Express delivery business volume prediction method and device, electronic equipment and storage medium
By introducing weekly and monthly impact factors into the express delivery business volume forecast and forecasting based on the daily average delivery benchmark, the problem of inaccurate business volume forecast in the existing technology is solved, and accuracy and efficiency are improved.
Patent Information
- Application Number
- CN202310614725.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-29
- Publication Date
- 2024-12-03
AI Technical Summary
The business volume forecast of the existing technology in the express delivery industry is not accurate enough, resulting in deviations in work distribution and route planning.
By obtaining the historical sunrise volume of the target date, determining the weekly and monthly impact factors, and making predictions based on the daily average output benchmark, weekly and monthly impact factors, improving the accuracy of business volume.
It improves the accuracy of business volume forecasting, facilitates reasonable allocation of work and planning of routes, reduces costs and improves delivery efficiency.
Smart Images

Figure CN119067705A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of logistics technology, and in particular, relates to a method, device, electronic device and storage medium for predicting express delivery business volume. Background Art
[0002] With the rapid development of online e-commerce, the express delivery industry is becoming a service provider for consumption transformation and upgrading. With the growth and changes in shipment volume, it is necessary to accurately predict future shipments, allocate work to personnel at each outlet, and plan routes for vehicles in a reasonable manner.
[0003] The existing methods for predicting express delivery business volume include qualitative prediction and linear regression prediction, but the specific scenarios of the express delivery industry result in inaccurate prediction of business volume.
[0004] The existing technology has the problem of inaccurate forecasting of business volume in the express delivery industry. Summary of the invention
[0005] The embodiments of the present application provide a method, device, electronic device and storage medium for predicting express delivery business volume, which can solve the problem of inaccurate business volume prediction in the express delivery industry.
[0006] In a first aspect, an embodiment of the present application provides a method for predicting express delivery business volume, comprising:
[0007] Obtain the daily shipment volume corresponding to the target date and the first preset number of historical dates;
[0008] Based on the daily volume of each historical date, determine the weekly impact factor and the monthly impact factor corresponding to the historical date;
[0009] Determine a second preset number of daily average shipment benchmark quantities corresponding to the historical dates based on the daily shipment quantities, the weekly impact factor, and the monthly impact factor corresponding to the historical dates respectively;
[0010] The predicted daily output quantity of the target date is predicted based on the average daily output benchmark quantity, the weekly impact factor of the week corresponding to the target date, and the monthly impact factor of the month corresponding to the target date.
[0011] In one embodiment, the step of determining the weekly impact factor and the monthly impact factor corresponding to each historical date based on the daily volume of items corresponding to each historical date includes:
[0012] Determine the weekly impact factor corresponding to each of the historical dates based on the daily volume of items corresponding to each of the historical dates;
[0013] Based on the daily volume of documents and the weekly impact factor respectively corresponding to the historical dates, the monthly impact factor corresponding to the historical dates is determined.
[0014] In one embodiment, the step of determining the weekly impact factor corresponding to each of the historical dates based on the daily volume of items corresponding to each of the historical dates includes:
[0015] Based on the daily shipment volume corresponding to each of the historical dates, determine the weekly average shipment volume for the week in which the historical date falls;
[0016] Based on the daily output volume corresponding to each of the historical dates and the weekly average output volume of the week in which each of the historical dates falls, the weekly impact factor corresponding to each of the historical dates is determined.
[0017] In one of the embodiments, the preset monthly impact factor includes a first preset monthly impact factor and a second preset monthly impact factor;
[0018] The step of determining the monthly impact factor corresponding to the historical date based on the daily volume of items and the weekly impact factor corresponding to the historical date respectively includes:
[0019] If the historical date satisfies the first preset condition, determining the first monthly impact factor corresponding to the historical date based on the daily volume and the weekly impact factor respectively corresponding to the historical date;
[0020] If the historical date satisfies a second preset condition, the second monthly impact factor corresponding to the historical date is determined based on the daily number of pieces and the weekly impact factor respectively corresponding to the historical date.
[0021] In one embodiment, the first preset condition is that the historical date is a historical date of a first preset number of days and a historical date of a second preset number of days, the first preset number of days is a preset number of days counting down from the last day of the month in which the historical date is located, and the second preset number of days is a preset number of days counting forward from the first day of the next month in which the historical date is located;
[0022] The step of determining the first monthly impact factor corresponding to the historical date based on the daily volume and the weekly impact factor respectively corresponding to the historical date if the historical date satisfies the first preset condition comprises:
[0023] If the historical date is a historical date of the first preset number of days and a historical date of the second preset number of days, determine the monthly proportion coefficient corresponding to each of the historical dates based on the daily number of items corresponding to each of the historical dates and the weekly impact factor;
[0024] Based on the daily number of pieces corresponding to each of the historical dates and the monthly proportion coefficient, the first month impact factor corresponding to each of the historical dates is determined.
[0025] In one embodiment, the step of determining the average daily output benchmark quantity corresponding to the second preset number of historical dates based on the daily output quantity, the weekly impact factor, and the monthly impact factor corresponding to the historical dates respectively includes:
[0026] Determine a baseline number of daily shipments for the historical date based on the daily shipment numbers, the weekly impact factor, and the monthly impact factor corresponding to the historical dates;
[0027] Based on the daily benchmark quantities of pieces on the historical dates of the second preset number, determine the average daily benchmark quantities of pieces corresponding to the historical dates of the second preset number.
[0028] In one embodiment, the calculation formula of the daily item forecasting model is:
[0029] P cnt =B cnt ×W ratio ×M ratio
[0030] Among them, P cnt Predicting quantity for said daily shipment;
[0031] B cnt The average daily output benchmark quantity;
[0032] W ratio is the weekly impact factor of the week corresponding to the target date;
[0033] M ratio is the monthly impact factor of the month corresponding to the target date.
[0034] In a second aspect, an embodiment of the present application provides a device for predicting express delivery business volume, including:
[0035] An acquisition module, used to acquire the daily shipment volume corresponding to the target date and a first preset number of historical dates;
[0036] A first determination module is used to determine the weekly impact factor and the corresponding monthly impact factor corresponding to each historical date based on the daily number of items corresponding to each historical date;
[0037] A second determination module is used to determine a daily average output benchmark quantity corresponding to a second preset number of the historical dates based on the daily output quantity, the weekly impact factor, and the monthly impact factor corresponding to the historical dates respectively;
[0038] The prediction module is used to predict the daily output quantity of the target date based on the average daily output benchmark quantity, the weekly impact factor of the week corresponding to the target date and the monthly impact factor of the month corresponding to the target date.
[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements a method as described in any one of the contents of the first aspect above.
[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described in any one of the contents of the first aspect above is implemented.
[0041] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any of the methods described in the first aspect above.
[0042] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.
[0043] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0044] The present application obtains the daily shipment volume corresponding to the target date and a first preset number of historical dates; determines the weekly impact factor and the corresponding monthly impact factor corresponding to the historical date based on the daily shipment volume corresponding to each historical date; determines the daily average shipment benchmark volume corresponding to the second preset number of historical dates based on the daily shipment volume, weekly impact factor and monthly impact factor respectively corresponding to the historical dates; predicts the daily shipment forecast volume of the target date based on the daily average shipment benchmark volume, the weekly impact factor of the week corresponding to the target date and the monthly impact factor of the month corresponding to the target date. As the weekly impact factor and the monthly impact factor are introduced and the express delivery business volume of the target date is predicted based on the daily average shipment benchmark volume, the accuracy of the business volume of the target date is improved, and it is convenient to reasonably allocate work to personnel at each branch and plan routes for vehicles, further reducing the cost of express delivery and improving the efficiency of express delivery. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0046] Figure 1 It is a flowchart of a method for predicting express delivery business volume provided by an embodiment of the present application;
[0047] Figure 2 It is a flowchart of determining the weekly impact factor and the corresponding monthly impact factor corresponding to each historical date based on the daily number of documents corresponding to each historical date provided by another embodiment of the present application;
[0048] Figure 3 It is a flowchart of determining the weekly impact factor corresponding to each historical date based on the daily number of articles corresponding to each historical date provided by another embodiment of the present application;
[0049] Figure 4 It is a flowchart of determining the monthly impact factor corresponding to a historical date based on the daily volume of documents and the weekly impact factor corresponding to each historical date, provided by another embodiment of the present application;
[0050] Figure 5 It is a flowchart of determining the first monthly impact factor corresponding to the historical date based on the daily volume and weekly impact factor corresponding to the historical date if the historical date meets the first preset condition, provided by another embodiment of the present application;
[0051] Figure 6 is a flowchart of determining the average daily output benchmark quantity corresponding to a second preset number of historical dates based on the daily output quantity, weekly impact factor, and monthly impact factor corresponding to each historical date, provided by another embodiment of the present application;
[0052] Figure 7 is a schematic diagram comparing the predicted number of daily shipments on a target date predicted by a daily shipment prediction model provided by another embodiment of the present application and the actual number of daily shipments;
[0053] Figure 8 It is a structural diagram of a device for predicting express delivery business volume provided in an embodiment of the present application. DETAILED DESCRIPTION
[0054] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0055] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0056] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0057] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0058] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0059] With the rapid development of online e-commerce, the express delivery industry is becoming a service provider for consumption transformation and upgrading. With the growth and changes in shipment volume, it is necessary to accurately predict future shipments, allocate work to personnel at each outlet, and plan routes for vehicles in a reasonable manner.
[0060] Existing methods for predicting express delivery volume include qualitative prediction and linear regression prediction. However, the specific scenarios of the express delivery industry result in inaccurate prediction of business volume. For example, customer ordering habits, industry fee settlement, etc. will cause the existing prediction methods to have high deviation values.
[0061] Therefore, the existing technology has the problem of inaccurate forecasting of business volume in the express delivery industry.
[0062] The present application obtains the daily shipment volume corresponding to the target date and a first preset number of historical dates; determines the weekly impact factor and the corresponding monthly impact factor corresponding to the historical date based on the daily shipment volume corresponding to each historical date; determines the daily average shipment benchmark volume corresponding to the second preset number of historical dates based on the daily shipment volume, weekly impact factor and monthly impact factor respectively corresponding to the historical dates; predicts the daily shipment forecast volume of the target date based on the daily average shipment benchmark volume, the weekly impact factor of the week corresponding to the target date and the monthly impact factor of the month corresponding to the target date. As the weekly impact factor and the monthly impact factor are introduced and the express delivery business volume of the target date is predicted based on the daily average shipment benchmark volume, the accuracy of the business volume of the target date is improved, and it is convenient to reasonably allocate work to personnel at each branch and plan routes for vehicles, further reducing the cost of express delivery and improving the efficiency of express delivery.
[0063] The technical solution of the present application is described below through specific embodiments.
[0064] First, as Figure 1 As shown, this embodiment provides a method for predicting express delivery business volume, including:
[0065] S100, obtaining the daily shipment volume corresponding to the target date and a first preset number of historical dates.
[0066] In one embodiment, the number of daily mails corresponding to the first preset number of historical dates is obtained, so as to determine the average value of the period and obtain the impact factor corresponding to the historical date according to the number of daily mails corresponding to the first preset number of historical dates. In one embodiment, in order to match the weekly impact factor, the first preset number is 7. In one embodiment, the specific number of the first preset number is set according to the requirements of the target date, for example, it is set to 14, 21, 28, and its specific value is not limited.
[0067] S200: Determine the weekly impact factor and the monthly impact factor corresponding to each historical date based on the daily number of items corresponding to each historical date.
[0068] In one embodiment, based on the daily number of items corresponding to each historical date, the weekly impact factor and the monthly impact factor corresponding to the historical date are determined, which is beneficial to reducing the amount of calculation for obtaining the weekly impact factor and the monthly impact factor.
[0069] In one embodiment, Figure 2 As shown, based on the daily volume of each historical date, the step of determining the weekly impact factor and the monthly impact factor corresponding to the historical date includes:
[0070] S210, determining the weekly impact factor corresponding to each historical date based on the daily number of pieces corresponding to each historical date.
[0071] In one embodiment, Figure 3 As shown, based on the daily volume of each historical date, the step of determining the weekly impact factor corresponding to each historical date includes:
[0072] S211, based on the daily shipment volume corresponding to each historical date, determine the weekly average shipment volume of the week in which the historical date falls.
[0073] In one embodiment, as shown in Table 1, the average weekly output volume avgA of the first week is determined based on the sum of the daily output volume A1 on the historical date Monday of the first week to the daily output volume A7 on the historical date Sunday and divided by 7, the average weekly output volume avgB of the second week is determined based on the sum of the daily output volume B1 on the historical date Monday of the second week to the daily output volume B7 on the historical date Sunday and divided by 7, and the average weekly output volume avgC of the third week is determined based on the sum of the daily output volume C1 on the historical date Monday of the third week to the daily output volume C7 on the historical date Sunday and divided by 7.
[0074] It should be noted that there is no limit on the number of weeks, and it can be set according to the requirements of the target date. For example, the number of weeks of the historical date can be set to 3 or a multiple of 3, or the number of weeks of the historical date can be set to 4 or a multiple of 4.
[0075] Table 1 Daily shipment volume on historical dates and average weekly shipment volume
[0076] on Monday Tuesday Wednesday Thursday Friday Saturday Sunday Weekly average Week 1 A1 A2 A3 A4 A5 A6 A7 avgA Week 2 B1 B2 B3 B4 B5 B6 B7 avgB Week 3 C1 C2 C3 C4 C5 C6 C7 avgC
[0077] S212: Determine the weekly impact factor corresponding to each historical date based on the daily output volume corresponding to each historical date and the weekly average output volume of the week in which each historical date falls.
[0078] In one embodiment, the step of determining the weekly impact factor corresponding to each historical date based on the daily output volume corresponding to each historical date and the weekly average output volume of the week in which each historical date falls includes:
[0079] Based on the daily output volume corresponding to each historical date and the weekly average output volume of the week in which each historical date falls, the weekly proportion coefficient corresponding to each historical date is determined; based on the weekly proportion coefficient corresponding to each historical date, the weekly impact factor corresponding to each historical date is determined.
[0080] In one embodiment, the weekly proportion coefficient corresponding to each historical date is determined based on the daily shipment volume corresponding to each historical date divided by the weekly average shipment volume of the week in which each historical date is located, and then the median of the number of weeks in which the historical date is located is obtained to determine the weekly impact factor corresponding to each historical date. On the basis of introducing the weekly impact factor to evaluate the daily shipment forecast volume, the calculation amount of the daily shipment forecast volume is reduced.
[0081] In one embodiment, as shown in Table 2, the weekly proportion coefficient R corresponding to the historical date Monday of the first week is determined based on the daily output volume A1 of the historical date Monday of the first week divided by the weekly average output volume avgA of the first week. A1 , and so on, until the weekly ratio coefficient R corresponding to the historical date Sunday of the first week is determined A7 ; Based on the daily output volume B1 on the historical date Monday of the second week divided by the weekly average output volume avgB of the second week, determine the weekly ratio coefficient R corresponding to the historical date Monday of the second week B1 , and so on, until the weekly ratio coefficient R corresponding to the historical date Sunday of the second week is determined B7 ; Based on the daily output volume C1 on the third week's historical date Monday divided by the weekly average output volume avgC of the third week, determine the weekly ratio coefficient R corresponding to the third week's historical date Monday C1 , and so on, until the weekly ratio coefficient R corresponding to the historical date Sunday of the third week is determined C7 .
[0082] In one embodiment, as shown in Table 2, the weekly ratio coefficient R corresponding to the historical date Monday of the first week is A1 , Weekly ratio coefficient R corresponding to the historical date Monday of the second week B1 And the weekly ratio coefficient R corresponding to the historical date Monday of the third week C1 The median operation is used to determine R A1 , R B1 and R C1 The median week ratio coefficient W among the three med1 , median cycle ratio coefficient W med1 The weekly impact factor W is the common Monday of the first week, the Monday of the second week, and the Monday of the third week. ratio1 ; And so on, until the common weekly impact factor W of the historical date Sunday of the first week, the historical date Sunday of the second week, and the historical date Sunday of the third week is determined ratio7 .
[0083] Table 2 Weekly ratio coefficients corresponding to each historical date and median weekly ratio coefficients from Monday to Sunday
[0084] on Monday Tuesday Wednesday Thursday Friday Saturday Sunday Week 1 <![CDATA[R A1 ]]> <![CDATA[R A2 ]]> <![CDATA[R A3 ]]> <![CDATA[R A4 ]]> <![CDATA[R A5 ]]> <![CDATA[R A6 ]]> <![CDATA[R A7 ]]> Week 2 <![CDATA[R B1 ]]> <![CDATA[R B2 ]]> <![CDATA[R B3 ]]> <![CDATA[R B4 ]]> <![CDATA[R B5 ]]> <![CDATA[R B6 ]]> <![CDATA[R B7 ]]> Week 3 <![CDATA[R C1 ]]> <![CDATA[R C2 ]]> <![CDATA[R C3 ]]> <![CDATA[R C4 ]]> <![CDATA[R C5 ]]> <![CDATA[R C6 ]]> <![CDATA[R C7 ]]> Median Week Ratio Coefficient <![CDATA[W med1 ]]> <![CDATA[W med2 ]]> <![CDATA[W med3 ]]> <![CDATA[W med4 ]]> <![CDATA[W med5 ]]> <![CDATA[W med6 ]]> <![CDATA[W med7 ]]>
[0085] S220, determining the monthly impact factor corresponding to the historical date based on the daily volume of documents and the weekly impact factor corresponding to each historical date.
[0086] In one embodiment, based on the daily shipment volume and weekly impact factor corresponding to each historical date, the monthly impact factor corresponding to the historical date is determined, and the calculation amount of the daily shipment forecast volume is reduced on the basis of introducing the monthly impact factor to evaluate the daily shipment forecast volume.
[0087] In one embodiment, the preset monthly impact factor includes a first preset monthly impact factor and a second preset monthly impact factor.
[0088] In one embodiment, Figure 4 As shown, based on the daily volume and weekly impact factor corresponding to each historical date, the step of determining the monthly impact factor corresponding to the historical date includes:
[0089] S221: If the historical date satisfies the first preset condition, determine the first monthly impact factor corresponding to the historical date based on the daily volume and weekly impact factor corresponding to the historical date.
[0090] In one embodiment, the first preset condition is a historical date with a first preset number of days and a historical date with a second preset number of days, the first preset number of days being the preset number of days counting down from the last day of the month in which the historical date is located, and the second preset number of days being the preset number of days counting forward from the first day of the next month in which the historical date is located.
[0091] In one embodiment, the first preset number of days is equal to the second preset number of days, so as to keep the first-month impact factor of the historical date that meets the first preset condition consistent and reduce the error of the daily shipment forecast.
[0092] In one embodiment, the first preset number of days and the second preset number of days are both less than or equal to 5 days, so as to reduce the amount of calculation of the impact factor of the first month.
[0093] In one embodiment, the first preset number of days and the second preset number of days are both 5 days, so as to obtain an accurate first-month impact factor according to the specific scenario of the express delivery business, so as to improve the accuracy of the daily shipment forecast.
[0094] In one embodiment, Figure 5 As shown, if the historical date meets the first preset condition, the step of determining the first month impact factor corresponding to the historical date based on the daily volume and weekly impact factor corresponding to the historical date includes:
[0095] S2211: If the historical date is a historical date of the first preset number of days and a historical date of the second preset number of days, determine the monthly proportion coefficient corresponding to each historical date based on the daily number of items and the weekly impact factor corresponding to each historical date.
[0096] In one embodiment, the first preset number of days and the second preset number of days are both 5 days. The 5th to the last day of the month in which the historical date of the first preset day is located are respectively represented as M-5, M-4, M-3, M-2, and M-1. The 1st to the 5th day of the next month in which the historical date of the second preset day is located are respectively represented as M+1, M+2, M+3, M+4, and M+5. The historical date of the second preset day adjacent to the first preset day is calculated according to the month in which the historical date of the first preset day is located. The number of daily shipments corresponding to the historical date that meets the first preset condition in the first month, the second month, and the third month is as shown in Table 3.
[0097] Table 3 Daily shipments corresponding to historical dates that meet the first preset condition
[0098]
[0099] In one embodiment, if the historical date is a historical date within a first preset number of days and a historical date within a second preset number of days, the step of determining the monthly proportion coefficient corresponding to each historical date based on the daily volume and weekly impact factor corresponding to each historical date includes:
[0100] If the historical date is a historical date of the first preset number of days and a historical date of the second preset number of days, determine the daily weekly factor corresponding to the historical date based on the daily number of items corresponding to the historical date divided by the value of the corresponding weekly impact factor; determine the average daily weekly factor corresponding to the month in which the historical dates of the first preset number of days and the second preset number of days are located based on the sum of the daily weekly factors corresponding to the month in which the historical dates of the first preset number of days and the second preset number of days are located; determine the monthly proportion coefficient corresponding to each historical date based on the daily weekly factors corresponding to the month in which the historical dates of the first preset number of days and the second preset number of days are located divided by the average daily weekly factors corresponding to the historical dates.
[0101] In one embodiment, as shown in Table 4, if the historical date M-5 of the first month is Tuesday, the weekly impact factor of Tuesday is W ratio2 , based on the daily volume A11 of the historical date M-5 in the first month divided by the weekly impact factor W of Tuesday ratio2 Determine the daily factor r corresponding to the historical date M-5 11 ; And so on, determine the day-week factor r of the first month corresponding to the historical dates M-4, M-3, M-2, M-1, M+1, M+2, M+3, M+4, and M+5 respectively 12 、r 13 、r 14 、r 15 、r 16 、r 17 、r 18 、r 19 、r 20; and by analogy, obtain the day-week factor of the second month of the historical date of the first preset day and the second preset day and the day-week factor of the third month of the historical date of the first preset day and the second preset day; divide the sum of the day-week factors of the historical dates M-5 to M+5 by 10, determine the average day-week factor avg_r1 corresponding to the first month of the historical dates of the first preset day and the second preset day, and by analogy, determine the average day-week factor avg_r2 corresponding to the second month of the historical dates of the first preset day and the second preset day, and determine the average day-week factor avg_r3 corresponding to the third month of the historical dates of the first preset day and the second preset day; determine the month proportion coefficient R corresponding to the first month of the historical dates M-5 to M+5 based on the day-week factor corresponding to the first month of the historical dates M-5 to M+5 divided by the average day-week factor corresponding to the historical dates 11 To R 20 , and so on, determine the monthly ratio coefficient R corresponding to the second month of historical dates M-5 to M+5 21 To R 30 , determine the monthly ratio coefficient R corresponding to the third month of historical dates M-5 to M+5 31 To R 40 , thereby eliminating the fluctuation of weekly factors of business volume at the end and beginning of the month and improving the accuracy of daily shipment forecast.
[0102] Table 4 The daily weekly factors of each historical date and the average daily weekly factors of the month that meet the first preset condition
[0103]
[0104] S2212: Determine the first month impact factor corresponding to each historical date based on the daily number of items and the monthly proportion coefficient corresponding to each historical date.
[0105] In one embodiment, based on the daily shipment volume and the monthly proportion coefficient corresponding to each historical date, the first month impact factor corresponding to each historical date is determined, thereby balancing the fluctuation impact of the daily shipment volume at the end and beginning of the month and improving the accuracy of the daily shipment forecast.
[0106] In one embodiment, as shown in Table 5, the monthly proportion coefficient R corresponding to the historical date M-5 of the first month is 11 , the monthly ratio coefficient R corresponding to the historical date week M-5 of the second month 21 and the monthly ratio coefficient R corresponding to the historical date M-5 of the third month 31 The median operation is used to determine R 11 , R 21 and R 31 The median monthly ratio coefficient M among the three med1 , median monthly proportion coefficient M med1The monthly impact factor M is the common monthly impact factor of the historical date M-5 of the first month, the historical date M-5 of the second month, and the historical date M-5 of the third month. ratio1 ; And so on, until the common monthly impact factor M of the historical date M+5 of the first month, the historical date M+5 of the second month, and the historical date M+5 of the third month is determined ratio10 .
[0107] Table 5 Monthly proportion coefficients and median monthly proportion coefficients of historical dates that meet the first preset condition
[0108]
[0109] S222: If the historical date satisfies the second preset condition, determine the second monthly impact factor corresponding to the historical date based on the daily number of items and the weekly impact factor corresponding to the historical date.
[0110] In one embodiment, the second preset condition is a historical date outside the month in which the historical date of the first preset condition is located. For example, the first preset condition is a historical date 5 days from the end of a month and 5 days from the beginning of the next month, and the historical date of the second preset condition is a historical date from the sixth day of the first day of the month to the sixth day of the last day of the month.
[0111] In one embodiment, if the historical date meets the second preset condition, the second monthly impact factor corresponding to the historical date is the preset impact factor, wherein the range of the preset impact factor is greater than 0 and less than or equal to 1. In one embodiment, in order to reduce the amount of calculation, the second monthly impact factor is 1.
[0112] S300, determining a daily average shipment benchmark quantity corresponding to a second preset number of historical dates based on the daily shipment quantity, weekly impact factor, and monthly impact factor corresponding to each historical date.
[0113] In one embodiment, based on the daily shipment volume, weekly impact factor, and monthly impact factor corresponding to each historical date, the average daily shipment benchmark volume corresponding to a second preset number of historical dates is determined, and the smoothed average daily shipment benchmark volume is obtained to avoid the impact of fluctuations on a single date on the predicted daily shipment volume, thereby improving the accuracy of the predicted daily shipment volume.
[0114] In one embodiment, Figure 6 As shown, based on the daily shipment volume, weekly impact factor, and monthly impact factor corresponding to the historical dates, the step of determining the daily average shipment benchmark volume corresponding to the second preset number of historical dates includes:
[0115] S310, determining a baseline quantity of daily shipments for a historical date based on the daily shipment quantities, weekly impact factors, and monthly impact factors corresponding to the historical dates.
[0116] In one embodiment, determining the baseline number of daily shipments for a historical date based on the daily shipment numbers, weekly impact factors, and monthly impact factors corresponding to the historical dates respectively includes:
[0117] Based on the daily shipment volume, weekly impact factor, and monthly impact factor corresponding to each historical date, the daily shipment baseline volume for a historical date is determined using the daily shipment baseline volume calculation formula.
[0118] In one embodiment, the calculation formula for the benchmark number of shipments per day is:
[0119] B cnt =nt×W ratio_t ×M ratio_t
[0120] Among them, B cnt The benchmark number of shipments per day;
[0121] cnt is the daily number of pieces on a historical date;
[0122] W ratio_t is the weekly impact factor of the week corresponding to the historical date;
[0123] M ratio_t is the monthly impact factor of the month corresponding to the historical date.
[0124] S320: Determine a daily average benchmark quantity of shipments corresponding to a second preset number of historical dates based on a benchmark quantity of shipments per day for a second preset number of historical dates.
[0125] In one embodiment, based on the benchmark quantity of daily shipments on a second preset number of historical dates, the average daily shipment benchmark quantity corresponding to the second preset number of historical dates is determined, the value of the second preset number is adjusted according to different express delivery business types, and the average daily shipment benchmark quantity corresponding to the second preset number of historical dates is determined, thereby improving the fitting effect of the average daily shipment benchmark quantity of historical dates and improving the accuracy of the predicted quantity of daily shipments.
[0126] In one embodiment, the second preset number is less than or equal to 7, which is convenient for weekly prediction. In one embodiment, the second preset number is 3, and reducing the number is convenient for further improving the fitting effect of the daily average output benchmark quantity of historical dates.
[0127] In one embodiment, based on the baseline quantity of daily shipments of a second preset number of historical dates, the average daily baseline quantity of shipments corresponding to the second preset number of historical dates is determined by dividing the sum of the baseline quantity of daily shipments of the second preset number of historical dates by two preset numbers.
[0128] In one embodiment, the second preset quantity is 3, and the first single-day delivery benchmark quantity is B. cnt1 The standard quantity of shipments on the second day is Bcnt2 The standard quantity of shipments on the third day is B cnt3 , then the average daily output quantity B cnt =(B cnt1 +B cnt2 +B cnt3 ) / 3.
[0129] S400, predicting the daily shipment forecast for the target date based on the daily average shipment benchmark quantity, the weekly impact factor of the week corresponding to the target date, and the monthly impact factor of the month corresponding to the target date.
[0130] In one embodiment, the daily output forecast for the target date is predicted based on the daily average output benchmark, the weekly impact factor of the week corresponding to the target date, and the monthly impact factor of the month corresponding to the target date. Since the weekly impact factor and the monthly impact factor are introduced, and the daily output of the second most recent preset number of historical dates is used as the daily average output benchmark, the stability of the cycle is used to offset the linear uncertainty, thereby reducing the amount of calculation for predicting the daily output forecast for the target date and improving the accuracy of predicting the daily output forecast for the target date.
[0131] In one embodiment, based on the daily average shipment benchmark quantity, the weekly impact factor of the week corresponding to the target date, and the monthly impact factor of the month corresponding to the target date, the daily shipment forecast quantity of the target date is predicted, including:
[0132] Based on the average daily output benchmark quantity, the weekly impact factor of the week corresponding to the target date and the monthly impact factor of the month corresponding to the target date, the output forecast model is used to predict the output forecast of the target date.
[0133] In one embodiment, the calculation formula of the daily shipment prediction model is:
[0134] P cnt =B cnt ×W ratio ×M ratio
[0135] Among them, P cnt Forecast quantity for daily shipments;
[0136] B cnt The average daily output volume;
[0137] W ratio is the weekly impact factor of the week corresponding to the target date;
[0138] M ratio is the monthly impact factor of the month corresponding to the target date.
[0139] In one embodiment, Figure 7As shown, the accuracy of the daily shipment forecast model in predicting the daily shipment forecast on the target date reached 97.83%, which is higher than the accuracy of the existing technology. It is convenient for rationally planning the work of outlets and delivery routes, reduces resource waste, and reduces the cost of express delivery services.
[0140] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0141] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0142] This embodiment obtains the daily shipment volume corresponding to the target date and a first preset number of historical dates; determines the weekly impact factor and the corresponding monthly impact factor corresponding to the historical date based on the daily shipment volume corresponding to each historical date; determines the daily average shipment benchmark volume corresponding to the second preset number of historical dates based on the daily shipment volume, weekly impact factor and monthly impact factor corresponding to the historical dates; predicts the daily shipment forecast volume of the target date based on the daily average shipment benchmark volume, the weekly impact factor of the week corresponding to the target date and the monthly impact factor of the month corresponding to the target date. Since the weekly impact factor and the monthly impact factor are introduced and the express delivery business volume of the target date is predicted based on the daily average shipment benchmark volume, the accuracy of the business volume of the target date is improved, and it is convenient to reasonably allocate work to personnel at each branch and plan routes for vehicles, further reducing the cost of express delivery and improving the efficiency of express delivery.
[0143] Second, as Figure 8 As shown, this embodiment provides a prediction device for express delivery business volume, including:
[0144] An acquisition module 100 is used to acquire the daily shipment volume corresponding to the target date and a first preset number of historical dates;
[0145] The first determination module 200 is used to determine the weekly impact factor and the corresponding monthly impact factor corresponding to each historical date based on the daily volume of each historical date;
[0146] The second determination module 300 is used to determine the average daily output benchmark quantity corresponding to a second preset number of historical dates based on the daily output quantity, weekly impact factor, and monthly impact factor corresponding to the historical dates respectively;
[0147] The prediction module 400 is used to predict the daily output quantity of the target date based on the daily average output benchmark quantity, the weekly impact factor of the week corresponding to the target date, and the monthly impact factor of the month corresponding to the target date.
[0148] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0149] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0150] In a third aspect, this embodiment provides a terminal device, including:
[0151] A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the above-mentioned first aspects is implemented.
[0152] In a fourth aspect, this embodiment further provides a computer-readable storage medium, including:
[0153] The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the contents of the first aspect is implemented.
[0154] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any of the methods described in the first aspect.
[0155] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.
[0156] The express delivery business volume prediction method provided in the embodiment of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiment of the present application does not impose any restrictions on the specific type of terminal devices.
[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by a processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.
[0158] The computer-readable medium may include at least: any entity or device capable of carrying computer program codes to a camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disk. In some jurisdictions, according to legislation and patent practice, a computer-readable medium cannot be an electric carrier signal or a telecommunication signal.
[0159] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0160] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0161] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0163] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for predicting express delivery business volume, It is characterized in that include: Obtain the daily shipment volume corresponding to the target date and the first preset number of historical dates; Based on the daily volume of each historical date, determine the weekly impact factor and the monthly impact factor corresponding to the historical date; Determine a second preset number of daily average shipment benchmark quantities corresponding to the historical dates based on the daily shipment quantities, the weekly impact factor, and the monthly impact factor corresponding to the historical dates respectively; The predicted daily output quantity of the target date is predicted based on the average daily output benchmark quantity, the weekly impact factor of the week corresponding to the target date, and the monthly impact factor of the month corresponding to the target date.
2. The method according to claim 1, It is characterized in that The step of determining the weekly impact factor and the monthly impact factor corresponding to each historical date based on the daily volume of items corresponding to each historical date includes: Determine the weekly impact factor corresponding to each of the historical dates based on the daily volume of items corresponding to each of the historical dates; Based on the daily volume of documents and the weekly impact factor respectively corresponding to the historical dates, the monthly impact factor corresponding to the historical dates is determined.
3. The method according to claim 2, It is characterized in that The step of determining the weekly impact factor corresponding to each of the historical dates based on the daily volume of items corresponding to each of the historical dates comprises: Based on the daily shipment volume corresponding to each of the historical dates, determine the weekly average shipment volume for the week in which the historical date falls; Based on the daily output volume corresponding to each of the historical dates and the weekly average output volume of the week in which each of the historical dates falls, the weekly impact factor corresponding to each of the historical dates is determined.
4. The method according to claim 1, It is characterized in that The preset monthly impact factor includes a first preset monthly impact factor and a second preset monthly impact factor; The step of determining the monthly impact factor corresponding to the historical date based on the daily volume of items and the weekly impact factor corresponding to the historical date respectively includes: If the historical date satisfies the first preset condition, determining the first monthly impact factor corresponding to the historical date based on the daily volume and the weekly impact factor respectively corresponding to the historical date; If the historical date satisfies a second preset condition, the second monthly impact factor corresponding to the historical date is determined based on the daily number of pieces and the weekly impact factor respectively corresponding to the historical date.
5. The method according to claim 4, It is characterized in that The first preset condition is that the historical date is a historical date of a first preset number of days and a historical date of a second preset number of days, the first preset number of days being the preset number of days counting down from the last day of the month in which the historical date is located, and the second preset number of days being the preset number of days counting forward from the first day of the next month in which the historical date is located; The step of determining the first monthly impact factor corresponding to the historical date based on the daily volume and the weekly impact factor respectively corresponding to the historical date if the historical date satisfies the first preset condition comprises: If the historical date is a historical date of the first preset number of days and a historical date of the second preset number of days, determine the monthly proportion coefficient corresponding to each of the historical dates based on the daily number of items corresponding to each of the historical dates and the weekly impact factor; Based on the daily number of pieces corresponding to each of the historical dates and the monthly proportion coefficient, the first month impact factor corresponding to each of the historical dates is determined.
6. The method according to claim 1, It is characterized in that The step of determining the daily average output benchmark quantity corresponding to a second preset number of historical dates based on the daily output quantity, the weekly impact factor, and the monthly impact factor corresponding to the historical dates respectively includes: Determine a baseline number of daily shipments for the historical date based on the daily shipment numbers, the weekly impact factor, and the monthly impact factor corresponding to the historical dates; Based on the daily benchmark quantities of pieces on the historical dates of the second preset number, determine the average daily benchmark quantities of pieces corresponding to the historical dates of the second preset number.
7. The method according to claim 1, It is characterized in that The predicting of the daily shipment forecast quantity of the target date based on the daily average shipment benchmark quantity, the weekly impact factor of the week corresponding to the target date, and the monthly impact factor of the month corresponding to the target date, includes: Based on the average daily output benchmark quantity, the weekly impact factor of the week corresponding to the target date and the monthly impact factor of the month corresponding to the target date, the output forecast quantity of the target date is predicted by the output forecast quantity model; The calculation formula of the daily shipment forecast model is: P cnt =B cnt ×W ratio ×M ratio Among them, P cnt Predicting quantity for said daily shipment; B cnt The average daily output benchmark quantity; W ratio is the weekly impact factor of the week corresponding to the target date; M ratio is the monthly impact factor of the month corresponding to the target date.
8. A device for predicting express delivery business volume, It is characterized in that include: An acquisition module, used to acquire the daily shipment volume corresponding to the target date and a first preset number of historical dates; A first determination module is used to determine the weekly impact factor and the corresponding monthly impact factor corresponding to each historical date based on the daily number of items corresponding to each historical date; A second determination module is used to determine a daily average output benchmark quantity corresponding to a second preset number of the historical dates based on the daily output quantity, the weekly impact factor, and the monthly impact factor corresponding to the historical dates respectively; The prediction module is used to predict the daily output quantity of the target date based on the average daily output benchmark quantity, the weekly impact factor of the week corresponding to the target date and the monthly impact factor of the month corresponding to the target date.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
