needs and task requirements
2Measurement precision
If sensors are continuously activated for gesture detection, then gesture recognition accuracy is maintained, but power consumption increases
Solution Approach 1:
The sensor activation is triggered periodically or event-driven by application notifications rather than continuous operation. The gesture recognition sensor is activated only when an application requires gesture control, maintaining detection accuracy while significantly reducing overall power consumption through intermittent rather than continuous operation
Solution Approach 2:
The system automatically manages sensor activation based on application needs without requiring manual user intervention. The information processing apparatus self-regulates sensor operation by receiving notifications from applications and autonomously activating or deactivating gesture recognition functionality according to contextual requirements
3Adaptability or versatility
If multiple operation methods are integrated, then operational versatility is improved, but system complexity increases
Solution Approach 1:
The patent combines gesture recognition, voice recognition, and button operation recognition systems into an integrated information processing apparatus with a unified architecture. Multiple recognition modules are merged into a single device that processes different input types through a common control framework, achieving operational versatility while managing system complexity through consolidation rather than separate independent systems
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There is provided an information processing apparatus including: a process execution unit configured to execute processes relating to voice operations recognized by a voice operation recognition unit configured to recognize the voice operations on a basis of information from a voice receiving unit and gesture operations recognized by a gesture recognition unit configured to recognize user's gestures recognized on a basis of information from a sensor. The voice operation recognition unit enters a voice operation waiting state in parallel with a gesture waiting state of the gesture recognition unit.