Automated Assistant Contextual Application Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face limitations when trying to send messages through automated assistants, as they often need to explicitly specify the application, leading to increased battery usage, processing resources, and prolonged user input.
Innovation Solution
An automated assistant that can identify the application through user interactions and contextual data, allowing users to send messages without explicitly specifying the application, thereby reducing the need for manual input and resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users explicitly specify the application when sending messages through automated assistant, then message sending accuracy is improved, but user input duration and complexity increase
Solution Approach 1:
The system performs preliminary action by proactively identifying the target application based on conversation context before the user needs to send a message. The automated assistant monitors ongoing conversations across multiple applications and pre-determines which application is currently active or most relevant, so when the user expresses intent to send a message, the target application is already identified and ready, eliminating the need for users to explicitly specify it.
Solution Approach 2:
The system applies self-service by enabling the automated assistant to autonomously determine the target application without requiring user specification. The assistant uses contextual clues from the conversation flow, such as the last active application or the application where the conversation is occurring, to self-identify the correct target, thereby simplifying user input while maintaining accuracy.
2Adaptability or versatility
If users navigate to and launch third party applications to send messages, then communication versatility is improved, but battery consumption and processing resources increase
Solution Approach 1:
The automated assistant implements universality by providing a single unified interface that can send messages across multiple different applications (OEM messaging, third-party messaging, social media, etc.). Instead of requiring users to manually navigate to each specific application, the assistant serves as a universal gateway that handles message sending for various communication platforms through a single voice or text command, thereby reducing the need to launch multiple applications and conserving battery resources.
Solution Approach 2:
The automated assistant acts as an intermediary between the user and multiple communication applications. It mediates the message sending process by receiving user intent through a single interface, automatically identifying the target application and conversation context, and then routing the message to the appropriate application backend. This intermediary role eliminates the need for users to directly interact with multiple application interfaces, reducing computational overhead and energy consumption.
3Measurement precision
If users recall and recite application aliases to the automated assistant, then message routing accuracy is improved, but user input complexity and duration increase
Solution Approach 1:
The system performs preliminary action by pre-identifying the target application through contextual analysis before the user needs to provide detailed specifications. The automated assistant monitors the conversation state and application usage patterns in advance, so when message sending is requested, the target is already determined based on the most recently active application or the application where the conversation is currently taking place, eliminating the need for users to recite aliases.
Solution Approach 2:
The automated assistant applies self-service by autonomously determining the target application using contextual clues from the ongoing conversation. It analyzes which application is currently active or most relevant to the conversation topic and self-identifies the correct target without requiring the user to provide the application alias, thereby simplifying user input while maintaining routing accuracy.
Data Source
AI summary
Implementations relate to an automated assistant that can respond to communications received via a third party application and/or other third party communication modality. The automated assistant can determine that the user is participating in multiple different conversations via multiple different third party communication services. In some implementations, conversations can be processed to identify particular features of the conversations. When the automated assistant is invoked to provide input to a conversation, the automated assistant can compare the input to the identified conversation features in order to select the particular conversation that is most relevant to the input. In this way, the automated assistant can assist with any of multiple disparate conversations that are each occurring via a different third party application.