Predicting downstream schedule effects of user task assignments

A method comprising:

• training a machine learning model to predict downstream effects of assigning tasks to users, the training comprising:
• obtaining training datasets, each training dataset comprising:
• historical task schedule data describing tasks performed at work centers by users;
• historical user data of users performing the tasks at the work centers, the historical user data including:
• historical user qualifications, historical work history data, historical task completion success rates, and historical time to complete the tasks;
• applying the training datasets to the machine learning model to generate an initial set of predictions;
• comparing the initial set of predictions to labels;
• and
• retraining the machine learning model to adjust parameters of the machine learning model based on differences between the initial set of predictions and the labels;
• identifying, by a work environment management engine, a first task corresponding to a first set of task parameters, the first set of task parameters including at least:
• a piece of equipment associated with performance of the first task and a first set of user qualifications recommended for performing the first task;
• comparing, by the work environment management engine, the first set of user qualifications to a plurality of sets of user qualifications corresponding to a plurality of users;
• responsive to comparing the first set of user qualifications to the plurality of sets of user qualifications corresponding to the plurality of users:
• identifying, by the work environment management engine, a first user with user qualifications that match the first set of user qualifications recommended for the first task;
• retrieving, by the work environment management engine, first task performance information for the first user, the first task performance information comprising at least one of (a) scheduling information, and (b) historical task-completion information for the first user;
• based on the first task performance information:
• generating, by the work environment management engine, a first candidate task schedule for a first workstation that includes assignment of the first task to the first user at the first workstation;
• and
• applying, by the work environment management engine, the machine learning model to the first candidate task schedule to predict a first downstream effect of assigning the first task to the first workstation, wherein the first downstream effect comprises an effect on the performance of one or more tasks in a second task schedule, wherein the first downstream effect comprises a first modification to the second task schedule, and wherein predicting the first downstream effect comprises predicting, based on the assignment of the first task to the first user at the first workstation, a change in a completion time of one or more tasks assigned to a second workstation that is different from the first workstation;
• and
• responsive to predicting the first downstream effect of assigning the first task to the first workstation:
• determining, by the work environment management engine, if the performance of the one or more tasks in the second task schedule meets a performance threshold;
• and
• based on determining the performance of the one or more tasks in the second task schedule meets the performance threshold:
• transmitting instructions to a first workstation computing device to modify a task queue of the first workstation to include the first task,
• wherein the first workstation computing device presents the first task for execution at the first workstation based on detecting completion of a preceding task in the task queue.

A system comprising:

• one or more processors;
• and
• memory storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
• training a machine learning model to predict downstream effects of assigning tasks to users, the training comprising:
• obtaining training datasets, each training dataset comprising:
• historical task schedule data describing tasks performed at work centers by users;
• historical user data of users performing the tasks at the work centers, the historical user data including:
• historical user qualifications, historical work history data, historical task completion success rates, and historical time to complete the tasks;
• applying the training datasets to the machine learning model to generate an initial set of predictions;
• comparing the initial set of predictions to labels;
• and
• retraining the machine learning model to adjust parameters of the machine learning model based on differences between the initial set of predictions and the labels;
• identifying, by a work environment management engine, a first task corresponding to a first set of task parameters, the first set of task parameters including at least:
• a piece of equipment associated with performance of the first task and a first set of user qualifications recommended for performing the first task;
• comparing, by the work environment management engine, the first set of user qualifications to a plurality of sets of user qualifications corresponding to a plurality of users;
• responsive to comparing the first set of user qualifications to the plurality of sets of user qualifications corresponding to the plurality of users:
• identifying, by the work environment management engine, a first user with user qualifications that match the first set of user qualifications recommended for the first task;
• retrieving, by the work environment management engine, first task performance information for the first user, the first task performance information comprising at least one of (a) scheduling information, and (b) historical task-completion information for the first user;
• based on the first task performance information:
• generating, by the work environment management engine, a first candidate task schedule for a first workstation that includes assignment of the first task to the first user at the first workstation;
• and
• applying, by the work environment management engine, the machine learning model to the first candidate task schedule to predict a first downstream effect of assigning the first task to the first workstation, wherein the first downstream effect comprises an effect on the performance of one or more tasks in a second task schedule, wherein the first downstream effect comprises a first modification to the second task schedule, and wherein predicting the first downstream effect comprises predicting, based on the assignment of the first task to the first user at the first workstation, a change in a completion time of one or more tasks assigned to a second workstation that is different from the first workstation;
• and
• responsive to predicting the first downstream effect of assigning the first task to the first workstation:
• determining, by the work environment management engine, if the performance of the one or more tasks in the second task schedule meets a performance threshold;
• and
• based on determining the performance of the one or more tasks in the second task schedule meets the performance threshold:
• transmitting instructions to a first workstation computing device to modify a task queue of the first workstation to include the first task,
• wherein the first workstation computing device presents the first task for execution at the first workstation based on detecting completion of a preceding task in the task queue.