Content-First Interaction Model Generation for Conversational Apps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current conversational interaction application development requires manual creation of interaction models, endpoint business logic, and content, which is time-consuming and inflexible, especially when handling multiple intents and platforms, and often necessitates redeployment for changes.
Innovation Solution
A content-first development platform with a pre-populated general interaction model that uses graph traversal and content index searching, allowing for abstract intents and open-ended slots, enabling developers to create content without coding and supporting deployment across multiple assistant platforms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual creation of interaction models and endpoint business logic is used, then customization and control are improved, but development time and complexity increase
Solution Approach 1:
The system pre-generates interaction models, sample utterances, and endpoint business logic templates based on content items before the developer needs them. This preliminary action eliminates the need for manual creation during development, significantly reducing development time while maintaining customization capability through subsequent content-specific adjustments.
Solution Approach 2:
The system creates templates and patterns that can be copied and reused across multiple interaction applications. Once an interaction model is generated for one content item, it serves as a template that can be replicated and adapted for similar content, reducing repetitive development work and accelerating the creation of multiple applications.
2Adaptability or versatility
If interaction models are created for multiple assistant platforms, then platform compatibility is improved, but device complexity and maintenance burden increase
Solution Approach 1:
The system generates a universal interaction model that can be deployed across multiple assistant platforms (Amazon Alexa, Google Assistant, Microsoft Cortana) without requiring separate custom models for each platform. The generated model uses platform-agnostic patterns and structures that maintain compatibility across different assistants, eliminating the need to create and maintain separate models for each platform.
3Measurement precision
If exact matching of sample utterances to intents is required, then interpretation accuracy is improved, but flexibility and adaptability decrease
Solution Approach 1:
The system transforms rigid exact-matching parameters into flexible pattern-based parameters. Instead of requiring precise literal matches between user utterances and sample utterances, the generated interaction models use pattern templates with variables (e.g., "{City}", "{Query}") that can match multiple variations of user input while maintaining accurate intent interpretation. This parameter transformation enables both accuracy and flexibility.
Data Source
AI summary
Among other things, a developer of an interaction application for an enterprise can create items of content to be provided to an assistant platform for use in responses to requests of end-users. The developer can deploy the interaction application using defined items of content and an available general interaction model including intents and sample utterances having slots. The developer can deploy the interaction application without requiring the developer to formulate any of the intents, sample utterances, or slots of the general interaction model.