Chatbot Invocation Timing in Medical Communication Sessions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing chatbot invocation systems are insufficient in determining the appropriate timing for engaging in conversations between human users, often requiring manual initiation or occurring at inappropriate times, which can distract medical professionals during online communication sessions.
Innovation Solution
A system and method that generate an interaction model trained on past conversation data and metadata to predict interaction points where additional content sharing is likely to occur, allowing a chatbot to automatically participate and share relevant content in real-time or near real-time online communication sessions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a medical professional manually shares additional content during an online communication session, then the communication quality and patient engagement are improved, but the medical professional loses time searching for content and is distracted from communicating with the patient
Solution Approach 1:
The system enables self-service by automatically detecting interaction points in the conversation and invoking the chatbot to share relevant content without requiring the medical professional to manually search for or initiate content sharing. The chatbot autonomously monitors the conversation, identifies when additional content would be beneficial, and presents relevant materials to the medical professional for sharing.
Solution Approach 2:
The chatbot acts as an intermediary between the medical professional and the content repository. Instead of the medical professional directly searching for and sharing content, the chatbot intermediates by monitoring the conversation, identifying relevant topics, retrieving appropriate content, and presenting it to the medical professional for sharing with the patient.
2Adaptability or versatility
If a chatbot is invoked at any time during a conversation, then the chatbot can provide computer-based assistance, but the timing may be inappropriate and distract the medical professional from communicating with the patient
Solution Approach 1:
The system uses feedback by continuously monitoring the conversation in real-time and analyzing interaction patterns to determine when the chatbot should be invoked. The system processes conversation data, identifies interaction points where additional content would be beneficial, and only then invokes the chatbot, ensuring timing is appropriate and does not disrupt the natural flow of communication between the medical professional and patient.
3Productivity
If the medical professional is well prepared with additional content before the session, then content sharing can occur smoothly, but the preparation time and effort increase
Solution Approach 1:
The system performs preliminary action by proactively analyzing the conversation as it occurs and identifying relevant content before the medical professional would need to share it. Instead of requiring preparation beforehand, the system pre-retrieves and prepares relevant content in real-time based on the actual conversation flow, presenting it to the medical professional at the optimal moment for sharing.
Data Source
AI summary
A chatbot may be invoked in an online communication session between two or more human users to share additional content in the communication session. To determine when to invoke the chatbot, e.g., at which point during their conversation, an interaction model may be trained on past conversation data between participants to determine so-termed interaction points in the past conversation data which are predictive of a subsequent sharing of additional content by one of the participants. Having generated the interaction model, the interaction model may be applied to an online communication session to detect such interaction points in a real-time or near real-time conversation between users and to invoke the chatbot to participate in the communication session in response to a detection.


