Digital Assistant Local Processing for Personal Request Privacy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intelligent automated assistants face challenges in securely and efficiently handling personal requests, as existing systems often require transmitting user requests to external devices, potentially exposing sensitive information and increasing latency and computational costs.
Innovation Solution
An electronic device determines whether a user request is personal and, if so, initiates the task locally without transmitting the request to an external device, thereby maintaining privacy and reducing latency and computational load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If user requests are transmitted to external devices for processing, then the digital assistant can leverage external computational resources and services, but personal data security is compromised and latency increases
Solution Approach 1:
The patent segments user requests into two categories: personal requests and non-personal requests. This segmentation allows the system to apply different processing strategies - local processing for personal requests to ensure security, and external processing for non-personal requests to leverage external resources.
Solution Approach 2:
The patent implements local quality by making the processing location dependent on the request type. Personal requests are processed locally on the user's device to maintain data security, while non-personal requests can be processed externally. This creates different processing qualities in different parts of the system based on security requirements.
2Productivity
If user requests are transmitted to external devices, then external computational resources can be utilized, but response time increases due to transmission and processing latency
Solution Approach 1:
The patent performs preliminary action by classifying the user request before transmission. By determining whether a request is personal or non-personal in advance, the system can immediately route personal requests for local processing, avoiding the transmission delay that would otherwise occur.
Solution Approach 2:
Instead of the conventional approach of always transmitting requests externally and then handling exceptions, the patent inverts the logic by defaulting to local processing for personal requests and only using external processing when necessary. This reversal prioritizes speed for time-sensitive personal requests.
3Device complexity
If user requests are processed externally, then the device can offload computational tasks, but battery life is reduced due to continuous network communication and processing overhead
Solution Approach 1:
The patent introduces dynamics by making the processing location adaptive based on request characteristics. The system dynamically decides whether to process requests locally or externally based on whether they are personal or non-personal, allowing optimal energy utilization for each specific request type.
Solution Approach 2:
The patent enables self-service by allowing the device to handle personal requests independently without external assistance. This self-processing capability reduces network communication overhead and external processing dependencies, thereby conserving battery life for requests that don't require external resources.
Data Source
AI summary
An example process includes at an electronic device with one or more processors and memory: receiving a natural language input including a user request; determining whether the user request corresponds to a personal request; in accordance with a determination that the user request does not correspond to a personal request: transmitting, by the electronic device, a representation of the user request to an external electronic device; and in accordance with a determination that the user request corresponds to a personal request: initiating, by the electronic device, a task based on the user request without transmitting the representation of the user request to the external electronic device; and providing a first result based on the initiated task.