Courier network management

• US 10,133,995 B1
• Filed: 02/19/2015
• Issued: 11/20/2018
• Est. Priority Date: 02/19/2015
• Status: Active Grant

• Current Assignee: DoorDash, Inc.
• Original Assignee: Square Inc (Block, Inc. (f/k/a Square, Inc.))
• Inventors: Reiss, Jesse Lee, Varma, Ajit Kalidindi, Iacono, Jeffrey Frank, Din, Richard David
• Primary Examiner(s): Mansfield, Thomas L
• Application Number:
  US14/625,673
• Time in Patent Office: 1,370 Days
• Field of Search: None
• CPC Class Codes: G06Q 10/063114 Status monitoring or status determination for a person or group
• CPC Class Codes: G06Q 10/083 Shipping
• CPC Class Codes: G06Q 30/0264 based upon schedule
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06Q 50/12 Hotels or restaurants

Abstract

In some examples, a service provider may determine, for a time of day and a day of a week, orders received by individual merchants of a plurality of merchants over a past period of time. The service provider may further determine, for the time of day and day of the week, based at least in part on the orders received over the past period of time, a first merchant predicted to receive an order. Based at least in part on a pickup location of the first merchant, the service provider may send a communication to a first courier device associated with a first courier of a plurality of couriers. For example, the communication may include location information for a recommended location to which the first courier is to move to be in position for picking up an order from the merchant that is predicted to receive the order.

Claims

1. A system enabling crowdsourcing of a plurality of couriers for providing a delivery service, wherein some of the couriers are active for receiving delivery assignments and some of the couriers are inactive, the system comprising:

one or more processors;

one or more communication interfaces coupled to the one or more processors for communicating over one or more networks with a plurality of courier devices associated with a plurality of couriers, a plurality of merchant devices associated with a plurality of merchants, and a plurality of buyer devices associated with a plurality of buyers; and

one or more computer-readable media storing instructions executable by the one or more processors, wherein the instructions program the one or more processors to;

determine, for the plurality of merchants, a respective pickup location associated with each merchant of the plurality of merchants, wherein the merchants are able to provide items for delivery by the couriers to the buyers within a service region;

store past order information for a plurality of past orders received in the past by the plurality of merchants and delivered by the couriers to the buyers;

determine, from the past order information, for an upcoming time period of a day of a week, the past orders received for the items provided by individual merchants of the plurality of merchants during a corresponding past time period of one or more past days;

determine, for the upcoming time period based at least in part on executing a computational model that takes into account the past orders received for items provided by the individual merchants during the corresponding past time period of one or more past days, a first plurality of merchants predicted to receive orders;

determine, for the upcoming time period, based at least in part on executing the computational model that takes into account the past orders received for items provided by the individual merchants during the corresponding past time period of one or more days, predicted order preparation times associated with the orders predicted to be received by the first plurality of merchants;

receive, from a subset of the courier devices, a plurality of respective electronic communications indicating that a subset of respective couriers associated with the subset of courier devices are active and able to receive assignments for delivery jobs;

receive, from the subset of the courier devices, additional respective electronic communications including location information obtained from respective Global Positioning System (GPS) devices associated with each courier device, the location information indicating respective geographic locations of each of the courier devices;

determine, based at least in part on the location information received from the subset of courier devices, respective indicated geographic locations of the subset of courier devices within the service region;

select, from the subset of couriers, based at least in part on the indicated geographic locations of the subset of courier devices, a first plurality of couriers associated with a first plurality of courier devices, respectively;

execute courier management logic to determine respective locations for the first plurality of couriers to move, wherein the courier management logic takes into account;

the time of day and the day of the week,

the pickup locations associated with the first plurality of merchants predicted to receive the order, and

the predicted order preparation times for the orders predicted to be received by the first plurality of merchants, and

send, via the one or more communication interfaces, respective messages to the first plurality of courier devices associated with the first plurality of couriers, the respective messages including an indication of the locations to which the respective couriers of the first plurality of couriers are to move prior to picking up respective items from the first plurality of merchants predicted to receive the orders.

2. The system as recited in claim 1, wherein the computational model includes a trained statistical model trained using the past order information, wherein the instructions further program the one or more processors to:

determine, using the computational model, for the upcoming time period, a number of orders predicted to be received by each of the merchants of the first plurality of merchants predicted to receive orders; and

send the respective messages to at least some of the subset of courier devices to indicate the respective locations to which the associated couriers are to move, wherein a number of the messages is based at least in part on the number of orders predicted to be received by each of the merchants of the first plurality of merchants predicted to receive orders.

3. The system as recited in claim 1, wherein the instructions further program the one or more processors to:

determine, for the upcoming time period, a number of orders predicted to be received by each of the merchants of the first plurality of merchants predicted to receive orders;

compare a number of couriers currently active with a total number of orders predicted to be received, wherein the number of active couriers is determined, at least in part, from the plurality of respective electronic communications received from the subset of courier devices; and

send a communication to at least one courier device associated with at least one inactive courier based at least in part on comparing the number of couriers currently active with the total number of orders predicted to be received, wherein the communication requests the at least one courier become active.

4. The system as recited in claim 1, wherein the instructions further program the one or more processors to use the computational model to determine the first plurality of merchants predicted to receive the orders based at least in part on at least one of:

weather information for weather in the service region;

or

event information for events taking place in the service region.

5. A method enabling crowdsourcing of a plurality of couriers for providing a delivery service, wherein some of the couriers are active for receiving delivery assignments and some of the couriers are inactive, the method comprising:

storing, by one or more processors, past order information for a plurality of past orders received in the past by a plurality of merchants and delivered by a plurality of the couriers;

determining, by the one or more processors, from the past order information, for an upcoming time period of a day of a week, the past orders received for individual merchants of the plurality of merchants during a corresponding past time period of one or more past days;

determining, for the upcoming time period, by the one or more processors, based at least in part on executing at least one of a computational model or first algorithm that takes into account the past orders received for the individual merchants in the past during the corresponding past time period, a plurality of first merchants predicted to receive orders;

receiving, by the one or more processors, from a subset of courier devices of a plurality of courier devices, a plurality of respective electronic communications indicating that a subset of respective couriers associated with the subset of courier devices are active and able to receive assignments for delivery jobs, the respective electronic communications indicating respective geolocations of the subset of courier devices determined by respective Global Positioning System (GPS) devices on the respective subset of courier devices;

determining, based on the electronic communications received from the subset of courier devices, by the one or more processors executing a second algorithm that takes into account the pickup locations of the merchants predicted to receive orders and the indicated respective geolocations of the subset of couriers, a plurality of respective locations to which to reposition a first plurality of the couriers of the subset of couriers; and

sending, by the one or more processors, respective messages to a first plurality of courier devices associated with the first plurality of couriers of the subset of couriers, the respective messages including an indication of the locations to which the first plurality of couriers are to move based at least in part on respective locations associated with the first plurality of merchants predicted to receive the orders.

6. The method as recited in claim 5, wherein determining, for the upcoming time period, the first plurality of merchants predicted to receive orders further comprises executing the computational model, including a statistical model trained using the past order information, to at least partially determine the first plurality of merchants predicted to receive orders.

7. The method as recited in claim 5, further comprising:

determining the plurality of locations to which the first plurality of couriers are to move based at least in part on the indicated locations of the subset of courier devices and based at least in part on a geographic distribution of the pickup locations associated with the first plurality of merchants.

8. The method as recited in claim 5, further comprising:

determining, for the upcoming time period, a total number of orders predicted to be received by the first plurality of merchants;

executing courier management logic for comparing a number of active couriers with the total number of orders predicted to be received, wherein the number of active couriers is determined, at least in part, from the plurality of respective electronic communications received from the subset of courier devices; and

sending, based at least in part on the comparing, a message to a first courier device associated with an inactive courier.

9. The method as recited in claim 8, wherein the sending the message includes sending a request for a current location of the first courier device associated with the inactive courier.

10. The method as recited in claim 9, further comprising:

receiving, from the first courier device, location information obtained from one or more location sensors associated with the first courier device, the location information indicating a current geographic location of the first courier device; and

sending, to the first courier device, based at least in part on the indicated current geographic location of the first courier device, another message indicating a location to which the courier associated with the first courier device is to move, based at least in part on a pickup location associated with one of the merchants predicted to receive an order.

11. The method as recited in claim 5, further comprising:

determining, for the upcoming time period, a number of orders predicted to be received by each merchant of the first plurality of merchants predicted to receive an order; and

sending respective communications to another subset of respective courier devices associated with inactive couriers, wherein a number of the respective communications is based at least in part on the number of orders predicted to be received by the first plurality of merchants predicted to receive orders.

12. The method as recited in claim 5, further comprising:

determining, based at least in part on the orders received for the individual merchants over the past period of time, one or more items predicted to be included in the orders predicted to be received for the first plurality of merchants;

determining, for the one or more items predicted to be included in the orders, respective predicted order preparation times associated with the orders; and

determining the respective locations to which the first plurality of couriers are to move based at least in part on the respective predicted order preparation times.

13. The method as recited in claim 5, further comprising determining the first plurality of merchants predicted to receive the orders based at least in part on at least one of:

weather information for weather in the service region;

or

event information for events taking place in the service region.

14. One or more non-transitory computer-readable media maintaining instructions that, when executed by one or more processors, program the one or more processors to:

determine a plurality of pickup locations within a service region, wherein each pickup location is associated with a respective merchant of a plurality of merchants;

store past order information for a plurality of past orders received in the past by the plurality of merchants and delivered by couriers to buyers;

receive, from a plurality of courier devices, respective electronic communications including location information from respective Global Positioning System (GPS) sensors associated with each courier device, the location information indicating respective geographic locations of each of the courier devices;

determine, based at least in part on the location information from the GPS sensors, respective indicated locations of the plurality of courier devices, wherein the plurality of courier devices are associated with a plurality of respective couriers;

determine, for an upcoming time period based at least in part on executing at least one of a computational model or a first algorithm that takes into account the past orders received for items provided by the respective merchants during one or more corresponding past time periods, a first plurality of merchants predicted to receive orders;

executing a second algorithm to determine, based on the respective indicated locations of the plurality of courier devices and the pickup locations of the first plurality of merchants predicted to receive orders, a plurality of respective locations to which to reposition the plurality of couriers; and

send respective messages to the plurality of courier devices, each respective message including an indication of a respective location to which the associated courier is to move, to distribute the couriers within the service region based at least in part on a geographic distribution of the pickup locations within the service region.

15. The one or more non-transitory computer-readable media as recited in claim 14, wherein the instructions further program the one or more processors to send at least one respective message to at least one of the plurality of courier devices prior to receiving an order for pick up by the courier associated with the at least one courier device.

16. The one or more non-transitory computer-readable media as recited in claim 14, wherein the instructions further program the one or more processors to:

determine, for the upcoming time period, the first plurality of merchants predicted to receive orders by executing the computational model, the computational model including a statistical model trained using the past order information, to at least partially determine the first plurality of merchants predicted to receive orders.

17. The one or more non-transitory computer-readable media as recited in claim 16, wherein the instructions further program the one or more processors to determine the first plurality of merchants predicted to receive the orders based at least in part on at least one of:

weather information for weather in the service region;

or

event information for events taking place in the service region.

18. The one or more non-transitory computer-readable media as recited in claim 16, wherein the instructions further program the one or more processors to:

determine, based at least in part on the orders received for the individual merchants over the past period of time, one or more items predicted to be included in the orders predicted to be received for the first plurality of merchants;

determine for the one or more items predicted to be included in the orders, respective predicted order preparation times associated with the orders; and

determine the respective location to which the plurality of couriers are to move based at least in part on the respective predicted order preparation times.

19. The one or more non-transitory computer-readable media as recited in claim 14, wherein the instructions further program the one or more processors to:

determine, for the upcoming time period, based at least in part on orders received for individual merchants of the plurality of merchants over a past period of time, a predicted total number of orders;

execute courier management logic to compare, for the upcoming time period, a number of active couriers with the total number of orders predicted to be received; and

send, based at least in part on the comparing, a message to a courier device associated with at least one inactive courier.

20. The one or more non-transitory computer-readable media as recited in claim 14, wherein the instructions further program the one or more processors to:

receive, from a buyer, an order for one or more items to be prepared by a first merchant of the first plurality of merchants;

based on the received order, send an offer to a first courier device associated with a first courier, the offer including a courier payment amount for delivery of the one or more items and a time threshold for acceptance of the offer; and

based at least in part on expiration of the time threshold, send the offer to a second courier device associated with a second courier.

21. A system enabling crowdsourcing of a plurality of couriers for providing a delivery service, wherein some of the couriers are active for receiving delivery assignments and some of the couriers are inactive, the system comprising:

one or more processors; and

one or more computer-readable media storing instructions executable by the one or more processors, wherein the instructions program the one or more processors to;

store past order information for a plurality of past orders received in the past by a plurality of merchants and delivered by the couriers to buyers;

determine, from past order information for an upcoming time period, past orders received for individual merchants of the plurality of merchants over a past period of time corresponding to the upcoming time period;

determine, for the upcoming time period, based at least in part on executing at least one of a computational model or first algorithm that takes into account the past orders received for the individual merchants over the past period of time, a predicted total number of orders predicted to be received over the upcoming time period;

execute courier management logic to compare, for the upcoming time period, a number of active couriers with the total number of orders predicted to be received; and

send, based at least in part on the comparing indicating an insufficient number of couriers, a message to a first courier device associated with at least one inactive first courier.

22. The system as recited in claim 21, wherein the instructions further program the one or more processors to:

send, with the message, a request for a current location of the first courier device associated with the at least one inactive first courier.

23. The system as recited in claim 22, wherein the instructions further program the one or more processors to:

determine, for the upcoming time period, based at least in part on executing the at least one of the computational model or the first algorithm that takes into account the past orders received for the individual merchants over the past period of time, a first plurality of merchants predicted to receive orders for the upcoming time period; and

send, to the first courier device, based at least in part on the current location of the first courier device, another message including an indicated location to which the first courier is to move, wherein the indicated location is based at least in part on a pickup location associated with a first one of the merchants predicted to receive the orders.

24. The system as recited in claim 21, wherein the instructions further program the one or more processors to:

prior to sending the message to the first courier device, receive, from a subset of courier devices of a plurality of courier devices, respective electronic communications indicating that a subset of respective couriers associated with the subset of courier devices are active and able to receive assignments for delivery jobs; and

send, to a second courier device included in the subset of courier devices and associated with an active courier, based at least in part on a current location of the second courier device, another message indicting that the active courier is being made inactive.