Personal Assistant Routing Across Devices and Voice Domains

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The proliferation of connected devices and personal assistants creates challenges for users and manufacturers, including device incompatibility, the need to remember which devices are compatible with specific assistants, and the difficulty of accessing all personal assistants across different hardware platforms, leading to a fractured personal assistant environment.

Innovation Solution

A platform that analyzes user requests based on contextual state, behavior profile, and semantic content to route inputs to the most suitable personal assistant, allowing seamless interaction with both native and third-party voice assistants, thereby eliminating the need for users to remember which assistant is best suited for a task and enabling OEMs to control equipment-specific personal assistants without burdening users with multiple interfaces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple personal assistants are used to support different smart devices, then device compatibility is improved, but user complexity increases as users must remember which devices are compatible with which personal assistant

Engineering Contradiction:
Improvedevice compatibilityVSAvoiduser memory burden
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a gateway device as an intermediary layer between smart devices and personal assistants. This gateway maintains compatibility mappings and routing information, automatically directing user requests to the appropriate personal assistant without requiring users to remember device-assistant compatibility relationships. The gateway acts as a mediator that transparently handles the complexity of multi-assistant coordination.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If personal assistants are distributed across multiple hardware platforms, then accessibility is improved, but system complexity increases making it difficult to access all personal assistants

Engineering Contradiction:
ImproveaccessibilityVSAvoidsystem architecture
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The gateway device is designed with universal functionality to communicate with multiple different personal assistant systems across various hardware platforms. It implements standardized interfaces and protocols that enable it to act as a common access point for diverse personal assistants, allowing users to interact with any assistant through a single unified device rather than needing access to multiple specific hardware platforms.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If OEMs develop custom personal assistants for their equipment, then equipment-specific functionality is improved, but the need for multiple interfaces increases burdening users

Engineering Contradiction:
Improveequipment-specific functionalityVSAvoidinterface complexity
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent merges multiple personal assistant interfaces into a single unified gateway interface. The gateway consolidates access to OEM-specific personal assistants and third-party assistants into one interface, allowing users to interact with all assistants through a common set of commands and interactions rather than learning multiple different interfaces. This combining approach maintains equipment-specific functionality while simplifying user interaction.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS20240296839A1Coordinating Electronic Personal Assistants
Publication Date: 2024.09.05 CERENCE OPERATING CO
  • US20240296839A1 patent drawing
  • US20240296839A1 patent drawing
  • US20240296839A1 patent drawing

AI summary

A method includes receiving a representation of a spoken utterance, processing the representation of the spoken utterance to identify, from a number of candidate domains, a request and a serving domain, and routing the request to a personal assistant based on the request and the serving domain. Identification of the serving domain is based on one or more of a contextual state, a behavior profile of a speaker of the utterance, and a semantic content of the utterance.