Systems and Methods for Imputation of Transshipment Locations

Abstract

The present disclosure provides systems and methods that impute planned transshipment locations for an itinerary associated with an item of cargo. In particular, according to one aspect of the present disclosure, a supply chain management computing system can obtain itinerary data that describes a planned shipment of an item of cargo from an origin location to a destination location. For example, the itinerary data can identify at least a shipping vehicle planned to transport the item of cargo. The supply chain management computing system can access vehicle location data associated with at least the shipping vehicle and can predict, based at least in part on the itinerary data and the vehicle location data, a transshipment location at which the item of cargo is transferred from the shipping vehicle to a different shipping vehicle.

What is claimed is: 
     
         1 . A computer-implemented method of imputing transshipment locations, the method comprising:
 training, by a computing system comprising one or more computing devices, a machine learning model using a set of training data indicating a set of historical outcomes of a set previous shipments;   obtaining, by the computing system, itinerary data that identifies (i) a planned shipment of an item of cargo from an origin location by a shipping vehicle without identifying a transshipment location for the item of cargo, and (ii) a destination location for the planned shipment wherein the transshipment location is where the item of cargo is to be discharged from the shipping vehicle and loaded onto a different shipping vehicle;   accessing, by the computing system, vehicle location data associated with the shipping vehicle and a set of different shipping vehicles;   analyzing, by the machine learning model, the itinerary data and the vehicle location data to:
 determine that the vehicle location data indicates that a different shipping vehicle of the set of different shipping vehicles will be present at the destination location within a threshold period of time from a currently estimated destination discharge date, 
 determine that a shared destination exists between the shipping vehicle and the different shipping vehicle, and 
 based on determining that the shared destination exists, predict that the shared destination will be the transshipment location at which the item of cargo is to be discharged from the shipping vehicle and loaded onto the different shipping vehicle; 
   inserting, by the computing system, the transshipment location into a data record associated with the planned shipment to produce an updated data record;   obtaining, by the computing system, vehicle schedule data that describes schedules of the shipping vehicle and the set of different shipping vehicles; and   refining, by the computing system using a schedule refinement machine learning model and based at least in part on the vehicle location data, the vehicle schedule data to produce refined vehicle schedule data.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein analyzing, by the machine learning model, the itinerary data and the vehicle location data is further to:
 determine that the vehicle location data indicates that the shipping vehicle will not be present at the destination location within the threshold period of time from the currently estimated destination discharge date.   
     
     
         3 . The computer-implemented method of  claim 1 , wherein the shared destination exists between the shipping vehicle and the different shipping vehicle when the shipping vehicle and the different shipping vehicle are scheduled to visit the shared destination within a threshold amount of time of each other. 
     
     
         4 . The computer-implemented method of  claim 1 , further comprising:
 updating information associated with the item of cargo based on the transshipment location.   
     
     
         5 . The computer-implemented method of  claim 1 , wherein refining the vehicle schedule data comprises:
 refining, by the computing system using the schedule refinement machine learning model and based at least in part on the vehicle location data and data obtained from locations, the vehicle schedule data.   
     
     
         6 . The computer-implemented method of  claim 1 , further comprising:
 prior to analyzing the itinerary data and the vehicle location data:
 obtaining, by the computing system, historical vehicle data that describes historical locations of the shipping vehicle, and 
 refining, by the computing system, the vehicle location data based at least in part on the historical vehicle data to produce refined vehicle location data. 
   
     
     
         7 . The computer-implemented method of  claim 1 , wherein the set of different shipping vehicles is related to the shipping vehicle via shared inclusion within a carrier network. 
     
     
         8 . A system for imputing transshipment locations, comprising:
 a memory storing a machine learning model and a schedule refinement machine learning model; and   one or more processors interfaced with the memory and configured to execute computer-readable instructions to cause the one or more processors to:
 train the machine learning model using a set of training data indicating a set of historical outcomes of a set previous shipments, 
 obtain itinerary data that identifies (i) a planned shipment of an item of cargo from an origin location by a shipping vehicle without identifying a transshipment location for the item of cargo, and (ii) a destination location for the planned shipment wherein the transshipment location is where the item of cargo is to be discharged from the shipping vehicle and loaded onto a different shipping vehicle, 
 access vehicle location data associated with the shipping vehicle and a set of different shipping vehicles, 
 analyze, by the machine learning model, the itinerary data and the vehicle location data to:
 determine that the vehicle location data indicates that a different shipping vehicle of the set of different shipping vehicles will be present at the destination location within a threshold period of time from a currently estimated destination discharge date, 
 determine that a shared destination exists between the shipping vehicle and the different shipping vehicle, and 
 based on determining that the shared destination exists, predict that the shared destination will be the transshipment location at which the item of cargo is to be discharged from the shipping vehicle and loaded onto the different shipping vehicle, 
 
 insert the transshipment location into a data record associated with the planned shipment to produce an updated data record, 
 obtain vehicle schedule data that describes schedules of the shipping vehicle and the set of different shipping vehicles, and 
 refine, by the computing system using the schedule refinement machine learning model and based at least in part on the vehicle location data, the vehicle schedule data to produce refined vehicle schedule data. 
   
     
     
         9 . The system of  claim 8 , wherein to analyze, by the machine learning model, the itinerary data and the vehicle location data is further to:
 determine that the vehicle location data indicates that the shipping vehicle will not be present at the destination location within the threshold period of time from the currently estimated destination discharge date.   
     
     
         10 . The system of  claim 8 , wherein the shared destination exists between the shipping vehicle and the different shipping vehicle when the shipping vehicle and the different shipping vehicle are scheduled to visit the shared destination within a threshold amount of time of each other. 
     
     
         11 . The system of  claim 8 , wherein the one or more processors is configured to execute the computer-readable instructions to further cause the one or more processors to:
 update information associated with the item of cargo based on the transshipment location.   
     
     
         12 . The system of  claim 8 , wherein to refine the vehicle schedule data, the one or more processors is configured to:
 refine, using the schedule refinement machine learning model and based at least in part on the vehicle location data and data obtained from locations, the vehicle schedule data.   
     
     
         13 . The system of  claim 8 , wherein the one or more processors is configured to execute the computer-readable instructions to further cause the one or more processors to:
 prior to analyzing the itinerary data and the vehicle location data:
 obtain historical vehicle data that describes historical locations of the shipping vehicle, and 
 refine the vehicle location data based at least in part on the historical vehicle data to produce refined vehicle location data. 
   
     
     
         14 . The system of  claim 8 , wherein the set of different shipping vehicles is related to the shipping vehicle via shared inclusion within a carrier network. 
     
     
         15 . A non-transitory computer-readable storage medium configured to store instructions executable by one or more processors, the instructions comprising:
 instructions for training a machine learning model using a set of training data indicating a set of historical outcomes of a set previous shipments;   instructions for obtaining itinerary data that identifies (i) a planned shipment of an item of cargo from an origin location by a shipping vehicle without identifying a transshipment location for the item of cargo, and (ii) a destination location for the planned shipment wherein the transshipment location is where the item of cargo is to be discharged from the shipping vehicle and loaded onto a different shipping vehicle;   instructions for accessing vehicle location data associated with the shipping vehicle and a set of different shipping vehicles;   instructions for analyzing the itinerary data and the vehicle location data to:
 determine that the vehicle location data indicates that a different shipping vehicle of the set of different shipping vehicles will be present at the destination location within a threshold period of time from a currently estimated destination discharge date, 
 determine that a shared destination exists between the shipping vehicle and the different shipping vehicle, and 
 based on determining that the shared destination exists, predict that the shared destination will be the transshipment location at which the item of cargo is to be discharged from the shipping vehicle and loaded onto the different shipping vehicle; 
   instructions for inserting the transshipment location into a data record associated with the planned shipment to produce an updated data record;   instructions for obtaining vehicle schedule data that describes schedules of the shipping vehicle and the set of different shipping vehicles; and   instructions for refining, using a schedule refinement machine learning model and based at least in part on the vehicle location data, the vehicle schedule data to produce refined vehicle schedule data.   
     
     
         16 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions for analyzing, by the machine learning model, the itinerary data and the vehicle location data is further to:
 determine that the vehicle location data indicates that the shipping vehicle will not be present at the destination location within the threshold period of time from the currently estimated destination discharge date.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 15 , wherein the shared destination exists between the shipping vehicle and the different shipping vehicle when the shipping vehicle and the different shipping vehicle are scheduled to visit the shared destination within a threshold amount of time of each other. 
     
     
         18 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions further comprise:
 instructions for updating information associated with the item of cargo based on the transshipment location.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions for refining the vehicle schedule data comprise:
 instructions for refining, using the schedule refinement machine learning model and based at least in part on the vehicle location data and data obtained from locations, the vehicle schedule data.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions further comprise:
 instructions for, prior to analyzing the itinerary data and the vehicle location data:
 obtaining, by the computing system, historical vehicle data that describes historical locations of the shipping vehicle, and 
 refining, by the computing system, the vehicle location data based at least in part on the historical vehicle data to produce refined vehicle location data.