Automated Assistant Input Reuse Across Apps to Cut Reprocessing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automated assistants often require users to repeat inputs to convey similar information to different applications, consuming processor resources and network bandwidth due to repetitive processing of spoken utterances, and inefficiently manage interactions across multiple applications.

Innovation Solution

An automated assistant on a client device retrieves data from multiple applications installed on the device to fulfill user requests, using on-device processing to generate responsive data and minimize network communication, thereby reducing resource consumption and improving interaction efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If users repeat inputs to convey similar information to different applications, then information can be communicated to multiple applications, but processor resources and network bandwidth are consumed due to repetitive processing

Engineering Contradiction:
Improveability to communicate information to multiple applicationsVSAvoidprocessor resources and network bandwidth consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The automated assistant pre-processes user input and stores it in a structured format that can be quickly retrieved and reused across multiple applications, eliminating the need for repetitive processing of the same information

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a reusable representation of user input that can be copied and applied to multiple applications simultaneously, allowing the same information to be communicated to different applications without repeating the original processing steps

Inventive Principle:
Principle #26Copying

2Ease of operation

If automated assistants process spoken utterances for each application interaction, then user requests can be fulfilled, but resource consumption increases due to repetitive processing of similar utterances

Engineering Contradiction:
Improveuser request fulfillment capabilityVSAvoidresource efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The automated assistant performs preliminary processing of spoken utterances into structured data representations that can be efficiently reused across multiple application interactions, reducing the need for repeated processing of the same user intent

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system transforms spoken utterances from their original audio form into structured parameter-based representations that can be efficiently queried and reused, changing the state of the data from unstructured speech to organized, reusable information

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4354339B1Automated assistant for generating, in response to a request from a user, application input content using application data from other sources
Publication Date: 2025.11.19 GOOGLE LLC
  • EP4354339B1 patent drawingFigure 1A
  • EP4354339B1 patent drawingFigure 1B
  • EP4354339B1 patent drawingFigure 2A

AI summary

Implementations set forth herein relate to an automated assistant that can be invoked while a user is interfacing with a foreground application in order to retrieve data from one or more different applications, and then provide the retrieved data to the foreground application. A user can invoke the automated assistant while operating the foreground application by providing a spoken utterance, and the automated assistant can select one or more other applications to query based on content of the spoken utterance. Application data collected by the automated assistant from the one or more other applications can then be used to provide an input to the foreground application. In this way, the user can bypass switching between applications in the foreground in order to retrieve data that has been generated by other applications.