Conversational Entity Self-Testing via Intent Comparison

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

It is challenging to test and validate changes in conversational interaction entities due to the large number and complexity of conversation paths and customer intents, making it difficult to ensure the functionality and accuracy of these systems.

Innovation Solution

A system is implemented that uses machine learning engines to automatically generate and test conversational phrases, comparing resultant intents to predetermined intents, and employing natural language generation to increase robustness, thereby reducing manual testing efforts and processing time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual testing methods are used for conversational interaction entities, then testing can be performed, but testing time and resources increase significantly due to the large number and complexity of conversation paths and customer intents

Engineering Contradiction:

Improvetesting accuracyVSAvoidtesting time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables automated self-testing of conversational interaction entities by having the entity test itself against stored conversation paths and expected responses, eliminating the need for extensive manual testing while maintaining comprehensive coverage of conversation paths and customer intents

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system creates copies of conversation paths and stores them in a database for automated testing, allowing the same testing data to be reused across multiple test iterations and scenarios without requiring manual recreation each time

Inventive Principle:

Principle #26Copying

2Adaptability or versatility

If the conversational interaction entity is modified frequently to encompass new offerings or refine conversations, then the entity remains up-to-date, but validating changes becomes increasingly difficult due to the large number and complexity of conversation paths

Engineering Contradiction:

Improveentity flexibilityVSAvoidvalidation difficulty

Core Design Contradiction:

Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system implements automated feedback loops where test results are immediately generated and can trigger alerts or notifications, providing rapid feedback on whether modifications to the conversational interaction entity have introduced errors or broken conversation paths

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary validation by automatically testing modifications against stored conversation paths before deploying changes to production, ensuring that new offerings or refined conversations do not break existing functionality

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12197860B2Conversational interaction entity testing

Publication Date: 2025.01.14 VERIZON PATENT & LICENSING INC

AI summary

One or more computing devices, systems, and/or methods are provided. In an example, a conversation path associated with a revised code segment of a conversational interaction entity is identified by a processor. The conversation path has a predetermined intent. A conversational phrase is generated by the processor for the conversation path. The conversational interaction entity is employed by the processor using the conversation path and the conversational phrase to generate a resultant intent. An issue report is generated by the processor for the conversational interaction entity responsive to the resultant intent not matching the predetermined intent.