Agent Selection via Real Environment Interaction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current artificial intelligence systems lack a unified mechanism for user interaction with multiple entities in real environments, resulting in inconsistent user experiences and requiring manual selection of chatbots or agents, which can be cumbersome and inefficient.

Innovation Solution

An agent selection component that detects user interaction with a real environment and evaluates it to select and activate appropriate artificial agents from multiple entities, providing a consistent user experience across different entities by allowing seamless interaction with various agents.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual selection of chatbots or agents is required for each entity, then users can access specific agents, but the user experience becomes inconsistent and the interaction process becomes cumbersome and inefficient

Engineering Contradiction:

Improveease of agent selectionVSAvoidtime for agent selection

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system automatically detects user interaction with the real environment and autonomously selects and activates the appropriate artificial agent without requiring manual user selection. The agent selection component evaluates detected interactions and automatically determines which agent to activate, allowing the system to serve itself in the agent selection process.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary detection and evaluation of user interactions with the real environment before agent activation. By detecting interactions in advance and pre-evaluating them, the system prepares the appropriate agent for activation, eliminating the need for manual selection and reducing the time users spend on agent selection.

Inventive Principle:

Principle #10Preliminary action

2Adaptability or versatility

If multiple separate mechanisms are used for interacting with different entities, then each entity can be accessed, but the system complexity increases and user experience consistency deteriorates

Engineering Contradiction:

Improveability to interact with multiple entitiesVSAvoidcomplexity of interaction mechanism

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The agent selection component serves as a universal mechanism that handles interactions with multiple different entities through a single unified interface. It detects various types of user interactions with the real environment and routes them to the appropriate artificial agents, allowing one component to perform multiple functions across different entities rather than requiring separate mechanisms for each entity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The agent selection component acts as an intermediary between the user and multiple artificial agents. It receives user interactions with the real environment, evaluates them, and selectively activates the appropriate agent from among multiple available agents. This intermediary approach unifies the interaction mechanism while maintaining the ability to access multiple entities.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If automated agent selection based on real environment interaction is implemented, then user experience consistency and efficiency improve, but the system requires detection and evaluation mechanisms

Engineering Contradiction:

Improveefficiency of agent accessVSAvoidcomplexity of detection and evaluation system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system uses the user's own interactions with the real environment as the basis for agent selection. By detecting interactions that users naturally perform in the real world and using those same interactions for evaluation and agent selection, the system leverages existing user behaviors rather than requiring additional complex detection mechanisms.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11803887B2Agent selection using real environment interaction

Publication Date: 2023.10.31 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

An agent selection component that selects and activates artificial agents for interacting with a user on behalf of various entity based on user interaction with a real environment. The agent selection component detects user interaction with the real environment, and evaluates the detected user interaction. Based on that evaluation, the agent selection component selects an artificial agent that acts for an entity from amongst multiple artificial agents that act for different entities (e.g., to answer questions, to place orders, to schedule, or the like). The agent selection component then causes the selected artificial agent to activate to interact with the entity. Thus, different interactions with a real environment may result in the agent selection component permitting the user to interface with artificial agents for different entities.