Conversational Agent Dialog Node Graph Change Propagation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conversational agents face challenges in maintaining consistency across dialog-based software projects due to the complexity of propagating changes, particularly in textual and structural aspects, which existing technologies struggle to handle efficiently.

Innovation Solution

A method is implemented using a directed graph to evaluate and propagate dialog changes across multiple nodes of a conversational agent, identifying nodes requiring similar changes based on textual and structural content, ensuring consistency in features like textual tone, voice, and expected responses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual change propagation is used across dialog nodes, then consistency can be maintained, but the complexity and time required for maintenance increases significantly

Engineering Contradiction:

ImproveconsistencyVSAvoidmaintenance complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system automatically identifies and propagates changes across dialog nodes without manual intervention. The computer evaluates the directed graph, identifies additional nodes requiring similar changes, and updates them automatically, making the system self-maintaining and eliminating the need for complex manual change management processes

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processes of change propagation with an automated computer-based system. The computer evaluates the directed graph structure and automatically propagates changes through the dialog nodes, substituting the mechanical manual process with an automated computational process that reduces complexity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If comprehensive change evaluation is performed across all nodes, then consistency is maintained, but the time required for change propagation increases

Engineering Contradiction:

ImproveconsistencyVSAvoidchange propagation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The directed graph structure is built in advance, organizing all dialog nodes and their relationships before changes are needed. This preliminary structuring allows the system to quickly evaluate and propagate changes by following pre-established relationships in the graph, rather than analyzing node relationships from scratch each time a change is needed

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces time-consuming manual evaluation and propagation processes with automated computer-based evaluation of the directed graph. The computer efficiently traverses the graph structure and identifies affected nodes automatically, substituting slow manual processes with fast computational processes that maintain consistency without significant time loss

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated change propagation is implemented, then maintenance efficiency improves, but the risk of introducing errors increases

Engineering Contradiction:

Improvemaintenance efficiencyVSAvoidaccuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system incorporates testing as a feedback mechanism to verify that propagated changes maintain consistency and do not introduce errors. The computer updates nodes and tests the changes to ensure accuracy, creating a feedback loop that validates the automated propagation process and maintains reliability while preserving efficiency

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent replaces error-prone manual change propagation with automated computer-based propagation that follows the directed graph structure precisely. The automated process eliminates human errors in identifying and updating nodes, substituting mechanical manual operations with reliable computational processes that maintain both efficiency and accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11604928B2Efficiently managing predictive changes for a conversational agent

Publication Date: 2023.03.14 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A dialog change service builds a directed graph of nodes, each described by code for a conversational agent stored in source control, the code comprising one or more dialog-based features. The dialog change service, responsive to receiving a request for a dialog change to a particular node of the conversational agent, evaluates the directed graph to identify an additional selection of nodes that require a similar changes as the dialog change based on textual and structural content. The dialog change service updates the code for the particular node and the additional selection of nodes to propagate the dialog change in the conversational agent stored in source control.