Continuous delivery
Implementations include determining a set of routes for delivery of assets within a delivery network based on realized and forecasted demand for a period, during at least partial execution of the set of routes, receiving real-time data representative of delivery of assets, and updated demand forecasts, determining, by an optimization controller, a time-to-trigger, and a cut-off time, and an updated demand forecast, the time-to-trigger defining an interval, at which the set of routes for delivery of assets is to be reoptimized, in response to the time-to-trigger being achieved, re-optimizing, by a route optimization module of the continuous delivery platform, the set of routes to provide a revised set of routes, and conveying at least one route of the revised set of routes to a delivery personnel, the at least one route being different from any route in the set of routes, and being executed during the period.
1. A computer-implemented method executed by one or more processors for selective optimization of delivery routes using a continuous delivery platform, the method comprising:
determining a set of routes for delivery of assets within a delivery network based on demand forecast and realized demand for a period, the demand forecast being indicative of prediction of demand for delivery of assets within the period;
during at least partial execution of the set of routes, receiving real-time data representative of delivery of assets, and updated demand forecast;
determining, by an optimization controller of the continuous delivery platform, one or more of a time-to-trigger, and a cut-off time at least partially based on the real-time data, and the updated demand forecast, the time-to-trigger defining an interval, at which the set of routes for delivery of assets is to be reoptimized;
in response to the time-to-trigger being achieved, re-optimizing, by a route optimization module of the continuous delivery platform, the set of routes to provide a revised set of routes; and
conveying at least one route of the revised set of routes to a delivery personnel, the at least one route being different from any route in the set of routes, and being executed during the period.
2. The method of claim 1 , wherein routes are defined as a plurality of dynamic nodes, at least one node changing between a route in the set of routes, and a route in the revised set of routes.
3. The method of claim 1 , wherein the time-to-trigger is intermittently updated during the period, and at least one subsequent re-optimization of routes is executed based on an updated time-to-trigger.
4. The method of claim 1 , wherein the time-to-trigger is at least partially determined by on incremental learning based on the demand forecast, and actual conditions within the delivery network.
5. The method of claim 4 , wherein the incremental learning at least partially comprises one of retraining a predictive model based on a most-recent dataset available, and retraining the predictive model based on a full dataset including historical data, and the most-recent dataset.
6. The method of claim 1 , wherein at least a portion of the real-time data is received from a mobile computing device of the deliver personnel, and the at least one route of the revised set of routes is conveyed to the mobile computing device.
7. The method of claim 1 , wherein the cut-off time defines a time during the period, after which re-optimization of the routes is not executed.
8. The method of claim 1 , wherein the at least one route comprises one of a new route, and a modified route.
9. The method of claim 1 , wherein the set of routes is determined based on historical asset demand data.
10. The method of claim 1 , wherein determining the set of routes includes predicting one or more route destinations.
11. The method of claim 1 , wherein the real-time data is representative of a location of a delivery vehicle and/or of a location of an asset.
12. The method of claim 1 , further comprising optimizing a time for delivery of an asset on one or more routes of the set of routes.
13. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for selective optimization of delivery routes using a continuous delivery platform, the operations comprising:
determining a set of routes for delivery of assets within a delivery network based on demand forecast and realized demand for a period, the demand forecast being indicative of prediction of demand for delivery of assets within the period;
during at least partial execution of the set of routes, receiving real-time data representative of delivery of assets, and updated demand forecast;
determining, by an optimization controller of the continuous delivery platform, one or more of a time-to-trigger, and a cut-off time at least partially based on the real-time data, and the updated demand forecast, the time-to-trigger defining an interval, at which the set of routes for delivery of assets is to be reoptimized;
in response to the time-to-trigger being achieved, re-optimizing, by a route optimization module of the continuous delivery platform, the set of routes to provide a revised set of routes; and
conveying at least one route of the revised set of routes to a delivery personnel, the at least one route being different from any route in the set of routes, and being executed during the period.
14. The computer-readable storage medium of claim 13 , wherein routes are defined as a plurality of dynamic nodes, at least one node changing between a route in the set of routes, and a route in the revised set of routes.
15. The computer-readable storage medium of claim 13 , wherein the time-to-trigger is intermittently updated during the period, and at least one subsequent re-optimization of routes is executed based on an updated time-to-trigger.
16. The computer-readable storage medium of claim 13 , wherein the time-to-trigger is at least partially determined by on incremental learning based on the demand forecast, and actual conditions within the delivery network.
17. The computer-readable storage medium of claim 16 , wherein the incremental learning at least partially comprises one of retraining a predictive model based on a most-recent dataset available, and retraining the predictive model based on a full dataset including historical data, and the most-recent dataset.
18. The computer-readable storage medium of claim 13 , wherein at least a portion of the real-time data is received from a mobile computing device of the deliver personnel, and the at least one route of the revised set of routes is conveyed to the mobile computing device.
19. The computer-readable storage medium of claim 13 , wherein the cut-off time defines a time during the period, after which re-optimization of the routes is not executed.
20. The computer-readable storage medium of claim 13 , wherein the at least one route comprises one of a new route, and a modified route.
21. The computer-readable storage medium of claim 13 , wherein the set of routes is determined based on historical asset demand data.
22. The computer-readable storage medium of claim 13 , wherein determining the set of routes includes predicting one or more route destinations.
23. The computer-readable storage medium of claim 13 , wherein the real-time data is representative of a location of a delivery vehicle and/or of a location of an asset.
24. The computer-readable storage medium of claim 13 , wherein operations further comprise optimizing a time for delivery of an asset on one or more routes of the set of routes.
25. A system, comprising:
one or more processors; and
a computer-readable storage device coupled to the one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for selective optimization of delivery routes using a continuous delivery platform, the operations comprising:
determining a set of routes for delivery of assets within a delivery network based on demand forecast and realized demand for a period, the demand forecast being indicative of prediction of demand for delivery of assets within the period;
during at least partial execution of the set of routes, receiving real-time data representative of delivery of assets, and updated demand forecast;
determining, by an optimization controller of the continuous delivery platform, one or more of a time-to-trigger, and a cut-off time at least partially based on the real-time data, and the updated demand forecast, the time-to-trigger defining an interval, at which the set of routes for delivery of assets is to be reoptimized;
in response to the time-to-trigger being achieved, re-optimizing, by a route optimization module of the continuous delivery platform, the set of routes to provide a revised set of routes; and
conveying at least one route of the revised set of routes to a delivery personnel, the at least one route being different from any route in the set of routes, and being executed during the period.
26. The system of claim 25 , wherein routes are defined as a plurality of dynamic nodes, at least one node changing between a route in the set of routes, and a route in the revised set of routes.
27. The system of claim 25 , wherein the time-to-trigger is intermittently updated during the period, and at least one subsequent re-optimization of routes is executed based on an updated time-to-trigger.
28. The system of claim 25 , wherein the time-to-trigger is at least partially determined by on incremental learning based on the demand forecast, and actual conditions within the delivery network.
29. The system of claim 28 , wherein the incremental learning at least partially comprises one of retraining a predictive model based on a most-recent dataset available, and retraining the predictive model based on a full dataset including historical data, and the most-recent dataset.
30. The system of claim 25 , wherein at least a portion of the real-time data is received from a mobile computing device of the deliver personnel, and the at least one route of the revised set of routes is conveyed to the mobile computing device.
31. The system of claim 25 , wherein the cut-off time defines a time during the period, after which re-optimization of the routes is not executed.
32. The system of claim 25 , wherein the at least one route comprises one of a new route, and a modified route.
33. The system of claim 25 , wherein the set of routes is determined based on historical asset demand data.
34. The system of claim 25 , wherein determining the set of routes includes predicting one or more route destinations.
35. The system of claim 25 , wherein the real-time data is representative of a location of a delivery vehicle and/or of a location of an asset.
36. The system of claim 25 , wherein operations further comprise optimizing a time for delivery of an asset on one or more routes of the set of routes.