Method, system, and computer program for estimating the weather inside a container from meteorological data

Abstract

To provide a method for estimating and managing the status of cargo.SOLUTION: The method includes: obtaining cargo delivery information; extracting a first set of weather information received from one or more databases from one or more locations corresponding to locations and time intervals of the cargo delivery information; performing pre-processing on the first set of weather information for input to an internal environment model configured to output an estimated result of the internal environment of the cargo; and obtaining an estimated result of the internal environment of the cargo from the internal environment model based on the input of the pre-processed first set of weather information, the first set of weather information being periodically resampled in response to updates to the cargo delivery information.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure generally relates to container management systems, and more particularly to systems and methods for estimating internal weather in containers for container management.

Background Art

[0002] Shipping containers transport most of the world's goods. The standardization of containers has supported world trade and brought economic efficiency. However, shipping containers are opaque and difficult to monitor, and the resulting lack of visibility of cargo conditions causes damage and waste, leading to various types of risks ranging from economic losses, delays, and environmental risks to legal risks. In recent decades, an increasing number of shipments have been monitored by Internet of Things (IoT) sensors that provide partial visibility of the location, condition, etc. of the cargo.

[0003] In related art, there is estimated sensor data (temperature, water vapor pressure (similar to humidity)) inside a container using measurement sensor data (temperature, humidity, solar radiation) outside the container using a multiple regression model. The model and dew condensation conditions are used to estimate the dew condensation probability using the above model.

[0004] In related art, there are embodiments in which sensors are attached to containers in transit to record the values of each sensor (gyro, inertial, humidity, temperature, light, pressure, etc.) and their confidence levels to determine whether items are being properly managed (no damage, injury, theft, etc.). This reliability is calculated by inputting sensor values into a reliability determination model using machine learning. The data can be stored on a blockchain.

Summary of the Invention

Problems to be Solved by the Invention

[0005] The exemplary embodiments described herein include "sensorless" solutions. Using external weather data to estimate the internal weather of a container can add significant value when the shipping container has no sensors, when there is a sensor failure, when the delivery is planned for the future, etc.

[0006] The value of having visibility into the cargo during transit is widely recognized. There are related arts regarding verifying the state of items during transit. However, almost all related arts assume that a measurement device (sensor) exists to measure the environment inside the shipping container. Unfortunately, attaching sensors inside the container is costly. Not all containers have sensors.

[0007] Furthermore, there is also a use case where, when a delivery is planned for the future, although measurement results do not yet exist, it is still necessary to estimate the risks of future delivery. Having an alternative when the internal measurement results of the container are not known is useful. The exemplary embodiments described herein facilitate such alternatives based on external weather data. The present disclosure further addresses the practical problems faced when implementing such solutions, namely, problems related to space-time synchronization, model creation, and ultimately, the estimation leading to risk mitigation.

[0008] In a first problem to be solved, there is unsynchronized data. The sensor data inside and outside the container may be measured at different times and even slightly different locations. In particular, when the outside data is obtained from a weather source, its timing and location are unlikely to match precisely using the sensors inside the cargo being measured. This asynchrony poses a challenge during the training phase when a model for converting external data to internal data is being built.

[0009] When external weather measurement results are input into a model that converts external weather data into internal weather data, internal weather data for the container is provided without sensors. Container data is inferred from that weather data, but the spatial-temporal association of data in training is a key step. The exemplary embodiments described herein can facilitate ensuring such an association, which addresses technical problems such that related art hinders implementing a similar model.

[0010] Containers with sensors attached usually conduct telecommunication for real-time tracking in a changing environment, so container data is often measured in irregular time intervals. In addition, time-series models and some other estimation methods usually require data at regular sampling intervals with synchronization.

[0011] In a second technical problem, in the related art, estimation depends on voyages. Container data (risks) depends on the route direction, time, and area. Embodiments of the related art tend to evaluate only a small number of cargos modeled by different linear equations, and new models need to be added for each new voyage, so the development cost of those solutions is high.

[0012] In a third technical problem, there is inaccurate or insufficient risk mitigation. The related art has not proposed a risk mitigation method and has not reached the main pain point, i.e., dealing with cargo deterioration, so it has insufficient economic advantages.

[0013] In a fourth technical problem, there may be containers with unknown contents. The item / customer name of the container may not be clear unless the customer shares the information or the information is inferred from another source such as customs data.

Means for Solving the Problems

[0014] The exemplary embodiments described herein can estimate container parameters and conditions / risks without IoT sensors and optionally using customer / item information. The exemplary embodiments also synchronize data timestamps / geographical locations to generate regular time data for training / estimating the estimation model. Additionally, the exemplary embodiments can propose risk mitigation methods to the user. Weather data can be used to estimate past and future data (using weather estimation).

[0015] Aspects of the present disclosure can include a method for estimating and managing the status of a shipment, the method including obtaining shipment information of the shipment; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the location and time interval of the shipment information of the shipment; performing preprocessing on the first set of weather information for input to an internal environment model configured to output an estimation result of the internal environment of the shipment; and obtaining an estimation result of the internal environment of the shipment from the internal environment model based on the input of the preprocessed first set of weather information, wherein the first set of weather information is periodically resampled in response to an update to the shipment information of the shipment.

[0016] Aspects of the present disclosure can include a computer program storing instructions for estimating and managing the status of a shipment, the instructions including obtaining shipment information of the shipment; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the location and time interval of the shipment information of the shipment; performing preprocessing on the first set of weather information for input to an internal environment model configured to output an estimation result of the internal environment of the shipment; and obtaining an estimation result of the internal environment of the shipment from the internal environment model based on the input of the preprocessed first set of weather information, wherein the first set of weather information is periodically resampled in response to an update to the shipment information of the shipment. The computer program and the instructions are stored on a non-transitory computer-readable medium and can be executed by one or more processors.

[0017] Aspects of the present disclosure may include a system for estimating and managing the status of goods. The system may include means for obtaining delivery information of the goods, means for extracting a first set of weather information received from one or more databases from one or more locations corresponding to the location and time interval of the delivery information of the goods, means for performing preprocessing on the first set of weather information for input to an internal environment model configured to output an estimation result of the internal environment of the goods, and means for obtaining an estimation result of the internal environment of the goods from the internal environment model based on the input of the preprocessed first set of weather information. The first set of weather information may be periodically resampled in response to an update to the delivery information of the goods.

[0018] Aspects of the present disclosure may include an apparatus configured to estimate and manage the status of goods. The apparatus may include a processor configured to obtain delivery information of the goods, extract a first set of weather information received from one or more databases from one or more locations corresponding to the location and time interval of the delivery information of the goods, perform preprocessing on the first set of weather information for input to an internal environment model configured to output an estimation result of the internal environment of the goods, and obtain an estimation result of the internal environment of the goods from the internal environment model based on the input of the preprocessed first set of weather information. The first set of weather information may be periodically resampled in response to an update to the delivery information of the goods.

Brief Description of the Drawings

[0019]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Best Mode for Carrying Out the Invention

[0020] The following detailed description provides details of the figures and exemplary embodiments of the present application. Reference numerals and descriptions of overlapping elements between the figures are omitted for clarity. The terms used throughout the description are provided as examples and are not intended to be limiting. For example, the use of the term "automated" can include fully automated or semi-automated implementations, including user or administrator control over specific aspects of the implementation, depending on the desired implementation of those skilled in the art practicing the implementation of the present application. The selection can be performed by the user via a user interface or other input means, or can be implemented via a desired algorithm. Exemplary embodiments as described herein can be utilized either alone or in combination, and the functions of those exemplary embodiments can be implemented via any means according to the desired embodiment.

[0021] The exemplary embodiments described herein are described with respect to shipping containers. However, other types of cargo are also available in the exemplary embodiments, and the present disclosure is not limited thereto. The terms "cargo" and "container" can be used interchangeably throughout the present disclosure.

[0022] During the training phase, the data cleaner acquires internal sensor data and external weather data. After cleaning (e.g., by geological and data preparation synchronization), it outputs clean external and internal data at regular intervals. The training phase then trains the internal state estimation model by using the clean external and internal data at regular intervals as the output from the data cleaner. This process updates the model parameters if there is already a pre-existing model. If there is no pre-existing model, this process generates the model.

[0023] Depending on the desired embodiment, the external weather data can be obtained from one or more external servers or databases. The internal sensor data is measured by sensors monitoring one or more loads and the cargo thereon. Such loads can be located on trucks, ships, and / or other locations depending on the desired embodiment.

[0024] FIG. 1 shows an example of an information processing device 1000 according to an exemplary embodiment. The information processing device 1000 can be implemented in any physical system for managing cargo as described herein, such as those described with respect to FIG. 16. Such an information processing device can include a processor 1001, a main storage device 1002 and an auxiliary storage device 1003 for storing local delivery information or weather information, an input device 1004, an output device 1005, and a communication device 1006 for communicating with a communication network and a management device as described in FIGS. 16 and 17.

[0025] FIG. 2 shows a system 100 for estimating the status of cargo in a training phase according to an exemplary embodiment. As shown in the cargo status estimation system 100, there can be one or more cargos 1101 equipped with sensors 1102 that provide internal sensor data 1103 of the cargo 1101. External servers 1104-1, 1104-2, 1104-3 are configured to provide external weather data according to the desired embodiment. The external weather data and the internal sensor data 1103 are provided to a delivery status management server 1100, which takes in the data and preprocesses the data using a data cleaning and region-time synchronization process 1105. The cleaned and synchronized data is provided as regularly cycled cleaned external and internal data 1106. Then, this cleaned external and internal data 1106 is used to train an internal state estimation model (1108) such that, depending on the desired embodiment, it either updates the parameters of an existing internal state estimation model 1107 or generates an internal state estimation model 1107.

[0026] Figure 3 shows a system for estimating the status of goods at the operating stage according to an exemplary embodiment. Specifically, Figure 3 shows other functions of the delivery status management server 1100 to facilitate the estimation of the status of goods for the model 1107 operating in the operating stage. In the operating stage, as described herein, the delivery status management server 1100 requires only the delivery information 1116 of the goods to be monitored and does not require sensor data.

[0027] In addition to the external weather data, the delivery information 1116 of the goods to be estimated is also provided for the data cleaning and region-time synchronization process 1105. The regularly cycled cleaned external data 1106 is used together with the delivery information 1116 and the operation model 1107 to estimate the internal sensor data of the goods to be estimated (1128). The estimation result is then stored as the estimated internal sensor data 1109 and provided to the customer / item identification unit 1111, which incorporates the metadata 1110 for generating the customer / item information 1112, and the customer / item information 1112 is provided to the visualization / input unit 1115 and the relaxation proposal unit 1114.

[0028] The visualization / input unit 1115 is configured to facilitate and display a user interface for displaying the proposal 1118 for relaxation and the customer / item information 1112, and may receive an input regarding the target container state 1117. Further details of the visualization / input unit 1115 are provided in connection with Figure 4.

[0029] The relaxation proposal unit 1114 is configured to refer to a database of relaxation plans 1113 and provide a proposal 1118 cited from the database of relaxation plans 1113 for achieving the target container state 1117 based on the customer / item information 1112 and the desired target container state 1117. Such a proposal is provided to the visualization / input unit 1115 and is called by the user via the user interface as needed.

[0030] FIG. 4 shows a visualization / input unit 1200 according to an exemplary embodiment. Specifically, FIG. 4 shows an example of a user interface for the visualization / input unit 1200.

[0031] Delivery route 1201 shows an exemplary component of a user interface that displays the delivery route of the goods to be tracked. The user can specify "location" and "date and time" by a pointer 1202 that can be implemented by a mouse, a touch screen, or other input means according to the desired implementation.

[0032] If the delivery information is known, it indicates the specified index 1203, location 1204, date and time 1205, and item name 1206 of the goods to be monitored, as well as other information according to the desired embodiment. The delivery information can be obtained from a physical platform and can be input via the visualization / input unit 1200 or by other desired embodiments. The user can edit the index 1203, location 1204, date and time 1205, etc. Such fields can also be filled by the operation of the delivery route 1201. For example, when the start and end dates and locations are supplied, the delivery route / trip can be generated by an algorithm, searching past deliveries, etc. The exemplary embodiment shown in FIG. 4 targets the item name 1206, but other information can also be used according to the desired embodiment. For example, a customer name or other mark can be used to specify this item. Depending on the desired embodiment, the item name 1206 of the container / goods can also be filled using metadata if this field is otherwise empty.

[0033] The target container state can include, according to an exemplary embodiment, an item name 1208, a container temperature 1209, and other information. In the interface for the target container state, the user can specify the desired target value for the container state. For example, the item name 1208 and the container temperature 1209 are specified as the tag names for managing the target, and the temperature inside the container can be set as the target.

[0034] The Estimation Execution 1210 is a button that can generate Estimation Information 1211 and Proposal 1212 when triggered. The Estimation Information 1211 visualizes the estimation information of meteorological data and the management risk (container status) when the Estimation Execution button is pressed. The Proposal 1212 proposes a risk mitigation method using the customer / item name of the container.

[0035] Figure 5 shows an exemplary flowchart of the training phase according to an exemplary embodiment. External meteorological data (e.g., temperature, relative humidity, etc.) 500 and past internal sensor data (e.g., temperature, relative humidity, etc.) 501 are obtained, the past database is referenced, and an attempt is made to synchronize the past external meteorological data and the past internal sensor data to train and learn the relationship between the past external meteorological data and the past internal sensor data.

[0036] For the process of such synchronization, at 502, first, for each date and time in the external meteorological data, a suitable location (e.g., the closest location) of the past internal sensor data is identified. At 503, the flow extracts the external meteorological data at the identified location of the internal sensor data for each date and time of the past internal sensor data.

[0037] After the synchronization of the geologies, the next process includes data preparation (cleaning and resampling of the synchronized past external meteorological data and internal sensor data). At 504, error and outlier removal are performed on the past external meteorological data and the past internal sensor data. The removal of errors and outliers can act on the samples at regular and irregular intervals.

[0038] At 505, a determination is made as to whether the resulting past external meteorological data and past internal sensor data are sampled at regular intervals. If not (No), at 506, an interpolation process is executed to perform interpolation and resampling to correct the data to regular intervals. The resampled and interpolated data is then aligned at 507 to maintain the synchronization between the past external meteorological data and the past internal sensor data.

[0039] The resulting data should be clean external data 508 and clean internal data 509 with a regular period. At 510, the training sample selection unit is executed to remove samples that are not suitable for training according to the desired embodiment. Then, using the remaining training samples, at 511, the container internal state estimation model 512 is trained to estimate the internal sensor data using the external weather data as input.

[0040] The training of this internal state estimation model is performed by using clean external and internal data with a regular period. This process updates the model parameters if the internal state estimation model has been generated previously. If it has not been generated previously, the internal state estimation model is generated.

[0041] The assumed relationship between the internal parameters of the container and the external weather parameters at the location of the container is given by the following. Y = M(X, Ω) Here, Y is the internal parameters such as the temperature and relative humidity of the container. X is the external weather parameters such as the temperature and relative humidity at the location of the container. Ω is other variables that can affect the internal parameters of the container, such as the container type and cargo type.

[0042] Note that the above equation assumes that X and Y correspond to the same location. M is estimated in the training stage, and as a result, a model approximating M, ˆM (circumflex M) is created.

Equation

[0043] Here, ˆM (circumflex M) can be any type of model, and the use of other information Ω by the model ˆM (circumflex M) is optional.

[0044] In use, the trained model, the circumflex M (⌒M), acts on known external weather parameters to calculate a circumflex Y (⌒Y) that is the estimated result of the internal parameters of the container at the location X of the container.

Number

[0045] FIG. 6 shows an exemplary flowchart of an operation phase according to an exemplary embodiment. This flow applies a pre-trained cargo internal state estimation model 512 to estimate internal sensor data from the input of clean external weather data during the operation of the model.

[0046] External weather data (such as temperature, relative humidity, etc.) 601 is synchronized with the delivery information (such as date, location, etc.) 602 of a physical system (such as a delivery ship, truck, docking port, etc.) that manages the cargo to be estimated. For the synchronized geolog, at 603, the flow identifies the preferred location (such as the nearest location) of the delivery information for each date and time in the external weather data. At 604, the flow extracts the external weather data at the identified location of the internal sensor data for each date and time.

[0047] When the corresponding external weather data is extracted, data preparation (cleaning and resampling) is performed. At 605, error and outlier removal is performed on the synchronized external weather data and delivery information. At 606, a determination is made as to whether the external weather data is sampled at regular intervals. If it is not sampled at regular intervals (No), the flow proceeds to 607, where the external weather data is interpolated and resampled to convert it to regular intervals. At 608, the resulting data is the cleaned external weather data with a regular period.

[0048] At 609, the internal state estimation model 512 takes in regularly periodic cleaned external weather data, estimates internal sensor data, and provides an estimation result of the internal sensor data (e.g., temperature, relative humidity).

[0049] FIG. 7 is an exemplary data set of external weather data 1500 according to an exemplary embodiment. Examples of external weather data can include the temperature at a date and time corresponding to geographical information (e.g., in the example of FIG. 7, the location). In the example of FIG. 7, the external weather data is collected at one location. However, the external weather data can be collected across multiple external servers that also have geographical information (e.g., server locations).

[0050] The external weather data 1500 can include, but is not limited to, fields such as an index of entry 1501, its weather location 1502, date and time 1503, and temperature 1504. Other fields such as relative humidity can also be used, and the present disclosure is not limited thereto. The location 1502 can include coordinates such as those from a Global Positioning System (GPS) or other methods according to the desired embodiment.

[0051] FIG. 8 is an exemplary data set of regularly periodic clean external weather data 1600 according to an exemplary embodiment. Exemplary fields of the regularly periodic clean external data 1600 can include, but are not limited to, an index of entry 1601, location 1602, date 1603, temperature 1604, weather date and time 1605, and item name 1606. The item name 1606 can include metadata according to the desired embodiment, identification information of goods / containers, customer names, and the like.

[0052] In the example of FIG. 8, the meteorological data may include the temperature 1604 from the meteorological model used for interpolation and the corresponding meteorological date and time 1605. The temperature 1604, together with the meteorological date and time 1605, may be shown on the estimated information part of the visualization / input unit. The example of FIG. 8 also shows the case where all data fields of past processes (such as dates and others) are carried forward. Some fields may also be used to detect the customer name / item name in the next process.

[0053] FIG. 9 is an exemplary dataset of estimated internal sensor data 1800 according to an exemplary embodiment. The estimated internal sensor data 1800 may include fields such as an index 1801, a position 1802, a date 1803, a temperature 1804, a meteorological day 1805, an estimated container temperature 1806, an item name 1807, etc., but is not limited thereto. Other fields (such as relative humidity) are also available and the present disclosure is not limited thereto.

[0054] The container / cargo temperature is the data of the estimated internal sensor data 1800 in the example of FIG. 9 and may be shown on the estimated information part within the visualization / input unit together with the meteorological date and time. Further, this example of FIG. 9 shows the case where all data fields of past processes (such as dates and others) are carried forward. Some fields may also be used to determine the mitigation method in the next process.

[0055] FIG. 10 is an exemplary flowchart of customer / item specifications according to an exemplary embodiment. This flow designates the item name of the container / cargo using metadata when the item name field of the container / cargo is empty. The item name is an example and other information may be used according to the desired embodiment. For example, the customer name may also be used to specify the item.

[0056] At 1023, the flow captures the estimated internal sensor data 1021, processes it, and determines whether it contains the customer name / item name. If it contains the customer name / item name (Yes), the flow proceeds to 1024 and exports the estimated internal sensor data as customer / item information. If it does not contain it (No), the flow proceeds to 1025. At 1025, the flow captures the metadata (e.g., customer name, item name, custom log, etc.) 1022 and specifies the customer name / item name by checking the metadata (e.g., by matching using the transport time and product name in the custom log). At 1026, the flow exports the customer / item information by adding the customer name / item name to the estimated internal sensor data. At 1027, the customer / item information 1027 is attached to the internal sensor data.

[0057] Figure 11 is an example of metadata 2000 according to an exemplary embodiment. The metadata 2000 may include, but is not limited to, fields such as a location 2001, a date 2002, and an item name 2003. The item name 2003 can indicate the type of item within the container / cargo or can be other information according to the desired embodiment.

[0058] The metadata 2000 includes the customer / item name 2003 and other information for detecting the customer / item name 2003 from other information. In the example of Figure 11, the metadata 2000 has the form of a custom log. The metadata has some information (location, data) associated with the item name. Thus, the customer / item identification unit can detect the item name by checking the relationship between the delivery information and the metadata 2000.

[0059] Figure 12 is an exemplary data set of customer / item information 2100 according to an exemplary embodiment. The customer / item information 2100 may include, but is not limited to, fields such as an index of an entry 2101, a location 2102, a date 2103, a temperature 2104, weather data 2105, a container temperature 2106, and an item name 2107.

[0060] In the example of FIG. 12, item name 2107 (e.g., water) is an example of customer / item information within this table. Further, the example of this FIG. 12 also shows the case where all data fields of past processes (e.g., date and others) are inherited. Some fields can also be used to determine relaxation methods in the next process.

[0061] FIG. 13 is an exemplary flowchart of a relaxation proposal according to an exemplary embodiment. First, at 1303, the flow receives customer / item information 1301 and target container / cargo status 1302 specified in the user interface. Next, at 1304, the flow examines the satisfied conditions and obtains the corresponding plan from the relaxation plan database 1305. At 1306, the obtained plan is output to be displayed on the user interface as a selectable proposal 1307 that is selected and executed to mitigate container / cargo damage caused by weather. Depending on the desired embodiment, the proposal may also include customer / item information for visualization in the user interface.

[0062] FIG. 14 is an exemplary dataset of a relaxation plan 2400 according to an exemplary embodiment. The relaxation plan 2400 may include fields such as conditions 2401 required for the plan and corresponding proposals / plans 2402, but is not limited thereto. The relaxation plan 2400 is managed by a delivery status management server or other server / database architecture according to the desired embodiment. In the example of FIG. 14, the relaxation plan (referred to as "plan" in this example) is included with each selection condition (referred to as "condition" in this example).

[0063] FIG. 15 is an exemplary dataset of proposal information 2500 according to an exemplary embodiment. The proposal information 2500 may include, but is not limited to, an item name 2501 and fields such as a corresponding plan 2502 for the item name. This example shows a selected proposal from a previous process. The plan is a defined field that includes proposal information and is shown on the proposal interface of the visualization / input unit. The item name can be used to explain whether it is required for a specific action shown in the plan. This field can be used to show multiple customers / items to the visualization / input unit.

[0064] Through the exemplary embodiments described herein, thereby, weather data acquisition without using sensors can be facilitated. The user can quickly estimate the weather data inside the container just by entering the delivery date and the origin-destination (or route or itinerary). The user does not need to attach sensors to their ship. In addition, the user can forecast the weather data inside the container of the ship planned for the future when future data is used in weather data.

[0065] Through the exemplary embodiments described herein, risk estimation in any route can be facilitated. The user can estimate the risk inside the container / cargo from the weather data by a pre-trained model. The container weather estimation for future deliveries facilitates risk estimation and mitigation by preparing an appropriate amount of drying material for ships where future humidity is important. In addition, the user can deal with insurance companies by using the estimated risk (value) inside a specific container.

[0066] Through the exemplary embodiments described herein, thereby, risk mitigation can be facilitated. The user can know the risk mitigation method inside the container / cargo by entering the delivery date and the origin-destination (or route or itinerary).

[0067] Through the exemplary embodiments described herein, customer / item information can be identified. A user can estimate the weather data / risk inside a container / cargo corresponding to the customer / item information even if they do not own the container / cargo. Such an ability is based substantially or entirely on publicly available information and is also useful for government or regulatory agencies aiming to identify high-risk containers or routes, or entities attempting to predict supply chain delays due to adverse conditions.

[0068] FIG. 16 shows a plurality of physical systems networked to a management device according to an exemplary embodiment. One or more physical systems 1621 (e.g., cargo ships, docking ports, trucks, etc.) that carry one or more loads are communicably connected to a network 1620 (e.g., a local area network (LAN), a wide area network (WAN)) via corresponding network interfaces of sensor systems installed in the physical systems 1621 connected to the management device 1622. The one or more systems 1621 may or may not be associated with sensors, depending on the desired embodiment. The management device 1622 manages a database 1623 that includes past data collected from the sensor systems of each of the physical systems 1621. In an alternative exemplary embodiment, data from the sensor systems of the physical systems 1621 can be stored in a central repository or central database, such as a proprietary database that captures data from the physical systems 1621, or in a system such as an enterprise resource planning system, and the management device 1622 can access and retrieve data from the central repository or central database. The sensor systems of the physical systems 1621 can include, but are not limited to, gyroscopes, accelerometers, Global Positioning System (GPS), thermometers, hygrometers, or any type of sensor capable of measuring one or more of temperature, humidity, gas levels (e.g., CO2 gas), etc., to facilitate the desired embodiments. As described herein, the management device 1622 can be configured to reach an external server to obtain appropriate weather data.

[0069] FIG. 17 is a diagram showing an exemplary computing environment having an exemplary computer device suitable for use in some exemplary embodiments, such as the management device 1622 shown in FIG. 16. The computer device 1705 in the computing environment 1700 can include one or more processing units, cores, or processors 1710, memory 1715 (e.g., RAM, ROM, and / or the like), internal storage 1720 (e.g., magnetic, optical, solid-state storage, and / or organic), and / or an I / O interface 1725, any of which can be coupled on a communication mechanism or bus 1730 for communicating information or can be incorporated into the computer device 1705. The I / O interface 1725 is further configured to receive images from a camera or provide images to a projector or display, depending on the desired implementation.

[0070] Computer device 1705 may be communicatively coupled to an input / user interface 1735 and an output device / interface 1740. One or both of the input / user interface 1735 and the output device / interface 1740 may be a wired or wireless interface and may be removable. The input / user interface 1735 may include any physical or virtual device, component, sensor, or interface (e.g., buttons, touch screen interface, keyboard, pointing / cursor control, microphone, camera, Braille, motion sensor, optical reader, and / or the like) that can be used to provide input. The output device / interface 1740 may include a display, television, monitor, printer, speaker, Braille, or the like. In some exemplary embodiments, the input / user interface 1735 and the output device / interface 1740 may be incorporated with or physically coupled to the computer device 1705. In other exemplary embodiments, other computer devices may function as or provide the functionality of the input / user interface 1735 and the output device / interface 1740 for the computer device 1705.

[0071] Examples of computer device 1705 may include, but are not limited to, highly mobile devices (e.g., smartphones, devices mounted on vehicles and other machines, devices held by persons 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 incorporated therein and / or televisions with one or more processors coupled thereto, radios, and the like).

[0072] Computer device 1705 can be communicatively coupled to external storage 1745 and network 1750 (e.g., via I / O interface 1725) for communication with any number of network-connected components, devices, and systems, including one or more computer devices of the same or different configurations. Computer device 1705 or any other connected computer device can function as, provide services as, or be referred to by the names of, a server, client, thin server, general-purpose machine, dedicated machine, or others.

[0073] I / O interface 1725 can include, but is not limited to, wired and / or wireless interfaces that use any communication or I / O protocol or convention (e.g., Ethernet, 802.11x, Universal System Bus, WiMax, modem, cellular network protocol, and the like) for information communication to and / or from at least all connected components, devices, and networks in computing environment 1700. Network 1750 can be any network or combination of networks (such as, for example, the Internet, local area network, wide area network, telephone network, cellular network, satellite network, and the like).

[0074] Computer device 1705 can use and / or communicate using computer-usable media or computer-readable media, including temporary media and non-temporary media. Temporary media includes transmission media (e.g., metal cables, optical fibers), signals, carrier waves, and the like. Non-temporary media includes magnetic media (e.g., disks and tapes), optical media (e.g., CD-ROM, digital video disk, Blu-ray (registered trademark) disk), solid-state media (e.g., RAM, ROM, flash memory, solid-state storage), and other non-volatile storage or memory.

[0075] Computer device 1705 can be used to implement techniques, methods, applications, processes, or computer-executable instructions in some exemplary computing environments. The computer-executable instructions can be retrieved from a temporary medium, stored in a non-temporary medium, and retrieved therefrom. The executable instructions can be derived from one or more of any programming language, scripting language, and machine language (such as C, C++, C#, Java, Visual Basic, Python, Perl, JavaScript, etc.).

[0076] Processor 1710 can run under any operating system (OS) (not shown) in a native or virtual environment. One or more applications can be deployed that include a logical unit 1760, an application programming interface (API) unit 1765, an input unit 1770, an output unit 1775, and an inter-unit communication mechanism 1795 for inter-unit communication, communication with the OS, and communication with other applications (not shown). The units and elements described above can be different in design, function, configuration, or implementation and are not limited to the above description. Processor 1710 can be in the form of a hardware processor such as a central processing unit (CPU), or can be a combination of hardware units and software units.

[0077] In some exemplary embodiments, when the API unit 1765 receives information or execution instructions, it can communicate them to one or more other units (e.g., the logic unit 1760, the input unit 1770, the output unit 1775). In some examples, the logic unit 1760 can control the information flow between units and, in some of the exemplary embodiments described above, can be configured to direct the services provided by the API unit 1765, the input unit 1770, and the output unit 1775. For example, one or more processes or execution flows can be controlled by the logic unit 1760, either alone or in conjunction with the API unit 1765. The input unit 1770 may be configured to obtain inputs for the calculations described in the exemplary embodiments, and the output unit 1775 may be configured to provide outputs based on the calculations described in the exemplary embodiments.

[0078] The processor 1710 can be configured to execute a method or instructions to estimate and manage the status of the goods, the method or instructions including obtaining the goods delivery information 602 as shown in FIG. 6, extracting a first set of weather information 601 received from one or more databases from one or more locations corresponding to the location and time interval of the goods delivery information as indicated by the external server 1104-1 and described with respect to FIGS. 6 and 7, performing preprocessing on the first set of weather information for input to an internal environment model configured to output an estimation result of the internal environment of the goods as shown at 605-608 in FIG. 6, and obtaining an estimation result of the internal environment of the goods from the internal environment model based on the input of the preprocessed first set of weather information and generating estimated internal sensor data 611 as shown at 609 and 512 in FIG. 6. Depending on the desired embodiment, the flow of FIG. 6 is executed with real-time updates, whereby the first set of weather information is periodically resampled in response to updates to the goods delivery information.

[0079] The processor 1710 may be configured to execute the method or instructions as described above, and the internal environment model preprocesses the past sensor data as shown in 504-508 of FIG. 5 from a database including past weather information as shown in 500 of FIG. 5 for past goods and past sensor data as shown in 501 of FIG. 5, and preprocesses a second set of past weather information corresponding to the location and time interval of the past sensor data of the past goods or the preprocessed past sensor data as shown in 504-509 of FIG. 5, and trains the internal environment model to learn the preprocessed past sensor data as an output from the input of the second cleaned set of past weather information as shown in 510-512 of FIG. 5.

[0080] The processor 1710 may be configured to execute the method or instructions as described above, and as shown in 504 of FIG. 5, the preprocessing of the past sensor data may include cleaning the past sensor data through removal of errors and outliers, and interpolating and resampling the past sensor data to form it into a regular time series as shown in 505-509 of FIG. 5.

[0081] The processor 1710 may be configured to execute the method or instructions as described above, and as shown in 504-508 of FIG. 5, the preprocessing of the second set of past weather information may include interpolating the second set of past weather information to align the time intervals of the past sensor data or the preprocessed sensor data.

[0082] As described herein, the past sensor data 501 may include any type of environmental variable measured by a sensor of past goods. Depending on the desired embodiment, such environmental variables may include, but are not limited to, temperature, relative humidity, etc.

[0083] Processor 1710 may be configured to execute the methods or instructions as described above, and may further include updating the internal environment model 1107 using the first preprocessed set of meteorological information, as described with respect to FIG. 2. That is, if the internal state estimation model 1107 has been previously generated, the update to the meteorological information can be used to further update the internal environment model.

[0084] Processor 1710 may be configured to execute the methods or instructions as described above, and the preprocessing of the first set of meteorological information may include cleaning the first set of past meteorological information through removal of errors and outliers, as shown at 605 in FIG. 6, and interpolating or resampling the first set of meteorological information to match the time interval, as shown at 607 in FIG. 6.

[0085] Depending on the desired embodiment, the meteorological data 601 may include time and meteorological data such as temperature, relative humidity, and other things depending on the desired embodiment and as shown in FIG. 7.

[0086] Depending on the desired embodiment, the delivery information may include trip information (e.g., delivery route or origin / destination of the cargo) and time information corresponding to the trip information of the cargo.

[0087] Depending on the desired embodiment, the relaxation plan is retrieved from the database and executed in response to the estimated result of the internal environment exceeding a predetermined parameter, as shown in FIG. 4 and based on the preconditions as shown in FIGS. 14 and 15.

[0088] 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 defined set of steps leading to a desired end state or result. In an exemplary embodiment, the steps executed require physical manipulation of physical quantities in order to effect a tangible result.

[0089] Unless otherwise noted, as will be apparent from the description, throughout this specification, descriptions using terms such as "processing," "computing," "calculating," "determining," "displaying," or the like may include actions and processes of a computer system or other information processing device that manipulates data represented as physical (electronic) quantities within the registers and memories of the computer system and transforms them into other data similarly represented as physical quantities within the memories or registers or other information storage devices, transmission devices, or display devices of the computer system.

[0090] Exemplary embodiments may further relate to an apparatus for performing operations herein. The apparatus may be specially constructed for the required purpose, or may include one or more general-purpose computers selectively activated or reconfigured by one or more computer programs. Such computer programs 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. The computer-readable signal medium may include media such as carrier waves. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. The computer program may include a software-only implementation including instructions to perform the operations of the desired embodiment.

[0091] Various general-purpose systems may be used with the programs and modules according to the examples herein, or it may be convenient as a result to construct specialized apparatuses by performing the steps of the desired method. Further, no reference is made to any particular programming language, and it will be understood that various programming languages may be used to implement the techniques of the exemplary embodiments as described herein. The instructions of the programming language may be executed by one or more processing devices such as, for example, a central processing unit (CPU), a processor, or a controller.

[0092] As is known in the art to which the present invention pertains, the operations described above can be performed by hardware, software, or some combination of software and hardware. While various aspects of the exemplary embodiments may be implemented using circuits and logic devices (hardware), other aspects may be implemented using instructions stored on a machine-readable medium (software) that, when executed by a processor, cause the processor to execute a method for implementing the present application. Further, some exemplary embodiments of the present application may be executed by hardware only, while other exemplary embodiments may be executed by software only. Additionally, the various functions described may be performed by a single unit or may be distributed across multiple components in any number of ways. When executed by software, the method may be executed by a processor, such as a general-purpose computer, based on instructions stored on a computer-readable medium. Optionally, the instructions may be stored on the medium in a compressed and / or encrypted format.

[0093] Furthermore, other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the technology of the present application. The various aspects and / or components of the exemplary embodiments described may be used singly or in any combination. The specification and exemplary embodiments are intended to be considered as examples only, and the true scope and spirit of the present application are indicated by the following claims.

Description of Reference Numerals

[0094] 1000 Information Processing Device 1001 Processor 1002 Main Memory Device 1003 Auxiliary Memory Device 1004 Input Device 1005 Output Device 1006 Communication Device 1100 Delivery Status Management Server 1101 Goods 1102 Sensor 1103 External meteorological data 1111 Customer / Item Identification Section 1114 Mitigation Proposal Section 1115 Visualization / Input Unit 1620 Network 1623 Database 1705 Computer Device 1710 Processor 1715 Memory 1720 Internal Storage 1725 I / O Interface 1735 Input / User Interface 1740 Output Device / Interface 1745 External Storage 1750 Network 1760 Logic Unit 1765 API Unit 1770 Input Unit 1775 Output Unit

Claims

1. A method for estimating and managing the status of a shipment, comprising: obtaining delivery information for the cargo; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the locations and time intervals of the delivery information for the shipment; performing pre-processing on the first set of meteorological information for input to an interior environment model configured to output an estimate of the interior environment of the cargo; obtaining the estimation of the internal environment of the cargo from an internal environment model based on the input of the pre-processed first set of meteorological information; the first set of weather information is periodically resampled in response to updates to the delivery information for the shipment; The internal environment model comprises: From the database containing past weather information and past sensor data of past cargoes, performing the pre-processing on the past sensor data; performing the pre-processing on a second set of the historical weather information corresponding to the location and the time interval of the historical sensor data or pre-processed historical sensor data of the historical shipment; training the internal environment model to learn the preprocessed historical sensor data as output from the second set of inputs of the preprocessed historical weather information; The method is trained by a process including:

2. The pre-processing of the historical sensor data includes cleaning the historical sensor data through removal of errors and outliers; interpolating and resampling the historical sensor data to form a regular time series of the historical sensor data; The method of claim 1 , comprising:

3. 2. The method of claim 1, wherein the pre-processing of the second set of historical weather information includes interpolating the second set of historical weather information to align the time intervals of the historical sensor data or the pre-processed sensor data.

4. The method of claim 1 , wherein the historical sensor data comprises environmental variables measured by sensors on a past cargo.

5. A method for estimating and managing the status of cargo, comprising: obtaining delivery information for the cargo; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the locations and time intervals of the delivery information for the shipment; performing pre-processing on the first set of meteorological information for input to an interior environment model configured to output an estimate of the interior environment of the cargo; obtaining the estimation of the internal environment of the cargo from an internal environment model based on the input of the pre-processed first set of meteorological information; the first set of weather information is periodically resampled in response to updates to the delivery information for the shipment; The method further comprising updating the internal environment model using the pre-processed first set of weather information.

6. The pre-processing of the first set of weather information further comprises: cleaning the first set of weather information through removal of errors and outliers; interpolating or resampling the first set of weather information to match the time interval; The method of claim 1 or 5, comprising:

7. The method of claim 1 or 5, wherein the weather information includes time and meteorological data.

8. The method of claim 1 or 5, wherein the delivery information includes journey information and time information corresponding to the journey information for the shipment.

9. 1. A computer program comprising instructions for estimating and managing the status of a shipment, the computer program comprising: obtaining delivery information for the cargo; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the locations and time intervals of the delivery information for the shipment; performing pre-processing on the first set of meteorological information for input to an interior environment model configured to output an estimate of the interior environment of the cargo; obtaining the estimation of the internal environment of the cargo from an internal environment model based on the input of the pre-processed first set of meteorological information; the first set of weather information is periodically resampled in response to updates to the delivery information for the shipment; The internal environment model comprises: From the database containing past weather information and past sensor data of past cargoes, performing the pre-processing on the past sensor data; performing the pre-processing on a second set of the historical weather information corresponding to the location and the time interval of the historical sensor data or pre-processed historical sensor data of the historical shipment; training the internal environment model to learn the preprocessed historical sensor data as output from the second set of inputs of the preprocessed historical weather information; A computer program that is trained by a process including:

10. A computer program comprising instructions for estimating and managing the status of a shipment, the instructions comprising: obtaining delivery information for the cargo; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the locations and time intervals of the delivery information for the shipment; performing pre-processing on the first set of meteorological information for input to an interior environment model configured to output an estimate of the interior environment of the cargo; obtaining the estimation of the internal environment of the cargo from an internal environment model based on the input of the pre-processed first set of meteorological information; the first set of weather information is periodically resampled in response to updates to the delivery information for the shipment; The computer program product, the instructions further comprising updating the internal environment model with the pre-processed first set of the weather information.

11. one or more physical systems associated with the cargo; and a management device configured to estimate and manage the status of the cargo, the management device comprising:

1. A processor comprising: obtaining delivery information for the cargo; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the locations and time intervals of the delivery information for the shipment; performing pre-processing on the first set of meteorological information for input to an interior environment model configured to output an estimate of the interior environment of the cargo; and obtaining the estimation of the interior environment of the cargo from an interior environment model based on the input of the pre-processed first set of meteorological information; the first set of weather information is periodically resampled in response to updates to the delivery information for the shipment; The internal environment model comprises: From the database containing past weather information and past sensor data of past cargoes, performing the pre-processing on the past sensor data; performing the pre-processing on a second set of the historical weather information corresponding to the location and the time interval of the historical sensor data or pre-processed historical sensor data of the historical shipment; training the internal environment model to learn the preprocessed historical sensor data as output from the second set of inputs of the preprocessed historical weather information; The system is trained by a process that includes:

12. One or more physical systems associated with a cargo; and a management device configured to estimate and manage the status of the cargo, the management device comprising:

1. A processor comprising: obtaining delivery information for the cargo; extracting a first set of weather information received from one or more databases from one or more locations corresponding to the locations and time intervals of the delivery information for the shipment; performing pre-processing on the first set of meteorological information for input to an interior environment model configured to output an estimate of the interior environment of the cargo; and obtaining the estimation of the interior environment of the cargo from an interior environment model based on the input of the pre-processed first set of meteorological information; the first set of weather information is periodically resampled in response to updates to the delivery information for the shipment; The processor is further operable to update the internal environment model using the pre-processed first set of weather information.

Images