Methods and systems for order processing

Patent metadata

Field	Value
Publication number	US-10657581-B2
Application number	US-201615547528-A
Country	US
Kind code	B2
Filing date	Jan 29, 2016
Priority date	Feb 2, 2015
Publication date	May 19, 2020
Grant date	May 19, 2020

Abstract

The present disclosure discloses an order allocation method. The method may include: receiving orders and extracting order information; extracting service provider information and obtaining features of service providers; determining whether the order information matches the features of the service providers, or determining whether the features of the service providers satisfy a preset condition to generate a determination result; ranking the service providers based on the determination result; generating orders to be allocated; and allocating the orders to be allocated to the service providers based on the ranking. The present disclosure also discloses an order allocation system that can perform the method above.

First claim

We claim:

1. A system for operating an online transportation platform to interact with service receivers and service providers through order processing, comprising:
at least one storage medium including a set of instructions; and
logic circuits connected to the at least one storage medium, wherein during operation, the logic circuits load the set of instructions and:
obtain electronic signals from a bus, the electronic signals encoding orders from terminals of the service receivers via a network;
extract order information based on the orders;
extract service provider information;
obtain features of the service providers using one or more trained machine learning models operating in real time on the online transportation platform, wherein each of the service providers is associated with a vehicle, the features of the service providers include characteristics of responding to orders, and the characteristics of responding to orders of each of the service providers indicate characteristics of change with time of probabilities that the service provider responds to the orders;
determine a result as to whether the order information matches the features of the service providers or whether the features of the service providers satisfy a preset condition;
rank the service providers based on the result;
generate orders to be allocated; and
send out, via the network, electronic signals encoding the orders to be allocated to terminals of the service providers based on the ranking.

2. The system of claim 1 , wherein the order information includes a time point, a time interval, a location, and a region.

3. The system of claim 1 , wherein the features of the service providers further include an order similarity, a preference rate, a failure rate, and a response time.

4. The system of claim 3 , wherein the order similarity includes a cosine similarity between a historical order and a current order.

5. The system of claim 3 , wherein the preference rate includes a preferential region and a preferential time interval.

6. The system of claim 3 , wherein the logic circuits further:
obtain the preference rate from the service provider or determine the preference rate by the at least one processor.

7. The system of claim 3 , wherein the logic circuits further:
send out electronic signals to access the at least one storage medium to obtain a longitude-latitude coordinate point corresponding to a destination of the order to be allocated;
determine a distance Az between the longitude-latitude coordinate point of the destination of the order to be allocated and a center of a preferential destination region of the service provider;
determine a preference rate L of the service provider for the destination of the order to be allocated based on the distance Az and a covering radius d of the preferential destination region of the service provider, wherein: L=Σ1/(1+e A z -d ).

8. The system of claim 3 , wherein to obtain the failure rate, the logic circuits further:
determine the failure rate with a formula as:
T x =Σ i=0 k C n k *p k *(1− p ) n-k ,

wherein Tx represents the failure rate, k represents a number of orders that the service provider x has failed to complete among n orders allocated to the service provider, C n k represents a number of combinations of selecting k from n, p represents an average failure rate.

9. The system of claim 3 , wherein the logic circuits further:
determine candidate requests from the service providers based on the response times; and
select one request for processing from the candidate requests.

10. The system of claim 1 , wherein the logic circuits further:
determine a geographic region;
determine an order group and a service provider group based on the geographic region;
analyze the order group and the service provider group to determine a completion rate, a success rate for responding to orders, and a receiving-responding rate for orders;
determine a weighted sum of the completion rate, the success rate for responding to orders, and the receiving-responding rate for orders; and
determine a mode for allocating orders based on the weighted sum.

11. A method for operating an online transportation platform to interact with service receivers and service providers through order processing, implemented on a machine having at least one processor and at least one storage device, the method comprising:
receiving, by the at least one processor, orders from terminals of service receivers via a network;
extracting; by the at least one processor, order information based on the orders;
extracting, by the at least one processor, service provider information;
obtaining, by the at least one processor, features of service providers using one or more trained machine learning models operating in real time on the online transportation platform, wherein each of the service providers is associated with a vehicle, the features of the service providers include characteristics of responding to orders, and the characteristics of responding to orders of each of the service providers indicate characteristics of change with time of probabilities that the service provider responds to the orders;
determining, by the at least one processor, a result as to whether the order information matches the features of the service providers or whether the features of the service providers satisfy a preset condition;
ranking, by the at least one processor, the service providers based on the result;
generating, by the at least one processor, orders to be allocated; and
allocating, by the at least one processor via the network, the orders to be allocated to terminals of the service providers based on the ranking.

12. The method for order processing of claim 11 , wherein the order information includes a time point, a time interval, a location, and a region.

13. The method for order processing of claim 11 , wherein the features of the service providers further include an order similarity, a preference rate, a failure rate, and a response time.

14. The method for order processing of claim 13 , wherein the order similarity includes a cosine similarity between a historical order and a current order.

15. The method for order processing of claim 13 , wherein the preference rate includes a preferential region and a preferential time interval.

16. The method for order processing of claim 13 , further comprising:
obtaining, by the at least one processor, the preference rate from the service provider; or
determining, by the at least one processor, the preference rate.

17. The method for order processing of claim 13 , further comprising:
obtaining, by the at least one processor, a longitude-latitude coordinate point corresponding to a destination of the order to be allocated;
determining, by the at least one processor, a distance Az between the longitude-latitude coordinate point of the destination of the order to be allocated and a center of a preferential destination region of the service provider;
determining, by the at least one processor, a preference rate L of the service provider for the destination of the order to be allocated based on the distance Az and a covering radius d of the preferential destination region of the service provider, wherein: L=Σ1/(1+e A z -d ).

18. The method for order processing of claim 13 , wherein the obtaining of the failure rate includes determining the failure rate with a formula as:
T x =Σ i=0 k C n k *p k *(1− p ) n-k ,

wherein Tx represents the failure rate

Assignees

• Beijing Didi Infinity Technology & Dev Co Ltd

Inventors

• Zhang Lingyu
• Sun Mingcong
• Cui Wei
• Qin Kaijie
• Hu Tao
• Hu Zhilin
• Lu Haiyang
• Bao Xiangxin

Classifications

• G06Q10/02

  Reservations, e.g. for tickets, services or events · CPC title

• G06Q10/08 Primary

  Logistics, e.g. warehousing, loading or distribution; Inventory or stock management · CPC title

• G06Q30/0635 Primary

  replenishment orders; recurring orders · CPC title

• G06Q50/30

  Physics · mapped topic

• G06Q50/40

  Business processes related to the transportation industry (shipping G06Q10/083) · CPC title