Method, device, medium and product for predicting and determining sorting plan of package pieces

Abstract

This application provides a method, equipment, medium, and product for predicting package quantity and determining sorting plan. By analyzing the time series data of package quantity at a target transfer station, the trend, seasonal, and remaining time series data are determined. For each time series data point, a prediction is made to obtain the volatility of the future time series data and the future remaining time series data within a preset time period. When this volatility is less than a preset volatility threshold, the package quantity within the preset time period is predicted based on the future time series data, resulting in the target package quantity prediction, thus achieving accurate prediction of the target package quantity. Subsequently, based on the sorting machine slot information in the target transfer station and the accurately predicted target package quantity, a sorting plan for the target transfer station is generated, effectively ensuring the sorting effect of the sorting plan.

Description

Technical Field

[0001] This application relates to the field of logistics sorting technology, specifically to a method, equipment, medium, and product for predicting package volume and determining sorting plans. Background Technology

[0002] In a logistics transit hub where sorting machines perform sorting operations, the sorting plan determines the mapping relationship between package tags and the sorting machine slots. Package tags are information markers attached or affixed by courier companies to designated locations on the main packaging of parcels for dispatching and internal operations. The sorting machine slots are used to sort packaged parcels, i.e., parcels with attached or affixed package tags.

[0003] Because the quantity of packaged items affects the sorting mode and the number of assigned slots during the generation and optimization of sorting plans, the accuracy of predicting the quantity of packaged items directly impacts the effectiveness of sorting plan generation or optimization. Sorting modes can be dynamic, static, or a combination of dynamic and static sorting. Generally, in dynamic sorting, the mapping between packaged items and slots is not fixed, and it's used for sorting small quantities of packaged items. In static sorting, the mapping is fixed, and it's used for sorting large quantities of packaged items. The combination of dynamic and static sorting modes combines both.

[0004] In existing technologies, a simple average calculation method based on the number of packaged items over multiple days is usually adopted to predict the number of packaged items. However, due to the limitations of human experience and calculation methods, the accuracy of the prediction is poor, and the sorting effect of the sorting plan generated or optimized based on the predicted number of packaged items is poor. Summary of the Invention

[0005] Based on the aforementioned deficiencies and shortcomings of the existing technology, this application proposes a method, equipment, medium, and product for predicting package quantity and determining sorting plan. This method can accurately predict the package quantity within a preset time period based on future trend time series data, future seasonal time series data, and future residual time series data with volatility less than a preset volatility threshold. Furthermore, based on this package quantity and the sorting machine slot information in the transfer area, a sorting plan is generated to ensure the sorting effectiveness of the plan.

[0006] According to a first aspect of the embodiments of this application, a method for predicting package quantity is provided, including:

[0007] Obtain time-series data of packaged goods volume at the target transit hub, wherein the time-series data includes a series of packaged goods volumes at the target transit hub arranged in chronological order;

[0008] Analyze the time series data of the packaged item quantity to determine the trend time series data, seasonal time series data, and remaining time series data in the time series data of the packaged item quantity.

[0009] For the time series data of the trend item, the time series data of the seasonal item, and the time series data of the remaining item, predictions are made respectively to obtain the volatility of the future time series data of the trend item, the future time series data of the seasonal item, the future time series data of the remaining item, and the future time series data of the remaining item within a preset time period;

[0010] When the volatility is less than a preset volatility threshold, the quantity of packaged items within the preset time period is predicted based on the future trend time series data, the future seasonal time series data, and the future residual time series data, to obtain the target packaged item prediction quantity.

[0011] According to a second aspect of the embodiments of this application, a sorting plan determination method is provided, comprising:

[0012] Determine the target package quantity prediction within a preset time period, wherein the target package quantity prediction is obtained by predicting the package quantity prediction method as described in any embodiment of the first aspect;

[0013] Based on the sorting machine slot information in the target transit area and the predicted quantity of the target package, a sorting plan for the target transit area is determined.

[0014] According to a third aspect of the embodiments of this application, a package quantity prediction device is provided, comprising:

[0015] The acquisition module is used to acquire time-series data of the number of packages in the target transit hub, wherein the time-series data includes a series of packages in the target transit hub arranged in chronological order;

[0016] The determination module is used to analyze the time series data of the packaged item quantity and determine the trend item time series data, seasonal item time series data and remaining item time series data in the time series data of the packaged item quantity.

[0017] The first prediction module is used to predict the trend term time series data, the seasonal term time series data, and the remaining term time series data respectively, and obtain the volatility of the future trend term time series data, the future seasonal term time series data, the future remaining term time series data, and the future remaining term time series data within a preset time period.

[0018] The second prediction module is used to predict the number of packaged items within the preset time period based on the future trend time series data, the future seasonal time series data, and the future residual time series data when the volatility is less than a preset volatility threshold, so as to obtain the target packaged item prediction quantity.

[0019] According to a fourth aspect of the embodiments of this application, a sorting plan determination apparatus is provided, comprising:

[0020] The first determining module is used to determine the target package item prediction quantity within a preset time period, wherein the target package item prediction quantity is predicted according to the package item quantity prediction method described in any embodiment of the first aspect;

[0021] The second determining module is used to determine the sorting plan of the target transfer center based on the sorting machine's grid information and the predicted quantity of the target package.

[0022] According to a fifth aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor;

[0023] The memory is connected to the processor and is used to store programs;

[0024] The processor is used to implement the package quantity prediction method as described in the first aspect or the sorting plan determination method as described in the second aspect by running a program in the memory.

[0025] According to a sixth aspect of the embodiments of this application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, it implements the package quantity prediction method as described in the first aspect or the sorting plan determination method as described in the second aspect.

[0026] According to a seventh aspect of the embodiments of this application, a computer program product is provided, including a computer program / instructions, which, when executed by a processor, implement the package quantity prediction method as described in the first aspect or the sorting plan determination method as described in the second aspect.

[0027] In the aforementioned methods, equipment, media, and products for predicting package quantity and determining sorting plans, the time series data of package quantity at the target transfer center can be analyzed to extract the trend, seasonal, and remaining time series data. For these time series data, the volatility of future trend, seasonal, and remaining time series data within a preset time period is predicted. When the volatility is less than a preset volatility threshold, the package quantity within the preset time period is predicted based on these data, yielding the target package quantity prediction, thus achieving accurate prediction of the target package quantity. Subsequently, based on the sorting machine's grid information and the target package quantity prediction, a sorting plan suitable for the target transfer center is generated, effectively ensuring the sorting effect of the sorting plan. Attached Figure Description

[0028] 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.

[0029] Figure 1 This is a flowchart illustrating a method for predicting the quantity of packaged goods according to an embodiment of this application.

[0030] Figure 2 This is a schematic diagram of a sorting plan determination method provided in an embodiment of this application;

[0031] Figure 3 This is a schematic diagram of the structure of a package quantity prediction device proposed in an embodiment of this application;

[0032] Figure 4 This is a schematic diagram of the structure of a sorting plan determination device according to an embodiment of this application;

[0033] Figure 5 This is a schematic diagram of the structure of an electronic device proposed in an embodiment of this application. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0035] As described in the background section, during the generation and optimization of sorting plans for logistics transit hubs, the number of packaged items affects the sorting pattern and the number of allocated slots. Therefore, the accuracy of predicting the number of packaged items (i.e., the quantity of packaged items) directly impacts the effectiveness of generating or optimizing the sorting plan. In existing technologies, a simple averaging method based on multiple days' packaged item quantities, relying on human experience, is used to predict the number of packaged items. However, due to limitations in human experience and calculation methods, the accuracy of predictions is poor, resulting in poor sorting performance for sorting plans generated or optimized based on the predicted packaged item quantities.

[0036] In this embodiment, by analyzing the time series data of the packaged item volume of the target transfer center, trend time series data, seasonal time series data, and remaining time series data are extracted from the time series data. For the trend time series data, seasonal time series data, and remaining time series data, the volatility of the future trend time series data, future seasonal time series data, future remaining time series data, and future remaining time series data within a preset time period are predicted respectively. When the volatility is less than a preset volatility threshold, the packaged item volume within the preset time period is predicted based on the future trend time series data, future seasonal time series data, and future remaining time series data to obtain the target packaged item predicted volume, thus achieving accurate prediction of the target packaged item predicted volume. Subsequently, based on the sorting machine slot information in the target transfer center and the target packaged item predicted volume, a sorting plan suitable for the target transfer center is generated, thereby effectively ensuring the sorting effect of the sorting plan.

[0037] Based on the above concept, this specification provides a method for predicting package quantity and determining sorting plan in the embodiments of this specification. The method for predicting package quantity and determining sorting plan in conjunction with the accompanying drawings will be described exemplarily below.

[0038] See Figure 1 In one exemplary embodiment, a method for predicting the quantity of packaged items is provided, applicable to any electronic device, such as a control device in a logistics sorting scenario. This control device is used to control the sorting of packaged items. In the sorting plan development stage, it is necessary to first predict the quantity of packaged items at the transit point within a preset time period. For example... Figure 1 As shown, the package quantity prediction method includes steps S101-S104:

[0039] S101: Obtain time-series data of the number of packages in the target transit area.

[0040] The target transit hub refers to any logistics transit hub. The time-series data of the packaged shipment volume of the target transit hub includes a series of packaged shipment volumes of the target transit hub arranged in chronological order, used to describe the changes in the packaged shipment volume of the target transit hub over time.

[0041] For example, the time series data of the packaged goods volume of the target transit point is the packaged goods volume data of transit point a in a certain month, including the packaged goods volume of transit point a for each day in a certain month.

[0042] The termination time of the time series data for package quantity is either the time when the time series data was acquired, or any time before the time when the time series data was acquired.

[0043] S102: Analyze the time series data of packaged item volume to determine the trend, seasonal, and residual time series data within the packaged item volume time series data.

[0044] The value of each moment in the time series data of package quantity can be decomposed into three parts: trend part, seasonal part, and residual part.

[0045] The seasonal term in the time series data of packaged item volume refers to the periodic fluctuations related to seasonal factors, including the trend of the value at each moment in the time series data. The trend term in the time series data of packaged item volume refers to the long-term upward or downward changes, including the seasonality of the value at each moment in the time series data. The residual term, also known as the random term, is the data remaining after removing the trend and seasonal terms from the time series data of packaged item volume. It includes the residual of the value at each moment in the time series data. The residual typically contains random fluctuations and noise.

[0046] The time series data of packaged goods volume in the target transit area is decomposed to extract the trend term time series data and the seasonal term time series data. The remaining part of the time series data excluding the trend term time series data and the seasonal term time series data is taken as the residual term time series data.

[0047] Specifically, the trend term time series data of time series data can be extracted using methods such as moving average, exponential smoothing, regression analysis, or seasonal trend decomposition using Loess (STL). The trend term time series data of time series data can also be extracted using seasonal decomposition or STL. The remaining term time series data of time series data can be extracted by subtracting the extracted trend term time series data and seasonal term time series data from the time series data.

[0048] For example, when decomposing the time series data of package quantity using the STL method to extract trend and seasonal time series data, the STL decomposition is performed iteratively multiple times until the estimates of the trend and seasonal components at each time point converge, i.e., stable estimates of the trend and seasonal components at each time point are obtained, or the specified number of iterations is reached, at which point the iteration stops. Then, the estimates of the trend components at each time point after the last iteration are used as the trend time series data, the estimates of the seasonal components at each time point after the last iteration are used as the seasonal time series data, and the estimates of the residual components at each time point after the last iteration are used as the residual time series data.

[0049] Specifically, performing STL decomposition on the time series data of package quantity can be achieved by inputting the time series data of package quantity into the STL decomposition equation.

[0050] When performing STL decomposition multiple times, repeat the following operations:

[0051] First, initial estimates of the trend and seasonal components at each time point are determined. These initial estimates of the trend component are subtracted from the time series data of packaged goods volume to obtain detrended series data. The data at each seasonal cycle position in the detrended series data are then smoothed, and the average value of the data at each seasonal cycle position is estimated using locally weighted regression (Loess) to obtain the estimate of the seasonal component at each time point. Next, the estimated trend component at each time point is subtracted from the time series data of packaged goods volume to obtain detrended series data. This detrended series data is then smoothed using Loess to obtain the estimate of the trend component at each time point. Finally, the estimates of the trend component at each time point and the estimated trend component at each time point are subtracted from the time series data of packaged goods volume to obtain the estimate of the residual component at each time point.

[0052] It should be noted that the above STL decomposition equation is obtained by adjusting the preset STL decomposition equation based on historical time series data of package quantity. The adjustments to the preset STL decomposition equation include, but are not limited to, adjustments to the parameter values ​​in the equation and adjustments to the algorithm.

[0053] S103: For the trend term time series data, seasonal term time series data, and residual term time series data respectively, predict the volatility of the future trend term time series data, future seasonal term time series data, future residual term time series data, and future residual term time series data within a preset time period.

[0054] The start time of the preset time period is the moment when the three time series data (i.e., trend, seasonal and residual) are predicted, or any moment after the moment when the three time series data are predicted. The length of the preset time period from the start time to the end time can be determined based on actual needs.

[0055] For trend-related time series data, predict future trend-related time series data within a preset time period; for seasonal time series data, predict future seasonal time series data within a preset time period; for residual time series data, predict future residual time series data within a preset time period and determine the volatility of the future residual time series data.

[0056] Specifically, corresponding prediction models can be established based on trend item time series data, seasonal item time series data, and remaining item time series data. By inputting the time series data of each item in the package quantity time series data into the corresponding prediction model, future period time series data, future period time series data, and future period remaining item time series data within the preset time period can be obtained.

[0057] In addition, the volatility of future period residual time series data is used to characterize the accuracy / confidence level of the future period residual time series data. Generally, the higher the volatility of future period residual time series data, the lower the accuracy / confidence level of the future period residual time series data.

[0058] Understandably, after multi-angle sequence data extraction in step S102, the time series data of packaged item quantity is decomposed into trend item time series data, seasonal item time series data, and remaining item time series data. When predicting the packaged item quantity for a preset time period, it is necessary to first analyze the future trend item time series data, future seasonal item time series data, and future remaining item time series data within the preset time period, and then predict the packaged item quantity within the preset time period based on the future time series data, so as to obtain an accurate target packaged item prediction quantity, thereby providing a basis for determining the effective sorting plan for packaged items.

[0059] S104: When the volatility is less than the preset volatility threshold, the number of packaged items within the preset time period is predicted based on the future trend term time series data, the future seasonal term time series data and the future residual term time series data, so as to obtain the target packaged item prediction quantity.

[0060] The preset fluctuation threshold can be determined based on actual working conditions or it can be a fixed value.

[0061] When the volatility is less than the preset volatility threshold, it indicates that the volatility of the future period residual time series data is low and the stability and reliability are high. At this time, based on the future period residual time series data, combined with the future period trend time series data and the future period seasonal time series data, the quantity of packaged items within the preset time period can be predicted to obtain the accurate target quantity of packaged items.

[0062] Correspondingly, when the volatility is greater than or equal to the preset volatility threshold, it indicates that the volatility of the future period residual time series data is high and the stability and reliability are low. At this time, when predicting the number of packages within the preset time period based on the future period residual time series data, combined with the future period trend time series data and the future period seasonal time series data, it may be necessary to redetermine the trend time series data, seasonal time series data and residual time series data because the future period residual time series data may be inaccurate or have no reference value. If the volatility of the predicted future period residual time series data is less than the preset volatility threshold, the number of packages within the preset time period should be predicted again, that is, the above steps S102-S104 should be repeated.

[0063] In this embodiment, by analyzing the time series data of the packaged goods volume of the target transit point, the trend time series data, seasonal time series data, and remaining time series data of the time series data are extracted. For each time series data, prediction is made to obtain the volatility of each time series data and the future remaining time series data within a preset time period. When the volatility is less than a preset volatility threshold, the packaged goods volume within the preset time period is predicted based on the future trend time series data, the future seasonal time series data, and the future remaining time series data, to obtain the target packaged goods predicted volume.

[0064] In this way, the time series data of packaged item volume is divided into multiple dimensions of time series data. Accurate predictions are made for each dimension of packaged item volume from different perspectives. When the volatility of the future period residual time series data is less than the preset volatility threshold, that is, when the future period residual time series data is relatively stable and reliable, the packaged item volume within the preset time period is predicted by combining the accurately predicted time series data of each dimension. This yields an accurate and reliable target packaged item prediction volume, providing a basis for determining a sorting plan with better sorting effect.

[0065] In some embodiments, the target package quantity can be determined by reverse reasoning based on the extraction of trend term time series data, seasonal term time series data and residual term time series data, combined with future trend term time series data, future seasonal term time series data and future residual term time series data.

[0066] Specifically, the time series data of the packaged goods volume at the target transshipment hub is analyzed. When extracting the trend, seasonal, and remaining time series data, an STL filtering equation is used to decompose the time series data of the packaged goods volume at the target transshipment hub, yielding the trend, seasonal, and remaining time series data. Correspondingly, based on the future trend, seasonal, and remaining time series data, the packaged goods volume within a preset time period is predicted. To obtain the target packaged goods prediction volume, the future trend, seasonal, and remaining time series data are input into the STL filtering equation for reverse inference, resulting in the target packaged goods prediction volume.

[0067] The STL filtering equation is the specific mathematical equation used to implement STL.

[0068] Before decomposing the time series data of packaged goods volume in the target transit site using the STL filtering equation to obtain the trend term time series data, seasonal term time series data, and remaining term time series data, the parameters of the STL filtering equation are first set based on the characteristics of the packaged goods volume time series data. These parameters include, but are not limited to, the length of the smoother for the seasonal term time series data and the length of the smoother for the trend term time series data. This yields the STL filtering equation used to extract the trend term time series data, seasonal term time series data, and remaining term time series data from the packaged goods volume time series data.

[0069] In this way, based on the STL filtering equation, the trend term time series data, seasonal term time series data, and residual term time series data in the time series data of packaged item quantity can be accurately extracted. And when performing reverse reasoning based on the future trend term time series data, future seasonal term time series data, and future residual term time series data to predict the packaged item quantity, the accurate prediction of the packaged item quantity can be achieved.

[0070] Alternatively, based on the characteristics of the time-series data of packaged goods volume at different logistics transit points, the parameters of the STL filter equation can be set separately to obtain the STL filter equations for the time-series data of packaged goods volume at different logistics transit points. This allows for accurate decomposition of the time-series data of packaged goods volume at each logistics transit point and accurate prediction of the packaged goods volume at different logistics transit points.

[0071] In this embodiment, the time series data of the packaged items volume of the target transit point is decomposed using the STL equation to obtain the trend term time series data, seasonal term time series data, and remaining term time series data. Based on the future trend term time series data, future seasonal term time series data, and future remaining term time series data, the packaged items volume within a preset time period is predicted to obtain the target packaged items predicted volume. When the future trend term time series data, future seasonal term time series data, and future remaining term time series data are input into the STL equation for reverse reasoning, the target packaged items predicted volume is obtained. Thus, through reverse reasoning using the extraction method of trend term time series data, seasonal term time series data, and remaining term time series data, the accurate target packaged items predicted volume is obtained.

[0072] In some embodiments, when predicting the volatility of future trend time series data, future seasonal time series data, future residual time series data, and future residual time series data within a preset time period for trend time series data, seasonal time series data, and residual time series data, the future trend time series data and future seasonal time series data are predicted based on the changing patterns of the trend time series data and seasonal time series data, and the mean process and volatility process of the residual time series data are fitted to predict the future residual time series data and volatility.

[0073] Specifically, based on the changing patterns of trend time series data, future trend time series data within a preset time period are predicted; based on the changing patterns of seasonal time series data, future seasonal time series data within a preset time period are predicted.

[0074] Alternatively, trend time series data can be input into, for example, a SARIMA model to obtain future trend time series data within a preset time period; seasonal time series data can be input into, for example, an ARIMA model to obtain future seasonal time series data within a preset time period.

[0075] Specifically, by fitting the mean and volatility processes of the residual term time series data using the ARIMA-EGARCH model, the future residual term time series data and volatility are obtained. Thus, by fitting the ARIMA-EGARCH model, the future residual term time series data can be predicted and its volatility determined using the residual term time series data.

[0076] In this embodiment, based on the changing patterns of trend term time series data and seasonal term time series data, future trend term time series data and future seasonal term time series data are predicted respectively. The mean and volatility processes of the remaining term time series data are fitted using the ARIMA-EGARCH model to predict future remaining term time series data and volatility. This achieves separate predictions of future trend term time series data, future seasonal term time series data, and future remaining term time series data within a preset time period, ensuring prediction accuracy. Simultaneously, the volatility of the future remaining term time series data is determined, facilitating the assessment of the reliability of the future remaining term time series data. This allows for accurate prediction of package quantity when the future remaining term time series data is reliable.

[0077] In some embodiments, before fitting the mean and volatility processes of the residual term time series data using the ARIMA-EGARCH model to obtain the future residual term time series data and volatility, it is necessary to first determine the corresponding ARIMA-EGARCH model based on the data characteristics of the residual term time series data.

[0078] Based on the data characteristics of the remaining time series data, the parameters of the ARIMA model and the EGARCH model are adjusted to obtain the target ARIMA model and the target EGARCH model. Then, the target ARIMA model and the target EGARCH model are combined to obtain the required ARIMA-EGARCH model.

[0079] Thus, by adjusting the parameters of the ARIMA and EGARCH models according to the data characteristics of the residual term time series data, a target ARIMA model suitable for predicting residual term time series data and a target EGARCH model for determining volatility can be obtained. Combining the target ARIMA model and the target EGARCH model, the required ARIMA-EGARCH model that can determine the residual term time series data and corresponding volatility in the future can be obtained. Therefore, the ARIMA-EGARCH model can be used to accurately predict the residual term time series data and corresponding volatility in the future.

[0080] For example, the process of predicting the number of packaged items at a certain logistics transit point can be carried out through the following steps:

[0081] Step 1: For a specific transit point, obtain the historical volume data of packaged items for that transit point, that is, the time series data of the volume of packaged items for that transit point.

[0082] Step 2: Perform STL filtering on the time series data of packaged items to extract the trend time series data, seasonal time series data, and remaining time series data of the time series data;

[0083] Step 3: Adapt the ARIMA-EGARCH model to the residual term time series data. This involves adjusting the parameters of the ARIMA-EGARCH model based on the residual term time series data to make it suitable for processing the residual term time series data. Then, the ARIMA-EGARCH model is used to simulate the mean-volatility process of the residual term time series data. In this way, the lagged residual term time series data, i.e., the residual term time series data extracted in Step 2, can be used to predict the future residual term time series data and volatility.

[0084] Step 4: Using the time series data of the future period remaining items predicted in Step 3, substitute it into the equation for STL filtering in Step 2, i.e., the above STL filtering equation, to obtain the effective prediction of future data using historical data, i.e., the above target package item prediction quantity.

[0085] Among them, the volatility of the future residual term time series data reflects the accuracy of the predicted future residual term time series data, and confidence intervals can be further obtained based on the volatility of the future residual term time series data, which serves as the basis for testing the prediction accuracy of the residual term time series data and the model for predicting the future data of the residual term time series data.

[0086] See Figure 2 In one exemplary embodiment, a sorting plan determination method is provided, applicable to any electronic device. For example... Figure 2 As shown, the sorting plan determination method includes steps S201-S202:

[0087] S201: Determine the predicted quantity of target package items within a preset time period.

[0088] The target package quantity prediction is obtained by predicting according to any embodiment of the package quantity prediction method described above.

[0089] For details on the specific implementation of predicting the target package item prediction quantity, please refer to the above content, which will not be repeated here.

[0090] Of course, based on actual working conditions, before executing the sorting plan determination method, the predicted quantity of the target package obtained by the above package quantity prediction method can be received and determined, and the predicted quantity of the target package can be stored in the local device.

[0091] S202: Based on the sorting machine slot information and the predicted quantity of target packages in the target transfer area, determine the sorting plan for the target transfer area.

[0092] The grid information includes grid identifier, number of grids, and grid flow direction.

[0093] Based on the sorting machine slot information and the predicted quantity of target package tags within the target transfer area, the predicted quantity of package tags is allocated to the slots of each sorting machine for sorting. A mapping relationship is established between package tags and slots, resulting in the sorting plan for the target transfer area. Specifically, each package tag is sorted through a slot with which it has a mapping relationship, or in other words, each slot is used to sort package tags with which it has a mapping relationship.

[0094] Specifically, based on the sorting machine's grid information in the target transfer area and the predicted quantity of target package items, the allocation mode and the grids to be allocated are determined. Then, according to the allocation mode, the package items with the predicted quantity of target package items are allocated to the grids to be allocated, thus obtaining the sorting plan.

[0095] The allocation modes include dynamic sorting, static sorting, or direct / mixed sorting.

[0096] After allocating the predicted number of target package packages to the slots to be assigned, a mapping relationship can be established between the predicted number of target package packages and the slots to be assigned.

[0097] Specifically, for the predicted number of target package items at each moment within the preset time period, the package items of the predicted number of target package items are allocated to the corresponding slots to be allocated in the manner described above.

[0098] In this embodiment, after obtaining the number of packaged items in the target transfer center within a preset time period according to the above-mentioned packaged item quantity prediction method, a sorting plan suitable for the sorting needs of the target transfer center within the preset time period is generated based on the sorting machine slot information and the predicted number of packaged items in the target transfer center, so as to ensure the sorting effect of the sorting plan.

[0099] Understandably, the aforementioned method for predicting package quantity can serve as a crucial component of sorting machine planning optimization. By deepening information mining, it extracts trend, seasonal, and remaining time-series data of package quantity, and combines this with the volatility of future remaining time-series data. When the volatility exceeds a preset threshold, it predicts the package quantity within a preset time period based on future trend, seasonal, and remaining time-series data. This allows for a complete prediction of future package quantity, improving prediction accuracy and precision. Subsequently, based on the target package quantity predicted using this method, and combined with grid information, the accuracy of sorting mode selection and grid allocation decisions can be effectively improved. This enhances sorting efficiency, reduces manual handling, ensures timeliness, and lowers personnel and equipment costs.

[0100] like Figure 3 As shown in the figure, this application embodiment also provides a package quantity prediction device, including an acquisition module 301, a determination module 302, a first prediction module 303 and a second prediction module 304.

[0101] in,

[0102] The acquisition module 301 is used to acquire time series data of the number of packages in the target transit yard, wherein the time series data includes a series of packages in the target transit yard arranged in chronological order;

[0103] The determination module 302 is used to analyze the time series data of the package quantity of the target transit point and determine the trend time series data, seasonal time series data and remaining time series data of the time series data;

[0104] The first prediction module 303 is used to predict the trend item time series data, the seasonal item time series data and the remaining item time series data respectively, and obtain the volatility of the future trend item time series data, the future seasonal item time series data, the future remaining item time series data and the future remaining item time series data within a preset time period.

[0105] The second prediction module 304 is used to predict the number of packaged items within the preset time period based on the future trend time series data, the future seasonal time series data and the future residual time series data when the volatility is less than a preset volatility threshold, so as to obtain the target packaged item prediction quantity.

[0106] The package quantity prediction device provided in this embodiment belongs to the same application concept as the package quantity prediction method provided in the above embodiments of this application. It can execute the method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the package quantity prediction method provided in the above embodiments of this application, and will not be repeated here.

[0107] The functions implemented by the acquisition module 301, determination module 302, first prediction module 303 and second prediction module 304 can be implemented by the same or different processors calling software, and this application embodiment does not limit this.

[0108] like Figure 4 As shown in the figure, this application embodiment also provides a sorting plan determination device, including a first determination module 401 and a second determination module 402.

[0109] in,

[0110] The first determining module 401 is used to determine the target package item prediction quantity within a preset time period. The target package item prediction quantity is obtained by predicting the package item quantity according to the above-mentioned package item quantity prediction method.

[0111] The second determining module 402 is used to determine the sorting plan of the target transfer center based on the sorting machine's grid information and the predicted quantity of the target package.

[0112] The sorting plan determination device provided in this embodiment belongs to the same concept as the sorting plan determination method provided in the above embodiments of this application. It can execute the method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the sorting plan determination method provided in the above embodiments of this application, and will not be repeated here.

[0113] The functions implemented by the first determining module 401 and the second determining module 402 described above can be implemented by the same or different processors calling software, and this application embodiment does not limit this.

[0114] Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 5 As shown, the electronic device includes a memory 500 and a processor 510.

[0115] The memory 500 is connected to the processor 510 and is used to store programs;

[0116] The processor 510 is used to implement the package quantity prediction method or sorting plan determination method disclosed in any of the above embodiments by running the program stored in the memory 500.

[0117] Specifically, the electronic device may also include: a bus, a communication interface 520, an input device 530, and an output device 540.

[0118] The processor 510, memory 500, communication interface 520, input device 530, and output device 540 are interconnected via a bus. Among them:

[0119] A bus can include a pathway for transmitting information between various components of a computer system.

[0120] The processor 510 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0121] The processor 510 may include a main processor, as well as a baseband chip, modem, etc.

[0122] The memory 500 stores a program for executing the technical solution of this application, and may also store an operating system and other critical business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 500 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0123] Input device 530 may include a device for receiving data and information input by a user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0124] Output device 540 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0125] The communication interface 520 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0126] The processor 510 executes the program stored in the memory 500 and calls other devices, and can be used to implement any of the steps of the package quantity prediction method or sorting plan determination method provided in the above embodiments of this application.

[0127] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0128] This application also proposes a chip, which includes a processor and a data interface. The processor reads and runs a program stored in a memory through the data interface to execute the package quantity prediction method or sorting plan determination method described in any of the above embodiments. For the specific processing procedure and its beneficial effects, please refer to the embodiments of the package quantity prediction method or sorting plan determination method described above.

[0129] In addition to the methods and apparatus described above, embodiments of this application provide a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the package quantity prediction method or sorting plan determination method according to various embodiments of this application as described in the "Exemplary Methods" section of this specification.

[0130] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0131] Furthermore, embodiments of this application also propose a storage medium storing a computer program, which is executed by a processor in the steps of the package quantity prediction method or sorting plan determination method according to various embodiments of this application as described in the "Exemplary Methods" section above.

[0132] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0133] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0134] It should also be noted that in the apparatus, device, and method of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of the present invention.

[0135] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0136] It should be understood that the qualifying terms "first", "second", "third", "fourth", "fifth" and "sixth" used in the description of the embodiments of the present invention are only used to more clearly illustrate the technical solutions and are not intended to limit the scope of protection of the present invention.

[0137] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for predicting the quantity of packaged goods, characterized in that, The method includes: Obtain time-series data of packaged goods volume at the target transit hub, wherein the time-series data includes a series of packaged goods volumes at the target transit hub arranged in chronological order; Analyze the time series data of the packaged item quantity to determine the trend time series data, seasonal time series data, and remaining time series data in the time series data of the packaged item quantity. For the time series data of the trend item, the time series data of the seasonal item, and the time series data of the remaining item, predictions are made respectively to obtain the volatility of the future time series data of the trend item, the future time series data of the seasonal item, the future time series data of the remaining item, and the future time series data of the remaining item within a preset time period; When the volatility is less than a preset volatility threshold, the quantity of packaged items within the preset time period is predicted based on the future trend time series data, the future seasonal time series data, and the future residual time series data, to obtain the target packaged item prediction quantity.

2. The method for predicting package quantity according to claim 1, characterized in that, The analysis of the time series data of the packaged item quantity, to determine the trend term time series data, seasonal term time series data, and remaining term time series data in the time series data of the packaged item quantity, includes: By using the STL seasonal trend decomposition filtering equation, the time series data of the package quantity of the target transit site is decomposed to obtain the trend term time series data, seasonal term time series data and residual term time series data of the time series data. The method of predicting the number of packaged items within the preset time period based on the future trend time series data, the future seasonal time series data, and the future residual time series data to obtain the target packaged item prediction quantity includes: The future trend time series data, the future seasonal time series data, and the future residual time series data are input into the STL filtering equation for reverse inference to obtain the target package item prediction quantity.

3. The method for predicting package quantity according to claim 1 or 2, characterized in that, The step of predicting the trend term time series data, the seasonal term time series data, and the residual term time series data respectively to obtain the volatility of the future trend term time series data, the future seasonal term time series data, the future residual term time series data, and the future residual term time series data within a preset time period includes: Based on the changing patterns of the trend term time series data and the seasonal term time series data, predict the future trend term time series data and the future seasonal term time series data respectively; The mean and volatility processes of the remaining term time series data are fitted to predict the future remaining term time series data and the volatility.

4. The method for predicting package quantity according to claim 3, characterized in that, The process of fitting the mean and volatility of the remaining term time series data to predict the future remaining term time series data and volatility includes: By fitting the mean and volatility processes of the remaining term time series data using the ARIMA-EGARCH model, the future period remaining term time series data and the volatility are obtained.

5. The method for predicting package quantity according to claim 4, characterized in that, The method further includes: Based on the data characteristics of the remaining time series data, the parameters of the ARIMA model and the EGARCH model are adjusted to obtain the target ARIMA model and the target EGARCH model. The target ARIMA model is combined with the target EGARCH model to obtain the ARIMA-EGARCH model.

6. A method for determining a sorting plan, characterized in that, The method includes: Determine the target package quantity prediction within a preset time period, wherein the target package quantity prediction is obtained by predicting the package quantity prediction method as described in any one of claims 1 to 5; Based on the sorting machine slot information in the target transit area and the predicted quantity of the target package, a sorting plan for the target transit area is determined.

7. The sorting plan determination method according to claim 6, characterized in that, The process of determining the sorting plan for the target transit area based on the sorting machine's compartment information and the predicted quantity of target packages includes: Based on the grid information and the predicted quantity of the target package, the allocation mode and the grid to be allocated are determined. The allocation mode is dynamic sorting mode, static sorting mode, or direct and mixed sorting mode. According to the allocation mode, the predicted number of package tags for the target package are allocated to the slots to be allocated, thus obtaining the sorting plan.

8. An electronic device, characterized in that, Including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the package quantity prediction method as described in any one of claims 1 to 5 or the sorting plan determination method as described in any one of claims 6 or 7 by running the program in the memory.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the package quantity prediction method as described in any one of claims 1 to 5 or the sorting plan determination method as described in any one of claims 6 or 7.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed, performs the package quantity prediction method as described in any one of claims 1 to 5 or the sorting plan determination method as described in any one of claims 6 or 7.

Images