Intelligent cargo tracking and management method and system based on Internet of Things

Abstract

The invention provides an intelligent cargo tracking and management method and system based on the Internet of Things, and relates to the technical field of intelligent logistics management, and the system comprises an edge computing device arranged in a boxcar, an Internet of Things environment sensor group and an edge computing device. The RFID reader is used for collecting cargo RFID tag data of each cargo in a boxcar; the edge computing device is used for comparing the cargo transfer station coordinates in the cargo RFID tag data with the vehicle positioning information according to the cargo RFID tag data, and executing a package transfer alarm action according to the cargo RFID tag data under the condition that the cargo transfer station coordinates in the cargo RFID tag data are matched with the vehicle positioning information; and for each environment parameter safety interval in the cargo RFID tag data, matching the environment parameter safety interval with the corresponding type of environment parameter in the environment sensing data, and executing a parcel state abnormal action according to the unmatched abnormal environment parameter. Therefore, the cargo tracking management efficiency is improved, and the trust satisfaction degree of customers to logistics services is enhanced.

Description

Technical Field

[0001] The present application relates to the field of intelligent logistics management technology, and in particular to an intelligent cargo tracking and management method and system based on the Internet of Things. Background Art

[0002] With the advancement of globalization and the booming e-commerce, the logistics industry has become an important pillar of the modern economy. However, this industry is facing unprecedented challenges, especially in cargo tracking and management. An efficient and accurate cargo tracking system is essential to improve logistics efficiency, reduce operating costs, and enhance customer satisfaction.

[0003] Currently, most logistics companies rely on barcode technology to track goods. Although this method is simple and low-cost, it requires manual scanning, which not only increases labor costs, but is also prone to inaccurate data due to human error or negligence. Barcodes cannot carry much information and are susceptible to physical damage, resulting in reading failures. In addition, barcodes are only updated as the goods are scanned when they pass through the transfer station, and the transportation process of the goods cannot be effectively supervised, resulting in the inability to ensure the safety of the goods.

[0004] The industry has not yet proposed a better solution to the above problems. Summary of the invention

[0005] The present application provides an intelligent cargo tracking and management method and system based on the Internet of Things, which is used to at least solve the problem that the safety of cargo transportation cannot be guaranteed due to the traditional reliance on barcode technology to track cargo.

[0006] The present application provides an intelligent cargo tracking and management method based on the Internet of Things, including: collecting cargo RFID tag data of each cargo in the truck compartment based on an RFID reader configured in the truck compartment, and sending each cargo RFID tag data to an edge computing device configured in the truck compartment; the cargo RFID tag data includes cargo identification information of the corresponding cargo, multiple environmental parameter safety intervals and cargo transfer station coordinates; each of the environmental parameter safety intervals has a corresponding environmental parameter type; collecting environmental sensor data corresponding to the truck compartment based on an Internet of Things environmental sensor group set in the truck compartment, and sending the environmental sensor data to the edge computing device; the environmental sensor data The data includes the following environmental parameters: environmental temperature parameters, environmental humidity parameters, vibration intensity parameters and acceleration parameters; the edge computing device is used to: obtain the vehicle positioning information of the truck compartment; for each of the cargo RFID tag data, perform the following operations: compare the cargo transfer station coordinates in the cargo RFID tag data with the vehicle positioning information, and when a match is determined, execute a package transfer alarm action according to the cargo RFID tag data; for each environmental parameter safety interval in the cargo RFID tag data, match the environmental parameter safety interval with the corresponding type of environmental parameter in the environmental sensor data, and execute a package status abnormal action according to the mismatched abnormal environmental parameters.

[0007] Optionally, a plurality of RFID tag boxes are arranged in the truck compartment, and each of the RFID tag boxes is used to accommodate corresponding goods; wherein the RFID tag box comprises an RFID tag generator, and the RFID tag generator is used to regenerate corresponding RFID tags according to the currently accommodated goods when it is determined that the type of the accommodated goods has changed.

[0008] Optionally, the RFID tag box is provided with a sound and light alarm module and a signal transmission module; the package transit alarm action includes: triggering the RFID tag box corresponding to the cargo RFID tag data to perform a light flashing alarm operation corresponding to the first alarm color, and performing a voice alarm operation according to a preset transit voice setting; the package status abnormal action includes: triggering the RFID tag box corresponding to the cargo RFID tag data to perform a light flashing alarm operation corresponding to the second alarm color, and sending the cargo identification information in the cargo RFID tag data to the edge computing device.

[0009] Optionally, the method also includes: the RFID tag generator is used to perform the following operations to determine the environmental parameter safety interval, specifically including: receiving cargo transportation environmental parameter settings corresponding to cargo identification information from a logistics management platform server; the logistics management platform server is also used to receive a cargo logistics setting request from a user terminal, wherein the cargo transportation environmental parameter settings are determined based on user input information corresponding to the cargo logistics setting request; determining a target calibration environmental parameter interval based on a preset environmental parameter calibration table combined with the cargo type corresponding to the cargo identification information; the environmental parameter calibration table contains multiple cargo types and corresponding calibration environmental parameter intervals; determining an environmental parameter safety interval based on the cargo transportation environmental parameter settings and the target calibration environmental parameter interval.

[0010] Optionally, the method also includes: the RFID tag generator is used to perform the following operations to determine the coordinates of the cargo transfer station, specifically including: receiving a cargo transportation route matching the cargo identification information from the logistics management platform server; receiving a truck navigation path from the on-board terminal corresponding to the truck compartment; and determining the coordinates of the cargo transfer station based on the matching result between the cargo transportation route and the truck navigation path.

[0011] Optionally, the RFID tag box is provided with a camera and an object classification model, specifically comprising: based on the camera, collecting a cargo image corresponding to the cargo contained in the RFID tag box; inputting the cargo image into the object classification model to determine the cargo type corresponding to the cargo, and the object classification model adopts a deep learning model.

[0012] Optionally, the object classification model comprises a deep residual network module, an SE network module and a classification network module; the deep residual network module is used to extract image features in the cargo image; the deep residual network module comprises a plurality of residual blocks, each residual block comprises a plurality of convolutional layers;

[0013] The structure of the residual block is:

[0014] F(x,{W i})+x

[0015] In the formula, F(x,{W i}) represents the residual mapping achieved by the convolutional layer, W i represents the weight of the convolutional layer, and x represents the input feature of the residual block, wherein the input feature corresponding to the first residual block is determined according to the cargo image;

[0016] The SE network module includes a plurality of SE blocks, each of which is inserted after each residual block in the deep residual network module to perform channel-level weight adjustment on a feature map output by each residual block;

[0017] The structure of the SE block is:

[0018]

[0019] In the formula, F(x) c,h,w represents the activation value of the element (h,w) at a specific position in the feature map on the cth channel, h and w represent the position index on the height and width of the feature map respectively; H and W are the height and width of the feature map; S represents the average activation value of all spatial positions of the feature map on channel c through the squeezing operation; σ represents the sigmoid activation function, δ represents the ReLU activation function, and W1 and W2 are the weights of the fully connected layer; represents the output of the SE block at the cth channel;

[0020] The classification network module is connected to the last SE block and is used to perform classification prediction based on the features adjusted by the SE block weights to output the corresponding target classification;

[0021] The structure of the classification network module is:

[0022]

[0023] Where P(y=j|x) represents the probability of determining that an item belongs to category j based on the input cargo image x, and z j It represents the output score of the jth category calculated by the classification layer, and K represents the total number of categories for object classification.

[0024] Optionally, the loss function of the object classification model is:

[0025]

[0026] In the formula, y k is the true label corresponding to the training sample. If the training sample belongs to category k, then y k =1, otherwise y k =0; p k is the probability of category k predicted by the model, w k represents the weight for category k, γ represents the preset adjustment focus parameter, m(k) represents the relative frequency of category k in the data set, and ζ represents a preset constant.

[0027] Optionally, the edge computing device is also used to perform the following operations: sending the positioning data, environmental sensor data and each cargo RFID tag data corresponding to the truck compartment to the logistics management platform server, so that the logistics management platform server updates the logistics transportation status of the cargo corresponding to each cargo RFID tag data according to the positioning data and the environmental sensor data.

[0028] The present application also provides an intelligent cargo tracking and management system based on the Internet of Things, including: an edge computing device, which is arranged in a truck compartment; an RFID reader, which is arranged in the truck compartment and is used to collect cargo RFID tag data of each cargo in the truck compartment, and send each cargo RFID tag data to the edge computing device; the cargo RFID tag data includes cargo identification information of the corresponding cargo, multiple environmental parameter safety intervals and cargo transfer station coordinates; each of the environmental parameter safety intervals has a corresponding environmental parameter type; an Internet of Things environmental sensor group, which is arranged in the truck compartment and is used to collect environmental sensor data corresponding to the truck compartment, and send the environmental sensor data to the edge computing device. device; the environmental sensor data includes the following environmental parameters: environmental temperature parameter, environmental humidity parameter, vibration intensity parameter and acceleration parameter; the edge computing device is used to perform the following operations: for each of the cargo RFID tag data, perform the following operations: compare the cargo transfer station coordinates in the cargo RFID tag data with the vehicle positioning information, and when a match is determined, perform a package transfer alarm action according to the cargo RFID tag data; for each environmental parameter safety interval in the cargo RFID tag data, match the environmental parameter safety interval with the corresponding type of environmental parameter in the environmental sensor data, and perform a package status abnormal action according to the mismatched abnormal environmental parameters.

[0029] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an intelligent cargo tracking and management method based on the Internet of Things as described above is implemented.

[0030] The present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the intelligent cargo tracking and management method based on the Internet of Things as described in any one of the above is implemented.

[0031] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned intelligent cargo tracking and management methods based on the Internet of Things.

[0032] The intelligent cargo tracking and management method and system based on the Internet of Things provided by this application can produce at least the following technical effects:

[0033] (1) By using RFID technology, automatic identification and data collection of goods can be achieved without manual barcode scanning, reducing logistics synchronization errors caused by human operation errors and barcode damage, and improving the accuracy and efficiency of cargo tracking.

[0034] (2) Corresponding edge computing devices are deployed in each carriage to process RFID tag data and environmental sensor data in real time. The environmental conditions of the goods during transportation (such as temperature, humidity, vibration, etc.) can be monitored in real time to ensure that the goods are transported under safe environmental conditions, especially for those goods that are sensitive to the environment, to enhance cargo safety monitoring.

[0035] (3) By comparing the transfer station coordinates in the RFID tag data of the goods with the real-time positioning information of the vehicle, the location of the goods can be accurately grasped, and an alarm can be automatically issued when the goods arrive at the predetermined transfer station, ensuring that the goods are prompted to transfer when they arrive at the transfer station, without the need to obtain the transfer information of the goods through scanning, thereby ensuring that the logistics accuracy and efficiency of the goods are improved.

[0036] (4) The environmental parameters of each cargo are monitored using IoT sensor groups. When the environmental parameters exceed the safety range, abnormal actions for the package status can be executed in a timely manner, such as sounding an alarm or notifying management personnel, so that measures can be taken quickly to deal with potential cargo safety issues. In this way, the safety of cargo transportation can be ensured.

[0037] (5) Each cargo in the truck compartment is equipped with corresponding cargo RFID tag data, which can realize the personalized setting of the environmental parameter safety range and cargo transfer station coordinates of each cargo, meeting the personalized logistics and transportation needs of different cargoes.

[0038] Through the embodiments of this application, RFID technology, IoT sensors, edge computing and other advanced technologies are integrated to achieve automated tracking and monitoring, reduce reliance on manual labor, and thus reduce labor costs. As a result, the efficiency of cargo tracking and management is improved, and the additional costs caused by cargo loss and delays are reduced. Based on accurate and real-time cargo tracking information, the transparency of logistics services is also improved, and customers can better understand the status and location of their goods, which enhances customer trust and satisfaction with logistics services. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A structural schematic diagram of an example of an intelligent cargo tracking and management system based on the Internet of Things according to an embodiment of the present application is shown;

[0041] Figure 2 A flowchart showing an example of a processing flow executed by an edge computing device according to an embodiment of the present application;

[0042] Figure 3 A structural schematic diagram showing another example of an intelligent cargo tracking and management system based on the Internet of Things according to an embodiment of the present application;

[0043] Figure 4 A schematic diagram showing the cargo layout of a truck compartment according to an embodiment of the present application is shown.

[0044] Figure 5 A schematic structural diagram of an example of an RFID tag box according to an embodiment of the present application is shown;

[0045] Figure 6 An operation flow chart of an example of determining a safety interval of an environmental parameter by an RFID tag generator according to an embodiment of the present application is shown;

[0046] Figure 7 An operation flow chart of an example of determining the coordinates of a cargo transfer station by an RFID tag generator according to an embodiment of the present application is shown;

[0047] Figure 8 An operation flow chart showing an example of identifying category information of an object according to an embodiment of the present application;

[0048] Fig. 9 A schematic diagram showing a structure of an example of an object classification model according to an embodiment of the present application;

[0049] Fig.10 A flowchart showing an example of an intelligent cargo tracking and management method based on the Internet of Things according to an embodiment of the present application is shown;

[0050] Fig.11 It is a schematic diagram of the structure of the electronic device provided by this application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] Figure 1 A structural schematic diagram of an example of an intelligent cargo tracking and management system based on the Internet of Things according to an embodiment of the present application is shown.

[0053] like Figure 1 As shown, the IoT-based intelligent cargo tracking and management system includes an edge computing device 110, an RFID reader 120, and an IoT environmental sensor group 130. More specifically, the edge computing device 110, the RFID reader 120, and the IoT environmental sensor group 130 are all arranged in the same truck compartment.

[0054] The RFID reader 110 can collect the cargo RFID tag data of each cargo in the truck compartment and send each cargo RFID tag data to the edge computing device. The cargo RFID tag data includes cargo identification information of the corresponding cargo, multiple environmental parameter safety intervals and cargo transfer station coordinates, and each environmental parameter safety interval has a corresponding environmental parameter type.

[0055] The IoT environment sensor group 130 can collect environment sensor data corresponding to the truck compartment and send the environment sensor data to the edge computing device. Here, the environment sensor data includes the following environment parameters: environment temperature parameter, environment humidity parameter, vibration intensity parameter and acceleration parameter.

[0056] Figure 2 A flowchart showing an example of a processing flow executed by an edge computing device according to an embodiment of the present application is shown.

[0057] like Figure 2 As shown, in step S210, for each cargo RFID tag data, the cargo transfer station coordinates in the cargo RFID tag data are compared with the vehicle positioning information, and when a match is determined, a package transfer alarm action is executed according to the cargo RFID tag data.

[0058] In this way, the transfer of each cargo in the truck compartment to the station can be automatically monitored, and the transfer management of the cargo can be achieved without scanning the cargo barcode.

[0059] In step S220, for each environmental parameter safety interval in the cargo RFID tag data, the environmental parameter safety interval is matched with the corresponding type of environmental parameters in the environmental sensor data, and the package status abnormal action is performed according to the unmatched abnormal environmental parameters.

[0060] Therefore, by matching the safety interval of each environmental parameter with the corresponding type of environmental parameter in the environmental sensor data, and when the environmental parameters do not meet the safety environment conditions, the safety supervision of the cargo transportation status is achieved.

[0061] Figure 3 A structural schematic diagram of another example of an intelligent cargo tracking and management system based on the Internet of Things according to an embodiment of the present application is shown.

[0062] like Figure 3 As shown, the intelligent cargo tracking and management system based on the Internet of Things includes an edge computing device 110, an RFID reader 120, an Internet of Things environmental sensor group 130, and a logistics management platform server 140. Here, the logistics management platform server 140, as the center point of the edge computing network, can communicate with the edge computing devices 110 in each carriage and collect data from each edge computing device 110.

[0063] More specifically, each edge computing device can also send the positioning data, environmental sensor data and each cargo RFID tag data corresponding to the truck compartment to the logistics management platform server, so that the logistics management platform server can update the logistics transportation status of the cargo corresponding to each cargo RFID tag data according to the positioning data and environmental sensor data.

[0064] Thus, the in-transit status tracking and supervision of all transported goods can be achieved in the logistics management platform. In some embodiments, the logistics transportation status of the goods is visualized by combining the positioning data and environmental sensor data of each cargo received with the GIS map system, so as to make it easier for the platform administrator to supervise the in-transit goods. In addition, users can also access the logistics management platform server through the user terminal to query the in-transit location status and damage status information of their packages in real time, instead of having to wait until the package reaches the destination to update, thereby improving the quality of logistics services and user experience. In addition, by deploying edge computing devices in each carriage, it is possible to support the corresponding processing of data in the local carriage to realize the corresponding functions, without having to synchronously transmit all data to the central platform, which can reduce the processing pressure on the cloud platform to a large extent.

[0065] Figure 4 A schematic diagram of cargo layout of a truck compartment according to an embodiment of the present application is shown.

[0066] like Figure 4As shown, a plurality of RFID tag boxes 41 are provided in a truck compartment 400, and each RFID tag box 41 is used to accommodate corresponding goods. Here, each RFID tag box 41 is evenly spaced and arranged on the wall cabinet of the truck compartment, but it should be understood that it can also be arranged in other ways, which should not be limited here. In addition, the form of the RFID tag box can be diverse and can be adjusted according to the type or size of the goods being transported. For example, some goods require frozen transportation conditions. At this time, a freezing module can be integrated in some RFID tag boxes in the truck compartment to provide transportation conditions close to a cold storage.

[0067] Figure 5 A schematic structural diagram of an example of an RFID tag box according to an embodiment of the present application is shown.

[0068] like Figure 5 As shown, the RFID tag box 41 includes an RFID tag generator 510 , an audio and video alarm module 520 , a signal transmission module 530 , a camera 540 and an object classification model 550 .

[0069] Based on the RFID tag generator 510, when it is determined that the cargo type of the contained cargo has changed, the corresponding RFID tag is regenerated according to the currently contained cargo. Thus, through the RFID tag generator 510, the RFID tags can be automatically updated for different items being transported by logistics without manual labeling, thereby reducing the manual operation cost and logistics information deviation. In combination with the application scenario, after the logistics transportation of the first shift of cargo is completed and the second shift of cargo is loaded in the carriage, the cargo type change signal is triggered by a button, so that the RFID tag generator 510 automatically updates the corresponding RFID tag. In other scenarios, there is no need to manually trigger the cargo type change signal. The RFID tag box can automatically identify the type of the contained object, and automatically update the corresponding RFID tag when a type change is detected. The identification details of the object type will be expanded in conjunction with other examples below.

[0070] In some examples of the embodiments of the present application, based on the sound and light alarm module 520 and the signal transmission module 530, the package transfer alarm action and the package status abnormal action of the RFID tag box 41 can be implemented.

[0071] In some embodiments, the parcel transfer alarm action includes: triggering the RFID tag box corresponding to the cargo RFID tag data to perform a light flashing alarm operation corresponding to the first alarm color, and performing a voice alarm operation according to the preset transfer voice setting. For example, the corresponding RFID tag box is triggered to flash a red light, and a corresponding voice message "the parcel will deviate from the transportation route and needs to be transferred" is broadcasted, and then the logistics manager can open the RFID tag box, take out the goods and place them at the transfer point to wait for other shifts of trucks to pack and transfer transportation.

[0072] In some embodiments, the abnormal package status action includes: triggering the RFID tag box corresponding to the cargo RFID tag data to perform a flashing alarm operation corresponding to the second alarm color, and sending the cargo identification information in the cargo RFID tag data to the edge computing device. Exemplarily, triggering the corresponding RFID tag box to flash a yellow light, and sending a message containing cargo identification information to the edge computing device, "XX cargo has an abnormal transportation status, please pay attention", and then the edge computing device can send the message to the logistics management platform server for centralized management. In addition, the edge computing device can also send the message to the truck computer to remind the driver to take quick countermeasures, so as to ensure that the transported goods are in a safe state in real time.

[0073] As described above, the RFID tag generated by the RFID tag generator integrates the environmental parameter safety interval and the coordinates of the cargo transfer station. The setting method of the environmental parameter safety interval and the coordinates of the cargo transfer station can be set according to the needs of users (including platform administrators, truck drivers or ordinary consumer users), and then the RFID tag generator generates tags according to the set environmental parameter safety interval and the coordinates of the cargo transfer station, so as to meet the personalized transportation needs of different goods.

[0074] Figure 6 An operational flow chart of an example of determining a safety interval of an environmental parameter by an RFID tag generator according to an embodiment of the present application is shown.

[0075] like Figure 6 As shown, in step S610, cargo transportation environment parameter settings corresponding to cargo identification information are received from the logistics management platform server.

[0076] Here, the logistics management platform server is also used to receive a cargo logistics setting request from a user terminal, wherein the cargo transportation environment parameter setting is determined according to the user input information corresponding to the cargo logistics setting request. Exemplarily, the user operates the logistics APP to input the numerical range of various environmental parameters applicable to the cargo being transported, so as to send the cargo logistics setting request to the logistics management platform server.

[0077] In step S620, a target calibration environmental parameter interval is determined according to a preset environmental parameter calibration table in combination with the cargo type corresponding to the cargo identification information. The environmental parameter calibration table includes multiple cargo types and corresponding calibration environmental parameter intervals.

[0078] Here, the environmental parameter calibration table is used to pre-sort the environmental parameter ranges suitable for the transportation of various types of goods, so as to achieve standardized guidance on the transportation environment of various goods. For example, the calibrated vibration intensity parameters and calibrated acceleration parameters corresponding to fragile goods should be smaller, and the temperature range corresponding to frozen items should be lower to ensure the safe transportation of goods.

[0079] In step S630, the environmental parameter safety range is determined according to the cargo transportation environmental parameter settings and the target calibration environmental parameter range.

[0080] In some implementations, the intersection of the environmental parameter interval corresponding to the cargo transportation environmental parameter setting and the target calibration environmental parameter interval is determined as the environmental parameter safety interval. For example, if the cargo transportation environmental parameter setting obtained based on the user's personalized needs is [20, 40], and the corresponding target calibration environmental parameter interval is [25, 40], then the environmental parameter safety interval is [25, 40]. Thus, it is ensured that the environmental parameter safety interval can simultaneously meet the user's personalized settings and cargo safety transportation conditions.

[0081] Figure 7 An operational flow chart of an example of determining the coordinates of a cargo transfer station by an RFID tag generator according to an embodiment of the present application is shown.

[0082] like Figure 7 As shown, in step S710, a cargo transportation route matching the cargo identification information is received from a logistics management platform server.

[0083] Here, the logistics management platform server can plan the corresponding cargo transportation route according to the delivery address and delivery address corresponding to the cargo identification information. For more details, please refer to the current relevant technology, which will not be repeated here. Furthermore, the logistics management platform server can send the cargo transportation route to each edge computing device, which is forwarded to the RFID tag generator with the corresponding cargo identification information via the edge computing device.

[0084] In step S720, the truck navigation path is received from the vehicle terminal corresponding to the truck compartment.

[0085] Exemplarily, the RFID tag generator receives the truck navigation path from the on-board terminal via the edge computing device.

[0086] In step S730, the coordinates of the cargo transfer station are determined based on the matching result between the cargo transportation route and the truck navigation path.

[0087] In some embodiments, by matching the cargo transportation route with the truck navigation path, the route deviation point between the cargo transportation route and the truck navigation path is used as a cargo transfer station, and the coordinates of the cargo transfer station are determined as the transfer station coordinates, thereby automatically identifying the transfer station coordinates without the need for barcode scanning.

[0088] In some examples of the embodiments of the present application, the RFID tag box 41 automatically identifies the category information of the contained object through the cooperation of the camera 540 and the object classification model 550. Figure 8 An operational flowchart of an example of identifying category information of an object according to an embodiment of the present application is shown.

[0089] like Figure 8 As shown, in step S810, based on the camera, the cargo image corresponding to the cargo contained in the RFID tag box is collected.

[0090] In step S820, the cargo image is input into an object classification model to determine the cargo type corresponding to the cargo, and the object classification model adopts a deep learning model.

[0091] As a result, the RFID tag box can automatically identify the type of goods it contains, so that when the user replaces the goods in the RFID tag box, the change event of the goods type is identified, thereby automatically updating the corresponding goods RFID tag, improving the automated labeling process for logistics goods.

[0092] Fig. 9 A schematic structural diagram of an example of an object classification model according to an embodiment of the present application is shown.

[0093] like Fig. 9 As shown, the input of the object classification model 900 is a cargo image, i.e., an image of an object placed in a label box, and its output is a target classification, i.e., a probability distribution of the category to which the object belongs. The object classification model 900 includes a deep residual network module 910, an SE network module 920, and a classification network module 930.

[0094] More specifically, the deep residual network module 910 is used to extract image features in the target image set, and the deep residual network module includes multiple residual blocks, each of which includes several convolutional layers.

[0095] The structure of the residual block is:

[0096] F(x,{W i})+x formula (1)

[0097] In the formula, F(x,{W i}) represents the residual mapping achieved by the convolutional layer, W i Represents the weight of the convolutional layer, x represents the input feature of the residual block, where the input feature corresponding to the first residual block is determined according to the target image set.

[0098] The SE network module 920 includes multiple SE blocks, each of which is inserted after each residual block in the deep residual network module to perform channel-level weight adjustment on the feature map output by each residual block.

[0099] The structure of the SE block is:

[0100]

[0101] Where F(x) c,h,w represents the activation value of the element (h,w) at a specific position in the feature map on the cth channel, h and w represent the position index on the height and width of the feature map respectively; H and W are the height and width of the feature map; S represents the average activation value of all spatial positions of the feature map on channel c through the squeezing operation; σ represents the sigmoid activation function, δ represents the ReLU activation function, and W1 and W2 are the weights of the fully connected layer; represents the output of the SE block at the cth channel.

[0102] The classification network module 930 is connected to the last SE block and is used to perform classification prediction based on the features adjusted by the SE block weights to output the corresponding target classification.

[0103] The structure of the classification network module 930 is:

[0104]

[0105] Where P(y=j|x) represents the probability of determining that an object belongs to category j based on the input target image set x, and z j It represents the output score of the jth category calculated by the classification layer, and K represents the total number of categories for object classification.

[0106] Based on the above processing flow, features are extracted through the deep residual network module 910, and the importance of the features is adjusted at the channel level using the SE network module 920. Finally, the probability of each category is output through the classification network module 930 to accurately identify and classify various items to be transported in logistics.

[0107] It should be noted that in logistics scenarios, the shapes, sizes, and appearances of items may vary greatly. The model designed with this structure can effectively cope with the diversity of classification targets while maintaining efficient and accurate classification performance. Specifically, after extracting complex image features using a deep network structure, the introduced SE block emphasizes important feature channels through an attention mechanism, allowing the model to focus on information that is most helpful for classification, thereby improving classification accuracy. In addition, the attention mechanism reduces the processing of irrelevant information by focusing on key features, thereby improving the processing efficiency of the model.

[0108] Furthermore, in combination with the object classification scenario of the intelligent logistics system of the embodiment of the present application, in order to improve the classification performance and training efficiency of the model, especially when facing the classification processing of multi-category and unbalanced data sets, the embodiment of the present application provides a loss function that combines cross entropy loss and focal loss, namely, the weighted focal cross entropy loss function.

[0109] In some examples of the embodiments of the present application, the loss function of the object classification model is:

[0110]

[0111] In the formula, y k is the true label corresponding to the training sample. If the training sample belongs to category k, then y k =1, otherwise y k =0; p k is the probability of category k predicted by the model, w k represents the weight for category k, γ represents the preset adjustment focus parameter, m(k) represents the relative frequency of category k in the data set, and ζ represents a preset constant. Here, ζ is a small constant (e.g., 1.02) used to ensure numerical stability.

[0112] In the loss function provided in the embodiment of the present application, in order to solve the problem of class imbalance, each class k is assigned a weight w k , which is inversely proportional to the frequency of occurrence of the class. The focus parameter γ is used to reduce the relative loss of easily classified samples and increase the penalty for difficult or misclassified samples.

[0113] Here, γ is mainly used to reduce the relative contribution of easy-to-classify samples while increasing attention to hard-to-classify samples. The determination process for γ can be diverse. For example, the typical initial value of γ can start from 2.0 based on experience. If it is found that the model performs poorly for hard-to-classify samples (for example, the accuracy of some minority categories is low), you can try to increase the value of γ. On the contrary, if the model over-punishes easy-to-classify samples, resulting in a decrease in overall performance, the value of γ can be reduced.

[0114] Through the embodiments of the present application, in logistics scenarios, some items may appear more frequently than other items. The weighted focal cross entropy loss is used to assign different weights to samples of different categories to solve this imbalance and ensure that the model does not favor more common categories. Through the focus parameters, the model pays more attention to samples that are difficult to classify (i.e., samples with a low model prediction probability), which helps to improve the model's ability to recognize complex or uncommon items. As a result, the object classification model can more effectively handle category imbalance in the intelligent logistics system, focusing on improving the recognition ability of difficult-to-classify samples, thereby improving the classification performance of the overall model.

[0115] Fig.10 A flowchart of an example of an intelligent cargo tracking and management method based on the Internet of Things according to an embodiment of the present application is shown.

[0116] like Fig.10 As shown, in step S1010, the cargo RFID tag data of each cargo in the truck compartment is collected based on the RFID reader configured in the truck compartment, and the RFID tag data of each cargo is sent to the edge computing device configured in the truck compartment.

[0117] Here, the cargo RFID tag data includes cargo identification information of the corresponding cargo, multiple environmental parameter safety intervals, and cargo transfer station coordinates; each environmental parameter safety interval has a corresponding environmental parameter type;

[0118] In step S1020, environmental sensor data corresponding to the truck compartment is collected based on the IoT environmental sensor group installed in the truck compartment, and the environmental sensor data is sent to the edge computing device.

[0119] Here, the environmental sensing data includes the following environmental parameters: environmental temperature parameter, environmental humidity parameter, vibration intensity parameter and acceleration parameter.

[0120] In step S1030, based on the edge computing device, the vehicle positioning information of the truck compartment is obtained, and for each cargo RFID tag data, the coordinates of the cargo transfer station in the cargo RFID tag data are compared with the vehicle positioning information, and when a match is determined, the package transfer alarm action is executed according to the cargo RFID tag data.

[0121] In step S1040, for each environmental parameter safety interval in the cargo RFID tag data, the environmental parameter safety interval is matched with the corresponding type of environmental parameters in the environmental sensor data, and the package status abnormal action is executed according to the unmatched abnormal environmental parameters.

[0122] For details of the above-mentioned intelligent cargo tracking and management method based on the Internet of Things, part of the description in conjunction with the intelligent cargo tracking and management system based on the Internet of Things may be referred to above, and the references may correspond to each other.

[0123] In some embodiments, an embodiment of the present application provides a non-volatile computer-readable storage medium, in which one or more programs including execution instructions are stored. The execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute the above-mentioned IoT-based intelligent cargo tracking and management method of the present application.

[0124] In some embodiments, the embodiments of the present application also provide a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned intelligent cargo tracking and management method based on the Internet of Things.

[0125] In some embodiments, the embodiments of the present application also provide an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute an intelligent cargo tracking and management method based on the Internet of Things.

[0126] Fig.11 is a schematic diagram of the hardware structure of an electronic device for executing an intelligent cargo tracking and management method based on the Internet of Things provided by another embodiment of the present application, such as Fig.11 As shown, the device includes:

[0127] One or more processors 1110 and memory 1120, Fig.11 A processor 1110 is taken as an example.

[0128] The device for executing the intelligent cargo tracking and management method based on the Internet of Things may further include: an input device 1130 and an output device 1140 .

[0129] The processor 1110, the memory 1120, the input device 1130 and the output device 1140 may be connected via a bus or other means. Fig.11 The example of connecting through bus is taken in the following.

[0130] The memory 1120, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the intelligent cargo tracking and management method based on the Internet of Things in the embodiment of the present application. The processor 1110 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 1120, that is, the intelligent cargo tracking and management method based on the Internet of Things in the above method embodiment is realized.

[0131] The memory 1120 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 1120 may optionally include a memory remotely arranged relative to the processor 1110, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0132] The input device 1130 may receive input digital or character information and generate signals related to user settings and function control of the electronic device. The output device 1140 may include a display device such as a display screen.

[0133] The one or more modules are stored in the memory 1120, and when executed by the one or more processors 1110, the intelligent cargo tracking and management method based on the Internet of Things in any of the above method embodiments is executed.

[0134] The above-mentioned product can execute the intelligent cargo tracking and management method based on the Internet of Things provided in the embodiment of this application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of this application.

[0135] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

[0136] (1) Mobile communication equipment: This type of equipment is characterized by having mobile communication functions and its main purpose is to provide voice and data communications. This type of terminal includes: smart phones, multimedia phones, functional phones, and low-end phones.

[0137] (2) Ultra-mobile personal computer devices: These devices belong to the category of personal computers, have computing and processing functions, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, etc.

[0138] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players, handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0139] (4) Other onboard electronic devices with data interaction functions, such as on-board devices installed in vehicles.

[0140] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent cargo tracking and management method based on the Internet of Things, comprising: Based on the RFID reader configured in the truck compartment, the cargo RFID tag data of each cargo in the truck compartment is collected, and each cargo RFID tag data is sent to the edge computing device configured in the truck compartment; the cargo RFID tag data includes cargo identification information of the corresponding cargo, multiple environmental parameter safety intervals and cargo transfer station coordinates; each environmental parameter safety interval has a corresponding environmental parameter type; Based on the IoT environmental sensor group set in the truck compartment, the environmental sensor data corresponding to the truck compartment is collected, and the environmental sensor data is sent to the edge computing device; the environmental sensor data includes the following environmental parameters: environmental temperature parameter, environmental humidity parameter, vibration intensity parameter and acceleration parameter; The edge computing device is used to: Obtaining vehicle positioning information of the truck compartment; For each of the cargo RFID tag data, the following operations are performed: Comparing the cargo transfer station coordinates in the cargo RFID tag data with the vehicle positioning information, and executing a package transfer alarm action according to the cargo RFID tag data if a match is determined; For each environmental parameter safety interval in the cargo RFID tag data, the environmental parameter safety interval is matched with the corresponding type of environmental parameters in the environmental sensor data, and the package status abnormal action is performed according to the unmatched abnormal environmental parameters.

2. The method according to claim 1, wherein: A plurality of RFID tag boxes are arranged in the truck compartment, and each of the RFID tag boxes is used to contain corresponding goods; The RFID tag box includes an RFID tag generator, and the RFID tag generator is used to regenerate a corresponding RFID tag according to the currently contained goods when it is determined that the goods type of the contained goods has changed.

3. The method according to claim 2, wherein: The RFID tag box is provided with an audible and visual alarm module and a signal transmission module; The parcel transfer alarm action includes: triggering the RFID tag box corresponding to the cargo RFID tag data to perform a light flashing alarm operation corresponding to a first alarm color, and performing a voice alarm operation according to a preset transfer voice setting; The abnormal package status action includes: triggering the RFID tag box corresponding to the cargo RFID tag data to perform a light flashing alarm operation corresponding to the second alarm color, and sending the cargo identification information in the cargo RFID tag data to the edge computing device.

4. The method according to claim 2, wherein: The method further comprises: The RFID tag generator is used to perform the following operations to determine the environmental parameter safety interval, specifically including: Receiving cargo transportation environment parameter settings corresponding to cargo identification information from a logistics management platform server; the logistics management platform server is also used to receive a cargo logistics setting request from a user terminal, wherein the cargo transportation environment parameter settings are determined according to user input information corresponding to the cargo logistics setting request; Determine a target calibration environmental parameter interval according to a preset environmental parameter calibration table in combination with the cargo type corresponding to the cargo identification information; the environmental parameter calibration table includes multiple cargo types and corresponding calibration environmental parameter intervals; An environmental parameter safety range is determined based on the cargo transportation environmental parameter settings and the target calibration environmental parameter range.

5. The method according to claim 4, wherein: The method further comprises: The RFID tag generator is used to perform the following operations to determine the coordinates of the cargo transfer station, specifically including: Receiving a cargo transportation route matching the cargo identification information from the logistics management platform server; receiving a truck navigation path from a vehicle-mounted terminal corresponding to the truck compartment; The coordinates of the cargo transfer station are determined according to the matching result of the cargo transportation route and the truck navigation path.

6. The method according to claim 2, wherein: The RFID tag box is provided with a camera and an object classification model, which specifically includes: Based on the camera, collecting the cargo image corresponding to the cargo contained in the RFID tag box; The cargo image is input into an object classification model to determine the cargo type corresponding to the cargo, and the object classification model adopts a deep learning model.

7. The method according to claim 6, wherein: The object classification model includes a deep residual network module, an SE network module and a classification network module; The deep residual network module is used to extract image features in the cargo image; the deep residual network module includes a plurality of residual blocks, each of which includes a plurality of convolutional layers; The structure of the residual block is: F(x,{W i })+x In the formula, F(x,{W i }) represents the residual mapping achieved by the convolutional layer, W i represents the weight of the convolutional layer, and x represents the input feature of the residual block, wherein the input feature corresponding to the first residual block is determined according to the cargo image; The SE network module includes a plurality of SE blocks, each of which is inserted after each residual block in the deep residual network module to perform channel-level weight adjustment on a feature map output by each residual block; The structure of the SE block is: In the formula, F(x) c,h,w represents the activation value of the element (h,w) at a specific position in the feature map on the cth channel, where h and w represent the position index in the height and width of the feature map respectively; H and W are the height and width of the feature map; S represents the average activation value of all spatial positions of the feature map on channel c through the squeezing operation; σ represents the sigmoid activation function, δ represents the ReLU activation function, and W1 and W2 are the weights of the fully connected layer; represents the output of the SE block at the cth channel; The classification network module is connected to the last SE block and is used to perform classification prediction based on the features adjusted by the SE block weights to output the corresponding target classification; The structure of the classification network module is: Where P(y=j|x) represents the probability of determining that an item belongs to category j based on the input cargo image x, and z j It represents the output score of the jth category calculated by the classification layer, and K represents the total number of categories for object classification.

8. The method according to claim 7, wherein: The loss function of the object classification model is: In the formula, y k is the true label corresponding to the training sample. If the training sample belongs to category k, then y k =1, otherwise y k =0; p k is the probability of category k predicted by the model, w k represents the weight for category k, γ represents the preset adjustment focus parameter, m(k) represents the relative frequency of category k in the data set, and ζ represents a preset constant.

9. The method according to any one of claims 1 to 8, wherein: The edge computing device is also used to perform the following operations: The positioning data, environmental sensor data and each cargo RFID tag data corresponding to the truck compartment are sent to the logistics management platform server, so that the logistics management platform server updates the logistics transportation status of the cargo corresponding to each cargo RFID tag data according to the positioning data and the environmental sensor data.

10. An intelligent cargo tracking and management system based on the Internet of Things, comprising: Edge computing equipment, installed in the truck compartment; An RFID reader is provided in the truck compartment and is used to collect cargo RFID tag data of each cargo in the truck compartment and send each cargo RFID tag data to the edge computing device; the cargo RFID tag data includes cargo identification information of the corresponding cargo, a plurality of environmental parameter safety intervals and cargo transfer station coordinates; each environmental parameter safety interval has a corresponding environmental parameter type; An IoT environment sensor group is arranged in the truck compartment and is used to collect environment sensor data corresponding to the truck compartment and send the environment sensor data to the edge computing device; the environment sensor data includes the following environment parameters: environment temperature parameter, environment humidity parameter, vibration intensity parameter and acceleration parameter; The edge computing device is used to perform the following operations: For each of the cargo RFID tag data, the following operations are performed: Comparing the cargo transfer station coordinates in the cargo RFID tag data with the vehicle positioning information, and executing a package transfer alarm action according to the cargo RFID tag data if a match is determined; For each environmental parameter safety interval in the cargo RFID tag data, the environmental parameter safety interval is matched with the corresponding type of environmental parameters in the environmental sensor data, and the package status abnormal action is performed according to the unmatched abnormal environmental parameters.

Images