Automated Sample Expression Generation for Digital Assistant Intents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating diverse and high-quality sample expressions for intent classification models in digital assistants is inefficient and costly, requiring significant human expertise and time, especially when modeling numerous intents and actions across multiple applications.
Innovation Solution
Automate the generation of sample expressions using a generative machine learning model, leveraging application metadata to produce structured prompts that guide the model to generate varied and comprehensive expressions, which are then processed and integrated into a configuration file for the digital assistant.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If sample expressions are created manually by human experts, then data quality and accuracy are improved, but time consumption and costs increase significantly
Solution Approach 1:
The patent uses a generative machine learning model to automatically generate sample expressions by learning from existing metadata and application documentation, creating synthetic training data that replicates the quality of manually created samples without requiring expert human intervention for each expression
Solution Approach 2:
The system enables automated self-generation of sample expressions using the generative model, which autonomously creates diverse training data from available metadata and documentation, eliminating the need for manual expert creation while maintaining data quality standards
2Adaptability or versatility
If the number of intents and actions to be modeled increases, then the digital assistant's functionality is improved, but the complexity of data generation increases
Solution Approach 1:
The generative machine learning model serves as a universal data generation tool that can handle multiple applications, intents, and actions across different domains simultaneously, using the same underlying technology to generate diverse sample expressions for various functionalities without requiring separate manual processes for each
3Measurement precision
If more diverse sample expressions are generated, then the intent classification model's accuracy is improved, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary generation of diverse sample expressions during the training phase using the generative model, creating a comprehensive dataset in advance that enables accurate intent classification during deployment without requiring real-time generation, thus balancing diversity with processing efficiency
Data Source
AI summary
Example systems and methods described herein relate to the automated generation of sample expressions. Metadata is accessed for each of a plurality of applications. The metadata includes a functional description of each application. Prompt data is provided to a generative machine learning model. The prompt data includes the metadata for each of the plurality of applications and an instruction to generate, for each of the plurality of applications, a plurality of sample expressions corresponding to user input provided to a digital assistant to invoke an action related to the application. One or more responses that were generated by the generative machine learning model based on the prompt data are processed to obtain output data including the plurality of sample expressions for each of the plurality of applications in a structured format. The output data is used to configure the digital assistant.