Ambient multi-device framework for agent companions

The ambient multi-device framework addresses the lack of interconnectivity among computing devices by optimizing input and output distribution using environment-based prompt generation and generative models, enhancing device interoperability and computational efficiency.

JP7888791B2Active Publication Date: 2026-07-13GOOGLE LLC
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2025061256
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2023-12-20
Filing Date
2025-04-02
Publication Date
2026-07-13
Estimated Expiration
2044-11-21

AI Technical Summary

Technical Problem

Existing computing devices in a user's environment lack interconnectivity, leading to inefficient utilization of their functionalities, as they cannot determine how to interact effectively to provide context-specific outputs or inputs.

Method used

An ambient multi-device framework that leverages environment-based prompt generation and generative models to optimize input acquisition and output distribution across multiple computing devices, utilizing their diverse capabilities to provide immersive and high-quality responses.

Benefits of technology

Enhances interoperability among computing devices, reducing computational resources and providing efficient, high-quality input and output across devices, creating an interconnected ecosystem.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007888791000001
    Figure 0007888791000001
  • Figure 0007888791000002
    Figure 0007888791000002
  • Figure 0007888791000003
    Figure 0007888791000003
Patent Text Reader

Abstract

To provide an ambient multi-device framework for agent companions.SOLUTION: Systems and methods for generating and providing outputs in a multi-device system can include leveraging environment-based prompt generation and generative model response generation to provide dynamic response generation and display. The systems and methods can obtain input data associated with one or more computing devices within an environment, can obtain environment data descriptive of the plurality of computing devices within the environment, and can generate a prompt based on the input data and environment data. The prompt can be processed with a generative model to generate a model-generated output. The model-generated output can then be transmitted to a particular computing device of the plurality of computing devices.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Interface for in-vehicle equipment

    JP2005178473A

  • Disambiguating heteronyms in speech synthesis

    JP2016122183A

  • Intelligent automatic assistant for tv user interaction

    JP2017530567A

  • Persona chatbot control method and system

    JP2022180282A

  • Multi-device Mediation for Assistant Systems

    US20220358917A1