Abstract: The technologies described herein are generally directed to allocating a resource to perform a task based on a predicted capacity of the resource. For example, a method described herein can include identifying a selected capacity associated with completion of tasks of a particular task type. Further, the method can include, evaluating a result of work by a worker resource performing a task of the particular task type. The method can further include, based on the result, predicting that the worker resource has the selected capacity and, based on this prediction, assign the worker resource to perform another task of the particular task type.

Abstract: The technologies described herein are generally directed to managing interactions between disparate resource types to complete tasks in an organization. For example, a method described herein can include identifying a task for achieving a task result, with task resources combining to complete the task including, communication resources, worker resources, and computer hardware resources. The method can further include mapping interactions between ones of the task resources to the task result. Further, the method can include, based on analyzing the interactions, allocate, for another task, additional interactions between selected ones of the task resources.

Abstract: Concepts and technologies disclosed herein are directed to automated optimization of events by engagement and format. According to one aspect disclosed herein, an event management system can create an event for a specified topic based upon input provided, at least in part, by an event creator. The input can identify initial event content, a plurality of event attendees, a location for the event, and an event presenter. The event management system can receive a selection of a desired audience for the event. The event management system can accept the initial event content to be presented during the event and can determine a time for the event. The event management system can perform engagement sampling during the event. The event management system can utilize the selection, the time, and the engagement sampling to optimize the event. The event management system can determine a follow-up action to be performed after the event.

Abstract: A computer vision-based system may assist in wire installation. The system may use computer vision techniques to assess the quality of service wire installations. The system may generate text descriptions of the image of service installation work, assessing the quality of the work to facilitate searching and summarization.

Abstract: Aspects of the subject disclosure may include, for example, engaging in first communications between a device and a first user device, the first communications comprising a first visual representation sent from the first user device to the device of first actions performed by a first user; engaging in second communications between the device and a second user device, the second communications comprising a second visual representation sent from the second user device to the device of second actions performed by a second user, the second communications occurring substantially simultaneously with the first communications; making a first determination via machine learning, based at least in part upon the first visual representation, whether performance of a first task by the first user has been completed; making a second determination via the machine learning, based at least in part upon the second visual representation, whether performance of the first task by the second user has been completed; responsive to th

Abstract: An example method, executed by a processing system, includes receiving data from a data source, routing the data to a plurality of different data labelers to label the data, determining that an inflection point associated with an accuracy of the plurality of different data labelers is reached, re-routing additional data from the data source to a machine learning model, and activating the machine learning model to label the additional data.

Abstract: An example method performed by a processing system includes acquiring a set of troubleshooting notes. The set of troubleshooting notes is generated by a human customer support representative in response to a condition that is reported by a customer. The troubleshooting notes are written in natural language. A plurality of predictions for the set of troubleshooting notes is generated. Each prediction of the plurality of predictions indicates a likelihood that a root cause of the condition is a different one of a plurality of predefined root causes, and each prediction of the plurality of predictions is generated using a different binary classifier of a plurality of binary classifiers. At least two of the plurality of predictions are encoded into a single vector which concatenates a plurality of bits, wherein each bit of the plurality of bits represents one prediction of the at least two of the plurality of predictions.