Method and apparatus for predicting delivery time of a shipping document

Abstract

The application provides a way and device for predicting the delivery time of a waybill. The delivery process of the waybill includes a first stage and a second stage. The way of predicting the delivery time of the waybill includes: obtaining a first to-be-predicted waybill; determining the first-stage predicted delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples; updating the first to-be-predicted waybill according to the first-stage predicted delivery time to obtain a second to-be-predicted waybill; determining the second-stage predicted delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples; and determining the target waybill predicted delivery time according to the second-stage predicted delivery time. The application can improve the accuracy of the way of predicting the delivery time of the waybill.

Description

Technical Field

[0001] This application mainly relates to the field of big data technology, specifically to a method and apparatus for predicting waybill delivery time. Background Technology

[0002] When a user places an order, logistics companies typically offer an estimated delivery time, known as the promised delivery time. A high success rate in achieving this promised delivery time, or a significant discrepancy between the promised and actual delivery times, can lead to customer complaints and a poor user experience. Existing promised delivery times are based on a coarse-grained historical 80% achievement rate at the administrative region level. However, this administrative region is too broad and fails to reflect the timeliness differences between different delivery points. Problems with existing methods include: firstly, while administrative region-level promised delivery times guarantee an 80% success rate, the administrative region is too broad to reflect finer-grained differences in timeliness between delivery points; secondly, most solutions treat the entire process from order placement to delivery as a single, ambiguous unit, failing to capture intermediate steps and resulting in low delivery time accuracy.

[0003] In other words, the accuracy of existing methods for predicting waybill delivery time is not high. Summary of the Invention

[0004] This application provides a method and apparatus for predicting waybill delivery time, aiming to solve the problem of low accuracy in existing waybill delivery time prediction methods.

[0005] In a first aspect, this application provides a method for predicting the delivery time of a waybill, wherein the delivery process of the waybill includes a first stage and a second stage, and the method for predicting the delivery time of the waybill includes:

[0006] Obtain the first shipment to be forecasted;

[0007] The first-stage predicted delivery time of the first shipment to be predicted is determined based on the first shipment to be predicted and multiple first historical shipment samples.

[0008] The first shipment to be predicted is updated based on the predicted delivery time of the first stage to obtain the second shipment to be predicted.

[0009] The second-stage predicted delivery time of the second shipment to be predicted is determined based on the second shipment to be predicted and multiple second historical shipment samples.

[0010] The target waybill's predicted delivery time is determined based on the second-stage predicted delivery time.

[0011] Optionally, determining the first-stage predicted delivery time of the first shipment to be predicted based on the first shipment to be predicted and multiple first historical shipment samples includes:

[0012] Obtain the first stage start time of the first shipment to be predicted;

[0013] Obtain the plurality of first historical waybill samples that match the start time of the first stage;

[0014] The first-stage predicted delivery time of the first shipment to be predicted is determined based on the first shipment to be predicted and the plurality of first historical shipment samples.

[0015] Optionally, determining the first-stage predicted delivery time of the first shipment to be predicted based on the first shipment to be predicted and multiple first historical shipment samples includes:

[0016] Obtain the achievement rate of the preset target;

[0017] The first quantile parameter and the second quantile parameter are determined based on the preset target achievement rate;

[0018] The first stage predicted delivery time of the first predicted waybill is determined based on the first quantile parameter, the first waybill to be predicted, and multiple first historical waybill samples.

[0019] The step of determining the second-stage predicted delivery time of the second shipment based on the second shipment to be predicted and multiple second historical shipment samples includes:

[0020] The second-stage predicted delivery time of the second shipment to be predicted is determined based on the second quantile parameter, the second shipment to be predicted, and multiple second historical shipment samples.

[0021] Optionally, determining the first-stage predicted delivery time of the first shipment based on the first quantile parameter, the first shipment to be predicted, and multiple first historical shipment samples includes:

[0022] Calculate the similarity between the first waybill to be predicted and the plurality of first historical waybill samples, respectively;

[0023] The first historical waybill sample with a similarity higher than the preset similarity to the first waybill to be predicted is placed into the waybill set;

[0024] The target waybill sample is obtained from the waybill set according to the first quantile parameter;

[0025] The actual delivery time of the first stage of the target waybill sample is determined as the predicted delivery time of the first stage of the waybill to be predicted.

[0026] Optionally, calculating the similarity between the first waybill to be predicted and the plurality of first historical waybill samples includes:

[0027] Obtain the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample, wherein the waybill feature vector includes waybill spatial features, waybill temporal features and waybill attribute features;

[0028] The similarity of the waybill is obtained by calculating the vector similarity between the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample.

[0029] Optionally, determining the first quantile parameter and the second quantile parameter based on the preset target achievement rate includes:

[0030] Based on the preset target achievement rate, multiple candidate quantile parameter combinations and training sets are obtained. Each candidate quantile parameter combination includes a first-stage candidate quantile parameter and a second-stage candidate quantile parameter. The training set includes multiple training samples and the actual delivery time of each training sample's waybill.

[0031] The delivery time of each training sample in the training set is predicted based on the combination of multiple candidate quantile parameters, and the predicted delivery time of each training sample is obtained.

[0032] Based on the predicted delivery time of each training sample's waybill and the actual delivery time of each training sample's waybill, determine multiple prediction performance index values ​​corresponding to multiple candidate quantile parameter combinations.

[0033] The candidate quantile parameter combination corresponding to the predicted effect index value that meets the preset conditions is determined as the first quantile parameter and the second quantile parameter.

[0034] Optionally, obtaining multiple candidate quantile parameter combinations and a training set based on the preset target achievement rate includes:

[0035] The quantile reference parameters are determined based on the preset target achievement rate and the number of stages in the transportation process;

[0036] The quantile value range is determined based on the quantile reference parameter, wherein the value of the quantile value range is not greater than the quantile reference parameter;

[0037] Multiple quantile parameters are obtained from the quantile value range according to a preset step size and combined to obtain multiple candidate quantile parameter combinations.

[0038] Secondly, this application provides a method for predicting the delivery time of a waybill, wherein the waybill transportation process includes a first stage and a second stage, and the method for predicting the delivery time of the waybill includes:

[0039] The acquisition unit is used to acquire the first waybill to be predicted.

[0040] The first determining unit is used to determine the first stage predicted delivery time of the first predicted waybill based on the first waybill to be predicted and multiple first historical waybill samples.

[0041] The update unit is used to update the first waybill to be predicted based on the predicted delivery time of the first stage, so as to obtain the second waybill to be predicted.

[0042] The second determining unit is used to determine the second-stage predicted delivery time of the second shipment to be predicted based on the second shipment to be predicted and multiple second historical shipment samples.

[0043] The third determining unit is used to determine the predicted delivery time of the target waybill based on the predicted delivery time in the second stage.

[0044] Optionally, the first determining unit is configured to:

[0045] Obtain the first stage start time of the first shipment to be predicted;

[0046] Obtain the plurality of first historical waybill samples that match the start time of the first stage;

[0047] The first-stage predicted delivery time of the first shipment to be predicted is determined based on the first shipment to be predicted and the plurality of first historical shipment samples.

[0048] Optionally, the first determining unit is configured to:

[0049] Obtain the achievement rate of the preset target;

[0050] The first quantile parameter and the second quantile parameter are determined based on the preset target achievement rate;

[0051] The first stage predicted delivery time of the first predicted waybill is determined based on the first quantile parameter, the first waybill to be predicted, and multiple first historical waybill samples.

[0052] The second determining unit is used for:

[0053] The second-stage predicted delivery time of the second shipment to be predicted is determined based on the second quantile parameter, the second shipment to be predicted, and multiple second historical shipment samples.

[0054] Optionally, the first determining unit is configured to:

[0055] Calculate the similarity between the first waybill to be predicted and the plurality of first historical waybill samples, respectively;

[0056] The first historical waybill sample with a similarity higher than the preset similarity to the first waybill to be predicted is placed into the waybill set;

[0057] The target waybill sample is obtained from the waybill set according to the first quantile parameter;

[0058] The actual delivery time of the first stage of the target waybill sample is determined as the predicted delivery time of the first stage of the waybill to be predicted.

[0059] Optionally, the first determining unit is configured to:

[0060] Obtain the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample, wherein the waybill feature vector includes waybill spatial features, waybill temporal features and waybill attribute features;

[0061] The similarity of the waybill is obtained by calculating the vector similarity between the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample.

[0062] Optionally, the first determining unit is configured to:

[0063] Based on the preset target achievement rate, multiple candidate quantile parameter combinations and training sets are obtained. Each candidate quantile parameter combination includes a first-stage candidate quantile parameter and a second-stage candidate quantile parameter. The training set includes multiple training samples and the actual delivery time of each training sample's waybill.

[0064] The delivery time of each training sample in the training set is predicted based on the combination of multiple candidate quantile parameters, and the predicted delivery time of each training sample is obtained.

[0065] Based on the predicted delivery time of each training sample's waybill and the actual delivery time of each training sample's waybill, determine multiple prediction performance index values ​​corresponding to multiple candidate quantile parameter combinations.

[0066] The candidate quantile parameter combination corresponding to the predicted effect index value that meets the preset conditions is determined as the first quantile parameter and the second quantile parameter.

[0067] Optionally, the first determining unit is configured to:

[0068] The quantile reference parameters are determined based on the preset target achievement rate and the number of stages in the transportation process;

[0069] The quantile value range is determined based on the quantile reference parameter, wherein the value of the quantile value range is not greater than the quantile reference parameter;

[0070] Multiple quantile parameters are obtained from the quantile value range according to a preset step size and combined to obtain multiple candidate quantile parameter combinations.

[0071] Thirdly, this application provides a computer device, the computer device comprising:

[0072] One or more processors;

[0073] Memory; and

[0074] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the waybill delivery time prediction method as described in any of the first aspects.

[0075] Fourthly, this application provides a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to perform the steps in the waybill delivery time prediction method described in any one of the first aspects.

[0076] This application provides a method and apparatus for predicting the delivery time of waybills. The waybill delivery process includes a first stage and a second stage. The method for predicting the delivery time of waybills includes: obtaining a first waybill to be predicted; determining a first-stage predicted delivery time of the first waybill to be predicted based on the first waybill to be predicted and multiple first historical waybill samples; updating the first waybill to be predicted based on the first-stage predicted delivery time to obtain a second waybill to be predicted; determining a second-stage predicted delivery time of the second waybill to be predicted based on the second waybill to be predicted and multiple second historical waybill samples; and determining a target waybill's predicted delivery time based on the second-stage predicted delivery time. This application divides the waybill delivery process into at least two stages: a first stage and a second stage. First, the predicted delivery time for the first stage is predicted based on a first waybill to be predicted and historical data. Then, the predicted delivery time for the first stage is updated to obtain a second waybill to be predicted. Finally, the predicted delivery time for the second stage is predicted based on the second waybill to be predicted and historical data. On the one hand, dividing the entire waybill delivery process into at least two stages for separate prediction reflects the differences in intermediate stages, making it more accurate than the old approach that treats the period from order placement to delivery as a whole. On the other hand, the prediction for subsequent stages is based on the prediction and updating of the first waybill to be predicted in the previous stage, enhancing the correlation between the two stages and making the prediction more accurate. Therefore, this application can improve the accuracy of the waybill delivery time prediction method. Attached Figure Description

[0077] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0078] Figure 1 This is a schematic diagram of a scenario for the waybill delivery time prediction system provided in an embodiment of this application.

[0079] Figure 2 This is a schematic flowchart of an embodiment of the waybill delivery time prediction method provided in this application.

[0080] Figure 3 This is a flowchart illustrating another embodiment of the waybill delivery time prediction method provided in this application.

[0081] Figure 4 This is a schematic diagram of an embodiment of the waybill delivery time prediction device provided in this application.

[0082] Figure 5 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0083] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0084] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0085] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0086] This application provides a method and apparatus for predicting waybill delivery time, which will be described in detail below.

[0087] Please see Figure 1 , Figure 1 This is a schematic diagram of a waybill delivery time prediction system provided in an embodiment of this application. The waybill delivery time prediction system may include a computer device 100, which integrates a waybill delivery time prediction device.

[0088] In this embodiment, the computer device 100 can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0089] In this embodiment, the computer device 100 described above can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device 100 can be a desktop computer, a portable computer, a network server, a handheld computer (Personal Digital Assistant, PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc. This embodiment does not limit the type of computer device 100.

[0090] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include more than one application scenario. Figure 1 The number of computer devices shown is more or less, for example Figure 1Only one computer device is shown in the document. It is understood that the waybill delivery time prediction system may also include one or more other computer devices capable of processing data, which are not specifically limited here.

[0091] In addition, such as Figure 1 As shown, the waybill delivery time prediction system may also include a memory 200 for storing data.

[0092] It should be noted that, Figure 1 The schematic diagram of the waybill delivery time prediction system shown is merely an example. The waybill delivery time prediction system and scenario described in this application embodiment are for the purpose of more clearly illustrating the technical solutions of this application embodiment and do not constitute a limitation on the technical solutions provided in this application embodiment. As those skilled in the art will know, with the evolution of waybill delivery time prediction systems and the emergence of new business scenarios, the technical solutions provided in this application embodiment are also applicable to similar technical problems.

[0093] First, this application provides a method for predicting the delivery time of a waybill. The waybill delivery process includes a first stage and a second stage. The method for predicting the delivery time of a waybill includes: obtaining a first waybill to be predicted; determining a first-stage predicted delivery time of the first waybill to be predicted based on the first waybill to be predicted and multiple first historical waybill samples; updating the first waybill to be predicted based on the first-stage predicted delivery time to obtain a second waybill to be predicted; determining a second-stage predicted delivery time of the second waybill to be predicted based on the second waybill to be predicted and multiple second historical waybill samples; and determining a target waybill's predicted delivery time based on the second-stage predicted delivery time.

[0094] like Figure 2 As shown, Figure 2 This is a flowchart illustrating an embodiment of the waybill delivery time prediction method provided in this application. The waybill delivery time prediction method includes the following steps S201 to S205:

[0095] S201. Obtain the first shipment to be predicted.

[0096] In this embodiment, the waybill feature vector of the first waybill to be predicted is obtained. The waybill feature vector may include waybill spatial features, waybill temporal features, and waybill attribute features. The waybill temporal features mainly include pick-up and delivery address information; the waybill time features mainly include order placement time, pickup shift, etc.; the waybill attribute features mainly include sender and recipient information, product type, timeliness type, cost, weight, and items to be transported, etc.

[0097] S202. Determine the first-stage predicted delivery time of the first shipment to be predicted based on the first shipment to be predicted and multiple first historical shipment samples.

[0098] In this embodiment, the waybill delivery process includes a first stage and a second stage. In other embodiments, the waybill delivery process includes a first stage, a second stage, and a third stage, wherein the first stage is the collection stage, which begins when the user places the order and ends when the waybill arrives at the origin transit station; the second stage is the transit stage, which begins when the waybill arrives at the origin transit station and ends when the waybill arrives at the destination transit station; and the third stage is the delivery stage, which begins when the waybill arrives at the destination transit station and ends when the user signs for the package. Of course, the delivery process can also be divided into more stages, depending on the specific circumstances.

[0099] In this embodiment of the application, determining the first-stage predicted delivery time of the first shipment to be predicted based on the first shipment to be predicted and multiple first historical shipment samples may include:

[0100] (1) Obtain the first stage start time of the first shipment to be predicted.

[0101] In this embodiment of the application, the first stage is the receiving stage. The start time of the first stage of the first order to be predicted can be the order placement time of the order. For example, if the user places an order at 5 o'clock, then the start time of the first stage is 5 o'clock.

[0102] (2) Obtain multiple first historical waybill samples that match the start time of the first phase.

[0103] In this embodiment, multiple initial historical waybill samples within a preset historical time period are obtained, and multiple first historical waybill samples matching the start time of the first stage are selected from these initial historical waybill samples. The preset historical time period can be 2 months, 3 months, etc., depending on the specific setting. For example, there are 1000 initial historical waybill samples within a 3-month historical period. The waybill feature vector of each initial historical waybill sample can include waybill spatial features, waybill time features, and waybill attribute features. Each initial historical waybill sample is labeled with a tag, which represents the actual delivery time of the first stage of the initial historical waybill sample. The waybill feature vector of each initial historical waybill sample includes the historical start time of the first stage, which is generally the order placement time.

[0104] In one specific embodiment, obtaining multiple first historical waybill samples that match the start time of the first phase from multiple initial historical waybill samples includes: determining a preset time range based on the start time of the first phase, wherein the preset time range includes the start time of the first phase, and determining initial historical waybill samples whose start time of the first phase belongs to the preset time range as multiple first historical waybill samples matching the start time of the first phase. The preset time range can be set according to specific circumstances; for example, if the start time of the first phase is 5:00, the preset time range is 4:50-5:10. Preferably, the midpoint of the preset time range is the start time of the first phase. Since the first historical waybill samples and the first waybill to be predicted have similar order placement times, predicting the predicted delivery time of the first waybill to be predicted based on the first historical waybill samples can be more accurate. Of course, in other embodiments, initial historical waybill samples whose start time of the first phase is equal to the start time of the first phase can also be determined as multiple first historical waybill samples matching the start time of the first phase.

[0105] (3) Determine the first stage predicted delivery time of the first shipment based on the first shipment to be predicted and multiple first historical shipment samples.

[0106] In this embodiment of the application, determining the first-stage predicted delivery time of the first shipment to be predicted based on the first shipment to be predicted and multiple first historical shipment samples may include: obtaining a preset target achievement rate; determining a first quantile parameter and a second quantile parameter based on the preset target achievement rate; and determining the first-stage predicted delivery time of the first shipment to be predicted based on the first quantile parameter, the first shipment to be predicted, and multiple first historical shipment samples. A quantile, also known as a percentile point, refers to a numerical point that divides the probability distribution range of a random variable into several equal parts. Commonly used quantiles include the median (i.e., quartile), quartile, and percentile.

[0107] In this embodiment of the application, the preset target achievement rate is a preset indicator, such as 0.85, which means that the predicted result of the first waybill to be predicted has an 85% probability of being delivered before the scheduled delivery time. That is, 85% of the waybills in a batch are required to be delivered before the scheduled delivery time.

[0108] In this embodiment of the application, determining the second-stage predicted delivery time of the second-to-be-predicted waybill based on the second waybill to be predicted and multiple second historical waybill samples may include: determining the second-stage predicted delivery time of the second waybill to be predicted based on the second quantile parameter, the second waybill to be predicted, and multiple second historical waybill samples.

[0109] In this embodiment, the first quantile parameter p1 can represent the probability of on-time delivery in the first stage, and the second quantile parameter p2 can represent the probability of on-time delivery in the second stage, used to adjust the accuracy of delivery time prediction. Of course, if the waybill delivery process includes a first stage, a second stage, and a third stage, then a third quantile parameter p3 is also obtained.

[0110] In one specific embodiment, determining the first quantile parameter and the second quantile parameter based on the preset target achievement rate may include: determining quantile reference parameters based on the preset target achievement rate and the number of stages in the transportation process, and defining the quantile reference parameters as the first quantile parameter p1 and the second quantile parameter p2. If the transportation process of the waybill includes a first stage, a second stage, and a third stage, then the quantile reference parameters are determined as the first quantile parameter p1 and the second quantile parameter p2 to obtain the third quantile parameter p3. For example, if the preset target achievement rate is 0.85, and the number of stages in the transportation process is two, then the quantile reference parameter is... If the number of stages in the transportation process is 3, then the quantile reference parameter is: First quantile parameter p1 = Second quantile parameter p2 = Third quantile parameter That is, treating each stage as an independent process and making predictions separately can simplify calculations.

[0111] In this embodiment of the application, determining the first-stage predicted delivery time of the first predicted waybill based on the first quantile parameter, the first waybill to be predicted, and multiple first historical waybill samples may include:

[0112] (1) Calculate the similarity of the first waybill to be predicted and multiple first historical waybill samples respectively.

[0113] Specifically, the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample are obtained. The waybill feature vector includes waybill spatial features, waybill temporal features and waybill attribute features. The vector similarity is calculated based on the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample to obtain the waybill similarity.

[0114] In this embodiment, the set of multiple first historical waybill samples is M = {g1, g2, ..., gm}. The waybill similarity between the first waybill to be predicted and the first historical waybill samples is calculated according to formula (1). The waybill feature vector of the first waybill to be predicted sample is used as f. j Where j = 1, 2, ..., n; the waybill feature vector of the first historical waybill sample is used as g. i Where i = 1, 2, ..., m, substituting into formula (1), we obtain the waybill similarity S(f j ,g i gi = (x1, x2, ..., xn), where x1 represents each feature. j = (y1, y2, ..., yn), where y1 represents each feature.

[0115]

[0116] (2) The first historical waybill sample with a similarity higher than the preset similarity with the first waybill to be predicted is put into the waybill set.

[0117] In this embodiment, after obtaining the similarity between the first waybill to be predicted and multiple first historical waybill samples, the first historical waybill samples with a similarity higher than a preset similarity are placed into a waybill set. The preset similarity can be set according to specific circumstances, for example, a preset similarity of 60%. In other embodiments, after obtaining the similarity between the first waybill to be predicted and multiple first historical waybill samples, the multiple first historical waybill samples can be sorted according to their similarity from smallest to largest, and a preset number k of the first historical waybill samples with the lowest similarity are placed into a waybill set H1. For example, H1 = L{w1 <w2<…<wk}。

[0118] (3) Obtain the target waybill sample from the waybill set according to the first quantile parameter.

[0119] In this embodiment of the application, the first historical waybill sample corresponding to the first quantile parameter in the waybill set is used as the target waybill sample. For example, if the first quantile parameter p1 is 95%, then the first historical waybill sample that ranks 95th in the waybill set is determined as the target waybill sample.

[0120] (4) The actual delivery time of the first stage of the target waybill sample is determined as the predicted delivery time of the first stage of the first waybill to be predicted.

[0121] The first-stage predicted delivery time T1 is based on the first quantile parameter p1, which is determined according to the preset target achievement rate. Therefore, the first-stage predicted delivery time can meet the preset target achievement rate and is the shortest among the predicted times that meet the preset target achievement rate. The first-stage predicted delivery time is the shortest while meeting the preset target achievement rate. The first quantile parameter p1 is 95%, indicating that there is a 95% probability that the order will arrive at the first-stage predicted delivery time at the end of the first stage.

[0122] S203. Update the first shipment to be predicted based on the predicted delivery time in the first stage to obtain the second shipment to be predicted.

[0123] In this embodiment, the start time of the second stage of the first forecasted waybill is updated to the predicted delivery time T1 of the first stage. That is, the waybill arrives at the originating transit station at the predicted delivery time T1 of the first stage and begins the second stage. This application updates the waybill after obtaining the delivery time for each stage and then performs the prediction for the next stage, linking the predictions of each stage and improving the accuracy of the prediction.

[0124] S204. Determine the second-stage predicted delivery time of the second shipment based on the second shipment to be predicted and multiple second historical shipment samples.

[0125] In this embodiment of the application, determining the second-stage predicted delivery time T2 of the second-to-be-predicted waybill based on the second waybill to be predicted and multiple second historical waybill samples includes: obtaining the second-stage start time of the second waybill to be predicted; obtaining multiple second historical waybill samples that match the second-stage start time; and determining the second-stage predicted delivery time T2 of the second waybill to be predicted based on the second waybill to be predicted and multiple second historical waybill samples.

[0126] Furthermore, determining the second-stage predicted delivery time T2 of the second-to-be-predicted waybill based on the second waybill to be predicted and multiple second historical waybill samples includes: determining the second-stage predicted delivery time T2 of the second waybill to be predicted based on the second quantile parameter, the second waybill to be predicted, and multiple second historical waybill samples.

[0127] Furthermore, the second-stage predicted delivery time T2 of the second-to-be-predicted waybill is determined based on the second quantile parameter, the second waybill to be predicted, and multiple second historical waybill samples. This includes: calculating the waybill similarity between the second waybill to be predicted and multiple second historical waybill samples respectively; placing second historical waybill samples with a similarity higher than a preset similarity to the second waybill to be predicted into a waybill set H2; obtaining a target waybill sample from the waybill set H2 based on the second quantile parameter; and determining the second-stage actual delivery time of the target waybill sample as the second-stage predicted delivery time T2 of the second waybill to be predicted.

[0128] S205. Determine the target waybill's predicted delivery time based on the predicted delivery time in the second stage.

[0129] Specifically, if the delivery process of a waybill consists of only a first stage and a second stage, then the predicted delivery time T2 of the second stage is determined as the predicted delivery time T of the waybill.

[0130] If the delivery process of a waybill consists of a first stage, a second stage, and a third stage, then the second waybill to be predicted is updated based on the predicted delivery time T2 of the second stage, resulting in the third waybill to be predicted. Based on the third waybill to be predicted and multiple third historical waybill samples, the predicted delivery time T3 of the third stage of the third waybill to be predicted is determined, and then the predicted delivery time T3 of the third stage is determined as the predicted delivery time T of the waybill.

[0131] In the previous embodiment, each stage of the waybill delivery process was calculated as an independent stage. However, in reality, the stages are interconnected. Therefore, to improve the accuracy of the prediction, this application provides another embodiment, see reference. Figure 3 , Figure 3 This is a flowchart illustrating another embodiment of the method for predicting waybill delivery time provided in this application. In a specific embodiment, the method for predicting waybill delivery time may include steps S301-S310:

[0132] S301. Obtain the first shipment to be predicted.

[0133] S302. Obtain the achievement rate of the preset target.

[0134] S303. Obtain multiple candidate quantile parameter combinations and training sets based on the preset target achievement rate.

[0135] Each candidate quantile parameter combination includes a first-stage candidate quantile parameter and a second-stage candidate quantile parameter. The training set includes multiple training samples and the actual delivery time of each training sample's waybill.

[0136] In a specific embodiment, obtaining multiple candidate quantile parameter combinations and a training set based on a preset target achievement rate may include:

[0137] (1) Determine the quantile reference parameters based on the preset target achievement rate and the number of stages in the transportation process.

[0138] In this embodiment, the quantile reference parameter is: Where Z represents the preset target achievement rate, and b is the number of stages in the delivery process. For example, if the preset target achievement rate is 0.85, and the number of stages in the delivery process is two, then the quantile reference parameter is... If the number of stages in the transportation process is 3, then the quantile reference parameter is:

[0139] (2) Determine the range of quantile values ​​based on the quantile reference parameter, wherein the value of the quantile range is not greater than the quantile reference parameter.

[0140] In one specific embodiment, the quantile reference parameter is 0.95, and the quantile value range is [0.5-0.85] or [0.5-0.95]. The quantile value range can be set according to specific circumstances.

[0141] (3) Obtain multiple quantile parameters from the quantile value range according to the preset step size and combine them to obtain multiple candidate quantile parameter combinations.

[0142] In one specific embodiment, the preset step size can be 0.05, which can be set according to the specific situation. For example, multiple candidate quantile parameter combinations are (0.85, 0.85), (0.8, 0.85), (0.75, 0.07), (0.7, 0.85), (0.85, 0.7).

[0143] S304. Based on the combination of multiple candidate quantile parameters, predict the delivery time of each training sample in the training set to obtain the predicted delivery time of the waybill for each training sample.

[0144] In this embodiment of the application, each training sample can be used as the first waybill to be predicted in S201, and the predicted delivery time of the waybill for each training sample can be calculated according to the steps of S201-S205.

[0145] S305. Based on the predicted delivery time of the waybill for each training sample and the actual delivery time of the waybill for each training sample, determine multiple prediction performance index values ​​corresponding to multiple candidate quantile parameter combinations.

[0146] In this embodiment of the application, the prediction performance index can be the achievement rate Y and the mean square error (MSE), or it can be the achievement rate Y and the mean absolute error (MAE). The mean square error L is shown in formula (2).

[0147]

[0148] Where yi represents the actual delivery time of the waybill for each training sample. Predict the delivery time for each waybill in the training samples, where n is the total number of training samples.

[0149] The achievement rate Y is shown in formula (3).

[0150] Y = m / n >= 0.85 (3)

[0151] Where n is the total number of training samples, and m is the number of training samples where the predicted actual delivery time of the waybill is later than the predicted delivery time of the waybill.

[0152] The mean absolute error (MAE) is shown in formula (4).

[0153]

[0154] Where yi represents the actual delivery time of the waybill for each training sample. Predict the delivery time for each waybill in the training samples, where n is the total number of training samples.

[0155] S306. The candidate quantile parameter combination corresponding to the prediction effect index value that meets the preset conditions is determined as the first quantile parameter and the second quantile parameter.

[0156] In this embodiment, the preset condition can be that the predicted performance index value with the smallest mean squared error is among those whose achievement rate Y is not less than the preset target achievement rate. Alternatively, the preset condition can be that the predicted performance index value with the smallest mean absolute error is among those whose achievement rate Y is not less than the preset target achievement rate. For example, multiple candidate quantile parameter combinations are: (0.85, 0.85), (0.8, 0.85), (0.75, 0.0.7), (0.7, 0.85), (0.85, 0.7). The corresponding predicted performance index values ​​are Y = 0.9, MAE = 0.5; Y = 0.86, MAE = 0.2; Y = 0.91, MAE = 0.1; Y = 0.7, MAE = 0.05; Y = 0.6, MAE = 0.5. First, we obtain the prediction performance index values ​​for an achievement rate Y that is not less than the preset target achievement rate: Y = 0.9, MAE = 0.5; Y = 0.86, MAE = 0.2; Y = 0.91, MAE = 0.1. Then, we select the value with the smallest mean squared error, i.e., Y = 0.91, MAE = 0.1. MAE describes the accuracy of the prediction result; the smaller the MAE, the higher the prediction accuracy. That is, when the achievement rate is above 85%, a smaller MAE parameter is better. Therefore, the quantile parameter combination (0.75, 0.0.7) corresponding to Y = 0.91, MAE = 0.1 is determined as the first quantile parameter and the second quantile parameter.

[0157] When the shipping process includes three stages, with the first quantile parameter p1 = 0.54, the second quantile parameter p2 = 0.74, and the third quantile parameter p3 = 0.82, and with an achievement rate of over 85%, the prediction error of the product is reduced by 38% compared to using the default parameters and by 55% compared to the old scheme.

[0158] S307. Determine the first-stage predicted delivery time of the first shipment based on the first quantile parameter, the first shipment to be predicted, and multiple first historical shipment samples.

[0159] In this embodiment, the specific implementation of S307 can be referred to the previous embodiment, and will not be repeated here.

[0160] S308. Update the first shipment to be predicted based on the predicted delivery time in the first stage to obtain the second shipment to be predicted.

[0161] In this embodiment, the specific implementation of S308 can be referred to the previous embodiment, and will not be repeated here.

[0162] S309. Determine the second-stage predicted delivery time of the second shipment based on the second quantile parameter, the second shipment to be predicted, and multiple second historical shipment samples.

[0163] In this embodiment, the specific implementation of S309 can be referred to the previous embodiment, and will not be repeated here.

[0164] S310. Determine the target waybill's predicted delivery time based on the predicted delivery time in the second stage.

[0165] In this embodiment, the specific implementation of S310 can be referred to the previous embodiment, and will not be repeated here.

[0166] To better implement the waybill delivery time prediction method in the embodiments of this application, based on the waybill delivery time prediction method, the embodiments of this application also provide a waybill delivery time prediction device, such as... Figure 4 As shown, the waybill delivery time prediction device 400 includes:

[0167] Acquisition unit 401 is used to acquire the first waybill to be predicted;

[0168] The first determining unit 402 is used to determine the first stage predicted delivery time of the first predicted waybill based on the first waybill to be predicted and multiple first historical waybill samples.

[0169] Update unit 403 is used to update the first shipment to be predicted based on the first stage predicted delivery time to obtain the second shipment to be predicted.

[0170] The second determining unit 404 is used to determine the second-stage predicted delivery time of the second shipment to be predicted based on the second shipment to be predicted and multiple second historical shipment samples.

[0171] The third determining unit 405 is used to determine the predicted delivery time of the target waybill based on the predicted delivery time of the second stage.

[0172] Optionally, the first determining unit 402 is used for:

[0173] Obtain the first phase start time of the first shipment to be predicted;

[0174] Obtain multiple first-stage historical waybill samples that match the start time of the first stage;

[0175] The first-stage predicted delivery time of the first shipment to be predicted is determined based on the first shipment to be predicted and multiple samples of first historical shipments.

[0176] Optionally, the first determining unit 402 is used for:

[0177] Obtain the achievement rate of the preset target;

[0178] The first quantile parameter and the second quantile parameter are determined based on the preset target achievement rate;

[0179] The first stage predicted delivery time of the first predicted waybill is determined based on the first quantile parameter, the first waybill to be predicted, and multiple first historical waybill samples.

[0180] The second determining unit 404 is used for:

[0181] The second-stage predicted delivery time of the second shipment to be predicted is determined based on the second quantile parameter, the second shipment to be predicted, and multiple samples of the second historical shipments.

[0182] Optionally, the first determining unit 402 is used for:

[0183] Calculate the similarity between the first waybill to be predicted and multiple first historical waybill samples, respectively;

[0184] The first historical waybill sample with a similarity higher than the preset similarity to the first waybill to be predicted is placed into the waybill set;

[0185] The target waybill sample is obtained from the waybill set based on the first quantile parameter;

[0186] The actual delivery time of the first stage of the target waybill sample is determined as the predicted delivery time of the first stage of the first waybill to be predicted.

[0187] Optionally, the first determining unit 402 is used for:

[0188] Obtain the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample, wherein the waybill feature vector includes waybill spatial features, waybill temporal features and waybill attribute features;

[0189] The similarity between the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample is calculated to obtain the waybill similarity.

[0190] Optionally, the first determining unit 402 is used for:

[0191] Based on the preset target achievement rate, multiple candidate quantile parameter combinations and training sets are obtained. Each candidate quantile parameter combination includes a first-stage candidate quantile parameter and a second-stage candidate quantile parameter. The training set includes multiple training samples and the actual delivery time of each training sample's waybill.

[0192] The delivery time of each training sample in the training set is predicted based on multiple combinations of candidate quantile parameters, and the predicted delivery time of each training sample is obtained.

[0193] Based on the predicted delivery time of each training sample's waybill and the actual delivery time of each training sample's waybill, determine multiple prediction performance index values ​​corresponding to multiple candidate quantile parameter combinations.

[0194] The candidate quantile parameter combination corresponding to the predicted effect index value that meets the preset conditions is determined as the first quantile parameter and the second quantile parameter.

[0195] Optionally, the first determining unit 402 is used for:

[0196] The quantile reference parameters are determined based on the preset target achievement rate and the number of stages in the delivery process;

[0197] The range of quantile values ​​is determined based on the quantile reference parameter, wherein the value within the quantile range is not greater than the quantile reference parameter.

[0198] Multiple quantile parameters are obtained from the quantile value range according to a preset step size and combined to obtain multiple candidate quantile parameter combinations.

[0199] This application also provides a computer device that integrates any of the waybill delivery time prediction devices provided in this application. The computer device includes:

[0200] One or more processors;

[0201] Memory; and

[0202] One or more applications, wherein the applications are stored in memory and configured to be executed by a processor, the steps of the waybill delivery time prediction method in any of the embodiments described above.

[0203] like Figure 5 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0204] The computer device may include components such as a processor 501 with one or more processing cores, a memory 502 with one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will understand that the computer device structure shown in the figures does not constitute a limitation on the computer device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0205] Processor 501 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in memory 502, and by calling data stored in memory 502, thereby providing overall monitoring of the computer device. Optionally, processor 501 may include one or more processing cores; processor 501 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Preferably, processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may not be integrated into processor 501.

[0206] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0207] The computer equipment also includes a power supply 503 that supplies power to the various components. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 503 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0208] The computer device may also include an input unit 504, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0209] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 501 in the computer device loads the executable files corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 501 runs the application programs stored in the memory 502 to realize various functions, as follows:

[0210] Obtain the first shipment to be predicted; determine the first stage predicted delivery time of the first shipment to be predicted based on the first shipment to be predicted and multiple first historical shipment samples; update the first shipment to be predicted based on the first stage predicted delivery time to obtain the second shipment to be predicted; determine the second stage predicted delivery time of the second shipment to be predicted based on the second shipment to be predicted and multiple second historical shipment samples; determine the predicted delivery time of the target shipment based on the second stage predicted delivery time.

[0211] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0212] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the waybill delivery time prediction methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps:

[0213] Obtain the first shipment to be predicted; determine the first stage predicted delivery time of the first shipment to be predicted based on the first shipment to be predicted and multiple first historical shipment samples; update the first shipment to be predicted based on the first stage predicted delivery time to obtain the second shipment to be predicted; determine the second stage predicted delivery time of the second shipment to be predicted based on the second shipment to be predicted and multiple second historical shipment samples; determine the predicted delivery time of the target shipment based on the second stage predicted delivery time.

[0214] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0215] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0216] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0217] The above provides a detailed description of a method and apparatus for predicting waybill delivery time according to embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for predicting waybill delivery time, characterized in that, The delivery process of the waybill includes a first stage and a second stage. The first stage is the collection stage, which begins when the user places the order and ends when the waybill arrives at the origin transit station. The second stage is the transit stage, which begins when the waybill arrives at the origin transit station and ends when the waybill arrives at the destination transit station. The method for predicting the delivery time of the waybill includes: Obtain the first shipment to be forecasted; Obtain the preset target achievement rate, which is used to characterize the probability of completing delivery before the predetermined delivery time; Based on the preset target achievement rate and the number of stages in the transportation process, determine the first quantile parameter and the second quantile parameter; Based on the first quantile parameter, the first waybill to be predicted, and multiple first historical waybill samples, the first stage predicted delivery time of the first waybill to be predicted is determined; wherein, the first historical waybill samples are matched with the first stage start time. The first shipment to be predicted is updated based on the predicted delivery time of the first stage to obtain the second shipment to be predicted. Based on the second quantile parameter, the second waybill to be predicted, and multiple second historical waybill samples, the second stage predicted delivery time of the second waybill to be predicted is determined; wherein, the second historical waybill samples are matched with the start time of the second stage. The target waybill's predicted delivery time is determined based on the second-stage predicted delivery time.

2. The method for predicting waybill delivery time according to claim 1, characterized in that, The method further includes: Obtain the first stage start time of the first shipment to be predicted; Obtain the plurality of first historical waybill samples that match the start time of the first stage; The first-stage predicted delivery time of the first shipment to be predicted is determined based on the first shipment to be predicted and the plurality of first historical shipment samples.

3. The method for predicting waybill delivery time according to claim 1, characterized in that, The step of determining the first-stage predicted delivery time of the first shipment to be predicted based on the first quantile parameter, the first shipment to be predicted, and multiple first historical shipment samples includes: Calculate the similarity between the first waybill to be predicted and the plurality of first historical waybill samples, respectively; The first historical waybill sample with a similarity higher than the preset similarity to the first waybill to be predicted is placed into the waybill set; The target waybill sample is obtained from the waybill set according to the first quantile parameter; The actual delivery time of the first stage of the target waybill sample is determined as the predicted delivery time of the first stage of the waybill to be predicted.

4. The method for predicting waybill delivery time according to claim 3, characterized in that, The step of calculating the similarity between the first waybill to be predicted and the plurality of first historical waybill samples includes: Obtain the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample, wherein the waybill feature vector includes waybill spatial features, waybill temporal features and waybill attribute features; The similarity of the waybill is obtained by calculating the vector similarity between the waybill feature vector of the first waybill to be predicted and the waybill feature vector of the first historical waybill sample.

5. The method for predicting waybill delivery time according to claim 1, characterized in that, The determination of the first quantile parameter and the second quantile parameter based on the preset target achievement rate and the number of stages in the transportation process includes: Based on the preset target achievement rate, multiple candidate quantile parameter combinations and training sets are obtained. Each candidate quantile parameter combination includes a first-stage candidate quantile parameter and a second-stage candidate quantile parameter. The training set includes multiple training samples and the actual delivery time of each training sample's waybill. The delivery time of each training sample in the training set is predicted based on the combination of multiple candidate quantile parameters, and the predicted delivery time of each training sample is obtained. Based on the predicted delivery time of each training sample's waybill and the actual delivery time of each training sample's waybill, determine multiple prediction performance index values ​​corresponding to multiple candidate quantile parameter combinations. The candidate quantile parameter combination corresponding to the predicted effect index value that meets the preset conditions is determined as the first quantile parameter and the second quantile parameter.

6. The method for predicting waybill delivery time according to claim 5, characterized in that, The step of obtaining multiple candidate quantile parameter combinations and training sets based on the preset target achievement rate includes: The quantile reference parameters are determined based on the preset target achievement rate and the number of stages in the transportation process; The quantile value range is determined based on the quantile reference parameter, wherein the value of the quantile value range is not greater than the quantile reference parameter; Multiple quantile parameters are obtained from the quantile value range according to a preset step size and combined to obtain multiple candidate quantile parameter combinations.

7. A device for predicting waybill delivery time, characterized in that, The delivery process of the waybill includes a first stage and a second stage. The first stage is the collection stage, which begins when the user places the order and ends when the waybill arrives at the origin transit station. The second stage is the transit stage, which begins when the waybill arrives at the origin transit station and ends when the waybill arrives at the destination transit station. The waybill delivery time prediction device includes: The acquisition unit is used to acquire the first waybill to be predicted. The first determining unit is configured to obtain a preset target achievement rate, which represents the probability of completing delivery before a predetermined delivery time; determine a first quantile parameter and a second quantile parameter based on the preset target achievement rate and the number of stages in the delivery process; and determine the first stage predicted delivery time of the first shipment based on the first quantile parameter, the first shipment to be predicted, and multiple first historical shipment samples; wherein the first historical shipment samples are matched with the start time of the first stage. The update unit is used to update the first waybill to be predicted based on the predicted delivery time of the first stage, so as to obtain the second waybill to be predicted. The second determining unit is used to determine the second-stage predicted delivery time of the second-to-be-predicted waybill based on the second quantile parameter, the second waybill to be predicted, and multiple second historical waybill samples; wherein the second historical waybill samples are matched with the start time of the second stage. The third determining unit is used to determine the predicted delivery time of the target waybill based on the predicted delivery time in the second stage.

8. A computer device, characterized in that, The computer device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the waybill delivery time prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to execute the steps of the method for predicting the delivery time of a waybill as described in any one of claims 1 to 6.

Images