Conversational Bot Skill Exchange via Manifest Marketplace

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conversational bots often struggle to process complex user queries due to lacking necessary skills or information, leading to incomplete responses or misunderstandings, and there is a need for efficient identification and utilization of external bots to fulfill requests.

Innovation Solution

A system where conversational bots can access a manifest marketplace to identify and hand off tasks to other bots with required skills, enabling seamless execution of queries and commands by determining the necessary skills and information needed, and routing requests to the appropriate bots for completion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a single conversational bot is used to handle user requests, then the system structure is simple, but the bot cannot process complex queries that require skills it does not possess

Engineering Contradiction:

Improveskill capabilityVSAvoidsystem structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the conversational bot system into multiple specialized bots, each possessing specific skills. Instead of one bot trying to handle all queries, the system divides functionality across multiple bots with focused capabilities, allowing complex queries to be broken down and handled by appropriate specialized bots.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent creates a universal bot framework that can perform multiple functions by coordinating different specialized bots. The primary bot serves as a universal interface that can handle various types of requests by routing them to appropriate secondary bots, making the overall system multi-functional while maintaining simple individual components.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If multiple conversational bots are deployed to handle different skills, then the system can process complex queries, but the coordination and routing between bots becomes complex

Engineering Contradiction:

Improvequery processing capabilityVSAvoidcoordination mechanism

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a manifest marketplace as an intermediary component that facilitates coordination between bots. The marketplace stores standardized manifests that describe bot capabilities, skills, and interfaces, serving as a mediator that enables automatic matching and routing without complex direct-to-direct bot communication protocols.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent standardizes bot interfaces by changing the parameters of bot interaction through uniform manifest structures. By defining standard parameters for skill description, capability declaration, and communication protocols in manifests, the system enables automated routing and coordination without requiring complex custom integration logic for each bot pair.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If conversational bots use available skills to fulfill requests, then the bot can provide comprehensive responses, but privacy concerns arise when using external skills

Engineering Contradiction:

Improveresponse completenessVSAvoidprivacy risk

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent implements preliminary action by requiring that privacy considerations be addressed before skill execution. The system performs advance checks on skill manifests to identify privacy-sensitive operations, and obtains necessary user permissions or applies privacy protections before external skills are executed, preventing privacy violations rather than reacting to them afterward.

Inventive Principle:

Principle #10Preliminary action

4Adaptability or versatility

If a bot hands off tasks to other bots with required skills, then the bot can fulfill complex requests, but the conversation flow may become discontinuous

Engineering Contradiction:

Improverequest fulfillment capabilityVSAvoidconversation continuity

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent implements feedback mechanisms where secondary bots report their execution results back to the primary bot through standardized manifest-defined interfaces. This feedback loop enables the primary bot to maintain awareness of the conversation state, synthesize information from multiple bots, and present unified responses to users, preserving conversation continuity despite task handoffs.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20230359655A1Enabling exchange of conversational BOT skills during conversational chat

Publication Date: 2023.11.09 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

In non-limiting examples of the present disclosure, systems, methods, and devices for enabling conversational bot communications are presented. A marketplace comprising an identity of a plurality of skills may be maintained, each of the plurality of skills associated with a manifest and a conversational bot. A request for execution of a specific skill may be received. A plurality of conversational bots may be identified, each of the plurality of conversational bots being associated with a manifest for executing the specific skill. The plurality of conversational bots may be ranked. The specific skill may be caused to be executed by the highest ranked conversational bot. In some examples, a plurality of highest ranked conversational bots may be surfaced and a bot that is selected may execute the specific skill.