Using a trained machine-learning model to facilitate picking items in a warehouse

A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to perform steps comprising:

• collecting, via a sensor-computing system installed on a moveable cart in a location of a source, source data including images and videos of a set of places in the location of the source;
• uploading, via a network and from the sensor-computing system, the collected source data;
• receiving, via the network and from at least one of one or more devices associated with one or more pickers, a device a associated with the source, one or more devices associated with one or more users of a computer system, or a computing system associated with a physical receptacle utilized in the location of the source, data with information about an item including an indication that the item cannot be found in the location of the source;
• obtaining, from the collected source data and responsive to the indication, a source signal representing an inventory evidence about the item in relation to the location of the source;
• accessing a findability prediction model of the computer system, wherein the findability prediction model is a machine-learning model trained to predict a findability of the item in the location of the source representing a likelihood of not finding the item given that the item is actually available in the location of the source;
• applying the findability prediction model to the received data and the source signal to generate a findability score for the item that is indicative of the findability of the item;
• generating, using the findability score, one or more action signals for triggering one or more automated actions to enhance the findability of the item;
• and
• communicating, via the network, the one or more action signals to at least one of a device associated with a picker in the location of the source, the device associated with the source, or a device associated with a user of the computer system, the one or more action signals further prompting one or more actions by at least one of the picker, the source, or the user in relation to the item.

A computer system comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium having instructions that, when executed by the processor, cause the computer system to perform steps comprising:
• collecting, via a sensor-computing system installed on a moveable cart in a location of a source, source data including images and videos of a set of places in the location of the source;
• uploading, via a network and from the sensor-computing system, the collected source data;
• receiving, via the network and from at least one of one or more devices associated with one or more pickers, a device associated with the source, one or more devices associated with one or more users of the computer system, or a computing system associated with a physical receptacle utilized in the location of the source, data with information about an item including an indication that the item cannot be found in the location of the source;
• obtaining, from the collected source data and responsive to the indication, a source signal representing an inventory evidence about the item in relation to the location of the source;
• accessing a findability prediction model of the computer system, wherein the findability prediction model is a machine-learning model trained to predict a findability of the item in the location of the source representing a likelihood of not finding the item given that the item is actually available in the location of the source;
• applying the findability prediction model to the received data and the source signal to generate a findability score for the item that is indicative of the findability of the item;
• generating, using the findability score, one or more action signals for triggering one or more automated actions to enhance the findability of the item;
• and
• communicating, via the network, the one or more action signals to at least one of a device associated with a picker in the location of the source, the device associated with the source, or a device associated with a user of the computer system, the one or more action signals further prompting one or more actions by at least one of the picker, the source, or the user in relation to the item.