Freight loading method, system, equipment and medium

Abstract

The invention provides a method, a system, an electronic device and a non-transitory storage medium for carrying out freight loading. The method comprises the steps that a historical time period is determined, the historical time period can reflect the periodical rule of historical loading data corresponding to the current time period, and the historical time period comprises two or more historical periodical time periods corresponding to the current time period; predicting a current freight demand mode in a current time period based on the historical loading data of the historical time period; and carrying out freight loading at least based on the current freight demand mode. According to the scheme provided by the invention, the current freight demand mode in the current time period is predicted based on the determined historical loading data of the long time period capable of reflecting the periodic rule, so that the method is different from a traditional product which mainly emphasizes short-term execution and operation plans in the market; this new solution greatly extends the time range of the loading plan and makes the loading plan predictable or meaningful to predict. The time range of the extended loading plan based on the periodic law can ensure that the freight loading plan is not only efficient, but also remains consistent over a longer time range.

Description

Technical Field

[0001] The present application relates to the field of cargo transportation, and more specifically to methods, systems, electronic devices, and non-transitory storage media for cargo loading. Background Art

[0002] Load planning systems for trucks and trailers play a vital role in optimizing cargo transportation, ensuring efficient space utilization, and minimizing logistics operating costs. Traditional load planning systems typically focus on short-term execution and operational planning, often solving immediate shipping needs, such as how to place cargo packages to maximize the use of the container space of a truck or trailer to achieve the best fill rate. Summary of the invention

[0003] According to one aspect of the present application, there is provided a method for freight loading, comprising: determining a historical time period, the historical time period being able to reflect the periodicity of historical loading data corresponding to a current time period, the historical time period comprising two or more historical periodic time periods corresponding to the current time period;

[0004] A current freight demand pattern in a current period is predicted based on the historical loading data of the historical time period; and freight loading is performed based at least on the current freight demand pattern.

[0005] According to one aspect of the present application, a system for freight loading is provided, comprising: a determination device, configured to determine a historical time period, wherein the historical time period can reflect the periodicity of historical loading data corresponding to a current time period, wherein the historical time period includes two or more historical periodic time periods corresponding to the current time period; a prediction device, configured to predict a current freight demand pattern in the current time period based on the historical loading data of the historical time period; and a loading device, configured to perform freight loading based at least on the current freight demand pattern.

[0006] According to another aspect of the present application, an electronic device is provided, including: a memory for storing instructions; a processor for reading the instructions in the memory and executing a method according to an embodiment of the present application.

[0007] According to another aspect of the present application, a non-transitory storage medium is provided, on which instructions are stored, wherein when the instructions are read by a processor, the processor executes a method according to an embodiment of the present application.

[0008] Since the solution according to the present application predicts the current freight demand pattern in the current period based on historical loading data of a longer time period that can reflect periodic laws, unlike traditional products on the market that mainly emphasize short-term execution and operation plans, this new solution greatly extends the time range of loading plans and makes loading plans predictable or meaningfully predictable. This extended time range of loading plans based on periodic laws can ensure that freight loading plans are not only efficient, but also consistent over a longer time frame. The solution according to the present application uses the power of historical demand and shipping data to make wise loading plan decisions. By analyzing these data, the solution can identify trends, changes and patterns in freight demand based on historical loading data with periodic laws, predict the current freight demand pattern in the current period, and thus provide valuable insights for optimizing loading allocation. And because the solution uses historical loading data for a longer period of time, it also ensures the consistency of long-term loading plans, which is crucial to maintaining stable logistics operations and adapting to changes in demand without interruption. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 A flow chart of a method for freight loading according to an embodiment of the present application is shown.

[0011] Figure 2 A flow chart showing operational details of a system for performing freight loading according to an embodiment of the present application.

[0012] Figure 3 A schematic diagram of a single package loading algorithm according to an embodiment of the present application is shown.

[0013] Figure 4 An example of a mixed package loading algorithm for multiple types of packages according to an embodiment of the present application is shown.

[0014] Figure 5 A schematic diagram of two algorithms, namely, stacking priority optimization and ground space priority optimization, of a loading fill rate optimization algorithm according to an embodiment of the present application is shown.

[0015] Figure 6 A block diagram of a system for performing freight loading according to an embodiment of the present application is shown.

[0016] Figure 7A block diagram of an exemplary electronic device suitable for implementing embodiments of the present application is shown.

[0017] Figure 8 A schematic diagram of a non-transitory computer-readable storage medium according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] Reference will now be made in detail to specific embodiments of the present application, examples of which are illustrated in the accompanying drawings. Although the present application will be described in conjunction with specific embodiments, it will be understood that it is not intended to limit the present application to the described embodiments. On the contrary, it is intended to cover changes, modifications and equivalents included in the spirit and scope of the present application as defined by the appended claims. It should be noted that the method steps described herein can all be implemented by any functional block or functional arrangement, and any functional block or functional arrangement can be implemented as a physical entity or a logical entity, or a combination of the two.

[0019] As used herein, the article "a" is intended to have its ordinary meaning in the patent art, i.e., "one or more". For example, "a multi-beam element" means one or more multi-beam elements, and thus, "multi-beam element" here means "multi-beam element (or multiple)". Similarly, any reference to "top", "bottom", "above", "below", "upper", "lower", "front", "back", "first", "second", "left" or "right" here is not intended to be limiting. Here, the term "about", when applied to a value, generally means within the tolerance range of the device used to generate the value, or can mean plus or minus 10%, or plus or minus 5%, or plus or minus 1%, unless otherwise expressly specified. In addition, as used herein, the term "substantially" means most, or almost all, or all, or an amount in the range of about 51% to about 100%. Moreover, the examples here are intended to be illustrative only and are presented for the purpose of discussion, not as a limitation.

[0020] The problem of long-term strategic load planning in a truck and trailer environment has been around for quite some time, and researchers, practitioners, and software developers have made various attempts to address this challenge. While the specific focus on long-term planning horizons and historical data analysis may not have been as prevalent in the past, efforts to optimize load planning and transportation logistics are decades old. The following is a brief overview of the state of the art on how others have attempted to solve similar problems.

[0021] 1. Early Optimization Techniques: Even in the pre-digital era, logistics professionals recognized the importance of optimizing load plans. Manual methods, such as paper-and-pencil calculations and heuristic algorithms, were used to ensure efficient space utilization in trucks and trailers.

[0022] 2. Simple Algorithm Introduction: As computers became more and more popular, basic algorithms were developed to help with load planning. These algorithms are designed to optimally distribute cargo within a vehicle while taking into account weight limits, dimensions, and constraints.

[0023] 3. Route and load optimization software: The advent of computer software has led to the development of load optimization tools that take into account route planning and load allocation. These systems are designed to reduce transportation costs by optimizing load locations and transportation routes.

[0024] 4. Real-time execution systems: Recent solutions focus on real-time execution, providing instant load optimization suggestions based on real-time data such as current shipments, orders, and vehicle locations. These solutions meet the need for instant adjustments.

[0025] 5. Integrated logistics software: Some logistics software platforms offer integrated solutions that combine load planning with other aspects of supply chain management, aiming to provide end-to-end optimization.

[0026] 6. Machine Learning and Artificial Intelligence: In recent years, machine learning and artificial intelligence (AI) technologies have been applied to load planning to optimize models of load planning strategies.

[0027] The inventors have considered the following problems of the prior art:

[0028] 1. Short-term focus: Traditional load planning solutions are designed for short-term planning. However, this narrow planning horizon limits the system's ability to consider long-term trends, seasonality, and demand changes that may extend beyond this limited time frame.

[0029] 2. Emphasis on real-time data: Existing load planning solutions rely heavily on real-time or near real-time data, usually focusing on immediate shipment demand. While this approach is suitable for optimizing the execution of current shipments, it lacks the ability to leverage historical data for long-term planning improvements.

[0030] 3. Operational Execution: Known solutions focus primarily on optimizing operational execution, aiming to efficiently load trucks and trailers for upcoming shipments. These systems lack the ability to provide strategic guidance based on historical data analysis and do not take into account consistent long-term planning.

[0031] 4. Limited data coverage: Traditional systems mainly use data related to current shipments and real-time orders. This limitation hinders the ability to analyze historical demand patterns and make informed decisions beyond the near term.

[0032] 5. Immediate optimization focus: Existing load planning systems emphasize immediate load optimization and route efficiency. While this is critical for short-term execution, it does not take into account the broader perspective of optimizing load fill rates over an extended planning horizon.

[0033] In summary, there is a gap in the market for load planning systems. Although traditional load planning systems focus primarily on short-term execution and operational planning, they are significantly deficient in addressing long-term strategic planning based on historical data analysis. This gap in the market presents a challenge that the disclosed solution is intended to overcome. The disclosed solution solves an important problem in the field of truck and trailer load planning.

[0034] The novel solution of the present disclosure focuses on a longer time period planning horizon and utilizes longer time period historical data to improve the efficiency and consistency of loading planning.

[0035] Specifically, the present disclosure describes a novel loading planning solution that is differentiated from existing market products by extending the planning horizon to a longer time period, such as more than 12 weeks (a quarter). Unlike traditional systems that emphasize execution and operational aspects, the loading planning solution of the present disclosure prioritizes the execution of strategic plans based on long-duration historical data analysis.

[0036] The disclosed load planning solution utilizes historical demand and loading data spanning a longer period of time (typically more than 12 weeks). By analyzing this historical data, the solution can identify trends, patterns, and changes in demand. This analysis allows the solution to provide fill rate optimization goals, ensuring that each truck or trailer is loaded to its maximum capacity while minimizing empty space. In addition, the solution is able to generate corresponding load planning strategies that remain consistent over an extended planning horizon.

[0037] This innovative load planning approach offers significant benefits in terms of operational efficiency, resource utilisation and cost savings. By addressing the strategic dimensions of load planning and optimising fill rates over a longer period, it offers a comprehensive solution that complements and extends existing load planning systems on the market.

[0038] Figure 1 A flow chart of a method 100 for performing freight loading according to an embodiment of the present application is shown.

[0039] like Figure 1As shown, a method 100 for freight loading includes: step 110, determining a historical time period, the historical time period can reflect the periodic law of historical loading data corresponding to the current time period, and the historical time period includes more than two historical periodic time periods corresponding to the current time period; step 120, predicting the current freight demand pattern in the current time period based on the historical loading data of the historical time period; step 130, performing freight loading at least based on the current freight demand pattern.

[0040] Since the solution according to the present application predicts the current freight demand pattern in the current period based on historical loading data of a longer period of time that can reflect periodic laws, unlike traditional products on the market that mainly emphasize short-term execution and operational planning, this new solution greatly extends the time range of loading plans and makes loading plans predictable or meaningfully predictable. This extended time range of loading plans based on periodic laws can ensure that freight loading plans are not only efficient, but also consistent over a longer time frame. The solution according to the present application uses the power of historical demand and shipping data to make wise loading plan decisions. By analyzing these data, the solution can identify trends, changes and patterns in freight demand based on historical loading data with periodic laws, predict current freight demand patterns in the current period, and thus provide valuable insights for optimizing loading allocation. And because the solution uses historical loading data for a longer period of time, it also ensures the consistency of long-term loading plans, which is crucial to maintaining stable logistics operations and adapting to changes in demand without interruption.

[0041] Figure 2 A flow chart showing operational details of a system 200 for performing freight loading according to an embodiment of the present application.

[0042] Specifically, if Figure 2 As shown, the system 200 for freight loading receives historical loading data 1, the type and size of the current package to be loaded 2, and the transport vehicle information 3 as inputs of the system 200 for freight loading. Note that the package in the text can also be replaced by a pallet and the package thereon.

[0043] First, the freight loading demand analysis and prediction processor 4 in the system 200 for performing freight loading can predict the current freight demand pattern in the current period based on the historical loading data 1 of the historical time period.

[0044] Prior to this, the historical time period is determined first, for example, the length and span of the historical time period are determined. The historical time period can reflect the periodicity of the historical loading data corresponding to the current time period. The historical time period includes more than two historical periodic time periods corresponding to the current time period.

[0045] For example, the historical time period may include more than 12 weeks before the current day, the current period includes the current day, and the historical periodic period includes 1 day of every 4 weeks corresponding to the current day. The reason for selecting 12 weeks here is that there is a certain correlation between multiple quarters. For example, the freight demand of each day of each month of each quarter and the freight demand of the day of the month of the next quarter may have a periodic law such as similarity or linear relationship. However, more than 12 weeks as a historical time period is only an example. In fact, it can also be other historical time periods, such as 11 weeks, 16 weeks, 1 year, 2 years or more, as long as the historical time period can reflect a long-term regular demand, that is, it can reflect the periodic law of historical loading data corresponding to the current period. Or the historical time period may include 2 years before the current day, and the historical periodic period includes 1 day of each year corresponding to the current day. For example, during the annual shopping carnival, the freight demand will surge, so a historical time period of up to 2 years can also be set to predict the freight demand pattern of the day of the next year. I will not give examples one by one here. In general, historical loading data is recorded and organized in days, that is, the length of the current period is 1 day. This is because the delivery cycle is generally days, but the length of the current period is not limited to 1 day. If the delivery cycle is hourly, then the historical loading data can also be recorded and organized in hours. That is, the current period is 1 hour, then the historical periodic time period can be the hour of the day of each month (year) corresponding to the hour for more than 12 weeks (or more than 2 years), or the hour of every day for more than 12 weeks (or more than 2 years), as long as the current period has a periodic pattern between the corresponding historical periodic periods in the historical time period.

[0046] In one embodiment, the historical loading data 1 may include at least one of the following: shipping time, package type, package volume, and package quantity, wherein one package type corresponds to one package volume. The fields may be expressed as (shipping time DATE / TIME, package type PACKAGE TYPE / ID, package volume PACKAGE VOLUME, package quantity PACKAGE AMOUNT). Here, if the shipping time is a day, it may be expressed by the shipping date, and if the shipping time is by hour, it may be expressed by the shipping hour. Different package types may be identified by package IDs, and different package types may correspond to different package sizes (sizes or dimensions) and also to different volumes. Because there are many different sizes of packages to be shipped, the historical loading data records how many packages of different sizes were shipped at the shipping time.

[0047] In one embodiment, the current freight mode indicates at least one of the package type, package length, package width, package height, package volume, and the number of packages of each type to be loaded in the current time period. It is usually assumed that the dimensions of packages of the same type are consistent. Here, a specific package type to be loaded may correspond to a specific package length, a specific package width, a specific package height, and a specific package volume. The package volume may be calculated by multiplying the package length, the package width, and the package height. Here, it is assumed that the package to be loaded is a cuboid, and of course, a cube is a special form of a cuboid.

[0048] In one embodiment, in order to predict the current freight demand pattern in the current period based on the historical loading data 1 of the historical time period, the freight loading demand analysis and prediction processor 4 in the system 200 for freight loading can use a time series model or an artificial intelligence model to predict the current freight demand pattern in the current period.

[0049] In one embodiment, the artificial intelligence model is trained by historical loading training data and demand pattern labels, wherein the demand pattern labels include at least one of the package type, package volume, and package quantity of a specific day of a month in a periodic time period. For example, the historical loading training data is the package type, package volume, and package quantity of the historical loading on a specific day, for example, 4 months ago, and the demand pattern label is, for example, the package type, package volume, and package quantity of the actual loading on the specific day, for example, 1 month ago. Thus, the artificial intelligence model can be used to train the weight parameters of the neural network on how to accurately predict the package type, package volume, and package quantity of the actual loading on the specific day 1 month ago for the package type, package volume, and package quantity of the historical loading on the specific day 3 months ago, and a trained artificial intelligence model has been obtained. Therefore, the trained artificial intelligence model can be used to predict the package type, package volume, and package quantity that needs to be loaded in the next cycle, for example, the specific day (current day) of the month, by using the package type, package volume, and package quantity of the loading on the previous cycle, for example, 3 months ago. Of course, the training and prediction processes of the above artificial intelligence models are examples, and those skilled in the art can construct other artificial intelligence models based on the principles.

[0050] In one embodiment, the time series model includes averaging or fitting the number of packages of a specific type in each historical periodic period in the historical time period. For example, for the averaging scheme, the number of packages of a specific package type on a specific day (e.g., the 1st) of each month in the first three months is 150, 120, and 150 respectively, then the average is calculated to predict that the number of packages of a specific package type on a specific day (e.g., the 1st) of the current month is 140. For the fitting scheme, for another example, the number of packages of a specific package type on a specific day (e.g., the 1st) of each month in the first three months is 110, 120, and 130 respectively, then the number of packages of a specific package type on a specific day (e.g., the 1st) of the current month is predicted to be 140 according to linear fitting. Of course, the construction process of the above time series model is an example, and those skilled in the art can construct other time series models according to the principle.

[0051] In one embodiment, freight loading based at least on the current freight demand pattern also includes: freight loading based on the current freight demand pattern (which can be predicted by the freight loading demand analysis and prediction processor 4 based on historical loading data 1 for a historical time period), the type and size 2 of the package currently to be loaded, and transportation tool information 3.

[0052] In one embodiment, the type and size of the package currently to be loaded include at least one of the following: package type, package length, package width, package height, package volume, bendability, traceability, etc.

[0053] In one embodiment, the transport vehicle information includes at least one of the following: transport vehicle identification, transport vehicle space length, transport vehicle space width, transport vehicle space height, transport vehicle space volume, etc. Transport vehicles include trucks, vans, trains, vans, airplanes, containers, etc., as long as there is space for storing goods inside. The transport vehicle identification can indicate which type of transport vehicle it is, and it is usually assumed that the space of the same type of transport vehicle is consistent. The transport vehicle space is assumed to be a rectangular parallelepiped. The transport vehicle space length refers to the length of the space inside the transport vehicle for loading goods, the transport vehicle space width refers to the width of the space inside the transport vehicle for loading goods, and the transport vehicle space height refers to the height of the space inside the transport vehicle for loading goods. The transport vehicle space volume can be the product of the transport vehicle space length, the transport vehicle space width, and the transport vehicle space height.

[0054] Of course, the parameters included above are only examples, and other parameters can be added or reduced. For example, when the volume is not needed or the volume is calculated from the length, width, and height, the parameters related to the volume can be removed. In addition, bendability includes whether the package can be bent to other sizes. If so, the subsequent package placement algorithm process can consider the size after bending, which is not described in detail here. Traceability includes whether the package has a traceable barcode or RFID (radio frequency identification) tag, etc., which is irrelevant to the placement of the package, but can be used as auxiliary information.

[0055] In one embodiment, freight loading based on the current freight demand pattern (which can be predicted by the freight loading demand analysis and prediction processor 4 based on the historical loading data 1 of the historical time period), the type and size 2 of the package to be loaded, and the transportation tool information 3 includes: Figure 2 The historical load guide processor 7 shown utilizes (by Figure 2 After the transport vehicle is loaded with the single package loading algorithm based on the current freight demand pattern, the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle are determined by the loading process processor 8 based on the type and size of the packages currently to be loaded and the transport vehicle information; the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle are determined by the loading process processor 8 based on the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle. Figure 2 The single package loading algorithm (implemented by the single package loading processor 5 shown) and (implemented by Figure 2 The loading fill rate optimizer 6 shown in the figure is used to implement the loading fill rate optimization algorithm to obtain the package loading fill rate optimization result.

[0056] Specifically, by Figure 2 The historical load guide processor 7 shown, based on the current freight demand pattern and transportation tool information, uses (by Figure 2 In the step of loading the transport vehicle with a single package loading algorithm implemented by the single package loading processor 5 shown in FIG. Figure 3 This is implemented using the single package loading algorithm shown. Figure 3A schematic diagram of a single package loading algorithm according to an embodiment of the present application is shown. The core of the single package loading algorithm is to determine how to place the same type of packages based on the length, width, height of the same type of packages and the length, width, height of a certain space or all spaces of the transport vehicle to accommodate the maximum number of packages, that is, to maximize the use of a certain space or all spaces of the transport vehicle, for example, whether the long side of the package is aligned with the long side of the space, or the long side of the package is aligned with the short side of the space, that is, whether the package is placed horizontally, sideways, or vertically.

[0057] like Figure 3 As shown, assuming the following parameters:

[0058] Ltruck: length of truck space;

[0059] Wtruck: width of truck space;

[0060] Htruck: Truck space height;

[0061] Lpallet: the parcel length of a single parcel;

[0062] Wpallet: package width;

[0063] Hpallet: package height;

[0064] Nfloor: number of truck floors;

[0065] NX: the number of packages in the X zone in the truck space;

[0066] NRX: the number of packages in the RX zone of the truck space;

[0067] NY: the number of packages in the Y zone in the truck space;

[0068] NRY: the number of packages in the RY area of ​​the truck space;

[0069] x: the number of packages placed along the length of the truck space, based on the long side of the package;

[0070] y: the number of packages placed along the length of the truck space, based on the short side of the package;

[0071] LRY: the remaining length of the Y area;

[0072] WRY: The remaining width of the Y area;

[0073] total: the total number of packages loaded on each layer;

[0074] Total: The total number of packages loaded on the truck.

[0075] The single package loading algorithm is to maximize the expression Total(x) under the following constraints, that is, the total number of packages in all layers of the truck is maximized:

[0076] ll(x)≤Ltruck, for x=1,2,……p

[0077] lw(y)≤Ltruck, for y=1,2,……q

[0078] wl(x)≤Wtruck, for x=1,2,……p

[0079] wl(y)≤Wtruck, for y=1,2,……q

[0080] Where p = [Ltruck / Lpallet]. Note that [] here means rounding up, i.e. the largest integer less than or equal to Ltruck / Lpallet. [] in the subsequent formulas have the same meaning. ll(x)

[0081] ≤Ltruck means that along the length of the truck space, the total length of the packages placed on the long side of the packages does not exceed the length of the truck space, and lw(y)≤Ltruck means that along the length of the truck space, the total length of the packages placed on the short side of the packages does not exceed the length of the truck, wl(x)≤Wtruck means that along the length of the truck space, the total width of the packages placed on the long side of the packages does not exceed the width of the truck space, and wl(y)≤Wtruck means that along the length of the truck space, the total width of the packages placed on the short side of the packages does not exceed the width of the truck space.

[0082] As for how many layers the parcel can be placed in the truck space, Nfloor = [Htruck / Hpallet], that is, the height of the truck space divided by the height of the parcel gives the maximum number of layers the parcel can be placed in.

[0083] The specific algorithm is as follows:

[0084] For each x=1,2,...p:

[0085] y = [(Ltruck-x×Lpallet) / Wpallet], which means that when the number of packages placed along the long side of the package along the length of the truck space is x, after it is full, how many packages can be placed along the short side of the package along the remaining length of the truck space.

[0086] NX = x x [Wtruck / Wpallet], which means the number of packages placed along the width of the truck space on the short side of the package ([Wtruck / Wpallet]) multiplied by the number of packages placed along the length of the truck space x, to get the number of packages in the occupied X area.

[0087] NRX = 0, because the maximum number of packages has been placed along the width of the truck space including the short sides, so there is no way to place more than one package in the RX area.

[0088] NY=y×[Wtruck / Lpallet], which means the number of packages placed along the width of the truck space with the short side of the package ([Wtruck / Lpallet]) multiplied by the number of packages y placed along the length of the truck space, to obtain the number of packages in the occupied Y area.

[0089] LRY=Ltruck-x×Lpallet, which represents the remaining length after x packages are placed along the long side of the package along the length direction of the truck space, that is, the length of the RY area.

[0090] WRY=Wtruck-[Wtruck / Lpallet]×Lpallet, which represents the remaining width after the package is placed along the width direction of the truck space with its long side, that is, the width of the RY area.

[0091] NRY is:

[0092] If LRY>=Lpallet and WRY>=Wpallet

[0093] Then NRY=[WRY / Wpallet]×[WRY / Wpallet]

[0094] Otherwise, NRY is 0, indicating that there is no way to place the package in the RY area.

[0095] This means that if the length and width of the RY area are at least larger than the length and width of a package, at least one package can be placed in the RY area. The number of packages that can be placed is calculated by multiplying the length of the RY area divided by the length of the package (how many packages can be placed on the long side of the RY area) and the width of the RY area divided by the width of the package (how many packages can be placed on the short side of the RY area).

[0096] Then the total number of packages in one layer can be obtained as the sum of packages in all regions, that is, Where areas is the total number of areas, and i is equal to 1, 2, ...areas.

[0097] For all values ​​of x, total is calculated once and sorted in descending order to obtain the maximum total number of packages, i.e. Max(total).

[0098] Finally, the total number of packages on one floor is multiplied by the total number of floors to obtain the maximum total number of packages in the entire truck space, that is, Total = Max (total) × Nfloor.

[0099] The above describes how to maximize the use of a predetermined space for one type of package, which in the above example is the interior space of a truck, but the same principle can be applied to any predetermined space.

[0100] Therefore, with respect to the predicted current freight demand pattern, for example, how many packages of the first type (size), how many packages of the second type, how many packages of the third type, and so on, it is possible to use a single package loading algorithm to determine how to place these types of packages for each type of package based on the transport vehicle space conditions obtained from the transport vehicle information (for example, according to a predetermined order). For example, first use a single package loading algorithm to determine how to place the first type of package and the transport vehicle space, then use a single package loading algorithm to determine how to place the second type of package and the remaining space, then use a single package loading algorithm to determine how to place the third type of package and the remaining space, and so on.

[0101] Figure 4 An example of a mixed parcel loading algorithm for multiple types of parcels according to an embodiment of the present application is shown. In fact, the principle is to call a single parcel loading algorithm to fill each type of parcel in turn. Specifically, assuming that the truck space length is Ltruck, the truck space width is Wtruck, the truck space height is Htruck, and the parcel length of the i-th parcel is Lpallet i , the width of the i-th package is Wpallet i , the package height of the i-th package is Hpallet i . There are a total of p types of packages. So for the i-th package, the single package loading algorithm is triggered to obtain the placement method and number of packages for loading the i-th package. Note that here, the mixed package loading algorithm actually calls the single package loading algorithm, so in this article, the single package loading algorithm is used to represent the effect of this mixed package loading of the single package loading algorithm for each type of package.

[0102] After loading each type of package for the predicted current freight demand pattern, it is also necessary to calculate whether the actual number of packages that need to be loaded have been loaded.

[0103] Specifically, for the i-th type of package, assuming that the total number of the i-th type of packages actually to be loaded is N i Then calculate the number of packages of the ith type that can be loaded from side to side in the interior space of the truck after being arranged in this way, and then use the total number of packages of the ith type to be loaded as N i Subtract the number of packages that can be loaded by the single package algorithm, that is, NumMixed i =Ni -NumSingle i , and get the number of the i-th package remaining to be loaded. At the same time, the remaining space in the truck interior can be calculated by subtracting the remaining space Area(i) after loading the respective number of packages of each type from the total space of the truck after loading using the single package loading algorithm and the mixed package loading algorithm.

[0104] like Figure 4 As shown, it is assumed that the first type of package fills the space (294) with a single package loading algorithm, and the second type of package fills one of the remaining spaces (V64) with a single package loading algorithm, and so on, which will not be repeated here.

[0105] Note that since this is a planned package placement for the current freight demand pattern predicted based on historical freight data, it is generally believed that the current freight demand pattern predicted based on historical freight data will not exceed the space of the transport tool, that is, after the placement method and quantity of each type of package are determined by the single package loading algorithm, there is still surplus space to load the remaining packages to be loaded, rather than not being able to fit all the packages in the predicted current freight demand pattern. However, it is also possible that the current freight demand pattern predicted based on historical freight data has actually exceeded the space of the transport tool, and all the packages required by the current freight demand pattern cannot be placed no matter how they are placed. In this case, you can consider placing each type of package as much as possible in turn according to the single package loading algorithm until one or some types of packages cannot be placed.

[0106] The following description only focuses on the situation where there is still surplus space after the placement and quantity of each type of package are determined using the single package loading algorithm and the mixed package loading algorithm.

[0107] Since the various types of package loading methods obtained by the single package loading algorithm are based on a given rectangular (or cube) space as Figure 3 The length, width, and height of the truck space shown in the figure are used to load as much as possible, but there may be surplus space after loading. For example, although the remaining space in each of the above rectangular (or cube) spaces cannot load a certain type of package, it may be able to load other types of packages, and there may be a lot of space left (because the number of packages required by the current freight demand model may not be large). Therefore, it is also possible to consider continuing to optimize the loading method to maximize the use of the remaining space.

[0108] Next, after the transport vehicle is loaded using the single package loading algorithm based on the current freight demand pattern, the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle can be determined by the loading process processor 8 based on the type and size of the packages currently to be loaded and the transport vehicle information. Because even if the single package loading algorithm is adopted, it is not necessarily possible to load all the packages currently to be loaded. After the transport vehicle is loaded using the single package loading algorithm based on the current freight demand pattern, a portion of the packages currently to be loaded has been planned to be loaded (i.e., the types and quantities of packages in the current freight demand pattern), so the types and sizes of the remaining packages to be loaded can be determined, and the space occupied by the packages that have been planned to be loaded is subtracted from the original space of the transport vehicle to obtain the remaining space in the transport vehicle.

[0109] Next, the loading process processor 8, based on the types and sizes of the remaining packages to be loaded, the remaining space in the transport vehicle, and the utilization (by Figure 2 The single package loading algorithm (implemented by the single package loading processor 5 shown) and (implemented by Figure 2 The loading fill rate optimizer 6 shown in the figure is used to implement the loading fill rate optimization algorithm to obtain the package loading fill rate optimization result.

[0110] In one embodiment, after determining the remaining space, the remaining packages can be stacked in the remaining space. Figure 2 The loading fill rate optimization algorithm implemented by the loading fill rate optimizer 6 shown may include at least one of a stacking priority optimization and a floor space priority optimization. Figure 5 A schematic diagram of two algorithms, namely, stacking priority optimization and ground space priority optimization, of a loading fill rate optimization algorithm according to an embodiment of the present application is shown.

[0111] like Figure 5 As shown on the left, priority stacking optimization means that if there is remaining space, the same type of packages or different types of packages (if there are no packages of the same type that need to be installed) are stacked on top according to the type of packages stacked on the ground or below. Figure 5 As shown on the right, the optimization of preferentially filling the ground space means that if there is remaining space, the ground space is preferentially filled with stacked packages. Of course, the loading fill rate optimization algorithm can also include other types of filling optimization methods, which are not listed here one by one. In this way, different loading methods can be obtained under the two optimization methods. Therefore, it is possible to consider which optimization method can load the most packages to further improve the package loading fill rate, where FilingRate is used to represent the package loading fill rate, and LoadingAmount is used to represent the package loading quantity.

[0112] In one embodiment, loading freight based at least on the current freight demand pattern also includes: calculating the optimized loading fill rate after obtaining the package loading fill rate optimization result by using a single package loading algorithm and a loading fill rate optimization algorithm based on the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle; obtaining an optimized loading plan based on the package loading fill rate optimization result, wherein the optimized loading plan includes the loading method of each package type, the loading quantity of the package type and the loading plane layout; and loading freight according to the optimized loading plan.

[0113] Specifically, after obtaining the package loading filling rate optimization result by using the single package loading algorithm and the loading filling rate optimization algorithm based on the types and sizes of the remaining packages to be loaded and the remaining space in the transport vehicle, the optimized loading filling rate is calculated. The optimized loading filling rate can be calculated by dividing the total volume of the filled packages by the original space volume of the transport vehicle after filling all the spaces of the transport vehicle with various types of packages according to the above method according to the embodiment of the present application.

[0114] In one embodiment, loading freight based on at least the current freight demand pattern further includes: after loading the transport using the single package loading algorithm based on the current freight demand pattern, calculating a historical loading fill rate, which is the total volume of packages filled after loading only the number of packages of the types required by the current freight demand pattern using the single package loading algorithm (before filling the remaining packages) divided by the original space volume of the transport.

[0115] In this way, after calculating the optimized load filling rate and the historical load filling rate, it can be compared whether the optimized load filling rate is better than the historical load filling rate and how much better it is than the historical load filling rate.

[0116] In addition, an optimized loading plan is obtained based on the package loading filling rate optimization result, wherein the optimized loading plan includes the loading method of each package type, the loading quantity of the package type and the loading plane layout diagram;

[0117] Carry out freight loading according to the optimized loading plan. After the above method of the present application is calculated, the loading method of each package type, the loading quantity of the package type and the loading plane layout diagram of the ground of the transportation vehicle can be known to form an optimized loading plan. Then, the optimized loading plan can be sent to the actual loading personnel of the transportation vehicle to load according to the plan.

[0118] Therefore, embodiments according to the present application address these problems by introducing a loading planning scheme that operates over an extended planning horizon, typically spanning, for example, more than 12 weeks. By leveraging historical loading data over an extended time period, embodiments according to the present application address the shortcomings of existing solutions. Specifically, the focus on long-term strategic planning according to embodiments of the present application allows for the identification of demand patterns, trends, and changes that exceed short-term system constraints. By leveraging historical data, embodiments according to the present application leverage the accumulated knowledge of past shipments to provide more accurate and robust fill rate optimization targets. The ability to provide consistent loading planning strategies over extended periods of time according to embodiments of the present application ensures better resource utilization, reduces inefficiencies, and increases cost savings. This innovative solution goes beyond the scope of immediate optimization and provides a comprehensive solution that addresses the needs of both short-term execution and long-term planning.

[0119] In essence, embodiments according to the present application bridge the gap between traditional load planning systems and the need for more strategic, data-driven, and comprehensive solutions that take into account the historical context and long-term planning requirements of logistics operations. By doing so, embodiments according to the present application revolutionize the field of load planning and contribute to more efficient, effective, and optimized transportation logistics.

[0120] Figure 6 A block diagram of a system 600 for performing freight loading according to an embodiment of the present application is shown.

[0121] like Figure 6 As shown, a system 600 for freight loading includes: a determination device 610, configured to determine a historical time period, the historical time period can reflect the periodicity of historical loading data corresponding to the current time period, and the historical time period includes two or more historical periodic time periods corresponding to the current time period; a prediction device 620, based on the historical loading data of the historical time period to predict the current freight demand pattern in the current time period; a loading device 630, configured to perform freight loading based on at least the current freight demand pattern.

[0122] Since the solution according to the present application predicts the current freight demand pattern in the current period based on historical loading data of a longer period of time that can reflect periodic laws, unlike traditional products on the market that mainly emphasize short-term execution and operational planning, this new solution greatly extends the time range of loading plans and makes loading plans predictable or meaningfully predictable. This extended time range of loading plans based on periodic laws can ensure that freight loading plans are not only efficient, but also consistent over a longer time frame. The solution according to the present application uses the power of historical demand and shipping data to make wise loading plan decisions. By analyzing these data, the solution can identify trends, changes and patterns in freight demand based on historical loading data with periodic laws, predict current freight demand patterns in the current period, and thus provide valuable insights for optimizing loading allocation. And because the solution uses historical loading data for a longer period of time, it also ensures the consistency of long-term loading plans, which is crucial to maintaining stable logistics operations and adapting to changes in demand without interruption.

[0123] In one embodiment, the historical shipping data includes at least one of the following: shipping time, package type, package volume, and package quantity, wherein one package type corresponds to one package volume.

[0124] In one embodiment, the current freight demand pattern indicates at least one of a type of packages, a length of packages, a width of packages, a height of packages, a volume of packages, and a quantity of each type of packages predicted to be loaded during the current time period.

[0125] In one embodiment, the forecasting device 620 is configured to use a time series model or an artificial intelligence model to forecast the current freight demand pattern in the current period.

[0126] In one embodiment, the artificial intelligence model is trained using historical loading training data and demand pattern labels, wherein the demand pattern labels include at least one of package type, package volume, and package quantity in historical periodic time periods, and wherein the time series model includes averaging or fitting the quantity of packages of a specific type in each historical periodic time period in the historical time period.

[0127] In one embodiment, the historical time period includes more than 12 weeks, the current period includes today, and the historical period includes 1 day every 4 weeks corresponding to today; or the historical time period includes more than 2 years, and the historical period includes 1 day every year corresponding to today.

[0128] In one embodiment, the loading device 630 is configured to perform freight loading based on the current freight demand pattern, the type and size of the package currently to be loaded, and the transport vehicle information, wherein the type and size of the package currently to be loaded include at least one of the following: package type, package length, package width, package height, package volume, bendability, and traceability, and the transport vehicle information includes at least one of the following: transport vehicle identification, transport vehicle space length, transport vehicle space width, transport vehicle space height, and transport vehicle space volume.

[0129] In one embodiment, freight loading based on the current freight demand pattern, the type and size of the packages currently to be loaded, and the transport vehicle information includes: loading the transport vehicle using a single package loading algorithm based on the current freight demand pattern and the transport vehicle information; after loading the transport vehicle using a single package loading algorithm based on the current freight demand pattern, determining the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle based on the type and size of the packages currently to be loaded and the transport vehicle information; obtaining a package loading fill rate optimization result based on the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle using a single package loading algorithm and a loading fill rate optimization algorithm; wherein the loading fill rate optimization algorithm includes at least one of priority stacking optimization and priority filling ground space optimization.

[0130] In one embodiment, the loading device 630 is further configured to: calculate the optimized loading fill rate 9 after obtaining the package loading fill rate optimization result by using a single package loading algorithm and a loading fill rate optimization algorithm based on the type and size of the remaining packages to be loaded and the remaining space in the transport vehicle; obtain an optimized loading plan 10 based on the package loading fill rate optimization result, wherein the optimized loading plan includes the loading method of each package type, the loading quantity of the package type and the loading plane layout diagram; and carry out freight loading according to the optimized loading plan.

[0131] In one embodiment, the loading device 630 is further configured to calculate a historical loading fill rate after loading the transport vehicle using a single package loading algorithm based on the current freight demand pattern.

[0132] In summary, the solution according to the present application presents a new, different and advantageous approach to solving the problem of long-term strategic loading planning in a truck and trailer environment. The following is how the solution according to the present application stands out from past solutions or attempted solutions, and the advantages and technical benefits it provides.

[0133] The novelty and uniqueness of the program:

[0134] 1. Extended planning horizon: Unlike past solutions that focused primarily on short-term execution or immediate optimization, the embodiments of the present application significantly extend the planning horizon, typically spanning 12 weeks. This long-term perspective enables the solutions of the present application to address demand trends, seasonality, and changes that occur over a longer period of time, thereby providing strategic advantages in planning.

[0135] 2. Historical data driven analysis: The emphasis of the solution according to the present application on the analysis of historical demand and shipment data distinguishes it from previous attempts. By leveraging historical data, the solution according to the present application captures insights into demand patterns and trends that are not feasible when using real-time or near real-time data alone.

[0136] 3. Fill rate optimization: The solution according to the present application introduces the concept of a fill rate optimization target, which ensures that each truck or trailer is loaded to its maximum capacity while minimizing idle space. This solution improves efficiency by more effectively utilizing available space, reducing the need for additional trips, and optimizing resource utilization.

[0137] 4. Consistency over time: The ability of the solution according to the present application to provide consistent load planning strategies over an extended planning horizon is a unique feature. This consistency minimizes disruptions caused by sudden changes and shifts in demand, contributing to smoother logistics operations.

[0138] Advantages and technical strengths of the solution according to the present application include:

[0139] 1. Optimized resource utilization: By analyzing historical data and providing fill rate optimization targets, the solution according to this application maximizes the utilization of available space in trucks and trailers. This optimization reduces transportation costs because fewer trips are required to transport the same amount of goods.

[0140] 2. Data-driven strategic planning: Leveraging historical demand and shipment data enables informed decision making based on the scenario applied. This data-driven approach allows companies to adjust their logistics strategy based on actual demand patterns and make proactive adjustments.

[0141] 3. Reduced waste and environmental impact: By optimizing the filling rate and reducing the empty space during transportation, the solution according to the present application helps to reduce waste and lower environmental impact. Fewer trips means lower fuel consumption and emissions.

[0142] 4. Improve long-term efficiency: The long-term planning scope of the solution according to this application helps enterprises better respond to demand fluctuations, seasonal changes and other market dynamics. This improves efficiency because the load planning system predicts and adapts to changes in advance.

[0143] 5. Enhanced cost savings: By focusing on consistent, long-term loading plans and fill rate optimization, the solutions according to the present application result in significant cost savings by minimizing inefficiencies and waste of resources.

[0144] 6. Strategic Decision Support: The solution according to this application is used as a decision support tool for logistics managers and planners, providing insights into historical trends and suggesting load planning strategies that are consistent with long-term demand patterns.

[0145] In summary, the solution according to the present application introduces a paradigm shift in the field of load planning by providing extended planning horizons, historical data-driven analysis, fill rate optimization, and consistent load planning strategies. These innovations provide tremendous advantages in resource utilization, efficiency, cost savings, and strategic decision making. The unique combination of features of the embodiments according to the present application makes it a valuable solution that addresses the shortcomings of previous attempts and provides a new level of integration in the optimization of truck and trailer load planning.

[0146] Figure 7 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present application is shown.

[0147] The electronic device may include a processor (H1); a storage medium (H2) coupled to the processor (H1) and storing computer executable instructions therein for performing the steps of each method of an embodiment of the present application when executed by the processor.

[0148] The processor (H1) may include, but is not limited to, one or more processors or microprocessors, etc.

[0149] The storage medium (H2) may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disk, floppy disk, solid state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0150] In addition, the electronic device may also include (but not limited to) a data bus (H3), an input / output (I / O) bus (H4), a display (H5), and input / output devices (H6) (for example, a keyboard, a mouse, a speaker, etc.), etc.

[0151] The processor (H1) may communicate with external devices (H5, H6, etc.) through an I / O bus (H4) via a wired or wireless network (not shown).

[0152] The storage medium (H2) may also store at least one computer executable instruction for executing the various functions and / or method steps in the embodiments described in the present technology when the instruction is executed by the processor (H1).

[0153] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0154] Figure 8 A schematic diagram of a non-transitory computer-readable storage medium according to an embodiment of the present application is shown.

[0155] like Figure 8 As shown, instructions are stored on the computer-readable storage medium 820, and the instructions are, for example, computer-readable instructions 810. When the computer-readable instructions 810 are executed by the processor, the various methods described above can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the computer-readable storage medium 820 may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions 810 stored on the computer-readable storage medium 820, the various methods described above may be performed.

[0156] Of course, the above-mentioned specific embodiments are merely examples rather than limitations, and those skilled in the art can, according to the concept of the present application, merge and combine some steps and devices from the various embodiments described separately above to achieve the effects of the present application. Such merged and combined embodiments are also included in the present application, and such merges and combinations are not described one by one here.

[0157] Note that the advantages, strengths, effects, etc. mentioned in this disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of this application. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, not limitation, and the above details do not limit this application to being implemented by adopting the above specific details.

[0158] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0159] The step flow charts and the above method descriptions in this disclosure are only illustrative examples and are not intended to require or imply that the steps of each embodiment must be performed in the order given. As will be appreciated by those skilled in the art, the order of the steps in the above embodiments can be performed in any order. Words such as "thereafter", "then", "next", etc. are not intended to limit the order of steps; these words are only used to guide the reader through the description of these methods. In addition, any reference to a singular element, such as using the article "one", "one", or "the" is not to be construed as limiting the element to the singular.

[0160] In addition, the steps and devices in the various embodiments of this document are not limited to being implemented in a certain embodiment. In fact, according to the concept of this application, relevant partial steps and partial devices in the various embodiments of this document can be combined to conceive new embodiments, and these new embodiments are also included in the scope of this application.

[0161] Each operation of the method described above may be performed by any suitable means capable of performing the corresponding functions. The means may include various hardware and / or software components and / or modules, including but not limited to hardware circuits, application specific integrated circuits (ASICs) or processors.

[0162] The various illustrated logic blocks, modules and circuits may be implemented or described using a general purpose processor, a digital signal processor (DSP), an ASIC, a field programmable gate array signal (FPGA) or other programmable logic device (PLD), discrete gate or transistor logic, discrete hardware components or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but as an alternative, the processor may be any commercially available processor, controller, microcontroller or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, a microprocessor cooperating with a DSP core, or any other such configuration.

[0163] The steps of the method or algorithm described in conjunction with the present disclosure can be directly embedded in hardware, in a software module executed by a processor, or in a combination of the two. A software module can exist in any form of tangible storage medium. Some examples of storage media that can be used include random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, etc. A storage medium can be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. In an alternative manner, the storage medium can be integral with the processor. A software module can be a single instruction or many instructions, and can be distributed over several different code segments, between different programs, and across multiple storage media.

[0164] The methods disclosed herein include actions for implementing the described methods. Methods and / or actions may be interchangeable with each other without departing from the scope of the claims. In other words, unless a specific order of actions is specified, the order and / or use of specific actions may be modified without departing from the scope of the claims.

[0165] The above functions can be implemented by hardware, software, firmware or any combination thereof. If implemented in software, the functions can be stored as instructions on a tangible computer-readable medium. The storage medium can be any available tangible medium that can be accessed by a computer. By way of example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage device or any other tangible medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer. As used herein, a disk and a disc include a compact disc (CD), a laser disc, an optical disc, a digital versatile disc (DVD), a floppy disc and a blue disc, wherein the disc usually reproduces data magnetically, and the disc reproduces data optically using a laser.

[0166] Therefore, the present disclosure may also include computer program products, wherein the computer program products can perform the methods, steps and operations presented herein. For example, such computer program products can be computer software packages, computer code instructions, computer-readable tangible media having computer instructions tangibly stored (and / or encoded) thereon, which instructions can be executed by a processor to perform the operations described herein. The computer program product can include packaging materials.

[0167] Software or instructions may also be transmitted via a transmission medium. For example, the software may be transmitted from a website, server or other remote source using a transmission medium such as coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technology such as infrared, radio or microwave.

[0168] In addition, the module and / or other appropriate means for carrying out the methods and techniques described herein can be downloaded and / or otherwise obtained by the user terminal and / or base station when appropriate. For example, such a device can be coupled to a server to facilitate the transmission of the means for carrying out the methods described herein. Alternatively, the various methods described herein can be provided via a storage component (e.g., RAM, ROM, a physical storage medium such as a CD or a floppy disk, etc.) so that the user terminal and / or base station can obtain the various methods when being coupled to the device or providing a storage component to the device. In addition, any other appropriate technology for providing the methods and techniques described herein to the device can be utilized.

[0169] Other examples and implementations are within the scope and spirit of the present disclosure and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hard wiring, or any combination of these. Features that implement the functions can also be physically located in various locations, including being distributed so that parts of the functions are implemented at different physical locations. Moreover, as used herein, including as used in the claims, "or" used in a list of items that begin with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). In addition, the wording "exemplary" does not mean that the example described is preferred or better than other examples.

[0170] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0171] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0172] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for freight loading, comprising: Determine a historical time period, wherein the historical time period can reflect the periodicity of the historical loading data corresponding to the current time period, and the historical time period includes two or more historical periodic time periods corresponding to the current time period; predicting a current freight demand pattern in a current period based on the historical loading data for the historical period; Freight loading is performed based at least on the current freight demand pattern.

2. The method according to claim 1, wherein: The historical loading data includes at least one of the following: shipping time, package type, package volume, and package quantity, wherein one package type corresponds to one package volume, and wherein the current freight demand pattern indicates at least one of the package type, package length, package width, package height, package volume, and the quantity of each type of packages predicted to be loaded during the current time period.

3. The method according to claim 1 or 2, wherein: Predicting a current freight demand pattern in a current period based on the historical loading data of the historical time period includes predicting the current freight demand pattern in the current period using a time series model or an artificial intelligence model.

4. The method according to claim 3, wherein: The artificial intelligence model is trained using historical loading training data and demand pattern labels, wherein the demand pattern labels include at least one of package type, package volume, and package quantity in the historical periodic period.

5. The method according to claim 3, wherein: The time series model includes averaging or fitting the number of packages of a specific type in each historical periodic period in the historical time period.

6. The method according to claim 1, wherein: The historical time period includes more than 12 weeks, the current time period includes today, and the historical periodic time period includes 1 day in every 4 weeks corresponding to today; or the historical time period includes more than 2 years, and the historical periodic time period includes 1 day in each year corresponding to today.

7. The method of claim 1, wherein performing freight loading based at least on the current freight demand pattern further comprises: Carry out freight loading based on the current freight demand pattern, the type and size of the packages currently to be loaded, and the transportation tool information, The type and size of the package to be loaded currently include at least one of the following: package type, package length, package width, package height, package volume, bendability, and traceability. The transportation tool information includes at least one of the following: transportation tool identification, transportation tool space length, transportation tool space width, transportation tool space height, and transportation tool space volume.

8. The method according to claim 7, wherein: Carrying out freight loading based on the current freight demand pattern, the type and size of the packages currently to be loaded, and the transportation tool information includes: loading the transport vehicle using a single package loading algorithm based on the current freight demand pattern and the transport vehicle information; After loading the transport vehicle using a single package loading algorithm based on the current freight demand pattern, determining the type and size of remaining packages to be loaded and the remaining space in the transport vehicle based on the type and size of the current package to be loaded and the transport vehicle information; Based on the types and sizes of the remaining packages to be loaded and the remaining space in the transportation vehicle, using a single package loading algorithm and a loading filling rate optimization algorithm to obtain a package loading filling rate optimization result; The loading fill rate optimization algorithm includes at least one of priority stacking optimization and priority filling ground space optimization.

9. The method of claim 8, wherein said performing freight loading based at least on said current freight demand pattern further comprises: After obtaining a parcel loading fill rate optimization result using a single parcel loading algorithm and a loading fill rate optimization algorithm based on the types and sizes of the remaining parcels to be loaded and the remaining space in the transport vehicle, an optimized loading fill rate is calculated; An optimized loading plan is obtained based on the package loading filling rate optimization result, wherein the optimized loading plan includes a loading method for each package type, a loading quantity of each package type, and a loading plane layout diagram; Freight loading is performed according to the optimized loading plan.

10. The method of claim 8, wherein said performing freight loading based at least on said current freight demand pattern further comprises: After loading the transport using a single package loading algorithm based on the current freight demand pattern, a historical load fill rate is calculated.

11. A system for loading freight, comprising: A determination device is configured to determine a historical time period, wherein the historical time period can reflect the periodicity of the historical loading data corresponding to the current time period, and the historical time period includes two or more historical periodic time periods corresponding to the current time period; Prediction means, configured to predict a current freight demand pattern in a current period based on the historical loading data for the historical period; The loading device is configured to perform freight loading based at least on the current freight demand pattern.

12. An electronic device comprising: A memory for storing instructions; A processor, configured to read instructions in the memory and execute the method according to any one of claims 1 to 10.

13. A non-transitory storage medium having stored thereon instructions, in, When the instructions are read by a processor, the processor is caused to execute the method according to any one of claims 1 to 10.

Images