Conversational Bot Skill Handoff via Manifest Marketplace
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conversational bots often struggle to process complex user queries and commands due to lack of necessary skills or information, leading to incomplete responses or inability to fulfill requests.
Innovation Solution
A system where conversational bots can identify and hand off tasks to other bots with required skills through a manifest marketplace, allowing seamless execution of skills without direct user interaction, and ensuring privacy-oriented skills are used when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a conversational bot attempts to handle all user queries independently, then the bot must have comprehensive skills and information access, but this increases device complexity and reduces reliability when skills are insufficient
Solution Approach 1:
The patent divides the skill repository into modular skill units that can be independently registered, published, and executed. Each skill is a separate entity that can be discovered through the manifest marketplace, allowing the bot to handle complex queries by composing multiple skills rather than requiring a monolithic comprehensive skill set.
Solution Approach 2:
The manifest marketplace acts as an intermediary between users and skills. Instead of the bot needing to know all possible skills internally, the marketplace provides a discovery and registration mechanism where skills are published and can be dynamically selected for query execution, reducing the bot's internal complexity while maintaining comprehensive capability.
2Productivity
If conversational bots execute skills directly without user interaction, then processing efficiency improves, but privacy concerns arise when sensitive data is processed
Solution Approach 1:
The patent introduces privacy-oriented skills as a specialized subset of skills that handle sensitive data with enhanced security measures. These skills have different execution characteristics compared to regular skills, implementing local quality variations in data handling procedures throughout the skill repository.
Solution Approach 2:
The system provides feedback mechanisms that allow the bot to identify when a query requires privacy-oriented handling and automatically select appropriate skills. The manifest marketplace includes metadata about skill privacy characteristics, enabling the bot to make informed decisions about which skills to execute based on the query's privacy implications.
3Adaptability or versatility
If the bot queries every possible skill in the marketplace for each user request, then comprehensive query fulfillment is achieved, but processing time increases
Solution Approach 1:
The patent implements preliminary indexing and categorization of skills in the manifest marketplace. Skills are pre-organized by type, capability, and privacy characteristics, allowing the bot to perform targeted searches rather than querying all skills. This preliminary structuring enables rapid skill discovery based on query patterns.
Solution Approach 2:
Instead of exhaustively searching all skills, the bot uses partial action by querying only the subset of skills relevant to the current query type. The manifest marketplace provides filtering capabilities that allow the bot to limit its search to appropriate skill categories, reducing processing time while maintaining comprehensive query fulfillment capability.
Data Source
AI summary
In non-limiting examples of the present disclosure, systems, methods and devices for enabling conversational bot communications are presented. A natural language input may be received by a first conversational bot. A skill needed to fulfill a request in the natural language input may be identified. A determination may be made that the skill is not executable by the first conversational bot. A determination may be made that the skill is executable by a second conversational bot. A request for execution of the skill may be sent from the first conversational bot to the second conversational bot. A request for information needed for the second conversational bot to execute the skill may be received by the first conversational bot from the second conversational bot. The information may be sent from the first conversational bot to the second conversational bot. The skill may be executed.