AI Virtual Proxy Nodes for Smart Audio Intent Resolution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Smart audio devices face issues with intent disambiguation, leading to unnecessary broadcasts to all devices, causing power loss, security threats, and increased latency, as well as privacy concerns due to all devices receiving user information.

Innovation Solution

Implementing AI-based virtual proxy nodes within smart audio devices to track interactions with secondary devices, use historical data to predict successful responses, and selectively broadcast commands to the most appropriate device, reducing irrelevant broadcasts and enhancing security.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the smart audio device broadcasts the command to all nearby devices when intent identification is not successful, then the command may be picked up by the correct device, but this causes power loss, security threats, increased latency, and privacy concerns

Engineering Contradiction:
Improveintent resolution accuracyVSAvoidpower consumption
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary actions by tracking interactions and deriving historical data before broadcasting commands. The virtual proxy nodes continuously monitor and record interaction patterns between devices, building a knowledge base that enables predictive intent resolution without requiring broad broadcasts

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by tracking interactions between the smart audio device and secondary devices, using this historical data to improve future intent resolution accuracy and reduce unnecessary broadcasts

Inventive Principle:
Principle #23Feedback

2Reliability

If the smart audio device broadcasts the command to all nearby devices, then the correct device may respond, but this increases latency

Engineering Contradiction:
Improvecommand delivery successVSAvoidcommand latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The virtual proxy nodes perform preliminary analysis of interaction history and device capabilities before command broadcast, pre-processing data to enable faster intent resolution and reducing the time required for command delivery

Inventive Principle:
Principle #10Preliminary action

3Reliability

If the smart audio device broadcasts the command to all nearby devices, then the command may be executed correctly, but this creates security threats and privacy concerns

Engineering Contradiction:
Improvecommand execution accuracyVSAvoidsecurity threats
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system extracts and isolates only the necessary information for intent resolution from the full command context, processing only relevant data through virtual proxy nodes rather than exposing all user information to all devices, thereby maintaining security while achieving accurate command delivery

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS11929845B2AI-based virtual proxy nodes for intent resolution in smart audio devices
Publication Date: 2024.03.12 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US11929845B2 patent drawing
  • US11929845B2 patent drawing
  • US11929845B2 patent drawing

AI summary

A system and method are disclosed that utilizes an artificial intelligence based virtual proxy node. The virtual proxy node includes an intent resolution model and communicates between a smart audio device and at least one secondary device, wherein the at least one secondary device is configured to be controlled by a smart audio device or smart hub. The virtual proxy node tracks interactions between the smart audio device and the at least one secondary device to derive historical and context data from the tracking interactions. The virtual proxy node uses the historical and context data to predict which secondary device will be successful in responding to the user input command and broadcasts the input command to the virtual proxy node associated with one of the at least one secondary device. The virtual proxy node includes an intent resolution model trained by historical and context data.