Voice Application Enablement via Backend Intent Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice-activated electronic devices face complexity in enabling and disabling applications using speech, as they require manual intervention or switching between touch-based and voice-based interfaces, which can detract from the user experience and introduce additional complexities not typically associated with non-sound-based systems.
Innovation Solution
A method and system that allow users to enable or disable applications on a backend system using voice commands, where the device sends audio data to a backend system for processing, determining the intent, querying an applications database, and updating the user's account with the necessary language models and invocation phrases, enabling seamless switching between applications without the need for manual input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice commands are used to enable/disable applications, then ease of operation is improved, but device complexity increases due to speech processing functionality
Solution Approach 1:
The patent introduces a backend system as an intermediary that handles speech processing, application enablement/disablement logic, and language model management. This mediator absorbs the complexity of voice processing while keeping the user device simple, allowing voice commands to enable/disable applications without burdening the device with complex speech processing functionality.
Solution Approach 2:
The patent extracts the complex speech processing and application management logic from the user device and relocates it to a remote backend system. This separation allows the device to maintain simplicity while still providing voice-based application control, resolving the contradiction between ease of operation and device complexity.
2Device complexity
If manual intervention is required to switch between interfaces, then device complexity is reduced, but ease of operation deteriorates
Solution Approach 1:
The system enables self-service operation where users can directly manage application enablement/disablement through natural voice commands without needing to manually navigate between touch and voice interfaces. The backend system automatically processes the speech, determines intent, and updates the user account, making the system serve itself rather than requiring manual interface switching.
Solution Approach 2:
The backend system provides universal functionality by handling both speech processing and application management in a unified manner. It can process various types of voice commands and automatically manage application enablement/disablement across different contexts, eliminating the need for separate interface modes and providing consistent multi-functional operation.
3Adaptability or versatility
If speech processing functionality is integrated into the device, then adaptability is improved, but device complexity increases
Solution Approach 1:
The backend system serves as an intermediary that provides adaptability for speech processing without requiring the device itself to become complex. The mediator handles language model updates, speech intent determination, and application-specific adaptations, allowing the device to remain simple while still achieving high adaptability through the remote system.
Solution Approach 2:
The patent moves the complexity from the device dimension to the network/cloud dimension. By relocating speech processing functionality to a remote backend system, the device maintains simplicity in its physical and computational dimensions while gaining adaptability through network-connected services, effectively trading spatial dimension for functional capability.
Data Source
AI summary
Methods and devices for enabling and disabling applications using voice are described herein. In some embodiments, an individual speak an utterance to their electronic device, which may send audio data representing the utterance to a backend system. The backend system may generate text data representing the utterance, and may determine that an intent of the utterance was for an application to be enabled or disabled for their user account on the backend system. If, for instance, the intent was to enable the application, the backend system may receive one or more rules for performing functionalities of the application, as well as one or more sample templates of sample utterances and sample responses that future utterances may use when requesting the application. Furthermore, one or more invocation phrases that may be used within the future utterances to invoke the application may be received, along with slot values for the sample templates.