Group Messaging Prompts for Multi-User Generative Chat Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional generative models are designed for single-user interactions and cannot maintain conversation context in group conversations, preventing their incorporation into computer-implemented messaging applications that support group discussions.
Innovation Solution
Incorporating a generative model into a computer-implemented messaging application by providing a prompt that identifies the conversation as a group conversation, including participant identities and messages, and training the model to recognize multiple users, allowing it to generate outputs based on multiple messages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a conventional generative model is used for single-user chat interactions, then the model can maintain conversation context effectively, but the model cannot be incorporated into group conversation messaging applications
Solution Approach 1:
The patent segments the conversation context by creating separate context windows for different users in a group conversation. Each user's messages are tracked individually with unique identifiers, allowing the generative model to process multiple user inputs while maintaining distinct context for each participant. This segmentation enables the model to participate in group conversations while preserving conversation context reliability.
2Adaptability or versatility
If a generative model is trained to recognize multi-user conversations, then it can disambiguate between different users, but the model design becomes more complex
Solution Approach 1:
The patent applies preliminary action by pre-processing user messages to attach unique user identifiers and context information before feeding them to the generative model. The messaging application constructs prompts that include user identity information in advance, so the model receives pre-organized multi-user context without requiring complex internal disambiguation mechanisms. This reduces model design complexity while maintaining multi-user recognition capability.
Data Source
AI summary
A computing system includes a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving multiple messages from multiple users in a messaging application that supports group conversations, where the multiple messages are included in a group conversation. The acts also include providing a prompt to a generative model, where the prompt includes the multiple messages. The acts additionally include receiving, from the generative model, an output generated by the generative model based upon the prompt and including the output as a turn in the group conversation.