Follow-Up Prompt Generation Using Dialog Context and Entity Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing natural language processing systems struggle to determine when and how to output follow-up prompts effectively to continue user-system dialogs, often leading to unsatisfactory user experiences due to inappropriate or irrelevant prompts.
Innovation Solution
A system that utilizes named entity recognition, metadata extraction, and machine learning models to analyze user inputs and system responses to identify appropriate follow-up prompts, ensuring they align with user interests and dialog context, thereby enhancing user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the system outputs follow-up prompts to continue user-system dialogs, then user engagement is improved, but the prompts may be inappropriate or irrelevant leading to unsatisfactory user experiences
Solution Approach 1:
The system employs machine learning models that analyze user inputs and system responses to generate follow-up prompts based on dialog context and user interests. The model continuously learns from user interactions, adjusting prompt generation to improve relevance and appropriateness over time, thereby resolving the contradiction between increasing user engagement and maintaining prompt quality
Solution Approach 2:
The system dynamically adjusts parameters such as prompt timing, content selection, and delivery method based on analyzed user interests and dialog context. By changing these parameters adaptively, the system maintains prompt relevance while maximizing user engagement opportunities
2Measurement precision
If the system analyzes user inputs and system responses using named entity recognition and metadata extraction, then prompt accuracy is improved, but processing complexity increases
Solution Approach 1:
The analysis process is divided into distinct modules: named entity recognition component, metadata extraction component, and machine learning model component. Each module handles a specific aspect of the analysis, improving prompt accuracy through specialized processing while managing overall system complexity through modular architecture
Solution Approach 2:
The machine learning model serves multiple functions: it analyzes user inputs, processes system responses, identifies user interests, and generates follow-up prompts. This multi-functionality consolidates multiple processing tasks into a single system, improving prompt accuracy without proportionally increasing processing complexity
Data Source
AI summary
Techniques for determining a follow-up natural language prompt, to continue a user-system dialog, are described. The system determines ASR output data representing a user input and/or a system-generated responsive thereto. The system determines one or more entities represented in the ASR output data and/or the system-generated response, and identifies one or more natural language prompts associated with the one or more entities in storage. The system filters out prompts classified as likely to result in an unsatisfactory user experience, using dialog history data including a previous user input(s) and/or a previous system-generated response(s). The system determines context(s) associated with the instant user and/or device, and uses this context(s), the ASR output data, and/or the system-generated response to determine which of the follow-up prompts is to be presented to the user.