Voice Assistant Device Registration via Function Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice assistant systems face difficulties in effectively integrating and controlling new devices within a home network environment, particularly in reflecting their functions accurately in response to voice inputs, especially when these devices are not pre-registered with the service.
Innovation Solution
A system and method that utilize pre-registered device functions to register and generate utterance and action data for new devices, by comparing technical specifications, identifying matching functions, and generating corresponding data to update the voice assistant model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a new device is added to a home network environment with a voice assistant service, then the device functionality is expanded, but the system cannot effectively control or recognize the new device functions through voice input
Solution Approach 1:
The system copies utterance data and action data from pre-registered devices to newly added devices. When a new device is detected, the server retrieves technical specifications, identifies matching functions with existing devices, and transfers the corresponding utterance-action data pairs. This allows the voice assistant to immediately recognize and control new devices without requiring separate training or registration for each device type.
Solution Approach 2:
The system creates a universal voice control framework where a single set of utterance data can control multiple device types through function matching. By comparing technical specifications and identifying common functions across different devices, the system enables one utterance dataset to serve multiple purposes, allowing the voice assistant to operate effectively across diverse device types without device-specific customization.
2Measurement precision
If the voice assistant system maintains separate device registrations, then device function accuracy is improved, but the complexity of device management increases
Solution Approach 1:
The system merges device management by consolidating utterance data and action data into a unified structure that can serve multiple devices. Instead of maintaining completely separate registration systems for each device, the server combines data from pre-registered devices and applies it to new devices through function matching, reducing management complexity while preserving function recognition accuracy through the matching process.
Solution Approach 2:
The system uses data copying from pre-registered devices to newly added devices, eliminating the need for manual re-registration of each device type. The server copies relevant utterance-action data pairs based on function matching, thereby maintaining accurate device function recognition without requiring complex separate registration processes for each new device.
3Ease of manufacture
If the system uses pre-registered device data for new devices, then the registration process is simplified, but the accuracy of new device function control may be compromised
Solution Approach 1:
The system applies local quality by customizing the copied data to match the specific functions of the new device. When utterance data and action data are copied from pre-registered devices, the server filters and selects only those data pairs that correspond to functions actually present in the new device's technical specifications. This ensures that while the registration process remains simple, the control accuracy is maintained by ensuring data-re device function correspondence.
Solution Approach 2:
The system changes parameters by adapting copied data to match the new device's specific characteristics. The server compares technical specifications, identifies function matches, and modifies or selects utterance-action data pairs based on the new device's capabilities. This parameter adjustment ensures that the simplified registration process still produces accurate device control by tailoring the copied data to the specific device being registered.
Data Source
AI summary
A system and method for registering a new device for a voice assistant service. The method, performed by a server, of registering a new device for a voice assistant service includes: comparing functions of a pre-registered device with functions of the new device; identifying functions corresponding to the functions of the pre-registered device among the functions of the new device, based on the comparison; obtaining pre-registered utterance data related to at least some of the identified functions; generating action data for the new device based on the identified functions and the pre-registered utterance data.