Microsoft Technology Licensing, LLC (20240296278). EFFICIENT MULTI-TURN GENERATIVE AI MODEL SUGGESTED MESSAGE GENERATION simplified abstract

EFFICIENT MULTI-TURN GENERATIVE AI MODEL SUGGESTED MESSAGE GENERATION

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Susan Marie Grimshaw of Kirkland WA (US)

Poonam Ganesh Hattangady of Seattle WA (US)

Caleb Whitmore of San Francisco CA (US)

Tashfeen Ahmed of Dublin (IE)

Ravi Teja Koganti of Bellevue WA (US)

Michael Ivan Borysenko of Brighton (CA)

EFFICIENT MULTI-TURN GENERATIVE AI MODEL SUGGESTED MESSAGE GENERATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240296278 titled 'EFFICIENT MULTI-TURN GENERATIVE AI MODEL SUGGESTED MESSAGE GENERATION

Simplified Explanation: The patent application describes a system and method for using a generative artificial intelligence model in a multi-turn process to generate suggested draft replies to selected messages.

Key Features and Innovation:

• Utilizes a multi-turn process to generate draft replies from an AI model.
• Shortens, summarizes, and converts AI-generated draft replies into reply options for users.
• Provides customization options for more relevant and personalized responses.

Potential Applications: This technology can be applied in messaging platforms, customer service interactions, and email communication to assist users in drafting replies more efficiently.

Problems Solved: Addresses the challenge of generating appropriate responses to messages by leveraging AI technology to provide suggested draft replies.

Benefits:

• Saves time for users in composing replies.
• Improves the quality and relevance of responses.
• Enhances user experience in communication platforms.

Commercial Applications: This technology can be utilized in chatbots, email clients, and social media platforms to streamline communication processes and enhance user engagement.

Prior Art: Prior art related to this technology may include research on natural language processing, AI-generated content, and communication systems.

Frequently Updated Research: Stay updated on advancements in natural language processing, AI models, and communication technologies to enhance the capabilities of this system.

Questions about AI Draft Reply Generation: 1. How does the multi-turn process improve the quality of suggested draft replies? 2. What are the potential privacy concerns associated with using AI models to generate draft replies?

Original Abstract Submitted

systems and methods for using a generative artificial intelligence (ai) model using a multi-turn process to generate a suggested draft reply to a selected message. a first turn of the multi-turn process uses a shorter prompt including at least a portion of the body of the selected message and that requests multiple draft replies from the ai model. the resulting ai-generated draft replies are shortened, summarized, and/or otherwise converted into a plurality of shortened summaries that are presented as reply options to a user. upon selecting a shortened summary, a more robust prompt is generated in a second turn with the ai model with the selected reply option to generate a more complex suggested draft reply to the selected message. additionally, various customization options are provided, which when selected, reframe a query presented to the ai model to generate a more relevant and personalized response.