US 12,463,924 B1
Method and system of generating training data for identifying messages related to meetings
Ian Gordon Blackadder, London (GB); and Royi Ronen, London (GB)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on May 1, 2024, as Appl. No. 18/652,411.
Int. Cl. H04L 51/046 (2022.01); G06F 40/166 (2020.01); G06F 40/279 (2020.01); G06F 40/40 (2020.01); G06N 3/0455 (2023.01)
CPC H04L 51/046 (2013.01) [G06F 40/166 (2020.01); G06F 40/279 (2020.01); G06F 40/40 (2020.01); G06N 3/0455 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A data processing system for training a machine-learning (ML) model to identify chat messages related to a meeting, the data processing system comprising:
a processor; and
a memory in communication with the processor, the memory comprising executable instructions that, when executed by the processor alone or in combination with other processors, cause the data processing system to perform functions of:
accessing a plurality of chat messages between one or more users;
retrieving additional data related to the meeting;
constructing a prompt, via a prompt construction engine, for transmission to a generative artificial intelligence (AI) tool, the prompt including one or more of the plurality of chat messages and at least some of the additional data;
transmitting the prompt to the generative AI tool;
receiving from the generative AI tool a summary of the one or more of the plurality of chat messages, the summary citing a subset of the one or more of the plurality of chat messages;
providing the cited subset of the one or more of the plurality of chat messages for display to a user;
collecting user feedback data related to the cited subset of the one or more of the plurality of chat messages;
labeling the cited subset of the one or more of the plurality of chat messages using the user feedback data;
generating a training dataset using the labeled subset of the one or more of the plurality of chat messages;
using the training dataset to train the ML model to identify the chat messages related to the meeting; and
iterating a process of generating the training dataset and training the ML model with larger sets of chat messages until the trained ML model meets a threshold of accuracy.