Systems and methods for ai-based detection of delays in a shipping network

Abstract

Embodiments provide systems, methods and computer program products for artificial intelligence-based detection of delays in a shipping network that include training a machine learning model using a training set of in-flight snapshots to infer, based on a set of predictive features, whether a shipment having an estimated delivery dates will meet the estimated delivery date. The machine learning model represents a set of shipment statuses, a set of timings relative estimated delivery dates, and a set of shipment outcomes of the plurality of historical shipments.

What is claimed: 
     
         1 . A computer-implemented method of assessing in-progress shipments, the method comprising:
 accessing, by at least one processor, a set of records representing a plurality of shipments, each shipment in the plurality of shipments having a training set of multiple in-flight snapshots, wherein each in-flight snapshot in the training set of multiple in-flight snapshots represents a record of that shipment at a respective snapshot time while that shipment was in-flight and before that shipment was delivered;   for each training set of multiple in-flight snapshots respectively corresponding to the plurality of shipments:
 extracting, by the at least one processor, a set of features from that training set of multiple in-flight snapshots, and 
 generating, by the at least one processor, a feature vector based on the set of features that was extracted; 
   training, by the at least one processor, a machine learning model using the feature vectors that were respectively generated for the training sets of multiple in-flight snapshots;   accessing, by the at least one processor, shipment information for an in-progress shipment, the shipment information comprising a status and an estimated delivery date for the in-progress shipment; and   analyzing, by the at least one processor using the machine learning model, the shipment information for the in-progress shipment to assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein accessing the set of records comprises:
 accessing, by the at least one processor, the set of records representing a plurality of historical shipments.   
     
     
         3 . The computer-implemented method of  claim 1 , wherein analyzing the shipment information for the in-progress shipment comprises:
 analyzing, by the at least one processor using the machine learning model, the shipment information for the in-progress shipment to determine a probability of whether the in-progress shipment will be delayed.   
     
     
         4 . The computer-implemented method of  claim 1 , further comprising:
 accessing, by the at least one processor, additional shipment information for the in-progress shipment; and   analyzing, by the at least one processor using the machine learning model, the additional shipment information for the in-progress shipment to further assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         5 . The computer-implemented method of  claim 1 , further comprising:
 extracting, by the at least one processor from the shipment information for the in-progress shipment, a set of additional features for the in-progress shipment; and   generating, by the at least one processor, an additional feature vector based on the set of additional features for the in-progress shipment.   
     
     
         6 . The computer-implemented method of  claim 5 , wherein analyzing the shipment information for the in-progress shipment comprises:
 analyzing, by the at least one processor using the machine learning model, the additional feature vector to assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         7 . The computer-implemented method of  claim 1 , further comprising:
 storing, in a database indexed for an application, information indicating whether the delivery of the in-progress shipment will be on-time or delayed.   
     
     
         8 . A system for assessing in-progress shipments, comprising:
 a memory storing a set of computer-executable instructions; and   at least one processor interfaced with the memory and configured to execute the set of computer-executable instructions to cause the at least one processor to:
 access a set of records representing a plurality of shipments, each shipment in the plurality of shipments having a training set of multiple in-flight snapshots, wherein each in-flight snapshot in the training set of multiple in-flight snapshots represents a record of that shipment at a respective snapshot time while that shipment was in-flight and before that shipment was delivered, 
 for each training set of multiple in-flight snapshots respectively corresponding to the plurality of shipments:
 extract a set of features from that training set of multiple in-flight snapshots, and 
 generate a feature vector based on the set of features that was extracted, 
 
 train a machine learning model using the feature vectors that were respectively generated for the training sets of multiple in-flight snapshots, 
 access shipment information for an in-progress shipment, the shipment information comprising a status and an estimated delivery date for the in-progress shipment, and 
 analyze, using the machine learning model, the shipment information for the in-progress shipment to assess whether delivery of the in-progress shipment will be on-time or delayed. 
   
     
     
         9 . The system of  claim 8 , wherein the set of records represents a plurality of historical shipments. 
     
     
         10 . The system of  claim 8 , wherein to analyze the shipment information for the in-progress shipment, the at least one processor is configured to:
 analyze, using the machine learning model, the shipment information for the in-progress shipment to determine a probability of whether the in-progress shipment will be delayed.   
     
     
         11 . The system of  claim 8 , wherein the at least one processor is configured to execute the set of computer-executable instructions to further cause the at least one processor to:
 access additional shipment information for the in-progress shipment, and   analyze, using the machine learning model, the additional shipment information for the in-progress shipment to further assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         12 . The system of  claim 8 , wherein the at least one processor is configured to execute the set of computer-executable instructions to further cause the at least one processor to:
 extract, from the shipment information for the in-progress shipment, a set of additional features for the in-progress shipment, and   generate an additional feature vector based on the set of additional features for the in-progress shipment.   
     
     
         13 . The system of  claim 12 , wherein to analyze the shipment information for the in-progress shipment, the at least one processor is configured to:
 analyze, using the machine learning model, the additional feature vector to assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         14 . The system of  claim 8 , further comprising:
 a database indexed for an application;   
       wherein the at least one processor is configured to execute the set of computer-executable instructions to further cause the at least one processor to:
 store, in the database indexed for the application, information indicating whether the delivery of the in-progress shipment will be on-time or delayed. 
 
     
     
         15 . A non-transitory computer-readable storage medium configured to store instructions executable by one or more processors, the instructions comprising:
 instructions for accessing a set of records representing a plurality of shipments, each shipment in the plurality of shipments having a training set of multiple in-flight snapshots, wherein each in-flight snapshot in the training set of multiple in-flight snapshots represents a record of that shipment at a respective snapshot time while that shipment was in-flight and before that shipment was delivered;   for each training set of multiple in-flight snapshots respectively corresponding to the plurality of shipments:
 instructions for extracting a set of features from that training set of multiple in-flight snapshots, and 
 instructions for generating a feature vector based on the set of features that was extracted; 
   instructions for training a machine learning model using the feature vectors that were respectively generated for the training sets of multiple in-flight snapshots;   instructions for accessing shipment information for an in-progress shipment, the shipment information comprising a status and an estimated delivery date for the in-progress shipment; and   instructions for analyzing, using the machine learning model, the shipment information for the in-progress shipment to assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         16 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions for analyzing the shipment information for the in-progress shipment comprise:
 instructions for analyzing, using the machine learning model, the shipment information for the in-progress shipment to determine a probability of whether the in-progress shipment will be delayed.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions further comprise:
 instructions for accessing additional shipment information for the in-progress shipment; and   instructions for analyzing, using the machine learning model, the additional shipment information for the in-progress shipment to further assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions further comprise:
 instructions for extracting, from the shipment information for the in-progress shipment, a set of additional features for the in-progress shipment; and   instructions for generating an additional feature vector based on the set of additional features for the in-progress shipment.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 18 , wherein the instructions for analyzing the shipment information for the in-progress shipment comprise:
 instructions for analyzing, using the machine learning model, the additional feature vector to assess whether delivery of the in-progress shipment will be on-time or delayed.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 15 , wherein the instructions further comprise:
 instructions for storing, in a database indexed for an application, information indicating whether the delivery of the in-progress shipment will be on-time or delayed.