Automated Assistant Data Sync via Simultaneous Hotword Arbitration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As automated assistants become decentralized across multiple client devices, data used by these assistants becomes siloed, leading to inconsistent user experiences and outdated information, especially when devices are not connected to the internet or lack cloud-based accounts.
Innovation Solution
Cross-device data synchronization is achieved through simultaneous hotword triggers, allowing seamless sharing of personalized models, preferences, and other user data between devices in a peer-to-peer manner, even when they are not centrally connected, using local determinations and device arbitration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated assistants are decentralized across client devices to preserve user privacy and reduce latency, then user privacy and response speed are improved, but user data becomes siloed leading to inconsistent user experiences and outdated data
Solution Approach 1:
The patent introduces a peer-to-peer data synchronization mechanism that acts as an intermediary between decentralized devices. When a hotword is detected on one device, it triggers arbitration with other devices to determine which device should handle the query, and subsequently initiates data synchronization between devices. This mediator approach enables data sharing without requiring a centralized cloud server, thus preserving privacy while maintaining data consistency.
2Loss of energy
If automated assistants run locally on client devices without cloud connections, then resource conservation and privacy are improved, but data becomes outdated and user experience consistency deteriorates
Solution Approach 1:
The patent implements continuous data synchronization between devices through hotword-triggered arbitration. Instead of periodic cloud-sync operations that consume network resources, the system continuously monitors for hotword detections and automatically synchronizes data between devices when triggered. This maintains data currency through on-device peer-to-peer communication, avoiding cloud dependency while preserving resource conservation.
3Ease of operation
If data synchronization is implemented between multiple devices, then user experience consistency is improved, but device complexity and processing requirements increase
Solution Approach 1:
The patent performs preliminary arbitration between devices before initiating data synchronization. When a hotword is detected, the system first determines which device should handle the query through arbitration with other devices. Only after this preliminary decision is made does data synchronization occur. This preliminary action approach simplifies the synchronization mechanism by avoiding unnecessary sync operations and reducing processing complexity.
4Productivity
If hotword-triggered arbitration is implemented between devices, then data synchronization efficiency is improved, but processing load and system complexity increase
Solution Approach 1:
The patent uses periodic hotword detections as triggers for arbitration and data synchronization operations. Instead of continuous monitoring or cloud-pushed updates, the system waits for natural hotword triggers from user interactions. This periodic action approach improves synchronization efficiency by activating data exchange only when necessary, reducing processing load while maintaining essential data currency through event-driven synchronization.
Data Source
AI summary
Techniques are described herein for cross-device data synchronization based on simultaneous hotword triggers. A method includes: executing a first instance of an automated assistant in an inactive state at least in part on a first computing device operated by a user; while in the inactive state, receiving, via one or more microphones of the first computing device, audio data that captures a spoken utterance of the user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a threshold that is indicative of the one or more hotwords being present in the audio data; in response to determining that the predicted output satisfies the threshold, performing arbitration with at least one other computing device that is executing at least in part at least one other instance of the automated assistant; and in response to performing arbitration with the at least one other computing device, initiating synchronization of user data or configuration data between the first instance of the automated assistant on the first computing device and the at least one other instance of the automated assistant on the at least one other computing device, the user data comprising data that is based on one or more interactions with the user at the first computing device, the one or more interactions occurring prior to the receiving of the audio data.