Systems and methods for container condition determination in transport refrigeration

Abstract

Systems and methods for container condition determination are disclosed. In some embodiments, a system includes one or more optical sensors; at least one processor; and a memory storing instructions executable by the at least one processor, the instructions, when executed, causing the system to: obtain image data of a container from the one or more optical sensors; determine, from the image data, location information of one or more items located within the container; determine, from the image data, air delivery information in the container; determine, using the location information of the one or more items and the air delivery information, airflow characteristics of the container; and determine, using the location information of the one or more items and the airflow characteristics, a probability that an item of the one or more items is damaged.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 201840, filed on May 14, 2021, the contents of which are hereby incorporated in their entirety. Technical Field

[0003] This invention generally relates to transport refrigeration, and more particularly to determining the condition of containers in transport refrigeration. Background Technology

[0004] For many years, computer models have been used to create simulations of the thermal behavior of refrigerated transport of perishable goods on a finite-project basis. Using such models on a routine operational basis may be impractical because it is difficult to efficiently obtain the inputs required to ensure the accuracy of simulations using such models. Summary of the Invention

[0005] This disclosure relates to methods, apparatus, and / or systems for determining container condition.

[0006] In some embodiments, a system for determining the condition of a container includes: one or more optical sensors; at least one processor; and a memory storing instructions executable by the at least one processor, the instructions, when executed, causing the system to: acquire image data of a container from the one or more optical sensors; determine position information of one or more items located within the container from the image data; determine air delivery information in the container from the image data; determine airflow characteristics of the container using the position information of the one or more items and the airflow characteristics; and determine the probability that an item in the one or more items is damaged using the position information of the one or more items and the airflow characteristics.

[0007] In some embodiments, the system is configured to determine the condition of one or more components of the container based on image data of the container, the condition of the one or more components indicating the presence or absence of damage to the one or more components; and to determine the condition of the container based on the condition of the one or more components.

[0008] In some embodiments, the system is configured to determine the loading mode of the container based on the location information of one or more items located within the container.

[0009] In some embodiments, the system is configured to obtain environmental information within the container from sensors placed within the container; and to determine temperature control performance within the container based on the obtained environmental information; such that the probability of damage to the item is further determined based on the environmental information or the temperature control performance.

[0010] In some embodiments, the system is configured to determine thermal information for the container based on the image data; and to generate one or more of a thermal simulation, an airflow simulation, or a loading mode simulation based on one or more of the thermal, airflow, or loading information.

[0011] In some embodiments, a method for determining the condition of a container is implemented in a system including one or more optical sensors, at least one processor, and a memory storing instructions. The method includes: acquiring image data of a container from the one or more optical sensors; determining position information of one or more items located within the container from the image data; determining air delivery information within the container from the image data; determining airflow characteristics of the container using the position information of the one or more items and the airflow characteristics; and determining the probability that an item among the one or more items is damaged using the position information of the one or more items and the airflow characteristics.

[0012] In some embodiments, a non-transitory computer-readable storage medium storing program instructions, the program instructions being computer-executable to perform: acquiring image data of a container from one or more optical sensors; determining position information of one or more items located within the container from the image data; determining air delivery information in the container from the image data; determining airflow characteristics of the container using the position information of the one or more items and the air delivery information; and determining the probability that an item in the one or more items is damaged using the position information of the one or more items and the airflow characteristics.

[0013] Various other aspects, features, and advantages of the invention will become apparent from the detailed description and accompanying drawings. It should also be understood that the foregoing general description and the following detailed description are exemplary and not intended to limit the scope of the invention. Attached Figure Description

[0014] Figure 1 An example of a system for determining container conditions is shown according to one or more embodiments.

[0015] Figure 2 Example operations are shown by a system for determining container conditions, according to one or more embodiments.

[0016] Figure 3 Example operations are shown by a system for determining container conditions, according to one or more embodiments.

[0017] Figure 4 Example operations are shown by a system for determining container conditions, according to one or more embodiments.

[0018] Figure 5 Example operations are shown by a system for determining container conditions, according to one or more embodiments.

[0019] Figure 6 Example operations are shown by a system for determining container conditions, according to one or more embodiments.

[0020] Figure 7A -D illustrates an example of operations performed by a system for determining container conditions according to one or more embodiments.

[0021] Figure 8 A diagram illustrating a method for determining container condition according to one or more embodiments.

[0022] Figure 9 Examples of computer systems that can be used to implement aspects of the techniques described herein are shown. Detailed Implementation

[0023] In the following description, numerous specific details are set forth for purposes of explanation in order to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will appreciate that embodiments of the invention may be practiced without these specific details or with equivalent arrangements. In other instances, well-known structures and arrangements are illustrated in block diagram form to avoid unnecessarily obscuring embodiments of the invention.

[0024] Figure 1 An example of a system 100 for determining container condition according to one or more embodiments is shown. In some embodiments, system 100 may be configured to automatically capture, interpret, analyze, and report information related to the transport of containers and details of the transport using the captured information. In some embodiments, system 100 may provide simulation and visualization of the transport, which may facilitate both assessment of individual transports and process improvement activities. System 100 may include an analysis system 110, one or more sensors 102, and / or other components. Other components known to those skilled in the art may be included in system 100 to collect, process, transmit, receive, acquire, and provide information used in conjunction with the disclosed embodiments. Additionally, system 100 may also include other components that perform or assist in performing one or more processes consistent with the disclosed embodiments.

[0025] In some embodiments, system 100 may include a network 190 connecting one or more components of system 100. In some embodiments, network 190 may be any type of network configured to provide communication between components of system 100. For example, network 190 may be any type of network (including infrastructure) that provides communication, exchanges of information, and / or facilitates the exchange of information, such as the Internet, local area network, near field communication (NFC), optical code scanner, cellular network, text messaging system (e.g., SMS, MMS), frequency (RF) link, Bluetooth®, Wi-Fi, or other suitable connections that enable the sending and receiving of information between components of system 100. It will be understood that this is not intended to be limiting, and the scope of this disclosure includes implementations in which one or more client components of system 100 are operatively linked via some other communication medium.

[0026] In some embodiments, the analysis system 110 includes an image module 120, a parameter module 130, an airflow determination module 150, a thermal information module 160, a loading mode module 170, an analysis module 180, a feedback module 182, and / or other components. In some embodiments, the analysis system 110 may include computing resources, such as a processor and memory devices for storing instructions (e.g., referred to herein as...). Figure 9 The computing system 900 is described. The processor can be configured to execute software instructions to perform various operations of the system 100. The computing resources may include software instructions used to perform operations of modules 110, 120, 130, 150, 160, 170, 180, 182 and / or other components of the system 100.

[0027] Image module 120 can be configured to acquire image data of containers, container components, and / or cargo contents. "Container" can refer to a transport container, trailer, intermodal transport container, ocean container, truck, and / or other receptacle that can be used to store and / or transport cargo by road, rail, air, or sea. Containers can be refrigerated or unrefrigerated. "Cargo contents" and "cargo articles" refer to articles located within the container, articles to be loaded (placed) within the container, and / or articles unloaded (removed) from the container.

[0028] In some embodiments, one or more image data may be of the interior, exterior, and / or surrounding area of ​​the container. In some embodiments, the image data may be obtained from sensor 102, an image database, and / or other databases located within or outside system 100. Sensor 102 is configured to generate an output signal that conveys information related to the container, container components, and / or cargo contents. Sensor 102 may include one or more of the following: optical sensors, image or video capturing devices, thermal imaging sensors, depth sensors, scanners, LiDAR sensors, RADAR sensors, 3D capturing devices, infrared light sensors, hyperspectral imagers, multispectral imagers, and / or other sensors. In some embodiments, sensor data obtained from sensor 102 may be processed (e.g., using references herein). Figure 9 The processor 910 described is used to extract image information. In some embodiments, sensor data obtained by sensor 102 may include images, videos, multidimensional depth images, thermal images, infrared light measurements, light reflection time measurements, radio wave measurements, range, angles, and / or other sensor data. In some embodiments, multiple sensor data from multiple sensors of sensor 102 may be combined to extract information. For example, images from different locations and angles, multidimensional depth images, thermal images, range, angles, and / or other image data obtained from sensor 102 may be combined to provide information about a container, container assembly, or a particular cargo item.

[0029] In some embodiments, sensor 102 may be positioned at any location that allows sensor measurements of containers, container assemblies, and cargo items. For example, one or more sensors of sensor 102 may be located on a machine (e.g., a forklift, etc.) used for loading cargo contents at a receiving dock, loading dock, container door, loading area, or storage area.

[0030] In some embodiments, parameter module 130 is configured to acquire one or more parameters related to the container and / or cargo. In some embodiments, parameter module 130 may be configured to extract information (e.g., to detect, identify, or determine the position and orientation of an object in image data acquired from sensor 102) from a data image. In some embodiments, parameter module 130 may extract information by comparing image data with images from an image database. In some embodiments, computer vision techniques may be used to process the image data to detect, identify, or determine position or orientation. For example, image data may be combined, filtered, and processed to identify objects (e.g., containers, container components, and / or cargo). Once identified, the object can be measured, and its position and orientation extracted.

[0031] For example, in some embodiments, parameter module 130 may be configured to process image data using keyframe extraction techniques to determine which frames will be used for evaluation. For example, in some embodiments, parameter module 130 may be configured to filter image data based on one or more of motion detection, object detection, image quality, etc. For example, in some embodiments, parameter module 130 may be configured to use frames that do not have a predetermined level of movement and / or do not have a specific object (e.g., a forklift image, a person image, or other objects in the image). In some embodiments, parameter module 130 may be configured to use monocular depth measurement techniques (e.g., perspective cues) to locate appropriate guidelines and / or calculate depth. For example, visual gradients can be used to locate guidelines, product edges, trailer heads, and / or other information.

[0032] In some embodiments, parameter module 130 may include a machine learning system for extracting information from image data of the container. The machine learning system may use one or more of supervised learning, semi-supervised learning, unsupervised learning, reinforcement learning, and / or other machine learning techniques. In some embodiments, the machine learning model may include decision trees, support vector machines, regression analysis, Bayesian networks, random forest learning, dimensionality reduction algorithms, boosting algorithms, artificial neural networks (e.g., fully connected neural networks, deep convolutional neural networks, or recurrent neural networks), deep learning, and / or other machine learning models.

[0033] The parameter module 130 can be configured to determine one or more container parameters based on the output signal (e.g., image data) from the sensor 102. For example, the parameter module 130 can detect, locate, or determine that a container is present in the vicinity of the sensor 102 (e.g., in a receiving dock). Container parameters may include location information, identification information, container component information, and / or other container parameters.

[0034] In some embodiments, container location information may include the container's physical location relative to the receiving dock (e.g., approaching, leaving, docking), relative to other containers / vehicles in the area, or relative to the overall physical location of the container. For example, parameter module 130 may determine whether the container is docked correctly / incorrectly (e.g., by measuring clearance) or may provide guidance during docking. In some embodiments, identification information may include the container's size, shape, operator, manufacturer, brand, model, ID number, markings, refrigerator manufacturer, refrigerator model, refrigerator ID, and / or any other identification information. In some embodiments, as described above, identification information may be extracted from sensor 102 (e.g., through image and text processing) and / or database information.

[0035] Figure 2Example operations performed by a system 100 for container condition determination according to one or more embodiments are shown. Parameter module 130 is configured to determine trailer identification information. For example, such as... Figure 2 As shown, the identification information determined by parameter module 130 includes the trailer's location (dock number 201), trailer operator 202, trailer manufacturer 204, trailer number 206, refrigeration compartment manufacturer 208, sign 210, control panel 212, trailer operator and number 214 (obtained from inside the trailer). In some embodiments, one or more features may be used to identify the container, refrigeration unit, manufacturer, or model (e.g., grille style, trim type, etc.). This can be used where the name, sign, or identification information is unclear or unavailable.

[0036] In some embodiments, the parameter module 130 is configured to determine the configuration of the container. In some embodiments, determining the container configuration includes identifying one or more components of the container (e.g., determining the presence, type, location, and / or quantity of one or more components of the container). Components of the container may include a rear or side door, air chute, ceiling, partition, track, shelf, wall, slide, floor, air delivery points, refrigeration unit, empty space, sensors, and / or one or more other components of the container. In some embodiments, determining container parameters may include determining air delivery information within the container based on image data. For example, the parameter module may be configured to detect air delivery points within the container. In some embodiments, the air delivery information may include one or more of the following: location, number of air delivery points, type of air delivery, and / or other information within the container.

[0037] In some embodiments, parameter module 130 may use the output signal from sensor 102 to determine the condition (e.g., physical, thermal, or other condition) of a component in the container or container assembly. In some embodiments, the container condition may be determined based on container parameters (as described above). For example, parameter module 130 may assess the condition of one or more components of the container (walls, ceiling, partitions, floor, doors, air ducts, refrigeration units, air delivery points, and / or other components of the container). In some embodiments, parameter module 130 may determine the container's sealing condition or detect heat leaks based on image data (e.g., from thermal images) from sensor 102. In some embodiments, assessing the condition of a component may include determining the presence / absence of damage to the component, determining the probability of damage to the component, and / or predicting damage to the component. In some embodiments, parameter module 130 may determine the container condition based on the condition of the components of the container.

[0038] Figure 3Example operations of a system 100 for determining the condition of a container are illustrated according to one or more embodiments. For example, parameter module 130 may be configured to determine the condition of the trailer based on damage detected by sensor 102. Detected damage includes damage 302 to the trailer ceiling, debris 304 on the trailer floor, damage 306 to the walls, and heat leakage 308 caused by damage 306 to the walls. Figure 4 Another example of operation is illustrated by a system 100 for determining container condition, according to one or more embodiments. A parameter module 130 can detect that air chute 402 is torn and air chute 404 is not properly attached. This information can be used to determine the condition of the trailer.

[0039] Return to Figure 1 In some embodiments, parameter module 130 may be configured to determine one or more cargo / item parameters. For example, parameter module 130 may use output signals from sensor 102 to detect, locate, or determine the presence of items within the container. Parameter module 130 may be configured to determine cargo / item parameters based on image data. Cargo / item parameters may include location information, identification information, and / or other cargo / item parameters.

[0040] In some embodiments, the position information of the items may include their physical location within the container, the rotational orientation of the items, their height, and / or information indicating their location. In some embodiments, the parameter module 130 is configured to determine the position of the goods items with reference to the components of the container and / or other goods items. For example, the parameter module 130 may determine the position of the goods items within the container based on the distance between the goods items and the components of the container (e.g., distance from the container walls, top, rear, doors, corners, air ducts, refrigerated compartments, air delivery points, and / or other components). In some cases, the position may be determined based on the distance between the items and other items within the goods. In some embodiments, the position information may indicate the proximity, below, above, against, top of, or any related position of the items relative to the components of the container or another goods item. In some embodiments, the position information may indicate the arrangement of the goods items. For example, items may be arranged in rows, stacked one on top of the other, positioned relative to another part of the container (e.g., most items facing the rear of the container), arranged at an angle to a wall (or rear, side, top, etc.), arbitrarily arranged within the container, and / or arrangement information. In some embodiments, parameter module 130 may determine the use (or presence) of padding material (e.g., any material used to hold goods in place) in the container. Parameter module 130 may determine the size, shape, and / or construction of the padding material.

[0041] In some embodiments, parameter module 130 can identify one or more goods or articles based on the output signal of sensor 102. In some embodiments, parameter module 130 can determine one or more of the following: type, brand, size, shape, dimensions, weight, destination, special instructions (fragile, heavy, keep refrigerated, do not stack, expiry date, or other article-specific instructions). Some of the identification information can be extracted by sensor 102 scanning text printed on the article, barcodes, QR codes, links, logos, or other identification information on the article.

[0042] The loading mode determination module 140 is configured to determine one or more loading characteristics (or loading modes) of the container based on information from the parameter module 130 (e.g., container parameters and / or cargo / item parameters). For example, in some embodiments, loading characteristics may be determined based on container information (e.g., size, dimensions, shape, etc.), container components (presence and location of components), and / or cargo / item information (e.g., location of cargo / items within the container, space between items / pallets). For example, the loading mode may indicate loading type (e.g., centerline / wall loading, proximity to door / wall), loading height (e.g., pallet height or stacking height), use of padding, amount and location of empty space, cargo / item count, and / or other loading characteristics. For example, in some embodiments, the loading mode determination module 140 may be configured to determine whether a pallet is contacting a door / wall; whether there is space between pallets at the center; whether the top of a pallet exceeds a predetermined height; whether the top of a pallet is contacting (pressing down) an air chute; whether a loading lock is present; whether a height marker is present; whether an environmental sensor is present within the container; and / or other loading modes.

[0043] In some embodiments, the loading pattern module determining 140 can be configured to determine loading characteristics using output signals from sensors (e.g., using computer vision to determine the loading pattern without going through the step of determining parameters of the cargo items). In some embodiments, the loading characteristics can be compared with historical loading information, loading information from similar containers, best practice loading information, and / or other reference loading information to determine the container's loading pattern.

[0044] Figure 5 Example operations are shown by a system 100 for determining container conditions according to one or more embodiments. The loading mode determination module 140 can be configured to determine loading height 502, the use of padding 504, and loading type 508 (wall loading) and loading type 506 (centerline loading) of the cargo in the trailer. In this case, for example, the loading mode determination module 140 can determine that the loading height 502 is too high.

[0045] In some embodiments, the airflow determination module 150 may be configured to determine environmental information within the container based on image data. Environmental information may include airflow information, temperature information, air pressure, humidity, and / or other environmental information. In some embodiments, the airflow determination module 150 may be configured to determine airflow characteristics within the container. Information obtained from the parameter module 130 (e.g., container parameters, cargo content parameters, container condition, etc.) may be used to determine the airflow characteristics within the container. The airflow characteristics within the container may be determined based on the type, model, or size of the container. In some embodiments, the airflow within the container may be determined based on the air delivery point and its location, the cargo items and their location, container components, and / or the condition of the container. For example, the condition of the container (e.g., the presence of damage, debris, or heat leakage) may affect the airflow within the container. The placement of the cargo items (e.g., distance from walls, tops, or each other) may affect the airflow within the container. The size of the container, the amount of empty space within the container, the location of the refrigeration unit and the air delivery point, and / or obstructions may affect the airflow within the container. Any combination of information from the parameter module 130 may be used to determine the airflow within the container. In some embodiments, the airflow within the container may be given in the form of a measurement (e.g., l / s, ft³ / min, kg / s, air change / h, or equivalent measurement). In some embodiments, the airflow determination module may determine the airflow index, airflow quality index, airflow loss, and / or other airflow characteristics.

[0046] The thermal information module 160 can be configured to determine thermal information within the container. For example, in some embodiments, the temperature, humidity, and / or temperature of one or more items of cargo within the container can be extracted from the output signal of sensor 102. In some embodiments, the thermal information module 160 can detect heat leaks or areas within the container where the temperature is abnormally high or low. For example, thermal parameters can be extracted from image data from a thermal imaging device and compared with reference thermal parameters to determine the thermal conditions within the trailer. In some embodiments, environmental information can be determined based on airflow characteristics and / or the thermal information obtained from the airflow determination module 150 and the thermal information module 160.

[0047] Analysis module 180 is configured to analyze data obtained from image module 120, parameter module 130, loading mode determination module 140, airflow determination module 150, and / or thermal information module 160 to determine the state of the container, its components, cargo, airflow, thermal information, loading mode, and / or other obtained parameters. In some embodiments, determining the state includes determining a probability or prediction of the state based on the obtained information. For example, analysis module 180 may determine the probability of damage to the container (or its components) or to the cargo based on analysis of the obtained data. In some embodiments, the state may be determined by comparing a reference parameter (e.g., obtained against a reference database) with a current parameter. The reference parameter may be based on historical data associated with the item and / or container, or data from similar items / containers. In some embodiments, analysis module 180 may be configured to assign scores to the container, cargo, airflow, thermal information, loading mode, and / or other obtained parameters based on this comparison (e.g., the closer the current parameter is to the reference parameter, the higher the score, and vice versa). In some embodiments, the analysis module 180 may determine the status (e.g., good, bad, reasonable, damaged, etc.) in response to the score reaching, meeting, or exceeding an item score threshold.

[0048] For example, analysis module 180 can be configured to determine the integrity of cargo items. For example, the integrity of a pallet, box, or other cargo item can be determined based on the determination of the item's position / orientation relative to the floor or ceiling of the container. For example, analysis module 180 can be configured to determine that a pallet (or box) is damaged if the pallet is less than perpendicular to the floor.

[0049] In some embodiments, the analysis module 180 can determine the state (e.g., good, bad, damaged, packaging integrity, etc.) of one or more items in a cargo article. The state of the item can be determined based on one or more of cargo article parameters, container parameters, airflow, thermal information, loading mode, and / or other parameters. For example, in some embodiments, the analysis module 180 can determine the probability that an item in one or more cargo articles is damaged based on the airflow characteristics and location information of one or more items. In some embodiments, the analysis module 180 can be configured to obtain environmental information within a container from sensors placed within the container. The analysis module 180 can determine the temperature control performance within the container based on the obtained environmental information. In some embodiments, the analysis module 180 can be configured to determine the probability that an item is damaged based on environmental information or temperature control performance from sensors within the container. In some embodiments, the analysis module 180 can be configured to estimate water loss from one or more cargo articles (e.g., fresh products) based on information from sensors within the container (e.g., humidity measurement), thermal information, airflow information, or temperature control performance within the container.

[0050] The status of an item can be determined by comparing a reference parameter with current parameters associated with the item. The reference parameter may be based on historical data associated with the item and / or container, or data from similar items / containers. In some embodiments, the analysis module 180 may be configured to assign an item score based on comparison (e.g., a higher score is given if the status parameter is closest to the reference status parameter, and vice versa). In some embodiments, the analysis module 180 may determine the probability of an item's status (e.g., good, bad, acceptable, damaged, etc.) in response to a score reaching, meeting, or exceeding an item score threshold. Figure 6 Example operations performed by a system 100 for determining container conditions are illustrated according to one or more embodiments. Analysis module 180 may detect cargo / item collapse (pallet collapse 602 or box collapse 604) based on image data received from image module 120. In some embodiments, analysis module 180 may be configured to determine the probability of damage to the collapsed box 604 and / or damage to the box in the collapsed pallet 602.

[0051] In some embodiments, analysis module 180 may be configured to assign parameter scores to one or more of the determined parameters. For example, in some embodiments, analysis module 180 may assign scores to airflow, load pattern, heat, and / or other parameters. In some embodiments, parameter scores may be based on a comparison of a reference parameter with a current parameter. For example, a load pattern score may be determined based on a comparison of a reference load pattern with a determined load pattern (e.g., from load pattern determination module 140). In some embodiments, the closer the load pattern is to the load pattern reference, the higher the score, and vice versa. In some embodiments, analysis 180 may characterize a load pattern (e.g., good, bad, reasonable, etc.) in response to a load pattern score reaching, meeting, or exceeding a load pattern score threshold.

[0052] Similarly, analysis module 180 can assign airflow scores. In some embodiments, the airflow score can be based on a comparison of an airflow reference with a determined airflow (e.g., from airflow determination module 150). In some embodiments, the closer the airflow is to the airflow reference, the higher the score, and vice versa. In some embodiments, analysis module 180 can determine the state of the airflow (e.g., good, bad, reasonable, etc.) in response to the airflow score reaching, satisfying, or exceeding an airflow score threshold. Furthermore, analysis module 180 can assign thermal scores. In some embodiments, the thermal score can be based on a comparison of a thermal reference with determined thermal information (e.g., from thermal information module 160). In some embodiments, the closer the thermal parameter is to the thermal reference, the higher the score, and vice versa. In some embodiments, analysis module 180 can characterize a thermal parameter (e.g., good, bad, reasonable, etc.) in response to the thermal score reaching, satisfying, or exceeding a thermal score threshold. It should be understood that the examples of state determination described herein are merely examples of embodiments for illustrative purposes. Other techniques for analysis and state determination are also contemplated within this disclosure. For example, in some embodiments, the state of one or more parameters (including scores) can be based on the state of other parameters. In other words, the state of one parameter can affect the state of other parameters. For example, if the goods inside the container score low, the loading mode, thermal parameters, or airflow may also score low.

[0053] In some embodiments, the analysis module 180 may use machine learning techniques to determine the state and / or assign a score. For example, one or more parameters may be input into the machine learning system to train multiple models to determine the state or assign a score. The machine learning system may use any combination of parameters to train the model. For example, in some cases, it may use only image data. In some embodiments, one or more of image data, identification information, location information, container information, container component information, airflow, thermal information, loading pattern, and / or other parameters may be used to train the model. The machine learning system may use one or more of supervised learning, semi-supervised learning, unsupervised learning, reinforcement learning, and / or other machine learning techniques. In some embodiments, the machine learning model may include decision trees, support vector machines, regression analysis, Bayesian networks, random forest learning, dimensionality reduction algorithms, boosting algorithms, artificial neural networks (e.g., fully connected neural networks, deep convolutional neural networks, or recurrent neural networks), deep learning, and / or other machine learning models.

[0054] In some embodiments, the analysis module 180 may be configured to determine a container status and / or score. For example, the container status and / or score may indicate the overall condition of the container. In some embodiments, the container status and / or score may be determined based on one or more parameters (thermal parameters, airflow parameters, loading patterns, item parameters, etc.). In some embodiments, the container status and / or score may be determined based on parameter scores. For example, the container score may be the sum of parameter scores. In some embodiments, the scores may be weighted before being used to calculate the container score. In some embodiments, the analysis module 180 may be configured to create one or more simulations of the container. For example, the analysis module 180 may use thermal parameters to create a thermal simulation of the container. Similarly, airflow parameters may be used to create an airflow simulation, and / or a loading pattern may be used to create a loading simulation of the container. In some embodiments, one or more simulations may be displayed for user visualization. In some embodiments, one or more simulations may be combined into a single container simulation that can be displayed to the user.

[0055] In some embodiments, the feedback module 182 may be configured to provide feedback and / or recommendations based on one or more determined parameters, states, and / or scores. For example, the feedback module 182 may provide feedback and / or recommendations by comparing information from the container with historical information related to the container or similar containers, or best practices in the industry. In some embodiments, the feedback may include one or more of the obtained parameters and scores (e.g., 702 shown in FIG7-A), selected images from image data (e.g., selected image 704 shown in FIG7), loading pattern diagrams (e.g., 706 shown in FIG7-A), and / or total container score (obtained parameters and scores (e.g., 708 shown in FIG7-A)).

[0056] In some embodiments, feedback may indicate cargo items or cargo components that may require the user's attention. For example, the user may receive an alert / feedback after the container is opened and before unloading, indicating that an item may be damaged. The feedback may provide the type of item, its location within the container, the type of damage, the probability of damage, the cause of damage, and / or recommended actions, etc. In some embodiments, the feedback may include recommendations for repairing one or more components of the container (or the entire container) based on one or more determined parameters, status, and / or scores.

[0057] For example, feedback could indicate that a box of bananas located on pallet 4 may be damaged (e.g., crushed). The feedback could include a container simulation display showing the exact location of the item. In other examples, the feedback could include notifications such as: one of the air chute has become disconnected and the item on that side of the container may require additional inspection. In yet another example, feedback could indicate poor airflow in the container. In this case, the feedback could include the cause of the poor airflow (e.g., loading pattern, blockage of the air delivery point, etc.) and recommended actions (e.g., repairing container components, inspecting the items on pallets 2-3, checking the air delivery point, changing the future loading pattern, etc.).

[0058] In some embodiments, the feedback module 182 may be configured to compare information obtained from sensor 102 with sensor measurements obtained from sensors within the container (e.g., an item sensor, a position sensor, an environmental sensor, or other sensors placed within the container). In some embodiments, the feedback module 182 may indicate the difference between the measurements from the sensors within the container and the measurements from sensor 102. The feedback provided by the feedback module 182 may indicate the difference between the measurements, the cause of the difference, and / or possible actions to minimize the difference. For example, the feedback may indicate that the sensor is defective and recommend replacement, or that the sensor is blocked and recommend changing the sensor's position or changing the loading mode, etc.

[0059] In some embodiments, the feedback module 182 can be configured to adjust the future loading mode of the container. The future loading mode can be adjusted (or updated) based on data from the analysis module 180 (e.g., based on loading mode scores, container scores, or other scores). In some embodiments, the feedback module 182 can be configured to optimize the loading mode based on a comparison of the current loading mode with best practices for similar containers. In some cases, the feedback module 182 can recommend cargo types for future loading plans. For example, the feedback module 182 can determine that the container is not suitable for transporting additional cold cargo items and recommend other types of cargo items that can still be transported in the container under the current conditions. In some embodiments, the recommendations can take the form of a set of options, and when the user navigates through the options, the feedback module guides the user to the best recommendation given the options made by the user (e.g., if the user chooses not to repair the wall damage, one of the recommendations would be to transport non-perishable items).

[0060] In some embodiments, the feedback module 182 can be configured to generate visual feedback. For example, in some embodiments, airflow characteristics, thermal parameters, and / or loading patterns can be input into the modeling system to generate visual simulations of one or more of these parameters. In some embodiments, the visual feedback may include thermal simulations (showing the thermal properties of the container or cargo), airflow simulations (showing the airflow within the container), loading pattern simulations (showing the current loading pattern of the container), and / or other models. In some embodiments, these simulations may be combined into a container simulation and provided as visual feedback to the user.

[0061] Figure 7A -D illustrates an example of visual feedback according to one or more embodiments of the present disclosure. For example, Figure 7-B illustrates an example of a user interface 710 including visual feedback. As can be seen, the feedback may include one or more scores (712). For example, in some embodiments, the feedback may include a total score (84.5%), a trailer characteristic score (87.5%), a trailer condition score (75%), a trailer loading score (100%), etc.

[0062] In some embodiments, visual feedback may include one or more image data 714. Figures 7-C illustrate examples of image data included in visual feedback (user interface). Image data may include one or more image data analyses. For example, guide and depth indicators 726 and 730 (based on perspective positioning technology) 730, height indicator 722, height measurement 724, and distance measurement 734 (e.g., distance between pallets and / or distance to a wall). In some embodiments, visual feedback may include visualization of the trailer. Figures 7-D illustrate examples of trailer 760 according to one or more embodiments. Visualization 760 may include the position 762 of items (e.g., pallets) within the trailer and / or the orientation 766 of the items. To understand, Figure 7A The example visual feedback (or user interface) shown in -D is for illustrative purposes only. Other information may be included. For example, Figures 1-6 One or more pieces of information shown may be included in the visual feedback. In some embodiments, the visual feedback may show actual measurements (e.g., height, distance, orientation, size, etc.). Measurements may be in alphanumeric format and may use any unit of measurement.

[0063] It should be understood that the illustrated components are depicted as discrete functional blocks, but the embodiments are not limited to systems in which the functionality described herein is organized as illustrated. The functionality provided by each of the components may be provided by software or hardware modules organized differently from those currently depicted; for example, such software or hardware may be mixed, combined, replicated, decomposed, distributed (e.g., within a data center or geographically), or otherwise organized differently. The functionality described herein may be provided by one or more processors of one or more computers executing code stored on a tangible, non-transitory, machine-readable medium.

[0064] Figure 8 The illustration depicts a method 800 for determining container conditions according to one or more embodiments of the present disclosure. The operation of the method 800 presented below is intended to be illustrative. In some implementations, method 800 may be implemented using one or more additional operations not described and / or without utilizing one or more operations discussed. Furthermore, the operation of method 800 in… Figure 8 The order shown in the diagram and described below is not intended to be limiting.

[0065] In some embodiments, the method may be implemented in one or more processing devices (e.g., digital processors, analog processors, digital circuits designed to process information, analog circuits designed to process information, state machines, and / or other mechanisms for electronically processing information). The processing device may include one or more means for performing some or all of the operations of the method in response to instructions stored electronically on an electronic storage medium. The processing device may include one or more means configured by hardware, firmware, and / or software specifically designed to perform one or more operations of the method.

[0066] At operation 802 of method 800, image data of the container from one or more optical sensors can be obtained. In some embodiments, operation 802 can be performed by (in...) Figure 1 The image module 120 shown in the figure and described herein is the same as or similar to the image module used to perform this function.

[0067] At operation 804 of method 800, the location information of one or more items located within the container can be determined based on image data. In some embodiments, operation 804 can be performed by (in...) Figure 1 The parameter module 130 shown in the figure and described herein is the same as or similar to the parameter module used in this paper.

[0068] At operation 806 of method 800, air delivery information in the container can be determined from the image data. In some embodiments, operation 806 can be performed by (in...) Figure 1The parameter module 130 shown in the figure and described herein is the same as or similar to the parameter module used in this paper.

[0069] At operation 808 of method 800, the airflow characteristics of the container can be determined. The airflow characteristics of the container can be determined based on the location information of one or more items and air delivery information. In some embodiments, operation 808 can be performed by (in...) Figure 1 The airflow determination module 150 shown in the figure and described herein is the same as or similar to the airflow determination module used to perform this function.

[0070] At operation 810 of method 800, the probability of an item being damaged among one or more items is determined. In some embodiments, the probability of an item being damaged can be determined based on location information and airflow characteristics. In some embodiments, operation 810 can be performed by (in...) Figure 1 The analysis module 180 shown in the figure and described herein is the same as or similar to the analysis module.

[0071] Embodiments of one or more technologies characterized by containers as described herein can be executed on one or more computer systems capable of interacting with a variety of other devices. Figure 9 The diagram illustrates such a computer system 900. Figure 9 Examples of computer systems that can be used to implement aspects of the techniques described herein are shown. In various embodiments, computer system 900 may include any combination of hardware or software capable of performing the indicated functions, including, but not limited to, computers, personal computer systems, desktop computers, laptop computers, notebook or netbook computers, mainframe computers, handheld computers, workstations, network computers, imaging devices, set-top boxes, mobile devices, network devices, internet appliances, PDAs, wireless telephones, pagers, consumer devices, video game consoles, handheld video game devices, application servers, storage devices, peripheral devices such as switches, modems, routers, or other types of computing or electronic devices.

[0072] In the illustrated embodiment, computer system 900 includes one or more processors 910 coupled to system memory 920 via input / output (I / O) interface 930. Computer system 900 also includes a network interface 940 coupled to I / O interface 930, and one or more input / output devices 950, such as cursor control device 960, keyboard 970, and one or more displays 980. In some embodiments, it is contemplated that a single instance of computer system 900 may be used to implement the embodiment, while in other embodiments, multiple such systems or multiple nodes constituting computer system 900 may be configured to host different portions or instances of the embodiment. For example, in one embodiment, some elements may be implemented via one or more nodes of computer system 900, which are different from those nodes implementing other elements.

[0073] In various embodiments, computer system 900 may be a single-processor system including one processor 910, or a multiprocessor system including several processors 910 (e.g., two, four, eight, or another suitable number). Processor 910 may be any suitable processor capable of executing instructions. It may include one or more semiconductors and / or transistors (e.g., electronic integrated circuits (ICs)). In such a context, processor-executable instructions may be electronically executable instructions. For example, in various embodiments, processor 910 may be any general-purpose or embedded processor implementing any of a variety of instruction set architectures (ISAs) such as x86, PowerPC, SPARC, or MIPS ISA or any other suitable ISA. In a multiprocessor system, each of the processors 910 may, but not necessarily, implement the same ISA.

[0074] In some embodiments, at least one processor 910 may be a graphics processing unit (GPU). A GPU can be considered a dedicated graphics rendering device for a personal computer, workstation, game console, or other computing or electronic device. Modern GPUs can be very efficient at manipulating and displaying computer graphics, and their highly parallel architecture can make them more efficient than a typical CPU used for a series of complex graphics algorithms. For example, a GPU can implement multiple graphics primitive operations in a way that makes performing graphics primitive operations much faster than drawing directly to the screen using a host central processing unit (CPU). In various embodiments, the image processing methods disclosed herein can be implemented at least in part by program instructions configured to execute on one of such GPUs or in parallel on two or more such GPUs. The GPU(s) can implement one or more application programming interfaces (APIs) that allow programmers to call the functionality of the GPU(s). Suitable GPUs are available from vendors such as NVIDIA Corporation, ATI Technologies (AMD), etc. In some embodiments, one or more computers may include multiple processors operating in parallel. The processor can be a central processing unit (CPU) or a dedicated computing device, such as a graphics processing unit (GPU), an integrated circuit or system-on-a-chip, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a complex programmable logic device (CPLD), or an application-specific integrated circuit.

[0075] System memory 920 may be configured to store program instructions and / or data accessible by processor 910. In various embodiments, system memory 920 may be implemented using any suitable memory technology, such as static random access memory (SRAM), synchronous dynamic RAM (SDRAM), non-volatile / flash memory, or any other type of memory. In the illustrated embodiment, program instructions and data that perform the intended function (e.g., the functions described in this disclosure) are shown stored within system memory 920 as program instructions 925 and data storage 935, respectively. In other embodiments, program instructions and / or data may be received, transmitted, or stored on different types of computer-accessible media or on similar media separate from system memory 920 or computer system 900. Generally, computer-accessible media may include storage media or memory media, such as magnetic or optical media, such as a disk or CD / DVD-ROM coupled to computer system 900 via I / O interface 930. Program instructions and data stored via a computer-accessible medium can be transmitted via a transmission medium or signal (e.g., electrical, electromagnetic, or digital signal), which can be transmitted via a communication medium (e.g., a network and / or a wireless link), for example via a network interface 940.

[0076] In one embodiment, I / O interface 930 may be configured to coordinate I / O traffic between processor 910, system memory 920, and any peripheral devices within the device, including network interface 940 or other peripheral device interfaces such as input / output device 950. In some embodiments, I / O interface 930 may perform any necessary protocols, timing, or other data conversions to convert data signals from one component (e.g., system memory 920) into a format for use by another component (e.g., processor 910). In some embodiments, I / O interface 930 may include support for devices attached via various types of peripheral buses (e.g., variants of the Peripheral Component Interconnect (PCI) bus standard or the Universal Serial Bus (USB) standard). In some embodiments, the functionality of I / O interface 930 may be divided into two or more separate components, such as a northbridge and a southbridge. Additionally, in some embodiments, some or all of the functionality of I / O interface 930 (e.g., the interface to system memory 920) may be directly incorporated into processor 910.

[0077] Network interface 940 can be configured to allow data exchange between computer system 900 and other devices attached to the network (e.g., other computer systems) or between nodes of computer system 900. In various embodiments, network interface 940 can support communication via wired or wireless general-purpose data networks (e.g., any suitable type of Ethernet network), such as communication via telecommunications / telephone networks (e.g., analog voice networks or digital fiber optic communication networks); communication via storage area networks such as Fibre Channel SANs; or communication via any other suitable type of network and / or protocol.

[0078] In some embodiments, the input / output device 950 may include one or more display terminals, cursor control devices (e.g., mice), keyboards, keypads, touchpads, touchscreens, scanning devices, voice or optical recognition devices, or any other devices adapted to input or retrieve data through one or more computer systems 900. Multiple input / output devices 950 may be present in the computer system 900 or distributed across various nodes of the computer system 900. In some embodiments, similar input / output devices may be separate from the computer system 900 and may interact with one or more nodes of the computer system 900 via wired or wireless connections (e.g., via network interface 940).

[0079] Those skilled in the art will appreciate that the computer system 900 is merely illustrative and not intended to limit the scope of this disclosure. In particular, the computer system 900 may also be connected to other devices not shown, or conversely, may operate as a stand-alone system. Furthermore, in some embodiments, the functionality provided by the illustrated components may be combined in fewer components or distributed across additional components. Similarly, in some embodiments, the functionality of some illustrated components may not be provided, and / or other additional functionality may be available.

[0080] It should be understood that the specification and drawings are not intended to limit the invention to the specific forms disclosed, but rather, the invention is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention as defined by the appended claims. Further modifications and alternative embodiments of various aspects of the invention will be apparent to those skilled in the art in light of this specification. Therefore, this specification and drawings are to be interpreted as illustrative only and for the purpose of teaching those skilled in the art the general manner in which the invention is practiced. It will be understood that the forms of the invention shown and described herein will be considered as examples of embodiments. Elements and materials may be substituted for those shown and described herein, parts and processes may be reversed or omitted, and certain features of the invention may be utilized independently, all of which will be apparent to those skilled in the art who have benefited from this specification. Changes may be made to the elements described herein without departing from the spirit and scope of the invention as defined in the appended claims. The headings used herein are for organizational purposes only and are not intended to limit the scope of this specification.

[0081] As used throughout this application, the word “may” is used in a permissive sense (i.e., meaning possible) rather than a mandatory sense (i.e., meaning must). The words “include,” “including,” and “includes,” etc., mean including but not limited to. As used throughout this application, the singular forms “a” and “the” include the plural objects referred to, unless the content expressly indicates otherwise. Thus, for example, a reference to “an element” includes a combination of two or more elements, although other terms and phrases such as “one or more” are used for one or more elements. The term “or” is non-exclusive, meaning it encompasses both “and” and “or”, unless otherwise indicated. Terms describing conditional relationships (e.g., "in response to X, perform Y," "when X, perform Y," "if X, then perform Y," "at X, perform Y," etc.) encompass causal relationships where the antecedent is a necessary causal condition, a sufficient causal condition, or a contributing causal condition to the outcome. For example, "when condition Y is obtained, state X occurs" is common to "only when Y occurs" and "when Y and Z occur, X occurs." Such conditional relationships are not limited to results immediately following the acquisition of the antecedent, as some results may be delayed, and in conditional statements, the antecedent is linked to its outcome; for example, precedents relate to the likelihood of the outcome occurring. Furthermore, unless otherwise indicated, a statement that a value or action is "based on" another condition or value covers two cases: where the condition or value is the only factor, and where the condition or value is one of several factors. Unless otherwise indicated, a statement that "each" instance in a set has a certain property should not be read as excluding the possibility that some other identical or similar members in a larger set do not have that property; that is, "each" does not necessarily mean "all." Unless otherwise specifically stated, as will be understood from the discussion, throughout the specification, the use of terms such as “processing,” “calculation,” “operation,” and “determining” refers to the actions or processes of a particular device such as a dedicated computer or similar dedicated electronic processing / computing apparatus.

Claims

1. A system for determining the condition of a container, the system comprising: One or more optical sensors; At least one processor; as well as A memory storing instructions executable by the at least one processor, which, when executed, cause the system to: Image data of the container is obtained from the one or more optical sensors; The location information of one or more items located within the container is determined from the image data; Determine air delivery information in the container from the image data; The airflow characteristics of the container are determined using the location information of the one or more items and the air delivery information; as well as The location information of the one or more items and the airflow characteristics are used to determine the probability that an item among the one or more items will be damaged.

2. The system as claimed in claim 1, wherein, The instructions further enable the system to: The condition of one or more components of the container is determined based on the image data of the container, and the condition of the one or more components indicates the presence or absence of damage to the one or more components; as well as The condition of the container is determined based on the condition of the one or more components.

3. The system as described in claim 2, wherein, The condition of the one or more components is one or more of a sealed or thermal condition.

4. The system as claimed in claim 1, wherein, The instructions further enable the system to: The loading mode of the container is determined based on one or more of the location information or orientation information of one or more items located within the container.

5. The system as claimed in claim 1, wherein, The instructions further enable the system to: Identification information of the one or more items is determined, and the probability of the item being damaged is further determined based on the identification information.

6. The system of claim 1, wherein, The instructions further enable the system to: Environmental information within the container is obtained from sensors placed inside the container; and The temperature control performance in the container is determined based on the obtained environmental information; wherein the probability of the item being damaged is further determined based on the environmental information or the temperature control performance.

7. The system of claim 4, wherein, The instructions further enable the system to: Determine thermal information for the container based on the image data; and One or more of the following can be generated based on one or more of the thermal, airflow, or loading information: thermal simulation, airflow simulation, or loading mode simulation.

8. A method for determining the condition of a container, the method being implemented in a system comprising one or more optical sensors, at least one processor, and a memory storing instructions, the method comprising: Image data of the container is obtained from the one or more optical sensors; The location information of one or more items located within the container is determined from the image data; Determine air delivery information in the container from the image data; The airflow characteristics of the container are determined using the location information of the one or more items and the air delivery information; as well as The location information of the one or more items and the airflow characteristics are used to determine the probability that an item among the one or more items will be damaged.

9. The method of claim 8, further comprising: The condition of one or more components of the container is determined based on the image data of the container, and the condition of the one or more components indicates the presence or absence of damage to the one or more components; as well as The condition of the container is determined based on the condition of the one or more components.

10. The method of claim 9, wherein, The condition of the one or more components is one or more of a sealed or thermal condition.

11. The method of claim 8, further comprising: The loading mode of the container is determined based on the location or orientation information of one or more items located within the container.

12. The method of claim 8, further comprising: Identification information of the one or more items is determined, and the probability of the item being damaged is further determined based on the identification information.

13. The method of claim 8, further comprising: Environmental information inside the container is obtained from sensors placed inside the container; as well as The temperature control performance in the container is determined based on the obtained environmental information; wherein the probability of the item being damaged is further determined based on the environmental information or the temperature control performance.

14. The method of claim 11, further comprising: Determine thermal information for the container based on the image data; as well as One or more of the thermal simulation, airflow simulation, or loading mode simulation are generated based on one or more of the aforementioned thermal, airflow, or loading information.

15. A non-transitory computer-readable storage medium storing program instructions, wherein the program instructions are computer-executable to implement: Image data of the container is obtained from the one or more optical sensors; The location information of one or more items located within the container is determined from the image data; Determine air delivery information in the container from the image data; The airflow characteristics of the container are determined using the location information of the one or more items and the air delivery information; as well as The location information of the one or more items and the airflow characteristics are used to determine the probability that an item among the one or more items will be damaged.

16. The non-transitory computer-readable storage medium of claim 15, wherein, The program instructions are computer-executable to implement: The condition of one or more components of the container is determined based on the image data of the container, and the condition of the one or more components indicates the presence or absence of damage to the one or more components; as well as The condition of the container is determined based on the condition of the one or more components.

17. The non-transitory computer-readable storage medium of claim 16, wherein, One or more of the conditions of the one or more components being sealed or in a thermal condition.

18. The non-transitory computer-readable storage medium of claim 15, wherein, The program instructions are computer-executable to implement: The loading mode of the container is determined based on the location information of one or more items located within the container.

19. The non-transitory computer-readable storage medium of claim 15, wherein, The program instructions are computer-executable to implement: Environmental information within the container is obtained from sensors placed inside the container; and The temperature control performance in the container is determined based on the obtained environmental information; wherein the probability of the item being damaged is further determined based on the environmental information or the temperature control performance.

20. The non-transitory computer-readable storage medium of claim 18, wherein, The program instructions are computer-executable to implement: Determine thermal information for the container based on the image data; and One or more of the thermal simulation, airflow simulation, or loading mode simulation are generated based on one or more of the aforementioned thermal, airflow, or loading information.

Images