Order allocation system and method

• US 10,977,585 B2
• Filed: 01/29/2016
• Issued: 04/13/2021
• Est. Priority Date: 01/29/2015
• Status: Active Grant

• Current Assignee: Beijing Didi Infinity Technology And Development Co.Ltd.
• Original Assignee: Beijing Didi Infinity Technology And Development Co.Ltd.
• Inventors: Hu, Tao, Cui, Wei, Yin, Jun, Hu, Zhilin, Ye, Yong, Yang, Ping, Deng, Xiaolin, Zhang, Yu, Liu, Yangbiao, Shi, Kuan, Cao, Zhongyu
• Primary Examiner(s): Chen, George
• Assistant Examiner(s): Ma, Lisa
• Application Number:
  US15/547,221
• Publication Number:
  US 20180012153A1
• Time in Patent Office: 1,901 Days
• Field of Search: 705 13
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083

Abstract

The present disclosure relates to a system and a method of allocating orders. The system may include a non-transitory computer readable storage medium and a processor. The non-transitory computer may store an executable module. The processor may execute the executable module stored in the computer readable storage medium. The non-transitory computer readable storage medium may include a receiving unit (231) and an order allocation unit (361). The receiving unit (231) may receive order information and user information. The user information may include location information and/or time information. The order allocation unit (361) may allocate an order based on the location information and/or the time information. The method may include receiving order information and user information, wherein the order information and the user information may include location information and/or time information, and allocating an order based on the location information and/or the time information.

Claims

1. A system, comprising:

at least one storage medium including a set of instructions;

at least one processor in communication with the at least one storage medium, wherein when executing the set of instructions, the at least one processor is directed to;

receive first electrical signals encoding order information and user information from a terminal of an order requestor and terminals of order recipients via a network, wherein the user information includes information related to an order requestor and information related to order recipients, wherein the order information and the user information are associated with an order and include at least one of location information or time information, the location information including location of the order requester and location of each of the order recipients determined using positioning technology;

determine a road distance between the order requester and each of the order recipients according to a traffic map information of an area where the order requester is located, the location of the order requester, and the location of each of the order recipients;

determine an order snatching probability of each of the order recipients based on the road distance and a pre-established prediction model;

operate logical circuits in the at least one processor to determine at least one service provider from the order recipients based on the order snatching probability of each of order recipients; and

send the order information to a terminal of the at least one service provider via the network for displaying on an interface of the terminal of the at least one service provider,

wherein the pre-established prediction model is generated by;

obtaining a plurality of historical orders of the user in a preset time period;

obtaining feature information of each of the plurality of historical orders and historical road distance of each of the plurality of historical orders; and

determining the pre-established prediction model by training a regression model using the feature information of each of the plurality of historical orders and the historical road distance of each of the plurality of historical orders, wherein the historical road distance is taken as a predictive variable, and order snatching results representing whether the historical orders are snatched or not is taken as a target variable.

2. The system of claim 1, wherein the time information includes at least one of an order spread time or an order snatching time associated with each of the order recipients.

3. The system of claim 1, wherein the location information further includes at least one of a departure location, an original location, a destination, or a geographical region.

4. The system of claim 3, wherein the at least one processor is further directed to:

operate the logical circuits in the at least one processor to obtain at least one of an order spread region of the order or an order receiving range of each of the order recipients;

operate the logical circuits in the at least one processor to obtain a number of orders within the order spread region; and

operate the logical circuits in the at least one processor to obtain an order density based on at least one of the order spread region, the order receiving range, or the number of orders.

5. The system of claim 1, wherein the at least one processor is further directed to:

operate the logical circuits in the at least one processor to determine an accuracy of the order snatching probability.

6. The system of claim 5, wherein the at least one processor is further directed to:

operate the logical circuits in the at least one processor to determine an actual order snatching probability of the order recipients for the order; and

operate the logical circuits in the at least one processor to determine the accuracy of the order snatching probability based on the predicted order snatching probability and the actual order snatching probability of the order recipients.

7. The system of claim 1, wherein the generation of the pre-established prediction model further comprising optimizing the pre-established prediction model using machine learning algorithms according to related feature information of related orders obtained in real time online and related road distance corresponding to the related orders.

8. The system of claim 1, wherein the regression model is a linear regression model.

9. The system of claim 8, wherein the linear regression model includes one of a logistic regression model and a support vector machine model.

10. The system of claim 1, wherein the road distance includes a straight line distance between the order requester and each of the order recipients or an actual vehicle driving distance from each of the order recipients to the order requester.

11. A method implemented on a computing device having at least one processor, at least one computer-readable storage medium, and a communication platform connected to a network, comprising:

receiving first electrical signals encoding order information and user information from a terminal of an order requestor and terminals of order recipients via a network, wherein the user information includes information related to an order requestor and information related to order recipients, wherein the order information and user information are associated with an order and include at least one of location information or time information, the location information including location of the order requester and location of each of the order recipients using positioning technology;

determining a road distance between the order requester and each of the order recipients according to a traffic map information of an area where the order requester is located, the location of the order requester, and the location of each of the order recipients;

determining an order snatching probability of each of the order recipients based on the road distance and a pre-established prediction model;

operating logical circuits in the at least one processor to determine at least one service provider from the order recipients based on the order snatching probability of each of order recipients; and

sending the order information to a terminal of the at least one service provider via the network for displaying on an interface of the terminal of the at least one service provider,

wherein the pre-established prediction model is generated by;

obtaining a plurality of historical orders of the user in a preset time period;

obtaining feature information of each of the plurality of historical orders and historical road distance of each of the plurality of historical orders; and

determining the pre-established prediction model by training a regression model using the feature information of each of the plurality of historical orders and the historical road distance of each of the plurality of historical orders, wherein the historical road distance is taken as a predictive variable, and order snatching results representing whether the historical orders are snatched or not is taken as a target variable.

12. The method of claim 11, wherein the time information includes at least one of an order snatching time of each of the order recipients.

13. The method of claim 11, wherein the location information further includes at least one of a departure location, an original location, a destination, or a geographical region.

14. The method of claim 13, further comprising:

operating the logical circuits in the at least one processor to obtain at least one of an order spread region of the order or an order receiving range of each of the order recipients, and a number of orders;

operating the logical circuits in the at least one processor to obtain an order density based on at least one of the order spread region or the order receiving range, and the number of orders; and

operating the logical circuits in the at least one processor to determine the at least one service provider based on the order density.

15. The method of claim 11, further comprising:

operating the logical circuits in the at least one processor to determine an accuracy of the order snatching probability.

16. The method of claim 15, further comprising:

operating the logical circuits in the at least one processor to obtain a predicted order snatching probability of the order recipients for the order;

operating the logical circuits in the at least one processor to determine an actual order snatching probability of the order recipients for the order; and

operating the logical circuits in the at least one processor to determine the accuracy of the order snatching probability based on the predicted order snatching probability and the actual order snatching probability of the order recipients.