Intelligent card slot control method for closed border operation

Abstract

The application provides an intelligent checkpoint control method for closed-border operation, which includes breaking the defect of existing regulatory node dispersion through a distributed node cluster architecture, and realizing centralized management of intelligent checkpoints and associated regulatory nodes. Through a closed-loop link of registration-state awareness-lifetime management, the running state of each regulatory node is mastered. Based on the identification code, unique identification is established for regulatory nodes, regulatory node devices, and objects to be tracked, and an associated mapping of identification code-attribute information is formed, solving the problem of identity confusion and tracing difficulty of multi-source control objects. By encapsulating real-time data into standardized messages of a preset format, and combining the multi-source heterogeneous feature extraction of edge computing nodes, the dispersed attribute information is fused into structured data sets, realizing efficient data interconnection and accurate comparison across nodes and systems. Combined with a preset abnormality judgment model, the structured data sets are compared with the benchmark threshold to implement intelligent checkpoint control and realize accurate identification.

Description

Technical Field

[0001] This application relates to the field of system control technology, and in particular to an intelligent checkpoint control method for customs clearance operations. Background Technology

[0002] The existing port checkpoints generally adopt a decentralized operation model, with checkpoint systems deployed separately in different regulatory sites and secondary ports. This has failed to form a complete control system within a designated area, making it difficult to coordinate and allocate checkpoint resources and resulting in insufficient standardization of business management. Summary of the Invention

[0003] The purpose of this application is to at least partially solve one of the technical problems in the related art.

[0004] Therefore, the first objective of this application is to propose an intelligent checkpoint control method for customs closure operations.

[0005] The second objective of this application is to propose an intelligent checkpoint control device for customs clearance operations.

[0006] The third objective of this application is to propose an electronic device.

[0007] The fourth objective of this application is to provide a computer-readable storage medium.

[0008] The fifth objective of this application is to provide a computer program product.

[0009] To achieve the above objectives, the first aspect of this application proposes a smart checkpoint control method for customs closure operations, comprising: For various monitoring nodes containing smart checkpoints within a designated area, a management system is established based on a distributed node cluster architecture to complete the registration and status awareness of each monitoring node. Based on the monitoring node operation status association information obtained from the status awareness, full lifecycle management is implemented for each monitoring node to form a full lifecycle management link for the monitoring node. Based on the device ledger information of the registered regulatory nodes in the full lifecycle management link, an identification code is assigned to each regulatory node and the corresponding controlled object, and an association mapping relationship is established between the identification code and the attribute information of the corresponding controlled object, wherein the controlled object includes regulatory node devices, associated terminal devices and objects to be tracked; Based on the association mapping relationship between the identification code and the corresponding controlled object attribute information, real-time data of each smart checkpoint is collected, wherein the real-time data includes transportation equipment information, cargo information and attribute information related to the controlled object; The real-time data is encapsulated into standardized messages in a preset format, and the standardized messages are subjected to multi-source heterogeneous feature extraction based on identifier anchoring on edge computing nodes with a distributed node cluster architecture to generate a fusion dataset containing the identity features, running status features, and spatiotemporal correlation features of the managed objects. Based on a preset anomaly detection model, the baseline threshold of the attribute information of the controlled object is compared with the fused feature dataset to identify the abnormal state of the controlled object, and a preset control strategy is matched according to the abnormal state to execute intelligent checkpoint control.

[0010] To achieve the above objectives, a second aspect of this application provides an intelligent checkpoint control device for customs closure operations, comprising: The node management module is used to establish a management system based on a distributed node cluster architecture for various types of regulatory nodes containing smart checkpoints within a specified area to complete the registration and status awareness of each regulatory node, and to implement full life cycle management of each regulatory node based on the regulatory node operation status association information obtained from the status awareness, so as to form a full life cycle management link for regulatory nodes. The coding management module is used to assign identification codes to each regulatory node and its corresponding controlled object based on the device ledger information of the registered regulatory nodes in the full life cycle management link, and to establish an association mapping relationship between the identification codes and the attribute information of the corresponding controlled objects, wherein the controlled objects include regulatory node devices, associated terminal devices and objects to be tracked; The data acquisition module is used to collect real-time data from each smart checkpoint based on the association mapping relationship between the identification code and the corresponding controlled object attribute information. The real-time data includes transportation equipment information, cargo information and attribute information related to the controlled object. The message management module is used to encapsulate the real-time data into standardized messages in a preset format, and to perform multi-source heterogeneous feature extraction based on identifier code anchoring on the standardized messages on edge computing nodes based on a distributed node cluster architecture, thereby generating a fusion dataset containing the identity features, running status features, and spatiotemporal correlation features of the controlled object. The operation and control module is used to identify the abnormal state of the controlled object by comparing the baseline threshold of the attribute information of the controlled object with the fused feature dataset based on a preset anomaly judgment model, and to match a preset control strategy according to the abnormal state to execute intelligent checkpoint control.

[0011] To achieve the above objectives, a third aspect of this application provides an electronic device, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the steps of the smart checkpoint control method for customs clearance operations proposed in the first aspect of this application.

[0012] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium that, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the steps of the smart checkpoint control method for customs clearance operations proposed in the first aspect of this application.

[0013] To achieve the above objectives, a fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor in a communication device, implements the steps of the smart checkpoint control method for customs clearance operations proposed in the first aspect of this application.

[0014] In this embodiment, a distributed node cluster architecture overcomes the shortcomings of existing decentralized regulatory nodes, enabling centralized and coordinated management of all smart checkpoints and associated regulatory nodes within a designated area, thus addressing pain points such as difficulty in resource scheduling and inconsistent management standards. Through a closed-loop link of registration, status awareness, and full lifecycle management, the operational status of each regulatory node is monitored in real time. Combined with load balancing and collaborative fault handling mechanisms, the efficiency of regulatory resource utilization and overall system stability are improved, adapting to the large-scale needs of expanding the number and scope of regulatory nodes within the area. A unique identifier is established for all controlled objects, including regulatory nodes, regulatory node equipment, and objects to be tracked, based on identification codes, forming an association mapping between identification codes and attribute information, solving the problems of identity confusion and traceability difficulties for multi-source controlled objects. By encapsulating real-time data into standardized messages in a preset format, the data collection and transmission formats are unified. Combined with multi-source heterogeneous feature extraction from edge computing nodes, scattered information on transport equipment, cargo, and attribute information related to controlled objects is integrated into a structured dataset, achieving efficient data exchange and accurate comparison across nodes and systems, providing data support for control decisions. By integrating the identity features, operational status features, and spatiotemporal correlation features of the controlled objects into a unified dataset, and comparing them with a pre-set anomaly judgment model and a benchmark threshold, the system can accurately identify scenarios such as equipment failure, cargo anomalies, and transportation violations, thus avoiding misjudgments and omissions caused by existing single-dimensional judgments.

[0015] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0016] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart illustrating a smart checkpoint control method for customs clearance operations provided in this application embodiment; Figure 2 A schematic diagram of the structure of an intelligent checkpoint control device for customs clearance operations provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0017] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0018] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the embodiments of this application. The singular forms “a” and “the” as used in the embodiments of this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0019] It should be understood that although the terms first, second, third, etc., may be used to describe various information in the embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words "if" and "suppose" as used herein can be interpreted as "when," "when," or "in response to a determination."

[0020] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0021] The existing checkpoint systems at ports of entry are deployed using individual hardware devices (such as weighbridges, inspection equipment, and servers), lacking a cross-site resource sharing mechanism. Due to fluctuations in business volume, some ports experience equipment saturation and queue congestion during peak hours, while idle equipment in adjacent regulatory sites cannot provide rapid support.

[0022] In a decentralized model, each checkpoint needs to be equipped with its own personnel for maintenance, inspection, and scheduling, and the skill levels of these personnel vary widely. When an emergency occurs at a checkpoint (such as equipment failure or a surge in business), it is impossible to quickly allocate manpower support from other checkpoints, resulting in low efficiency in emergency response. Moreover, the lack of a unified scheduling platform for personnel operating across checkpoints leads to delayed information transmission, further affecting the overall smoothness of operations.

[0023] Each checkpoint system has its own independent computing and storage architecture, which cannot form a clustered computing power support. Faced with massive amounts of video surveillance data, cargo inspection data, and equipment operation data, the storage capacity of a single checkpoint system is easily saturated, data backup and disaster recovery capabilities are weak, and the dispersed computing power is difficult to support the complex data comparison, feature extraction and other intelligent analysis needs, thus restricting the improvement of the level of intelligent supervision.

[0024] Different regulatory sites and secondary ports have established their own operational procedures based on their respective management requirements, resulting in differences in cargo inspection standards, personnel access regulations, and data recording formats. For example, some checkpoint systems adopt a "check first, then enter" model, while others adopt a "enter first, then check" model. This causes goods flowing across checkpoints to have to repeatedly adapt to different procedures, reducing customs clearance efficiency. At the same time, the differences in procedures can easily lead to problems such as missed inspections and incorrect data entry, affecting the standardization of supervision.

[0025] Due to the lack of unified data management standards, the data collected by various checkpoint systems (such as container numbers, license plate numbers, and cargo weights) are inconsistent in format and field definitions, and there are even cases of duplicate data collection and missing key information. This fragmented data cannot form a complete regulatory data chain, making it difficult to support data sharing and collaborative analysis across checkpoint systems and departments, and also failing to provide accurate and comprehensive data support for regulatory decisions, leading to subjectivity and blindness in regulatory decisions.

[0026] The following description, with reference to the accompanying drawings, describes an embodiment of an intelligent checkpoint control method for customs clearance operations.

[0027] Figure 1 This is a flowchart illustrating a smart checkpoint control method for customs clearance operations provided in an embodiment of this application. Figure 1 As shown, this intelligent checkpoint control method for customs closure operations includes, but is not limited to, the following steps: S101 establishes a management system based on a distributed node cluster architecture for various regulatory nodes with smart checkpoints within a designated area to complete the registration and status awareness of each regulatory node. Based on the operational status association information of the regulatory nodes obtained from the status awareness, it implements full lifecycle management of each regulatory node to form a full lifecycle management link for the regulatory nodes.

[0028] In one feasible implementation, a distributed node cluster architecture is constructed, comprising a main management node, edge sensing nodes, and communication relay nodes. Specifically, the main management node performs registration review and full lifecycle management decisions for the monitoring nodes; edge sensing nodes are deployed near each smart checkpoint to collect the operational status of the monitoring nodes; and communication relay nodes are configured based on a preset encrypted transmission protocol to perform data interaction between the main management node and the edge sensing nodes.

[0029] In some embodiments, the main management node is configured to receive registration applications for regulatory nodes, review application materials, and provide feedback on registration results. It is also granted full lifecycle management decision-making authority to generate status assessment conclusions, maintenance scheduling instructions, and deregistration and scrapping decisions for regulatory nodes.

[0030] In some embodiments, edge sensing nodes are deployed within a preset range of the corresponding smart checkpoint based on the geographical location and monitoring scope of each smart checkpoint. The acquisition parameters and acquisition frequency of the edge sensing nodes are configured so that the edge sensing nodes can acquire real-time operating status data of the monitoring nodes. The operating status data includes equipment voltage, operating temperature, data transmission rate, and fault alarm signals.

[0031] In some embodiments, a preset encrypted transmission protocol including a key negotiation algorithm, a data encryption algorithm, and an integrity verification algorithm is selected. Based on the selected preset encrypted transmission protocol, the communication relay node is configured, setting the communication ports, IP address mappings, and encryption keys between the main management node and the edge sensing nodes. A connectivity test is performed on the configured communication relay node to verify the data sending, receiving, and encryption / decryption functions between the main management node and each edge sensing node, ensuring the security and stability of data interaction.

[0032] In some embodiments, the main management node, edge sensing node, and communication relay node adopt a database sharding and table partitioning strategy, and implement data sharding storage based on Sharding-JDBC. It should be noted that after the main management node, edge sensing node, and communication relay node are deregistered, data archives for a preset period (e.g., 60 days) are retained through a scheduled task mechanism, and asynchronous deletion operations are supported.

[0033] In one feasible implementation, the registration of the monitoring node includes: triggering a registration request when a new monitoring node containing a smart checkpoint is detected in a designated area, wherein the registration request carries basic information of the monitoring node, including node type, device model, installation location, and the control area to which it belongs; verifying the registration request based on a distributed node cluster architecture to obtain verification information containing the completeness of the basic information and whether the monitoring node meets the preset access standards; if the verification information indicates that the verification is successful, registering the monitoring node and completing the archiving; if the verification information indicates that the verification is unsuccessful, returning a verification failure message and supplementary correction suggestions.

[0034] In some embodiments, a standardized registration interface is designed based on a RESTful API, and JWT tokens are used to implement identity authentication and permission verification for registration requests. Metadata storage for channels, port areas, terminals, checkpoints, and equipment adopts a structured data table design, and Redis caching of frequently accessed registration information improves query response speed.

[0035] In one feasible implementation, the status perception adopts a combination of periodic perception and triggering perception. Periodic control is executed based on a preset cycle; triggering perception is executed when the monitoring node is detected to start, restart, or generate a fault alarm. The perception content includes the smart checkpoint's device operating parameters, network connection status, data transmission rate, and load status, as well as device voltage, operating temperature, and fault alarm signals.

[0036] S102. Based on the equipment ledger information of the registered regulatory nodes in the full lifecycle management link, assign identification codes to each regulatory node and the corresponding controlled object, and establish an association mapping relationship between the identification code and the attribute information of the corresponding controlled object. The controlled object includes regulatory node equipment, associated terminal equipment and objects to be tracked.

[0037] In one feasible implementation, the equipment ledger information includes the equipment model, production batch, deployment location, region, and a list of associated equipment for the monitoring nodes. The specific scope of the controlled objects is clearly defined, encompassing the monitoring node equipment itself, associated terminal devices that interact with the monitoring nodes, and objects to be tracked via smart checkpoints.

[0038] In one feasible implementation, based on the differentiated characteristics in the equipment ledger information, a unique identification code is assigned to each regulatory node, associated terminal device and object to be tracked. The identification code contains an identification segment used to distinguish the object type.

[0039] In some embodiments, a hierarchical coding structure is used to design the identification code. The hierarchical coding structure includes a region coding segment, a node type coding segment, a device number segment, and a first check code segment. Specifically, the administrative region information of the smart checkpoint is mapped to the region coding segment, the device type information of the regulatory node is mapped to the node type coding segment, a unique device number is assigned to each regulatory node and controlled object as the device number segment, and the verification result generated based on the region coding segment, node type coding segment, and device number segment serves as the first check code segment.

[0040] For example, the snowflake algorithm is used to assign a unique identifier to each monitoring node, associated terminal device, and object to be tracked.

[0041] In one feasible implementation, an association mapping relationship is established between the identification code and the corresponding attribute information of the controlled object, including: classifying and collecting static and dynamic attributes of the controlled object, wherein the static attributes include the equipment name, equipment model, equipment rated parameters, size and material of the object to be tracked, and the dynamic attributes include the equipment operating parameters, the moving speed of the object to be tracked, the location information of the object to be tracked, and the interaction data between the equipment and the object to be tracked, wherein the equipment includes regulatory node equipment and associated terminal equipment.

[0042] In one feasible implementation, an association mapping relationship is established between identifier codes and static and dynamic attributes. An association mapping database is built, establishing a one-to-one correspondence between each identifier code and each static and dynamic attribute, and an update interface for static and dynamic attribute information is set up to ensure data real-time performance. The established association mapping relationship is validated by querying the corresponding attribute information through the identifier code to verify the accuracy and completeness of the information. Once the validation is successful, the formal establishment of the association mapping relationship is complete.

[0043] S103. Based on the association mapping relationship between the identification code and the corresponding controlled object attribute information, collect real-time data from each smart checkpoint. The real-time data includes information on the transport equipment, cargo, and attribute information related to the controlled object.

[0044] In one feasible implementation, the association mapping relationship is used to sort out the list of controlled objects and their corresponding identification codes within the coverage area of ​​each smart checkpoint, forming a data collection benchmark catalog.

[0045] In one feasible implementation, a data acquisition device for a smart checkpoint is configured and associated with an identification code in the data acquisition baseline catalog. This allows the data acquisition device to accurately identify the controlled object through the identification code, ensuring that the collected data corresponds one-to-one with the controlled object.

[0046] In one feasible implementation, a multi-dimensional data collection process is initiated to collect information on the transport equipment passing through the smart checkpoint, such as its license plate, model, load capacity, and speed; and to collect information on the goods carried by the transport equipment, such as the name, quantity, weight, and hazard class of the goods.

[0047] In one feasible implementation, dynamic attribute information related to the controlled object is collected in a targeted manner by combining the attribute information of the controlled object in the association mapping relationship, including the real-time operating parameters of the monitoring node equipment, the interaction data of the associated terminal equipment, and the location and status information of the object to be tracked.

[0048] In one feasible implementation, during the data collection process, each piece of real-time data is bound and marked with the identification code of the corresponding controlled object to form an associated data group of "identification code-real-time data".

[0049] In one feasible implementation, the bound associated data group is initially verified to check whether the data format matches the attribute information specifications in the associated mapping relationship, invalid data is removed, and the validity and relevance of the collected data are ensured.

[0050] S104 encapsulates real-time data into standardized messages in a preset format, and performs multi-source heterogeneous feature extraction based on identifier code anchoring on the standardized messages on edge computing nodes with a distributed node cluster architecture, generating a fusion dataset containing the identity features, operating status features, and spatiotemporal correlation features of the managed objects.

[0051] In one feasible implementation, a standardized message format is preset. This preset format includes a message header, an identifier field, a data type field, a data length field, a data field, and a second verification field. The message header is used to identify the smart checkpoint number, and the second verification field is used to verify message integrity. In some embodiments, the preset standardized message format includes XML and JSON; standardized message transmission is performed through a Socket communication interface built using the Netty framework.

[0052] In one feasible implementation, based on the associated data group of "identification code-real-time data", the information of the transport equipment, cargo, and attribute information of the controlled object are filled into the corresponding fields according to the preset format, thereby completing the standardized encapsulation of a single real-time data and forming a standardized message.

[0053] In one feasible implementation, the standardized message is subjected to integrity verification. The algorithm logic of the second verification field verifies whether the data in each field is complete and whether the format is compliant. Messages that fail the verification are removed and fed back to the collection device of the corresponding smart checkpoint.

[0054] In one feasible implementation, the standardized message that has passed verification is transmitted to the edge computing node of the distributed node cluster architecture, and the mapping relationship between the identifier code and the attribute information of the managed object is synchronized to the edge computing node.

[0055] In one feasible implementation, edge computing nodes perform multi-source heterogeneous feature extraction based on identifier anchoring. In some embodiments, using the identifier as an anchor point, multi-source (different acquisition devices), heterogeneous type (structured / unstructured) message data associated with the same identifier are aggregated.

[0056] In one feasible implementation, multi-source heterogeneous feature extraction is performed on the standardized messages after classification and aggregation. The identification code and type identifier of the controlled object are extracted as identity features; the equipment operating parameters and load status are extracted as operating status features; and a fused dataset containing the identity features of the controlled object, operating status features (including equipment operating parameters and load status), and spatiotemporal correlation features (including timestamps, smart checkpoint location information, etc.) is generated.

[0057] In some embodiments, the data collected by the smart checkpoint includes, but is not limited to: real-time customs clearance data pushed via WebSocket, multi-dimensional statistical analysis data on customs clearance status of seaports, airports, and railways built based on E-Charts, video stream data, and voice data.

[0058] In one feasible implementation, after generating a fused dataset containing the identity characteristics, operational status characteristics, and spatiotemporal correlation characteristics of the controlled object, the summary information of the fused dataset is obtained, and the generation time of the fused dataset is recorded. The corresponding identifier, summary information, and generation time are associated, and the associated information is encrypted using blockchain-level encryption. The encryption result is written into a blockchain block. Simultaneously, the hash value and block height of the block are recorded, completing the blockchain notarization of the fused dataset information and ensuring the data's immutability and traceability.

[0059] It should be noted that if a smart checkpoint encounters a network outage, the discrete data generated during the outage should be analyzed. This discrete data includes intermittent status data of the controlled object, discrete signals triggered by device start-up and shutdown, and instantaneous data from sudden failures. Timestamps and corresponding identification codes for the controlled object are added to the discrete data, and it is standardized according to a preset discrete data format specification to ensure compatibility with the standardized message format generated earlier. A discrete data synchronization channel is established, and an asynchronous synchronization mechanism is used to transmit the standardized discrete data to the edge computing node. During the synchronization process, the data transmission status is recorded, and a retransmission mechanism is triggered for discrete data that fails to transmit. After receiving the discrete data, the edge computing node associates and aggregates the discrete data with the standardized message data that has passed verification, based on the identification code, ensuring that continuous data and discrete data of the same controlled object form a complete data chain. The standardized message after associating and aggregating the discrete data is transmitted to the edge computing node in a distributed node cluster architecture, while simultaneously synchronizing the mapping relationship between the identification code and the controlled object attribute information to the edge computing node.

[0060] S105, based on a preset anomaly judgment model, compares the baseline threshold of the attribute information of the controlled object with the fused feature dataset, identifies the abnormal state of the controlled object, and matches the preset control strategy according to the abnormal state to execute intelligent checkpoint control.

[0061] In one feasible implementation, the anomaly judgment model is obtained by training multiple sets of data through machine learning. The multiple sets of data include a first type of data and a second type of data. Each set of data in the first type of data includes the historical normal state of the controlled object and the first label corresponding to the historical normal state. Each set of data in the second type of data includes the historical abnormal state of the controlled object and the second label corresponding to the historical abnormal state.

[0062] In one feasible implementation, a baseline threshold for the attribute information of the controlled object is determined based on the application scenario, industry standards, and actual control requirements. An anomaly detection model compares the baseline threshold with the corresponding feature indicators in the fused feature dataset. Combining this with the normal / abnormal state identification logic learned during model training, the model outputs the abnormal state identification result for the controlled object. The abnormal state identification result includes whether it is abnormal, the type of abnormality, and the severity of the abnormal state.

[0063] In one feasible implementation, abnormal states are categorized into minor, moderate, and severe abnormalities based on their severity. Corresponding preset control strategies are matched to different levels of abnormal states: minor abnormalities correspond to early warning prompts, moderate abnormalities correspond to access restrictions, and severe abnormalities correspond to forced shutdown and alarm activation.

[0064] In one feasible implementation, the matched control measures are sent to the execution device of the corresponding smart checkpoint to perform the smart checkpoint control operation and record the time, content and result of the control operation.

[0065] In summary, the intelligent checkpoint control method for customs clearance operations provided in this application overcomes the shortcomings of existing decentralized regulatory nodes through a distributed node cluster architecture, achieving centralized and unified management of all intelligent checkpoints and associated regulatory nodes within a designated area, thus solving the pain points of difficult resource scheduling and inconsistent management standards. Through a closed-loop link of registration-status awareness-full lifecycle management, the operating status of each regulatory node is monitored in real time. Combined with load balancing and collaborative fault handling mechanisms, the efficiency of regulatory resource utilization and overall system stability are improved, adapting to the large-scale needs of expanding the number and scope of regulatory nodes within the area. Based on identification codes, unique identifiers are established for all controlled objects, including regulatory nodes, regulatory node equipment, and objects to be tracked, forming an association mapping between identification codes and attribute information, solving the problems of identity confusion and traceability difficulties for multi-source controlled objects. By encapsulating real-time data into standardized messages in a preset format, the data collection and transmission formats are unified. Combined with multi-source heterogeneous feature extraction from edge computing nodes, scattered information on transport equipment, cargo, and attribute information related to controlled objects are integrated into a structured dataset, achieving efficient data exchange and accurate comparison across nodes and systems, providing data support for control decisions. By integrating the identity features, operational status features, and spatiotemporal correlation features of the controlled objects into a unified dataset, and comparing them with a pre-set anomaly judgment model and a benchmark threshold, the system can accurately identify scenarios such as equipment failure, cargo anomalies, and transportation violations, thus avoiding misjudgments and omissions caused by existing single-dimensional judgments.

[0066] Corresponding to the aforementioned smart checkpoint control method for border closure operations, this application also provides a smart checkpoint control device for border closure operations. Since the embodiments of the smart checkpoint control device for border closure operations in this application correspond to the embodiments of the aforementioned smart checkpoint control method for border closure operations, details not disclosed in the embodiments of the smart checkpoint control device for border closure operations can be referred to the embodiments of the aforementioned smart checkpoint control method for border closure operations, and will not be repeated here.

[0067] Figure 2 This is a schematic diagram of the structure of an intelligent checkpoint control device for customs clearance operations provided in an embodiment of this application.

[0068] like Figure 2 As shown, the intelligent checkpoint control device 200 for customs closure operations includes: The node management module 201 is used to establish a management system based on a distributed node cluster architecture for various regulatory nodes containing smart checkpoints within a specified area to complete the registration and status awareness of each regulatory node. Based on the status awareness and the associated information of the regulatory node's operating status, the module implements full lifecycle management of each regulatory node to form a full lifecycle management link for the regulatory node. The coding management module 202 is used to assign identification codes to each regulatory node and corresponding controlled object based on the equipment ledger information of the registered regulatory nodes in the full life cycle management link, and to establish an association mapping relationship between the identification codes and the attribute information of the corresponding controlled objects. The controlled objects include regulatory node equipment, associated terminal equipment and objects to be tracked. The data acquisition module 203 is used to collect real-time data from each smart checkpoint based on the association mapping relationship between the identification code and the corresponding controlled object attribute information. The real-time data includes information on the transport equipment, cargo information, and attribute information related to the controlled object. The message management module 204 is used to encapsulate real-time data into standardized messages in a preset format, and to extract multi-source heterogeneous features of the standardized messages based on the identifier anchoring of the edge computing nodes of the distributed node cluster architecture, thereby generating a fusion dataset containing the identity features, running status features and spatiotemporal correlation features of the controlled object. The operation and control module 205 is used to identify the abnormal state of the controlled object by comparing the baseline threshold of the attribute information of the controlled object with the fused feature dataset based on the preset abnormal judgment model, and to match the preset control strategy according to the abnormal state to execute intelligent checkpoint control.

[0069] The methods and apparatus provided in the embodiments of this application have been described above. To achieve the functions of the methods provided in the embodiments of this application, the methods and apparatus can be further refined using electronic devices.

[0070] Figure 3 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0071] like Figure 3As shown, the electronic device 300 includes a processor 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from memory 306 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processor 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0072] The following components are connected to I / O interface 305: memory 306 including hard disks, etc.; and communication section 307 including network interface cards such as LAN (Local Area Network) cards, modems, etc., which performs communication processing via a network such as the Internet; and driver 308 is also connected to I / O interface 305 as needed.

[0073] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 307. When the computer program is executed by processor 301, it performs the functions defined in the methods of this application.

[0074] In an exemplary embodiment, a storage medium including instructions is also provided, such as a memory including instructions, which can be executed by a processor 301 of an electronic device 300 to perform the above-described method. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0075] In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0076] In this embodiment of the disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods disclosed in the above embodiments.

[0077] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0078] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A smart checkpoint control method for customs closure operations, characterized in that, include: For various monitoring nodes containing smart checkpoints within a designated area, a management system is established based on a distributed node cluster architecture to complete the registration and status awareness of each monitoring node. Based on the monitoring node operation status association information obtained from the status awareness, full lifecycle management is implemented for each monitoring node to form a full lifecycle management link for the monitoring node. Based on the device ledger information of the registered regulatory nodes in the full lifecycle management link, an identification code is assigned to each regulatory node and the corresponding controlled object, and an association mapping relationship is established between the identification code and the attribute information of the corresponding controlled object, wherein the controlled object includes regulatory node devices, associated terminal devices and objects to be tracked; Based on the association mapping relationship between the identification code and the corresponding controlled object attribute information, real-time data of each smart checkpoint is collected, wherein the real-time data includes transportation equipment information, cargo information and attribute information related to the controlled object; The real-time data is encapsulated into standardized messages in a preset format, and the standardized messages are subjected to multi-source heterogeneous feature extraction based on identifier anchoring on edge computing nodes with a distributed node cluster architecture to generate a fusion dataset containing the identity features, running status features, and spatiotemporal correlation features of the managed objects. Based on a preset anomaly detection model, the baseline threshold of the attribute information of the controlled object is compared with the fused feature dataset to identify the abnormal state of the controlled object, and a preset control strategy is matched according to the abnormal state to execute intelligent checkpoint control.

2. The method according to claim 1, characterized in that, The management system established based on the distributed node cluster architecture includes: Build a distributed node cluster architecture that includes a main management node, edge sensing nodes, and communication relay nodes; Specifically, the main management node performs registration review and full lifecycle management decisions for the monitoring nodes; edge sensing nodes are deployed near each smart checkpoint to collect the operating status of the monitoring nodes; and the communication relay node is configured based on a preset encrypted transmission protocol to perform data interaction between the main management node and the edge sensing nodes.

3. The method according to claim 1, characterized in that, The registration of the regulatory node includes: If a new monitoring node containing a smart checkpoint is detected in a designated area, a registration request is triggered. The registration request carries basic information about the monitoring node, including node type, device model, installation location, and the control area to which it belongs. The registration request is verified based on a distributed node cluster architecture to obtain verification information that includes the integrity of basic information and whether the monitoring node meets the preset access standards. If the verification information indicates that the verification is successful, the monitoring node is registered and archived. If the verification information indicates that the verification failed, a verification failure message will be returned along with supplementary correction suggestions.

4. The method according to claim 1, characterized in that, The status perception adopts a combination of periodic perception and trigger-based perception. Periodic control is executed based on a preset cycle; trigger-based perception is executed when the monitoring node is detected to start, restart, or generate a fault alarm. The perception content includes the device operating parameters, network connection status, data transmission rate, and load status of the smart checkpoint.

5. The method according to claim 1, characterized in that, The process of assigning identification codes to each regulatory node and its corresponding controlled object includes: The identification code is designed using a hierarchical coding structure, which includes a region coding segment, a node type coding segment, a device number segment, and a first check code segment. Specifically, the administrative region information of the smart checkpoint is mapped to the region code segment, the device type information of the regulatory node is mapped to the node type code segment, a device number is assigned to each regulatory node and the controlled object as the device number segment, and the verification result generated based on the region code segment, the node type code segment and the device number segment is used as the first verification code segment.

6. The method according to claim 1, characterized in that, The process of establishing the association mapping relationship between the identifier and the corresponding attribute information of the controlled object includes: The static and dynamic attributes of the objects to be monitored are collected and classified. The static attributes include equipment name, equipment model, equipment rated parameters, size and material of the object to be tracked, and the dynamic attributes include equipment operating parameters, moving speed of the object to be tracked, location information of the object to be tracked, and interaction data between the equipment and the object to be tracked. The equipment includes monitoring node equipment and associated terminal equipment. Establish an association mapping relationship between the identifier code and the static attribute and the dynamic attribute.

7. The method according to claim 5, characterized in that, The process involves encapsulating the real-time data into standardized messages of a preset format, and then performing multi-source heterogeneous feature extraction based on identifier code anchoring on the standardized messages using edge computing nodes with a distributed node cluster architecture. This generates a fused dataset containing the identity features, operational status features, and spatiotemporal correlation features of the managed object, including: The preset format includes a message header, an identifier field, a data type field, a data length field, a data field, and a second verification field; The standardized message is transmitted to the edge computing node of the distributed node cluster architecture, and the edge computing node classifies and aggregates the standardized message from different sources based on the identification code field; Multi-source heterogeneous feature extraction is performed on the standardized messages after classification and aggregation to generate a fusion dataset containing the identity features, operating status features, and spatiotemporal correlation features of the controlled objects.

8. The method according to claim 7, characterized in that, After generating the fused dataset containing the identity features, operational status features, and spatiotemporal correlation features of the controlled objects, the process also includes: Obtain the summary information of the fused dataset and record the generation time of the fused dataset; The corresponding identifier, the summary information, and the generation time are associated, the associated information is encrypted using blockchain-level encryption, and the encryption result is written into a blockchain block.

9. The method according to claim 1, characterized in that, The method based on a preset anomaly detection model compares the baseline threshold of the controlled object's attribute information with the fused feature dataset to identify the abnormal state of the controlled object, including: The anomaly detection model is obtained by training multiple sets of data through machine learning. The multiple sets of data include a first type of data and a second type of data. Each set of data in the first type of data includes the historical normal state of the controlled object and a first label corresponding to the historical normal state. Each set of data in the second type of data includes the historical abnormal state of the controlled object and a second label corresponding to the historical abnormal state. The baseline thresholds for the attribute information of the controlled objects are determined based on the application scenarios, industry standards, and actual control needs of the controlled objects. The fused feature dataset is input into the anomaly detection model, the baseline threshold is compared with the fused feature dataset, and the anomaly status identification result of the controlled object is output.

10. The method according to claim 1, characterized in that, The step of matching a preset control strategy based on the abnormal state to execute intelligent checkpoint management includes: Based on the severity of the abnormal state, the abnormal state is divided into minor abnormality, general abnormality and severe abnormality; For different levels of abnormal states, corresponding preset control strategies are matched. Among them, minor abnormalities correspond to early warning prompts, general abnormalities correspond to access restrictions, and severe abnormalities correspond to forced shutdown and alarm linkage. Intelligent checkpoint management is implemented based on the control strategy matched to the abnormal state.

Images