Mobile Terminal Voice Call Content Recognition and Tagging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile terminals lack efficient methods for controlling voice call content execution and acquiring desired data during calls, particularly through speech recognition, which limits their functionality in performing voice searches and multicasting.
Innovation Solution
Incorporating a speech recognition unit and a controller in mobile terminals to recognize voice call contents, tag them to specific items, and control item execution, enabling voice searches and efficient multicasting during calls.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If speech recognition is integrated into mobile terminals during calls, then voice call content recognition and item execution control are improved, but device complexity increases
Solution Approach 1:
The patent combines the speech recognition unit with the existing mobile terminal architecture, integrating voice call content recognition capabilities into the call handling system. The controller is enhanced to perform both call management and speech recognition tasks, merging multiple functions into a unified system that reduces overall complexity despite adding new capabilities.
Solution Approach 2:
The controller in the mobile terminal is designed to perform multiple functions: traditional call management, speech recognition processing, item tagging, and execution control. This multi-functional approach allows a single component to handle diverse tasks, improving adaptability without proportionally increasing device complexity.
2Adaptability or versatility
If speech recognition unit and controller functions are added to enable voice search and multicasting, then functionality during calls is improved, but device complexity increases
Solution Approach 1:
The patent implements preliminary action by pre-tagging voice call contents to relevant items before execution is needed. The controller continuously monitors and tags speech recognition results during calls, so that when a user wants to perform a voice search or multicast, the relevant data is already prepared and associated with appropriate items, enabling rapid response without complex real-time processing.
3Ease of operation
If voice call contents are tagged to items and item execution is controlled, then data acquisition convenience is improved, but processing time increases
Solution Approach 1:
The patent maintains continuous tagging of voice call contents to items throughout the call duration. Rather than processing requests in batches or on-demand, the controller continuously captures speech recognition results and associates them with relevant items in real-time, ensuring that data is always prepared and accessible, thus eliminating delays between user request and data availability.
Data Source
AI summary
A mobile terminal including a speech recognition unit configured to recognize input speech; a mobile communication unit configured to perform a calling operation with at least one other terminal; and a controller configured to receive a predetermined input while performing the calling operation, to recognize voice call contents through the speech recognition unit based on the received predetermined input, to tag the recognized voice call contents to at least one application executed by the mobile terminal, and to execute the at least one application using the tagged voice call contents.