Method for predicting turnover time of container

Abstract

A method performed by an electronic device for predicting a turnover time of a container is disclosed. The method includes obtaining shipping data associated with shipping of one or more containers. The method includes generating a turnaround time parameter indicative of a turnaround time of the container by applying a predictive model to the shipping data based on the shipping data. The method includes providing an output based on the turnaround time parameter.

Description

[0001] The present disclosure relates to the field of transportation and freight. The present disclosure relates to a method for predicting turnaround time of a container and related electronic devices. BACKGROUND

[0002] Shipping of a container involves arrival of the container at a port and / or subsequent departure from the port. During shipping, many actions related to the container are performed, such as unloading and loading the container on a ship and / or other means of transportation, searching for the container, and / or obtaining documents associated with the container. The time required to perform the various operations can vary greatly and depends on many variables. SUMMARY

[0003] The time period between the time at which a container arrives at a terminal in order to be unloaded from a ship and the time at which the container returns to the terminal (e.g., after the container has been emptied of items to be shipped to a recipient) can be considered turnaround time. Turnaround time can be influenced by many factors. There is a need for an electronic device and method that can provide a prediction of turnaround time of a container (e.g., turnaround time of a container at a port).

[0004] Accordingly, there is a need for an electronic device and method for predicting turnaround time of a container that mitigates, alleviates, or solves existing disadvantages and can allow for more accurate, more robust, and more time-efficient prediction of turnaround time of a container.

[0005] A method performed by an electronic device for predicting turnaround time of a container is disclosed. The method includes obtaining shipping data associated with shipping of one or more containers. The method includes generating, based on the shipping data, a turnaround time parameter indicative of turnaround time of the container by applying a prediction model to the shipping data. The method includes providing an output based on the turnaround time parameter.

[0006] An electronic device is disclosed that includes memory circuitry, processor circuitry, and an interface, wherein the electronic device is configured to perform any of the methods according to the methods disclosed herein.

[0007] A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by an electronic device with a display and a touch-sensitive surface, cause the electronic device to perform any of the methods disclosed herein.

[0008] The advantage of this disclosure is that the disclosed electronic devices and methods provide more accurate, robust, and time-efficient predictions of container turnaround times. This can lead to improved efficiency across various operations. For example, turnaround time estimates can be provided to consignees that take into account the return of empty containers to the terminal and mitigate the risks of unforeseen operations (such as unforeseen additional time and / or associated costs due to, for example, demurrage, or delays). This can lead to improved container resource management, which in turn can result in shipping success and thereby reduce the number of complaints. Attached Figure Description

[0009] The above and other features and advantages of this disclosure will be readily apparent to those skilled in the art from the following detailed description of exemplary embodiments with reference to the accompanying drawings, in which:

[0010] Figure 1A -B is a flowchart illustrating an exemplary method for predicting container turnaround time performed by an electronic device according to the present disclosure.

[0011] Figure 2 This is a block diagram illustrating an exemplary electronic device according to the present disclosure, and

[0012] Figure 3A -C is an example representation of the example output of the disclosed technology. Detailed Implementation

[0013] Various exemplary embodiments and details are described below with reference to the accompanying drawings, where applicable. It should be noted that the drawings may be drawn to scale or not, and elements with similar structure or function are indicated by the same reference numerals in all the drawings. It should also be noted that the drawings are intended only to facilitate the description of embodiments. The drawings are not intended as an exhaustive description of this disclosure or a limitation on the scope of this disclosure. Furthermore, the illustrated embodiments need not possess all the aspects or advantages shown. Aspects or advantages described in connection with a particular embodiment are not necessarily limited to that embodiment and can be practiced in any other embodiment, even if not so shown or explicitly described.

[0014] For clarity, the accompanying drawings are schematic and simplified, and only details that aid in understanding this disclosure are shown, while other details are omitted. Throughout, the same reference numerals are used for the same or corresponding parts.

[0015] During the importation of a container, the consignee is the party that receives a full container and returns an empty one. The consignee can be considered the recipient of the shipped container. In other words, the consignee can be considered the party responsible for receiving the goods (e.g., articles) within the container. The shipper can be considered the transporter of the container (e.g., the carrier). For example, the shipper can transport the container (e.g., containing goods) on behalf of the consignee.

[0016] Consignees can opt for time extensions (such as free time extensions) when booking container shipping to allow more time for loading and / or unloading. This helps consignees and / or shippers mitigate the risks of costly operations, such as demurrage and detention charges (D&D) that apply when a consignee holds carrier equipment at the terminal for longer than the agreed-upon time. However, consignees cannot mitigate the risks of unforeseen time extensions (e.g., D&D). This leads to operational inefficiencies and a lack of transparency and / or robustness in operations and services. This can result in disputes, lost revenue, and ultimately, consignee dissatisfaction.

[0017] This disclosure specifically proposes predicting container turnaround time, allowing consignees extended time to allocate and choose when booking container shipping. This can reduce the risks of unforeseen operations, associated time, and costs.

[0018] Turnover time can be considered as the time period from the arrival of a loaded container (e.g., a container containing goods) at the port to the return of an unloaded container (e.g., a container excluding goods, such as an empty container and / or a partially empty container) to the port. For example, the time between the arrival of a container at the terminal for unloading from the vessel and the time between the container returning to the terminal (e.g., after the container has been emptied of its contents destined for the recipient) can be considered turnover time. In some examples, turnover time includes only dwell time. For example, turnover time can be considered as the time between the departure of a container from the terminal for delivery to the recipient and the time between the container returning to the terminal (e.g., after the container has been emptied of its contents destined for the recipient). Forecasts of turnover time can be based on one or more factors, such as the given goods to be transported, the given port involved, and / or the consignee.

[0019] The goods disclosed herein can be considered as objects and / or articles to be placed in containers for transport. For example, goods can be considered as cargo articles, such as freight articles, such as objects to be shipped. For example, goods can be considered as articles that can be loaded into containers. It should be noted that in some examples, the term "goods" can be used interchangeably with the term "cargo." For example, goods can include articles that can be placed in containers, such as cargo. For example, cargo can include materials such as petroleum, crude oil, raw materials, timber, industrial raw materials, plants (such as fruits and vegetables, seeds, beans), food (such as tea, coffee), fertilizers, paper, metals, chemicals, vehicles, fossil fuels, stone, tiles, glass, plastics, and rubber. For example, cargo can include consumer goods manufactured by companies, such as shoes, clothing, toys, and other general consumer goods, as well as fast-moving consumer goods such as packaged foods, beverages, cosmetics, and pharmaceuticals. Examples of goods include rectangular stackable cartons with variable weight and volume transported in one or more dry containers.

[0020] The container disclosed herein can be considered as a shell used to enclose goods for transport. For example, a container can be considered as a box. In this disclosure, the term container may be used interchangeably with box.

[0021] The time extensions disclosed herein can be considered as additional time periods (e.g., days, hours) required to return a container to the port. Time extensions can be selected at the time of booking and will not incur additional charges after booking. This time extension may be referred to as a free time extension. The time extension can vary depending on the goods in the container, the consignee associated with the container, the container's attributes (e.g., container type and / or size), port location, booking type, container type, etc. In some examples, the granted time extension can be considered as additional time for the container to be stored at the port. In some examples, the time extension may be granted by the competent authority associated with the port. In some examples, the time extension period may be extended. For example, time extensions can be selected for one or more containers (e.g., selected by the consignee).

[0022] In some examples, containers may be assigned to allocated container space within a terminal and / or port. To deliver the contents of the container to the recipient and / or destination (e.g., a warehouse), the container may be transported (e.g., unloaded) to a location outside the terminal and / or port. In some examples, failure to remove the container from the terminal and / or port (e.g., the allocated container space) before the time extension expires may result in additional operations (e.g., additional charges to the consignee). The time consumed by the container at the terminal and / or port can be considered demurrage time.

[0023] In some examples, detention can be considered as the time a container is held / retained by the container consignee outside the terminal and / or port. In some examples, costs incurred due to detention may be incurred when a container is not returned to the terminal and / or port before the time limit expires.

[0024] The turnaround times disclosed herein may include demurrage turnaround time and / or dwell turnaround time. Demurrage turnaround time is, for example, the time from the arrival of a container at a terminal and / or port to the collection of the container from the terminal and / or port for transport to the recipient and / or destination (e.g., unloading at least a portion of the container). Dwell turnaround time is, for example, the time from the collection of a container from a terminal and / or port (e.g., unloading) until the container is returned to the terminal and / or port (e.g., after unloading). For example, the returned container may contain fewer items than before it was transported from the terminal and / or port to the recipient. In some examples, the returned container may be empty.

[0025] The turnaround time parameters disclosed herein can be considered as parameters indicating turnaround time. For example, turnaround time parameters may include values ​​(e.g., integers, decimals, percentages, etc.) indicating the turnaround time of containers.

[0026] Figure 1 illustrates an exemplary system 1 according to the present disclosure, which includes an example method 100 performed by an electronic device for predicting the turnaround time of a container. Method 100 can be performed to predict turnaround time parameters associated with the container. Method 100 is performed by an electronic device, such as those disclosed herein, such as… Figure 2 Electronic device 300.

[0027] Method 100 includes obtaining, in S102, shipping data associated with the shipping of one or more containers. In one or more examples, the shipping of one or more containers can be considered as shipping (e.g., transportation) comprising one or more containers of one or more items. The shipping data includes information associated with the shipping of one or more items contained in one or more containers. In some examples, the shipping data includes information associated with containers. For example, the shipping data includes information associated with the shipping of one or more containers. For example, the shipping data includes data elements.

[0028] In some examples, acquiring shipping data includes preprocessing the shipping data, such as extracting and / or transforming it. In some examples, acquiring shipping data includes receiving and / or retrieving shipping data from storage media, such as one or more databases storing the shipping data. In some examples, acquiring shipping data includes receiving data from electronic devices (e.g., Figure 2The electronic device 300) acquires shipping data from its memory. In some examples, acquiring shipping data includes obtaining (e.g., receiving) shipping data from one or more external servers.

[0029] In one or more example methods, shipping data includes one or more of the following: time extension data associated with container time extension, transaction data associated with one or more transactions, container movement data associated with the movement of one or more containers, commodity data associated with one or more commodities, consignee data associated with one or more consignees, container data associated with one or more containers, booking data associated with one or more shipping bookings, port data associated with one or more shipping ports, turnaround time data, and historical shipping data.

[0030] Time extension data can be associated with the shipping of one or more containers. In some examples, time extension data includes information indicating the available (e.g., purchased), granted, and / or used (e.g., consumed) time extensions.

[0031] In some examples, transaction data includes information associated with one or more transactions linked to a consignee. For instance, transaction data may indicate the number of transactions, such as the number of shipments associated with a consignee (e.g., the number of shipments per port, per container type, per booking type). In other words, transaction data may include information indicating the number of transactions for each consignee (e.g., the number of transactions between a specific shipper and a specific consignee).

[0032] In some examples, container movement data includes information indicating the movement of containers. In some examples, container movement data includes time data associated with one or more events (e.g., container arrival) related to the shipping of one or more containers. For example, container movement data includes information indicating the arrival date, unloading date, and / or return date associated with the shipping of one or more containers.

[0033] In some examples, commodity data includes information indicating the type and / or category of goods associated with a shipment of one or more containers. For example, when the goods are paper, the commodity data includes information indicating that the goods are paper.

[0034] Consignee data may include information indicating the consignee associated with the shipping of one or more containers. For example, consignee data may include a consignee identifier, consignee status, and one or more parameters indicating the past dwell time of the consignee (e.g., each port and / or each commodity).

[0035] In some examples, container data includes information indicating the size and / or type of the container. For example, container data includes information indicating the volume of the container. For example, container data may indicate that the container is a 20-foot (such as 20 cubic feet) or 40-foot (such as 40 cubic feet) container.

[0036] In some examples, booking data includes information associated with bookings for one or more containers. For instance, booking data includes information indicating the type of booking associated with the shipment of one or more containers. For example, the booking type could be a temporary booking (e.g., on-site booking) and / or a contractual booking (e.g., the booking may be part of a contract). For example, on-site bookings can be made online (e.g., as an online service).

[0037] Port data can include information indicating the port associated with a container. A port can be considered a facility that transfers cargo containers between different transport vehicles for continued transport. The term "port" can be used interchangeably with the term "terminal." For example, port data can indicate the port associated with the shipping of one or more containers. For example, port data can include information indicating the port's geographical location. In some examples, port data can include information indicating the port's size, information about port capacity, and information about demurrage statistics.

[0038] Turnover time data may include information associated with one or more turnover time parameters for one or more shipments. For example, turnover time data may include one or more turnover time parameters for each booking type, each container type (e.g., attributes, size, and / or volume), each port, and / or each commodity. In some examples, turnover time data includes information indicating the turnover time of a shipment. In some examples, turnover time data includes one or more turnover time parameters (e.g., the current turnover time parameter).

[0039] In some examples, shipping data includes historical shipping data. For example, historical shipping data is associated with the shipping of one or more containers. Historical shipping data can be considered as previous (e.g., past) shipping data. In one or more example methods, historical shipping data includes one or more of the following: historical time extension data associated with container time extension, historical transaction data associated with one or more transactions, historical container movement data associated with the movement of one or more containers, historical commodity data associated with one or more commodities, historical consignee data associated with one or more consignees, historical container data associated with one or more containers, historical booking data associated with one or more shipping bookings, historical port data associated with one or more shipping ports, and historical turnaround time data.

[0040] In some examples, obtaining historical shipping data includes data from electronic devices (e.g., Figure 2 The electronic device 300 retrieves historical shipping data from its memory. In some examples, retrieving shipping data includes obtaining (e.g., receiving and / or retrieving) shipping data from one or more external servers (e.g., databases and / or warehouses).

[0041] In some examples, historical turnaround time data may include historical information associated with one or more shipping operations. In some examples, historical turnaround time data includes previous (e.g., past) turnaround time parameters. In some examples, historical turnaround time data includes historical average turnaround time.

[0042] In some examples, historical time extension data includes information indicating the availability (e.g., purchase), grant, and / or use (e.g., consumption) of historical time extensions. For example, historical time extensions can be viewed as historical time extensions.

[0043] Method 100 includes generating (e.g., predicting) a turnaround time parameter S112, indicating the turnaround time of containers, based on shipping data by applying a predictive model S112A to the shipping data. In some examples, the turnaround time parameter indicates the turnaround time of one or more containers in a shipment. In some examples, the turnaround time parameter includes a value indicating the turnaround time of containers and expressed in, for example, a unit of time (e.g., an integer, a decimal, etc.). In some examples, the turnaround time parameter may be considered as an estimate and / or prediction of the turnaround time of a shipment (e.g., of containers).

[0044] In some examples, the turnaround time parameter is generated based on one or more of the following: time extension data associated with container time extension, transaction data associated with one or more transactions, container movement data associated with the movement of one or more containers, commodity data associated with one or more goods, consignee data associated with one or more consignees, container data associated with one or more containers, booking data associated with one or more shipping bookings, port data associated with one or more shipping ports, turnaround time data, and historical shipping data. In other words, in some examples, the predictive model is applied to one or more of the following: time extension data associated with container time extension, transaction data associated with one or more transactions, container movement data associated with the movement of one or more containers, commodity data associated with one or more goods, consignee data associated with one or more consignees, container data associated with one or more containers, booking data associated with one or more shipping bookings, port data associated with one or more shipping ports, turnaround time data, and historical shipping data.

[0045] In one or more example methods, applying the S112A predictive model includes applying one or more machine learning techniques and / or forecasting techniques to shipping data. In one or more example methods, the predictive model is a machine learning model. For example, the predictive model may be configured to perform one or more machine learning techniques. In one or more example methods, the one or more machine learning techniques include one or more of the following: linear regression models, random forest models, decision tree-based models, and ensemble models.

[0046] Linear regression can be viewed as a model that characterizes the relationship between the turnaround time parameter and at least one element of the shipping data by fitting a linear equation to the acquired shipping data, and can be used to predict the value of the turnaround time parameter based on at least one element of the shipping data.

[0047] Random forests can be viewed as an ensemble learning method for classification, regression, and other tasks, which operates by building an ensemble of decision trees based on shipping data. For example, shipping data may be affected by data bagging and feature randomness in order to build each individual tree to predict turnaround time parameters.

[0048] In one or more example methods, the predictive model can be configured to perform one or more prediction techniques. In one or more example methods, the prediction technique includes time series prediction techniques. For example, the prediction technique includes an Autoregressive Integrated Moving Average (ARIMA) model. In some examples, the prediction technique includes an Autoregressive Integrated Moving Average (ARIMAX) model with explanatory variables. In some examples, the prediction technique includes a Seasonal Autoregressive Integrated Moving Average (SARIMAX) model with exogenous factors.

[0049] Method 100 includes providing an output S114 based on a turnaround time parameter. In some examples, the output includes information (e.g., one or more values) indicating the container's turnaround time (e.g., the predicted turnaround time). For example, the output indicates a container turnaround time parameter. In some examples, the output can be provided for further processing (e.g., for further calculations). In some examples, the output is a time extension parameter calculated based on the turnaround time parameter. In some examples, providing the output based on the turnaround time parameter includes determining the time extension parameter based on the turnaround time parameter. In some examples, it can be done via an interface (e.g., Figures 3A to 3C Output is provided to a user interface (e.g., to a user and / or recipient). For example, output can be provided (e.g., displayed) to a user (e.g., a recipient) via a user interface (UI). The UI can be provided by... Figure 3AThe interface shown in -C is provided. For example, the UI indicates (e.g., represents) the container turnaround time parameter.

[0050] In one or more example methods, method 100 includes generating a commodity risk factor S104 for at least one commodity based on shipping data. In some examples, generating a commodity risk factor for at least one commodity includes generating a commodity risk factor for each of a plurality of commodities. In some examples, the commodity risk factor is associated with at least one commodity and the port involved in the shipping. The port involved in the shipping is, for example, the port of arrival of the container (e.g., the port of arrival of the container shipment). The risk factor (e.g., the commodity risk factor) may be expressed as a unit of time (e.g., a day, 15 hours, 400 minutes, etc.). In some examples, the risk factor may be expressed as a coefficient. The commodity risk factor includes, for example, a value (e.g., an integer and / or a real number). In other words, the commodity risk factor may include a value indicating a time period.

[0051] In one or more example methods, generating the S104 commodity risk factor includes calculating one or more commodity distribution parameters for S104A for at least one commodity (e.g., for each commodity) based on shipping data. In one or more example methods, the one or more commodity distribution parameters for at least one commodity indicate a distribution of at least one of the following for at least one commodity (e.g., for each commodity): container return delays for at least one commodity, the ratio of elapsed time extension to granted shipping time extension for at least one commodity, and the ratio of elapsed time extension to available shipping time extension for at least one commodity.

[0052] In some examples, time extensions can be considered as free time extensions. One or more commodity distribution parameters are associated, for example, with the shipment of one or more containers. One or more commodity distribution parameters are, for example, values ​​associated with the commodities shipped (e.g., integers, fractions, percentages, etc.). One or more commodity parameters are generated, for example, based on historical data (e.g., N years of historical data, where N is a positive integer). One or more commodity distribution parameters are generated, for example, by booking type and / or by port.

[0053] For example, a return delay of a container for at least one commodity could indicate that the consignee did not return one or more containers (e.g., empty containers or properly empty containers) after removing the goods. In some examples, the return delay of a container for at least one commodity could be the percentile of delayed container returns for each commodity and / or the average delay of containers associated with at least one commodity (e.g., each commodity). For example, S104A, calculated based on shipping data, includes calculating the percentile of delayed container returns (e.g., empty containers returning to port) for each commodity based on historical data.

[0054] The ratio of the elapsed time extension to the granted time extension for the shipment of at least one commodity can, for example, be regarded as an indication of the ratio (e.g., percentage) of the time extension consumed for a given commodity relative to the granted time extension. The elapsed time extension can be a value indicating the time elapsed for the granted time extension of a container. The granted time extension is, for example, a value indicating the total amount of the granted time extension for a container. For example, the ratio of the elapsed time extension to the granted time extension can indicate how much time extension has been consumed for a given commodity.

[0055] In some examples, the ratio of used time extension to available time extension for the shipment of at least one good (e.g., each good) can be viewed as a ratio (e.g., percentage) of the proportion of time extension purchased (e.g., by the consignee) for at least one good (e.g., each good). Available time extension can, for example, be viewed as the amount of time extension purchased for one or more containers (e.g., for a particular shipment and / or port). For example, the ratio of used time extension to available time extension for the shipment of at least one good (e.g., each good) indicates how much time extension was actually used by the user or consignee.

[0056] In one or more example methods, generating the S104 commodity risk factor (e.g., for each commodity and a given port) involves generating the S104B commodity risk factor based on one or more commodity distribution parameters (e.g., for each commodity). In one or more example methods, generating the S104 commodity risk factor involves applying a normalization function (S103) to one or more commodity distribution parameters and / or one or more consignee distribution parameters (e.g., for each commodity). In some examples, the normalization function provides an output ranging from 0 to 1. In one or more example methods, the normalization function is a sigmoid function. In one or more example methods, the normalization function is a tanh normalization function and / or a rectified linear unit (ReLU) function. In some examples, generating the S104 commodity risk factor involves generating a commodity risk factor associated with a port. For example, each port may be associated with a corresponding commodity risk factor. In one or more example methods, generating the S104 commodity risk factor involves applying a normalization function (S103) to one or more commodity distribution parameters.

[0057] In one or more example methods, method 100 includes grouping consignees S106 into: a first primary consignee group comprising consignees present in the turnaround time system of the electronic device; and a first secondary consignee group comprising consignees not present in the turnaround time system. For example, the first primary consignee group may include one or more existing consignees. For example, the first secondary consignee group may include one or more new consignees.

[0058] A turnaround time system can be viewed as a system configured to perform the methods disclosed herein. Electronic devices (e.g., Figure 2 The electronic device 300 can be configured to execute a turnaround time system.

[0059] In some examples, the first primary consignee group includes consignees associated with the turnaround time system. For example, the first primary consignee group includes consignees already associated with historical shipping data (e.g., stored in...). Figure 2 The first primary consignee group can be considered to include existing consignees (e.g., those already existing on the turnaround time system). In some examples, the first primary consignee group includes consignees unrelated to shipping on the turnaround time system. For example, the first primary consignee group includes consignees associated with historical shipping data (e.g., stored in memory 301). Figure 2 (In memory 301) unrelated consignees. In other words, the first-level consignee group can be considered to include new consignees (e.g., those not existing in the turnaround time system).

[0060] In one or more example methods, method 100 includes generating S108 consignee risk factors for at least one consignee based on shipping data.

[0061] Consignee risk factors can be expressed as time units (e.g., 1 day, 15 hours, 400 minutes, etc.). In some examples, consignee risk factors can be expressed as coefficients. Consignee risk factors include, for example, values ​​(e.g., integers and / or real numbers). In other words, consignee risk factors can include values ​​indicating a time period. In some examples, generating consignee risk factors based on shipping data includes generating consignee risk factors for each of the multiple consignees in a first primary consignee group based on shipping data.

[0062] In one or more example methods, generating S108 consignee risk factors based on shipping data includes calculating one or more consignee distribution parameters for at least one consignee under S108A based on shipping data. In one or more example methods, the one or more consignee distribution parameters for at least one consignee indicate a distribution for at least one consignee of at least one of the following: the proportion of delayed containers for at least one consignee, the ratio of elapsed time extension to granted shipping time extension for at least one consignee, and the ratio of elapsed time extension to available shipping time extension for at least one consignee. In some examples, the one or more consignee distribution parameters are calculated based on one or more of the following (e.g., for each consignee): time extension data associated with container time extensions, transaction data associated with one or more transactions, container movement data associated with the movement of one or more containers, commodity data associated with one or more commodities, consignee data associated with one or more consignees, container data associated with one or more containers, booking data associated with one or more shipping bookings, port data associated with one or more shipping ports, turnaround time data, and historical shipping data.

[0063] Consignee risk factors are generated, for example, according to S108 for existing consignees (such as consignees in the first primary consignee group).

[0064] One or more consignee distribution parameters are associated, for example, with the shipping of one or more containers. One or more consignee distribution parameters are, for example, values ​​associated with the consignees of the shipping (e.g., integers, fractions, percentages, percentiles, etc.).

[0065] The proportion of delayed containers for at least one consignee can indicate that the consignee did not return one or more containers after removing the goods. In some examples, for at least one consignee, the container return delay can be the average delay of containers associated with that consignee. For example, the method includes calculating the percentile (e.g., proportion) of delayed container returns (e.g., empty containers returning to port) for each type of commodity based on historical data.

[0066] The ratio of the time extension used to the time extension granted to at least one consignee's shipment can be regarded as a ratio (e.g., percentage and / or percentile) indicating the proportion of time extension used by the consignee to the time extension purchased.

[0067] The ratio of the time extension used to the available time extension for at least one consignee's shipment can be viewed as a ratio (e.g., percentage and / or percentile) indicating the proportion of the time extension used by at least one consignee to the time extension purchased by (e.g., the consignee). In some examples, the available time extension can be viewed as an optional time extension. In other words, the available time extension can be viewed as, for example, additional time for the container that can be purchased by the consignee.

[0068] In one or more example methods, generating the S108 consignee risk factor based on shipping data includes generating the S108B consignee risk factor based on one or more consignee distribution parameters. In one or more example methods, generating the S108 consignee risk factor includes applying a normalization function (S103) to one or more commodity distribution parameters and / or one or more consignee distribution parameters.

[0069] In one or more example methods, generating the S108 consignee risk factors involves applying a standardized function to one or more consignee distribution parameters using S103.

[0070] In one or more example methods, method 100 includes generating a seasonality factor S110 indicating the seasonality of the turnaround time parameter at a port based on shipping data. In some examples, the method includes generating a seasonality factor based on shipping data that indicates the seasonality of the turnaround time parameter at a port and / or the seasonality of container type (e.g., attributes (e.g., dry bulk, refrigerated, insured), size and / or volume) and / or commodity. In one or more example methods, generating a seasonality factor indicating the seasonality of the turnaround time parameter at a port based on shipping data includes applying one or more forecasting techniques. In one or more examples, the seasonality factor is generated based on one or more of the following: time extension data associated with container time extension, transaction data associated with one or more transactions, container movement data associated with the movement of one or more containers, commodity data associated with one or more commodities, consignee data associated with one or more consignees, container data associated with one or more containers, booking data associated with one or more shipping bookings, port data associated with one or more shipping ports, turnaround time data, and historical shipping data. In one or more examples, the seasonality factor is generated based on transaction data associated with one or more transactions.

[0071] In some examples, the method includes generating seasonality factors that indicate the seasonality of turnaround time parameters at ports based on historical shipping data. In some examples, seasonality can be viewed as a characteristic of a time series, where the data undergoes regular and predictable changes (e.g., patterns) that are likely to repeat over a period of time, such as each calendar year. For example, seasonality can be viewed as a seasonal pattern associated with a dataset (e.g., a time series). Seasonal factors can be values ​​(e.g., decimals, fractions, integers) that are seasonally associated with turnaround time parameters at ports. For example, seasonal factors can be values ​​that indicate a time period (e.g., 1 day, 0 days).

[0072] In one or more example methods, generating the seasonality factor S110 based on shipping data includes classifying consignees S110A into a second primary consignee group and a second secondary consignee group based on shipping data (e.g., at least based on consignee data and / or transaction data). In some examples, based on historical shipping data (e.g., historical transaction data and / or historical consignee data, such as the number of transactions per consignee), the seasonality factor includes classifying consignees into a second primary consignee group and a second secondary consignee group based on shipping data. In other words, generating the seasonality factor includes classifying consignees into a second primary consignee group and a second secondary consignee group based on shipping data.

[0073] In some examples, classifying recipients into a second primary recipient group and a second secondary recipient group involves determining whether the number of transactions (e.g., shipping) associated with the recipient meets a criterion. For example, the first criterion is based on a first threshold. A threshold is, for example, a value (e.g., an integer, a real number, etc.). Thresholds are, for example, 10, 20, 30, 40, 100, 200, 400. For example, thresholds are between 20 and 80, 30 and 70, and / or 40 and 60. In some examples, the threshold is 50. For example, recipients associated with more than 50 transactions (e.g., recipients in a turnaround time system) are grouped (e.g., classified) into the second primary recipient group. For example, recipients associated with fewer than 50 transactions (e.g., recipients in a turnaround time system) are grouped (e.g., classified) into the second secondary recipient group.

[0074] The second primary consignee group includes consignees who meet the criteria for being associated with a number of shipments exceeding a threshold (e.g., transactions between consignees and shippers). For example, the second primary consignee group includes consignees associated with more than 50 transactions. Consignees grouped into the second primary consignee group can be considered large consignees.

[0075] The second-level consignee group includes consignees associated with a number of shipments equal to or less than a threshold (e.g., transactions between the consignee and the shipper), thus failing to meet the criteria. For example, the second primary consignee group includes consignees associated with fewer than 50 transactions. Consignees grouped into the second-level consignee group can be considered small consignees.

[0076] In some examples, whether the number of transactions for each recipient (e.g., obtained from historical transaction data associated with the recipient) meets the criterion depends on whether the number of transactions for each recipient is greater than or less than a threshold. For example, when the number of transactions for each recipient is greater than the threshold, the number of transactions for each recipient can be considered to meet the criterion. Conversely, when the number of transactions for each recipient is less than the threshold, the number of transactions associated with the recipient can be considered not to meet the criterion.

[0077] For example, classifying consignees into a second primary consignee group and a second secondary consignee group based on shipping data includes grouping consignees into the second primary consignee group based on meeting certain criteria. Conversely, classifying consignees into a second primary consignee group and a second secondary consignee group based on shipping data includes grouping consignees into the second secondary consignee group based on not meeting certain criteria.

[0078] In one or more example methods, generating the S110 seasonality factor based on shipping data includes obtaining a first seasonal value at the current time for S110B associated with container and port turnaround time parameters for one or more consignees in the second primary consignee group. The first seasonal value, for example, indicates the seasonality of container and port turnaround times. In some examples, the first seasonal value is a number (e.g., an integer). For example, the first seasonal value could be a number between 0 and 1. In some examples, a first seasonal value of 1 (or close to 1) could indicate high seasonality. In some examples, a first seasonal value of 0 (or close to 0) could indicate low seasonality. In some examples, the method may include omitting the acquisition of first seasonal values ​​for consignees in the second-level consignee group because they are associated with a lack of shipping data.

[0079] In some examples, the first seasonal value can be considered as 0 (e.g., no seasonality) when it is less than a threshold (e.g., 0.5). For example, the first seasonal value can be considered as 1 (e.g., significant seasonality) when it is greater than a threshold (e.g., 0.5).

[0080] In one or more example methods, generating S110 seasonality factors based on shipping data involves determining second seasonal values ​​for S110C in relation to turnaround time parameters and ports for each time period of the year, based on a first seasonal value and a forecasting technique. In some examples, the forecasting technique may be a time-series forecasting technique (e.g., ARIMA, SARIMAX, etc.).

[0081] In one or more example methods, generating the S110 seasonality factor based on shipping data includes assigning a second seasonality value, S110D, to a seasonality factor that indicates a turnaround time parameter for a specific time of the year.

[0082] A specific time of year is, for example, a specific month of that year (e.g., February). For example, seasonal factors indicate the turnaround time parameters for a specific month of that year.

[0083] In one or more example methods, the turnaround time parameter includes a consignee turnaround time parameter associated with the container's consignee. The consignee turnaround time parameter, for example, indicates the turnaround time of the container associated with the consignee. In some examples, the consignee turnaround time parameter is a value indicating the turnaround time of the container associated with the consignee at the port. For example, the consignee turnaround time parameter is a value indicating a time period (e.g., an integer, a decimal). For example, the consignee turnaround time parameter can be expressed as a unit of time (e.g., 1 day, 15 hours, 400 minutes, etc.).

[0084] In one or more example methods, generating the S112 turnaround time parameter based on shipping data includes generating the S112B consignee turnaround time parameter based on shipping data.

[0085] In one or more example methods, generating S112B consignee turnaround time parameters based on shipping data includes generating S112BA model-based consignee turnaround time parameters based on shipping data and at least one of one or more machine learning techniques. In some examples, generating model-based consignee turnaround time parameters includes applying at least one of one or more machine learning techniques to shipping data (e.g., historical shipping data). Model-based consignee turnaround time parameters are, for example, values ​​indicating the turnaround time of containers associated with a consignee at a port. In some examples, model-based consignee turnaround time parameters are generated based on shipping data by applying linear regression models, random forest models, tree-based models, ensemble models, etc. In some examples, model-based consignee turnaround time parameters may be considered as the output of one or more machine learning models. In some examples, one or more machine learning models are based on container type (e.g., 20-foot) and / or booking type (e.g., Spot). In some examples, one or more machine learning techniques may include dynamic autoregressive machine learning techniques.

[0086] Understandably, in some examples, machine learning models are generated for each combination of consignee, goods, and port.

[0087] In one or more example methods, generating the S112BA model-based consignee turnaround time parameter based on shipping data and at least one of one or more machine learning techniques includes generating a set of aggregated data for S112BAA based on historical time extension data and corresponding historical turnaround time data at each port.

[0088] In some examples, the aggregated data includes time extension data (e.g., historical time extension data) and / or turnaround time data (e.g., historical turnaround time data) for each port. In some examples, historical time extension data includes historical information indicating available, granted, and / or used historical time extensions. In some examples, historical turnaround time data includes previous (e.g., past) turnaround time parameters.

[0089] In some examples, generating model-based consignee turnaround time parameters based on shipping data and at least one of one or more machine learning techniques includes generating a set of aggregated data for each container type and / or each booking type based on historical time extension data and corresponding historical turnaround time data at each port. In some examples, at least one of one or more machine learning techniques is associated with the booking type and / or container type.

[0090] In one or more examples, generating model-based consignee turnaround time parameters involves aggregating and / or inputting time extension data, turnaround time data, and / or port data, and applying one or more machine learning models to the aggregated results. For example, time extension data corresponds to port turnaround time data. In one or more examples, generating model-based consignee turnaround time parameters involves aggregating and / or inputting historical time extension data (e.g., the granted time), historical turnaround time data, and / or historical port data, and applying this to one or more machine learning models. For example, historical time extension data corresponds to historical port turnaround time data.

[0091] In one or more example methods, generating the S112BA model-based consignee turnaround time parameter based on shipping data and at least one of one or more machine learning techniques includes applying at least one of one or more machine learning techniques to the aggregated data set.

[0092] In some examples, applying one or more machine learning techniques to this set of aggregated data includes applying machine learning-based regression models for booking type, container type, and / or port. For instance, applying one or more machine learning techniques to this set of aggregated data includes applying machine learning-based regression models for 20-foot SPOT, 40-foot SPOT, 20-foot CONTRACTUAL, and / or 40-foot CONTRACTUAL, where SPOT and CONTRACTUAL are booking types, and where 20-foot and 40-foot are container types. For example, each machine learning-based regression model may be associated with a port.

[0093] In one or more example methods, generating the S112B consignee turnaround time parameter based on shipping data includes generating the S112BB consignee turnaround time parameter based on the model-based consignee turnaround time parameter and one or more of the following: commodity risk factors, consignee risk factors, and seasonal factors. In some examples, the consignee turnaround time parameter is derived based on the model-based consignee turnaround time parameter and one or more of the following: commodity risk factors, consignee risk factors, and seasonal factors. In some examples, generating the consignee turnaround time parameter includes summing one or more of the model-based consignee turnaround time parameter, commodity risk factors, consignee risk factors, and / or seasonal factors. For example, the consignee turnaround time parameter may be associated with the consignee and / or commodity associated with the shipping of the container. The consignee turnaround time parameter can be viewed as a turnaround time forecast, indicating the container turnaround time for a given consignee at the port.

[0094] In one or more example methods, generating the S112 turnaround time parameter based on shipping data includes generating the S112C consignee turnaround time parameter associated with at least one consignee in the first-level consignee group (e.g., a new consignee) based on shipping data.

[0095] In one or more example methods, generating the consignee turnaround time parameter associated with S112C and at least one consignee in the first-level consignee group includes identifying the earliest transaction of at least one consignee of S112CA, such as the earliest transaction of a given consignee. Identifying the earliest transaction of at least one consignee includes, for example, sorting the consignee's transactions (e.g., by time order). In some examples, identifying the earliest transaction of at least one consignee includes identifying one or more goods associated with the earliest transaction.

[0096] In one or more example methods, generating the consignee turnaround time parameter associated with S112C and at least one consignee in the first primary consignee group includes: for the product, determining the consignee turnaround time parameter associated with S112CB and at least one consignee in the first primary group based on the consignee turnaround time parameters of the consignees in the first primary consignee group and the consignees in the first primary consignee group.

[0097] In some examples, generating a recipient turnaround time parameter associated with at least one recipient in the first primary recipient group (e.g., a new recipient) involves averaging the recipient turnaround time parameters for all recipients (e.g., existing recipients) in the first primary recipient group for a given product.

[0098] In some examples, product data may not be available for use by the turnaround time system. For instance, when product data is unavailable, generating a turnaround time parameter associated with at least one recipient in the first primary recipient group (e.g., a new recipient) involves averaging the turnaround time parameter over all products and / or all recipients in the first primary recipient group (e.g., existing recipients).

[0099] In one or more example methods, the turnaround time parameter includes port turnaround time parameters associated with the port. In some examples, the turnaround time parameter includes port turnaround time parameters associated with the port, such as port turnaround time parameters per month, per commodity, and / or per container type (e.g., size and / or volume).

[0100] In some examples, the port turnaround time parameter can indicate the turnaround time of one or more containers in a shipment at the port. In other examples, the port turnaround time parameter can be viewed as a prediction (e.g., an estimate) of the turnaround time of one or more containers in a shipment at the port.

[0101] In one or more example methods, generating S112 turnaround time parameters based on shipping data includes generating S112D port turnaround time parameters based on shipping data by applying estimation techniques to the shipping data.

[0102] In some examples, generating turnaround time parameters based on shipping data includes generating port turnaround time parameters by applying one or more time series forecasting techniques (e.g., ARIMA, SARIMAX, etc.) to the shipping data. In some examples, generating port turnaround time parameters includes applying forecasting techniques (e.g., forecasting models) associated with a specific time period (e.g., month), commodity and / or container type (e.g., attributes, size, and / or volume).

[0103] In one or more example methods, the turnaround time parameter includes a commodity turnaround time parameter associated with (e.g., for a given port) the commodity. In some examples, the turnaround time parameter includes commodity turnaround time parameters associated with the commodity, such as monthly, per commodity, and / or per container type (e.g., attributes, size, and / or volume) commodity turnaround time parameters.

[0104] In some examples, the goods turnaround time parameter can indicate the turnaround time of goods associated with one or more containers in a shipment. In some examples, the goods turnaround time parameter can be viewed as a prediction (e.g., an estimate) of the turnaround time of one or more containers in a shipment associated with a given good.

[0105] In one or more example methods, generating the S112 turnaround time parameter based on shipping data includes generating the S112E commodity turnaround time parameter based on shipping data by applying estimation techniques to the shipping data.

[0106] In some examples, generating turnaround time parameters based on shipping data includes generating commodity turnaround time parameters by applying one or more time series forecasting techniques (e.g., ARIMA, SARIMAX, etc.) to the shipping data. In some examples, generating commodity turnaround time parameters includes applying forecasting techniques (e.g., forecasting models) associated with a specific time period (e.g., month), port (e.g., port location), and / or container type (e.g., attributes, size, and / or volume).

[0107] Figure 2 This is a block diagram illustrating an exemplary electronic device according to the present disclosure. The electronic device 300 includes a memory circuitry 301, a processor circuitry 302, and an interface 303. The electronic device 300 is configured to perform... Figure 1A Any of the methods disclosed in -B. In other words, the electronic device 300 is configured to predict the container turnaround time.

[0108] Electronic device 300 is configured (e.g., via memory circuitry 301 and / or interface 303) to acquire shipping data associated with the shipping of one or more containers.

[0109] Electronic device 300 is configured to generate turnaround time parameters indicating the turnaround time of containers by applying a prediction model to the shipping data (e.g., via processor 302) based on shipping data.

[0110] Electronic device 300 is configured (e.g., via processor 302 and / or interface 303) to provide outputs associated with turnaround time parameters.

[0111] Processor circuit 302 is optionally configured to execute Figure 1A Any of the operations disclosed in -B (such as any one or more of the following: S102, S103, S104, S104A, S104B, S106, S108, S108A, S108B, S110, S110A, S110B, S110C, S110D, S112, S112A, S112AA, S112B, S112BA, S112BAA, S112BAB, S112BB, S112C, S112CA, S112CB, S112D, S112E). The operation of 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 circuitry 301) and executed by processor circuitry 302.

[0112] Furthermore, the operation of electronic device 300 can be considered as a method configured to be performed by electronic device 300. Additionally, while the described functions and operations can be implemented in software, such functions can also be implemented via dedicated hardware or firmware, or some combination of hardware, firmware, and / or software.

[0113] The memory circuit system 301 may be one or more of a buffer, flash memory, hard disk drive, removable media, volatile memory, non-volatile memory, random access memory (RAM), or other suitable devices. In a typical arrangement, the memory circuit system 301 may include non-volatile memory for long-term data storage and volatile memory used as system memory for the processor circuit system 302. The memory circuit system 301 may exchange data with the processor circuit system 302 via a data bus. Control lines and an address bus may also exist between the memory circuit system 301 and the processor circuit system 302. Figure 2 (Not shown in the image). The memory circuitry 301 is considered a non-transitory computer-readable medium.

[0114] The memory circuit system 301 can be configured to store shipping data, historical shipping data, turnaround time parameters, prediction models, commodity risk factors, consignee risk factors, seasonal factors, one or more commodity distribution parameters, one or more consignee distribution parameters, a first primary consignee group, a first secondary consignee group, a second primary consignee group, a second secondary consignee group, seasonal factors, a first seasonal value, and / or a second seasonal value in a portion of the memory.

[0115] Figure 3A -C shows an example representation of the example output of the disclosed technology. Figure 3A A user interface 350 for providing predicted turnaround time parameters for containers, according to this disclosure, is shown, which may be an example output of the disclosed method.

[0116] User interface 350 includes user interface objects that can be switched by the user (e.g., button drop-down menus). For example, the user can switch and / or select the consignee, port, booking type, container attributes (such as container type and / or container size), and / or the granted time extension. As an example, the user can update the container type from 20 to 40 (e.g., 40 feet).

[0117] User interface 350 displays the predicted turnaround time parameters associated with the consignee, port, and goods. User interface 350 includes user interface object 12 representing the consignee turnaround time parameter of the container (e.g., the predicted consignee turnaround time). For example, user interface object 12 shows that the consignee turnaround time parameter (e.g., the predicted consignee turnaround time parameter) is 9 days.

[0118] User interface 350 includes user interface object 14, which represents the port turnaround time parameter for the container (e.g., the predicted port turnaround time parameter). For example, user interface object 14 shows a port turnaround time parameter (e.g., the predicted port turnaround time parameter) of 7 days.

[0119] User interface 350 optionally displays bar graphs representing the predicted product turnover time parameters (in days) for different products. For example, for the product "timber," the bar graph shows a product turnover time parameter (such as the predicted product turnover time parameter) of 8 days.

[0120] Users are provided with turnaround time parameters that reflect the dynamic internal state of the shipping system, and the option to extend the time is supported. For example, users can select a time extension of 6 to 10 days in the user interface 350, which is displayed based on consignee turnaround time parameters, commodity turnaround time parameters, and / or port turnaround time parameters.

[0121] Figure 3BA user interface 400 for guiding the use of extended time is shown.

[0122] User interface 400 includes user interface object 401, which represents a user time extension indicator for the booked container, such as the average time extension for the consignee. For example, user interface object 401 indicates that the time extension can be 6 days when taking the consignee into account.

[0123] User interface 400 may include user interface object 402, which represents the port availability time of the port selected for shipping, such as the average time extension for this port. For example, user interface object 402 indicates that the time extension may be 5 days when taking the port into account.

[0124] User interface 400 may include user interface object 403, which represents the port availability time for the commodity portion of the shipping, such as the average availability time of the port. For example, user interface object 402 indicates that the time extension may be 5 days when taking into account the commodity and / or industry.

[0125] User interface 400 shows that the current available time is 4 days, and the time may be extended to 1 to 2 days depending on factors such as the consignee, port and goods.

[0126] The output of the disclosed method can be used to determine the time extension for each factor, such as consignee, port, and commodity.

[0127] Figure 3C User interfaces 20, 22, and 24 for booking containers are shown.

[0128] User interfaces 20, 22, and 24 are related to container 1, where the corresponding user interface objects represent: the estimated arrival time at the port as September 12, 2022; availability on September 13, 2022; the last free day as September 16, 2022; a time extension switch for adjusting the number of extension days; the latest pickup date; and additional time extension costs in GBP.

[0129] For example, a time extension of 0 days (i.e., no time extension) is considered high risk to D&D costs. This could be because, for example, the projected turnaround time at this port and / or for this commodity is greater than 0 days.

[0130] For example, an extension of 2 days is considered to pose a moderate risk to D&D costs. This could be because, for example, the projected turnaround time at this port and / or for this commodity is approaching 2 days.

[0131] For example, an extension of 3 days is considered low risk in terms of D&D costs. This could be because, for example, the projected turnaround time at this port and / or for this commodity is less than 3 days.

[0132] The implementation of the methods and products (electronic devices) according to this disclosure is set forth in the following terms:

[0133] Clause 1. A method for predicting container turnaround time, executed by an electronic device, the method comprising:

[0134] - Obtain shipping data associated with the shipping of one or more containers;

[0135] - Based on the shipping data, a turnaround time parameter indicating the turnaround time of the container is generated by applying a prediction model to the shipping data; and

[0136] - Output is provided based on the turnaround time parameter.

[0137] Clause 2. The method according to Clause 1, wherein applying the predictive model includes applying one or more machine learning techniques and / or estimating techniques to the shipping data.

[0138] Clause 3. The method according to Clause 2, wherein the one or more machine learning techniques include one or more of the following: linear regression models, random forest models, decision tree-based models and ensemble models, and wherein the prediction technique includes time series prediction techniques.

[0139] Clause 4. The method according to any one of the preceding clauses, wherein the shipping data includes one or more of the following: time extension data associated with the time extension of the container, transaction data associated with one or more transactions, container movement data associated with the movement of the one or more containers, commodity data associated with one or more commodities, consignee data associated with one or more consignees, container data associated with the one or more containers, booking data associated with one or more shipping bookings, port data associated with one or more shipping ports, turnaround time data, and historical shipping data.

[0140] Clause 5. The method according to any one of the preceding clauses, wherein the method includes generating a commodity risk factor for at least one commodity based on the shipping data, wherein the commodity risk factor is associated with the at least one commodity and the port involved in the shipping.

[0141] Clause 6. The method described in Clause 5, wherein generating the risk factors for the goods includes:

[0142] - Calculate one or more commodity distribution parameters for the at least one commodity based on the shipping data, wherein the one or more commodity distribution parameters for the at least one commodity indicate a distribution of at least one of the following for the at least one commodity:

[0143] - Delay in the return of the container for the at least one of the goods

[0144] - The ratio of the time extension used to the time extension granted for the shipping of at least one commodity, and

[0145] - The ratio of the time elapsed to the available time elapsed in the shipping of the at least one commodity; and

[0146] - Generate the commodity risk factors based on the one or more commodity distribution parameters.

[0147] Clause 7. The method according to any one of the preceding clauses, wherein the method comprises grouping consignees into: a first primary consignee group, the first primary consignee group comprising consignees present in the turnaround time system of the electronic device; and a first secondary consignee group, the first secondary consignee group comprising consignees not present in the turnaround time system.

[0148] Clause 8. The method according to any one of the preceding clauses, wherein the method includes generating a consignee risk factor for at least one consignee based on the shipping data.

[0149] Clause 9. The method described in Clause 8, wherein generating the consignee risk factors based on the shipping data includes:

[0150] - Calculate one or more consignee distribution parameters for the at least one consignee based on the shipping data, wherein the one or more consignee distribution parameters for the at least one consignee indicate a distribution of at least one of the following for the at least one commodity:

[0151] - The proportion of containers delayed for at least one consignee.

[0152] - The ratio of the elapsed time extension to the granted time extension for the shipment of the at least one consignee, and

[0153] - - The ratio of the elapsed time to the available time for the shipment of the at least one consignee; and

[0154] - Generate the consignee risk factors based on the one or more consignee distribution parameters.

[0155] Clause 10. The method according to Clause 6 and / or 9, wherein generating the commodity risk factor and / or the consignee risk factor includes applying a standardized function to the one or more commodity distribution parameters and / or the one or more consignee distribution parameters.

[0156] Clause 11. The method according to any one of the preceding clauses, wherein the method includes generating a seasonality factor based on the shipping data that indicates the seasonality of the turnaround time parameter at the port.

[0157] Clause 12. The method according to Clause 11, wherein generating the seasonality factor based on the shipping data includes:

[0158] - Based on the shipping data, the consignees are classified into a second primary consignee group and a second secondary consignee group;

[0159] - Obtain a first seasonal value at the current time for one or more consignees in the second primary consignee group, which is associated with the turnaround time parameters of the container and the port;

[0160] - Based on the first seasonal value and the forecasting technique, determine a second seasonal value for each time period of the year associated with the turnaround time parameter and the port; and

[0161] - The second seasonal value is assigned to the seasonality factor of the turnover time parameter that indicates a specific time of the year.

[0162] Clause 13. The method according to any one of the preceding clauses, wherein the turnaround time parameter includes a consignee turnaround time parameter associated with the consignee of the container.

[0163] Clause 14. The method according to Clause 13, wherein generating the turnaround time parameter based on the shipping data includes generating the consignee turnaround time parameter based on the shipping data.

[0164] Clause 15. The method according to Clause 14, wherein generating the consignee turnaround time parameter based on the shipping data includes generating a model-based consignee turnaround time parameter based on the shipping data and at least one of the one or more machine learning techniques.

[0165] Clause 16. The method according to Clause 15, wherein generating the model-based consignee turnaround time parameter based on at least one of the one or more machine learning techniques based on the shipping data includes:

[0166] - Generate an aggregated set of data based on the aforementioned historical time extension data and the corresponding historical turnaround time data at each port; and

[0167] - Apply at least one of the one or more machine learning techniques to the set of aggregated data.

[0168] Clause 17. The method according to any one of Clauses 11 to 12 and 14 to 15, wherein generating the consignee turnaround time parameter based on the shipping data includes generating the consignee turnaround time parameter based on the model-based consignee turnaround time parameter and one or more of the following: the commodity risk factor, the consignee risk factor, and the seasonality factor.

[0169] Clause 18. The method according to any one of Clauses 7 and 14 and Clauses 8 to 13 and 15 to 17, wherein generating the turnaround time parameter based on the shipping data includes generating a consignee turnaround time parameter associated with at least one consignee in the first-level consignee group based on the shipping data.

[0170] Clause 19. The method according to Clause 18, wherein generating the consignee turnaround time parameter associated with the at least one consignee in the first-level consignee group comprises:

[0171] - The earliest transaction identifying the at least one consignee; and

[0172] - Based on the recipient turnaround time parameters of the recipients in the first primary recipient group and the recipients in the first secondary recipient group, determine the recipient turnaround time parameters associated with at least one recipient in the first secondary recipient group for the goods.

[0173] Clause 20. The method according to any one of the preceding clauses, wherein the turnaround time parameter includes port turnaround time parameters associated with the port.

[0174] Clause 21. The method according to Clause 20, wherein generating the turnaround time parameter based on the shipping data includes generating the port turnaround time parameter based on the shipping data by applying the estimation technique to the shipping data.

[0175] Clause 22. The method according to any one of the preceding clauses, wherein the turnover time parameter includes a merchandise turnover time parameter associated with the merchandise.

[0176] Clause 23. The method according to Clause 22, wherein generating the turnaround time parameter based on the shipping data includes generating the commodity turnaround time parameter based on the shipping data by applying the estimation technique to the shipping data.

[0177] Clause 24. An electronic device comprising memory circuitry, processor circuitry, and an interface, wherein the electronic device is configured to perform any one of the methods according to any one of Clauses 1 to 23.

[0178] Clause 25. A computer-readable storage medium storing one or more programs, said one or more programs including instructions that, when executed by an electronic device, cause the electronic device to perform any of the methods described in Clauses 1 to 23.

[0179] The use of terms such as "first," "second," "third," and "fourth," "primary," "secondary," and "third-level" does not imply any particular order, but is included to identify individual elements. Furthermore, the use of terms such as "first," "second," "third," and "fourth," "primary," "secondary," and "third-level" does not indicate any order or importance, but is used to distinguish one element from another. Please note that the use of the terms "first," "second," "third," and "fourth," "primary," "secondary," and "third-level" here and elsewhere is solely for labelling purposes and is not intended to indicate any particular spatial or temporal order. Moreover, the labeling of a first element does not imply the existence of a second element, and vice versa.

[0180] It is understandable that Figure 1 to Figure 3C This includes some circuit systems or operations shown in solid lines and some circuit systems or operations shown in dashed lines. The circuit systems or operations included in the solid lines are those included in the most broad example implementation. The circuit systems or operations included in the dashed lines are those that can be included in or are part of the circuit systems or operations of the solid-line example implementation, or are further circuit systems or operations that can be taken in addition to the circuit systems or operations of the solid-line example implementation. It should be understood that these operations do not need to be performed in the order presented. Furthermore, it should be understood that not all operations need to be performed. Exemplary operations can be performed in any order and in any combination.

[0181] It should be noted that the word "including" does not necessarily exclude the existence of other elements or steps besides those listed.

[0182] It should be noted that the words "one" or "a kind" preceding an element do not preclude the existence of multiple such elements.

[0183] It should also be noted that any reference numerals in the drawings do not limit the scope of the claims, exemplary embodiments may be implemented at least in part by both hardware and software, and several “components,” “units,” or “devices” may be represented by the same hardware article.

[0184] The various exemplary methods, devices, nodes, and systems described herein are described in the general context of method steps or processes. In one aspect, these method steps or processes may be implemented by a computer program product embodied in a computer-readable medium, including computer-executable instructions, such as program code, that are executed by a computer in a networked 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), optical disc (CD), digital versatile disc (DVD), etc. Generally, program circuitry may include routines, programs, objects, components, data structures, etc., that perform a specified task or implement a particular abstract data type. Computer-executable instructions, associated data structures, and program circuitry represent examples of program code for performing steps of the methods disclosed herein. Specific sequences of such executable instructions or associated data structures represent examples of corresponding actions for implementing the functionality described in such steps or processes.

[0185] Although features have been shown and described, it should be understood that they are not intended to limit the scope of the claimed disclosure, and it will be apparent to those skilled in the art that various changes and modifications can be made without departing from the scope of the claimed disclosure. Therefore, this specification and accompanying drawings should be considered illustrative rather than restrictive. The claimed disclosure is intended to cover all alternatives, modifications, and equivalents.

Claims

1. A method for predicting container turnaround time, executed by an electronic device, the method comprising: - Obtain shipping data associated with the shipping of one or more containers; - Based on the shipping data, a turnaround time parameter indicating the turnaround time of the container is generated by applying a prediction model to the shipping data; as well as - Output is provided based on the turnaround time parameter.

2. The method of claim 1, wherein applying the prediction model includes applying one or more machine learning techniques and / or estimation techniques to the shipping data.

3. The method according to claim 2, wherein the one or more machine learning techniques include one or more of the following: linear regression model, random forest model, decision tree-based model and ensemble model, and wherein the prediction technique includes time series prediction technique.

4. The method according to any one of the preceding claims, wherein the shipping data includes one or more of the following: time extension data associated with the time extension of the container, transaction data associated with one or more transactions, container movement data associated with the movement of the one or more containers, commodity data associated with one or more goods, consignee data associated with one or more consignees, container data associated with the one or more containers, booking data associated with one or more shipping bookings, port data associated with one or more shipping ports, turnaround time data, and historical shipping data.

5. The method according to any one of the preceding claims, wherein the method includes generating a commodity risk factor for at least one commodity based on the shipping data, wherein the commodity risk factor is associated with the at least one commodity and the port involved in the shipping.

6. The method of claim 5, wherein generating the commodity risk factors comprises: - Calculate one or more commodity distribution parameters for the at least one commodity based on the shipping data, wherein the one or more commodity distribution parameters for the at least one commodity indicate a distribution of at least one of the following for the at least one commodity: - Delay in the return of the container for at least one of the goods. - The ratio of the time extension used to the time extension granted for the shipping of at least one commodity, and - The ratio of the time elapsed to the available time elapsed in the shipping of the at least one commodity; and - Generate the risk factors for the commodities based on the one or more commodity distribution parameters.

7. The method according to any one of the preceding claims, wherein the method comprises grouping consignees into: a first primary consignee group, the first primary consignee group comprising consignees present in the turnaround time system of the electronic device; and a first secondary consignee group, the first secondary consignee group comprising consignees not present in the turnaround time system.

8. The method according to any one of the preceding claims, wherein the method includes generating a consignee risk factor for at least one consignee based on the shipping data.

9. The method of claim 8, wherein generating the consignee risk factors based on the shipping data comprises: - Calculate one or more consignee distribution parameters for the at least one consignee based on the shipping data, wherein the one or more consignee distribution parameters for the at least one consignee indicate a distribution of at least one of the following for the at least one commodity: - The proportion of containers delayed for at least one consignee. - The ratio of the elapsed time extension to the granted time extension for the shipment of the at least one consignee, and --The ratio of the elapsed time to the available time for the shipment of the at least one consignee; and - Generate the consignee risk factors based on the one or more consignee distribution parameters.

10. The method according to any one of the preceding claims, wherein the turnaround time parameter includes a consignee turnaround time parameter associated with the consignee of the container.

Images