Method and device for predicting pickup duration, storage medium and electronic equipment

Abstract

The present disclosure relates to a method and device for predicting the pickup time of an order, a storage medium and an electronic device. The method comprises: inputting the historical related data of a target order, the feature information of the target order and the feature information of the delivery personnel of the target order into a first prediction model established in advance to obtain a first pickup time of the target order; determining a second pickup time of the target order according to the path planning information between the current location of the delivery personnel and the merchant address of the target order; and inputting the first pickup time and the second pickup time into a second prediction model established in advance to obtain the final prediction result of the pickup time of the target order. Through the technical solution of the present disclosure, the pickup time of an order can be accurately predicted.

Description

Technical Field

[0001] The present disclosure relates to the field of the Internet, and in particular, to a method, device, storage medium, and electronic device for predicting pickup time. Background Art

[0002] With the continuous development of network technology, instant delivery services are becoming increasingly popular. The order processing process of instant delivery services usually includes the user placing an order, the merchant providing the goods, the delivery person arriving at the merchant to pick up the goods, and then delivering the goods.

[0003] In order to facilitate merchants to reasonably arrange the shipping order, it is necessary to accurately predict the pickup time of each order, that is, the time required for the delivery person of the order to reach the merchant address from the current location.

[0004] In the prior art, order pickup time is typically predicted based on the route planning information between the delivery person's location and the merchant's address. However, the accuracy of the pickup time obtained by this prediction method is low. Summary of the Invention

[0005] In order to overcome the problems existing in the prior art, the present disclosure provides a method, device, storage medium and electronic device for predicting pickup time.

[0006] To achieve the above objectives, the present disclosure provides, in a first aspect, a method for predicting pickup time, comprising:

[0007] Inputting historical data related to a target order, characteristic information of the target order, and characteristic information of a delivery person for the target order into a pre-established first prediction model to obtain a first pickup time for the target order;

[0008] Determining a second pickup time for the target order based on route planning information between the delivery person's current location and the merchant address of the target order;

[0009] The first pickup time and the second pickup time are input into a pre-established second prediction model to obtain a final prediction result of the pickup time of the target order.

[0010] Optionally, the method further includes:

[0011] Obtain a sample order set, and use feature information of the sample order set, feature information of each sample order in the sample order set, and feature information of a delivery person for each sample order as a first training data set;

[0012] The first training data set is used to train an xgboost model to obtain the first prediction model.

[0013] Optionally, the method further includes:

[0014] For each sample order, predict the sample order based on the first prediction model to obtain the first pickup time of the sample order; and

[0015] Determine the second pickup time for the sample order based on the route planning information between the real-time location of the delivery person for the sample order and the merchant address for the sample order;

[0016] The first pickup time and the second pickup time of each sample order are used as a second training data set, and the second training data set is used to train a logistic regression LR model to obtain the second prediction model.

[0017] Optionally, the second prediction model is:

[0018] P=W1·Mod1+W2·Mod2

[0019] Among them, P is the final prediction result of the pickup time of the target order; W1 is the first preset constant; W2 is the second preset constant; Mod1 is the first pickup time of the target order; Mod2 is the second pickup time of the target order.

[0020] Optionally, the method further includes:

[0021] The final prediction result of the pickup time of the target order is sent to the destination end.

[0022] A second aspect of the present disclosure provides a device for predicting pickup time, comprising:

[0023] a first prediction module, configured to input historical data related to a target order, characteristic information of the target order, and characteristic information of a delivery person for the target order into a pre-established first prediction model to obtain a first pickup time for the target order;

[0024] A first determining module is configured to determine a second pickup time for the target order based on path planning information between the delivery person's current location and the merchant address of the target order;

[0025] The second prediction module is used to input the first pickup time and the second pickup time into a pre-established second prediction model to obtain a final prediction result of the pickup time of the target order.

[0026] Optionally, the device further comprises:

[0027] an acquisition module, configured to acquire a sample order set, and use feature information of the sample order set, feature information of each sample order in the sample order set, and feature information of a delivery person for each sample order as a first training data set;

[0028] The first training module is used to train the xgboost model using the first training data set to obtain the first prediction model.

[0029] Optionally, the device further comprises:

[0030] a third prediction module, configured to predict, for each sample order, the sample order based on the first prediction model, and obtain a first pickup time for the sample order;

[0031] A second determination module is configured to determine, for each sample order, a second pickup time for the sample order based on path planning information between the delivery person's real-time location and the merchant address of the sample order;

[0032] The second training module is used to use the first pickup time and the second pickup time of each sample order as a second training data set, and use the second training data set to train a logistic regression LR model to obtain the second prediction model.

[0033] Optionally, the second prediction model is:

[0034] P=W1·Mod1+W2·Mod2

[0035] Among them, P is the final prediction result of the pickup time of the target order; W1 is the first preset constant; W2 is the second preset constant; Mod1 is the first pickup time of the target order; Mod2 is the second pickup time of the target order.

[0036] Optionally, the device further comprises:

[0037] The sending module is used to send the final prediction result of the pickup time of the target order to the destination end.

[0038] A third aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for predicting the pickup time described in the first aspect.

[0039] A fourth aspect of the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for predicting the pickup time described in the first aspect when executing the computer program.

[0040] The above technical solution can at least achieve the following technical effects:

[0041] Based on the first prediction model, the pickup time of the order is predicted according to the historical relevant information, feature information of the order and the feature information of the delivery person of the order, which are factors affecting the pickup time, and the first pickup time output by the first prediction model and the second pickup time calculated according to the delivery person's path planning information are comprehensively evaluated by the second prediction model to obtain the final prediction result of the pickup time. Compared with the prior art in which the pickup time of the order is calculated according to the delivery person's path planning information, the technical solution provided by the present disclosure can accurately predict the pickup time of the order.

[0042] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0044] Figure 1 This is a flow chart of a method for predicting pickup time according to an exemplary embodiment of the present disclosure;

[0045] Figure 2 is a block diagram of a device for predicting pickup time according to an exemplary embodiment of the present disclosure;

[0046] Figure 3 is a block diagram of a device for predicting pickup time according to another exemplary embodiment of the present disclosure;

[0047] Figure 4 The figure is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0048] The following describes the specific embodiments of the present disclosure in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure.

[0049] It should be noted that the terms "first", "second", etc. in the description, claims and drawings of the present disclosure are used to distinguish similar objects and are not necessarily understood as describing a specific order or sequence.

[0050] The existing method for predicting pickup time is usually based on an operations planning algorithm to obtain the path planning information between the delivery person's current location and the merchant's address, and then obtain the pickup time of the order point by point based on the path planning information.

[0051] However, due to multiple uncertainties in the delivery driver's pickup process, such as the delivery driver not arriving at the merchant address to pick up the goods completely according to the route planning information, the delivery driver's pickup speed being slowed down by traffic, terrain or weather reasons, the delivery driver being unable to contact the user when collecting and delivering other orders causing delays, etc., these factors will lead to the low accuracy of the pickup time obtained by the existing prediction method.

[0052] In order to solve the above technical problems, the embodiments of the present disclosure provide a method for predicting the pickup time to accurately predict the pickup time of an order.

[0053] Figure 1 FIG. 1 is a flow chart of a method for predicting pickup time according to an exemplary embodiment of the present disclosure. Figure 1 As shown, the method includes the following steps:

[0054] In step S11, historical data related to the target order, characteristic information of the target order, and characteristic information of the delivery person of the target order are input into a pre-established first prediction model to obtain a first pickup time for the target order.

[0055] The method may be implemented by a server of an instant delivery operator, which stores a large number of delivered and undelivered orders. The target order is an order among the undelivered orders stored by the server that has been assigned to a delivery driver but has not been picked up by the delivery driver.

[0056] The historical relevant data of the target order may include the number of delivered orders of all merchants in the area to which the merchant of the target order belongs within a preset time period (for example, within 30 minutes from the current moment) and the path planning information between the current location of the delivery person of each delivered order and the merchant address of the delivered order, which is used to characterize the load changes in the area to which the merchant of the target order belongs within the preset time period.

[0057] The characteristic information of the target order may include the price of the goods of the target order in the current time period, which is used to characterize the delivery difficulty of the target order.

[0058] The characteristic information of the deliveryman of the target order may include the deliveryman's historical average delivery time, the historical average pickup punctuality rate, and the straight-line distance between the deliveryman's current location and the merchant address of the target order, which is used to characterize the deliveryman's delivery capability.

[0059] These feature information can accurately describe the dynamic situation of delivery personnel picking up goods.

[0060] The first prediction model is a pre-established model for predicting the pickup time of an order. By inputting historical relevant information of the target order, characteristic information of the target order, and characteristic information of the delivery person of the target order into the first prediction model, the prediction result of the pickup time of the target order can be obtained.

[0061] In step S12, the second pickup time of the target order is determined based on the path planning information between the current location of the delivery person and the merchant address of the target order.

[0062] Alternatively, the delivery person's current location can be obtained through the delivery person's user terminal (e.g., a mobile phone), and path planning information from the current location to the merchant's address can be obtained based on an operations planning algorithm. The specific method for determining the path planning information from the current location to the merchant's address based on the operations planning algorithm is well known to those skilled in the art and will not be elaborated in detail in this disclosure.

[0063] After obtaining the route planning information, the pickup time for the target order can be determined point by point based on the delivery driver's route planning information. For example, the route planning information includes the delivery driver's route information from their current location to Merchant Address A for Order A, the route information from Merchant Address A to User Address A for Order A, and the route information from User Address A to the merchant address for the target order. Accordingly, the duration of each route segment is calculated based on the route information for each segment. The sum of the durations of all routes is the second pickup time for the target order.

[0064] In step S13, the first pickup time and the second pickup time are input into a pre-established second prediction model to obtain a final prediction result of the pickup time of the target order.

[0065] The second prediction model is a pre-established model for comprehensively evaluating the first pickup time and the second pickup time to output a final prediction result of the pickup time.

[0066] For example, the second prediction model can be P=W1·Mod1+W2·Mod2, where P is the final prediction result of the pickup time of the target order; W1 is the first preset constant; W2 is the second preset constant; Mod1 is the first pickup time of the target order; Mod2 is the second pickup time of the target order.

[0067] The above method is adopted to combine machine learning with operations research. Based on the first prediction model, the pickup time of the order is predicted according to the historical relevant information, feature information of the order and the feature information of the delivery person of the order, which are factors affecting the pickup time, to obtain the first pickup time. The operations planning algorithm is used to determine the second pickup time of the order based on the path planning information between the current location of the delivery person and the merchant address of the order. Finally, the first pickup time and the second pickup time are comprehensively evaluated by the second prediction model to obtain the final prediction result of the pickup time. Compared with the prior art of calculating the pickup time of the order based on the path planning information of the delivery person, the technical solution provided by the present disclosure can accurately predict the pickup time of the order.

[0068] It is worth noting that in actual application, the above-mentioned pickup time prediction method can be executed once every preset time interval (for example, 10 minutes) to continuously update the pickup time of the order and avoid inaccurate pickup time prediction caused by factors such as changes in the status of other unfinished orders of the delivery staff.

[0069] In addition, for the sake of simplicity, the above method embodiments are described as a series of action combinations, but those skilled in the art should know that the present disclosure is not limited to the order of the actions described. For example, the above steps S11 and S12 can be performed simultaneously.

[0070] In another embodiment of the present disclosure, the pickup time prediction method further includes a method for establishing a first prediction model. The method for establishing the first prediction model includes: obtaining a sample order set, and using feature information of the sample order set, feature information of each sample order in the sample order set, and feature information of the delivery person for each sample order as a first training data set; and training an xgboost model using the first training data set to obtain a first prediction model.

[0071] The sample order set can include a large number of sample orders delivered to all merchants in different time periods and regions. Feature information for the sample order set can include the number of sample orders in each region during each time period, as well as route planning information from the delivery driver's location to the merchant address for each sample order. This information is used to characterize the load changes in each region during each time period.

[0072] The characteristic information of each sample order includes the price of the goods of the sample order in each time period, which is used to characterize the delivery difficulty of the sample order.

[0073] The characteristic information of the deliveryman for each sample order includes the deliveryman's historical average delivery time, the historical average pickup punctuality rate, and the straight-line distance between the deliveryman's location and the merchant address of the sample order, which is used to characterize the deliveryman's delivery capability.

[0074] By establishing the first prediction model, factors related to the pickup time can be mined from the implicit historical order information. Furthermore, by predicting the pickup time based on the first prediction model, the purpose of accurately predicting the pickup time can be achieved.

[0075] In another embodiment of the present disclosure, the above-mentioned method for predicting the pickup time also includes a method for establishing a second prediction model. The method for establishing the second prediction model includes: for each sample order, predicting the sample order based on the first prediction model to obtain the first pickup time of the sample order, and determining the second pickup time of the sample order based on the path planning information between the real-time location of the delivery person of the sample order and the merchant address of the sample order. Finally, the first pickup time and the second pickup time of each sample order are used as the second training data set, and the second training data set is used to train the logistic regression (LR) to obtain the second prediction model.

[0076] It is worth noting that the specific method of determining the second pickup time of the sample order based on the path planning information between the real-time location of the delivery person of the sample order and the merchant address of the sample order can be found in the description of the above step S12 and will not be repeated here.

[0077] By using a logistic regression model, we learn the fusion parameters of the two methods: predicting the order pickup time based on the first prediction model and determining the order pickup time based on the delivery person's path planning information, and achieve the optimal combination of the two.

[0078] In another embodiment of the present disclosure, the above-mentioned method for predicting the pickup time further includes: sending the final prediction result of the pickup time of the target order to the destination end. The destination end may include the client of the merchant of the order and / or the client of the subscribing user. By sending the final prediction result of the pickup time to the merchant client, it is convenient for the merchant to reasonably arrange the processing order of the order according to the final prediction result of the pickup time, and reduce the time the delivery person waits for pickup after arriving at the merchant address. By sending the final prediction result of the pickup time to the subscribing user client, the subscribing user can be provided with an accurate pickup time, which is convenient for the subscribing user to make subsequent arrangements.

[0079] The present disclosure provides a device for predicting the pickup time. Figure 2 FIG. 1 is a block diagram of a device for predicting pickup time according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the device 200 includes:

[0080] A first prediction module 201 is configured to input historical data related to a target order, characteristic information of the target order, and characteristic information of the delivery person of the target order into a pre-established first prediction model to obtain a first pickup time for the target order;

[0081] A first determining module 202 is configured to determine a second pickup time for the target order based on the route planning information between the delivery person's current location and the merchant address of the target order;

[0082] The second prediction module 203 is used to input the first pickup time and the second pickup time into a pre-established second prediction model to obtain a final prediction result of the pickup time of the target order.

[0083] Among them, the historical relevant data of the target order may include the number of delivered orders of all merchants in the area where the merchant of the target order belongs within a preset time period and the path planning information between the current location of the delivery person of each delivered order and the merchant address of the delivered order, which is used to characterize the load changes in the area where the merchant of the target order belongs at present and in the future.

[0084] The characteristic information of the target order may include the price of the goods of the target order in the current time period, which is used to characterize the delivery difficulty of the target order.

[0085] The characteristic information of the deliveryman of the target order may include the deliveryman's historical average delivery time, the historical average pickup punctuality rate, and the straight-line distance between the deliveryman's current location and the merchant address of the target order, which is used to characterize the deliveryman's delivery capability.

[0086] The above-mentioned device is used to combine machine learning with operations research. Based on the first prediction model, the pickup time of the order is predicted according to the historical relevant information, feature information of the order and the feature information of the delivery person of the order, which are factors affecting the pickup time, to obtain the first pickup time. And using operations research, the second pickup time of the order is determined according to the path planning information between the current location of the delivery person and the merchant address of the order. Finally, the first pickup time and the second pickup time are comprehensively evaluated by the second prediction model to obtain the final prediction result of the pickup time. Compared with the prior art of calculating the pickup time of the order based on the path planning information of the delivery person, the technical solution provided by the present disclosure can accurately predict the pickup time of the order.

[0087] Alternatively, as Figure 3 As shown, the device 300 further includes:

[0088] An acquisition module 205 is configured to acquire a sample order set and use feature information of the sample order set, feature information of each sample order in the sample order set, and feature information of the delivery person of each sample order as a first training data set;

[0089] The first training module 206 is configured to train an xgboost model using the first training data set to obtain the first prediction model.

[0090] The sample order set can include a large number of sample orders delivered to all merchants in different time periods and regions. Feature information for the sample order set can include the number of sample orders in each region during each time period, as well as route planning information from the delivery driver's location to the merchant address for each sample order. This information is used to characterize the load changes in each region during each time period.

[0091] The characteristic information of each sample order includes the price of the goods of the sample order in each time period, which is used to characterize the delivery difficulty of the sample order.

[0092] The characteristic information of the deliveryman for each sample order includes the deliveryman's historical average delivery time, the historical average pickup punctuality rate, and the straight-line distance between the deliveryman's location and the merchant address of the sample order, which is used to characterize the deliveryman's delivery capability.

[0093] By establishing the first prediction model, factors related to the pickup time can be mined from the implicit historical order information. Furthermore, based on the first prediction model, the purpose of accurately predicting the pickup time can be achieved.

[0094] Alternatively, as Figure 3 As shown, the device 200 further includes:

[0095] A third prediction module 207 is configured to predict each sample order based on the first prediction model to obtain a first pickup time for the sample order;

[0096] A second determining module 208 is configured to determine, for each sample order, a second pickup time for the sample order based on the route planning information between the real-time location of the delivery person for the sample order and the merchant address for the sample order;

[0097] The second training module 209 is configured to use the first pickup time and the second pickup time of each sample order as a second training data set, and use the second training data set to train a logistic regression (LR) model to obtain the second prediction model.

[0098] By using a logistic regression model, we learn the fusion parameters of the two methods: predicting the order pickup time based on the first prediction model and determining the order pickup time based on the delivery person's path planning information, and achieve the optimal combination of the two.

[0099] Optionally, the second prediction model is:

[0100] P=W1·Mod1+W2·Mod2

[0101] Among them, P is the final prediction result of the pickup time of the target order; W1 is the first preset constant; W2 is the second preset constant; Mod1 is the first pickup time of the target order; Mod2 is the second pickup time of the target order.

[0102] Alternatively, as Figure 3 As shown, the device 200 further includes:

[0103] The sending module 210 is used to send the final prediction result of the pickup time of the target order to the destination end.

[0104] The destination end may include the client of the merchant placing the order and / or the client of the subscriber. By sending the final prediction of the pickup time to the merchant's client, the merchant can rationally arrange the order processing sequence based on the final prediction of the pickup time, reducing the waiting time for delivery personnel after arriving at the merchant's address to pick up the goods. By sending the final prediction of the pickup time to the subscriber's client, the subscriber is provided with an accurate pickup time, facilitating subsequent arrangements by the subscriber.

[0105] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0106] In addition, those skilled in the art will clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0107] An embodiment of the present disclosure also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for predicting the pickup time when executing the computer program.

[0108] For example, Figure 44 is a block diagram of an electronic device 400 according to an exemplary embodiment. For example, the electronic device 400 may be provided as a server. Figure 4 The electronic device 400 includes one or more processors 422 and a memory 432 for storing a computer program executable by the processor 422. The computer program stored in the memory 432 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 422 may be configured to execute the computer program to perform the aforementioned method for predicting pickup time.

[0109] In addition, the electronic device 400 may further include a power supply component 426 and a communication component 450. The power supply component 426 may be configured to perform power management of the electronic device 400, and the communication component 450 may be configured to implement communication, such as wired or wireless communication, of the electronic device 400. In addition, the electronic device 400 may further include an input / output (I / O) interface 458. The electronic device 400 may operate based on an operating system stored in the memory 432, such as Windows Server™, Mac OS X™, Unix™, Linux™, etc.

[0110] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, the program instructions implement the steps of the aforementioned method for predicting pickup time. For example, the computer-readable storage medium may be the aforementioned memory 432 including the program instructions. The program instructions may be executed by the processor 422 of the electronic device 400 to implement the aforementioned method for predicting pickup time.

[0111] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0112] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0113] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for predicting pickup time, characterized in that: include: Inputting historical data related to a target order, characteristic information of the target order, and characteristic information of the delivery person of the target order into a pre-established first prediction model to obtain a first pickup time length for the target order, wherein the historical data related to the target order includes the number of delivered orders for all merchants within the region to which the merchant of the target order belongs within a preset time period and the path planning information between the current location of the delivery person of each delivered order and the merchant address of the delivered order; the characteristic information of the delivery person of the target order includes the historical average delivery time of the delivery person, the historical average on-time pickup rate, and the straight-line distance between the current location of the delivery person and the merchant address of the target order; Determining a second pickup time for the target order based on route planning information between the delivery person's current location and the merchant address of the target order; The first pickup time and the second pickup time are input into a pre-established second prediction model to obtain a final prediction result of the pickup time of the target order.

2. The method according to claim 1, characterized in that The method further comprises: Obtain a sample order set, and use feature information of the sample order set, feature information of each sample order in the sample order set, and feature information of a delivery person for each sample order as a first training data set; The first training data set is used to train an xgboost model to obtain the first prediction model.

3. The method according to claim 2, characterized in that The method further comprises: For each sample order, predict the sample order based on the first prediction model to obtain the first pickup time of the sample order; and Determine the second pickup time for the sample order based on the route planning information between the real-time location of the delivery person for the sample order and the merchant address for the sample order; The first pickup time and the second pickup time of each sample order are used as a second training data set, and the second training data set is used to train a logistic regression LR model to obtain the second prediction model.

4. The method according to claim 1, wherein The second prediction model is: in, The final prediction result of the pickup time of the target order; is the first preset constant; is the second preset constant; The first pickup time for the target order; The second pickup time for the target order.

5. The method according to claim 1, wherein The method further comprises: The final prediction result of the pickup time of the target order is sent to the destination end.

6. A device for predicting the pickup time, characterized in that: include: a first prediction module, configured to input historical data related to a target order, characteristic information of the target order, and characteristic information of a delivery person for the target order into a pre-established first prediction model to obtain a first pickup time for the target order, wherein the historical data related to the target order includes the number of delivered orders for all merchants within the region to which the merchant of the target order belongs within a preset time period and path planning information between the current location of the delivery person for each delivered order and the merchant address of the delivered order; and the characteristic information of the delivery person for the target order includes the historical average delivery time of the delivery person, the historical average on-time pickup rate, and the straight-line distance between the current location of the delivery person and the merchant address of the target order; A first determining module is configured to determine a second pickup time for the target order based on path planning information between the delivery person's current location and the merchant address of the target order; The second prediction module is used to input the first pickup time and the second pickup time into a pre-established second prediction model to obtain a final prediction result of the pickup time of the target order.

7. The device according to claim 6, characterized in that The device further comprises: an acquisition module, configured to acquire a sample order set, and use feature information of the sample order set, feature information of each sample order in the sample order set, and feature information of a delivery person for each sample order as a first training data set; The first training module is used to train the xgboost model using the first training data set to obtain the first prediction model.

8. The device according to claim 7, characterized in that The device further comprises: a third prediction module, configured to predict, for each sample order, the sample order based on the first prediction model, and obtain a first pickup time for the sample order; A second determination module is configured to determine, for each sample order, a second pickup time for the sample order based on path planning information between the delivery person's real-time location and the merchant address of the sample order; The second training module is used to use the first pickup time and the second pickup time of each sample order as a second training data set, and use the second training data set to train a logistic regression LR model to obtain the second prediction model.

9. The device according to claim 6, characterized in that The second prediction model is: in, The final prediction result of the pickup time of the target order; is the first preset constant; is the second preset constant; The first pickup time for the target order; The second pickup time for the target order.

10. The device according to claim 6, characterized in that The device further comprises: The sending module is used to send the final prediction result of the pickup time of the target order to the destination end.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the order processing method according to any one of claims 1 to 5 are implemented.

12. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.

Images