Order cold region prediction method, device and electronic equipment

Abstract

The present application discloses an order cold region prediction method, apparatus and electronic device. The method includes: predicting the number of empty vehicles in a first region on a preset date; obtaining the shipment order information of M second regions in N days in history, and establishing N scenarios according to the shipment order information of each day in the N days; determining the expected probability of each scenario in the N scenarios occurring on the preset date according to a probability model; respectively matching the empty vehicles with the shipment orders in the N scenarios, traversing all matching schemes, and calculating the expected value of each matching scheme; when the maximum expected value among all matching schemes is less than a preset value, it is determined that the first region is an order cold region on the preset date. It is possible to predict a certain region based on historical scenarios, effectively predict the generation of order cold regions, provide important data support in the process of order price adjustment and order allocation, and make order price adjustment and order allocation more accurate.

Description

Technical Field

[0001] This application relates to the field of logistics technology. Specifically, it relates to a method, device, and electronic device for predicting cold regions of orders. Background Art

[0002] Currently, in the logistics field, especially in the truck freight field, there is the concept of cold regions for orders, which is also called "desert cities", and its impact on freight transportation is very large. "Desert cities" can be simply understood as regions or cities where the inbound volume is much greater than the outbound volume. That is, when a vehicle delivers goods to a "desert city", not only can it not make a profit, but it will also incur losses. Moreover, "desert cities" are not fixed, and it is very likely that due to factors such as seasonal climate changes, some regions or cities will form "desert cities" or some "desert cities" will disappear. If a vehicle delivers goods to a "desert city", it is very likely that the vehicle will not find a subsequent connection order in the city, so it can only leave the city empty. In this case, the greater the cost generated by the empty run, the greater the loss of the carrier. In addition, even if some vehicles find a connection order in the city, but since the delivery time of this connection order is several days later, it causes the vehicle to wait in place. During this period, the vehicle's outage will also bring certain losses.

[0003] Therefore, how to accurately predict cold regions of logistics orders in advance has become an urgent problem to be solved. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, and electronic device for predicting cold regions of orders, to solve the problem of how to accurately predict cold regions of logistics orders in advance.

[0005] To achieve the above object, according to the first aspect of the present application, an order cold region prediction method is provided, including: predicting the number of empty vehicles in a first region on a preset date; obtaining the shipment order information of M second regions in N days in history, and establishing N scenarios according to the shipment order information of each day in the N days. Each scenario includes the shipment order information of the M second regions within one day, where M and N are positive integers greater than zero; determining the expected probability of each of the N scenarios occurring on the preset date according to a probability model, where the probability model is a model established based on the shipment order information of M regions in N days in history for determining the occurrence probability of the N scenarios in history on the preset date; respectively matching the empty vehicles with the shipment orders in the N scenarios, traversing all matching schemes, and calculating the expected value of each matching scheme. The expected value is the sum of the expected revenues of all empty vehicles in the matching scheme, where the expected value = (the price of the matched order - the empty driving cost for receiving the order) × the expected probability of the scenario where the matched order is located; when the maximum expected value among all matching schemes is less than a preset value, it is determined that the first region is an order cold region on the preset date.

[0006] Optionally, before determining the expected probability of each of the N scenarios occurring on the preset date according to the probability model, the method further includes: establishing a probability model according to the distance relationship between each scenario and the preset date in the time dimension and / or the cycle dimension.

[0007] Optionally, in the time dimension, the expected probability of the scenario occurring is inversely correlated with the number of days between the actual occurrence date of the scenario and the preset date.

[0008] Optionally, in the cycle dimension, the expected probability of the scenario occurring is positively correlated with the number of days between the actual occurrence date of the scenario and the preset date within the cycle.

[0009] Optionally, predicting the number of empty vehicles in the first region includes: predicting the number of shipment orders and the number of inbound orders in the first region on the preset date. If the number of inbound orders is greater than the number of shipment orders, the difference between the number of inbound orders and the number of shipment orders is used as the number of empty vehicles.

[0010] Optionally, determining the expected probability of each scenario occurring on the preset date according to the probability model includes: determining the occurrence probability of the N scenarios on the preset date according to the probability model; regularizing the N occurrence probabilities to obtain the expected probabilities of the N scenarios.

[0011] To achieve the above object, according to the first aspect of the present application, an order cold region prediction device is provided, including: an empty vehicle prediction module for predicting the number of empty vehicles in a first region on a preset date; a first acquisition module for acquiring the shipment order information of M second regions in N days in history, and establishing N scenarios according to the shipment order information of each day in the N days. Each scenario includes the shipment order information of the M second regions within one day, where M and N are positive integers greater than zero; a probability prediction module for determining the expected probability of each of the N scenarios occurring on the preset date according to a probability model, and the probability model is a model established according to the shipment order information of M regions in N days in history for determining the occurrence probability of the N scenarios in history on the preset date; an order matching module for respectively matching the empty vehicles with the shipment orders in the N scenarios, traversing all matching schemes, and calculating the expected value of each matching scheme. The expected value is the sum of the expected revenues of all empty vehicles in the matching scheme, where the expected value = (the price of the matched order - the cost of empty driving for receiving the order) × the expected probability of the scenario where the matched order is located; a region determination module for determining that the first region is an order cold region on the preset date when the maximum expected value among all matching schemes is less than a preset value.

[0012] To achieve the above object, according to the third aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the order cold region prediction method described in any item of the first aspect above.

[0013] To achieve the above object, according to the fourth aspect of the present application, an electronic device is provided, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to cause the at least one processor to execute the order cold region prediction method described in any item of the first aspect above.

[0014] In the embodiments of the present application, multiple second regions outside the first region to be predicted are used to establish N scenarios according to the order information in the past N days. Each scenario includes the shipping order information of the M second regions within one day, and the expected probability of each scenario on a preset date is calculated. The empty trucks predicted in the first region are respectively matched with the shipping orders in the N scenarios, and the expected value of each matching scheme is calculated based on the expected probability of the scenario where the shipping order is located and the price of the shipping order. When the maximum expected value among all matching schemes is less than the preset value, it can be determined that the first region is a cold order region on the preset date. The prediction of a certain region can be based on historical scenarios, so as to accurately predict whether a certain region is a cold order region on a certain day, effectively determine the generation of the cold order region, and thus provide important data support in the process of order price adjustment and order allocation, making the order price adjustment and order allocation more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting a part of the present application are used to provide a further understanding of the present application, making other features, objects, and advantages of the present application more obvious. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0016] Figure 1 is a flowchart of a method for predicting a cold order region according to an embodiment of the present application;

[0017] Figure 2 is a schematic diagram of a probability model established according to the distance relationship between each scenario and the preset date in the time dimension according to an embodiment of the present application;

[0018] Figure 3 is a schematic diagram of a probability model established according to the distance relationship between each scenario and the preset date in the cycle dimension according to an embodiment of the present application;

[0019] Figure 4 is a schematic diagram of a probability model established according to the distance relationship between each scenario and the preset date in the time dimension and the cycle dimension according to an embodiment of the present application;

[0020] Figure 5 is a block diagram of the composition of a device for predicting a cold order region according to an embodiment of the present application;

[0021] Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to implement the embodiments of this application described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the drawings and describe this application in detail in conjunction with the embodiments.

[0025] According to an embodiment of this application, an order cold region prediction method is provided. As Figure 1 shown, the method includes the following steps:

[0026] S101. Predict the number of empty trucks in the first region on a preset date. As an exemplary embodiment, the number of empty trucks can be determined based on the number of outbound orders and inbound orders in the first region on the preset date. Specifically, the above-mentioned number of outbound orders and inbound orders can be compared. If the number of inbound orders is greater than the number of outbound orders, the difference between the number of inbound orders and the number of outbound orders is used as the number of empty trucks; if the number of inbound orders is not greater than the number of outbound orders, the first region is not an order cold region on the preset date. Exemplarily, before predicting the number of outbound orders and inbound orders in the first region on the preset date, the first region to be predicted can be selected. In this embodiment, the type of the first region is not limited. The region can be a region, county, city, province or other artificially divided regions or areas. In this embodiment, the first region can be taken as an example of a city, such as Zhangye City. Of course, it can also be certain regions, administrative regions, etc. The preset date can be a certain day, such as August 1, 2021.

[0027] After that, it is necessary to predict the number of outbound orders and inbound orders in the first region on a preset date. Since there are methods in the current prior art for predicting the number of outbound orders and inbound orders in a certain region on a certain day, the present application does not limit the prediction method, as long as it can predict the number of outbound orders and inbound orders in the first region on the preset date.

[0028] After predicting the number of outbound orders and inbound orders in the first region on the preset date, the sizes of the outbound order quantity and the inbound order quantity can be directly compared. When the inbound order quantity is greater than the outbound order quantity, the difference between the inbound order quantity and the outbound order quantity is used as the number of empty trucks.

[0029] S102. Obtain the outbound order information of M second regions in N days in history, and establish N scenarios according to the outbound order information of each day in the N days. Each scenario includes the outbound order information of the M second regions within one day, where M and N are positive integers greater than zero. As an exemplary embodiment, in this embodiment, the second region can be a region different from the first region, and the M second regions can be all other regions except the first region within the country, such as cities; if considering reducing the calculation amount, regions that are far from the first region can be not used as the second regions, which can reduce the calculation amount.

[0030] After determining the M second regions, the outbound order information of these second regions in N days in history can be obtained from the database. In this embodiment, the outbound order information can include various relevant information such as the outbound order price, loading place, unloading place, loading time, shipping time, etc., so as to complete the subsequent matching work; regarding which days in history are selected as the N days in history, it is not limited in this embodiment. It is entirely possible to select all historical data, or select some continuous or discontinuous historical data, and all of them can complete the subsequent prediction work; relatively speaking, the more historical data is used, that is, the larger N is, the more guaranteed the final result is.

[0031] Subsequently, according to the outbound orders of each day in the N days, N scenarios are established correspondingly. Each scenario contains the outbound order information of the M second regions within one day.

[0032] For example, the first region is Zhangye City, and the preset date is August 26, 2020 (assuming the current date is August 25, 2020).

[0033] The M second regions are Jiuquan City and Jinchang City. Then, the historical outbound order data of N days on and before August 25, 2020 can be obtained. Here, for the convenience of explanation, only two regions are used as the M second cities, and at the same time, only the historical data of 3 days from August 20 to 22, 2020 is assumed for explanation.

[0034] Three scenarios are correspondingly established according to the shipping orders for each of the three days.

[0035] For example, within August 20, 2020, there is a shipping order A in Jiuquan City and no shipping order in Jinchang City. Then the corresponding scenario can be

[0036] Scenario 1 (the scenario corresponding to August 20, 2020):

[0037] Jiuquan City, Order A: Depart from Jiuquan City to Dunhuang City, order price 1000 yuan.

[0038] It should be noted that the scenarios can be established in the form of a list. In addition, the order information in the above scenarios is only for convenience of explanation. In actual situations, more information, even all the information of the shipping orders, can be included when establishing scenarios.

[0039] The information of the following two scenarios is given below.

[0040] Within August 21, 2020, there is one shipping order in Jiuquan City and two shipping orders in Jinchang City. Then the corresponding scenario can be

[0041] Scenario 2 (the scenario corresponding to August 21, 2020):

[0042] Jiuquan City, Order B: Depart from Jiuquan City to Jiayuguan City, order price 100 yuan.

[0043] Jinchang City, Order C: Depart from Jinchang City to Wuwei City, order price 200 yuan.

[0044] Jinchang City, Order D: Depart from Jinchang City to Wuwei City, order price 200 yuan.

[0045] Within August 22, 2020, there are two shipping orders in Jiuquan City and no shipping order in Jinchang City. Then the corresponding scenario can be

[0046] Scenario 3 (the scenario corresponding to August 22, 2020):

[0047] Jiuquan City, Order E: Depart from Jiuquan City to Jiayuguan City, order price 100 yuan.

[0048] Jiuquan City, Order F: Depart from Jiuquan City to Jiayuguan City, order price 100 yuan.

[0049] In the above example, three scenarios are correspondingly established according to the shipping orders for each of the three days from August 20 to 22, 2020. Each scenario contains the shipping order information of the two second-level regions, Jiuquan City and Jinchang City, within one day.

[0050] S103. Determine the expected probability of each of the N scenarios occurring on the preset date according to the probability model. The probability model is a model established based on the shipment order information of M second regions in N historical days for determining the occurrence probability of N historical scenarios on the preset date. As an exemplary embodiment. Since there are repeated occurrences of orders with the same route and the same price, and the scenario not only includes various information of individual orders but also the correlation relationships between various orders, a probability model is established based on the scenario using the distance relationship between the date corresponding to the scenario and the preset date. After that, as long as the date or time corresponding to the scenario is input into the probability model, the occurrence probability of the scenario can be obtained. Here, an existing probability model in the prior art, such as a uniform distribution probability model, can also be directly used.

[0051] After obtaining the occurrence probabilities of the N scenarios on the preset date respectively, the N occurrence probabilities can be regularized to obtain the expected probabilities of the N scenarios respectively, so as to ensure that the sum of the expected probabilities of the N scenarios is 1.

[0052] Suppose the occurrence probability of scenario 1 obtained is 0.07, the occurrence probability of scenario 2 is 0.23, and the occurrence probability of scenario 3 is 0.6. Then, after regularization, the expected probability of scenario 1 is 0.078, the expected probability of scenario 2 is 0.256, and the expected probability of scenario 3 is 0.666.

[0053] S104. Match the empty vehicles with the shipment orders in the N scenarios respectively, traverse all matching schemes, and calculate the expected value of each matching scheme. The expected value is the sum of the expected revenues of all empty vehicles in the matching scheme, where the expected revenue = (the price of the matching order - the empty driving cost for receiving the order) × the expected probability of the scenario where the matching order is located.

[0054] Since the number of empty vehicles has been obtained previously, it is equivalent to having the corresponding number of empty vehicles. Here, only the empty vehicles need to be matched with the shipment orders in the N scenarios; the two parties to be matched are the empty vehicles and the shipment orders in the N scenarios, and multiple matching schemes can be obtained;

[0055] Suppose there are currently two empty vehicles, namely vehicle 1 and vehicle 2, and 6 shipment orders in the N scenarios, from order A to order F.

[0056] For example, in scheme 1, vehicle 1 is matched with order A, and vehicle 2 is matched with order B;

[0057] In scheme 2, vehicle 1 is matched with order A, and vehicle 2 is matched with order C;

[0058] The specific schemes are not listed one by one here, but a total of 30 schemes can be matched here.

[0059] It should be noted that the number of matching schemes in practice may be relatively large. However, there are currently many algorithms or technologies that can use computers to match and traverse all schemes, which can be used to save matching time and will not be elaborated here.

[0060] Subsequently, it is necessary to calculate the expected value of each matching scheme. The expected value is the sum of the expected revenues of all empty vehicles in the scheme; the expected revenue = (the price of the matched order - the empty driving cost for receiving the order) × the expected probability of the scenario where the matched order is located.

[0061] First, let's talk about the empty driving cost for receiving an order. The empty driving cost for receiving an order is the cost generated when the vehicle drives empty to the loading place to undertake the order. Here, the distance of driving empty to the loading place is known, that is, the driving distance from the first city (i.e., the first region) to a certain second city (i.e., the second region) (relevant values can be obtained using existing technologies such as navigation). And the cost generated by the vehicle for driving per unit distance can also be obtained based on existing data, such as data on the vehicle's fuel consumption per 100 kilometers and the oil price, etc. Then, the empty driving cost for receiving an order can be obtained based on these data. In the implementation process, there are many methods to obtain the empty driving cost for receiving an order. The unit distance driving cost of the vehicle can be comprehensively considered and set as a fixed value, and the product of the driving distance from the first city to the second city where the order is located and this fixed value is used as the empty driving cost for receiving the order.

[0062] Use the data in the above example to continue the description of the steps;

[0063] Suppose the empty driving cost for the vehicle to receive an order from Zhangye City to Jiuquan City is 400 yuan, and the empty driving cost for the vehicle to receive an order from Zhangye City to Jinchang City is 400 yuan.

[0064] Example

[0065] In Scheme 1

[0066] Since Vehicle 1 is matched with Order A, the price of the matched order is the price of Order A, which is 1000 yuan; the empty driving cost for receiving the order is the empty driving cost of Vehicle 1. Since Vehicle 1 is currently located in Zhangye City and the loading place of Order A is in Jiuquan City, the empty driving cost of the vehicle from Zhangye City to Jiuquan City is the empty driving cost for receiving the order when Vehicle 1 is matched with Order A, which is 400 yuan. In addition, the expected probability of Scenario 1 where Order A is located is 0.078. Therefore, the expected revenue of Vehicle 1 and Order A = (the price of the matched order - the empty driving cost for receiving the order) × the expected probability of the scenario where the matched order is located = (1000 - 400) × 0.078 = 46.8;

[0067] Similarly, since vehicle 2 is matched with order B, the price of the matched order is the price of order B, which is 100 yuan; the empty running cost for taking the order is the empty running cost of vehicle 2. Since vehicle 2 is currently located in Zhangye City and the loading location of order B is in Jinchang City, the empty running cost of the vehicle from Zhangye City to Jinchang City is the empty running cost when vehicle 2 is matched with order B, which is 400 yuan. In addition, the expected probability of scenario 2 where order B is located is 0.256. Therefore, the expected revenue of vehicle 2 and order B = (price of the matched order - empty running cost for taking the order) × expected probability of the scenario where the matched order is located = (100 - 400) × 0.256 = -76.8;

[0068] Actually, the expected value of Plan 1 can be calculated here, that is, the expected value of Plan 1 = the sum of the expected revenues of all empty vehicles = the expected revenue of vehicle 1 + the expected revenue of vehicle 2 = 46.8 - 76.8 = -30; However, for a more detailed explanation, the following calculation process that can be omitted is described here.

[0069] The matching plan in Plan 1 is that vehicle 1 is matched with order A, vehicle 2 is matched with order B, and at the same time, no vehicle is matched with order C, order D, order E, or order F.

[0070] Since no vehicle is matched with order C, order C belongs to the order that is not matched or order C does not belong to the matched order. Therefore, the price of the matched order can be recorded as 0; similarly, since there is no match, there will be no empty running cost for taking the order. Therefore, the empty running cost for taking the order can be recorded as 0; in addition, the expected probability of scenario 2 where order C is located is 0.256; Therefore, it can be recorded that the expected revenue of no vehicle and order C = (price of the matched order - empty running cost for taking the order) × expected probability of the scenario where the matched order is located = (0 - 0) × 0.256 = 0;

[0071] Similarly, the expected probability of scenario 2 where order D is located is 0.256. Therefore, it can be recorded that the expected revenue of no vehicle and order D = (0 - 0) × 0.256 = 0;

[0072] Similarly, the expected probability of scenario 3 where order E is located is 0.666. Therefore, it can be recorded that the expected revenue of no vehicle and order E = (0 - 0) × 0.666 = 0;

[0073] Similarly, the expected probability of scenario 3 where order F is located is 0.666. Therefore, it can be recorded that the expected revenue of no vehicle and order F = (0 - 0) × 0.666 = 0;

[0074] Through the above calculations, the expected value of Plan 1 = 46.8 - 76.8 + 0 + 0 + 0 + 0 = -30;

[0075] Similarly, in Solution 2, the expected revenue of Vehicle 1 and Order A = (1000 - 400) × 0.078 = 46.8; the expected revenue of Vehicle 2 and Order C = (200 - 400) × 0.256 = -51.2; then the expected value of Solution 2 = 46.8 - 51.2 = -4.4.

[0076] Here, the expected values of 30 solutions can be obtained in total.

[0077] It should be noted that even when the number of empty vehicles is greater than the number of orders, the above method is equally applicable, that is, since the vehicle is not matched, its corresponding expected revenue = 0; however, in actual situations, as long as the values of M and N are not very small, the probability of this situation occurring is relatively small.

[0078] Next, regarding the expected probability of the scenario where the scenario order is located;

[0079] Since the expected probabilities of N scenarios have been obtained previously, they can be directly used here. Here, the above example is used for illustration. In the above example, three scenarios are provided, namely Scenario 1, Scenario 2, and Scenario 3.

[0080] The expected probability of Scenario 1 is 0.078. Since Scenario 1 includes Order A, the expected probability of the scenario where the scenario order of Order A is located is 0.078;

[0081] Similarly,

[0082] The expected probability of Scenario 2 is 0.256. Since Scenario 2 includes Order B, Order C, and Order D, the expected probabilities of the scenarios where the scenario orders of Order B, Order C, and Order D are located are all 0.256;

[0083] The expected probability of Scenario 3 is 0.666. Since Scenario 3 includes Order E and Order F, the expected probabilities of the scenarios where the scenario orders of Order E and Order F are located are all 0.666;

[0084] As shown in the following table

[0085]

[0086] S105. When the maximum expected value among all matching solutions is less than the preset value, it is determined that the first region is a desert area on the preset date.

[0087] It is possible to traverse the expected values of all matching scenarios and select the matching scenario with the maximum expected value. When the expected value of the matching scenario with the maximum expected value is less than the preset value, and the preset value is 0. Of course, other values can also be set as the preset value according to the actual situation. Then, this first region is a cold order region (desert city) on the preset date. Exemplarily, refer to the description of the calculation of the expected values of each matching scenario in the above embodiments. Since the maximum of the expected values of these 30 scenarios is -4.4, which is less than 0 (the preset value), Zhangye City (the first region) is a cold order region (desert city) on August 26, 2020 (the preset date).

[0088] Establish N scenarios for multiple second regions outside the first region to be predicted according to the order information in the previous N days. Each scenario includes the shipping order information of the M second regions within one day, and calculate the expected probability of each scenario on the preset date. Match the empty trucks predicted for the first region with the shipping orders in the N scenarios respectively, and calculate the expected values of each matching scenario based on the expected probability of the scenario where the shipping order is located and the price of the shipping order. When the maximum expected value among all matching scenarios is less than the preset value, it can be determined that the first region is a cold order region on the preset date. It is possible to predict a certain region based on historical scenarios, so as to accurately predict whether a certain region is a cold order region on a certain day, effectively determine the generation of cold order regions, and thus provide important data support for the order price adjustment and order allocation processes, making the order price adjustment and order allocation more accurate.

[0089] After determining the cold order region, it is also possible to send the information of the cold order region (address information, time information, etc.) to the client of the user or the driver to notify the user or the driver, reduce the entry of freight vehicles into this region, and thus reduce the situation of their losses, while avoiding waste of resources.

[0090] This embodiment will elaborate on the establishment of the model.

[0091] First of all, it should be noted that the model is obtained before the calculation of the expected value of the matching scenario, but its establishment is not limited to being executed before or after which step before calculating the expected value of the matching scenario; the probability model can also be established in advance. In addition, the model can also be established separately in an independent system or device, and then directly provided for the system to use through the acquisition method.

[0092] As an exemplary embodiment, the method for establishing the model can be: establish a probability model according to the relationship between each scenario and the preset date in the time dimension; or establish a probability model according to the relationship between each scenario and the preset date in the cycle dimension; or establish a probability model according to the relationship between each scenario and the preset date in both the time dimension and the cycle dimension. The following will explain each case separately:

[0093] 1. Establish a probability model according to the distance relationship between each scenario and the preset date in the time dimension, and obtain the occurrence probabilities of N scenarios based on the probability model (which can also be understood as the occurrence or recurrence probabilities of N scenarios on the preset date). Among them, in the said time dimension, the expected probability of the scenario occurrence is inversely correlated with the number of days between the actual occurrence date of the scenario and the preset date. Specifically, the farther the actual occurrence date of the scenario is from the preset date, the lower the occurrence probability; the closer the actual occurrence date of the scenario is to the preset date, the higher the occurrence probability. As Figure 2 shown, the figure gives an illustrative explanation that the closer the actual occurrence date of the scenario is to the preset date, the higher the occurrence probability. In the figure, since scenario 2 is closer to the preset date than scenario 1, the occurrence probability of scenario 2 is higher than that of scenario 1.

[0094] 2. Establish a probability model according to the distance relationship between each scenario and the preset date in the cycle dimension, and obtain the occurrence probabilities of N scenarios on the preset date based on the probability model. Among them, in the said cycle dimension, the expected probability of the scenario occurrence is positively correlated with the number of days between the actual occurrence date of the scenario within the cycle and the preset date. Specifically, the farther the position of the actual occurrence date of the scenario within the cycle is from the position of the preset date within the cycle, the lower the occurrence probability; the closer the position of the actual occurrence date of the scenario within the cycle is to the position of the preset date within the cycle, the higher the occurrence probability. It should be noted here that the cycle can be a cycle such as a week, a month, a quarter, a year, or a cycle of alternating peak and off-peak seasons in logistics and freight transportation, etc. As Figure 3 shown, if scenario 2 and the preset date are both on Wednesday and scenario 1 is on Sunday, from the cycle dimension, scenario 2 is closer to the preset date while scenario 1 is farther away, so the occurrence probability of scenario 2 is higher than that of scenario 1.

[0095] 3. Establish a probability model according to the distance relationship between each scenario and the preset date in both the time dimension and the cycle dimension, and obtain the occurrence probabilities of N scenarios on the preset date. It can be that the farther the actual occurrence date of the scenario is from the preset date and the farther the position of the actual occurrence date of the scenario within the cycle is from the position of the preset date within the cycle, the lower the occurrence probability; the closer the actual occurrence date of the scenario is to the preset date and the closer the position of the actual occurrence date of the scenario within the cycle is to the position of the preset date within the cycle, the higher the occurrence probability. As Figure 4 shown, by integrating the time dimension and the cycle dimension, a probability model can be established, and then the occurrence probabilities of scenario 2 and scenario 1 can be obtained.

[0096] Furthermore, for the establishment of the above-mentioned 3rd probability model, a more specific model is given for explanation as follows.

[0097] The probability model established according to the distance relationship between the scenario and the preset date in the time dimension and the cycle dimension is as follows:

[0098]

[0099] Among them, T x represents the value corresponding to scenario x in the time dimension, and this value increases as the difference in the number of days between the date of the scenario and the preset date increases.

[0100] C x represents the value corresponding to scenario x in the cycle dimension, and this value can be set artificially. For example, Figure 4 as shown in x if 2 scenarios involve a total of 4 cycles, then the C x corresponding to the preset date within one cycle is 0.9, the C x corresponding to a difference of one cycle is 0.8, the C x corresponding to a difference of two cycles is 0.7, and the C corresponding to a difference of three cycles is 0.6. Then finally, C2 = 0.8 and C1 = 0.6; this value can also be directly obtained using historical data. For example, the formula becomes x where D0 represents the date of the preset date, and D

[0101] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0102] According to an embodiment of the present application, there is also provided an order cold region prediction device for implementing the above Figure 1 method. As Figure 5 shown, this device includes:

[0103] An empty vehicle prediction module 21, used to predict the number of empty vehicles in the first region on the preset date;

[0104] A first acquisition module 22, used to acquire the shipment order information of M second regions in the past N days, and establish N scenarios according to the shipment order information of each day in the N days. Each scenario includes the shipment order information of the M second regions within one day, where M and N are positive integers greater than zero;

[0105] A probability prediction module 23, configured to determine the expected probability of each of the N scenarios occurring on the preset date according to a probability model, where the probability model is a model established based on the shipment order information of M regions in the historical N days for determining the occurrence probability of the historical N scenarios on the preset date;

[0106] An order matching module 24, configured to respectively match empty vehicles with the shipment orders in the N scenarios, traverse all matching schemes, and calculate the expected value of each matching scheme, where the expected value is the sum of the expected values of all empty vehicles in the matching scheme, and the expected revenue = (the price of the matched order - the cost of empty driving for receiving the order) × the expected probability of the scenario where the matched order is located; a region determination module 25, configured to determine that the first region is an order cold region on the preset date when the maximum expected value among all matching schemes is less than a preset value.

[0107] Specifically, for the specific processes of each unit and module in the device of the embodiment of the present application to implement their functions, reference may be made to the relevant descriptions in the method embodiments, which will not be elaborated here.

[0108] Figure 6 is a structural block diagram of an optional electronic device according to an embodiment of the present application, as Figure 6 shown, including a processor 602, a communication interface 604, a memory 606, and a communication bus 608. Among them, the processor 602, the communication interface 604, and the memory 606 complete mutual communication through the communication bus 608, where,

[0109] The memory 606 is used to store a computer program;

[0110] The processor 602 is configured to execute the computer program stored on the memory 606 to implement the process steps of the order cold region prediction method in the above embodiments.

[0111] Optionally, in this embodiment, the above communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0112] The communication interface is used for communication between the above electronic device and other devices.

[0113] The memory may include RAM and may also include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0114] As an example, as Figure 6 shown, the above-mentioned memory 606 may but is not limited to include the functional modules in the above-mentioned order cold region prediction device. In addition, it may also include but is not limited to other module units in the above-mentioned order cold region prediction device, which will not be elaborated in this example.

[0115] The above-mentioned processor may be a general-purpose processor, which may include but is not limited to: CPU (Central Processing Unit, central processor), NP (Network Processor, network processor), etc.; it may also be a DSP (Digital Signal Processing, digital signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), FPGA (Field-Programmable Gate Array, field programmable gate array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0116] Optionally, the specific examples in this embodiment may refer to the examples described in the above-mentioned embodiment, and will not be elaborated here.

[0117] Those of ordinary skill in the art can understand that Figure 6 the structure shown is only schematic, and the device for implementing the above-mentioned order cold region prediction method may be a terminal device, and the terminal device may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a mobile Internet device (Mobile Internet Devices, MID), a PAD and other terminal devices. Figure 6 It does not limit the structure of the above-mentioned electronic device. For example, the terminal device may also include more or fewer components (such as a network interface, a display device, etc.) than Figure 6 shown, or have a different configuration from Figure 6 shown.

[0118] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, and the storage medium can include: a flash drive, ROM, RAM, a magnetic disk, or an optical disc, etc.

[0119] According to another aspect of the embodiments of the present application, a storage medium is also provided. Optionally, in this embodiment, the above storage medium can be used to execute the program code of the order cold region prediction method.

[0120] Optionally, in this embodiment, the above storage medium can be located on at least one of the multiple network devices in the network shown in the above embodiments.

[0121] Optionally, in this embodiment, the storage medium is set to store the program code for executing the process steps of the order cold region prediction method in the above embodiments.

[0122] Optionally, the specific examples in this embodiment can refer to the examples described in the above embodiments, and details are not described herein again.

[0123] Optionally, in this embodiment, the above storage medium can include but is not limited to: various media such as a USB flash drive, ROM, RAM, a mobile hard disk, a magnetic disk, or an optical disc that can store program code.

[0124] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0125] If the integrated unit in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in the storage medium and includes several instructions for causing one or more computer devices (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0126] In the above embodiments of the present application, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] In several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in electrical or other forms.

[0128] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0129] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0130] The above is only the preferred embodiment of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting the cold area of an order, characterized in that, The method includes: Predicting the number of empty trucks in the first region on a preset date; Obtaining the shipment order information of M second regions in N days in history, and establishing N scenarios according to the shipment order information of each day in the N days. Each scenario includes the shipment order information of the M second regions within one day, where M and N are positive integers greater than zero; Determining the expected probability of each of the N scenarios occurring on the preset date according to a probability model, where the probability model is a model established based on the shipment order information of M regions in N days in history for determining the occurrence probability of the N scenarios in history on the preset date; Matching the empty trucks with the shipment orders in the N scenarios respectively, traversing all matching schemes, and calculating the expected value of each matching scheme. The expected value is the sum of the expected revenues of all empty trucks in the matching scheme, where the expected revenue = (the price of the matched order - the cost of empty driving for receiving the order) × the expected probability of the scenario where the matched order is located; When the maximum expected value among all matching schemes is less than a preset value, it is determined that the first region is an order cold region on the preset date; The predicting the number of empty trucks in the first region includes: Predicting the number of shipment orders and the number of inbound orders in the first region on the preset date. If the number of inbound orders is greater than the number of shipment orders, the difference between the number of inbound orders and the number of shipment orders is used as the number of empty trucks; Determining the expected probability of each scenario occurring on the preset date according to the probability model includes: Determining the occurrence probability of the N scenarios on the preset date according to the probability model; Regularizing the N occurrence probabilities to obtain the expected probabilities of the N scenarios.

2. The order cold region prediction method according to claim 1, wherein Before determining the expected probability of each of the N scenarios occurring on the preset date according to the probability model, the method further includes: Establishing a probability model according to the relationship between the distance of each scenario from the preset date in the time dimension and / or the cycle dimension.

3. The order cold area prediction method according to claim 2, wherein In the time dimension, the expected probability of the scenario occurring is inversely correlated with the number of days between the actual occurrence date of the scenario and the preset date.

4. An order cold area prediction device, characterized in that, The device includes: An empty truck prediction module for predicting the number of empty trucks in the first region on a preset date; A first acquisition module for obtaining the shipment order information of M second regions in N days in history, and establishing N scenarios according to the shipment order information of each day in the N days. Each scenario includes the shipment order information of the M second regions within one day, where M and N are positive integers greater than zero; A probability prediction module for determining the expected probability of each of the N scenarios occurring on the preset date according to a probability model, where the probability model is a model established based on the shipment order information of M regions in N days in history for determining the occurrence probability of the N scenarios in history on the preset date; An order matching module for matching the empty trucks with the shipment orders in the N scenarios respectively, traversing all matching schemes, and calculating the expected value of each matching scheme. The expected value is the sum of the expected revenues of all empty trucks in the matching scheme, where the expected revenue = (the price of the matched order - the cost of empty driving for receiving the order) × the expected probability of the scenario where the matched order is located; An area determination module, configured to determine that the first region is an order cold area on the preset date when the maximum expected value among all matching solutions is less than a preset value; The predicting the number of empty trucks in the first region includes: Predicting the number of outgoing orders and incoming orders in the first region on the preset date. If the number of incoming orders is greater than the number of outgoing orders, the difference between the number of incoming orders and the number of outgoing orders is used as the number of empty trucks; Determining the expected probability of each scenario occurring on the preset date according to the probability model includes: Determining the occurrence probability of the N scenarios on the preset date according to the probability model; Regularizing the N occurrence probabilities to obtain the expected probabilities of the N scenarios.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the order cold area prediction method according to any one of claims 1-3.

6. An electronic device, characterized in that, Including: At least one processor; And a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to cause the at least one processor to execute the order cold area prediction method according to any one of claims 1-3.

Images