Selectable UI Agent Invocation for Fewer Assistant Dialog Turns

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users often require extensive interactions with automated assistants to discover and perform specific functions, leading to resource inefficiency and unawareness of available functionalities, especially for those with dexterity issues.

Innovation Solution

A selectable graphical element in a non-automated assistant interface allows direct invocation of an agent module associated with the application, reducing the need for explicit invocation phrases and dialog turns by transitioning to a conversational interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If users explicitly invoke the automated assistant and provide invocation phrases to access agent functionalities, then the automated assistant can perform specific functions, but the user requires extensive interactions and dialog turns to discover and perform functions

Engineering Contradiction:

Improveease of accessing agent functionalityVSAvoidtime required for dialog turns

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-configuring selectable graphical elements within application interfaces that directly map to agent functionalities. These elements are prepared in advance within the application UI, allowing users to access agent capabilities without needing to know invocation phrases or engage in discovery dialog turns. The selectable elements are already positioned and labeled appropriately within the application context.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary mechanism - the selectable graphical element - that bridges the application interface and the automated assistant. This intermediary allows direct invocation of agent functionalities without requiring the user to explicitly call the automated assistant first. The selectable element acts as a mediator that translates user selection directly into agent activation within the automated assistant framework.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If users engage in extensive dialog turns to discover automated assistant functionalities, then they can learn available functions, but computational resources are consumed inefficiently

Engineering Contradiction:

Improvediscovery of automated assistant functionalitiesVSAvoidcomputational resource consumption

Core Design Contradiction:

Loss of informationVSUse of energy by moving object

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent enables self-service by allowing the application interface itself to provide direct access to agent functionalities through its native selectable elements. The application UI serves itself by incorporating actionable elements that directly invoke agents, eliminating the need for users to service the system through extensive automated assistant dialog turns. The application interface becomes self-sufficient for function discovery and access.

Inventive Principle:

Principle #25Self-service

3Adaptability or versatility

If the automated assistant is used as a separate application, then it can provide broad functionality, but users may be unaware of its capabilities and prefer less resource-efficient applications

Engineering Contradiction:

Improvebroad functionality of automated assistantVSAvoiduser awareness of automated assistant capabilities

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent merges the automated assistant's agent invocation capability directly into the application interface by embedding selectable graphical elements within the application UI. This integration combines the versatility of the automated assistant with the familiar context of the application interface, making capabilities visible and accessible where users already expect to interact. The merging eliminates the separation between the application and the automated assistant, presenting a unified interface.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent applies universality by designing selectable graphical elements that can invoke different agent functionalities based on the same interaction paradigm. The same type of selectable element can trigger different agents depending on context, making the system universally accessible across multiple functions and applications. This multi-functionality allows a single interface pattern to serve multiple agent invocation purposes.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentEP4167084B1Initializing a conversation with an automated agent via selectable graphical element

Publication Date: 2026.03.11 GOOGLE LLC

Figure 1A~1C
Figure 2
Figure 3

AI summary

Methods, apparatus, systems, and computer-readable media are provided for invoking an agent module in an automated assistant application in response to user selection of a selectable element presented at a graphical user interface rendered by a non-automated assistant application. The invoked agent module can be associated with other content rendered in the non-automated assistant graphical user interface, and can optionally be invoked with values that are based on user interactions via the non-automated assistant application. Responsive content can be received from the agent module in response to the invocation, and corresponding content provided by the automated assistant application via an automated assistant interface. In these and other manners, selection of the selectable element causes transition from a non-conversational interface, to a conversational automated assistant interface - where an agent (relevant to content in the non-conversational interface) is invoked in the automated assistant interface.