Graphical Agent Invocation for Faster Assistant Conversations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often lack awareness of automated assistant functionalities and invocation phrases, leading to inefficient interactions and resource usage, especially for those with dexterity issues.
Innovation Solution
A selectable graphical element is introduced in non-automated assistant interfaces to invoke an agent module via an automated assistant, allowing single-tap or single-click interaction, reducing the number of inputs required and promoting discovery of automated assistant functionalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users explicitly invoke the automated assistant through particular verbal phrases or hardware inputs, then the automated assistant can be activated to perform functions, but the interaction process becomes complex and requires multiple inputs that consume computational resources and time
Solution Approach 1:
The patent applies preliminary action by placing selectable graphical elements directly within the application interface that pre-configure the automated assistant invocation. When users select these elements, the invocation phrase and target function are already determined, eliminating the need for users to manually compose verbal phrases or navigate through multiple dialog turns to discover available functions.
Solution Approach 2:
The selectable graphical elements act as intermediaries between the application and the automated assistant. These elements embed invocation capabilities within the application interface, serving as a mediator that translates user selections into automated assistant commands without requiring users to directly interact with the automated assistant's invocation mechanism.
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 and user experience deteriorates
Solution Approach 1:
The selectable graphical elements are pre-configured with specific function identifiers and invocation phrases. This preliminary configuration allows users to directly access automated assistant functionalities without engaging in exploratory dialog turns, thereby preventing computational resource consumption while ensuring users can discover and access available functions through the presented interface elements.
Solution Approach 2:
The patent segments the automated assistant's functionality into discrete selectable graphical elements within the application interface. Each element corresponds to a specific function or action, allowing users to directly select desired functionalities without needing to explore through multiple dialog turns. This segmentation makes functionality discovery efficient and resource-efficient.
3Loss of energy
If the automated assistant interface is used for all interactions, then resource efficiency is improved, but users with dexterity issues face difficulty with multiple inputs required
Solution Approach 1:
The patent segments the interaction process into a single selection action followed by automated assistant processing. By embedding selectable graphical elements directly in the application interface, users with dexterity issues can complete their intent with a single tap or click rather than multiple sequential inputs, maintaining resource efficiency while improving accessibility.
Solution Approach 2:
The selectable graphical elements serve as intermediaries that accommodate users with dexterity issues by requiring only a single selection action. These elements mediate between the user's limited input capability and the automated assistant's processing requirements, enabling resource-efficient interactions without demanding multiple precise inputs from users with dexterity challenges.
Data Source
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.