Voice Command Segmentation for Reduced Development Man-Hours
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The development of voice-activated processing systems is hindered by the need for a large number of execution commands, which increases development time and cost, while limiting voice-activated processes to frequently executed tasks reduces user operability.
Innovation Solution
A voice-operated system that generates specific commands for processing devices based on user voice inputs, including both execution and screen transition commands, to reduce the number of required execution commands and maintain user operability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice-activated processes are expanded to cover all processes, then user operability is improved, but development man-hour and cost increase significantly
Solution Approach 1:
The patent segments voice command handling into two distinct types: execution commands for frequently used processes and screen transition commands for less frequently used processes. This segmentation allows the system to apply different command generation strategies based on process frequency, reducing overall development complexity while maintaining comprehensive voice operability.
Solution Approach 2:
The patent applies partial action by generating execution commands only for frequently executed processes rather than all possible processes. For less frequently used processes, the system generates only screen transition commands. This partial approach significantly reduces development man-hour while still providing functional voice operability for all processes.
2Ease of manufacture
If voice-activated processes are limited to frequently executed processes, then development cost is reduced, but user operability for less frequently executed processes deteriorates
Solution Approach 1:
The patent makes the voice command system universal by ensuring that voice commands can trigger both execution commands for frequent processes and screen transition commands for less frequent processes. This multi-functionality allows the system to handle all types of processes through voice input, maintaining user operability across the full range of device functions.
Solution Approach 2:
The patent introduces screen transition commands as an intermediary mechanism for less frequently executed processes. Instead of requiring full execution commands for all processes, the system uses screen transitions as a middle step that guides users to the appropriate interface, thereby maintaining operability while reducing development complexity.
3Adaptability or versatility
If execution commands are generated for all processes, then complete voice control is achieved, but the number of required commands increases enormously
Solution Approach 1:
The patent segments the command set into execution commands and screen transition commands based on process frequency. This segmentation dramatically reduces the total number of commands required, as screen transition commands are simpler and fewer in number compared to full execution commands.
Solution Approach 2:
The patent changes the parameter of command complexity by using different types of commands (execution vs. screen transition) depending on the process. This parameter change allows the system to achieve complete voice control coverage while minimizing the total number of commands that need to be developed and maintained.
Data Source
AI summary
A voice-operated system includes a processing device, and a controller that communicates with the processing device. The processing device includes a first processor to perform: displaying, on an operating panel, an operation screen for instructing a process for execution by the processing device, to receive user's instruction; and executing a process corresponding to a command received from the controller. The controller includes a second processor to perform: generating the command for the processing device based on an input voice; and transmitting the command to the processing device. The generation of the command includes, when the voice instructs the processing device to execute a first process, generating a first command for instructing the operating panel to display the operation screen for instructing execution of the first process; and when the voice instructs the processing device to execute a second process, generating a second command for instructing execution of the second process.


