Intelligent ship and cargo matching method, device and equipment

Abstract

The embodiment of the invention provides an intelligent ship and cargo matching method, device and equipment. The method comprises the following steps: in response to received rule constraint data predefined by a user, constructing and initializing a rule base about ship and cargo matching based on the rule constraint data; wherein the rule base comprises a multi-level rule system which is divided into a hard constraint and a soft constraint; in response to the received ship transport capacity data and cargo demand data, performing preliminary matching screening on the ship and cargo combination based on a rule base, and generating a candidate matching set; based on the candidate matching set, a Pareto optimal solution set for ship and cargo matching is solved and generated through a multi-objective optimization algorithm; in response to the received real-time shipping data, updating a matching scheme in the Pareto optimal solution set through a dynamic feedback mechanism, and generating an updated matching scheme; and determining a final ship and cargo matching result based on the updated matching scheme. By using the method provided by the embodiment of the invention, the decision-making efficiency of shipping logistics can be comprehensively improved.

Description

Technical Field

[0001] This disclosure relates to the interdisciplinary field of intelligent shipping logistics and industrial artificial intelligence, specifically to an intelligent ship-cargo matching method, apparatus, and equipment. Background Technology

[0002] Traditional ship-cargo matching relies heavily on the personal experience of dispatchers, manually filtering and pairing limited ship and cargo information. This method is not only inefficient and ill-suited for large-scale, multi-variable, and complex dispatching scenarios, but also highly dependent on individual judgment, leading to a lack of consistency and objective standards in the decision-making process. Matching results often remain at the level of meeting basic transportation needs, failing to achieve comprehensive optimization of multiple objectives such as transportation cost, timeliness, and safety.

[0003] With the development of information technology, some solutions attempt to achieve automated matching using rule engines or basic operations research methods. However, these methods typically have significant limitations: while engines based on fixed rules can ensure business compliance, their rigid rule systems cannot adapt to the rapidly changing real-world shipping environment and struggle to handle complex decisions requiring trade-offs; traditional optimization algorithms often focus on a single economic objective, or when faced with numerous complex business constraints such as "safety and seaworthiness," their computational complexity increases dramatically, resulting in low solution efficiency and even difficulty in obtaining a feasible solution within a reasonable timeframe. More importantly, existing methods generally lack effective dynamic adjustment and self-learning capabilities. If unexpected situations arise during plan execution, such as shipping delays or new orders, the system cannot respond quickly and generate reliable adjustment plans, significantly reducing the resilience and efficiency of the entire transportation chain. Summary of the Invention

[0004] To address the aforementioned technical problems, the present disclosure provides a solution. Embodiments of this disclosure offer an intelligent ship-cargo matching method, apparatus, and device.

[0005] According to a first aspect of the present disclosure, an intelligent ship-cargo matching method is provided, wherein the method includes: In response to receiving user-defined rule constraint data, a rule base for ship-cargo matching is constructed and initialized based on the rule constraint data; wherein, the rule base contains a multi-level rule system that distinguishes between hard constraints and soft constraints; In response to receiving ship capacity data and cargo demand data, a preliminary matching and screening of ship-cargo combinations is performed based on the rule base to generate a candidate matching set; Based on the candidate matching set, a Pareto optimal solution set for ship-cargo matching is generated by solving a multi-objective optimization algorithm; In response to receiving real-time shipping data, the matching scheme in the Pareto optimal solution set is updated through a dynamic feedback mechanism to generate an updated matching scheme; Based on the updated matching scheme, the final ship-cargo matching result is determined.

[0006] According to a second aspect of the present disclosure, an intelligent ship-cargo matching device is provided, wherein the device includes: The initialization unit is configured to: in response to receiving user-defined rule constraint data, construct and initialize a rule base for ship-cargo matching based on the rule constraint data; wherein the rule base contains a multi-level rule system that distinguishes between hard constraints and soft constraints; The filtering unit is configured to: in response to receiving ship capacity data and cargo demand data, perform preliminary matching filtering on ship and cargo combinations based on the rule base, and generate a candidate matching set; The multi-objective optimization unit is configured to: generate a Pareto optimal solution set for ship-cargo matching based on the candidate matching set using a multi-objective optimization algorithm; The update unit is configured to: in response to receiving real-time shipping data, update the matching scheme in the Pareto optimal solution set through a dynamic feedback mechanism, and generate an updated matching scheme; The result determination unit is configured to determine the final ship-cargo matching result based on the updated matching scheme.

[0007] According to a third aspect of the present disclosure, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the intelligent ship-cargo matching method of the present disclosure.

[0008] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, the storage medium storing a computer program for executing the intelligent ship-cargo matching method of the present disclosure.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, implements the intelligent ship-cargo matching method described in the present disclosure.

[0010] As described above, the intelligent ship-cargo matching method provided in this disclosure significantly improves the overall efficiency of ship-cargo matching through a three-layer collaborative architecture of pre-defined rule constraints, intelligent optimization core, and dynamic feedback closed loop. Specifically, firstly, the introduction of a rule base enables efficient preliminary screening, greatly reducing computational complexity and improving matching speed and resource utilization; secondly, a multi-objective optimization algorithm ensures the global optimality of the solution set, balancing multiple objectives such as transportation costs, time windows, and compliance to generate high-quality trade-off solutions; furthermore, the dynamic feedback mechanism, combined with real-time data and digital twin simulation, endows the system with strong adaptive capabilities, enabling it to respond quickly to emergencies such as ship delays and weather changes, reducing operational risks; finally, while ensuring safety and the implementation of business strategies, the system achieves intensive use of computing resources, providing continuously optimized, reliable, and efficient intelligent decision support for shipping logistics. Attached Figure Description

[0011] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0012] Figure 1 This is a flowchart illustrating an exemplary embodiment of the intelligent ship-cargo matching method provided in this disclosure; Figure 2 This is a schematic diagram of the core algorithm architecture of the intelligent ship-cargo matching scheme provided in an exemplary embodiment of this disclosure; Figure 3 This is a public announcement Figure 1 Another exemplary flowchart of the intelligent ship-cargo matching method provided in the embodiment; Figure 4 This is a public announcement Figure 1 Another exemplary flowchart of the intelligent ship-cargo matching method provided in the embodiments; Figure 5 This is a public announcement Figure 1 Another exemplary flowchart of the intelligent ship-cargo matching method provided in the embodiments; Figure 6 This is a public announcement Figure 1 Another exemplary flowchart of the intelligent ship-cargo matching method provided in the embodiments; Figure 7 This is a schematic diagram of a voyage progress monitoring view provided in an exemplary embodiment of this disclosure; Figure 8 This is a public announcement Figure 1 Another exemplary flowchart of the intelligent ship-cargo matching method provided in the embodiments; Figure 9 This is a schematic diagram of the structure of an intelligent ship-cargo matching device provided in an exemplary embodiment of this disclosure; Figure 10 This is a schematic diagram of the structure of one application embodiment of the electronic device disclosed herein. Detailed Implementation

[0013] The present disclosure will be further described below with reference to the embodiments shown in the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present disclosure, and not all embodiments of the present disclosure. It should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0014] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0015] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0016] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0017] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0018] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0019] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0020] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0021] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0022] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0024] Overview of the inventive concept The core inventive concept of the disclosed technical solution lies in: referring to Figure 2 By integrating a three-layer architecture of pre-defined rule constraints, intelligent optimization core, and dynamic feedback loop, the system achieves end-to-end optimization of ship-cargo matching. Specifically, firstly, a multi-level rule base is dynamically constructed based on business rules and historical data, distinguishing between hard constraints to ensure safety and soft constraints to support adaptive adjustment, thereby efficiently screening candidate matching sets. Subsequently, a multi-objective optimization algorithm is used to generate a set of trade-off solutions considering transportation costs, time, and compliance. Finally, real-time data-driven digital twin simulation and reinforcement learning mechanisms are used to dynamically adjust rule weights and algorithm parameters, responding to sudden anomalies and continuously optimizing matching results, thereby comprehensively improving the decision-making efficiency, economy, and adaptability of shipping logistics.

[0025] Based on the above-mentioned inventive concept, this disclosure proposes an intelligent ship-cargo matching scheme as described in the following embodiments.

[0026] Example 1 Figure 1 This is a schematic flowchart of an intelligent ship-cargo matching method provided in an exemplary embodiment of this disclosure. The method can be executed on a server (e.g., a cloud service platform, a locally deployed server).

[0027] Specifically, refer to Figure 1 The intelligent ship-cargo matching method includes: S110. In response to receiving user-defined rule constraint data, construct and initialize a rule base for ship-cargo matching based on the rule constraint data.

[0028] The rule base contains a multi-level rule system that distinguishes between hard constraints and soft constraints.

[0029] The "user-defined rule constraint data" is a comprehensive dataset encompassing three dimensions: security, economy, and business. The specific parameters and weights of all these rules can be dynamically modified and adjusted by business personnel based on actual business changes.

[0030] Specifically, safety rule data is used to ensure the basic safety of ship navigation, cargo loading and unloading, and route selection, and consists of mandatory constraints. This mainly includes: ship seaworthiness data; for example, requiring that the ship's deadweight tonnage must meet cargo weight requirements to avoid overloading or wasted capacity. Safety rule data for specific routes; for example, explicitly prohibiting older vessels from operating in inland waterways such as the Yangtze River (i.e., the "older vessels not entering the river" rule) to avoid potential dangers in high-risk navigation areas. Crew fatigue management data; for example, to address the safety risks of continuous high-intensity operations, innovative fatigue scoring rules have been established for inland port operations, stipulating that the cumulative fatigue level of a vessel within a certain time window must not exceed a safety threshold.

[0031] Specifically, economic efficiency rules aim to improve the economic efficiency of individual voyages and overall fleet operations. They are typically prioritized as soft constraints, and their weights can be dynamically adjusted. These mainly include: efficiency indicators; for example, setting a minimum threshold for single-voyage load factor (e.g., greater than 80%) to improve vessel space utilization; cost control data; for example, requiring vessels to use economic speeds during navigation to save fuel costs; and referencing current market freight rates to ensure competitiveness when making single-voyage charter decisions; and empty-run loss control data; for example, implicit in the matching logic, aiming to prioritize cargo-ship combinations that reduce empty-run distances.

[0032] Specifically, business rule data translates a company's business strategies and customer relationship management requirements into actionable matching rules. This primarily includes: customer priority data; for example, prioritizing the matching of cargo transportation needs for core customers or key strategic partners to ensure supply chain stability. Operational strategy data; for example, designating certain vessels as fixed-route vessels to maintain stable and reliable service on specific routes. Other customized business requirements; for example, business personnel can define corresponding rules based on temporary or special business arrangements.

[0033] As an optional implementation method, refer to Figure 3 Step S110, "constructing and initializing the rule base for ship-cargo matching based on the rule constraint data," may include: S1110, retrieve historical matching data and business strategy data.

[0034] As an optional example, the server, acting as the execution entity, can retrieve data from a database that pre-stores the "historical matching data and business strategy data".

[0035] The historical matching data may include past execution records and feedback data of ship-cargo matching.

[0036] The business strategy data can be data that represents the strategies formulated by users based on business needs.

[0037] S1120. Based on the rule constraint data, historical matching data, and business strategies, formulate the multi-level rule system.

[0038] The multi-level rule system includes security rule data, economic benefit rule data, and business rule data.

[0039] As an optional example, when formulating the multi-level rule system, the server, as the implementing entity, first integrates and analyzes the received user-defined rule constraint data, historical matching data retrieved from the database, and business strategy data. Based on the company's strategic goals defined in the business strategy (such as ensuring supply to core customers and improving fleet turnover efficiency) and market conditions (such as the degree of capacity shortage), the server determines the overall direction of the rule system. Subsequently, the server classifies and vectorizes the rules according to three dimensions: safety, economy, and business, constructing a structured multi-level rule system.

[0040] The safety rules data includes requirements for vessel load capacity to meet cargo weight limits, compatibility between port facilities and vessels, and innovative vessel fatigue scoring rules designed to address the risks of continuous river operations. The economic efficiency rules data includes single-voyage load factor thresholds, economic speed requirements, and market-based charter cost control rules. The business rules data includes rules reflecting commercial strategies, such as priority matching for specific clients and fixed routes for scheduled vessels. All rules are stored in the rule base as configurable parameters.

[0041] S1130. Divide the rules in the multi-level rule system into hard constraints and soft constraints.

[0042] The hard constraints are configured as mandatory constraints and subject to a veto system, while the soft constraints are configured as priority constraints and support dynamic adjustment of weights through reinforcement learning.

[0043] As an optional example, after completing the rule system construction, the server, acting as the execution entity, categorizes the rules into hard and soft constraints based on their importance and business tolerance. The server sets most of the safety rules (such as ship seaworthiness and port safety conditions) and some core clauses in the business rules (such as absolute prohibitions in contracts) as hard constraints. During the subsequent matching and screening process, the server applies these hard constraints to any ship-cargo combination with a veto system; any violation immediately filters out the combination, ensuring the safety and compliance of the matching scheme. For economic benefit rules and some business rules, the server sets them as soft constraints. Soft constraints are not absolute prohibitions but rather part of the optimization objectives. The server assigns an initial weight to each soft constraint and configures a dynamic weight adjustment interface implemented through a reinforcement learning module. This mechanism allows the weight of soft constraints to adaptively adjust based on real-time feedback (such as market freight rate fluctuations and shifts in company strategy), thereby balancing the priorities of different objectives during the optimization process.

[0044] S1140. Set the initial weights of the soft constraints and the threshold parameters of the hard constraints, and optimize the initial configuration based on historical high-quality matching schemes in the historical matching data.

[0045] As an optional example, for soft constraints, the server, as the implementing entity, assigns initial weights based on business strategies (e.g., increasing the weight of the "customer priority" rule during peak supply periods and increasing the weight of the "economic benefit" rule during off-peak seasons). For hard constraints, the server, as the implementing entity, sets specific threshold parameters (e.g., 80% in "load rate greater than 80%" is the threshold). To improve the initial quality of the rule base, the server calls historical high-quality matching solutions (i.e., those solutions that have achieved good operational efficiency and customer satisfaction in actual implementation) from historical matching data for machine learning analysis. By analyzing the rule patterns that these high-quality solutions generally satisfy or slightly violate, the server can reverse-engineer the initial weight settings of soft constraints and fine-tune the threshold parameters of hard constraints (e.g., if the load rate of high-quality solutions is generally between 85% and 95%, the threshold or suggested range can be adjusted appropriately), making the initial state of the rule base closer to optimal business practices and laying a solid foundation for subsequent efficient matching.

[0046] As an optional implementation, the method further includes: dynamically updating the rule weights or rule items in the rule base in response to receiving a user modification instruction.

[0047] First, it should be noted that the method of this disclosure embodiment can be encapsulated as software and deployed on a server to form a "system" that provides services to the outside world. Based on this, it can specifically include the following steps: 1) The system receives user modification instructions through the rule base management interface. The instructions contain three key dimensions: rule identifier (specifying the specific rule to be modified), modification type (weight adjustment or rule item change), and new parameter value. The instruction parsing module first verifies the user's operation permissions to ensure that only authorized personnel can modify the rules, and then performs syntax and logic checks on the instructions to prevent illegal input. 2) When the modification type is weight adjustment, the system calls the reinforcement learning module for collaborative optimization. Taking the "load rate threshold" in the economic benefit rule as an example, if the business personnel increase the priority weight from 0.6 to 0.8, the system will not only directly update the weight parameter, but also trigger the following linkage mechanism: the reinforcement learning module will analyze the impact of the weight adjustment on the objective function in recent matching schemes; combine the simulation results of the digital twin platform to verify the actual effect of the new weight; and automatically adjust the weights of other associated rules to maintain system balance. 3) For modifications to the rule items themselves (such as adding a "summer energy efficiency gain rule"), the system performs a deep update: the syntax parser verifies the completeness of the new rule logic; the conflict detection module checks the compatibility between the new rule and existing rules; historical data backtesting ensures that the new rule will not cause high-quality solutions to be incorrectly filtered. 4) After each modification, the system automatically performs the following operations: generates a rule update report, including a comparison of parameters before and after the modification; runs typical scenarios in the test environment to verify the modification effect; notifies relevant business modules to update their caches via a message queue; and records modification logs for subsequent rule self-evolution analysis.

[0048] S120. In response to receiving ship capacity data and cargo demand data, perform preliminary matching and screening of ship and cargo combinations based on the rule base to generate a candidate matching set.

[0049] As an optional implementation method, refer to Figure 4 Step S120 may include: S1210. The ship and cargo combination is filtered using the hard constraints to obtain a first matching combination.

[0050] As an optional example, a mandatory filtering process is first applied to all ship-cargo combinations using hard constraints. Rules marked as hard constraints in the rule base (such as safety rules like "ship tonnage must meet cargo weight requirements" and "older ships are prohibited from operating on rivers") are used as filtering conditions to verify the compliance of each ship-cargo combination. In practice, parallel computing technology is used to perform a Cartesian product operation on the ship and cargo queues, applying all hard constraint rules to each combination one by one. Any combination that violates any hard constraint is immediately eliminated by the system. For example, if a ship's tonnage is detected to be less than the cargo weight requirement, the combination is directly marked as "mismatched" and eliminated. Through this filtering, the system can quickly eliminate high-risk or infeasible matching schemes within milliseconds, generating a first matching combination that meets basic safety and compatibility requirements.

[0051] S1220. The first matching combination is filtered based on a score using the soft constraints to obtain a second matching combination.

[0052] The scoring is determined based on rule satisfaction metrics.

[0053] As an optional example, soft constraints are applied to the first matching combination selected through hard constraints for refined scoring. The rule satisfaction quantification engine is invoked to convert each soft constraint (such as "load rate greater than 80%" in the economic benefit rule and "customer priority" in the business rule) into a continuous score value in the range [0,1]. The scoring process employs a multi-dimensional weighted evaluation: first, the original satisfaction level of each combination on each soft constraint is calculated (such as the ratio of actual load rate to target value); then, a weighted comprehensive score is performed by combining dynamically adjusted weight coefficients from the rule base. Specifically, for qualitative rules such as "customer priority," the system quantifies them into specific scores using a fuzzy evaluation method. Finally, each matching combination receives a comprehensive score, and the combinations are ranked according to their scores, with the top-ranked high-quality combinations forming the second matching combination.

[0054] S1230. Based on the ranking results of the scores and the second matching combination, a candidate matching set is generated.

[0055] As an optional example, a candidate matching set is intelligently generated based on the score ranking results. First, a dynamic threshold is set (e.g., retaining the top 20% of combinations, or all combinations with a score greater than 0.8), and high-quality candidate solutions are selected from the second set of matching combinations. Then, a diversity guarantee mechanism is employed to ensure that the candidate set includes representative solutions from different types of ships and different routes, avoiding getting trapped in local optima. The candidate set is also compared with historical high-quality matching solutions to further verify its rationality. The final generated candidate matching set not only satisfies all hard constraints but also performs excellently on soft constraints, providing a high-quality initial solution space for subsequent optimization algorithms. This rule-guided candidate set generation method significantly improves the efficiency of subsequent optimization by more than 50% compared to traditional random initialization.

[0056] S130. Based on the candidate matching set, a Pareto optimal solution set for ship-cargo matching is generated by solving a multi-objective optimization algorithm.

[0057] As an optional implementation method, refer to Figure 5 Step S130 may include: S1310. Based on the candidate matching set, a graph neural network is used to learn the potential feature representation of ship cargo matching to generate an initial solution set.

[0058] As an alternative example, graph neural network techniques are employed to learn latent feature representations for ship-cargo matching to generate a high-quality initial solution set. First, a bipartite graph structure is constructed, where ships and cargo are represented as two types of nodes, and feasible matching relationships in the candidate matching set are represented as edges connecting these nodes.

[0059] Each ship node i Assigned a feature vector This includes, but is not limited to: vessel type, deadweight tonnage, current location, and available time. Each cargo node... j Assigned a feature vector This includes, but is not limited to, coal type, transport volume, loading and unloading ports, and loading time.

[0060] Through the message passing mechanism of graph neural networks, node features are propagated through multiple layers to generate embedded representations. Its basic form can be expressed as:

[0061] in, Represents a node v The set of neighbors; , Indicates the first l The trainable parameters of the layer; This represents the activation function.

[0062] Using historical high-quality matching schemes as training data, the parameters of the graph neural network are optimized through supervised learning. After training, the candidate matching set is input into the trained network to obtain the latent feature representation of each matching combination, and a high-quality initial solution set is generated accordingly. Compared to random initialization, this method provides a starting point closer to the optimal region for subsequent optimization algorithms, significantly improving convergence speed.

[0063] S1320. With the objectives of minimizing transportation costs, minimizing transportation time, and minimizing rule violations, the third-generation non-dominated sorting genetic algorithm is used to iteratively solve the initial solution set to obtain a Pareto optimal solution set containing multiple trade-offs.

[0064] The degree of violation of the rules is determined through a tiered penalty mechanism.

[0065] As an optional example, the step of using the third-generation non-dominated sorting genetic algorithm (i.e., NSGA-III) to iteratively solve the initial solution set includes: dynamically adjusting the distribution of reference points to maintain the uniformity of the Pareto front; and adjusting the density of reference points according to the data representing business preferences in the business strategy data.

[0066] Specifically, a third-generation non-dominated sorting genetic algorithm is used to process the initial solution set. The core of iterative solution is to handle a multi-objective optimization problem. The mathematical model of this problem involves the following key elements: I1) Define binary decision variables , indicating ships i Does it carry goods? j (1 indicates a match, 0 indicates no match). It also involves time-related variables, such as ships. i Departure time and arrival time .

[0067] I2) The optimization objective is to minimize the following three core metrics. Specifically: Minimize operating costs, i.e., the objective function The goal is to minimize total operating costs, which can be expressed as:

[0068] in, Indicates the transport of goods j Freight revenue; Indicates a ship i Transporting goods j The resulting fuel costs; Indicates a ship i Transporting goods j The resulting port costs.

[0069] Minimize transportation time (or maximize ship turnaround rate); that is, the objective function Focusing on efficiency can be expressed as minimizing total time or maximizing turnover rate:

[0070] in, Indicates a ship i In the cycle l Number of transport trips within the area; Indicates period l The length of time.

[0071] Minimize the degree of rule violation; that is, the objective function To ensure compliance, a tiered penalty mechanism is used:

[0072] in, Indicates the first k The degree of violation of the rules; This indicates the corresponding penalty weight; for hard constraints, Setting it to a maximum value triggers a "veto"; for soft constraints, It can be dynamically adjusted; It can be calculated based on the deviation between the actual value and the threshold.

[0073] I3) Optimization Algorithm and Process. Specifically, the NSGA-III algorithm is used to handle the above multi-objective optimization problem. This algorithm iterates through non-dominated sorting, reference point guidance, and elite preservation strategies.

[0074] During the iteration process, the server dynamically adjusts the distribution density of reference points in the target space based on the preferences represented in the business strategy data (such as prioritizing cost or timeliness) to ensure that the final Pareto front solution set has good distribution uniformity and can reflect the decision-maker's preferences.

[0075] The algorithm employs an adaptive strategy to adjust the crossover and mutation rates, maintaining larger values ​​in the early stages of evolution to enhance global exploration, and decreasing them in the later stages to facilitate fine-grained local searches.

[0076] As described above, through the aforementioned implementation method, the server ultimately outputs a Pareto optimal solution set, which contains several (e.g., 3-5) non-dominated solutions. Each solution represents an optimal trade-off among the aforementioned multiple objectives, for the decision-maker to choose from. Through this structured modeling and optimization process, the system can efficiently generate high-quality, multi-choice ship-cargo matching solutions under complex constraints.

[0077] S140. In response to receiving real-time shipping data, the matching scheme in the Pareto optimal solution set is updated through a dynamic feedback mechanism to generate an updated matching scheme.

[0078] As an optional implementation method, refer to Figure 6 Step S140 may include: S1410. Input the matching schemes in the Pareto optimal solution set into the digital twin platform for simulation operation, predict the key performance indicators of each matching scheme, and obtain the simulation results.

[0079] The key performance indicators include simulation results of predicted fuel consumption, on-time performance, and fatigue accumulation.

[0080] As an alternative example, matching schemes from the Pareto optimal solution set can be input into a high-fidelity digital twin platform for simulated operation. The virtual mapping system built on this platform can generate... Figure 7 The voyage progress monitoring view shown uses color codes to distinguish status: gray represents "completed," blue represents "seaworthiness in progress," and red warns of "voyage overdue." Based on ship performance models and real-time environmental data, the platform performs a full voyage simulation for each matching scheme, accurately predicting key performance indicators. The simulation results are displayed as a visual progress bar, including a comparison of planned and actual estimated times for each node, such as berthing and departure times. The platform also generates a detailed schedule of subsequent plans, including complete information such as user, vessel name, voyage number, loading / unloading ports, cargo volume, and planned arrival time, providing a clear basis for scheme feasibility assessment.

[0081] S1420. In response to the deviation between the simulation results and the preset target of the optimization stage, the hyperparameters of the multi-objective optimization algorithm and the weights of the soft constraints in the rule base are adjusted based on reinforcement learning.

[0082] As an optional example, a reinforcement learning adaptive mechanism is established by comparing the results of digital twin simulations with the optimization objective. When a red overdue warning appears on the monitoring interface or the node time deviation exceeds the threshold, the system automatically triggers the parameter adjustment process.

[0083] Specifically, schedule deviations can be converted into reward function inputs. For example, for consecutive node delays, the weight of the "time window priority" rule is automatically increased; for cargo loading rate deviations, the parameter configuration of the economic benefit rule is optimized. At the same time, the system dynamically adjusts the hyperparameter set of the multi-objective optimization algorithm, including adaptively adjusting the population size and mutation rate based on the schedule stability index, to ensure that the algorithm parameters are optimized in sync with the actual operating status.

[0084] S1430. In response to the detection of a sudden event in the real-time shipping data, based on the adjusted hyperparameters and soft constraint weights of the multi-objective optimization algorithm, a re-optimization mechanism is performed on the matching scheme affected by the sudden event to match the type of the sudden event, thereby obtaining a re-optimized candidate matching scheme.

[0085] As an optional example, a tiered event response mechanism can be established by real-time analysis of voyage progress data. When the following event is detected... Figure 7 When a voyage exceeds its expiration date (marked in red) or a node execution error occurs, the system immediately triggers the corresponding re-optimization process.

[0086] For events causing schedule delays, a local time window repair algorithm is activated to re-plan the node time sequence while maintaining the original ship-cargo matching relationship. For new tasks, an incremental optimization engine is invoked to quickly generate supplementary solutions. For major route changes, a global refactoring is performed and relevant constraints are temporarily adjusted. All re-optimization operations inherit the parameter configuration adjusted in S1420 to ensure that the solution conforms to the current optimization direction and has emergency response capabilities.

[0087] S1440. Based on the candidate matching scheme, update the Pareto optimal solution set and generate the updated matching scheme.

[0088] As an alternative example, an elitist retention strategy is employed to update the Pareto optimal solution set, and the optimization results are deeply integrated with the cruise schedule management system. The cruise schedule management system can generate updated plans containing complete schedules, each accompanied by, for example... Figure 7 The visual progress preview interface clearly marks the status and time schedule of each node.

[0089] In addition, the updated plan is pushed to the business system via API, automatically generating executable work orders containing detailed information such as vessel name, voyage number, loading and unloading ports, cargo volume, and planned time. The business system establishes a version management mechanism to retain a record of plan iterations, ensuring full traceability of progress monitoring and plan optimization.

[0090] As described above, through these improvements, the implementation method further emphasizes the close integration of the digital twin platform with actual business monitoring, strengthens the closed-loop management concept from simulation verification to execution monitoring, and makes the technical solution more valuable for practical guidance.

[0091] S150. Based on the updated matching scheme, determine the final ship-cargo matching result.

[0092] As an optional implementation method, refer to Figure 8 Step S150 may include: S1510. Based on the updated matching scheme, output a set of trade-off schemes to the user terminal.

[0093] The set of trade-off solutions includes multiple Pareto optimal solutions.

[0094] As an optional example, a set of trade-off solutions containing multiple Pareto optimal solutions can be generated based on the updated matching scheme and pushed to the user terminal through a visual interface. A multi-dimensional comparison display method can also be adopted to generate a complete performance evaluation report for each scheme, including economic indicators (estimated transportation costs, profit margins), timeliness indicators (estimated total flight time, node time windows), and compliance indicators (rule compliance, risk score).

[0095] In addition, the system can intelligently label the unique advantages of each solution, for example, by using tags such as "cost-optimal solution," "time-optimal solution," or "balanced solution." The system also provides a solution comparison function, allowing users to view the differences in key performance indicators across different solutions side-by-side. Each solution is accompanied by simulated predictive data from a digital twin platform, including potential risks and corresponding mitigation suggestions, providing decision-makers with comprehensive decision support.

[0096] S1520. In response to receiving the final solution selected by the user from the set of trade-off solutions, perform transportation plan allocation and generate the final ship-cargo matching result.

[0097] The final ship-cargo matching result includes the target vessel, cargo, route, and time window.

[0098] As an optional example, upon receiving the final solution selected by the user from the set of trade-off solutions, the transportation plan allocation process can be initiated immediately. Specifically, the selected solution is first subjected to a final compliance check to ensure that all constraints are met. Subsequently, a standardized transportation plan work order is automatically generated, including target vessel information (vessel name, deadweight tonnage, crew configuration), cargo details (cargo type, quantity, special requirements), route planning (port call sequence, estimated sailing time), and time window arrangements accurate to the hour.

[0099] The server, acting as the execution entity, can push the final ship-cargo matching results to the shipping management system via API, triggering subsequent business processes such as slot confirmation and work order issuance. The shipping management system can simultaneously establish execution monitoring tasks, connecting planned data with the real-time operations system to enable dynamic closed-loop management throughout the entire process. All relevant parties (including ship owners, cargo owners, port dispatchers, etc.) will automatically receive task notifications through their respective systems, ensuring information synchronization and efficient collaboration.

[0100] Through the above implementation methods, a seamless connection can be achieved from intelligent recommendation to decision execution, ensuring both the scientific nature of the decision and the feasibility of the solution, thus fully demonstrating the practical value of the intelligent ship-cargo matching solution.

[0101] In summary, the intelligent ship-cargo matching method provided in this disclosure significantly improves the overall efficiency of ship-cargo matching through a three-layer collaborative architecture of pre-defined rule constraints, intelligent optimization core, and dynamic feedback closed loop. Specifically, firstly, the introduction of a rule base enables efficient preliminary screening, greatly reducing computational complexity and improving matching speed and resource utilization; secondly, the multi-objective optimization algorithm ensures the global optimality of the solution set, balancing multiple objectives such as transportation costs, time windows, and compliance to generate high-quality trade-off solutions; furthermore, the dynamic feedback mechanism, combined with real-time data and digital twin simulation, endows the system with strong adaptive capabilities, enabling agile responses to emergencies such as ship delays and weather changes, reducing operational risks; finally, while ensuring safety and the implementation of business strategies, the system achieves intensive use of computing resources, providing continuously optimized, reliable, and efficient intelligent decision support for shipping logistics.

[0102] Example 2 It should be understood that the intelligent ship-cargo matching method described in the foregoing embodiments herein can also be similarly applied to the following intelligent ship-cargo matching devices for similar extensions. For simplicity, they are not described in detail.

[0103] Figure 9 This is a schematic diagram of the structure of an intelligent ship-cargo matching device provided in an exemplary embodiment of this disclosure. (Refer to...) Figure 9 The device includes: The initialization unit 910 is configured to: in response to receiving user-defined rule constraint data, construct and initialize a rule base for ship-cargo matching based on the rule constraint data; wherein the rule base contains a multi-level rule system that distinguishes between hard constraints and soft constraints; The filtering unit 920 is configured to: in response to receiving ship capacity data and cargo demand data, perform preliminary matching filtering on the ship and cargo combination based on the rule base, and generate a candidate matching set; The multi-objective optimization unit 930 is configured to: generate a Pareto optimal solution set for ship-cargo matching based on the candidate matching set by a multi-objective optimization algorithm; The update unit 940 is configured to: in response to receiving real-time shipping data, update the matching scheme in the Pareto optimal solution set through a dynamic feedback mechanism to generate an updated matching scheme; The result determination unit 950 is configured to: determine the final ship-cargo matching result based on the updated matching scheme.

[0104] As described above, the intelligent ship-cargo matching device provided in this disclosure significantly improves the overall efficiency of ship-cargo matching through a three-layer collaborative architecture of pre-defined rule constraints, intelligent optimization core, and dynamic feedback closed loop. Specifically, firstly, the introduction of a rule base enables efficient preliminary screening, greatly reducing computational complexity and improving matching speed and resource utilization; secondly, a multi-objective optimization algorithm ensures the global optimality of the solution set, balancing multiple objectives such as transportation costs, time windows, and compliance to generate high-quality trade-off solutions; furthermore, the dynamic feedback mechanism, combined with real-time data and digital twin simulation, endows the system with strong adaptive capabilities, enabling it to respond quickly to emergencies such as ship delays and weather changes, reducing operational risks; finally, while ensuring safety and the implementation of business strategies, the system achieves intensive use of computing resources, providing continuously optimized, reliable, and efficient intelligent decision support for shipping logistics.

[0105] Example 3 In addition, this disclosure also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, wherein when the computer program is executed, it implements the intelligent ship-cargo matching method described in any of the above embodiments of this disclosure.

[0106] Figure 10 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Below, reference is made to… Figure 10 This describes an electronic device according to embodiments of the present disclosure. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0107] like Figure 10 As shown, the electronic device includes one or more processors and memory. The processor may be a central processing unit (CPU) or other processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the intelligent ship-cargo matching method of the various embodiments of this disclosure described above and / or other desired functions.

[0108] In one example, the electronic device may further include input and output devices, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). Furthermore, the input device may include, for example, a keyboard, a mouse, etc. The output device can output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0109] Of course, for the sake of simplicity, Figure 10 Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0110] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the intelligent ship-cargo matching methods according to various embodiments of this disclosure as described in the foregoing portion of this specification.

[0111] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0112] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the intelligent ship-cargo matching method according to various embodiments of this disclosure as described in the foregoing portion of this specification.

[0113] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0114] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0115] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0116] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0117] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0118] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0119] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0120] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0121] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. An intelligent ship cargo matching method, characterized by, The method comprises: in response to receiving user-defined rule constraint data, constructing and initializing a rule base for ship-cargo matching based on the rule constraint data; wherein the rule base contains a multi-level rule system differentiated into hard constraints and soft constraints; in response to receiving ship capacity data and cargo demand data, performing preliminary matching screening on ship-cargo combinations based on the rule base to generate a candidate matching set; based on the candidate matching set, generating a Pareto optimal solution set of ship-cargo matching by a multi-objective optimization algorithm; in response to receiving real-time shipping data, updating the matching schemes in the Pareto optimal solution set through a dynamic feedback mechanism to generate updated matching schemes; based on the updated matching schemes, determining the final ship-cargo matching result.

2. The method of claim 1, wherein, The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base.

3. The method of claim 1, wherein, The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base.

4. The method of claim 1, wherein, The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base.

5. The method of claim 2, wherein, The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base.

6. The method of claim 5, wherein, The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or rule items in the rule base. The method further comprises: in response to receiving user modification instructions, dynamically updating the rule weights or 7. The method of claim 1, wherein, The response to receiving real-time shipping data, through a dynamic feedback mechanism to update the matching scheme in the Pareto optimal solution set, generate updated matching scheme, comprising: The matching scheme in the Pareto optimal solution set is input into the digital twin platform for simulation operation, and the key performance indicators of each matching scheme are predicted to obtain the simulation results; wherein the key performance indicators include the simulation results of predicted fuel consumption, on-time rate and fatigue accumulation; In response to the deviation between the simulation results and the preset target in the optimization stage, the hyperparameters of the multi-objective optimization algorithm and the weights of the soft constraints in the rule base are adjusted based on reinforcement learning; In response to detecting a sudden event in the real-time shipping data, based on the adjusted hyperparameters of the multi-objective optimization algorithm and the weights of the soft constraints, the matching scheme affected by the sudden event is executed to perform the re-optimization mechanism of the type of the sudden event, and the candidate matching scheme after re-optimization is obtained; Based on the candidate matching scheme, the Pareto optimal solution set is updated to generate the updated matching scheme.

8. The method of claim 1, wherein, Based on the updated matching scheme, the final ship cargo matching result is determined, comprising: Based on the updated matching scheme, a trade-off scheme set is output to the user terminal; wherein the trade-off scheme set contains multiple Pareto optimal solutions, In response to receiving the final scheme selected by the user from the trade-off scheme set, the transportation plan allocation is executed to generate the final ship cargo matching result; wherein the final ship cargo matching result includes target ship, cargo, route and time window.

9. An intelligent ship cargo matching device characterized by, The device comprises: An initialization unit configured to: in response to receiving user-defined rule constraint data, construct and initialize a rule base for ship cargo matching based on the rule constraint data; wherein the rule base contains a multi-level rule system differentiated into hard constraints and soft constraints; A screening unit configured to: in response to receiving ship capacity data and cargo demand data, perform preliminary matching screening on ship and cargo combinations based on the rule base to generate a candidate matching set; A multi-objective optimization unit configured to: based on the candidate matching set, generate a Pareto optimal solution set for ship cargo matching by solving a multi-objective optimization algorithm; An update unit configured to: in response to receiving real-time shipping data, update the matching scheme in the Pareto optimal solution set through a dynamic feedback mechanism to generate an updated matching scheme; A result determination unit configured to: based on the updated matching scheme, determine the final ship cargo matching result.

10. An electronic device, comprising: The electronic device comprises: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to realize the intelligent ship cargo matching method of claims 1-8.

Images