Method for handling shipping of containers and related electronic device

Abstract

A method performed by an electronic device for handling shipping of a container is disclosed. The method includes obtaining historical data associated with container shipping. The method includes determining a container usage pattern associated with the container based on the historical data. The method includes generating a delayed package associated with container shipping and characterized by package data based on a container usage pattern. The package data includes a delay parameter indicating a time period for extending a return time of the container and a cost parameter associated with the delay parameter. The method includes predicting selection parameters by applying a machine learning model to historical data and previous package data for one or more of the plurality of delay packages. The selection parameter indicates a likelihood of selecting a corresponding delay package.

Description

[0001] The present disclosure relates to the field of transportation and freight. The present disclosure relates to a method for handling shipping of containers and related electronic equipment. Background Art

[0002] When shipping containers, many factors can affect shipping, including when the container is returned to the shipping line (e.g. after delivery of its contents). The booking of a container can include an extension package that allows the user to extend the time to return the container. The user selects the extension package when booking. At the time, it is difficult to foresee how long the extension may be required. This can affect the availability of containers for the shipping line. Summary of the invention

[0003] Therefore, there is a need for an electronic device and method for handling the shipping of containers that mitigates, alleviates or addresses existing shortcomings and provides an adaptive deferral package that can result in improved container resource management.

[0004] A method for handling shipping of a container performed by an electronic device is disclosed. The method includes obtaining historical data associated with container shipping. The method includes determining a container usage pattern associated with the container based on the historical data. The method includes generating an extension package associated with the container shipping and characterized by package data based on the container usage pattern. The package data includes an extension parameter indicating a time period for extending the return time of the container and a cost parameter associated with the extension parameter. The method includes predicting a selection parameter for one or more extension packages of a plurality of extension packages by applying a machine learning model to the historical data and previous package data. The selection parameter indicates the likelihood of selecting the corresponding extension package. Optionally, the method includes determining extension cost data associated with the extension of the container shipping based on the selection parameter for the one or more extension packages. The method includes optionally providing updated package data associated with the extension package based on the extension cost data.

[0005] In addition, an electronic device is disclosed. The electronic device includes a memory, an interface, and a processor. The electronic device is configured to perform any one of the methods disclosed herein.

[0006] A computer-readable storage medium storing one or more programs including instructions that, when executed by an electronic device, cause the electronic device to perform any of the methods disclosed herein is disclosed.

[0007] The advantage of the present disclosure is that the disclosed electronic device and method provide improved provisioning of deferral packages, which allows for more optimal deferral periods and associated costs. The disclosed technology provides increased transparency for shipping companies and users in provisioning deferral packages. In addition, the disclosed technology allows for provisioning of adaptive deferral packages. The disclosed technology improves inventory management by taking into account container availability. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features and advantages of the present disclosure will be readily apparent to those skilled in the art through the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0009] Figure 1 is a flow chart illustrating an exemplary method performed by an electronic device for processing shipping of a container according to the present disclosure, and

[0010] Figure 2 is a block diagram illustrating an exemplary electronic device according to the present disclosure. DETAILED DESCRIPTION

[0011] Various exemplary embodiments and details are described below with reference to the accompanying drawings when relevant. It should be noted that the drawings may or may not be drawn to scale, and in all drawings, elements with similar structures or functions are represented by the same reference numerals. It should also be noted that the drawings are intended only to facilitate the description of the embodiments. The drawings are not intended to be a detailed description of the present disclosure or a limitation on the scope of the present disclosure. In addition, the illustrated embodiments do not necessarily have all the aspects or advantages shown. The aspects or advantages described in conjunction with a particular embodiment are not necessarily limited to the embodiment, and can be practiced in any other embodiment, even if not shown or not explicitly described as such.

[0012] For the sake of clarity, the drawings are schematic and simplified, and they only show details that are helpful for understanding the present disclosure, while other details are omitted. Throughout, the same reference numerals are used for the same or corresponding parts.

[0013] A container disclosed herein refers to a housing that packages items to be shipped for transportation. For example, a container can be considered a box. In this disclosure, the term container can be used interchangeably with box. For example, a container can be an intermodal container, so it is standardized and built for intermodal cargo transportation. For example, a container can be carried by shipping, rail, and road transportation.

[0014] Articles disclosed herein refer to objects to be placed in a container for transportation. For example, articles can be considered as cargo items, such as freight items, such as objects to be shipped. Note that the term article can be used interchangeably with cargo. For example, articles can include goods that can be placed in a container, such as consumer goods of large manufacturing companies, such as ordinary consumer goods such as shoes, clothing, toys, and fast-moving consumer goods such as packaged foods, beverages, cosmetics, and medicines.

[0015] For example, the articles disclosed herein may be viewed as commodities that may be packaged into, for example, rectangular stackable cartons having variable weights and volumes that are shipped in one or more containers (eg, in one or more dry containers).

[0016] In order to mitigate the risk of incurring penalties due to delays, deferral packages may be offered to users when they book shipping of a container. A deferral package may be viewed as an option and / or product for extending the time a container is returned to a shipping line. For example, a deferral package may be viewed as a deferral offer and / or deferral scheme. For example, a user may choose a deferral of up to 14 days, charged at a flat daily rate. Determining the costs associated with such deferral packages is very important in the logistics and shipping industry.

[0017] It should be noted that delayed return of a container is disadvantageous because other users may want to book the same container and may pay higher shipping costs.

[0018] Providing an optimal and / or advantageous deferral package including deferral parameters and associated fees for shipping lines and other users is very challenging due to the trade-offs between the revenues generated by various products, prevailing market conditions and various other factors. There is no readily available solution that can be quickly customized to address this challenge. If the deferral package is not optimal, there may be a significant cannibalization effect between revenue streams, which has a negative impact on revenue. Therefore, providing an optimal deferral package can lead to mitigating any negative impact.

[0019] Figure 1 A flowchart of an exemplary method 100 for processing shipping of a container according to the present disclosure performed by an electronic device is shown. The electronic device is an electronic device disclosed herein, such as Figure 2 An electronic device 300.

[0020] The method 100 includes obtaining S102 historical data associated with container shipping. In one or more examples, container shipping can be viewed as shipping (e.g., transporting) one or more containers including one or more items. For example, historical data is associated with one or more containers. For example, obtaining historical data includes obtaining historical data by querying one or more repositories (e.g., one or more databases and / or one or more data warehouses). For example, historical data includes one or more of the following: booking data, shipping data, and equipment data associated with previous container shipping, such as previous activities of the container (e.g., previous shipping of one or more items encapsulated in the container). Booking data includes information associated with bookings for one or more containers. Shipping data includes information associated with shipping of one or more items encapsulated in one or more containers. Equipment data includes information associated with the number of equipment used during shipping and / or information associated with the type of equipment used during shipping. In some examples, historical data includes information indicating data for requesting a container and / or a date for returning the container (e.g., an estimated return date provided by a user (such as a customer) and / or an actual return date detected by a service provider (such as a company)). For example, the historical data includes information associated with previous deferral requests. In other words, in some examples, the historical data includes package data for previous shipments of the container. In other words, the historical data includes, for example, deferral parameters (e.g., a time period for returning the container) and cost parameters associated with the deferral parameters for previous shipments of the container (e.g., associated with energy consumption and / or resource utilization and / or time of use of the container).

[0021] The method 100 comprises determining S104 a container usage pattern associated with the container based on the historical data. For example, the container usage pattern may be determined by using a statistical method that takes the historical data as input, e.g., to output a median and / or mean of a usage indicator. For example, the container usage pattern may be characterized by container usage parameters such as return time, mean and / or median daily charges over an extended period of time.

[0022] In one or more exemplary methods, determining S104 a container usage pattern associated with a container based on historical data includes determining S104A one or more container usage parameters based on historical data. In one or more exemplary methods, determining S104 a container usage pattern associated with a container based on historical data includes determining S104B a container usage pattern associated with a container based on one or more container usage parameters. In one or more examples, the container usage pattern indicates conditions associated with booking and / or shipping of a container based on historical data (e.g., booking data and / or shipping data and / or equipment data). For example, the container usage pattern can be considered as a current rental pattern associated with a container. In one or more exemplary methods, the one or more container usage parameters include one or more of the following: a ratio parameter indicating a ratio of users who select a corresponding extension package, an average delay in returning a container, an average turnaround time for returning a container, one or more rate parameters indicating a rate for a corresponding container size and / or country, one or more extension days for a corresponding container size and / or country, a statistical rate parameter indicating a rate for a corresponding container size and / or country, and a statistical extension day for a corresponding container size and / or country.

[0023] In one or more examples, average delays in returning containers and average turnaround time for returning containers are container usage parameters used to determine the impact on extended rate data (eg, cannibalization effect on demurrage and detention (D&D) revenue).

[0024] Optionally, the method 100 comprises generating S106 an extension package characterized by package data associated with the container shipping based on the container usage pattern. In some examples, the package data comprises an extension parameter indicating a time period for extending the return time of the container and a cost parameter associated with the extension parameter. For example, the extension package is characterized in that the package data comprises the extension parameter and its associated cost parameter. For example, the extension parameter comprises a time period for extending the return time of the container. For example, the cost parameter may indicate energy consumption, resource usage, time usage and / or pricing.

[0025] Optionally, the method 100 includes generating package data based on container usage patterns.

[0026] In one or more examples, a user may need an extension to return a container to a container location. For example, an extension is an extension of time requested by a user (e.g., a customer) for returning a container to a container location (e.g., a port and / or a terminal). In one or more examples, an extension package provides package data including an extension parameter (such as a time period, such as a range of days). In other words, the extension parameter includes the number of days for returning the container. Based on an example container usage pattern, 60% of users (e.g., a proportion parameter) request to return the container on the 5th day, 20% of users request to return the container on the 9th day, 10% of customers request to return the container on the 10th day, and 20% of users request to return the container on the 1st day, the 2nd day, and the 3rd day. For example, the 5th day, the 9th day, and the 10th day are days with a higher proportion of users requesting to return the container. For example, the package data of the extension package is determined based on the 5th day, the 9th day, and the 10th day. In some examples, the extension package can be recommended to the user by a shipping company.

[0027] Optionally, the method 100 includes generating a plurality of extension packages based on the container usage pattern, including a first extension package (characterized by first package data), a second extension package (characterized by second package data), and optionally a third extension package (characterized by third package data), etc. The first package data includes a first extension parameter and its associated first cost parameter. The second package data includes a second extension parameter and its associated second cost parameter. The third package data includes a third extension parameter and its associated third cost parameter.

[0028] In one or more exemplary methods, generating S106 a deferral package based on the container usage pattern includes generating S106B a plurality of deferral packages based on the container usage pattern. In one or more exemplary methods, each deferral package is characterized by corresponding package data.

[0029] In one or more exemplary methods, generating S106 the deferred package based on the container usage pattern includes generating S106A package data indicating the deferred package based on the container usage pattern.

[0030] In one or more exemplary methods, generating S106 the deferral packages based on the container usage pattern comprises: for each deferral package, generating S106C a corresponding deferral parameter and a corresponding fee parameter associated with each deferral package based on the container usage pattern.

[0031] In one or more exemplary methods, the deferral parameter includes a time period.

[0032] In one or more exemplary methods, for each deferral package, generating S106C a respective deferral parameter and a respective fee parameter associated with each deferral package based on the container usage pattern includes determining S106CA a first fee parameter associated with a first deferral package of the plurality of deferral packages.

[0033] In some examples, the method generates one or more of: first package data for a first extension package (e.g., 1 to 5 days and cost 1), second package data for a second extension package (e.g., 6 to 10 days and cost 2), third package data for a third extension package (e.g., 11 to 14 days and cost 3), fourth package data for a fourth extension package, and any other suitable number of extension packages. In some examples, the extension package may include one or more of: a first extension parameter (e.g., 1 to 5 days) and its associated first cost parameter, a second extension parameter (e.g., 6 to 10 days) and its associated second cost parameter, a third extension parameter (e.g., 11 to 14 days) and its associated third cost parameter, etc.

[0034] In one or more exemplary methods, for each extension package, generating S106C a corresponding extension parameter and a corresponding fee parameter associated with each extension package based on the container usage pattern includes: based on the first fee parameter and the difference parameter, determining S106CB the second fee parameter by maintaining the difference parameter between the first fee parameter and the second fee parameter associated with the second extension package in the plurality of extension packages. For example, the first fee parameter and the second fee parameter are from subsequent packages arranged in sequence. The difference parameter can be a percentage, such as 10%. Maintaining the difference parameter can be regarded as applying the same percentage. For example, the fee parameter associated with the first extension parameter is determined based on the difference parameter being a statistical rate parameter (e.g., the daily median rate of the corresponding container size and / or country). For example, the fee parameter associated with the second extension parameter is calculated based on the fee parameter associated with the first extension parameter (e.g., 10% less than the fee parameter associated with the first extension parameter). For example, the fee parameter associated with the third extension parameter is calculated based on the fee parameter associated with the second extension parameter (e.g., 10% less than the fee parameter associated with the first extension parameter).

[0035] The method 100 includes predicting S108 selection parameters for one or more deferred packages in a plurality of deferred packages by applying a machine learning model to historical data and previous package data. Previous package data includes, for example, historical package data. The selection parameter indicates the possibility of selecting a corresponding deferred package. For example, predicting selection parameters for one or more deferred packages in a plurality of deferred packages (such as, for each deferred package in a plurality of deferred packages).

[0036] For example, the selection parameter can be viewed as an acceptance rate and / or adoption rate of the user. In other words, the selection parameter indicates the likelihood of the user selecting the deferred package. For example, the selection parameter includes an adoption rate for each deferred package in a plurality of deferred packages. For example, applying a machine learning model to historical data and previous package data provides a predicted selection parameter (e.g., adoption rate) for one or more deferred packages in a plurality of deferred packages as an output. For example, the selection parameter indicates the likelihood of the user selecting the corresponding deferred package. For example, selecting the corresponding deferred package includes selecting the corresponding deferred package based on a cost parameter associated with the corresponding deferred parameter.

[0037] The method 100 includes determining S110 an extension fee associated with the extension of container shipping based on a selection parameter for one or more extension packages. The extension fee data can be viewed as a total fee associated with the extension (such as associated with the extension package provided by the user selection). For example, the extension fee data can include a benefit parameter indicating the benefit associated with the extension of container shipping.

[0038] The method 100 includes providing S112 the updated package data associated with the deferred package based on the extended cost data. The extended cost data can be used to update the package data associated with the deferred package, such as for updating the extended parameter and the cost parameter associated therewith. The updated package data can benefit from the extended cost data determined based on the selection parameter, for example, based on the possibility of the user selecting the corresponding deferred package. In other words, the updated package data provided for the deferred package is determined so that the possibility of the user selecting the deferred package is higher. For example, the updated package data can be regarded as the recommended package data of the recommended deferred package. In some examples, the updated package data can be the same as the package data before the update. In some examples, the updated package data can be different from the package data before the update. In other words, the package data can or can be not affected by the extended cost data.

[0039] In one or more exemplary methods, predicting S108 selection parameters by applying a machine learning model to historical data and previous package data includes: for one or more deferred packages, based on historical data and previous package data, determining S108A a first change parameter indicating a change in a cost parameter of the package data and a second change parameter indicating a corresponding change in a corresponding selection parameter.

[0040] For example, predicting the selection parameters includes determining, for each extension package (e.g., a package including days for returning a container), a first change parameter and a second change parameter based on a cost parameter associated with the historical data and previous package data. For example, the first change parameter can be viewed as a percentage change in a cost parameter of the package data (e.g., a price of the package data). For example, the second change parameter can be viewed as a percentage change in the adoption rate. In other words, predicting the selection parameters includes determining a percentage change in the cost parameter and a corresponding change in the selection parameter (e.g., the adoption rate) based on the cost parameter associated with the historical data and previous package data.

[0041] In one or more exemplary methods, predicting S108 the selection parameter by applying the machine learning model to the historical data and the previous package data includes training S108B the machine learning model based on the first change parameter and the second change parameter. For example, the machine learning model takes the historical data and the previous package data as input. For example, the machine learning outputs the selection parameter. For example, the historical data may include the first change parameter and the second change parameter. In other words, the machine learning model takes the percentage change of the cost parameter and the corresponding change of the selection parameter (e.g., the adoption rate) as input. The machine learning model can be trained using historical data.

[0042] For example, predicting a selection parameter (e.g., a percentage change in adoption rate) includes predicting the selection parameter for each of a plurality of deferred packages by applying a trained machine learning model (e.g., a machine learning model previously trained based on a first change parameter and a second change parameter).

[0043] In one or more exemplary methods, the machine learning model includes a linear regression model. In one or more exemplary methods, the machine learning model includes a regularized linear regression model, for example, the model is optimized to obtain higher accuracy. For example, the regularized linear regression model predicts the selection parameter based on historical data and previous package data. In other words, the regularized linear regression model provides a linear relationship between the selection parameter and the historical data and previous package data. The selection parameter can be determined by regularized linear regression based on the historical data and previous package data.

[0044] In one or more exemplary methods, predicting S108 the selection parameter by applying a machine learning model to historical data and previous package data includes determining S108C a third change parameter indicating a change in a cost parameter of the package data relative to a current fixed cost of the extension package for one or more extension packages. The third change parameter indicates a change in the cost parameter relative to the current fixed cost of the corresponding extension package with the corresponding extension parameter. For example, for each extension package in a plurality of extension packages, the third change parameter is determined. In one or more examples, the third change parameter indicates a percentage change in each cost parameter of the package data of the extension package relative to the current fixed cost of the corresponding extension package. For example, the current fixed cost of the extension package (e.g., the current flat rate) can be regarded as the cost (e.g., price) of obtaining such an extension parameter for extending the time period for returning the container.

[0045] In one or more exemplary methods, predicting S108 the selection parameter by applying the machine learning model to the historical data and the previous package data includes using the trained machine learning model to predict S108D a fourth change parameter indicating a change in the selection parameter for each cost parameter of the package data. In one or more examples, the fourth change parameter indicates a percentage change in the user's selection parameter (e.g., adoption rate) for the deferred package using the trained machine learning model for each cost parameter of each proposed deferred package (e.g., for each package data of the deferred package).

[0046] In one or more exemplary methods, determining S110 the extension cost data associated with the extension of the container shipping based on the selection parameters for each extension package includes: performing S110A simulation of the extension cost data of the package data of each extension package based on the selection parameters for each extension package. In other words, the extension cost data is determined by simulating the cost extension data based on the selection parameters. The extension cost data for each extension package is obtained by simulating the extension data for each extension package based on the selection parameters for each extension package. In one or more exemplary methods, determining S110 the extension cost data associated with the extension of the container shipping based on the selection parameters for each extension package includes: generating S110B the extension cost data based on the simulated extension cost data.

[0047] In one or more exemplary methods, the simulation is a Monte Carlo simulation configured to randomize the selection ratio of each deferred package. In one or more examples, the simulation of the extended cost data for the package data for each deferred package based on the selection parameters (e.g., adoption rate) for each deferred package allows the corresponding extended cost data (e.g., including the revenue parameter) to be determined.

[0048] In one or more exemplary methods, performing S110A the simulation includes generating demurrage and detention charge data indicating demurrage and detention charges for the container for each deferral package.

[0049] In one or more exemplary methods, the extension cost data includes demurrage and detention cost data. In some examples, the extension cost data includes demurrage and detention (D&D) yield parameters and deferred yield parameters.

[0050] For example, a Monte Carlo simulation slightly randomizes the consumption ratio of each block (slab) and runs for 1000 iterations. The simulation can calculate the deferral benefit parameters based on the fee parameters of each deferral package. The average of the deferral fees generated by all iterations is used as the input for the prediction.

[0051] It is understood that the present disclosure uses machine learning models to predict selected parameters (such as customer adoption) under specific cost parameters and extension parameters. The present disclosure proposes using Monte Carlo simulation techniques to predict approximate extended cost data, such as indicating extension benefits.

[0052] In one or more exemplary methods, providing S112 the updated package data based on the extended cost data includes providing S112A the updated package data based on the maximum extended cost of the extended cost data. In other words, the updated package data can maximize the extended cost (represented by the extended cost data, such as total revenue), and thus can be recommended. After running the simulation in sequence for all candidate price points, the price point that maximizes the total revenue is considered optimal and is recommended by the tool.

[0053] Figure 2 1 is a block diagram of an exemplary electronic device 300 according to the present disclosure. The electronic device 300 includes a memory 301, a processor 302, and an interface 303. The electronic device 300 is configured to execute Figure 1 In other words, the electronic device 300 is configured to process the shipping of containers.

[0054] Electronic device 300 is configured to obtain (eg, via interface 303 and / or using memory 301 ) historical data associated with container shipping.

[0055] The electronic device 300 is configured to determine (eg, using the processor 302 ) a container usage pattern associated with the container based on the historical data.

[0056] The electronic device 300 is configured to generate (e.g., using the processor 302) an extension package associated with a container shipping characterized by package data based on the container usage pattern. The package data includes an extension parameter indicating a time period for extending the return time of the container and a fee parameter associated with the extension parameter.

[0057] The electronic device 300 is configured to predict (eg, using the processor 302) a selection parameter for one or more of the multiple deferred packages by applying a machine learning model to historical data and previous package data. The selection parameter indicates the likelihood of selecting the corresponding deferred package.

[0058] The electronic device 300 is configured to determine (eg, using the processor 302 ) extension fee data associated with deferral of container shipping based on selection parameters for one or more deferral packages.

[0059] The electronic device 300 is configured to provide (eg, using the processor 302 and / or the interface 303) updated package data associated with the extended package based on the extended cost data.

[0060] The electronic device 300 is optionally configured to perform Figure 1 The operations disclosed in the electronic device 300 (such as any one or more of S104A, S104B, S106A, S106B, S106C, S106CA, S106CB, S108A, S108B, S108C, S108D, S110A, S110B, S112A). The operations of the electronic device 300 may be embodied in the form of executable logic routines (e.g., lines of code, software programs, etc.) stored on a non-transitory computer-readable medium (e.g., memory 301) and executed by the processor 302.

[0061] Furthermore, the operation of the electronic device 300 may be considered as a method that the electronic device 300 is configured to perform. In addition, although the functions and operations described may be implemented in software, such functions may also be implemented by dedicated hardware or firmware, or some combination of hardware, firmware and / or software.

[0062] The memory 301 may be one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, a random access memory (RAM), and any other suitable device. In a typical arrangement, the memory 301 may include a non-volatile memory for long-term data storage and a volatile memory used as a system memory for the processor 302. The memory 301 may exchange data with the processor circuit 302 via a data bus. There may also be control lines and an address bus ( Figure 2 Memory 301 is considered a non-transitory computer-readable medium.

[0063] The memory 301 may be configured to store historical data, container usage patterns, extended packages, package data, selection parameters, extended cost data, updated package data in a portion of the memory.

[0064] Embodiments of methods and products (electronic devices) according to the present disclosure are set forth in the following clauses:

[0065] Clause 1. A method for processing shipping of a container performed by an electronic device, the method comprising:

[0066] Acquiring (S102) historical data associated with container shipping;

[0067] determining (S104) a container usage pattern associated with the container based on the historical data;

[0068] generating ( S106 ) an extension package characterized by package data associated with the container shipping based on the container usage pattern, wherein the package data includes an extension parameter indicating a time period for extending the return time of the container and a fee parameter associated with the extension parameter;

[0069] For one or more deferred packages among the plurality of deferred packages, predicting ( S108 ) a selection parameter indicating a likelihood of selecting the corresponding deferred package by applying the machine learning model to the historical data and the previous package data;

[0070] determining (S110) extension cost data associated with the deferral of the container shipping based on the selection parameters for the one or more deferral packages; and

[0071] Updated package data associated with the extended package is provided (S112) based on the extended fee data.

[0072] Clause 2. The method according to clause 1, wherein generating (S106) the extension package based on the container usage pattern comprises generating (S106A) package data indicating the extension package based on the container usage pattern.

[0073] Clause 3. The method according to any one of the preceding clauses, wherein generating (S106) the extension package based on the container usage pattern comprises:

[0074] - Generating (S106B) the plurality of extension packages based on the container usage pattern, wherein each extension package is characterized by corresponding package data.

[0075] Clause 4. The method according to any one of the preceding clauses, wherein generating (S106) the extension package based on the container usage pattern comprises:

[0076] - For each deferral package, based on the container usage pattern, generating (S106C) a corresponding deferral parameter and a corresponding fee parameter associated with each deferral package.

[0077] Clause 5. A method according to any of the preceding clauses, wherein the delay parameter comprises the time period.

[0078] Clause 6. The method according to any one of clauses 4-5, wherein, for each extension package, based on the container usage pattern, generating (S106C) a corresponding extension parameter and a corresponding fee parameter associated with each extension package comprises:

[0079] - determining (S106CA) a first fee parameter associated with a first deferred package of the plurality of deferred packages, and

[0080] - Based on the first fee parameter and the difference parameter, determining (S106CB) the second fee parameter by maintaining a difference parameter between the first fee parameter and a second fee parameter associated with a second deferred package of the plurality of deferred packages.

[0081] Clause 7. A method according to any one of the preceding clauses, wherein predicting (S108) the selection parameter by applying the machine learning model to the historical data and the previous package data comprises:

[0082] - for the one or more deferred packages, determining (S108A) a first change parameter indicating a change of the cost parameter of the package data and a second change parameter indicating a corresponding change of a corresponding selection parameter based on the historical data and the previous package data.

[0083] Clause 8. The method according to clause 7, wherein predicting (S108) the selection parameter by applying the machine learning model to the historical data and the previous package data comprises:

[0084] -Training (S108B) the machine learning model based on the first change parameter and the second change parameter.

[0085] Clause 9. A method according to any of the preceding clauses, wherein the machine learning model comprises a linear regression model.

[0086] Clause 10. The method according to any one of the preceding clauses, wherein predicting (S108) the selection parameter by applying the machine learning model to the historical data and the previous package data comprises:

[0087] - for the one or more deferred packages, determining (S108C) a third change parameter indicating a change of the cost parameter of the package data relative to a current fixed cost of a deferred package; and

[0088] - Using the trained machine learning model to predict (S108D) a fourth change parameter indicating a change in the selection parameter for each cost parameter of the package data.

[0089] Clause 11. The method according to any of the preceding clauses, wherein determining (S110) the extension cost data associated with the deferral of the container shipping based on the selection parameters for each deferral package comprises:

[0090] - performing (S110A) simulation on the extension fee data of the package data of each extension package based on the selection parameters for each extension package; and

[0091] - generating (S110B) the extension fee data based on the simulated extension fee data.

[0092] Clause 12. The method of clause 11, wherein the simulation is a Monte Carlo simulation configured to randomize the selection ratio of each deferred package.

[0093] Clause 13. The method according to any one of clauses 11-12, wherein performing (S110A) the simulation comprises generating demurrage and detention charge data indicating demurrage and detention charges for the container for each deferral package.

[0094] Clause 14. The method of clause 13, wherein the extension charge data comprises the demurrage and detention charge data.

[0095] Clause 15. The method according to any one of the preceding clauses, wherein determining (S104) a container usage pattern associated with the container based on the historical data comprises:

[0096] - determining (S104A) one or more container usage parameters based on said historical data; and

[0097] - determining (S104B) a container usage pattern associated with said container based on said one or more container usage parameters.

[0098] Clause 16. A method according to any of the preceding clauses, wherein the one or more container usage parameters include one or more of the following:

[0099] - a ratio parameter indicating the ratio of users who select the corresponding extension package,

[0100] - average delay in returning said container, average turnaround time in returning said container,

[0101] - one or more rate parameters indicating the rate for the respective container size and / or country,

[0102] - one or more extension days for the respective container size and / or country,

[0103] - a statistical rate parameter indicating the rate for the corresponding container size and / or country, and

[0104] - Statistics extension day for corresponding container size and / or country.

[0105] Clause 17. A method according to any one of the preceding clauses, wherein providing (S112) updated package data based on the extended cost data comprises: providing (S112A) the updated package data based on a maximum extended cost of the extended cost data.

[0106] Clause 18. An electronic device comprising a memory, an interface and a processor, the electronic device being configured to perform any of the methods according to any of clauses 1-17.

[0107] Clause 19. A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that, when executed by an electronic device, cause the electronic device to perform any of the methods of clauses 1-17.

[0108] The use of the terms "first", "second", "third", and "fourth", "primary", "secondary", "tertiary", etc. does not imply any particular order, but is included to identify individual elements. Furthermore, the use of the terms "first", "second", "third", and "fourth", "primary", "secondary", "tertiary", etc. does not indicate any order or importance, but rather the terms "first", "second", "third", and "fourth", "primary", "secondary", "tertiary", etc. are used to distinguish one element from another. Please note that the use of the words "first", "second", "third", and "fourth", "primary", "secondary", "tertiary", etc., here and elsewhere, is for labeling purposes only and is not intended to indicate any particular spatial or temporal order. Furthermore, the labeling of a first element does not imply the presence of a second element, and vice versa.

[0109] Understandably, Figure 1-Figure 2 Some circuits or operations shown with solid lines and some circuits or operations shown with dotted lines are included. The circuits or operations included in the solid lines are the circuits or operations included in the most extensive example embodiments. The circuits or operations included in the dotted lines are exemplary embodiments, which may be included in or part of or be the other circuits or operations that can be adopted in addition to the circuits or operations of the solid line exemplary embodiments. It should be understood that these operations do not need to be performed in the order presented. In addition, it should be understood that not all operations need to be performed. The exemplary operations can be performed in any order and in any combination.

[0110] It should be noted that the word "comprising" does not necessarily exclude the presence of other elements or steps than those listed.

[0111] It should be noted that the word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements.

[0112] It should also be noted that any reference signs do not limit the scope of the claims, that exemplary embodiments may be implemented at least in part by both hardware and software, and that several "means," "units," or "devices" may be represented by the same item of hardware.

[0113] The various exemplary methods, devices, nodes, and systems described herein are described in the general context of method steps or processes, which in one aspect may be implemented by a computer program product embodied in a computer-readable medium (including computer-executable instructions, such as program code, executed by a computer in a network environment). Computer-readable media may include removable and non-removable storage devices, including but not limited to read-only memory (ROM), random access memory (RAM), compact disk (CD), digital versatile disk (DVD), etc. In general, program circuits may include routines, programs, objects, components, data structures, etc. that perform specified tasks or implement specific abstract data types. Computer executable instructions, associated data structures, and program circuits represent examples of program codes for performing the steps of the methods disclosed herein. A specific sequence of such executable instructions or associated data structures represents an example of corresponding actions for implementing the functions described in such steps or processes.

[0114] Although features have been shown and described, it will be understood that they are not intended to limit the claimed disclosure, and it will be apparent to those skilled in the art that various changes and modifications may be made without departing from the scope of the claimed disclosure. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. The claimed disclosure is intended to cover all alternatives, modifications, and equivalents.

Claims

1. A method for handling shipping of a container performed by an electronic device, the method comprising: Acquiring (S102) historical data associated with container shipping; determining (S104) a container usage pattern associated with the container based on the historical data; generating ( S106 ) an extension package characterized by package data associated with the container shipping based on the container usage pattern, wherein the package data includes an extension parameter indicating a time period for extending the return time of the container and a fee parameter associated with the extension parameter; For one or more deferred packages among the plurality of deferred packages, predicting ( S108 ) a selection parameter indicating a likelihood of selecting the corresponding deferred package by applying the machine learning model to the historical data and the previous package data; determining (S110) extension cost data associated with the deferral of the container shipping based on the selection parameters for the one or more deferral packages; and Updated package data associated with the extended package is provided (S112) based on the extended fee data.

2. The method according to claim 1, wherein: Generating (S106) the extension package based on the container usage pattern includes generating (S106A) package data indicating the extension package based on the container usage pattern.

3. A method according to any one of the preceding claims, wherein: Generating (S106) the extension package based on the container usage pattern includes: - Generating (S106B) the plurality of extension packages based on the container usage pattern, wherein each extension package is characterized by corresponding package data.

4. A method according to any one of the preceding claims, wherein: Generating (S106) the extension package based on the container usage pattern includes: - For each deferral package, based on the container usage pattern, generating (S106C) a corresponding deferral parameter and a corresponding fee parameter associated with each deferral package.

5. A method according to any one of the preceding claims, wherein: The delay parameters include the time period.

6. The method according to any one of claims 4 to 5, wherein: For each extension package, based on the container usage pattern, generating (S106C) corresponding extension parameters and corresponding fee parameters associated with each extension package includes: determining (S106CA) a first fee parameter associated with a first deferred package of the plurality of deferred packages, and Based on the first fee parameter and the difference parameter, the second fee parameter is determined (S106CB) by maintaining a difference parameter between the first fee parameter and a second fee parameter associated with a second deferred package of the plurality of deferred packages.

7. A method according to any one of the preceding claims, wherein: Predicting (S108) the selection parameter by applying the machine learning model to the historical data and the previous package data includes: - for the one or more deferred packages, determining (S108A) a first change parameter indicating a change of the cost parameter of the package data and a second change parameter indicating a corresponding change of a corresponding selection parameter based on the historical data and the previous package data.

8. The method according to claim 7, wherein: Predicting (S108) the selection parameter by applying the machine learning model to the historical data and the previous package data includes: -Training (S108B) the machine learning model based on the first change parameter and the second change parameter.

9. A method according to any one of the preceding claims, wherein: The machine learning model includes a linear regression model.

10. A method according to any one of the preceding claims, wherein: Predicting (S108) the selection parameter by applying the machine learning model to the historical data and the previous package data includes: - for the one or more deferred packages, determining (S108C) a third change parameter indicating a change of the cost parameter of the package data relative to a current fixed cost of a deferred package; and - Using the trained machine learning model to predict (S108D) a fourth change parameter indicating a change in the selection parameter for each cost parameter of the package data.

11. A method according to any one of the preceding claims, wherein: Determining (S110) the extension cost data associated with the extension of the container shipping based on the selection parameters for each extension package includes: - performing (S110A) simulation on the extension fee data of the package data of each extension package based on the selection parameters for each extension package; and - generating (S110B) the extension fee data based on the simulated extension fee data.

12. The method according to claim 11, wherein: The simulation is a Monte Carlo simulation configured to randomize the selection proportions of each extension package.

13. The method according to any one of claims 11 to 12, wherein: Performing (S110A) the simulation includes generating demurrage and detention cost data indicating demurrage and detention costs for the container for each deferral package.

14. The method according to claim 13, wherein: The extension fee data includes the demurrage and detention fee data.

15. A method according to any one of the preceding claims, wherein: Determining (S104) a container usage pattern associated with the container based on the historical data includes: - determining (S104A) one or more container usage parameters based on said historical data; and - determining (S104B) a container usage pattern associated with said container based on said one or more container usage parameters.

16. A method according to any one of the preceding claims, wherein: The one or more container usage parameters include one or more of the following: - a ratio parameter indicating the ratio of users who select the corresponding extension package, - average delay in returning said container, average turnaround time in returning said container, - one or more rate parameters indicating the rate for the respective container size and / or country, - one or more extension days for the respective container size and / or country, - a statistical rate parameter indicating the rate for the corresponding container size and / or country, and - Statistics extension day for corresponding container size and / or country.

17. A method according to any one of the preceding claims, wherein: Providing (S112) the updated package data based on the extension fee data includes providing (S112A) the updated package data based on the maximum extension fee of the extension fee data.

18. An electronic device comprising a memory, an interface and a processor, the electronic device being configured to execute any one of the methods according to any one of claims 1-17.

19. A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device cause the electronic device to perform any one of the methods according to claims 1-17.

Images