Command Processing System Application Selection Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Speech-controlled computing systems face challenges in accurately selecting the appropriate application to respond to user commands, often resulting in inadequate or no results due to similar probability scores among multiple applications, leading to inefficiencies in resource utilization and user experience.
Innovation Solution
The system improves application selection by sending NLU results to multiple applications, obtaining partial command-related output, and using post-results scores to determine the most appropriate application for responding, thereby reducing instances of inadequate results and enhancing user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system sends NLU results to multiple applications and obtains partial command-related output, then the accuracy of application selection is improved, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by sending NLU results to multiple applications in advance and obtaining partial command-related output before final selection. This allows the system to pre-evaluate multiple applications' capabilities and responses, ensuring more accurate application selection while managing processing time through staged evaluation.
2Reliability
If the system sends NLU results to multiple applications, then the reliability of command execution is improved, but the computational resources consumed increase
Solution Approach 1:
The system applies partial action by obtaining only partial command-related output from each application rather than complete execution. This allows the system to evaluate multiple applications' responses to determine the most suitable one without fully executing all applications, thereby improving command execution reliability while conserving computational resources.
3Ease of operation
If the system uses post-results scores to determine the most appropriate application, then the quality of user interaction is improved, but the complexity of the selection process increases
Solution Approach 1:
The system implements feedback mechanisms by using post-results scores from application responses to determine the most appropriate application. The partial command-related output and scoring system provide feedback that guides the selection process, improving user interaction quality through more accurate application matching while managing complexity through structured evaluation criteria.
Data Source
AI summary
Techniques for performing command processing are described. A system receives, from a device, input data corresponding to a command. The system determines NLU processing results associated with multiple applications. The system also determines NLU confidences for the NLU processing results for each application. The system sends NLU processing results to a portion of the multiple applications, and receives output data or instructions from the portion of the applications. The system ranks the portion of the applications based at least in part on the NLU processing results associated with the portion of the applications as well as the output data or instructions provided by the portion of the applications. The system may also rank the portion of the applications using other data. The system causes content corresponding to output data or instructions provided by the highest ranked application to be output to a user.