Abstract: A computing system for identifying tasks at risk in a collaborative project includes one or more processors configured to execute, during an inference-time phase, a collaborative project management program and a machine learning model. The collaborative project management program is configured to receive telemetry data associated with a task, process the telemetry data based at least in part on one or more task attributes, and output at least one feature associated with the task. The machine learning model is configured to receive, as inference-time input, the at least one feature associated with the task, and, responsive to receiving the at least one feature, output a risk prediction for the task. 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.

Abstract: Aspects of the present disclosure relate to obtaining task and/or list information from various types of media files. In examples, an image of an environment may be obtained, where the image may include a depiction of a plurality of tasks. The tasks may be extracted from the image and assigned to one or more users based contextual information within the image. In some examples, tasks within an image may be identified based on positional information of the text and/or character delimiters. In some examples, audio information may be received and processed such that the audio information is converted to text. The text may then be parsed to extract one or more items of a list and/or one or more tasks.

Abstract: A computing system for identifying tasks at risk in a collaborative project includes one or more processors configured to execute, during an inference-time phase, a collaborative project management program and a machine learning model. The collaborative project management program is configured to receive telemetry data associated with a task, process the telemetry data based at least in part on one or more task attributes, and output at least one feature associated with the task. The machine learning model is configured to receive, as inference-time input, the at least one feature associated with the task, and, responsive to receiving the at least one feature, output a risk prediction for the task. 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.

Abstract: Aspects of the present disclosure relate to obtaining task and/or list information from various types of media files. In examples, an image of an environment may be obtained, where the image may include a depiction of a plurality of tasks. The tasks may be extracted from the image and assigned to one or more users based contextual information within the image. In some examples, tasks within an image may be identified based on positional information of the text and/or character delimiters. In some examples, audio information may be received and processed such that the audio information is converted to text. The text may then be parsed to extract one or more items of a list and/or one or more tasks.

Abstract: Embodiments of the present invention automatically register user interfaces with a voice control system. Registering the interface allows interactive elements within the interface to be controlled by a user's voice. A voice control system analyzes audio including voice commands spoken by a user and manipulates the user interface in response. The automatic registration of a user interface with a voice control system allows a user interface to be voice controlled without the developer of the application associated with the interface having to do anything. Embodiments of the invention allow an application's interface to be voice controlled without the application needing to account for states of the voice control system.