UI Navigator Using Large Action Models for One-Shot Navigation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Devices with shallow-depth user interface (UI) frameworks face challenges in navigation due to limited actions under each node, leading to cumbersome and challenging user experiences, especially when compared to deep navigation systems like mobile phones.

Innovation Solution

A UI navigator that combines large action models (LAMs) with a shallow-depth UI framework to provide one-shot navigation, utilizing user inputs such as voice, text, and device interactions to infer user intent and directly navigate to intended UI states.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a shallow-depth UI framework is used, then device complexity is reduced, but navigation ease of operation deteriorates

Engineering Contradiction:

ImproveUI framework depthVSAvoidNavigation ease

Core Design Contradiction:

Device complexityVSEase of operation

Solution Approach 1:

The patent introduces a navigational assistant as an intermediary component that mediates between the user and the shallow-depth UI framework. This assistant provides intelligent navigation suggestions and automated navigation capabilities, compensating for the limited navigation depth of the shallow UI framework without increasing its structural complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements self-service navigation through automated navigation suggestions and execution capabilities. The navigational assistant autonomously analyzes user needs, generates navigation paths, and executes navigation actions within the shallow UI framework, reducing the operational burden on users despite the framework's limited depth.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If traditional multi-step navigation is used in shallow-depth UI, then navigation precision is maintained, but user time consumption increases

Engineering Contradiction:

ImproveNavigation precisionVSAvoidUser time consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The navigational assistant performs preliminary actions by proactively providing navigation suggestions before users complete their navigation tasks. The system analyzes the current UI state, predicts user intentions, and prepares navigation paths in advance, enabling users to reach their destinations faster while maintaining precise navigation control.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual mechanical navigation steps with an intelligent software-based navigational assistant. This substitution uses automated analysis and suggestion algorithms to determine navigation paths, replacing the traditional multi-step manual navigation process while maintaining precision through intelligent decision-making.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250298579A1User-Interface Navigator

Publication Date: 2025.09.25 GOOGLE LLC

AI summary

The present document describes techniques for a user-interface (UI) navigator. The UI navigator can provide a framework that combines large action models (LAMs) with a shallow-depth UI framework to one-shot travel to a user-intended destination within the UI framework. The input can be any combination of a user speech, text, and/or a device-interaction input (e.g., rotary dial, button press, touch gesture). The UI navigator infers user intent from the input(s), using the LAM, which is constrained to the UI framework. The output can be a graphical user interface (GUI) responding to (e.g., operating according to) the user intent.