Cross-Device Voice Context Sharing for Continuous Utterance Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices struggle to provide continuous and suitable responses to a user's utterances when the user moves between different devices, as they often fail to understand or respond appropriately to subsequent utterances in different locations.
Innovation Solution
A system and method for controlling electronic devices that involves receiving voice data, determining domain and intent information, broadcasting a signal for previous utterance-related information to connected devices, and extracting and outputting a response based on received information from external devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a user moves to another place and performs a second utterance to a different electronic device, then the user can interact with devices in different locations, but the new device may not understand the second utterance or may not perform a suitable operation
Solution Approach 1:
The patent introduces a network as an intermediary that connects multiple electronic devices. When a device receives an utterance it cannot process, it broadcasts the utterance through the network to other devices. This mediator enables cross-device communication while maintaining reliable utterance understanding, as the appropriate device can identify and handle the utterance regardless of which device initially received it.
Solution Approach 2:
The patent makes electronic devices universal by enabling them to perform multiple functions across different locations. Each device can both process its own domain utterances and relay other devices' utterances through the network. This multi-functionality ensures that any device in the network can potentially understand and respond to any utterance type, maintaining reliability while allowing location flexibility.
2Ease of operation
If each electronic device operates independently at its location, then device operation is simple and direct, but continuous utterances across different devices cannot be properly processed
Solution Approach 1:
The patent ensures continuity of useful action by maintaining utterance context across device boundaries. When a user moves from one device to another, the network preserves the utterance flow by broadcasting to and relaying between devices. This allows continuous processing of multi-device utterances without breaking the interaction chain, enhancing productivity while keeping individual device operations simple.
Solution Approach 2:
The patent segments the utterance processing function across multiple devices while maintaining overall system coherence. Each device independently processes its own domain utterances (simple operation), while the network coordinates cross-device communication (continuous processing). This segmentation allows devices to remain operationally simple while the system as a whole achieves continuous multi-device utterance processing capability.
3Ease of manufacture
If an electronic device only processes its own domain utterances, then device function is clear and focused, but it cannot understand or respond to utterances from other domains or locations
Solution Approach 1:
The network acts as an intermediary that prevents information loss when devices have focused, domain-specific functions. Each device maintains clear, focused functionality for its domain, while the network mediates by broadcasting and relaying utterances across device boundaries. This ensures complete utterance information is preserved and delivered to the appropriate device, even if that device is not the one that initially received the utterance.
Solution Approach 2:
The patent adds a layer of universality to domain-specific devices through network connectivity. Each device maintains its specialized function (ease of manufacture), but gains universal access to all utterances through the network (information completeness). Devices can identify and process relevant utterances from any source, ensuring no useful information is lost while preserving functional clarity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic device, a system, and a controlling method thereof are disclosed. The controlling method includes: receiving an input utterance, determining whether domain information and intent information are able to be extracted by analyzing the input utterance, based on at least one of the domain information and the intent information not being extracted, broadcasting a signal requesting previous utterance related information to one or more external devices connected to a same network as the electronic device, receiving the previous utterance related information from the at least one external device, extracting the domain information and the intent information based on the received previous utterance related information and the input utterance, and obtaining and outputting a response result based on the extracted domain information and intent information.