Authoring Platform for Third-Party Conversational Tasks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conversational understanding systems require complex and time-consuming processes for third-party application designers to create tasks and integrate language understanding models, making it difficult for them to efficiently execute user intents through spoken dialogue systems.
Innovation Solution
A user interface authoring platform that simplifies the task definition process by allowing designers to select or author language understanding models and leverage pre-existing canonicalization and resolution modules, enabling the execution of tasks through a semi-automated approach.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If third-party application designers design their own language understanding models and multiple turn dialogue handling, then the system can execute tasks through spoken conversation, but the process becomes complex and time-consuming
Solution Approach 1:
The patent introduces a conversational understanding system as an intermediary layer between the user's spoken input and the third-party application. This mediator handles the complex language understanding model and multiple turn dialogue handling, while providing a simplified interface to third-party applications. The mediator translates natural language into structured task parameters that applications can execute, thereby reducing the complexity burden from application designers while maintaining full conversational capability.
2Measurement precision
If third-party application designers create custom language understanding models, then the system can understand user intent accurately, but the integration process becomes difficult and time-consuming
Solution Approach 1:
The conversational understanding system performs preliminary action by pre-processing and structuring user input into standardized formats before passing it to third-party applications. The system anticipates the needs of applications by automatically extracting relevant parameters, entities, and intent from spoken language, and prepares this information in a ready-to-use format. This preliminary processing eliminates the need for application designers to spend time creating custom language understanding logic, as the work is already done by the conversational understanding system.
3Ease of operation
If a simplified authoring platform is provided, then third-party designers can easily define tasks, but the system requires pre-existing language understanding models and canonicalization modules
Solution Approach 1:
The authoring platform is designed with universality to serve multiple functions: it can select from pre-existing language understanding models, author new models, and integrate with various third-party applications through a standardized interface. The platform handles multiple task types and dialogue scenarios through a single unified system, eliminating the need for separate customization processes for each application. This multi-functional design maintains ease of operation while providing the flexibility to work with diverse models and applications.
Data Source
AI summary
Aspects herein provide third party application authors with a user interface authoring platform that automates and simplifies a task definition process while also providing the ability to leverage pre-existing language understanding models and canonicalization and resolution modules that are provided by the operating system on which the CU system resides or as provided by other third parties. In particular, the present disclosure provides a method and system for authoring a task using a user interface authoring platform.