Shared Memory Management for Conversational AI Bots

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conversational AI systems currently lack the ability for different bots to easily share information and manage conversations that span multiple topics or frames, as they maintain separate databases and tables, limiting user interactions to the active bot and its database, and making it difficult for bots to access and utilize data from other bots during a conversation.

Innovation Solution

A conversational AI framework that provides uniform access to shared memory spaces with different scope policies, allowing multiple bots to store and access conversational data, with data lifecycle management that erases data based on defined policies, enabling seamless data sharing across bots without direct communication or complex database queries.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If separate databases and tables are maintained for each bot, then data security and isolation are improved, but information sharing capability and conversation continuity deteriorate

Engineering Contradiction:

Improvedata isolationVSAvoidinformation sharing

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The memory space is segmented into multiple discrete regions, each associated with a different bot, while still providing uniform access through a shared interface. Each bot's data is isolated in its own memory region but can be accessed by other bots through the unified memory access mechanism, resolving the contradiction between isolation and sharing.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

A bot service acts as an intermediary layer between bots and the shared memory space. This service manages memory allocation, enforces access policies, and coordinates data sharing, allowing bots to access each other's data without direct communication while maintaining security and isolation through policy-based control.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If direct communication between bots is implemented, then information sharing is improved, but system complexity and coding difficulty worsen

Engineering Contradiction:

Improvedata sharingVSAvoidcommunication infrastructure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The bot service provides universal access to the shared memory space for all bots, eliminating the need for bot-to-bot communication infrastructure. Any bot can access any other bot's data through the unified memory interface, simplifying the system by replacing complex communication protocols with straightforward memory access.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

Bots can independently access and share data through the shared memory space without requiring direct communication protocols or coordination with other bots. Each bot autonomously reads and writes to its own memory region or accesses other regions through the unified interface, eliminating the need for inter-bot communication infrastructure.

Inventive Principle:

Principle #25Self-service

3Productivity

If complex database queries are used for data access, then data retrieval capability is improved, but coding complexity and development time worsen

Engineering Contradiction:

Improvedata retrievalVSAvoiddevelopment complexity

Core Design Contradiction:

ProductivityVSEase of manufacture

Solution Approach 1:

Instead of requiring bots to query complex databases, the system creates a simplified copy of the data access interface through the shared memory space. Bots access data through straightforward memory read/write operations rather than complex SQL queries or database protocols, dramatically simplifying the coding required for data retrieval while maintaining full data access capability.

Inventive Principle:

Principle #26Copying

4Loss of information

If unlimited data retention is implemented, then conversation history completeness is improved, but memory resource consumption and data management complexity worsen

Engineering Contradiction:

Improveconversation historyVSAvoiddata lifecycle management

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The memory management system dynamically adjusts data retention based on scope policies associated with each memory region. Different bots or memory regions can have different retention durations, allowing the system to optimize between conversation history completeness and resource consumption by automatically managing data lifecycles rather than using static unlimited retention.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11468122B2Shared memory space management for conversational artificial intelligence system

Publication Date: 2022.10.11 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A method for utilizing shared memory spaces for data lifecycle management in a conversational AI system includes receiving one or more storage requests directing conversational data to multiple nodes of a conversational data object and storing the conversational data that is directed to each different one of the multiple nodes within a different one of multiple discrete memory spaces. Each of the multiple discrete memory spaces is governed by a scope policy defining a lifetime for data stored within the memory space. The method further provides for erasing data of each node of the multiple different nodes of the conversational data object according to the lifetime defined by the scope policy governing the memory space storing the node.