US 11,947,902 B1
Efficient multi-turn generative AI model suggested message generation
Susan Marie Grimshaw, Kirkland, WA (US); Poonam Ganesh Hattangady, Seattle, WA (US); Caleb Whitmore, San Francisco, CA (US); Tashfeen Ahmed, Dublin (IE); Ravi Teja Koganti, Bellevue, WA (US); and Michael Ivan Borysenko, Brighton (CA)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Mar. 3, 2023, as Appl. No. 18/178,191.
Int. Cl. G06F 3/048 (2013.01); G06F 3/0482 (2013.01); G06F 3/04847 (2022.01); G06F 40/166 (2020.01); G06F 40/205 (2020.01); G06F 40/40 (2020.01); G06N 3/0475 (2023.01); G06N 3/09 (2023.01)
CPC G06F 40/166 (2020.01) [G06F 3/0482 (2013.01); G06F 3/04847 (2013.01); G06F 40/205 (2020.01); G06F 40/40 (2020.01); G06N 3/0475 (2023.01); G06N 3/09 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A system for generating a suggested reply message using a generative artificial intelligence (AI) model, comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the system to:
receive a selection of a message;
combine at least a portion of the message and a predefined request phrase to form a first prompt, the predefined request phrase requesting multiple draft replies;
provide the first prompt to a generative AI model;
receive, in response to the first prompt, a first output from the generative AI model including the multiple draft replies;
parse the first output to generate a shortened summary for each of the draft replies;
receive a selection of one of the shortened summaries;
generate a second prompt by combining the portion of the message, the selected shortened summary, and additional context for the message;
provide the second prompt to the generative AI model;
receive, in response to the second prompt, a second output from the generative AI model including a suggested draft reply; and
cause a display of the suggested draft reply.