Prediction method, prediction program, and prediction device

The method and system use sensor data and machine learning to predict and prioritize shipping containers for processing based on water damage, addressing the challenge of cargo deterioration during transportation.

JP7579380B2Active Publication Date: 2024-11-07HITACHI LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
JP2023065457
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2022-06-15
Filing Date
2023-04-13
Publication Date
2024-11-07
Estimated Expiration
2043-04-13

AI Technical Summary

Technical Problem

Existing systems fail to effectively monitor and predict water damage in shipping containers, which can lead to deterioration of perishable cargo during transportation.

Method used

A method and system that utilizes internal and external sensor data to model the environment within a shipping container, employing machine learning models to predict water damage and prioritize containers for processing based on the predicted damage.

Benefits of technology

Enables real-time tracking and prediction of water damage in any state (solid, liquid, or gaseous) within shipping containers, facilitating timely intervention and reducing cargo loss.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007579380000003
    Figure 0007579380000003
  • Figure 0007579380000004
    Figure 0007579380000004
  • Figure 0007579380000005
    Figure 0007579380000005
Patent Text Reader

Abstract

To track an environment within a container and predict a damage related to water in any state, namely a solid, liquid or gas state.SOLUTION: A method of prediction allows for a preemptive action to lessen damage by using a system for monitoring and predicting a water damage in a container.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates generally to shipping containers, and more particularly to a method, program and device for monitoring and predicting water damage in shipping containers. [Background technology]

[0002] FIG. 1 is a diagram illustrating an example of a shipping container. Such shipping containers are used to carry cargo all over the world. In the related art, once the cargo is inside the container, visibility of the cargo is low. Perishable cargo, such as coffee, cocoa, or powdered milk, may deteriorate during transportation. If water damage could be monitored in real time, it could facilitate prevention, faster transportation of replacement goods, faster insurance payouts, parametric insurance products, etc.

[0003] In an embodiment of the related art, there is a system and method for handling verification of the status of an item during transportation. Such an embodiment of the related art describes how data can be collected and transmitted to track the status, which status is general. For example, Patent Document 1 is an example of the above-mentioned related art. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] US Patent Publication No. 2022-0051183 Summary of the Invention [Problem to be solved by the invention]

[0005] In cargo transport situations, particularly in systems dealing with water damage, the adverse environment inside a container is a typical cause of damage to cargo during transport.

[0006] The objective of the present invention is to track the environment inside a container and predict damage associated with water in any state: solid, liquid or gas. [Means for solving the problem]

[0007] Aspects of the invention may include a method, the method may include executing a first model configured to model an interior environment of a shipping container, the first model configured to incorporate interior sensor data received from a sensor inside the shipping container and external data associated with an environment exterior to the shipping container, the first model configured to output interior environmental parameters of the shipping container, the method may further include executing a second model configured to derive water damage occurring to a cargo of the shipping container, the second model incorporating the interior environmental parameters of the shipping container; Water Damage and a machine learning model configured to output: Water Damage The method may include prioritizing shipping containers for processing based on:

[0008] Aspects of the invention may include a computer program, the computer program may include instructions including executing a first model configured to model an interior environment of a shipping container, the first model configured to incorporate interior sensor data received from a sensor inside the shipping container and external data associated with an environment external to the shipping container, the first model configured to output interior environmental parameters of the shipping container, the computer program may further include instructions including executing a second model configured to derive water damage occurring to the shipping container, the second model incorporating the interior environmental parameters of the shipping container, Water Damage and a machine learning model configured to output: Water DamageThe instructions and computer programs may include instructions for prioritizing shipping containers for processing based on a number of factors including the number of containers that can be processed, ... and the number of containers that can be processed. The instructions and computer programs may be stored on a non-transitory computer readable medium and executed by one or more processors.

[0009] Aspects of the invention may include a system, the system may include means for executing a first model configured to model an interior environment of a shipping container, the first model configured to incorporate interior sensor data received from a sensor inside the shipping container and external data associated with an environment exterior to the shipping container, the first model configured to output interior environmental parameters of the shipping container, the system may further include means for executing a second model configured to derive water damage occurring to the shipping container, the second model incorporating the interior environmental parameters of the shipping container, Water Damage and a machine learning model configured to output: Water Damage The system may include means for prioritizing shipping containers for processing based on:

[0010] Aspects of the invention may include an apparatus that may include a process, the process may be configured to execute a first model configured to model an interior environment of a shipping container, the first model configured to incorporate interior sensor data received from a sensor inside the shipping container and external data associated with an environment external to the shipping container, the first model configured to output interior environmental parameters of the shipping container, the process may be further configured to execute a second model configured to derive water damage occurring to the shipping container, the second model incorporating the interior environmental parameters of the shipping container, Water Damage and outputting a damage rate due to water damage or a damage rate to a shipping container. Water DamageThe system may be configured to prioritize shipping containers for processing based on: Effect of the Invention

[0011] According to one aspect of the invention, the environment inside a container can be tracked to predict damage associated with water in any state: solid, liquid or gas. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing an example of a shipping container. [Diagram 2] 1 is an overview of a method according to an embodiment; [Diagram 3] FIG. 1 illustrates exemplary data according to one embodiment. [Figure 4] FIG. 1 illustrates an example of in-container environment modeling, according to a preferred embodiment. [Diagram 5] FIG. 2 illustrates an exemplary flow for estimating the internal environment of a container, according to one embodiment. [Figure 6] FIG. 1 illustrates an example of damage modeling, according to one embodiment. [Figure 7] FIG. 1 illustrates a system including a plurality of shipping containers networked to a management device, according to one embodiment. [Figure 8] FIG. 1 illustrates an exemplary computing environment having an exemplary computing device suitable for use in some embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] The following detailed description provides details of the figures and examples of the present application. Reference numbers and descriptions of elements that are duplicated between figures are omitted for clarity. Terms used throughout the description are provided as examples and are not intended to be limiting.

[0014] For example, use of the term "automatic" may include fully automated or semi-automated implementations, including user or administrator control over particular aspects of the embodiment, depending on the desired implementation of one of skill in the art practicing the embodiments of the present application. Selections may be made by a user via a user interface or other input means, or may be performed via a desired algorithm.

[0015] The examples as described herein may be used either alone or in combination, and the functionality of the examples may be implemented via any means according to the desired embodiment.

[0016] FIG. 2 shows an overview of a method according to one embodiment.

[0017] As shown in the system of Figure 2, there is a shipping container 200 having sensors that measure the environment inside the container, as well as any other information that may be considered pertinent to the shipping container. Such other information may include sensors at weather stations that monitor weather conditions, sensors located around the ship or outside the container, etc., according to a desired embodiment.

[0018] The sensor measurements are provided as data 201, which may be managed by a database. Such data 201 is used to perform in-container environment modeling 202, which trains / implements an in-container environment model for the shipping container. Output interior environment parameters of the shipping container from in-container environment modeling 202 are provided to damage modeling 203, which is configured to predict damage to the shipping container based on the output.

[0019] The in-container environmental modeling 202 may be a machine learning model. For example, such a machine learning model may be a machine learning model trained from a database of historical data relating internal environmental parameters to internal sensor data and external data. Other models are possible and the disclosure is not limited thereto.

[0020] Depending on the desired embodiment, such a model may be a physics-based model, for example a thermodynamic model of the container's internal environment, or may be a signal processing model configured to derive the desired internal environmental parameters based on sampling of sensor data.

[0021] Damage modeling 202 may be configured to derive water damage occurring to the shipping container via a machine learning model configured to incorporate interior environmental parameters of the shipping container.

[0022] To train such a model, a machine learning model can be trained against historical data relating measured / estimated internal parameters of shipping containers to outcomes (e.g., percentage of damage attributable to water damage, whether or not damage occurred, etc.).

[0023] Other outputs that can be provided by Damage Modeling 203 can include, but are not limited to, damage and loss statistics, real-time alerts, predictions of future damage, instructions for damage mitigation, etc. As the embodiment is a machine learning model, desired outputs can be provided if adequate historical data is available for training the machine learning model.

[0025] Once the output is determined, a software platform associated with the shipping container Water Damage Shipping containers may be prioritized for processing based on:

[0026] In one example, Potential for water damage Shipping containers with high shipping rates may be flagged or sorted to be opened first at the port. Water Damage The method may include determining whether an alert should be generated based on the

[0027] If it is determined that an alert should be generated, an alert may be generated for the shipping container so that it may be opened during transport.

[0028] Further details are provided below: Figure 3 is a diagram showing example data according to one embodiment.

[0029] Examples of data that may be utilized in the implementations described herein may include, but are not limited to, data collected by sensors inside the shipping container 301, environmental data from outside the shipping container 302, and other data 303, according to a desired embodiment.

[0030] Data 301 collected by sensors inside the shipping container may include, but is not limited to, temperature, humidity, gas (such as CO2 and methane) levels, shock / acceleration, door open indicators, presence or absence of liquid water (e.g., on the floor), etc., according to a desired embodiment.

[0031] Environmental data 302 from outside the shipping container may include, but is not limited to, weather data (eg, temperature, humidity, etc.) and other data deemed relevant, according to a desired embodiment.

[0032] Other data 303 may include metadata and model parameters, such as, but not limited to, cargo shipment itinerary, location of shipping containers on the ship, etc., according to a preferred embodiment.

[0033] 4 is a diagram illustrating an example of environment modeling within a container, according to a preferred embodiment. The environment within a container is described by several parameters, including but not limited to air temperature, relative humidity (e.g., corresponding dew point), cargo surface temperature, presence or absence of water (e.g., including condensed water and ice on the cargo surface), gas (e.g., CO2 and methane) concentrations, etc.

[0034] In some cases, one or more of the above parameters are measured directly by sensors placed inside the container. For example, air temperature and humidity may be measured by sensors. However, there may be situations where direct measurements are not available, for example, either no sensors are present or the cargo movement has not yet taken place. Unlike air parameters (such as air temperature) that are easily measured by sensors, what is happening on the cargo surface may be more difficult to measure and often requires estimation.

[0035] To estimate such variables, the intracontainer environment modeling 202 may include two models that estimate variables when not directly measured.

[0036] The first model operates when there are no sensors measuring the temperature and humidity inside the container, and its logic is shown in Figure 4. An embodiment of the container's internal temperature and relative humidity estimation model 400 can take several forms. In a first form, the container's internal temperature and relative humidity estimation model 400 can be a physical model, such as a thermodynamic model that estimates how heat exchange occurs between the container's external and internal environments. Alternatively, the model can be a supervised machine learning model that is trained on data from containers with sensors inside them.

[0037] Here, the sensor measurements inside the container act as variables that the model predicts. Once this model is trained, it can be used to estimate the in-container sensor measurements in the absence of the sensors. An example of a machine learning model that can estimate the in-container time series is a LSTM (Long Short-Term Memory) model, although other types of models can also work according to desired embodiments and the disclosure is not limited thereto.

[0038] 4, in accordance with a desired embodiment, the container interior temperature and relative humidity estimation model 400 may incorporate other desired parameters, such as an exterior relative humidity measurement, an exterior temperature measurement, and an interior container measurement, if available. Based on this input, the container interior temperature and relative humidity estimation model 400 can thereby provide estimates of relative humidity and temperature.

[0039] The second model housed within the container environment modelling 202 is the cargo parameter estimation 401. The cargo parameter estimation 401 is used to estimate cargo parameters, in particular the temperature at the surface of the cargo and whether water in liquid form is present on the cargo surface.

[0040] There may be more than one way to estimate the cargo surface temperature. For example, one method may be based on Newton's law of cooling, which states that the rate of heat loss from a body is directly proportional to the temperature difference between the body and the surroundings. Using this as a principle, a differential equation can be derived, which can be solved to give the following equation that tracks the cargo temperature:

[0041]

number

[0042] In the above equation (1), the capital T generally refers to temperature and the lower case t refers to time. cargo (t) is the cargo temperature at time t, and T internal is the internal air temperature of the container. τ (tau) is a cargo-specific constant that determines how quickly the cargo temperature responds to its environment.

[0043] Condensation inside a container follows the same physical process as condensation in nature. To determine condensation, the dew point of the air is calculated from its temperature and relative humidity. Condensation occurs when the cargo temperature falls below the dew point of the air. Once condensation has occurred, it can be further calculated how long it will take for the condensate to evaporate away. Determining the presence of liquid water on the cargo surface is important as some serious types of water damage occur in the presence of liquid water.

[0044] 4, cargo parameter estimation 401 may incorporate internal relative humidity and internal temperature either from sensor data or estimated results from a container internal temperature and relative humidity estimation model 400. From this input, cargo parameter estimation 401 can thereby estimate the cargo temperature as well as the condensation on the surface of the cargo.

[0045] FIG. 5 illustrates an exemplary flow diagram for estimating a container internal environment, according to one embodiment.

[0046] At 500, the sensor measurements are processed to determine if the sensor is monitoring the internal environment of the container. If so (yes), the sensor data is used for parameters of the internal environment. If not (no), the estimated results are provided as parameters for the internal environment of the container by performing the container internal temperature and relative humidity estimation 400. The container internal temperature and relative humidity estimation 400 takes the available internal parameters and provides the estimated results accordingly, as described with reference to FIG. 4.

[0047] 6 is a diagram illustrating an example of damage modeling, according to one embodiment. Damage caused by water can take many forms, including but not limited to mold, corrosion, and / or structural weakening of the cargo or packaging.

[0048] Detecting or predicting damage, alert creation, etc., is considered as a supervised machine learning problem, typically viewed as classification where the classes are the degree of damage (e.g., no damage / moderate damage / severe damage). Engineered features help to increase accuracy and add explanatory power to the model output. With this in mind, damage modeling 203 may include two functions, such as feature engineering 600 based on damage type and machine learning model for damage 601.

[0049] With respect to damage type based feature engineering 600, the example of mold risk is provided as an example. Mold growth has been studied in controlled environments. The mold growth rate may have the following form:

[0050]

number

[0051] where a, c1, c2, c0 etc. are constants that depend on the substrate, T and RH are temperature and relative humidity, respectively, and M is the mold index. Within practical temperature and humidity ranges, mold grows rapidly at warm temperatures and high humidity. The mold index M calculated from appropriate temperature and humidity measurements can be a good feature for classifying cargo shipments by mold risk.

[0052] A machine learning model for mold damage 601 can use the mold index at any time as a feature to predict risk of mold. A similar approach can be applied to other forms of water damage as well.

[0053] Many cargoes are vulnerable to damage due to exposure to humidity / water. The ability to track, predict, and potentially prevent such damage is beneficial to manufacturers and shippers. The embodiments described herein outline the building blocks of a system for tracking and predicting water-induced damage.

[0054] Water damage can take many forms, and the embodiments described herein can account for a variety of scenarios ranging from a shipping container having no sensors inside to a scenario where multiple in-container sensors are available whose measurements still need to be converted into a valid output.

[0055] As shown in FIG. 6, according to a desired embodiment, Damage Modeling 203 may incorporate output from In-Container Environment Modeling 202, which may include, but is not limited to, timestamps of along-the-journey information, measured / estimated internal temperature of the shipping container, measured / estimated internal relative humidity of the shipping container, dew point temperature, cargo temperature, condensate on cargo surfaces, measured CO2 concentration, and other data.

[0056] From this data, feature engineering can be performed 600 based on the type of damage. Examples of features that can be extracted may include, but are not limited to, mold index, cumulative cargo condensation time, joint histograms including multiple inputs, and other features, depending on the desired embodiment. Such features are used as inputs for a machine learning model for damage 601 that is configured to provide a damage prediction result or damage alert, depending on the desired embodiment.

[0057] FIG. 7 illustrates a system including a number of shipping containers networked to a management device, according to one embodiment.

[0058] One or more shipping containers 701 incorporating various sensors are communicatively coupled to a network 700 (e.g., a local area network (LAN), a wide area network (WAN)) via corresponding network interfaces of the sensor systems mounted on the shipping containers 701, which are connected to a management device 702.

[0059] The management device 702 manages a database 703 containing historical data collected by the sensor systems from each of the shipping containers 701. In an alternative embodiment, the data from the sensor systems of the shipping containers 701 can be stored in a central repository or database, such as a proprietary database that captures data from the shipping containers 701, or a system such as an enterprise resource planning system, and the management device 702 can access or retrieve the data from the central repository or database.

[0060] The sensor system of the shipping container 701 may include any type of sensor that facilitates a desired embodiment, such as, but not limited to, a gyroscope, an accelerometer, a global positioning satellite (GPS), a thermometer, a hygrometer, or any sensor capable of measuring one or more of temperature, humidity, gas levels (e.g., CO2 gas), impact, acceleration, door open indicator, light, or the presence or absence of liquid water.

[0061] Depending on the desired embodiment, the receipt of the sensor data points is in real-time during cargo transport of the shipping container. For example, if the system of FIG. 8 is limited to a ship transporting shipping containers, the local area network can provide the sensor data points in real-time to the management device 702 or can be transmitted (e.g., via satellite) to a monitoring station.

[0062] In other embodiments, multiple sensor data points may be received after delivery of the shipping container (e.g., stored on board the ship or at port, and stored in a ship's database by the management device 702 for later retrieval and processing at the port).

[0063] Additionally, database 703 may include additional sensor data points associated with previously transported shipping containers (eg, either from the same vessel or imported from a master database).

[0064] In an embodiment, such additional sensor data points can supplement the multiple sensor data points from the current shipping container 701 if such previously transported shipping container was transported along the same route as the current shipping container 701.

[0065] Additionally, according to a desired embodiment, other external data may be transmitted to database 703. Such external data may be streaming information (e.g., regarding weather data), from the Internet, from sensors outside the shipping container, etc., according to a desired embodiment.

[0066] FIG. 8 illustrates an example computing environment having an example computing device suitable for use in some embodiments, such as the management device 702 shown in FIG.

[0067] A computing device 805 in the computing environment 800 may include one or more processing units, cores, or processors 810, memory 815 (e.g., RAM, ROM, and / or the like), internal storage 820 (e.g., magnetic, optical, solid-state storage, and / or organic), and / or I / O interfaces 825, any of which may be coupled over or incorporated into the computing device 805, a communication mechanism or bus 830 for communicating information.

[0068] I / O interface 825 is further configured to receive images from a camera or provide images to a projector or display, depending on the desired implementation.

[0069] The computing device 805 may be communicatively coupled to an input / user interface 835 and an output device / interface 840. Either one or both of the input / user interface 835 and the output device / interface 840 may be a wired or wireless interface and may be detachable.

[0070] Input / user interface 835 may include any device, component, sensor, or interface, physical or virtual, that can be used to provide input (e.g., buttons, touch screen interfaces, keyboards, pointing / cursor controls, microphones, cameras, Braille, motion sensors, optical readers, and / or the like). Output devices / interfaces 840 may include displays, televisions, monitors, printers, speakers, Braille, or the like.

[0071] In some embodiments, the input / user interface 835 and the output device / interface 840 may be incorporated with or physically coupled to the computing device 805. In other embodiments, other computing devices may function as or provide the functionality of the input / user interface 835 and the output device / interface 840 for the computing device 805.

[0072] Examples of computing devices 805 may include, but are not limited to, highly mobile devices (e.g., smartphones, devices mounted on vehicles and other machines, devices carried by people or animals, and the like), mobile devices (e.g., tablets, notebooks, laptops, personal computers, portable televisions, radios, and the like), and devices not designed for mobility (e.g., desktop computers, other computers, information kiosks, televisions with one or more processors embedded and / or televisions with one or more processors coupled thereto, radios, and the like).

[0073] Computing device 805 may be communicatively coupled (e.g., via I / O interface 825) to external storage 845 and a network 850 for communication with any number of networked components, devices, and systems, including one or more computing devices of the same or different configurations. Computing device 805 or any connected computing device may function as, provide services to, or be referred to as a server, client, thin server, general purpose machine, special purpose machine, or otherwise.

[0074] The I / O interfaces 825 may include, but are not limited to, wired and / or wireless interfaces using any communication or I / O protocol or convention (e.g., Ethernet, 802.11x, Universal system Bus, WiMax, modem, cellular network protocols, and the like) for communicating information to and / or from at least all connected components, devices, and networks in the computing environment 800.

[0075] Network 850 may be any network or combination of networks (eg, the Internet, a local area network, a wide area network, a telephone network, a cellular network, a satellite network, and the like).

[0076] The computing device 805 can use and / or communicate using computer usable or computer readable media, including transitory and non-transitory media. Transitory media include transmission media (e.g., metallic cables, optical fibers), signals, carrier waves, and the like. Non-transitory media include magnetic media (e.g., disks and tapes), optical media (e.g., CD-ROMs, digital video disks, Blu-ray® disks), solid-state media (e.g., RAM, ROM, flash memory, solid-state storage), and other non-volatile storage or memory.

[0077] The computing device 805 may be used to implement techniques, methods, applications, processes, or computer-executable instructions in some exemplary computing environments. The computer-executable instructions may be retrieved from a transitory medium and stored in and retrieved from a non-transitory medium. The executable instructions may be from one or more of any programming language, scripting language, and machine language (e.g., C, C++, C#, Java, Visual Basic, Python, Perl, JavaScript, etc.).

[0078] The processor 810 can execute under any operating system (OS) (not shown) in a native or virtual environment. One or more applications can be deployed, including a logic unit 860, an application programming interface (API) unit 865, an input unit 870, an output unit 875, and an inter-unit communication mechanism 895 for different units to communicate with each other, the OS, and other applications (not shown).

[0079] The above-mentioned units and elements may differ in design, function, configuration, or implementation and are not limited to the above description. The processor 810 may have the form of a hardware processor, such as a central processing unit (CPU), or may be a combination of hardware and software units.

[0080] In some embodiments, once information or instructions for execution are received by API unit 865, they may be communicated to one or more other units (e.g., logic unit 860, input unit 870, output unit 875). In some examples, logic unit 860 may be configured to control the flow of information between the units and direct the services provided by API unit 865, input unit 870, output unit 875 in some embodiments described above.

[0081] For example, one or more processes or implementation flows may be controlled by logic unit 860, alone or in conjunction with API unit 865. Input unit 870 may be configured to obtain inputs for the calculations described in the embodiments, and output unit 875 may be configured to provide outputs based on the calculations described in the embodiments.

[0082] The processor 810 may be configured to execute a method or instructions including executing a first model configured to model an interior environment of a shipping container, the first model configured to incorporate interior sensor data received from a sensor inside the shipping container and external data associated with an environment outside the shipping container such as shown in the container environment modeling 202 of FIG. 2, the first model configured to output an interior environmental parameter of the shipping container, and the processor 810 may be further configured to execute a method or instructions including executing a second model configured to derive water damage caused to the shipping container. 2 , and the second model includes a machine learning model configured to take in internal environmental parameters of the shipping container and output one or more of a damage rate attributable to water damage or a predicted severity of water damage to the shipping container, or one or more other metrics dependent on the damage rate or severity as shown in damage modeling 203 of FIG. 2 , and the processor 810 may be further configured to execute a method or instructions including prioritizing the shipping containers for processing based on one or more of the damage rate attributable to water damage or the predicted severity of water damage to the shipping container.

[0083] Depending on the desired embodiment, a machine learning model is trained from a database of historical data correlating interior environmental parameters with damage caused by water damage and the severity of water damage.

[0084] Depending on the desired embodiment, the first model may be a physics-based model, for example, a thermodynamic model of the interior environment of the container.

[0085] Depending on the desired embodiment, the first model may be a machine learning model trained from a database of historical data relating internal environmental parameters to internal sensor data and external data. Depending on the desired embodiment, the first model may be a signal processing model.

[0086] Depending on the desired embodiment, the internal environmental parameters may include one or more of a mold index or cumulative cargo condensation time.

[0087] Depending on the desired embodiment, the internal sensor data may include one or more of temperature, humidity, gas levels, shock, acceleration, door open indication, light, or the presence or absence of liquid water.

[0088] Depending on the desired embodiment, the external data may include one or more of temperature or humidity.

[0089] Depending on the desired embodiment, prioritizing shipping containers for processing may include determining whether an alert should be generated based on one or more of a damage rate due to water damage or a predicted severity of water damage to the shipping container, or metrics calculated from the damage rate and severity, and generating an alert for the shipping container if the determination indicates that an alert should be generated.

[0090] Depending on the desired embodiment, the one or more metrics calculated from the loss rate and severity may include one or more of cargo quality degradation, supply chain delays, or aggregate economic impact.

[0091] Some portions of the detailed description are presented in terms of algorithms and symbolic representations of operations within a computer. These algorithmic descriptions and symbolic representations are the means used by those skilled in the data processing arts to convey the substance of their innovations to others skilled in the art. An algorithm is a sequence of defined steps leading to a desired end state or result. In the illustrative examples, the steps performed require physical manipulations of tangible quantities to achieve a tangible result.

[0092] Unless otherwise noted, and as will be apparent from the description, throughout this specification, descriptions utilizing words such as "processing," "computing," "calculating," "determining," "displaying," or the like, are understood to include the actions and processes of a computer system or other information processing device that manipulates and converts data represented as physical (electronic) quantities in the registers and memory of the computer system into other data similarly represented as physical quantities in the memory or registers of the computer system or other information storage, transmission, or display devices.

[0093] Embodiments may further relate to apparatus for performing the operations herein, which may be specially constructed for the required purposes or may comprise one or more general-purpose computers selectively activated or reconfigured by one or more computer programs.

[0094] Such a computer program may be stored on a computer readable medium, such as a computer readable storage medium or a computer readable signal medium. The computer readable storage medium may include tangible media, such as, but not limited to, optical disks, magnetic disks, read-only memory, random access memory, solid-state devices and drives, or any other type of tangible or non-transitory medium suitable for storing electronic information.

[0095] A computer-readable signal medium may include a medium such as a carrier wave. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. A computer program may include a pure software implementation containing instructions for performing the operations of a desired embodiment.

[0096] Various general-purpose systems may be used with the programs and modules according to the examples herein, or it may prove convenient to construct specialized apparatus to perform the desired method steps, in addition, the examples are not described with reference to any particular programming language.

[0097] It will be appreciated that a variety of programming languages ​​may be used to implement the techniques of the embodiments as described herein, the instructions of which may be executed by one or more processing devices, such as, for example, a central processing unit (CPU), processor, or controller.

[0098] As is known in the art to which the present invention pertains, the operations described above may be performed by hardware, software, or some combination of software and hardware. Various aspects of the embodiments may be implemented using circuits and logic devices (hardware), while other aspects may be implemented using instructions stored on a machine-readable medium (software) that, when executed by a processor, cause the processor to perform methods that perform the implementation of the present application.

[0099] Further, some embodiments of the present application may be implemented solely in hardware, while other embodiments may be implemented solely in software. Moreover, the various functions described may be implemented in a single unit or may be distributed across multiple components in any number of ways. When implemented by software, the methods may be executed by a processor, such as a general purpose computer, based on instructions stored on a computer-readable medium. If desired, the instructions may be stored on the medium in a compressed and / or encrypted format.

[0100] Moreover, other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the techniques of the present application. Various aspects and / or components of the described examples may be used alone or in any combination. It is intended that the specification and examples be considered as examples only, with a true scope and spirit of the present application being indicated by the following claims. [Explanation of symbols]

[0101] 200 shipping containers 201 Data 202 Container Environment Modeling 203 Damage Modeling 700 Network 701 Shipping Container 702 Management device 703 Database 800 Computing Environment 805 Computer Devices 810 Processor 815 Memory 820 Internal Storage 825 I / O Interface 830 Bus 835 Input / User Interface 840 Output Device / Interface 845 External Storage 850 Network 860 Logical Units 865 API units 870 Input Unit 875 Output Unit 895 Inter-unit communication mechanism

Claims

1. A prediction method processed by a processor, comprising: executing a first model configured to model an interior environment of a shipping container; The first model is configured to capture internal sensor data received from a sensor within the shipping container and external data associated with an environment external to the shipping container; The first model is configured to output an internal environmental parameter of the shipping container; executing a second model configured to derive water damage caused to the shipping container; The second model is a machine learning model configured to capture the interior environmental parameters of the shipping container and predict the water damage to the shipping container based on the interior environmental parameters; prioritizing the shipping containers for processing based on the water damage; determining whether the sensor is monitoring an internal environment of the shipping container; If monitoring, the interior sensor data is used for the interior environmental parameters of the shipping container; A prediction method characterized in that, if not monitored, the internal environment of the shipping container is estimated by the first model, and the estimated internal environment is used as the internal environmental parameter of the shipping container.

2. The machine learning model is The method of claim 1 , wherein the method is trained from a database of historical data correlating the internal environmental parameters with the water damage.

3. The first model is 10. The method of claim 1, wherein the model is a physics-based model.

4. The physics-based model includes:

4. The method of claim 3, further comprising a thermodynamic model of the internal environment of the container.

5. The first model is 2. The method of claim 1, wherein the machine learning model is trained from a database of historical data relating the internal environmental parameters to the internal sensor data and the external data.

6. The first model is 2. The method of claim 1, wherein the method is a signal processing model.

7. The internal environmental parameters are:

2. The method of claim 1, further comprising one or more of a mold index or cumulative cargo condensation time.

8. The internal sensor data is 2. The method of claim 1, including one or more of temperature, humidity, gas levels, shock, acceleration, door open indicator, light, or the presence or absence of liquid water.

9. The external data is 2. The method of claim 1, further comprising one or more of temperature or humidity.

10. The process of prioritizing the shipping containers includes: determining whether an alert should be generated based on the water damage; generating the alert for the shipping container if the determination indicates that the alert should be generated; and The method of claim 1, further comprising:

11. 2. The method of claim 1, wherein the water damage is water-induced damage including mold or corrosion.

12. A program to be processed by a processor, The program is executing a first model configured to model an interior environment of a shipping container; The first model is configured to capture internal sensor data received from a sensor within the shipping container and external data associated with an environment external to the shipping container; The first model is configured to output an internal environmental parameter of the shipping container; The program is executing a second model configured to derive water damage caused to the shipping container; The second model is a machine learning model configured to capture the interior environmental parameters of the shipping container and predict the water damage to the shipping container based on the interior environmental parameters; The program is prioritizing the shipping containers for processing based on the water damage; The program is determining whether the sensor is monitoring an internal environment of the shipping container; If monitoring, the interior sensor data is used for the interior environmental parameters of the shipping container; A prediction program characterized in that, when the internal environment of the shipping container is not monitored, the internal environment of the shipping container is estimated using the first model, and the estimated internal environment is used as the internal environmental parameter of the shipping container.

13. A prediction device processed by a processor, The processor, configured to execute a first model configured to model an interior environment of a shipping container; The first model is configured to capture internal sensor data received from a sensor within the shipping container and external data associated with an environment external to the shipping container; The first model is configured to output an internal environmental parameter of the shipping container; The processor, configured to execute a second model configured to derive water damage caused to the shipping container; The second model is a machine learning model configured to capture the interior environmental parameters of the shipping container and predict the water damage to the shipping container based on the interior environmental parameters; The processor, configured to prioritize the shipping containers for processing based on the water damage; The processor, configured to determine whether the sensor is monitoring an internal environment of the shipping container; If monitoring, the interior sensor data is used for the interior environmental parameters of the shipping container; A prediction device characterized in that, when not monitored, the internal environment of the shipping container is estimated using the first model, and the estimated internal environment is used as the internal environmental parameter of the shipping container.

Citation Information

Patent Citations

  • Physical distribution supporting system and method and program therefor

    JP2003206028A

  • Information processing apparatus and method, and vehicle

    JP2005071295A

  • Real-time monitoring of cargo

    JP2013522142A

  • Management system, management server, management method, and management program

    JP2019048706A

  • Automated and predictive monitoring of perishable product parameters throughout the cold chain distribution system

    JP2019516162A