A method, apparatus, storage medium, and electronic equipment for predicting oil delivery volume from an oil depot.

Abstract

This application discloses a method, apparatus, storage medium, and electronic device for predicting oil delivery volume from an oil depot. The method includes: determining historical oil delivery data for a target oil depot within a preset time period; determining an initial predicted oil delivery volume for a target prediction date based on the historical oil delivery data using a preset oil delivery volume and time relationship model; determining the increment of an oil price change trend factor based on the target prediction date using a preset oil price change trend model; generating an oil delivery volume prediction model based on the initial predicted oil delivery volume, the value of a preset seasonality factor or a preset weeklyity factor, and the increment of the oil price change trend factor; and predicting the oil delivery volume of the target oil depot on the target prediction date based on the oil delivery volume prediction model. By first determining the initial predicted oil delivery volume, and then combining the value of the preset seasonality factor or the preset weeklyity factor, and the increment of the oil price change factor, an oil delivery volume prediction model is generated, which can accurately predict the oil delivery volume trend of the oil depot over a period of time.

Description

Technical Field

[0001] This application relates to the field of refined oil logistics scheduling technology, and in particular to a method, apparatus, storage medium and electronic equipment for predicting oil depot delivery volume. Background Technology

[0002] Oil depots are a key link in the logistics supply chain of refined oil sales companies. They receive refined oil products from refineries and other sources, and then dispatch and distribute them according to the needs of gas station terminals, thus enabling refined oil products to flow from the production stage to the retail stage.

[0003] The efficiency of oil depot operations is determined by the oil delivery plans to oil depots, the distribution schemes from oil depots to gas stations, and their execution in the refined oil logistics scheduling. Currently, the turnover rate of an oil depot can be used to assess its operational efficiency. Within a specified time period, a higher turnover rate indicates a greater overall frequency of oil product receipts and deliveries, and thus higher operational efficiency. Conversely, a lower turnover rate indicates that the storage and delivery capacity of the oil depot is not being fully utilized, and the depot needs further optimization.

[0004] To effectively improve oil depot turnover, it is necessary to develop oil receiving and dispatch plans that closely align with the actual conditions of the oil depot. This relies on a relatively accurate prediction of the oil dispatch volume. If the oil dispatch trend of a particular oil depot over a future period (such as a week or a month) can be predicted, then the oil inventory at that depot at a future point in time can be simulated. Especially when the inventory drops to a level requiring attention or triggering an alarm, corresponding replenishment plans should be developed to ensure that the oil inventory fluctuates within a reasonable range, thereby avoiding the risk of running out of oil and maximizing the depot's turnover efficiency.

[0005] In existing technical solutions, the average value of oil delivery for the next few days is usually calculated by averaging the oil delivery volume over the past few days. However, this solution cannot simulate the fluctuation of future oil delivery volume over the number of days, nor can it accurately predict the changing trend of oil depot inventory.

[0006] Some literature has used a neural network-based method to predict oil depot outflows. This method establishes a neural network model containing multiple factors based on the total outflow from the oil depot, achieving a prediction accuracy of approximately 85%. However, this method fails to distinguish between effective outflows in the outflow calculation, and while the established neural network model has high accuracy in simulating historical trends, its accuracy is poor when extended to predict future periods, thus it cannot fully meet the needs of actual oil depot scheduling.

[0007] Furthermore, while existing technologies can predict changes in gas station sales volume, oil depot delivery is also affected by factors such as bulk oil receiving and storage operations, customer self-pickup and delivery operations, and the distribution balance scheduling among multiple delivery stations. The difficulty of prediction is far greater than that of prediction for a single gas station, and the sales volume prediction model for gas stations cannot be extended to oil depot delivery prediction.

[0008] Therefore, there is an urgent need for a method that can more accurately predict the amount of oil delivered from oil depots. Summary of the Invention

[0009] To address the aforementioned problems, this application proposes a method, apparatus, storage medium, and electronic equipment for predicting oil depot delivery volume, which at least solves the problem that existing technologies cannot effectively predict oil depot delivery volume.

[0010] A first aspect of this application provides a method for predicting oil depot delivery volume, the method comprising:

[0011] Determine the historical oil delivery data of the target oil depot within a preset time period;

[0012] Based on the historical hair oil data, the initial predicted hair oil volume for the target prediction date is determined using a preset hair oil volume and time relationship model;

[0013] Based on the target prediction date, the increment of the oil price change trend factor is determined using a preset oil price change trend model;

[0014] Based on the initial predicted oil volume, the value of the preset oil seasonality factor or the value of the preset oil weeklyity factor, and the increment of the oil price change trend factor, an oil volume prediction model is generated.

[0015] The oil delivery volume of the target oil depot is predicted on the target prediction date based on the oil delivery volume prediction model.

[0016] In some embodiments, determining the historical oil delivery data of the target oil depot within a preset time period includes:

[0017] Obtain the raw oil delivery data of the target oil depot within a preset time period;

[0018] The original hair oil data is subjected to noise reduction processing to obtain the historical hair oil data.

[0019] In some embodiments, the noise reduction processing of the original hair oil data to obtain the historical hair oil data includes:

[0020] The trend items in the original hair oil data are removed to obtain the hair oil data after removing the trend items.

[0021] The hair oil data after removing the trend term is filtered to obtain the historical hair oil data.

[0022] In some embodiments, the filtering process includes:

[0023] Any one of Fourier transform, moving average method, and inertial filtering.

[0024] In some embodiments, determining the initial predicted oil volume for the target prediction date based on the historical oil data using a preset oil volume and time relationship model includes:

[0025] Obtain a target data set from the historical hair oil data, wherein the target data set contains historical hair oil data for a consecutive preset number of days prior to the target prediction date;

[0026] Based on the target data set, the initial predicted value of the oil volume for the target prediction date is determined using the preset oil volume and time relationship model.

[0027] In some embodiments, the hair oil volume prediction model includes:

[0028] b total =b·c+p

[0029] Among them, b total 1 is the total predicted oil volume for the target forecast date; b is the initial predicted oil volume for the target forecast date; c is the seasonality factor or weekly factor for oil delivery; p is the increment of the oil price trend factor.

[0030] In some embodiments, the preset oil price change trend model includes:

[0031] Δs=Δp·G·e -t / τ

[0032] Where Δs is the increment of the oil price change trend factor, Δp is the price change amount, G is the gain between the price change and the sales volume adjustment, τ is the time constant of the adjustment process model, and t is the number of days after the oil price adjustment.

[0033] A second aspect of this application provides an oil depot oil delivery volume prediction device, the device comprising:

[0034] The first determining module is used to determine the historical oil delivery data of the target oil depot within a preset time period;

[0035] The second determining module is used to determine the initial predicted value of the amount of oil applied to the target prediction date based on the historical oil application data and a preset oil application quantity and time relationship model.

[0036] The third determining module is used to determine the increment of the oil price change trend factor based on the target prediction date and a preset oil price change trend model.

[0037] The generation module is used to generate an oil delivery volume prediction model based on the initial oil delivery volume prediction value, the value of the preset oil delivery seasonality factor or the value of the preset oil delivery weekly factor, and the increment of the oil price change trend factor.

[0038] The prediction module is used to predict the oil delivery volume of the target oil depot on the target prediction date based on the oil delivery volume prediction model.

[0039] A third aspect of this application provides a computer-readable storage medium storing a computer program that can be executed by one or more processors to implement the method described above.

[0040] A fourth aspect of this application provides an electronic device including a memory and one or more processors, wherein a computer program is stored on the memory, and the memory and the one or more processors are communicatively connected to each other, and the computer program, when executed by the one or more processors, implements the method described above.

[0041] Compared with the prior art, the technical solution of this application has the following advantages or beneficial effects:

[0042] First, data preprocessing is used to eliminate factors that interfere with oil delivery forecasting in the target oil depot. Then, the initial oil delivery volume forecast for the target forecast date is determined by a self-learning iterative training method using actual historical data from the target oil depot. In conjunction with the introduced seasonal factors, weekly factors, oil price change factors, and other influencing parameters, a model for oil depot delivery volume forecasting is established. This model can accurately predict the trend of oil delivery volume changes in the target oil depot over a period of time, meeting the needs of oil sales companies for optimized decision-making and precise scheduling in logistics. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0044] Figure 1 A flowchart illustrating an oil depot oil release trend prediction method provided in this application embodiment;

[0045] Figure 2 A schematic diagram of the incremental adjustment process curve of a price change trend factor is provided for an embodiment of this application;

[0046] Figure 3 This is a schematic diagram of the structure of an oil depot oil release trend prediction device provided in an embodiment of this application;

[0047] Figure 4 A connection block diagram of an electronic device provided in an embodiment of this application;

[0048] Figure 5 This is a schematic diagram of an iterative learning framework provided in an embodiment of this application. Detailed Implementation

[0049] The following detailed description of the embodiments of this application, in conjunction with the accompanying drawings, will provide a thorough understanding of how this application uses technical means to solve technical problems and achieve corresponding technical effects, enabling its implementation. The embodiments of this application and the various features within them can be combined with each other without conflict, and all resulting technical solutions are within the protection scope of this application.

[0050] Example 1

[0051] This embodiment provides a method for predicting oil depot delivery volume. Figure 1 A flowchart illustrating a method for predicting oil depot delivery volume provided in this application embodiment is shown below. Figure 1 As shown, the method in this embodiment includes:

[0052] S110. Determine the historical oil delivery data of the target oil depot within a preset time period.

[0053] Oil depot dispatches include bulk dispatches via rail and pipeline, as well as road dispatches. The data to be predicted is for the sales portion of both bulk and road dispatches, referred to as the effective dispatch volume. For dispatches where customers pick up their own oil, accurate prediction is generally difficult due to the influence of the customer's decision regarding storage; therefore, this data needs to be excluded from the actual dispatch volume.

[0054] In some embodiments, determining the historical oil delivery data of the target oil depot within a preset time period includes:

[0055] Obtain the raw oil delivery data of the target oil depot within a preset time period;

[0056] The original hair oil data is subjected to noise reduction processing to obtain the historical hair oil data.

[0057] Optionally, the system can obtain continuous oil delivery data from the target oil depot within a preset time period, and remove the customer self-pickup type oil delivery data to obtain the effective oil delivery volume data.

[0058] Based on the obtained effective oil delivery data, noise reduction processing can be performed to determine the historical oil delivery data of the target oil depot within a preset time period.

[0059] It should be noted that the preset duration can be set according to the user's actual needs, such as the last six months. No specific limitation is made here.

[0060] In some embodiments, the noise reduction processing of the original hair oil data to obtain the historical hair oil data includes:

[0061] The trend items in the original hair oil data are removed to obtain the hair oil data after removing the trend items.

[0062] The hair oil data after removing the trend term is filtered to obtain the historical hair oil data.

[0063] In some embodiments, the filtering process includes:

[0064] Any one of Fourier transform, moving average method, and inertial filtering.

[0065] Optionally, using Fourier transform as an example, Fourier analysis is employed to denoise historical hair oil data within a specified time window. Fourier analysis can be used for data denoising, identifying data trends, and extracting hair oil data after removing the linear trend from a given period of data.

[0066] Assume the data sequence is as follows:

[0067] X = [x1, x2, ..., x N ]

[0068] The slope is defined as:

[0069] slop=(x N -x1) / (N-1)

[0070] Removing the trend term from X, we get X′:

[0071] X′=[x′1,x′2,x′3,…,x′ N ]=[x1,x2-slop·1,x3-slop·2,…,x N -slop·(N-1)]

[0072] Perform a Fourier transform on X′:

[0073]

[0074] Where a0 is the mean of X′, an and bn represent the amplitudes of each sine and cosine wave, L = N / 2, and the value of x ranges from 0 to N-1, thus the terms of X′ can be calculated.

[0075] Perform Fourier transform filtering on X′, that is, calculate the superposition of low-frequency harmonics, and add back the subtracted linear trend term to obtain the data after Fourier transform filtering. The filtered data is used as historical oil release data.

[0076] Noise reduction achieved through Fourier transform does not introduce the time lag defect similar to that of inertial filtering. In addition to Fourier transform filtering, other filtering methods such as moving average and inertial filtering can also be selected.

[0077] S120. Based on the historical oiling data, determine the initial predicted oiling volume for the target prediction date using a preset oiling volume and time relationship model.

[0078] In some embodiments, determining the initial predicted oil volume for the target prediction date based on the historical oil data using a preset oil volume and time relationship model includes:

[0079] Obtain a target data set from the historical hair oil data, wherein the target data set contains historical hair oil data for a consecutive preset number of days prior to the target prediction date;

[0080] Based on the target data set, the initial predicted value of the oil volume for the target prediction date is determined using the preset oil volume and time relationship model.

[0081] Optionally, a set of oiling volume data for the six consecutive days prior to the target prediction date can be obtained from the historical oiling data, or a set of oiling volume data for the most recent six consecutive days can be obtained from the historical oiling data.

[0082] For example, recent data is as follows:

[0083] Data timestamps are as follows (-1 represents data from one day ago, -2 represents data from two days ago, and so on):

[0084] [t -6 , t -5 , t -4 , t -3 , t -2 , t -1 ] = [-6, -5, -4, -3, -2, -1]

[0085] The oil application data is as follows (corresponding to the timestamp vector above):

[0086] [y -6 y -5 y-4 y -3 y -2 y -1 ] = [131.84, 84.326, 135.213, 47, 50.348, 98.148].

[0087] One possible preset model for the relationship between hair oil volume and time is:

[0088] y = b0 + b1t 1 +b2t 2 +b3t 3

[0089] Where b0 to b3 are constants, and t represents time.

[0090] Find the least-squares solution to the following system of equations:

[0091]

[0092] The above system of equations has 6 equations and only 4 unknowns, and generally has no solution. Therefore, we need to find an optimal b that minimizes d = ||A·bY||, which means minimizing d. 2 =(A·bY) T Minimize (A·bY):

[0093] d 2 =(A·bY) T ·(A·bY)= T YY T Ab-b T A T Y+b T A T Ab

[0094] That is, the following equation needs to be satisfied:

[0095]

[0096] make get:

[0097]

[0098] This yields vector b, which represents the coefficients of the optimal regression polynomial, used to predict the shipment volume for the current day and the following days. Substituting t=0 into the preset oil delivery volume and time relationship model, we obtain b0, which is the initial predicted oil delivery volume for the day; substituting t=1 into the preset oil delivery volume and time relationship model, we obtain: b0+1*1+1 2 *3+1 3*4; This is the initial oil volume forecast for tomorrow (the second day). The initial oil volume forecast for multiple days can be determined by analogy.

[0099] It should be noted that the order of the polynomial and the length of the data used for solving it need to be found optimally through multiple trials. First to third order are good choices, and after multiple verifications, a time window length of two to three times the order is preferred.

[0100] It should be further noted that different target prediction dates directly affect the historical oil delivery data within the predetermined time frame of the target oil depot. When the historical oil delivery data differs, the initial oil delivery volume prediction for the target prediction date needs to be determined through iterative training using actual historical data. Therefore, the polynomial needs to be recalculated, i.e., a rolling optimization approach is used for prediction. Here, matrix (A) ^T A) ^(-1) ·A ^T It can be calculated in advance and used directly later.

[0101] The above describes the general calculation process for multinomial regression. In practice, Partial Least Squares (PLS) can be used to replace traditional least squares. PLS projects a high-dimensional data space onto a low-dimensional feature space to obtain mutually orthogonal feature vectors, and then establishes a univariate linear regression relationship between these feature vectors. PLS transforms a multivariate regression problem into several univariate regressions, making it suitable for process modeling with a small number of samples and a large number of variables. When selecting feature vectors, it emphasizes the explanatory and predictive role of the input on the output, removing noise that is not beneficial to the regression, and minimizing the number of variables in the model. Therefore, PLS models have better robustness and predictive stability. However, for models such as neural networks or support vector machines, which generally require a large amount of data for training, the window length used in iterative learning frameworks cannot be too large, making them less suitable.

[0102] It should be noted that the preset number of days can be set according to the user's actual needs. For example, the preset number of days can be set to 6 days. No specific limitation is made here.

[0103] S130. Based on the target prediction date, determine the increment of the oil price change trend factor using a preset oil price change trend model.

[0104] In some embodiments, the preset oil price change trend model includes:

[0105] Δs=Δp·G·e -t /

[0106] Where Δs is the increment of the oil price change trend factor, Δp is the price change amount, G is the gain between the price change and the sales volume adjustment, τ is the time constant of the adjustment process model, and t is the number of days after the oil price adjustment.

[0107] Optionally, the price change trend factor represents the inhibitory effect on consumption after an increase in oil prices. However, the impact of price factors is often only in the initial period. After extensive data testing and analysis, the increment of the oil price change trend factor can be represented by the mathematical model described below:

[0108] Δs=Δp·G·e -t /

[0109] Where Δp is the price change, G is the gain between the price change and the sales volume adjustment, τ is the time constant of the adjustment process model (exponential decay model), and Δs is the final adjustment increment, i.e. the increment of the oil price change trend factor. The unit of the price change is yuan, and the unit of the oil price change trend factor increment is tons.

[0110] For example, given G = -5, Δp = 1, and τ = 6, a curve illustrating the incremental adjustment process of a price change trend factor can be found for reference. Figure 2 , Figure 2 This is a schematic diagram of the incremental adjustment process curve of a price change trend factor provided in an embodiment of this application, where the horizontal axis represents days, indicating the number of days after price adjustment, and the vertical axis represents the sales increment, indicating the sales increment affected by price factors.

[0111] It should be noted that the gain G between price changes and sales volume adjustments can be an empirical value obtained by comparing statistical data of gas stations over a certain period of time. This value will vary between gas stations of different sizes. The time constant τ of the adjustment process model (exponential decay model) can range from 3 to 8, depending on people's sensitivity to price changes. It is also the result obtained after long-term statistics of each gas station of different sizes.

[0112] Those skilled in the art will understand that the specific increment of the oil price change trend factor can be determined using an oil price change trend model based on the target forecast date. For example, refer to... Figure 2 First, determine the target forecast date as which day after the price adjustment. If the target forecast date is the 1st day after the price adjustment, then the value of the number of days after the price adjustment t in the preset oil price change trend model is 1, and the value of the increment of the oil price change trend factor can be -5 tons. If the target forecast date is the 19th day after the price adjustment, then the value of the number of days after the price adjustment t in the preset oil price change trend model is 19, and the value of the increment of the oil price change trend factor can be 0 tons.

[0113] S140. Generate an oil delivery volume prediction model based on the initial oil delivery volume prediction value, the preset oil delivery seasonality factor value or the preset oil delivery weekly factor value, and the oil price change trend factor increment.

[0114] After obtaining the initial oil delivery volume forecast for the target forecast date, the initial oil delivery volume forecast is adjusted accordingly based on the increments of seasonal factors, weekly factors, and price change trend factors. One possible adjustment rule includes:

[0115] Seasonal factors: For different busy farming seasons and holidays, the incremental amount for each holiday is determined based on historical data; for example, for typical holidays such as the Spring Festival, the amount of fuel used for agricultural facilities is relatively small, so the diesel sales forecast for the Spring Festival is multiplied by 0.7, while for holidays such as Labor Day and National Day, the gasoline sales forecast is multiplied by 1.2.

[0116] Weekly Factor: For each of the 7 days of the week, different incremental rules are set to obtain the corresponding weekly factor for fuel consumption. For example, based on the accumulated habits of fuel consumption on weekdays and weekends, fuel consumption is lower on weekdays and higher on weekends. The solution is to multiply the predicted result for weekdays by 0.9 and the predicted result for weekends by 1.15 to keep the overall data stable and the cumulative amount of data within a week unchanged.

[0117] It should be noted that the preset seasonality factor and the preset weeklyity factor of hair oil can be set according to the above conditions. For example, the preset seasonality factor can be set to 0.7 or 1.2 depending on the actual situation, and the preset weeklyity factor can be set to 0.9 or 1.15 depending on the actual situation. Of course, the preset seasonality factor and the preset weeklyity factor can also be set according to the user's actual needs, and no special restrictions are made here.

[0118] Optionally, after determining the initial oil delivery volume forecast value b for the target forecast date, an oil delivery volume forecast model is generated based on the value of the preset oil delivery seasonality factor or the value of the preset oil delivery weeklyity factor and the increment of the oil price change trend factor.

[0119] In some embodiments, the hair oil volume prediction model includes:

[0120] b total =·c+

[0121] Among them, b total 1 is the total predicted oil volume for the target forecast date; b is the initial predicted oil volume for the target forecast date; c is the seasonality factor or weekly factor for oil delivery; p is the increment of the oil price trend factor.

[0122] Optionally, in the above oil production prediction model, b total b is the total predicted oil volume for the target forecast date; c is the initial predicted oil volume for the target forecast date; c represents a constant coefficient, including the seasonality factor c_s and the weekly factor c_w; p is the increment of the oil price change trend factor.

[0123] Optionally, when the target forecast date falls within a holiday period, the influence of the weekly factor of hair oil is not considered; when the target forecast date falls outside a holiday period, the influence of the seasonal factor of hair oil is not considered.

[0124] As will be understood by those skilled in the art, oil yield prediction models can specifically include the following two forms:

[0125] b total1 =b·c_s+p; and

[0126] b total2 =b·c_w+p.

[0127] Among them, b total1 For oil delivery volume prediction models where the target prediction date falls within a holiday period; b total2 This is a prediction model for oil delivery volume when the target prediction date falls within a non-holiday period.

[0128] S150. Based on the oil delivery prediction model, predict the oil delivery volume of the target oil depot on the target prediction date.

[0129] Optionally, the total oil delivery volume for the target forecast date can be predicted using an oil delivery volume prediction model. Then, the total oil delivery volume forecast for that target forecast date can be determined by combining the seasonality factor, weekly factor, and oil price change trend factor of that day.

[0130] For example, when the target forecast date falls during a holiday period (such as the Spring Festival for diesel), assuming the initial forecast value of the oil delivery volume on the target forecast date is 100 tons based on the preset oil delivery volume and time relationship model; after combining the seasonal factor, it becomes 100 × 0.7 = 70 tons; and after combining the price change trend factor, the increment of the price change trend factor determined by the preset oil price change trend model is assumed to be -10 tons, then the total forecast value of the oil delivery volume on the target forecast date should be: 70 + (-10) = 60 tons.

[0131] It should be noted that, based on the prediction of the initial oil delivery volume of the target oil depot for multiple days by using the preset oil delivery volume and time relationship model, and by combining the value of the preset oil delivery seasonality factor or the preset oil delivery weekly factor and the increment of the oil price change trend factor, the total oil delivery volume for multiple days can be predicted, and thus the oil delivery trend of the target oil depot over a period of time can be predicted.

[0132] This application provides a prediction framework based on iterative learning, in which the filtering and noise reduction processing, regression modeling method, and various influencing factors can be adjusted according to the specific circumstances of different gas stations and different oil products.

[0133] The method disclosed in this application predicts semen volume using a self-learning iterative approach. In conjunction with effective semen volume data obtained through data preprocessing, a sliding window data confirmation process is performed before each prediction. Model parameters are then adjusted and optimized, and the model is trained by comparing with historical data to further refine the parameters. Only after completing the self-learning process is the actual prediction performed, ensuring that the semen volume prediction model yields a more accurate prediction each time. A detailed diagram of the iterative learning process can be found in [reference needed]. Figure 5 , Figure 5 This is a schematic diagram of an iterative learning framework provided in an embodiment of this application.

[0134] The method disclosed in this embodiment can be used for decision optimization in the field of refined oil logistics scheduling. In refined oil scheduling, the oil delivery plan to oil depots, the delivery scheme from oil depots to gas stations, and their execution determine the operational efficiency of oil depots. The turnover rate of oil depots can be used to assess their operational efficiency. Within a specified time period, the higher the turnover rate of oil depots, the greater the average overall frequency of oil receipts and deliveries, and the higher the operational efficiency of oil depots. To effectively improve the turnover rate of oil depots, it is necessary to formulate oil receipt and delivery plans that are closely aligned with the actual situation of oil depots. The key lies in making relatively accurate predictions of the oil delivery volume of oil depots. This application can relatively accurately predict the trend of oil delivery volume changes of a specified oil depot over a period of time, and further simulate the oil inventory of oil depots at a future point in time. Combined with the logistics scheduling system, it can ensure that the oil in the oil depot fluctuates within a reasonable range, avoiding the risk of oil depots having no oil to deliver or no empty capacity to receive oil, thereby maximizing the turnover efficiency of oil depots.

[0135] The oil depot delivery volume prediction method provided in this embodiment includes: firstly, determining the historical delivery data of the target oil depot within a preset time period; then, determining the initial delivery volume prediction value for the target prediction date based on the historical delivery data using a preset delivery volume and time relationship model, and determining the oil price change trend factor increment based on the target prediction date using a preset oil price change trend model; and generating an oil delivery volume prediction model based on the initial delivery volume prediction value, the value of a preset seasonality factor or a preset weeklyity factor, and the increment of the oil price change trend factor; and then predicting the delivery volume of the target oil depot on the target prediction date based on the oil delivery volume prediction model. Firstly, data preprocessing is used to eliminate factors interfering with the delivery prediction in the target oil depot. Then, the initial delivery volume prediction value for the target prediction date is determined through a self-learning iterative training method using the actual historical data of the target oil depot. Combined with the introduced seasonality factor, weeklyity factor, oil price change factor, and other influencing parameters, an oil depot delivery volume prediction model is established. This model can accurately predict the oil delivery volume change trend of the target oil depot over a period of time, meeting the needs of oil sales companies for optimized decision-making and precise scheduling in logistics dispatching.

[0136] Example 2

[0137] This embodiment provides an oil depot oil delivery volume prediction device. This device embodiment can be used to execute the method embodiment of this application. For details not disclosed in this device embodiment, please refer to the method embodiment of this application. Figure 3 This is a schematic diagram of the structure of a device provided in an embodiment of this application, such as... Figure 3 As shown, the device 300 provided in this embodiment includes:

[0138] The first determining module 301 is used to determine the historical oil delivery data of the target oil depot within a preset time period;

[0139] The second determining module 302 is used to determine the initial predicted value of the amount of oil applied to the target prediction date based on the historical oil application data and a preset oil application quantity and time relationship model.

[0140] The third determining module 303 is used to determine the increment of the oil price change trend factor based on the target prediction date and a preset oil price change trend model.

[0141] The generation module 304 is used to generate an oil delivery volume prediction model based on the initial oil delivery volume prediction value, the value of the preset oil delivery seasonality factor or the value of the preset oil delivery weeklyity factor, and the increment of the oil price change trend factor.

[0142] The prediction module 305 is used to predict the oil delivery volume of the target oil depot on the target prediction date based on the oil delivery volume prediction model.

[0143] In some embodiments, the first determining module 301 includes: an acquisition unit and a noise reduction unit; wherein...

[0144] The acquisition unit is used to acquire the original oil delivery data of the target oil depot within a preset time period;

[0145] A noise reduction unit is used to perform noise reduction processing on the original hair oil data to obtain the historical hair oil data.

[0146] In some embodiments, the noise reduction unit includes: a removal subunit and a filtering subunit; wherein,

[0147] The removal subunit is used to remove trend items from the original hair oil data to obtain hair oil data after removing trend items;

[0148] The filtering subunit is used to filter the hair oil data after removing the trend term to obtain the historical hair oil data.

[0149] In some embodiments, the filtering process includes:

[0150] Any one of Fourier transform, moving average method, and inertial filtering.

[0151] In some embodiments, the second determining module 302 includes: acquiring a sub-unit and determining a sub-unit; wherein...

[0152] The acquisition subunit is used to acquire a target data set from the historical hair oil data, wherein the target data set contains historical hair oil data for a consecutive preset number of days before the target prediction date;

[0153] A subunit is defined to determine the initial predicted value of the oil volume for the target prediction date based on the target data set and the preset oil volume and time relationship model.

[0154] In some embodiments, the hair oil volume prediction model includes:

[0155] b total =b·c+p

[0156] Among them, b total 1 is the total predicted oil volume for the target forecast date; b is the initial predicted oil volume for the target forecast date; c is the seasonality factor or weekly factor for oil delivery; p is the increment of the oil price trend factor.

[0157] In some embodiments, the preset oil price change trend model includes:

[0158] Δs=Δp·G·e -t / τ

[0159] Where Δs is the increment of the oil price change trend factor, Δp is the price change amount, G is the gain between the price change and the sales volume adjustment, τ is the time constant of the adjustment process model, and t is the number of days after the oil price adjustment.

[0160] Those skilled in the field can understand that Figure 3 The structures shown do not constitute a limitation on the apparatus of the embodiments of this application. They may include more or fewer modules / units than shown, or combine certain modules / units, or have different module / unit arrangements.

[0161] It should be noted that the above modules / units can be either functional modules or program modules, and can be implemented through software or hardware. For modules / units implemented in hardware, the above modules / units can reside in the same processor; or the above modules / units can be located in different processors in any combination.

[0162] The apparatus provided in this embodiment includes: a first determining module 301, used to determine historical oil delivery data of the target oil depot within a preset time period; a second determining module 302, used to determine the initial predicted oil delivery volume for the target prediction date based on the historical oil delivery data using a preset oil delivery volume and time relationship model; a third determining module 303, used to determine the increment of the oil price change trend factor based on the target prediction date using a preset oil price change trend model; a generating module 304, used to generate an oil delivery volume prediction model based on the initial predicted oil delivery volume, the value of a preset oil delivery seasonality factor or a preset oil delivery weeklyity factor, and the increment of the oil price change trend factor; and a prediction module 305, used to predict the oil delivery volume of the target oil depot on the target prediction date based on the oil delivery volume prediction model. First, data preprocessing is used to eliminate factors that interfere with oil delivery forecasting in the target oil depot. Then, the initial oil delivery volume forecast for the target forecast date is determined by a self-learning iterative training method using actual historical data from the target oil depot. In conjunction with the introduced seasonal factors, weekly factors, oil price change factors, and other influencing parameters, a model for oil depot delivery volume forecasting is established. This model can accurately predict the trend of oil delivery volume changes in the target oil depot over a period of time, meeting the needs of oil sales companies for optimized decision-making and precise scheduling in logistics.

[0163] Example 3

[0164] This embodiment also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the method steps as described in the foregoing method embodiments. This embodiment will not repeat the details here.

[0165] Computer-readable storage media may individually include computer programs, data files, data structures, etc., or combinations thereof. The computer-readable storage media or computer program may be specifically designed and understood by those skilled in the art of computer software, or the computer-readable storage media may be known and available to those skilled in the art of computer software. Examples of computer-readable storage media include: magnetic media, such as hard disks, floppy disks, and magnetic tapes; optical media, such as CD-ROMs and DVDs; magneto-optical media, such as optical discs; and hardware devices specifically configured to store and execute computer programs, such as read-only memory (ROM), random access memory (RAM), flash memory; or servers, application stores, etc. Examples of computer programs include machine code (e.g., code generated by a compiler) and files containing high-level code that can be executed by a computer using an interpreter. The described hardware devices may be configured to function as one or more software modules to perform the operations and methods described above, and vice versa. Furthermore, computer-readable storage media may be distributed across networked computer systems, allowing for the decentralized storage and execution of program code or computer programs.

[0166] Example 4

[0167] Figure 4 A connection block diagram of an electronic device provided in an embodiment of this application, such as... Figure 4 As shown, the electronic device 400 may include: one or more processors 401, memory 402, multimedia components 403, input / output (I / O) interface 404, and communication components 405.

[0168] One or more processors 401 are used to execute all or part of the steps as described in the foregoing method embodiments. Memory 402 is used to store various types of data, which may include, for example, instructions for any application or method in the electronic device, as well as application-related data.

[0169] One or more processors 401 may be implemented as an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, for performing the methods as described in the foregoing method embodiments.

[0170] The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0171] Multimedia component 403 may include a screen, which may be a touchscreen, and an audio component for outputting and / or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory or transmitted via a communication component. The audio component also includes at least one speaker for outputting audio signals.

[0172] I / O interface 404 provides an interface between one or more processors 401 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons can be virtual buttons or physical buttons.

[0173] The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wired communication includes communication via network ports, serial ports, etc.; wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, 5G, or one or more combinations thereof. Therefore, the corresponding communication component 405 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0174] In summary, this application provides a method, apparatus, computer-readable storage medium, and electronic device for predicting oil delivery volume from an oil depot. The method includes: first, determining historical oil delivery data for a target oil depot within a preset time period; then, based on the historical oil delivery data, determining an initial predicted oil delivery volume for a target prediction date using a preset oil delivery volume and time relationship model, and determining an increment of an oil price change trend factor based on the target prediction date using a preset oil price change trend model; generating an oil delivery volume prediction model based on the initial predicted oil delivery volume, the value of a preset seasonality factor or a preset weeklyity factor, and the increment of the oil price change trend factor; and finally, predicting the oil delivery volume of the target oil depot on the target prediction date based on the oil delivery volume prediction model. First, data preprocessing is used to eliminate factors that interfere with oil delivery forecasting in the target oil depot. Then, the initial oil delivery volume forecast for the target forecast date is determined by a self-learning iterative training method using actual historical data from the target oil depot. In conjunction with the introduced seasonal factors, weekly factors, oil price change factors, and other influencing parameters, a model for oil depot delivery volume forecasting is established. This model can accurately predict the trend of oil delivery volume changes in the target oil depot over a period of time, meeting the needs of oil sales companies for optimized decision-making and precise scheduling in logistics.

[0175] It should also be understood that the methods or systems disclosed in the embodiments provided in this application can also be implemented in other ways. The method or system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functions, and operations of possible implementations of methods and apparatus according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, computer program segment, or part of a computer program, which includes one or more computer programs for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings, and may actually be executed substantially in parallel. They may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer programs.

[0176] In this application, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "including one..." does not exclude the presence of other identical elements in the process, method, apparatus, or device that includes the element; the use of terms such as "first" and "second" is for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly indicating the number or sequence of the indicated technical features; in the description of this application, unless otherwise stated, the terms "multiple" or "many" mean at least two; if a server is described, it should be noted that a server can be an independent physical server or terminal, or a server cluster consisting of multiple physical servers, or a cloud server capable of providing basic cloud computing services such as cloud servers, cloud databases, cloud storage, and CDN; if a smart terminal or mobile device is described in this application, it should be noted that a smart terminal or mobile device can be a mobile phone, tablet computer, smartwatch, netbook, wearable electronic device, personal digital assistant (PDA), augmented reality (AR) device, virtual reality (VR) device, smart TV, smart speaker, personal computer (PC). The application may include, but is not limited to, computers (PCs), etc., and does not impose any special restrictions on the specific form of smart terminals or mobile devices.

[0177] Finally, it should be noted that in the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "a single example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0178] Although embodiments of this application have been shown and described above, it is to be understood that the above embodiments are exemplary and the content is only for the purpose of facilitating understanding of this application, and is not intended to limit this application. Any person skilled in the art to which this application pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope disclosed in this application, but the scope of protection of this application shall still be determined by the scope defined in the appended claims.

Claims

1. A method for predicting oil depot delivery volume, characterized in that, The method includes: Determining historical oil delivery data of a target oil depot within a preset time period includes: acquiring the original oil delivery data of the target oil depot within the preset time period; removing customer self-pickup type oil delivery data from the original oil delivery data to obtain effective oil delivery volume data; and performing noise reduction processing on the effective oil delivery data to obtain the historical oil delivery data. Determining the initial predicted amount of hair oil for a target prediction date based on the historical hair oil data using a preset hair oil volume and time relationship model includes: obtaining a target data set from the historical hair oil data, wherein the target data set contains historical hair oil data for a consecutive preset number of days prior to the target prediction date; determining the initial predicted amount of hair oil for the target prediction date based on the target data set using the preset hair oil volume and time relationship model; wherein the preset hair oil volume and time relationship model is a multinomial regression model or a partial least squares model, and the initial predicted amount of hair oil is determined through rolling optimization. The incremental oil price change trend factor is determined based on the target forecast date using a preset oil price change trend model; wherein, the preset oil price change trend model includes: in, This represents the increment of the oil price trend factor. Let G be the price change, G be the gain between the price change and the sales volume adjustment, τ be the time constant of the adjustment process model, and t be the number of days after the oil price adjustment. Based on the initial predicted oil volume, the value of the preset oil seasonality factor or the value of the preset oil weeklyity factor, and the increment of the oil price change trend factor, an oil volume prediction model is generated. The oil delivery volume of the target oil depot on the target prediction date is predicted according to the oil delivery volume prediction model; wherein, the oil delivery volume prediction model includes: in, The predicted total oil delivery volume for the target forecast date; The initial oil delivery volume forecast for the target forecast date; This refers to seasonal or weekly hair oil factors. This represents the increment of the oil price change trend factor.

2. The method according to claim 1, characterized in that, The step of performing noise reduction processing on the original hair oil data to obtain the historical hair oil data includes: The trend items in the original hair oil data are removed to obtain the hair oil data after removing the trend items. The hair oil data after removing the trend term is filtered to obtain the historical hair oil data.

3. The method according to claim 2, characterized in that, The filtering process includes: Any one of Fourier transform, moving average method, and inertial filtering.

4. An oil depot oil delivery volume prediction device applying the method described in claim 1, characterized in that, include: The first determining module is used to determine the historical oil delivery data of the target oil depot within a preset time period; The second determining module is used to determine the initial predicted value of the amount of oil applied to the target prediction date based on the historical oil application data and a preset oil application quantity and time relationship model. The third determining module is used to determine the increment of the oil price change trend factor based on the target prediction date and a preset oil price change trend model. The generation module is used to generate an oil delivery volume prediction model based on the initial oil delivery volume prediction value, the value of the preset oil delivery seasonality factor or the value of the preset oil delivery weekly factor, and the increment of the oil price change trend factor. The prediction module is used to predict the oil delivery volume of the target oil depot on the target prediction date based on the oil delivery volume prediction model.

5. A computer-readable storage medium, characterized in that, The computer program stored in the computer-readable storage medium, when executed by one or more processors, implements the method as described in any one of claims 1 to 3.

6. An electronic device, characterized in that, It includes a memory and one or more processors, wherein a computer program is stored on the memory, and the memory and the one or more processors are communicatively connected to each other. When the computer program is executed by the one or more processors, it performs the method as described in any one of claims 1 to 3.

Images