Virtual Assistant Social Question Answering Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conversational user interfaces with virtual assistants often fail to provide support for uncommon or poorly articulated user queries, leading to resource strain and negative user experiences, as they cannot be trained for every possible question or circumstance.
Innovation Solution
Integration of a conversational user interface with a social computing system using a generative question model and deep learning algorithms to transform user inputs into rephrased questions, which are then posted in a social computing system for community answers, allowing the virtual assistant to access and provide answers from user-generated content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a virtual assistant is trained to handle every possible question or circumstance, then the support coverage is improved, but the training time and resource consumption increase significantly
Solution Approach 1:
The system performs preliminary actions by proactively posting rephrased versions of user questions to the social computing system before the user needs an answer. This allows potential answers to be prepared in advance from community knowledge, reducing the need for extensive real-time processing and training.
Solution Approach 2:
The patent introduces an intermediary mechanism - a generative question model that transforms user inputs into rephrased questions, which then serve as intermediaries to query the social computing system. This intermediary layer enables the virtual assistant to handle diverse questions without being explicitly trained for each scenario.
2Loss of energy
If the virtual assistant handles all user queries, then the organizational resource strain is reduced, but the system complexity increases
Solution Approach 1:
The patent merges the virtual assistant system with the social computing system, combining automated AI processing with community-generated knowledge. This hybrid approach distributes the workload - the virtual assistant handles routine tasks while the social computing system provides supplementary support, reducing overall organizational resource strain without requiring a single complex system to handle everything.
3Ease of operation
If the virtual assistant is enhanced to handle uncommon questions, then the user experience is improved, but the training resources required increase
Solution Approach 1:
The system dynamically adapts to uncommon questions by using the generative question model to rephrase user inputs in real-time and query the social computing system. Rather than requiring static pre-training for all possible scenarios, the system dynamically generates appropriate queries and retrieves answers from community knowledge, improving user experience for uncommon questions without proportionally increasing training resources.
Data Source
AI summary
Certain aspects of the present disclosure provide techniques for providing assistance to users by integrating social computing system with conversational user interface. In some cases, a user interacting with a virtual assistant of a conversational user interface provides input that the virtual assistant is not able identify a matching intent. As a result, the virtual assistant can leverage the social computing system to generate a new question based on the user input and post the question to the social computing system. Users of the social computing system can provide an answer, which the virtual assistant provides to the user in the conversational user interface. The social computing system can also generate a new intent for the virtual assistant to increase efficiency of the virtual assistant.