Updating machine learning systems using previous output data

A method comprising:

• accessing image data acquired at a facility;
• determining, based on the image data, one or more possible item identifiers associated with an event at the facility, the event involving a first user handling an item;
• determining a confidence level associated with the one or more possible item identifiers is less than a threshold amount;
• based on the determining that the confidence level associated with the one or more possible item identifiers is less than the threshold amount, generating inquiry data associated with a selection of one of the one or more possible item identifiers associated with the event wherein the inquiry data comprises:
• at least a portion of the image data, and
• the one or more possible item identifiers;
• sending the inquiry data to one or more devices associated with one or more second users:
• causing one or more user interfaces to be presented to the one or more second users, the one or more user interfaces including the inquiry data;
• accessing response data, responsive to the inquiry data, the response data associated with the selection of the one of the one or more possible item identifiers;
• generating output data based on at least a portion of the response data;
• designating the image data and the output data as training data;
• and
• processing the training data using a machine learning system.

A system comprising:

• a camera;
• a memory storing computer-executable instructions;
• and
• a hardware processor configured to execute the computer-executable instructions to:
• access first image data acquired by the camera;
• determine an event based on the first image data, the event involving a first user handling an item;
• determine one or more possible item identifiers of the item handled by the first user;
• determine a confidence level associated with each of the one or more possible item identifiers is less than a threshold amount;
• based on determining that the confidence level associated with the each of the one or more possible item identifiers is less than the threshold amount, generate inquiry data associated with a selection of one of the one or more possible item identifiers, wherein the inquiry data comprises:
• at least a portion of the first image data, and
• one or more of the one or more possible item identifiers associated with the event;
• send the inquiry data to a device associated with a second user;
• cause a user interface to be presented to the second user, the user interface including the inquiry data;
• receive, responsive to the inquiry data, second data indicative of the selection of the one of the one or more possible item identifiers;
• generate third data based on the second data;
• designate the first image data and at least a portion of the third data as fourth data;
• and
• process the fourth data using a machine learning system.