Intelligent Assistant Privacy via External Task Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intelligent automated assistants often lack native configuration to handle private data domains, such as sensitive user-specific or health data, leading to security and efficiency issues when interacting with such data.
Innovation Solution
The system determines whether a natural-language input corresponds to a private domain and either performs tasks associated with it or requests access to necessary data, ensuring authorized data access and reducing power usage by avoiding unauthorized task determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the electronic device attempts to handle private data domains natively, then the assistant can process sensitive user-specific data, health data, and financial data, but security risks and reliability issues increase due to lack of native configuration
Solution Approach 1:
The patent introduces an intermediary mechanism where the electronic device sends natural language inputs to an external device for processing. The external device determines whether the input corresponds to a private domain and returns appropriate process flows or candidate tasks. This intermediary approach allows the system to handle private data domains without native configuration, while maintaining security and reliability by avoiding direct processing of sensitive data on the electronic device.
2Productivity
If the electronic device determines tasks for all natural-language inputs, then the assistant provides comprehensive responses, but power consumption increases due to unauthorized task determination attempts
Solution Approach 1:
The patent extracts the task determination function from the electronic device and relocates it to an external device. The electronic device only sends natural language inputs to the external device for processing. This extraction eliminates unnecessary task determination attempts on the electronic device, significantly reducing power consumption while maintaining comprehensive task processing capability through the external device's processing.
Solution Approach 2:
The patent segments the assistant functionality between two devices: the electronic device handles user interaction and data collection, while the external device handles task determination and processing. This segmentation allows each device to perform only its designated functions, preventing the electronic device from consuming power on unauthorized task determination while maintaining overall system productivity.
3Loss of information
If the electronic device processes all private domain requests locally, then data privacy is maintained, but device complexity increases due to need for domain-specific configurations
Solution Approach 1:
The patent uses an intermediary approach where the electronic device sends natural language inputs to an external device for processing. The external device determines whether the input corresponds to a private domain and returns appropriate process flows. This intermediary mechanism maintains data privacy by avoiding the need for the electronic device to have native configurations for private domains, while significantly reducing device complexity.
Solution Approach 2:
The external device serves as a universal processor that handles all types of inputs including private domain requests. Instead of the electronic device needing separate configurations for different private domains (health, financial, user-specific data), the external device provides universal processing capability for all private domain types through a single integrated system.
Data Source
AI summary
Systems and processes for operating an intelligent automated assistant to perform intelligent list reading are provided. In accordance with one example, a method includes, at an electronic device having one or more processors, receiving a natural-language input corresponding to a domain; providing the natural-language input to an external device; receiving, from the external device, a process flow corresponding to the domain; determining, with the process flow corresponding to the domain, a task associated with the natural-language input; performing the task; and providing an output indicating whether the task has been performed.


