Voice Action Phrase Classifier for Incomplete Command Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in learning to effectively invoke voice actions through voice commands due to the need for specific parameters, leading to incomplete phrases and prolonged prompting for omitted information, which can be inconvenient and unnatural.
Innovation Solution
A system that classifies received phrases as incomplete, generates prompts for parameter entry, and provides suggested complete phrases for voice actions using a device with a phrase classifier, prompt manager, and suggested phrase provider, utilizing text patterns to identify trigger terms and parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system prompts users to supply omitted parameters through multiple interactions, then the voice action can be performed with complete information, but the process takes a long time and feels unnatural to the user
Solution Approach 1:
The system performs preliminary classification of the received phrase to identify which parameters are missing before prompting the user. By pre-analyzing the phrase structure against required parameters, the system prepares the incomplete phrase classification in advance, reducing the interaction time needed to identify what information is missing.
Solution Approach 2:
The system provides feedback to the user by displaying the suggested complete phrase that incorporates the entered parameter. This feedback loop shows the user exactly what the complete command should look like, guiding them to provide the correct information in the next interaction, thereby reducing back-and-forth prompting.
2Reliability
If the system prompts users to supply omitted parameters through multiple interactions, then the voice action can be performed with complete information, but the process feels unnatural and inconveniences the user
Solution Approach 1:
The system provides immediate feedback by displaying the suggested complete phrase after the user enters a parameter. This shows the user the expected format and structure, making subsequent interactions more natural by guiding them toward the correct complete phrase without requiring multiple corrective prompts.
Solution Approach 2:
The system enables users to self-correct their incomplete phrases by showing them the suggested complete phrase. Users can learn from the suggestion and adjust their future voice commands accordingly, reducing the need for repeated system corrections and making the interaction feel more natural over time.
3Measurement precision
If the system requires specific parameters for voice actions, then the voice action can be performed accurately, but users have difficulty learning what specific words trigger the system
Solution Approach 1:
The system provides feedback by displaying the suggested complete phrase that includes all required parameters. This shows users exactly what words and structure are needed to trigger the voice action accurately, making the specific parameter requirements visible and learnable through direct example.
Solution Approach 2:
The system creates a template or pattern of the complete phrase based on the required parameters and the user's partial input. Users can copy this suggested phrase structure for future use, learning the correct format and triggering words by repetition rather than memorization through multiple failed attempts.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for suggesting a phrase for performing a voice action. The methods, systems, and apparatus include actions of classifying a received phrase as an incomplete phrase for performing a voice action based at least on determining that (i) the voice action requires a parameter, and (ii) that no term of the phrase corresponds to the parameter. Additional actions include, in response to classifying the phrase as an incomplete phrase, generating a prompt for entry of the parameter, and in response to the prompt, receiving data indicating an entered parameter. Further actions include providing, for output, a suggested complete phrase for performing the voice action using the entered parameter.