Intelligent Processing Method and System for Cross-border Trade Data Based on Smart Port

Abstract

The present application relates to the technical field of data processing, and discloses an intelligent processing method and system for cross-border trade data based on a smart port. The method includes: performing hierarchical processing on the functional model of cross-border trade business data to obtain a functional module call relationship network, and performing process template construction processing to obtain a dynamic process assembly rule library, and performing service buried point processing to obtain a user behavior analysis data set, and performing guidance strategy construction processing to obtain a service guidance rule library, and performing knowledge graph construction processing to obtain a business knowledge inference rule set, and performing cross-border trade data processing to obtain an intelligent decision-making plan for port business. The present application realizes the intelligent processing of cross-border trade data, constructs a complete technical chain from data collection, behavior analysis to decision support, provides accurate business guidance and intelligent decision support, and solves the problems of low business processing efficiency, inaccurate service guidance, weak decision support ability, etc. existing in the prior art.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular, to an intelligent processing method and system for cross-border trade data based on a smart port. Background Art

[0002] With the rapid development of cross-border trade business, the traditional port business processing method has been difficult to meet the modern trade needs. The current cross-border trade platforms mainly adopt fixed business process templates, conduct business approval and processing manually, and arrange customs clearance links and logistics paths relying on experience. In terms of data processing, the existing technologies mainly conduct simple data collection and analysis through preset rules, lacking in-depth understanding of user behaviors and business processes. In terms of service guidance, most adopt unified operation guides and fixed exception handling solutions, and are unable to provide personalized service support according to the characteristics of different enterprises.

[0003] However, the existing technologies have the following deficiencies: First, there is a lack of intelligent data analysis and decision support in the business processing process, resulting in low customs clearance efficiency and high logistics costs; Second, due to the lack of in-depth analysis and understanding of user behaviors, it is impossible to accurately identify key nodes and potential risks in the business handling process, affecting service quality; Third, the existing service guidance methods are too mechanical and unified, and are unable to provide accurate business guidance according to the specific situation of enterprises; Finally, information is isolated among various business links, the data value has not been fully explored and utilized, and it is difficult to form a complete knowledge system to support business decisions. Summary of the Invention

[0004] This application provides an intelligent processing method and system for cross-border trade data based on a smart port, which is used to realize the intelligent processing of cross-border trade data, construct a complete technical chain from data collection, behavior analysis to decision support, provide accurate business guidance and intelligent decision support, and solve the problems of low business processing efficiency, inaccurate service guidance, weak decision support ability, etc. existing in the prior art.

[0005] First aspect, the present application provides an intelligent processing method for cross-border trade data based on a smart port. The intelligent processing method for cross-border trade data based on a smart port includes: performing hierarchical processing on the functional model of cross-border trade business data to obtain a functional module call relationship network; the hierarchical processing of the functional model includes dividing the business data into an enterprise entity function layer and a business function layer, and constructing a data interaction interface between functional modules; performing process template construction processing on the functional module call relationship network to obtain a dynamic process assembly rule library; the process template construction processing includes designing a business declaration process and an exception handling process system based on the function call relationship; performing service buried point processing on the dynamic process assembly rule library to obtain a user behavior analysis data set; the service buried point processing includes setting buried point positions at key process nodes, collecting user operation behavior data, business data change data, and process execution status data; performing guidance strategy construction processing on the user behavior analysis data set to obtain a service guidance rule library; the guidance strategy construction processing includes designing operation prompts, formulating exception handling suggestions, and personalized guidance plans based on the user behavior pattern; performing knowledge graph construction processing on the service guidance rule library through a knowledge extraction algorithm to obtain a business knowledge reasoning rule set; the knowledge graph construction processing includes extracting business entities, constructing a relationship network, discovering knowledge rules, and establishing a causal relationship chain; performing cross-border trade data processing on the business knowledge reasoning rule set to obtain an intelligent decision-making plan for port operations; the cross-border trade data processing includes optimizing the customs clearance process, planning the logistics path, evaluating the risk level, and predicting the customs clearance time.

[0006] Second aspect, the present application provides an intelligent processing system for cross-border trade data based on a smart port. The intelligent processing system for cross-border trade data based on a smart port includes:

[0007] A functional module, configured to perform hierarchical processing on the functional model of cross-border trade business data to obtain a functional module call relationship network; the hierarchical processing of the functional model includes dividing the business data into an enterprise entity function layer and a business function layer, and constructing a data interaction interface between functional modules;

[0008] A process module, configured to perform process template construction processing on the functional module call relationship network to obtain a dynamic process assembly rule library; the process template construction processing includes designing a business declaration process and an exception handling process system based on the function call relationship;

[0009] A service buried point module, configured to perform service buried point processing on the dynamic process assembly rule library to obtain a user behavior analysis data set; the service buried point processing includes setting buried point positions at key process nodes, collecting user operation behavior data, business data change data, and process execution status data;

[0010] A service guidance module, which is used to perform guidance strategy construction processing on the user behavior analysis data set to obtain a service guidance rule library; the guidance strategy construction processing includes designing operation prompts, formulating exception handling suggestions, and personalized guidance plans based on user behavior patterns;

[0011] A knowledge graph module, which is used to perform knowledge graph construction processing on the service guidance rule library through a knowledge extraction algorithm to obtain a business knowledge inference rule set; the knowledge graph construction processing includes extracting business entities, constructing a relationship network, discovering knowledge rules, and establishing a causal relationship chain;

[0012] A decision-making module, which is used to perform cross-border trade data processing on the business knowledge inference rule set to obtain an intelligent decision-making plan for port business; the cross-border trade data processing includes optimizing the customs clearance process, planning the logistics path, evaluating the risk level, and predicting the customs clearance time limit.

[0013] In the technical solution provided by this application, through hierarchical processing of the function model of cross-border trade business data, the business data is divided into an enterprise main body function layer and a business function layer, and a data interaction interface between function modules is constructed, realizing modular management and flexible configuration of business functions; through constructing a process template for the function module call relationship network, designing a business declaration process and an exception handling process system, and establishing a complete dynamic process assembly rule library, the standardization and automation level of the business process are improved; through performing service buried point processing on the dynamic process assembly rule library, setting buried point positions at key process nodes, collecting user operation behavior data, business data change data, and process execution status data, realizing comprehensive monitoring and analysis of the business execution process; through performing guidance strategy construction processing on the user behavior analysis data set, designing operation prompts, formulating exception handling suggestions, and personalized guidance plans, improving the accuracy and efficiency of user operations; through performing knowledge graph construction processing on the service guidance rule library through a knowledge extraction algorithm, extracting business entities, constructing a relationship network, discovering knowledge rules, and establishing a causal relationship chain, forming a complete business knowledge system; through performing cross-border trade data processing on the business knowledge inference rule set through a cross-border trade intelligent analysis algorithm, completing customs clearance process optimization, logistics path planning, risk level evaluation, and customs clearance time limit prediction, realizing intelligent decision-making for port business. Through multi-level data processing and analysis, a complete technical chain from data collection, process monitoring to intelligent decision-making is constructed, significantly improving the processing efficiency and service quality of cross-border trade business, and reducing business risks. Brief Description of the Drawings

[0014] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0015] Figure 1 FIG. is a schematic diagram of an embodiment of the intelligent processing method for cross-border trade data based on a smart port in an embodiment of the present application;

[0016] Figure 2 FIG. is a schematic diagram of an embodiment of the intelligent processing system for cross-border trade data based on a smart port in an embodiment of the present application. Detailed implementation manners

[0017] The embodiments of the present application provide an intelligent processing method and system for cross-border trade data based on a smart port. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "comprising" or "having" and any deformation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0018] For ease of understanding, the following describes the specific process of the embodiments of the present application. Please refer to Figure 1 , an embodiment of the intelligent processing method for cross-border trade data based on a smart port in an embodiment of the present application includes:

[0019] Step S101: Perform hierarchical processing on the functional model of cross-border trade business data to obtain a functional module call relationship network; the hierarchical processing of the functional model includes dividing the business data into an enterprise entity function layer and a business function layer, and constructing a data interaction interface between functional modules;

[0020] Step S102: Perform process template construction processing on the functional module call relationship network to obtain a dynamic process assembly rule library; the process template construction processing includes designing a business declaration process and an exception handling process system based on the function call relationship;

[0021] Step S103: Perform service instrumentation on the dynamic process assembly rule library to obtain a user behavior analysis data set; the service instrumentation includes setting instrumentation positions at key process nodes, collecting user operation behavior data, business data change data, and process execution status data;

[0022] Step S104: Perform guidance strategy construction on the user behavior analysis data set to obtain a service guidance rule library; the guidance strategy construction includes designing operation prompts, formulating exception handling suggestions, and personalized guidance plans based on user behavior patterns;

[0023] Step S105: Perform knowledge graph construction on the service guidance rule library through a knowledge extraction algorithm to obtain a business knowledge inference rule set; the knowledge graph construction includes extracting business entities, constructing a relationship network, discovering knowledge rules, and establishing a causal relationship chain;

[0024] Step S106: Perform cross-border trade data processing on the business knowledge inference rule set to obtain a port business intelligent decision-making solution; the cross-border trade data processing includes customs clearance process optimization, logistics path planning, risk level assessment, and customs clearance time prediction.

[0025] It can be understood that the execution subject of this application can be a cross-border trade data intelligent processing system based on a smart port, or a terminal or a server. Specifically, it is not limited here. This application embodiment is described by taking the server as the execution subject as an example.

[0026] Specifically, perform functional model layering processing on cross-border trade business data. By analyzing and classifying data such as enterprise basic information, qualification certificates, and business declarations, the data is divided into an enterprise main function layer and a business function layer. The enterprise main function layer includes functions such as enterprise basic information management, qualification management, and authorization management. The business function layer includes functions such as customs clearance service, inspection service, manifest service, transit customs service, and logistics service. By designing interface rules and data exchange formats, establish data interaction interfaces between functional modules to achieve data sharing and business collaboration between different functional modules. For example, the basic information of an import and export enterprise includes data such as enterprise registration information, business scope, and credit rating. These data are sorted and stored in the enterprise main function layer after classification; the business data such as the enterprise's bill of lading, packing list, and bill of lading are stored in the business function layer. When constructing a process template for the functional module call relationship network, design corresponding business declaration processes and exception handling process systems according to the characteristics and requirements of different business types. Taking the goods customs clearance business as an example, the declaration process includes links such as filling out the bill of lading, submitting documents, and paying taxes; the exception handling process includes links such as supplementing documents, modifying declarations, and applying for reconsideration. These processes are flexibly configured through dynamic assembly rules to form a complete business processing chain.

[0027] In the service data tracking and processing stage, data on user operation behaviors, changes in business data, and process execution statuses are collected by setting data tracking points at key nodes in the business process. For example, data tracking points are set in the customs declaration form filling stage to record data such as the time when the user fills in each field, the number of modifications, and the error rate; data tracking points are set in the document review stage to record data such as the review time consumption, reasons for document rejection, and modified content; data tracking points are set in the inspection stage to record data such as the inspection method, inspection results, and abnormal situations. After being sorted out and analyzed, these data form a user behavior analysis data set. Based on the user behavior analysis data set, a guidance strategy construction process is carried out. By analyzing the user's operation habits and business handling characteristics, targeted operation prompts, exception handling suggestions, and personalized guidance plans are designed. For example, for users who are handling business for the first time, detailed form filling guidance and explanations of document requirements are provided; for users who often make specific errors, targeted error warnings and modification suggestions are provided; for users with specific business characteristics, the most suitable business handling paths and processing methods are recommended.

[0028] Through a knowledge extraction algorithm, a knowledge graph construction process is carried out on the service guidance rule library to extract business entities, construct a relationship network, discover knowledge rules, and establish a causal relationship chain. Taking goods declaration as an example, business entities include enterprises, commodities, means of transportation, etc.; the relationship network includes the trade relationship between enterprises and commodities, the loading relationship between commodities and means of transportation, etc.; knowledge rules include declaration requirements, inspection standards, tax rate regulations, etc. for various commodities; the causal relationship chain includes logical relationships such as document errors leading to document rejection and commodity attributes affecting the inspection method. These knowledge are organized and applied in the form of inference rules. Finally, cross-border trade data processing is carried out on the business knowledge inference rule set for customs clearance process optimization, logistics path planning, risk level assessment, and customs clearance time prediction. For example, during the customs clearance process of a container of goods, by analyzing historical data and the current status, it is identified that the declaration stage and the inspection stage are the main time bottlenecks, and accordingly the customs clearance process is optimized, the inspection batches are adjusted, and the operation time is reasonably arranged; by analyzing data such as ports, warehouses, and transportation routes, the optimal logistics path is planned to reduce transportation costs; by analyzing factors such as enterprise credit, commodity attributes, and document quality, the business risk level is assessed to determine the inspection intensity; by analyzing data such as the time consumption of each link, personnel allocation, and equipment status, the overall customs clearance time is predicted, and corresponding arrangements are made in advance.

[0029] It should be noted that the cross-border trade data intelligent processing system based on the intelligent port in this application can also be an intelligent enterprise service engine. It comprehensively sorts out the functions of various platform business applications by using artificial intelligence technology, learns cross-border trade business knowledge in multiple aspects such as customs, border control, transportation, aviation, and railway, reshapes the platform business handling process, and embeds services into various business handling links of the platform by using service buried point technology. It provides users of the platform with full business cycle services such as intelligent business judgment, process recommendation, and business handling guidance, helping users efficiently manage the cross-border trade customs declaration business process. By monitoring the dynamics of users' business handling in real time and using data visualization tools to mine users' potential needs and behavior patterns, it helps the platform continuously optimize the user experience. It aggregates the basic information, trade information, customs clearance information, and logistics information of enterprises with enterprises as the unit, provides data services such as customized collection, enterprise statistics query, industry trend, logistics status query, risk reminder, and preferential subsidy query for enterprises, and automatically and intelligently provides a variety of data services based on the real foreign trade data aggregated by the platform in accordance with the principles of "enterprise independent authorization, real foreign trade data, and single window authentication", building an enterprise service system that integrates data integrity verification, authorized data supplementation, data collaborative confirmation, and data service use, assisting the development of enterprises' foreign trade business, supporting direct connection of enterprise systems, improving system interoperability, and meeting the personalized and diverse needs of enterprises.

[0030] For example: An import and export enterprise declares a batch of medical devices. First, it conducts hierarchical processing on data such as the enterprise's qualification certificate, business scope, and commodity attributes to confirm that the enterprise has the qualification for importing medical devices and the commodity belongs to a special supervision category. According to these characteristics, it dynamically assembles corresponding business processes, including special commodity declaration processes, quality and safety approval processes, and special inspection processes. During the business handling process, through buried points, it is collected that users frequently make mistakes when filling in the medical device registration number, and the description of the relevant commodity specifications and models is inaccurate. Based on this, targeted filling guidance and error reminders are generated. Based on the regulatory rules and risk characteristics related to medical devices in the knowledge graph, it is evaluated that the risk level of this batch of goods is medium, and inspection is required. The predicted customs clearance time limit is 3 working days, and the optimal inspection time and goods transportation route are planned accordingly.

[0031] In the embodiments of the present application, through hierarchical processing of the functional model of cross-border trade business data, the business data is divided into the enterprise entity function layer and the business function layer, and a data interaction interface between functional modules is constructed to achieve modular management and flexible configuration of business functions; through the process template construction processing of the functional module call relationship network, the business declaration process and the exception handling process system are designed, and a complete dynamic process assembly rule library is established to improve the standardization and automation level of the business process; through the service buried point processing of the dynamic process assembly rule library, the buried point positions are set at key process nodes to collect user operation behavior data, business data change data, and process execution status data, achieving comprehensive monitoring and analysis of the business execution process; through the guiding strategy construction processing of the user behavior analysis data set, operation prompts are designed, exception handling suggestions and personalized guiding schemes are formulated to improve the accuracy and efficiency of user operations; through the knowledge extraction algorithm, the knowledge graph construction processing of the service guiding rule library is carried out, business entities are extracted, relationship networks are constructed, knowledge rules are discovered, and causal chains are established to form a complete business knowledge system; through the cross-border trade intelligent analysis algorithm, cross-border trade data processing of the business knowledge inference rule set is carried out to complete the optimization of the customs clearance process, the logistics path planning, the risk level assessment, and the customs clearance time prediction, achieving intelligent decision-making for port operations. Through multi-level data processing and analysis, a complete technical chain from data collection, process monitoring to intelligent decision-making is constructed, significantly improving the processing efficiency and service quality of cross-border trade business, and reducing business risks.

[0032] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0033] (1) Perform enterprise entity classification processing on the cross-border trade business data to obtain an enterprise basic information set, and perform enterprise entity function layer construction processing on the enterprise basic information set to obtain the enterprise entity function layer;

[0034] (2) Perform filing qualification processing on the enterprise entity function layer to obtain an enterprise qualification certificate set, and perform authorization processing on the enterprise qualification certificate set to obtain an enterprise function authorization form;

[0035] (3) Perform business function classification processing on the cross-border trade business data to obtain a business function element set, and perform business function layer construction processing on the business function element set to obtain the business function layer;

[0036] (4) Perform customs clearance service function configuration processing on the business function layer to obtain a customs clearance business process set, and perform inspection, manifest, transit, and logistics service function configuration processing on the customs clearance business process set to obtain a business service function set;

[0037] (5) Design and process the data interaction interfaces for the enterprise's main functional layer and business functional layer to obtain a functional interaction interface table, and then configure the interface rules for the functional interaction interface table to obtain the data interaction interfaces.

[0038] (6) Construct the call relationship of the data interaction interfaces through module association analysis to obtain the functional module call relationship network.

[0039] Specifically, clean and standardize the original data, including basic data such as enterprise registration information, organization code, legal person information, business scope, and registered capital. Through data standardization processing, convert data in different formats into a standard format. For the enterprise name, perform string standardization processing to convert full-width characters into half-width characters, and remove redundant spaces and special characters; for the registered capital amount, uniformly convert it to the unit of ten thousand yuan; for date-type data, uniformly convert it to the "YYYY-MM-DD" format. After data cleaning and standardization processing, obtain the enterprise basic information set. Subsequently, perform the construction process of the enterprise's main functional layer on the enterprise basic information set, mainly including information classification and sorting, functional permission configuration, and data association processing. Information classification and sorting classify the enterprise basic information according to different dimensions, such as basic information category, qualification information category, credit information category, etc.; functional permission configuration sets corresponding access and operation permissions for different types of information; data association processing establishes the association relationships between various types of enterprise information to form a complete enterprise main functional layer.

[0040] When conducting the record-filing qualification process for the enterprise's main functional layer, first extract the information of various enterprise qualification certificates, including the right to operate import and export, customs registration certificate, food business license, etc. Validate the effectiveness, manage the timeliness, and classify and store these qualification certificates to generate the enterprise qualification certificate set. Then perform the authorization process on the enterprise qualification certificate set, set corresponding business operation permissions according to different qualification types, determine the business scope and operation permissions that the enterprise can handle on the platform, and generate the enterprise function authorization table. When classifying the cross-border trade business data by business function, mainly classify various business data according to function types, including customs declaration business data, commodity inspection business data, logistics business data, etc., extract the key elements and characteristic parameters of each business type to form the business function element set. Then perform the construction process of the business functional layer on the business function element set, establish the association relationships between business functions, set business processing rules and flow logics to form a complete business functional layer.

[0041] When performing customs clearance service function configuration processing on the business function layer, corresponding function modules are set according to the characteristics of customs clearance business, including functions such as customs declaration form entry, document review, inspection application, and tax calculation, and corresponding business processing rules and operation procedures are formulated to generate a customs clearance business process set. Then, customs inspection, manifest, transit, and logistics service function configuration processing are carried out on the customs clearance business process set, corresponding function modules and processing rules are configured for different types of business, and collaborative processing of various types of business is realized to form a business service function set. Based on the enterprise main function layer and the business function layer, data interaction interface design processing is carried out, data exchange rules and interface parameters between the two function layers are designed, data transmission formats and interaction methods are defined, and a function interaction interface table is generated. Interface rule configuration processing is carried out on the function interaction interface table, data access permissions, interface call rules, and data synchronization mechanisms are set to form a standardized data interaction interface.

[0042] Finally, through module association analysis, a call relationship construction process is carried out on the data interaction interface, the dependency relationship and call sequence between each function module are analyzed, a complete function call link is established, and a function module call relationship network is formed.

[0043] For example: When an import and export trading enterprise registers on the platform, it submits materials such as the enterprise business license, foreign trade operator record-filing form, and customs declaration unit registration certificate. First, these original data are standardized. The enterprise name "ABC Trading Co., Ltd." is standardized to "ABC Trading Co., Ltd.", and the registered capital "5 million yuan" is standardized to "500", etc. Then, the standardized data are classified and sorted. The business license information is classified into basic information category, and the foreign trade operator record-filing is classified into qualification information category. Based on the qualification certificates provided by the enterprise, corresponding business permissions are set, such as having general trade import and export permissions, customs declaration registration permissions, etc. Then, the goods data declared by the enterprise are functionally classified. The customs declaration form data, inspection and quarantine certificates, transportation documents, etc. are classified according to business types, and key elements such as commodity codes, place of origin, and packaging specifications are extracted. On this basis, customs clearance service functions are configured. For example, in the automatic verification function of customs declaration form data, matching rules for commodity codes and declared elements, tariff commodity classification rules, etc. are set. Through interface design, the association between enterprise main body information and business data is realized, such as the association rule between enterprise qualifications and declarable commodity types, the association rule between enterprise credit ratings and inspection and release methods, etc. Finally, a complete function call network is formed, enabling the enterprise to efficiently handle various cross-border trade businesses on the platform according to its own qualification permissions.

[0044] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0045] (1)Perform business declaration process analysis and processing on the function module call relationship network to obtain a set of declaration process elements, and perform business declaration process design and processing on the set of declaration process elements to obtain a business declaration process;

[0046] (2)Perform abnormal type identification and processing on the business declaration process to obtain a list of abnormal situations, and perform construction processing on the abnormal situation list to build an abnormal handling process system;

[0047] (3)Perform process rule integration processing on the business declaration process and the abnormal handling process system to obtain a process assembly specification table, and perform rule dynamic configuration processing on the process assembly specification table to obtain a candidate process set;

[0048] (4)Perform rule assembly processing on the candidate process set through process rule mapping to obtain a dynamic process assembly rule library.

[0049] Specifically, extract the core elements of business declaration, including goods information (commodity code, quantity, value), enterprise information (importer / exporter, consignor / consignee), transportation information (transportation mode, port of entry / exit), etc. Identify the dependency relationships between various elements through correlation analysis, such as the corresponding relationship between commodity codes and declaration elements, and the association relationship between transportation modes and declaration documents, so as to form a set of declaration process elements. When performing business declaration process design and processing on the set of declaration process elements, design the sequence of declaration links according to the logical relationship of the elements, such as filling in basic information first, then filling in commodity information, and finally completing the upload of attached documents, thus forming a complete business declaration process.

[0050] The abnormal type identification and processing of the business declaration process mainly analyze various abnormal situations that occur in historical data, such as incomplete documents, incorrect commodity classification, incorrect filling of declaration elements, etc., to form a list of abnormal situations. Then, perform construction processing on the abnormal situation list to build an abnormal handling process system, design corresponding handling processes for different types of abnormalities, such as document supplementation process, commodity reclassification process, declaration element modification process, etc., to build a complete abnormal handling process system.

[0051] After completing the above process design, perform process rule integration processing on the business declaration process and the abnormal handling process system, integrate the rules of each process, establish association rules between processes, and form a process assembly specification table. Perform rule dynamic configuration processing on the process assembly specification table, flexibly combine various process rules according to the requirements of different business scenarios, and generate a candidate process set. Finally, perform rule assembly processing on the candidate process set through process rule mapping, assemble each rule according to the business logic, and form a dynamically adjustable process assembly rule library.

[0052] For example: For a batch of medical devices that need to be imported, the elements that need to be filled in during the business declaration process include: special information such as the medical device registration certificate number, product specification model, inspection and quarantine code, etc., plus basic elements such as general enterprise information and cargo information. These elements form a declaration element set after correlation analysis. According to the special requirements for the import of medical devices, a dedicated declaration process is designed, which requires adding a submission link for special documents such as medical device registration certificates on the basis of regular declaration information.

[0053] In actual operation, when encountering the situation that the validity period of the medical device registration certificate is about to expire, an exception handling process will be triggered. Exception handling includes specific operation steps such as notifying the enterprise to update the registration certificate, suspending the declaration process, and setting automatic warnings. Through rule integration, these special requirements are integrated with the regular process to form a complete declaration processing process for the import of medical devices, and the processing rules can be dynamically adjusted according to different models of medical devices.

[0054] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0055] (1) Conduct key node analysis and processing on the dynamic process assembly rule library to obtain a business key node table, and perform buried point position setting processing on the business key node table to obtain a key node buried point distribution map;

[0056] (2) Conduct page access record collection processing on the key node buried point distribution map to obtain user operation behavior data, and perform operation trajectory annotation processing on the user operation behavior data to obtain an operation trajectory feature set;

[0057] (3) Conduct function usage data statistics processing on the operation trajectory feature set to obtain a node operation frequency table, and perform business data change monitoring processing on the node operation frequency table to obtain business data change data;

[0058] (4) Conduct process execution status collection processing on the business data change data to obtain process execution status data, and perform key node monitoring processing on the process execution status data to obtain a node status sequence table;

[0059] (5) Conduct exception point identification processing on the node status sequence table to obtain an exception event feature set, and perform process stuck warning analysis processing on the exception event feature set to obtain a process warning index table;

[0060] (6) Through the time series feature analysis algorithm, integrate and process the user operation behavior data, business data change data, and process execution status data to obtain a user behavior analysis data set.

[0061] Specifically, when conducting key node analysis and processing on the dynamic process assembly rule library, it is necessary to identify important operation points, state transition points, and data change points in the business process. Key nodes include declaration document submission nodes, document review nodes, inspection operation nodes, release approval nodes, etc. Each node is marked with attribute information such as node type, node function, previous node, and subsequent node, forming a business key node table. Perform data collection point setting processing on the business key node table, set data collection points at each key node, determine the data items to be collected, collection frequency, and data format, and generate a key node data collection distribution map. When collecting and processing page access records, record information such as the access time, stay duration, and click times of users at each business node. The user operation behavior data undergoes unified format conversion and data cleaning to remove invalid access records and abnormal data. Perform operation trajectory annotation processing on the user operation behavior data, record information such as the operation sequence, operation timing, and operation results of users between different nodes, forming an operation trajectory feature set.

[0062] Perform function usage data statistics processing on the operation trajectory feature set, and calculate indicators such as the access frequency, average processing duration, and operation success rate of each node. The node operation frequency table reflects the usage and efficiency status of each business node. Perform business data change monitoring processing on the node operation frequency table, track and record the change situations of business data at each node, including data addition, deletion, modification, query operations, data value changes, data state transitions, etc., and generate business data change data. In the process execution status collection and processing link, focus on collecting the task execution situations of each node, including information such as task start time, execution duration, and completion status, forming process execution status data. Perform key node monitoring processing on the process execution status data, analyze the execution efficiency, task backlog situation, abnormal interruption situation, etc. of each node, and generate a node status sequence table.

[0063] Perform abnormal point identification processing on the node status sequence table, identify nodes with abnormal execution through setting threshold rules, such as situations like execution timeouts, repeated executions, and data inconsistencies, and generate an abnormal event feature set. Perform process stuck warning analysis processing on the abnormal event feature set, set different levels of warning indicators according to the type, frequency, and impact degree of abnormal events, and form a process warning indicator table. Finally, perform integrated processing on the user operation behavior data, business data change data, and process execution status data through a time series feature analysis algorithm. The time series feature analysis algorithm processes data through the following steps: First, perform time series alignment to unify the timestamps of different data sources to the same time scale; then extract time series features, including trend features, periodic features, mutation features, etc.; finally, perform feature fusion to generate a complete user behavior analysis data set.

[0064] For example: In cross-border trade business, a food import enterprise completes the declaration of 10 batches of goods in one day. Through buried point collection, it is found that in the commodity code filling link, each batch is modified 3 times on average, the interval between each modification is 5 minutes, and the filling accuracy rate is 70%. Data change monitoring shows that the modification frequency of elements such as commodity specifications and weights is relatively high, mainly occurring within 30 minutes after the first filling. Node status monitoring finds that the average processing time in the food inspection and quarantine link is 4 hours, which is 1 time longer than the normal processing time (2 hours). The abnormal identification result shows that 3 batches out of the recent 10 batches of declarations of this enterprise have caused process interruptions due to incomplete document information and need to supplement and submit health certificates. Based on these data, targeted warning indicators are generated: a yellow warning is issued when the number of document filling modifications exceeds 5 times, and a red warning is issued when the food inspection duration exceeds 3 hours. These data and warning mechanisms help the enterprise identify potential risks in advance and optimize the business handling process.

[0065] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0066] (1) Perform behavior pattern feature extraction processing on the user behavior analysis data set to obtain a user behavior pattern feature table, and perform operation prompt rule generation processing on the user behavior pattern feature table to obtain an operation prompt rule set;

[0067] (2) Perform intelligent prompt configuration processing on the operation prompt rule set to obtain a filling guidance rule table, and perform error reminder rule configuration processing on the filling guidance rule table to obtain an error reminder scheme;

[0068] (3) Perform business suggestion generation processing on the error reminder scheme to obtain a business suggestion set, and perform abnormal handling suggestion compilation processing on the business suggestion set to obtain an abnormal handling suggestion;

[0069] (4) Perform optimal path analysis processing on the abnormal handling suggestion to obtain a process recommendation list, and perform operation step configuration processing on the process recommendation list to obtain an operation step prompt;

[0070] (5) Perform relevant business association analysis processing on the operation step prompt to obtain a personalized guidance scheme, and perform guidance rule aggregation processing on the personalized guidance scheme to obtain a guidance rule collection;

[0071] (6) Perform rule integration processing on the guidance rule collection through rule mapping processing to obtain a service guidance rule library.

[0072] Specifically, analyze the operation characteristics of users during the business handling process, including operation sequence characteristics, time characteristics, error characteristics, etc. The operation sequence characteristics reflect the operation habits of users in different business links. The time characteristics include the processing duration and waiting time of each link. The error characteristics record common error types and error frequencies. These characteristics form different behavior pattern categories through cluster analysis and are recorded in the user behavior pattern feature table. Perform operation prompt rule generation processing on the user behavior pattern feature table, design corresponding operation prompt strategies for different behavior patterns, such as adding detailed explanations to frequently error-prone links and providing quick operation guidelines for time-consuming links, and finally form an operation prompt rule set. In the intelligent prompt configuration link, convert the operation prompt rules into specific filling guidance rules, including field filling specifications, document submission requirements, data format descriptions, etc., and generate a filling guidance rule table. When configuring error reminder rules for the filling guidance rule table, set the judgment conditions and reminder methods for various errors, such as providing correct examples for incorrect commodity codes and displaying standard units for incorrect weight units, to form an error reminder plan.

[0073] Perform business suggestion generation processing on the error reminder plan. Based on the error types and business scenarios, provide specific solutions and improvement suggestions to form a business suggestion set. Then compile exception handling suggestions for the business suggestion set, provide handling steps and precautions for different abnormal situations, and generate exception handling suggestions. Conduct optimal path analysis according to the exception handling suggestions, find the operation path with the highest processing efficiency and the lowest error rate through historical data analysis, and generate a process recommendation list. Configure the operation steps for the process recommendation list, convert the recommended path into detailed operation guidelines, including specific operation requirements and precautions for each link, to form operation step prompts.

[0074] Conduct relevant business association analysis on the operation step prompts, consider the association requirements between different business types, such as the association requirements between import declaration and inspection and quarantine application, and generate personalized guidance plans for different enterprise characteristics. Perform guidance rule aggregation processing on the personalized guidance plans, classify and organize various guidance rules according to business types and scenarios, and form a guidance rule collection. Finally, through rule mapping processing, establish a corresponding relationship between the rules in the guidance rule collection and specific business scenarios to form a complete service guidance rule library.

[0075] For example: A certain import enterprise has recently been mainly engaged in the import business of cold-chain food. By analyzing the declaration data of this enterprise in the recent 3 months, it is found that: in the filling process, the correct rate of commodity codes is 85%, but the correct rate of filling in information related to cold-chain requirements (such as temperature control, storage conditions, etc.) is only 60%; in the document submission process, the completeness rate of submitting food safety-related certificates is 90%, but the completeness rate of submitting cold-chain monitoring records is only 75%. Based on these data, targeted operation prompt rules are constructed: on the commodity information filling page, add filling prompts for special requirements of cold-chain commodities; in the document uploading process, set a mandatory reminder for cold-chain monitoring records. When the user fills in the temperature control requirements, the intelligent prompt configures a standard format example: "Storage temperature: -18°C ± 2°C". If the user enters an incorrect format (such as directly entering "-18 degrees"), an error reminder and modification suggestions are immediately provided. When there is a lack of cold-chain monitoring records, the business suggestion automatically prompts the supplementary requirements and provides a standard template. For the complete cold-chain food declaration process, the optimal operation path is recommended: first complete the basic information declaration → fill in the special cold-chain requirements → submit the food safety certificate → upload the cold-chain monitoring records → submit the inspection application. In specific operations, personalized document requirements and operation guides are provided according to the categories of cold-chain food of the enterprise (such as seafood, dairy products, etc.). These rules are finally integrated into the service guidance rule library to form a complete guidance plan for the cold-chain food import business.

[0076] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0077] (1) Perform business entity extraction processing on the service guidance rule library through a knowledge extraction algorithm to obtain an entity feature set, and perform business entity attribute annotation processing on the entity feature set to obtain a business entity dictionary;

[0078] (2) Perform relationship network construction processing on the business entity dictionary to obtain an initial relationship graph, and perform calculation processing on the association strength between entities in the initial relationship graph to obtain a relationship network;

[0079] (3) Perform knowledge rule extraction processing on the relationship network to obtain a rule candidate set, and perform rule verification processing on the rule candidate set to obtain knowledge rules;

[0080] (4) Perform causal chain construction processing on the knowledge rules to obtain a causal relationship table, and perform causal strength evaluation processing on the causal relationship table to obtain a causal relationship chain;

[0081] (5) Perform inference rule generation processing on the knowledge rules and the causal relationship chain through a rule induction algorithm to obtain a basic inference rule set, and perform rule completeness inspection processing on the basic inference rule set to obtain a rule verification report;

[0082] (6) Perform rule supplementation processing on the rule verification report to obtain a business knowledge inference rule set.

[0083] Specifically, use named entity recognition technology to identify key entities in business texts, including enterprise entities (such as importers / exporters, consignors / consignees), commodity entities (such as commodity names, specifications and models), document entities (such as customs declarations, bills of lading), etc. Extract features of the identified entities, including basic attributes (such as entity names, codes), business attributes (such as business types, processing authorities), attribute value constraints (such as data formats, value ranges), etc., to form an entity feature set. Then perform business entity attribute annotation on the entity feature set, annotate each entity with its complete attribute information, establish the correspondence between attributes and values, and generate a business entity dictionary. When constructing a relationship network for the business entity dictionary, it is necessary to analyze various association relationships between entities, such as the transaction relationship between enterprises and commodities, the attribution relationship between commodities and documents, the derivative relationship between documents, etc. Establish an initial relationship graph through relationship extraction technology, and quantitatively evaluate the entity associations in the graph, calculating the association strength between entities. The calculation of association strength considers factors such as business frequency, data consistency, and temporal correlation, and uses the following formula:

[0084]

[0085] Where: represents the association strength between entity and , represents the business interaction frequency, represents the degree of data consistency, represents the degree of temporal correlation, , , are weight coefficients.

[0086] Extract knowledge rules from the constructed relationship network, identify business rules contained in the network, such as the filling rules of declaration elements, the temporal rules of document submission, the logical rules of data verification, etc., to form a rule candidate set. Verify the rule candidate set, check the correctness, integrity, and consistency of the rules, and filter out valid knowledge rules. The scoring for rule verification uses the following formula:

[0087]

[0088] Where: represents the verification score of rule r , represents the rule accuracy rate, represents the rule completeness, represents the rule consistency, , , They are the weights of various indicators.

[0089] Based on knowledge rules, construct causal chains, analyze the causal relationships in business scenarios, such as review rejections caused by missing documents, inspection methods affected by commodity attributes, etc., to form a causal relationship table. Evaluate the strength of each causal chain in the causal relationship table, calculate the causal impact degree, and establish a complete causal relationship chain. Integrate the knowledge rules and causal relationship chains through a rule induction algorithm to form a basic inference rule set, and conduct a completeness test on the rule set to generate a rule verification report. Finally, based on the results of the verification report, supplement and improve the rules as necessary to form the final business knowledge inference rule set.

[0090] For example: In the import business of hazardous chemicals, through entity extraction, the core entities identified include: hazardous chemicals (commodity entities), dangerous goods transport documents (document entities), hazardous goods warehousing enterprises (enterprise entities), etc. Each entity is marked with specific attributes. For example, hazardous chemicals are marked with attributes such as UN numbers, hazard levels, storage requirements, etc. In the construction of the relationship network, it is found that the association strength between hazardous chemicals and transport documents is 0.85 (calculated based on business frequency 0.9, data consistency 0.8, and time series correlation 0.85), indicating a high degree of correlation between the two. Through rule extraction, it is found that when the hazard level of dangerous goods is Class A, a special transport permit must be provided; transport documents must be submitted before commodity declaration; warehousing enterprises must have corresponding level qualifications, etc. These rules have passed the verification score (accuracy 0.95, integrity 0.9, consistency 0.85, with weights of 0.4, 0.3, and 0.3 respectively), and the final verification score is 0.903, which is confirmed as an effective rule. In causal analysis, a causal chain of "hazard level of dangerous goods → transport requirements → document type → declaration time series" is established, and finally a complete business knowledge inference rule set for the import business of hazardous chemicals is formed.

[0091] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0092] (1) Conduct a customs clearance business process analysis on the business knowledge inference rule set to obtain a set of process bottleneck points, and perform customs clearance process optimization processing on the set of process bottleneck points to obtain candidate customs clearance process solutions;

[0093] (2) Perform process node configuration processing on the candidate customs clearance process solutions to obtain a customs clearance business flow chart, and perform path deviation analysis processing on the customs clearance business flow chart to obtain the baseline customs clearance process path;

[0094] (3) Perform logistics resource configuration processing on the baseline customs clearance process path to obtain a logistics resource distribution map, and perform logistics path planning processing on the logistics resource distribution map to obtain a logistics path planning scheme;

[0095] (4) Conduct a transportation timeliness evaluation on the logistics path planning scheme to obtain a transportation timeliness evaluation form, and perform logistics node optimization on the transportation timeliness evaluation form to obtain a logistics distribution path map;

[0096] (5) Identify risk factors in the logistics distribution path map to obtain a risk factor list, and conduct a risk level assessment on the risk factor list to obtain a risk level assessment report;

[0097] (6) Extract customs clearance timeliness factors from the risk level assessment report to obtain a timeliness impact factor table, and conduct customs clearance timeliness prediction on the timeliness impact factor table to obtain a customs clearance timeliness prediction result;

[0098] (7) Integrate the customs clearance process benchmark path, the logistics distribution path map, and the customs clearance timeliness prediction result to obtain a set of decision candidate solutions, and conduct a solution feasibility assessment on the set of decision candidate solutions to obtain a solution assessment report;

[0099] (8) Conduct intelligent decision-making generation on the solution assessment report to obtain an intelligent decision-making solution for port operations.

[0100] Specifically, identify the key business nodes in the customs clearance process, including declaration, inspection, taxation, release, etc. Through timeliness analysis and resource occupancy analysis, find out the bottleneck points that cause customs clearance delays or inefficiencies. The determination of bottleneck points is based on indicators such as node processing duration, backlog quantity, resource utilization rate, etc., to form a set of process bottleneck points. Conduct customs clearance process optimization on the set of bottleneck points, design improvement plans for different types of bottlenecks, such as adjusting the processing order, optimizing resource allocation, simplifying the operation process, etc., to generate multiple customs clearance process candidate solutions. When configuring process nodes for the customs clearance process candidate solutions, allocate specific processing resources and operation rules to each business node to form a complete business flow route and generate a customs clearance business flow map. Conduct path deviation analysis on the customs clearance business flow map, compare the differences between the actual execution effects and the expected goals of different solutions, and select the path with the smallest deviation as the customs clearance process benchmark path.

[0101] Configure logistics resources according to the customs clearance process benchmark path, consider the distribution of various logistics resources, including transportation tools, warehousing facilities, loading and unloading equipment, etc., to generate a logistics resource distribution map. Conduct path planning on the logistics resource distribution map, comprehensively consider factors such as transportation distance, cost, timeliness, etc., design the optimal logistics distribution route, and form a logistics path planning scheme. Conduct transportation timeliness evaluation on the logistics path planning scheme, analyze the time-consuming situation and possible delay factors of each transportation link, and generate a transportation timeliness evaluation form. Optimize the logistics nodes based on the evaluation results, adjust the resource allocation and operation timing of key nodes, and obtain an optimized logistics distribution path map.

[0102] In terms of risk management, risk factors are identified on the logistics distribution route map, including cargo safety risk, transportation delay risk, customs clearance blockage risk, etc., to form a risk factor list. By analyzing the probability of risk occurrence and the degree of impact, the risk factors are graded and a risk grade assessment report is generated. Based on the risk grade assessment report, the key factors affecting customs clearance timeliness are extracted to form a timeliness influencing factor table, and the overall customs clearance timeliness is predicted through historical data analysis and trend prediction to obtain the customs clearance timeliness prediction result.

[0103] The customs clearance process benchmark path, logistics distribution path map and customs clearance time prediction results are integrated to form multiple decision candidate solutions. The feasibility of these solutions is evaluated, and the solution evaluation report is generated by considering factors such as implementation difficulty, resource investment, and expected results. Finally, the optimal solution is selected based on the evaluation report to form the final intelligent decision-making solution for port business.

[0104] For example, in the customs clearance business of cold chain aquatic products of an import enterprise, the process analysis found that the inspection link was the main bottleneck, with an average waiting time of 4 hours, which was much higher than other links. The optimization plan includes: adding dedicated inspection channels, adjusting the distribution of inspection time periods, and making appointments for inspection. Through node configuration and path analysis, the benchmark path of "appointment inspection + dedicated channel" was determined, reducing the inspection waiting time to less than 2 hours. In the logistics link, considering the temperature control requirements of aquatic products, the logistics path of "wharf-cold storage-inspection site-enterprise warehouse" was planned, and refrigerated transportation vehicles and temperature control equipment were configured. The timeliness assessment showed that the complete logistics distribution took 8 hours, including 2 hours for loading and unloading, 4 hours for transportation, and 2 hours for inspection. The risk identification results showed that the main risks included: temperature control interruption risk (high risk), transportation delay risk (medium risk), and inspection backlog risk (medium risk). The timeliness prediction showed that after considering various risk factors, 90% of the goods could be cleared within 24 hours. The final decision-making plan includes specific measures such as selecting an appointment inspection time, using designated cold storage, equipping spare transport vehicles, and setting up full-process temperature control monitoring. The overall feasibility score of the plan reached 85 points (out of 100 points), and it is expected that the total customs clearance time can be controlled within 20 hours.

[0105] The above describes the cross-border trade data intelligent processing method based on the smart port in the embodiment of the present application. The following describes the cross-border trade data intelligent processing system based on the smart port in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of the cross-border trade data intelligent processing system based on the smart port includes:

[0106] The functional module 201 is used to perform hierarchical processing on the cross-border trade business data to obtain a functional module call relationship network; the hierarchical processing of the functional model includes dividing the business data into an enterprise entity function layer and a business function layer, and constructing a data interaction interface between functional modules;

[0107] The process module 202 is used to perform process template construction processing on the functional module call relationship network to obtain a dynamic process assembly rule library; the process template construction processing includes designing a business declaration process and an exception handling process system based on the function call relationship;

[0108] The service logging module 203 is used to perform service logging processing on the dynamic process assembly rule library to obtain a user behavior analysis data set; the service logging processing includes setting logging positions at key process nodes, collecting user operation behavior data, business data change data, and process execution status data;

[0109] The service guidance module 204 is used to perform guidance strategy construction processing on the user behavior analysis data set to obtain a service guidance rule library; the guidance strategy construction processing includes designing operation prompts, formulating exception handling suggestions, and personalized guidance plans based on the user behavior pattern;

[0110] The knowledge graph module 205 is used to perform knowledge graph construction processing on the service guidance rule library through a knowledge extraction algorithm to obtain a business knowledge inference rule set; the knowledge graph construction processing includes extracting business entities, constructing a relationship network, discovering knowledge rules, and establishing a causal relationship chain;

[0111] The decision-making module 206 is used to perform cross-border trade data processing on the business knowledge inference rule set to obtain an intelligent decision-making plan for port business; the cross-border trade data processing includes customs clearance process optimization, logistics path planning, risk level assessment, and customs clearance time prediction.

[0112] Through the collaborative cooperation of the above-mentioned various components, by performing hierarchical processing on the functional model of cross-border trade business data, the business data is divided into the enterprise entity function layer and the business function layer, and a data interaction interface between functional modules is constructed, realizing the modular management and flexible configuration of business functions; by performing process template construction processing on the call relationship network of functional modules, designing business declaration processes and exception handling process systems, and establishing a complete dynamic process assembly rule library, the standardization and automation levels of business processes are improved; by performing service buried point processing on the dynamic process assembly rule library, setting buried point positions at key process nodes, collecting user operation behavior data, business data change data, and process execution status data, realizing the comprehensive monitoring and analysis of the business execution process; by performing guidance strategy construction processing on the user behavior analysis data set, designing operation prompts, formulating exception handling suggestions, and personalized guidance plans, improving the accuracy and efficiency of user operations; by performing knowledge graph construction processing on the service guidance rule library through knowledge extraction algorithms, extracting business entities, constructing relationship networks, discovering knowledge rules, and establishing causal chains, forming a complete business knowledge system; by performing cross-border trade data processing on the business knowledge inference rule set through cross-border trade intelligent analysis algorithms, completing customs clearance process optimization, logistics path planning, risk level assessment, and customs clearance time prediction, realizing intelligent decision-making for port business. Through multi-level data processing and analysis, a complete technical chain from data collection, process monitoring to intelligent decision-making is constructed, significantly improving the processing efficiency and service quality of cross-border trade business, and reducing business risks.

[0113] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligent processing of cross-border trade data based on smart ports, characterized in that: The cross-border trade data intelligent processing method based on the smart port includes: Performing functional model hierarchical processing on cross-border trade business data to obtain a functional module call relationship network; the functional model hierarchical processing includes dividing the business data into an enterprise main function layer and a business function layer, and constructing a data interaction interface between the functional modules; Performing process template construction processing on the function module call relationship network to obtain a dynamic process assembly rule base; the process template construction processing includes designing a business declaration process and an exception handling process system based on the function call relationship; Performing service tracking processing on the dynamic process assembly rule library to obtain a user behavior analysis data set; the service tracking processing includes setting tracking locations at key process nodes to collect user operation behavior data, business data change data and process execution status data; Performing guidance strategy construction processing on the user behavior analysis data set to obtain a service guidance rule base; the guidance strategy construction processing includes designing operation prompts based on user behavior patterns, formulating exception handling suggestions and personalized guidance plans; The service guidance rule base is subjected to a knowledge graph construction process by a knowledge extraction algorithm to obtain a business knowledge reasoning rule set; the knowledge graph construction process includes extracting business entities, constructing a relationship network, discovering knowledge rules, and establishing a causal relationship chain; The business knowledge reasoning rule set is subjected to cross-border trade data processing to obtain an intelligent decision-making plan for port business; the cross-border trade data processing includes customs clearance process optimization, logistics route planning, risk level assessment and customs clearance time prediction.

2. According to claim 1, the intelligent processing method for cross-border trade data based on smart ports is characterized in that: The cross-border trade business data is subjected to hierarchical processing of the functional model to obtain a functional module calling relationship network; The functional model layered processing includes dividing the business data into the enterprise main function layer and the business function layer, and constructing the data interaction interface between the functional modules, including: Performing enterprise subject classification processing on the cross-border trade business data to obtain an enterprise basic information set, and performing enterprise subject function layer construction processing on the enterprise basic information set to obtain an enterprise subject function layer; Performing filing qualification processing on the enterprise main function layer to obtain an enterprise qualification certificate set, and performing authorization processing on the enterprise qualification certificate set to obtain an enterprise function authorization table; Performing business function classification processing on the cross-border trade business data to obtain a business function element set, and performing business function layer construction processing on the business function element set to obtain a business function layer; Performing customs clearance service function configuration processing on the business function layer to obtain a customs clearance business process set, and performing inspection declaration, manifest, transit and logistics service function configuration processing on the customs clearance business process set to obtain a business service function set; Performing data interaction interface design processing on the enterprise main function layer and the business function layer to obtain a function interaction interface table, and performing interface rule configuration processing on the function interaction interface table to obtain a data interaction interface; The data interaction interface is processed by performing call relationship construction through module association analysis to obtain a function module call relationship network.

3. The cross-border trade data intelligent processing method based on smart ports according to claim 1 is characterized in that: The process template construction process is performed on the function module call relationship network to obtain a dynamic process assembly rule library; The process template construction process includes designing a business declaration process and an exception handling process system based on a function call relationship, including: Performing business declaration process analysis on the function module call relationship network to obtain a declaration process element set, and performing business declaration process design on the declaration process element set to obtain a business declaration process; Performing an abnormal type identification process on the business declaration process to obtain an abnormal situation list, and constructing an abnormality handling process system on the abnormal situation list to obtain an abnormality handling process system; Performing process rule integration processing on the business declaration process and exception handling process system to obtain a process assembly specification table, and performing rule dynamic configuration processing on the process assembly specification table to obtain a candidate process set; The candidate process set is subjected to rule assembly processing through process rule mapping to obtain a dynamic process assembly rule base.

4. The cross-border trade data intelligent processing method based on smart ports according to claim 1 is characterized in that: The dynamic process assembly rule base is subjected to service tracking processing to obtain a user behavior analysis data set; the service tracking processing includes setting tracking locations at key process nodes, collecting user operation behavior data, business data change data and process execution status data, including: Performing key node analysis processing on the dynamic process assembly rule base to obtain a business key node table, and performing point location setting processing on the business key node table to obtain a key node point distribution map; Performing page access record collection and processing on the key node buried point distribution map to obtain user operation behavior data, and performing operation trajectory annotation processing on the user operation behavior data to obtain an operation trajectory feature set; Performing function usage data statistical processing on the operation trajectory feature set to obtain a node operation frequency table, and performing business data change monitoring processing on the node operation frequency table to obtain business data change data; Performing process execution status collection processing on the business data change data to obtain process execution status data, and performing key node monitoring processing on the process execution status data to obtain a node status sequence table; Performing abnormal point identification processing on the node state sequence table to obtain an abnormal event feature set, and performing process jam warning analysis processing on the abnormal event feature set to obtain a process warning indicator table; The user operation behavior data, business data change data and process execution status data are integrated and processed through a time series feature analysis algorithm to obtain a user behavior analysis data set.

5. The cross-border trade data intelligent processing method based on smart ports according to claim 1 is characterized in that: The user behavior analysis data set is processed for guiding strategy construction to obtain a service guiding rule base; The guidance strategy construction process includes designing operation prompts based on user behavior patterns, formulating exception handling suggestions and personalized guidance plans, including: Performing behavior pattern feature extraction processing on the user behavior analysis data set to obtain a user behavior pattern feature table, and performing operation prompt rule generation processing on the user behavior pattern feature table to obtain an operation prompt rule set; Performing intelligent prompt configuration processing on the operation prompt rule set to obtain a reporting guidance rule table, and performing error reminder rule configuration processing on the reporting guidance rule table to obtain an error reminder solution; Performing a business suggestion generation process on the error reminder scheme to obtain a business suggestion set, and performing an exception handling suggestion compilation process on the business suggestion set to obtain an exception handling suggestion; Performing optimal path analysis on the exception handling suggestion to obtain a process recommendation list, and performing operation step configuration on the process recommendation list to obtain operation step prompts; Performing relevant business association analysis on the operation step prompt to obtain a personalized guidance plan, and performing guidance rule aggregation processing on the personalized guidance plan to obtain a guidance rule collection; The guidance rule collection is subjected to rule integration processing through rule mapping processing to obtain a service guidance rule library.

6. The cross-border trade data intelligent processing method based on smart ports according to claim 1 is characterized in that: The service guidance rule base is subjected to a knowledge graph construction process by a knowledge extraction algorithm to obtain a business knowledge reasoning rule set; the knowledge graph construction process includes extracting business entities, constructing a relationship network, discovering knowledge rules, and establishing a causal relationship chain, including: Performing business entity extraction processing on the service guidance rule base through a knowledge extraction algorithm to obtain an entity feature set, and performing business entity attribute annotation processing on the entity feature set to obtain a business entity dictionary; Performing a relationship network construction process on the business entity dictionary to obtain an initial relationship graph, and performing an inter-entity association strength calculation process on the initial relationship graph to obtain a relationship network; Performing knowledge rule extraction processing on the relationship network to obtain a rule candidate set, and performing rule verification processing on the rule candidate set to obtain knowledge rules; Performing causal chain construction processing on the knowledge rules to obtain a causal relationship table, and performing causal strength evaluation processing on the causal relationship table to obtain a causal relationship chain; Performing inference rule generation processing on the knowledge rules and causal relationship chain through a rule induction algorithm to obtain a basic inference rule set, and performing rule completeness verification processing on the basic inference rule set to obtain a rule verification report; The rule verification report is subjected to rule supplementation processing to obtain a business knowledge reasoning rule set.

7. The cross-border trade data intelligent processing method based on smart ports according to claim 1 is characterized in that: The cross-border trade data is processed on the business knowledge reasoning rule set to obtain an intelligent decision-making solution for port business; The cross-border trade data processing includes customs clearance process optimization, logistics route planning, risk level assessment and customs clearance time prediction, including: Performing customs clearance business process analysis on the business knowledge reasoning rule set to obtain a set of process bottleneck points, and performing customs clearance process optimization processing on the set of process bottleneck points to obtain candidate solutions for the customs clearance process; Performing process node configuration processing on the candidate solutions for the customs clearance process to obtain a customs clearance business flow diagram, and performing path deviation analysis processing on the customs clearance business flow diagram to obtain a customs clearance process reference path; Performing logistics resource allocation processing on the customs clearance process reference path to obtain a logistics resource distribution map, and performing logistics path planning processing on the logistics resource distribution map to obtain a logistics path planning solution; Performing a transportation timeliness evaluation process on the logistics path planning scheme to obtain a transportation timeliness evaluation table, and performing a logistics node optimization process on the transportation timeliness evaluation table to obtain a logistics distribution path diagram; Performing risk factor identification processing on the logistics distribution route map to obtain a risk factor list, and performing risk level assessment processing on the risk factor list to obtain a risk level assessment report; Extracting customs clearance timeliness elements from the risk level assessment report to obtain a timeliness influencing factor table, and performing customs clearance timeliness prediction processing on the timeliness influencing factor table to obtain a customs clearance timeliness prediction result; Performing scheme integration processing on the customs clearance process benchmark path, logistics distribution path map and customs clearance time prediction results to obtain a decision candidate scheme set, and performing scheme feasibility evaluation processing on the decision candidate scheme set to obtain a scheme evaluation report; The scheme evaluation report is subjected to intelligent decision-making generation processing to obtain an intelligent decision-making scheme for port business.

8. A cross-border trade data intelligent processing system based on a smart port, used to implement the cross-border trade data intelligent processing method based on a smart port as described in any one of claims 1 to 7, characterized in that: The cross-border trade data intelligent processing system based on the smart port includes: Functional modules are used to perform functional model hierarchical processing on cross-border trade business data to obtain a functional module call relationship network; the functional model hierarchical processing includes dividing the business data into an enterprise main function layer and a business function layer, and constructing a data interaction interface between the functional modules; A process module is used to construct a process template for the function module call relationship network to obtain a dynamic process assembly rule base; the process template construction process includes designing a business declaration process and an exception handling process system based on the function call relationship; A service tracking module is used to perform service tracking processing on the dynamic process assembly rule library to obtain a user behavior analysis data set; the service tracking processing includes setting tracking positions at key process nodes to collect user operation behavior data, business data change data and process execution status data; A service guidance module, which is used to perform guidance strategy construction processing on the user behavior analysis data set to obtain a service guidance rule base; the guidance strategy construction processing includes designing operation prompts based on user behavior patterns, formulating exception handling suggestions and personalized guidance plans; A graph module is used to construct a knowledge graph for the service guidance rule base through a knowledge extraction algorithm to obtain a business knowledge reasoning rule set; the knowledge graph construction process includes extracting business entities, building a relationship network, discovering knowledge rules, and establishing a causal relationship chain; The decision-making module is used to process the cross-border trade data on the business knowledge reasoning rule set to obtain an intelligent decision-making plan for port business; the cross-border trade data processing includes customs clearance process optimization, logistics route planning, risk level assessment and customs clearance time prediction.

Images