US 12,002,012 B2
Identification of tasks at risk in a collaborative project
Mark James Encarnación, Bellevue, WA (US); Nalin Singal, Bellevue, WA (US); Michael Gamon, Seattle, WA (US); Shawon Sarkar, Seattle, WA (US); and Nouran Soliman, Lyndhurst, NJ (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on May 18, 2022, as Appl. No. 17/664,041.
Prior Publication US 2023/0376902 A1, Nov. 23, 2023
Int. Cl. G06Q 10/00 (2023.01); G06N 3/08 (2023.01); G06Q 10/0633 (2023.01); G06Q 10/0635 (2023.01); G06Q 10/10 (2023.01)
CPC G06Q 10/103 (2013.01) [G06N 3/08 (2013.01); G06Q 10/0633 (2013.01); G06Q 10/0635 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing system for identifying tasks at risk in a collaborative project, comprising:
a client computing device on which an action on a task of a collaborative project is performed; and
a server device including one or more processors configured to execute instructions using portions of associated memory to implement, during an inference-time phase:
a telemetry collection module configured to detect the action on the task, process the action, and output telemetry data associated with the action;
a collaborative project management program configured to receive the telemetry data associated with the action, process the telemetry data based at least in part on one or more attributes of the task, and output at least one feature associated with the task; and
a machine learning model including a trained neural network, the machine learning model being configured to:
receive, as inference-time input, at least one feature vector representing the at least one feature associated with the task; and
responsive to receiving the at least one feature vector, output a risk prediction for the task, wherein
the machine learning model is trained in an initial training phase with a training data set including a plurality of training data pairs, each training data pair including a training phase input indicating a training feature vector representing a training feature associated with a training task and ground truth output indicating a risk prediction for the training task, and
the system is configured to output an alert when the task is predicted to be at risk of not being completed by a predetermined due date.