Communication Terminal Voice Recording and Call Termination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication terminal devices consume excessive electrical power due to continuous speech recognition during calls and require inconvenient manual activation of voice commands to terminate calls.
Innovation Solution
A communication terminal device equipped with a proximity detecting unit, voice input accepting unit, recording unit, speech recognition unit, and call termination control unit that records user voice input during calls and terminates the call upon recognizing a predetermined keyword after the user's head is no longer detected, reducing unnecessary speech recognition and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If speech recognition function is activated at the start of a call and continues during the call, then call termination can be recognized automatically, but electrical power consumption increases significantly
Solution Approach 1:
The system performs preliminary actions by detecting head approach and preparing to record voice data before speech recognition is fully activated. The proximity detecting unit triggers voice recording in advance, and speech recognition is activated only when the head is approached, rather than continuously during the entire call.
Solution Approach 2:
The speech recognition function operates periodically rather than continuously. It is activated only during specific time windows when the proximity detecting unit confirms the user's head is approached to the terminal device, and deactivated otherwise, creating a periodic on-off pattern that reduces power consumption.
2Use of energy by moving object
If speech recognition is activated only when needed, then power consumption is reduced, but user convenience decreases as manual activation is required
Solution Approach 1:
The system provides self-service by automatically detecting when the user needs to terminate a call through the proximity detecting unit. When the user's head approaches the terminal device during a call, the system automatically activates voice recording and speech recognition without requiring any manual button press or touch-screen operation from the user.
Solution Approach 2:
The patent replaces the mechanical interaction system (buttons, touch-screen) with an acoustic field-based system. The proximity detecting unit uses electromagnetic fields to detect head approach, and the speech recognition unit processes acoustic signals to recognize termination keywords, eliminating the need for manual mechanical operations.
3Extent of automation
If speech recognition continues throughout the call, then natural speech can be recognized, but power consumption increases and accidental termination may occur
Solution Approach 1:
The system applies local quality by making speech recognition active only in specific local conditions - when the proximity detecting unit confirms the user's head is approached to the terminal device. This localized activation ensures speech recognition occurs only when the user is actually using the device, reducing the risk of accidental termination while maintaining recognition accuracy during legitimate use.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables call termination through natural user actions while minimizing electrical power usage by limiting speech recognition to specific instances and reducing the likelihood of accidental call termination.
Implementation Method 1
a proximity detecting unit configured to detect that a head of a user has approached the communication terminal device
Data Source
AI summary
A communication terminal device records voice data indicating a voice input during a call in memory (S2), and upon detecting that a proximity of a user's head to the communication terminal device has ceased to be detected (S3 and S4; YES), recognizes an utterance after a time point a predetermined period of time prior to a time point at which a proximity of the head to the communication terminal device has ceased to be detected, based on voice data recorded in the memory (S5). Upon detecting that a predetermined keyword has been recognized, and that no proximity of the head to the communication terminal device is detected, the communication terminal device terminates the call (S9).


