Hub Voice Assistant Model Storage for Fast Multi-Device Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-device systems, users face inconvenience in selecting a device to provide a service based on voice input due to varying service types, and existing on-device models are limited by memory capacity, processing speed, and network usage fees, leading to reduced response speed.
Innovation Solution
A multi-device system with a hub device that stores a voice assistant model to determine a device for operation based on user intent, including device and function determination models, optimizing memory usage and processing speed while reducing network reliance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a voice assistant service-providing server is used to control devices based on voice input, then service functionality is improved, but response speed is reduced and network usage fees are incurred
Solution Approach 1:
The patent segments the voice assistant functionality by separating the hub device from the voice assistant service-providing server. The hub device stores and executes a voice assistant model locally, while the server provides supplementary services. This segmentation enables fast local response while maintaining access to comprehensive server-based services, resolving the contradiction between response speed and service functionality.
2Speed
If an on-device voice assistant model is stored in the hub device's internal memory, then response speed is improved and network dependency is reduced, but the model may not be stored due to memory capacity limitations
Solution Approach 1:
The patent merges the hub device's internal memory with the cloud-based voice assistant service-providing server to form a hybrid storage system. The hub device stores a condensed voice assistant model locally for fast response, while the server stores the complete model and supplementary data. This merging allows the system to achieve both fast local response and comprehensive service functionality without being constrained by the hub device's limited memory capacity.
3Productivity
If the hub device stores a complete voice assistant model locally, then processing speed is improved, but device complexity increases
Solution Approach 1:
The patent extracts the heavy computational and storage burden from the hub device by separating the complete voice assistant model from the local device. Only a condensed version of the model is stored in the hub device's limited memory, while the full model resides on the server. This extraction reduces device complexity and memory requirements while maintaining fast local response capabilities through the condensed model.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method, performed by a hub device, of storing a voice assistant model for controlling a device includes receiving information about a first device connected to the hub device, requesting a voice assistant server to update a device determination model stored in the hub device; receiving the updated device determination model from the voice assistant server and storing the received updated device determination model; requesting, from the voice assistant server, information about a function determination model corresponding to the first device; receiving the information about the function determination model corresponding to the first device from the voice assistant server, and determining whether to store the function determination model in the hub device based on the received information; and based on the function determination model being determined to be stored in the hub device, storing, in the hub device, the function determination model corresponding to the first device