Product oil denitration prediction method, device, equipment and medium

Abstract

The invention belongs to the technical field of neural network optimization, and particularly relates to a product oil denitration prediction method and device, equipment and a medium. The method comprises the steps of obtaining a current product oil inventory of a target gas station and a weekly product oil weekly sales record within a preset duration range; determining a finished product oil week factor of the target gas station according to the plurality of finished product oil week sales records; according to all the weekly sales records of the product oil, determining period characteristics of the product oil of the target gas station every day in a week; predicting the predicted sales volume of the product oil in each time period in a future week according to the week factor of the product oil and the time period characteristics of the product oil; and predicting the denitration duration of the product oil according to the current product oil inventory and the predicted sales volume of the product oil in each time period. Therefore, the denitration prediction of the product oil is more accurate, the situation of denitration early warning errors caused by sensor problems can be well avoided, and guidance can be better provided for an oil depot distribution plan.

Description

Technical Field

[0001] The invention belongs to the technical field of neural network optimization, and specifically relates to a method, device, equipment and medium for predicting out-of-stock of refined oil. Background Art

[0002] The existing prediction of out-of-stock of refined oil uses out-of-stock warning to warn that refined oil will be out of stock and needs to be delivered. Relying on sensors, if the sensors are damaged or the measurement is inaccurate, it will cause out-of-stock warning errors. In addition, if it encounters a sales peak period, the oil products will not be delivered in time due to time lag after the warning, which will cause out-of-stock phenomenon and affect oil sales. Summary of the invention

[0003] In response to the above technical problems, the present invention proposes a method, device, equipment and medium for predicting out-of-stock of refined oil. This application obtains the current inventory of refined oil of the target gas station and the weekly sales records of refined oil every week within a preset time range; determines the weekly factor of refined oil of the target gas station according to multiple weekly sales records of refined oil, and the weekly factor of refined oil is used to represent the sales of refined oil of the target gas station every day in a week; determines the time period characteristics of refined oil of the target gas station every day in a week according to all the weekly sales records of refined oil, and the time period characteristics of refined oil are used to characterize the sales of refined oil in each time period of a day; predicts the predicted sales of refined oil in each time period in the next week according to the weekly factor of refined oil and the time period characteristics of refined oil; predicts the out-of-stock duration of refined oil according to the current inventory of refined oil and the predicted sales of refined oil in each time period. This makes the prediction of out-of-stock of refined oil more accurate, can well avoid the situation of out-of-stock warning errors caused by sensor problems, and can better provide guidance for oil depot distribution plans.

[0004] To solve the above technical problems, the technical solution adopted by the present invention includes four aspects.

[0005] In a first aspect, a method for predicting out-of-stock of refined oil is provided, comprising: obtaining a current refined oil inventory and weekly refined oil sales records of a target gas station within a preset time range; determining a refined oil weekly factor of the target gas station based on a plurality of the refined oil weekly sales records, the refined oil weekly factor being used to represent the refined oil sales of the target gas station every day of the week; determining a refined oil time period feature of the target gas station every day of the week based on all the refined oil weekly sales records, the refined oil time period feature being used to characterize the refined oil sales of each time period within a day; predicting the predicted sales volume of refined oil for each time period in the next week based on the refined oil weekly factor and the refined oil time period feature; and predicting the out-of-stock duration of the refined oil based on the current refined oil inventory and the predicted sales volume of refined oil for each time period.

[0006] In some embodiments, the weekly sales record of finished oil includes: daily sales record of finished oil; determining the weekly factor of finished oil of the target gas station based on multiple weekly sales records of finished oil includes: determining the daily average sales value of finished oil in week i based on the daily sales record of finished oil corresponding to week i in multiple weekly sales records of finished oil; determining the weekly average sales value of finished oil based on multiple weekly sales records of finished oil; determining the characteristic factor of week i based on the daily average sales value of finished oil and the weekly average sales value of finished oil; and forming a vector of the characteristic factors of 7 days to obtain the weekly factor.

[0007] In some embodiments, predicting the predicted sales volume of refined oil in each time period in the next week based on the refined oil weekly factor and the refined oil time period characteristic includes: determining the weekly average characteristics of each week based on the weekly factor and the weekly sales records of the refined oil in each week; predicting the predicted average characteristics of the next week based on the weekly average characteristics of multiple weeks; predicting the predicted sales volume of refined oil in each time period in the next week based on the predicted average characteristics, the weekly factor and the refined oil time period characteristic.

[0008] In some embodiments, determining the weekly average characteristics of each week based on the weekly factor and the weekly sales record of the refined oil includes: normalizing the weekly factor to obtain a normalized factor; and determining the weekly average characteristics based on the normalized factor and each weekly sales record of the refined oil.

[0009] In some embodiments, predicting the predicted average characteristics of the next week based on the weekly average characteristics of multiple weeks is achieved by the following formula: r_(i_yu)=0.5r_(i-1)+0.5r_(i-1_yu); wherein, r_(i-1_yu)=0.2r_(i-2_yu)+0.8r_(i-1), wherein r_(i-1) represents the weekly average characteristics of the i-1th week, and r_(i_yu) represents the predicted average characteristics of the i-th week, wherein i also represents the future week.

[0010] In some embodiments, predicting the predicted sales volume of refined oil in each time period within the next week based on the predicted average characteristics, the weekly factors and the refined oil time period characteristics includes: determining the predicted daily sales volume for the next week based on the predicted average characteristics and the weekly factors; predicting the predicted sales volume of refined oil in each time period of each day based on the predicted daily sales volume and the refined oil time period characteristics.

[0011] In some embodiments, before predicting the out-of-stock duration of finished oil based on the current finished oil inventory and the predicted sales volume of finished oil in each time period, the method further includes: obtaining the actual sales volume of the target gas station in each time period of the day; comparing the actual sales volume with the predicted sales volume of finished oil in the corresponding time period to obtain a comparison result; and correcting the predicted sales volume of finished oil in each time period of the day based on the comparison result.

[0012] In a second aspect, the present application provides a device for predicting out-of-stock of refined oil, comprising: a first acquisition module, used to acquire the current refined oil inventory of a target gas station and the weekly sales records of refined oil every week within a preset time range; a first determination module, used to determine the refined oil weekly factor of the target gas station based on multiple weekly sales records of refined oil; a second determination module, used to determine the refined oil time period characteristics of the target gas station every day of the week based on all the weekly sales records of refined oil; a first prediction module, used to predict the predicted sales volume of refined oil in each time period in the next week based on the refined oil weekly factor and the refined oil time period characteristics; a second prediction module, used to predict the out-of-stock duration of the refined oil based on the current refined oil inventory and the predicted sales volume of refined oil in each time period.

[0013] In a third aspect, the present application provides an electronic device, comprising: a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method described in any one of the first aspects is performed.

[0014] In a fourth aspect, the present application provides a storage medium, which stores a computer program that can be executed by one or more processors, and the computer program can be used to implement any method described in the first aspect.

[0015] Beneficial effects created by the present invention: The present application obtains the current inventory of finished oil of the target gas station and the weekly sales records of finished oil every week within a preset time range; determines the weekly factor of the finished oil of the target gas station according to a plurality of weekly sales records of finished oil, and the weekly factor of finished oil is used to represent the sales of finished oil of the target gas station every day in a week; determines the time period characteristics of the finished oil of the target gas station every day in a week according to all the weekly sales records of finished oil, and the time period characteristics of finished oil are used to characterize the sales of finished oil in each time period of a day; predicts the sales volume of finished oil in each time period in the next week according to the weekly factor of finished oil and the time period characteristics of finished oil; predicts the out-of-stock duration of finished oil according to the current inventory of finished oil and the predicted sales volume of finished oil in each time period. This makes the out-of-stock prediction of finished oil more accurate, can well avoid the out-of-stock warning errors caused by sensor problems, and can better provide guidance for oil depot distribution plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The scope of the present disclosure may be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. The drawings included are:

[0017] Figure 1 An overall flow chart of a method for predicting out-of-stock of refined oil provided in an embodiment of the present application;

[0018] Figure 2 A structural block diagram of a device for predicting out-of-stock of refined oil provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0021] If similar descriptions of "first\second\third" appear in the application documents, the following instructions will be added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0023] Embodiment 1:

[0024] The existing prediction of out-of-stock of refined oil uses out-of-stock warning to warn that refined oil will be out of stock and needs to be delivered. Relying on sensors, if the sensors are damaged or the measurement is inaccurate, it will cause out-of-stock warning errors. In addition, if it encounters a sales peak period, the oil products will not be delivered in time due to time lag after the warning, which will cause out-of-stock phenomenon and affect oil sales.

[0025] In view of the problems existing in the prior art, such as Figure 1As shown, the present application provides a method for predicting out-of-stock of refined oil, and the method is applied to an electronic device, and the electronic device can be a server, a mobile terminal, a computer, a cloud platform, etc. The function implemented by the device data processing provided in the embodiment of the present application can be implemented by calling a program code by a processor of the electronic device, wherein the program code can be stored in a computer storage medium, and the method for predicting out-of-stock of refined oil includes:

[0026] Step S1: Obtain the current inventory of refined oil products of the target gas station and the weekly sales records of refined oil products within a preset time range.

[0027] If you want to predict the out-of-stock of the target gas station's refined oil, you must obtain the current refined oil inventory of the target gas station and the refined oil sales record within a period of time. Because the sales of refined oil at the gas station are seriously affected by the day of the week, the sales records obtained in this application are based on the weekly cycle.

[0028] Step S2: Determine the refined oil weekly factor of the target gas station based on the plurality of refined oil weekly sales records, wherein the refined oil weekly factor is used to represent the refined oil sales situation of the target gas station every day in a week.

[0029] In a week, people's travel needs are different on different days, and vehicle fuel consumption is different. Therefore, in this application, if you want to predict the out-of-stock of refined oil, you must obtain the refined oil sales situation on different days of the week, or the refined oil sales proportion, that is, the weekly factor, where the refined oil weekly sales record includes the refined oil daily sales record for each day of the week.

[0030] Therefore, in some embodiments, step S2 of "determining the refined oil weekly factor of the target gas station according to the plurality of refined oil weekly sales records" includes:

[0031] Step S21: determining the average daily sales value of refined oil in week i according to the daily sales records of refined oil corresponding to week i in the plurality of weekly sales records of refined oil.

[0032] First, add up the daily sales records of refined oil on the same day of each week, and then divide by the number of weeks to get the average daily sales value of refined oil in week i.

[0033] For example, if i=3, then the daily sales volume of refined oil on all Wednesdays within the preset time range is added up, and then divided by the number on Wednesdays to obtain the average daily sales value of refined oil on Wednesdays.

[0034] Step S22: Determine the weekly average sales value of refined oil according to the plurality of weekly sales records of refined oil.

[0035] Add up all weekly sales of refined petroleum products and divide by the number of weeks to get the average weekly sales value.

[0036] Step S23: determining the characteristic factor of week i according to the daily average sales value of refined oil and the weekly average sales value of refined oil.

[0037] By dividing the average daily sales value of refined oil in week i by the average weekly sales value of refined oil, we can get the characteristic factor of week i.

[0038] The calculation expression of the characteristic factor of week i is: the average daily sales value of refined oil in week i / the average weekly sales value of refined oil. For example, to calculate the characteristic factor of Wednesday, it is the average daily sales value of refined oil on Wednesday / the average weekly sales value of refined oil.

[0039] Step S24: The characteristic factors of the seven days are combined into a vector to obtain the week factor.

[0040] The characteristic factors of each day of the week are organized into a one-dimensional vector of length 7, which is the week factor. The week factor is expressed by X, X = {x1, x2, x3, x4, x5, x6, x7}.

[0041] Step S3: Determine the refined oil time period characteristics of the target gas station every day in a week based on all the refined oil weekly sales records, and the refined oil time period characteristics are used to characterize the refined oil sales situation in each time period of a day.

[0042] Because the denitrification prediction of refined oil can guide the distribution of refined oil, the higher the out-of-stock prediction accuracy, the higher the distribution guidance value of refined oil, so in this application, the out-of-stock prediction accuracy of refined oil is hours. Therefore, it is necessary to predict the sales volume every hour in the next week, and it is necessary to determine the time period characteristics of refined oil every day in the week. Here, the time period can be one hour, multiple hours, or tens of minutes. In this application, the time period is one hour, that is, this application needs to obtain the refined oil sales situation of each hour in the next week.

[0043] In the weekly sales record of refined oil, the sales volume is formed by hour, that is to say, it includes the oil sales volume of each hour of the seven days of the week. Therefore, in this application, if you want to obtain the time period characteristics of refined oil in each time period, you only need to add up the refined oil sales volume at the same time on the same day, and all the refined oil sales volume within the preset time length, and you can get the time period characteristics of refined oil in each hour of each day in the week. The time period characteristics of refined oil are represented by S, which is a 7*24 matrix.

[0044] Step S4: predicting the sales volume of finished oil in each time period in the next week according to the finished oil weekly factor and the finished oil time period characteristics.

[0045] After obtaining the refined oil weekly factor and refined oil time period characteristics, the refined oil sales volume in each time period in the next week can be predicted, that is, the refined oil predicted sales volume.

[0046] Therefore, in some embodiments, step S4 "predicting the sales volume of refined oil in each period in the next week according to the refined oil weekly factor and the refined oil period characteristics" includes:

[0047] Step S41: Determine the weekly average characteristics of each week based on the weekly factor and the weekly sales records of the refined oil products.

[0048] Because this application is based on the weekly cycle prediction, if you want to get the predicted sales volume of refined oil in each period in the next week, you need to wait for the weekly predicted sales volume of refined oil in the next week, and the weekly predicted sales volume needs to be determined based on the predicted average characteristics. The predicted average characteristics need to rely on the previous weekly average characteristics.

[0049] Therefore, in some embodiments, step S41 "determine the weekly average characteristics of each week according to the weekly factor and the weekly sales record of the refined oil product" includes:

[0050] Step S411: normalize the week factor to obtain a normalized factor.

[0051] Step S412: Determine the weekly average feature according to the normalization factor and each of the weekly sales records of the refined oil.

[0052] First, normalize the week factor. The calculation formula for normalizing the week factor is as follows:

[0053]

[0054] The above calculation formula can be used to obtain the result of normalizing the week factor, the normalized factor.

[0055] After obtaining the normalization factor, the weekly average features can be calculated. The calculation expression of the weekly average features is:

[0056] Step S42: predicting the predicted average characteristics of the next week based on the weekly average characteristics of multiple weeks.

[0057] The predicted average feature expresses the prediction of sales volume in the next week. In this application, the predicted average feature of the next week is predicted by the following formula:

[0058] r_(i_yu)=0.5r_(i-1)+0.5r_(i-1_yu)

[0059] In the formula, r_(i-1_yu)=0.2r_(i-2_yu)+0.8r_(i-1), where r_(i-1) represents the weekly average characteristics of the i-1th week, r_(i_yu) represents the predicted average characteristics of the i-th week, and i also represents the future week.

[0060] Step S43: predicting the sales volume of refined oil in each time period in the next week according to the predicted average characteristics, the weekly factors and the time period characteristics of refined oil.

[0061] In some embodiments, step S43 "predicting the sales volume of refined oil products in each period of the next week according to the predicted average feature, the weekly factor and the refined oil product period feature" includes:

[0062] Step S431: Determine the predicted daily sales volume for the next week based on the predicted average characteristics and the weekly factor.

[0063] The predicted average feature is the prediction result of the total sales in the next week, so after combining the weekly factor, the sales volume for each day in the next week can be predicted, which is the predicted daily sales volume.

[0064] Step S432: predicting the sales volume of refined oil in each time period of each day according to the predicted daily sales volume and the time period characteristics of refined oil.

[0065] Because we know the time period characteristics of each time period every day of the week, after obtaining the predicted daily sales, we can get the predicted sales volume of refined oil in each time period of the day based on the corresponding time period characteristics and predicted daily sales.

[0066] P=r i *X*S. The predicted sales volume of refined oil is represented by P, which is a 7*24 matrix.

[0067] In some embodiments, although the final predicted sales volume of refined oil is obtained through steps S1 to S432, the actual situation cannot be fully predicted, so the method of the present application further includes:

[0068] Step S44: Obtain the actual sales volume of the target gas station at each time period of the day.

[0069] Step S45: Compare the actual sales volume with the predicted sales volume of refined oil in the corresponding period to obtain a comparison result.

[0070] Step S46: Correcting the predicted sales volume of refined oil at each time period of the day according to the comparison result.

[0071] Liquid level meters are installed in the oil tanks of gas stations. Liquid level meters can obtain the changes in the liquid level in the oil tanks in real time. Through the changes in the liquid level, the amount of oil consumed in each period of the day can be known, that is, the actual sales volume of each hour. At this time, the actual sales volume is compared with the predicted sales volume. If the comparison result is within an acceptable range, it means that the predicted sales volume is accurate. If the comparison result shows that the difference between the two is large, the predicted sales volume of finished oil in the subsequent time of the day will be corrected according to the actual sales volume. This makes the predicted sales volume of finished oil more accurate.

[0072] Step S5: predicting the out-of-stock duration of the refined oil according to the current refined oil inventory and the predicted sales volume of the refined oil in each time period.

[0073] After the method of step S1 to step S46, a relatively accurate predicted sales volume of refined oil has been obtained. At this time, it is possible to determine how long it will take for the current refined oil inventory to be sold out based on the current refined oil inventory and the predicted sales volume of refined oil in each time period, and then obtain the out-of-stock duration.

[0074] Compared with the prior art, the denitrification time obtained by the present application is more accurate and can provide effective guidance for the distribution of refined oil. When the refined oil is distributed according to the out-of-stock time of the present application, the out-of-stock level can be divided according to the out-of-stock time, and the distribution strategy of the refined oil that fails can be arranged according to the different out-of-stock levels, thereby improving the efficiency of refined oil distribution.

[0075] Embodiment 2:

[0076] Based on the foregoing embodiments, the embodiments of the present application provide a device for predicting out-of-stock of refined oil. The modules included in the device and the units included in each module can be implemented by a processor in a computer device; of course, they can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Microprocessor Unit), a digital signal processor (DSP, Digital Signal Processing) or a field programmable gate array (FPGA, Field Programmable Gate Array), etc.

[0077] like Figure 2 As shown, the present application provides a device for predicting out-of-stock of refined oil, comprising: a first acquisition module 1, a first determination module 2, a second determination module 3, a first prediction module 4 and a second prediction module 5.

[0078] The first acquisition module 1 is used to obtain the current finished oil inventory of the target gas station and the weekly sales records of finished oil every week within a preset time range. The first determination module 2 is used to determine the finished oil weekly factor of the target gas station based on multiple weekly sales records of finished oil. The second determination module 3 is used to determine the finished oil time period characteristics of the target gas station every day of the week based on all the weekly sales records of finished oil. The first prediction module 4 is used to predict the predicted sales volume of finished oil in each time period in the next week based on the finished oil weekly factor and the finished oil time period characteristics. The second prediction module 5 is used to predict the out-of-stock duration of finished oil based on the current finished oil inventory and the predicted sales volume of finished oil in each time period.

[0079] In some embodiments, the first determination module 2 includes: a third determination module, a fourth determination module, a fifth determination module and a first execution module.

[0080] The first determination module 2 is used to determine the daily average sales value of finished oil in week i according to the daily sales records of finished oil corresponding to week i in the multiple weekly sales records of finished oil. The fourth determination module is used to determine the weekly average sales value of finished oil according to the multiple weekly sales records of finished oil. The fifth determination module is used to determine the characteristic factor of week i according to the daily average sales value of finished oil and the weekly average sales value of finished oil. The first execution module is used to form a vector of the characteristic factors of 7 days to obtain the week factor.

[0081] In some embodiments, the second determination module 3 includes: a sixth determination module, a third prediction module and a fourth prediction module.

[0082] The sixth determination module is used to determine the weekly average characteristics of each week based on the weekly factor and the weekly sales records of the finished oil in each week. The third prediction module is used to predict the predicted average characteristics of the next week based on the weekly average characteristics of multiple weeks. The fourth prediction module is used to predict the predicted sales volume of finished oil in each time period in the next week based on the predicted average characteristics, the weekly factor and the time period characteristics of the finished oil.

[0083] In some embodiments, the sixth determination module includes: a second execution module and a seventh determination module.

[0084] The second execution module is used to normalize the weekly factor to obtain a normalized factor. The seventh determination module is used to determine the weekly average feature according to the normalized factor and each weekly sales record of the finished oil.

[0085] In some embodiments, the fourth prediction module includes: an eighth determination module and a fifth prediction module.

[0086] The eighth determination module is used to determine the predicted daily sales volume for the next week according to the predicted average characteristics and the weekly factor. The fifth prediction module is used to predict the predicted sales volume of refined oil in each time period of each day according to the predicted daily sales volume and the refined oil time period characteristics.

[0087] In some embodiments, the device further includes: a second acquisition module, a third execution module and a fourth execution module.

[0088] The second acquisition module is used to obtain the actual sales volume of the target gas station in each time period of the day. The third execution module is used to compare the actual sales volume with the predicted sales volume of the refined oil in the corresponding time period to obtain a comparison result. The fourth execution module is used to correct the predicted sales volume of the refined oil in each time period of the day according to the comparison result.

[0089] Each module in the above-mentioned out-of-stock prediction device for refined oil can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the device in the form of hardware, or can be stored in the memory in the processing device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0090] Embodiment 3:

[0091] The third aspect provides an electronic device including a storage device and a processor, wherein the storage device stores a computer program, and when the processor executes the computer program, the steps of a method for predicting out-of-stock of refined oil are implemented.

[0092] Embodiment 4:

[0093] The fourth aspect provides a storage medium, which stores a computer program that can be executed by one or more processors, and the computer program can be used to implement the steps of any one of the methods for predicting out-of-stock of refined oil products in the first aspect.

[0094] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0095] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and 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. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0096] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0097] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the 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 can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0098] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; 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 present embodiment.

[0099] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0100] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read Only Memory), disks or optical disks, etc. Various media that can store program codes.

[0101] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a controller to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0102] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting out-of-stock of refined oil, characterized in that: include: Obtain the current inventory of refined oil products of the target gas station and the weekly sales records of refined oil products within a preset time range; Determine a refined oil weekly factor of the target gas station according to a plurality of refined oil weekly sales records, wherein the refined oil weekly factor is used to represent the refined oil sales of the target gas station every day in a week; Determine the refined oil time period characteristics of the target gas station every day in a week according to all the refined oil weekly sales records, wherein the refined oil time period characteristics are used to characterize the refined oil sales situation in each time period of a day; Predicting the sales volume of refined oil in each period in the next week according to the refined oil weekly factor and the refined oil period characteristics; The out-of-stock duration of the refined oil is predicted based on the current refined oil inventory and the predicted sales volume of the refined oil in each time period.

2. The method for predicting out-of-stock of refined oil according to claim 1, characterized in that: The weekly sales record of refined oil includes: daily sales record of refined oil; the weekly factor of refined oil of the target gas station is determined according to a plurality of weekly sales records of refined oil, including: Determine the average daily sales value of refined oil in week i according to the daily sales records of refined oil corresponding to week i in the plurality of weekly sales records of refined oil; Determine the weekly average sales value of refined oil according to the plurality of weekly sales records of refined oil; Determine the characteristic factor of week i according to the daily average sales value of refined oil and the weekly average sales value of refined oil; The characteristic factors of the seven days are combined into a vector to obtain the week factor.

3. The method for predicting out-of-stock of refined oil according to claim 1, characterized in that: The predicted sales volume of refined oil in each period in the next week according to the refined oil weekly factor and the refined oil period characteristics includes: Determine the weekly average characteristics of each week according to the weekly factor and the weekly sales record of the refined oil product; Predicting the predicted average characteristics of the next week based on the weekly average characteristics of multiple weeks; The predicted sales volume of refined oil in each time period in the next week is predicted based on the predicted average characteristics, the weekly factors and the refined oil time period characteristics.

4. The method for predicting out-of-stock of refined oil according to claim 3, characterized in that: The method of determining the weekly average characteristics of each week based on the weekly factor and the weekly sales records of the refined oil products includes: Normalizing the week factor to obtain a normalized factor; The weekly average characteristic is determined according to the normalization factor and each of the weekly sales records of the refined oil.

5. The method for predicting out-of-stock of refined oil according to claim 3, characterized in that: The predicted average features of the next week are predicted based on the weekly average features of multiple weeks, and are achieved by the following formula: r i_yu ＝0.5r i-1 +0.5r i-1_yu In the formula, r i-1_yu =0.2r i-2_yu +0.8r i-1 , where r i-1 represents the weekly average characteristics of the i-1th week, r i_yu represents the predicted average features for week i, where i also represents the next week.

6. The method for predicting out-of-stock of refined oil according to claim 3, characterized in that: The predicted sales volume of refined oil in each period in the next week according to the predicted average feature, the weekly factor and the refined oil period feature includes: Determine the predicted daily sales volume for the next week based on the predicted average feature and the weekly factor; The predicted sales volume of refined oil in each time period of each day is predicted based on the predicted daily sales volume and the time period characteristics of the refined oil.

7. The method for predicting out-of-stock of refined oil according to claim 1, characterized in that: Before predicting the out-of-stock duration of the refined oil according to the current refined oil inventory and the predicted sales volume of the refined oil in each time period, the method further includes: Obtain the actual sales volume of the target gas station at each time period of the day; Comparing the actual sales volume with the predicted sales volume of the refined oil in the corresponding period to obtain a comparison result; The predicted sales volume of refined oil in each time period of the day is corrected according to the comparison result.

8. A device for predicting out-of-stock of refined oil, characterized in that: include: The first acquisition module is used to obtain the current inventory of refined oil products of the target gas station and the weekly sales records of refined oil products within a preset time range; A first determination module is used to determine the refined oil weekly factor of the target gas station according to a plurality of the refined oil weekly sales records; The second determination module is used to determine the time period characteristics of the finished oil of the target gas station every day of the week according to all the weekly sales records of the finished oil; The first prediction module is used to predict the sales volume of finished oil in each period in the next week according to the weekly factor of the finished oil and the time period characteristics of the finished oil; The second prediction module is used to predict the out-of-stock duration of the refined oil according to the current refined oil inventory and the predicted sales volume of the refined oil in each time period.

9. An electronic device, characterized in that: include: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is executed.

10. A storage medium, characterized in that: The computer program stored in the storage medium can be executed by one or more processors, and the computer program can be used to implement the method according to any one of claims 1 to 7.

Images