Method and device for scheduling logistics based on cultural events, electronic equipment and medium

Abstract

The application relates to the technical field of logistics scheduling based on cultural events, and discloses a logistics scheduling method and device based on cultural events, an electronic device and a medium, wherein the method comprises the following steps: introducing a large language model to analyze cultural events, deeply understanding the actual influence of the cultural events on customs clearance operations, quantifying cultural event factors into association rules, predicting and responding to the risk of customs clearance delay or process change caused by events in advance, and then performing multi-objective optimization scheduling to obtain a hierarchical logistics scheduling scheme. The application has the beneficial effects that the congestion of high-grade goods in the high-influence period of events can be effectively avoided, the dynamic matching of logistics resources and the operation capacity of related agencies is realized, and the risks of goods delay, destination congestion and goods damage caused by scheduling mismatch are reduced from the source.

Description

Technical Field

[0001] This invention relates to the fields of logistics scheduling based on cultural events and the application of artificial intelligence in logistics optimization, and particularly to a logistics scheduling method, apparatus, electronic device and medium based on cultural events. Background Technology

[0002] In the field of international logistics, accurate prediction of customs clearance time is the core of developing efficient logistics scheduling plans. However, existing customs clearance time prediction systems and methods have significant flaws. Currently, the industry generally relies on static historical data, such as simply using the average customs clearance cycle of a certain destination as a prediction benchmark. This method completely ignores the short-term and drastic impact of local cultural events on customs clearance efficiency, resulting in actual clearance times far exceeding the static predictions. This leads to a high prediction error rate and may cause widespread delays in goods, resulting in destination congestion, soaring warehousing costs, and an increased risk of cargo damage. Summary of the Invention

[0003] Therefore, it is necessary to propose a logistics scheduling method, device, electronic equipment and medium based on cultural events to address the existing logistics scheduling problem based on cultural events.

[0004] A logistics scheduling method based on cultural events, the method comprising:

[0005] Real-time acquisition of data related to cultural events and historical customs clearance operation logs;

[0006] The data related to the cultural events and the historical customs clearance operation logs are input into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations;

[0007] Obtain a set of logistics order information to be processed; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information.

[0008] Based on the association rules and the cargo order information, a predicted customs clearance time window is generated for each cargo order information;

[0009] Input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model;

[0010] In the mathematical model, a multi-objective optimization strategy is used for collaborative decision-making, and the logistics scheduling of each of the goods order information is carried out in a hierarchical manner.

[0011] Furthermore, before the step of inputting the predicted customs clearance time window and the cargo order information into the preset mathematical model, the method further includes:

[0012] Based on the destination of each cargo order in the logistics order information set, the corresponding target area is determined;

[0013] Obtain regulatory information for each of the target regions and the spatiotemporal labels of the regulatory information;

[0014] The various regulatory information and the spatiotemporal labels are mapped to a preset mathematical space to form multiple constraints in the preset mathematical space, thereby obtaining the mathematical model.

[0015] Furthermore, after the step of mapping each of the regulatory information and the spatiotemporal label to a preset mathematical space to form multiple constraints in the preset mathematical space, thereby obtaining the mathematical model, the method further includes:

[0016] A soft time window constraint is introduced into the mathematical model to increase the penalty cost for scheduling schemes that exceed the predicted customs clearance time window, thereby obtaining an optimized mathematical model.

[0017] Further, the step of generating a predicted customs clearance time window for each cargo order based on the association rules and the cargo order information includes:

[0018] Each of the aforementioned goods order information is matched with the association rule to obtain the target cultural event factor for each of the aforementioned goods order information;

[0019] The cargo order information is input into a preset customs clearance time prediction model to obtain the baseline customs clearance time under the influence of no cultural events.

[0020] Based on the target cultural event factors, the baseline customs clearance time is corrected to generate a customs clearance time window that includes the earliest predicted customs clearance time window and the latest predicted customs clearance time window.

[0021] Furthermore, the step of inputting the cultural event-related data and historical customs clearance operation logs into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations includes:

[0022] The abnormal customs clearance events, such as customs clearance delays and increased inspection rates, that occurred during historical and cultural events are extracted from the historical customs clearance operation logs using a pre-defined large language model.

[0023] By analyzing the cultural event-related data using the large language model, event characteristics that are strongly correlated with the abnormal customs clearance event are identified;

[0024] The event features are associated with customs clearance operation parameters to generate association rules that take the event features as input and the expected customs clearance impact as output.

[0025] Furthermore, after the step of performing collaborative decision-making through a multi-objective optimization strategy in the mathematical model and hierarchically scheduling logistics for each of the goods order information, the method further includes:

[0026] Customs clearance is performed on each cargo order in the aforementioned logistics order information set according to the tiered logistics scheduling scheme;

[0027] Real-time acquisition of the actual customs clearance progress of each of the aforementioned goods orders;

[0028] Determine whether the deviation between the actual customs clearance progress and the theoretical customs clearance progress of the tiered logistics schedule is greater than a preset threshold.

[0029] When the deviation between the actual customs clearance progress and the theoretical customs clearance progress exceeds a preset threshold, the set of target orders that have not yet been cleared is obtained.

[0030] The goods orders in the target order set are rescheduled according to the mathematical model.

[0031] Furthermore, after the step of performing collaborative decision-making through a multi-objective optimization strategy in the mathematical model and hierarchically scheduling logistics for each of the goods order information, the method further includes:

[0032] Based on the scheduling results of each goods order, a scheduling confirmation instruction is sent to each relevant terminal;

[0033] Receive feedback information from each of the relevant terminals;

[0034] Determine whether each feedback message indicates a rejection;

[0035] If the feedback is a rejection, then obtain the corresponding target goods order information;

[0036] The cargo level information in the target cargo order information is adjusted, and the logistics scheduling of each cargo order information is re-arranged according to its level.

[0037] A logistics scheduling device based on cultural events, the device comprising:

[0038] The historical customs clearance operation log acquisition module is used to acquire data related to cultural events and historical customs clearance operation logs in real time.

[0039] The association rule generation module is used to input the cultural event-related data and historical customs clearance operation logs into a preset large language model for parsing, so as to generate association rules between cultural events and customs clearance operations.

[0040] The logistics order information set acquisition module is used to acquire a set of logistics order information to be processed; wherein the logistics order information set contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information.

[0041] The predicted customs clearance time window generation module is used to generate a predicted customs clearance time window for each of the cargo order information based on the association rules and the cargo order information.

[0042] The input module is used to input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model;

[0043] The hierarchical logistics scheduling module is used to make collaborative decisions in the mathematical model through multi-objective optimization strategies, and to perform hierarchical logistics scheduling for each of the goods order information.

[0044] An electronic device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0045] Real-time acquisition of data related to cultural events and historical customs clearance operation logs;

[0046] The data related to the cultural events and the historical customs clearance operation logs are input into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations;

[0047] Obtain a set of logistics order information to be processed; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information.

[0048] Based on the association rules and the cargo order information, a predicted customs clearance time window is generated for each cargo order information;

[0049] Input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model;

[0050] In the mathematical model, a multi-objective optimization strategy is used for collaborative decision-making, and the logistics scheduling of each of the goods order information is carried out in a hierarchical manner.

[0051] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0052] Real-time acquisition of data related to cultural events and historical customs clearance operation logs;

[0053] The data related to the cultural events and the historical customs clearance operation logs are input into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations;

[0054] Obtain a set of logistics order information to be processed; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information.

[0055] Based on the association rules and the cargo order information, a predicted customs clearance time window is generated for each cargo order information;

[0056] Input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model;

[0057] In the mathematical model, a multi-objective optimization strategy is used for collaborative decision-making, and the logistics scheduling of each of the goods order information is carried out in a hierarchical manner.

[0058] The beneficial effects of this invention are as follows: By introducing a large language model to analyze cultural events, we can gain a deep understanding of the actual impact of cultural events on customs clearance operations. By quantifying cultural event factors into association rules, we can predict and respond to the risks of customs clearance delays or process changes caused by events in advance. This allows for multi-objective optimization of scheduling, resulting in a tiered logistics scheduling scheme. This can effectively avoid congestion of high-level goods during the high-impact period of events, achieve dynamic matching of logistics resources and the operational capabilities of relevant institutions, and reduce the risks of cargo delays, destination congestion, and cargo damage caused by scheduling mismatches from the source. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] in:

[0061] Figure 1 This is a diagram illustrating the application environment of a logistics scheduling method based on cultural events in one embodiment.

[0062] Figure 2 This is a flowchart of a logistics scheduling method based on cultural events in one embodiment;

[0063] Figure 3 This is a structural block diagram of a logistics scheduling device based on cultural events in one embodiment;

[0064] Figure 4This is a structural block diagram of an electronic device in one embodiment. Detailed Implementation

[0065] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] Figure 1 This is a diagram illustrating a logistics scheduling application environment based on cultural events in one embodiment. (Refer to...) Figure 1 This cultural event-based logistics scheduling method is applied to a cultural event-based logistics scheduling system. The system includes a terminal 110 and a server 120. The terminal 110 and server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal, specifically a mobile phone, tablet, laptop, or other similar devices. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to acquire cultural event-related data and historical customs clearance operation logs, while the server 120 is used for hierarchical logistics scheduling of various cargo order information.

[0067] like Figure 2 As shown, in one embodiment, a logistics scheduling method based on cultural events is provided. This method can be applied to both terminals and servers; this embodiment illustrates its application to terminals. The logistics scheduling method based on cultural events specifically includes the following steps:

[0068] S1: Real-time acquisition of data related to cultural events and historical customs clearance operation logs;

[0069] S2: Input the cultural event-related data and historical customs clearance operation logs into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations;

[0070] S3: Obtain a set of logistics order information to be processed; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information;

[0071] S4: Generate a predicted customs clearance time window for each of the cargo order information based on the association rules and the cargo order information;

[0072] S5: Input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo order information into the preset mathematical model;

[0073] S6: In the mathematical model, a multi-objective optimization strategy is used for collaborative decision-making to perform hierarchical logistics scheduling for each of the goods order information.

[0074] As described in step S1 above, data related to cultural events and historical customs clearance operation logs are acquired in real time. Information related to cultural events is collected in real time through various data sources, such as connecting to social media networks in various regions through various API interfaces, or relevant cultural event databases. These cultural events may specifically affect customs clearance speed. For example, certain festivals may lead to the temporary absence of customs clearance personnel, or the customs clearance process may become more cumbersome due to specific destinations. The information contained in the historical logs is of great significance for understanding past customs clearance cycles and their impact, such as the customs clearance time, inspection frequency, and tariff processing for each shipment during a specific cultural event.

[0075] As described in step S2 above, the cultural event-related data and historical customs clearance operation logs are input into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations. The large language model can automatically extract information from complex datasets. Specifically, the large language model can be a GPT, Deppseek, or other large models. It identifies the characteristics of cultural events and their impact on the customs clearance process. This includes analyzing the specific impact of different events on customs clearance efficiency. For example, during carnivals, relevant agencies may experience decreased work efficiency due to holidays. At this stage, the model not only integrates historical customs clearance operation logs and cultural event-related data but also uses natural language processing technology to analyze text data to generate association rules between cultural events and customs clearance operations. These rules form a dynamic knowledge base, enabling the system to quickly adapt to similar cultural events that may occur in the future, improving the accuracy of customs clearance timeliness prediction. The large language model parses unstructured cultural event data and quantifies it into computable association rules.

[0076] As described in step S3 above, a set of logistics order information to be processed is obtained; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination, and goods grade information. Each order information should contain at least key data, such as goods category (e.g., food, electronic products, cosmetics, etc.), destination (the final delivery location of the goods, such as country or city), and goods grade (e.g., general goods, sensitive goods, high-value goods, etc.). Through the analysis of order information, the system can determine the additional customs clearance preparations that a certain type of goods may need under the influence of specific cultural events, and flexibly adjust the prediction strategy.

[0077] As described in step S4 above, a predicted customs clearance time window is generated for each of the goods order information based on the association rules and the goods order information. The predicted time window is not just a single point in time, but a possible time range to more accurately reflect the actual situation. The system considers multiple factors, including the customs clearance impact related to cultural events mentioned in the association rules, statistical trends in historical customs clearance data, etc. This allows the prediction results to more fully reflect the temporary changes caused by cultural activities, thereby avoiding errors caused by relying on historical averages.

[0078] As described in step S5 above, the predicted customs clearance time window and the order information for each cargo order are input into a preset mathematical model. The mathematical model is a multi-objective integer programming model, with objective functions including minimizing customs clearance delay costs and maximizing resource utilization. The mathematical model typically includes multiple variables to analyze the customs clearance efficiency of different orders under different conditions. The mathematical model can employ various mathematical modeling methods such as linear programming, nonlinear programming, and integer programming to adapt to different optimization objectives. By associating the dynamic predicted time window generated in the previous steps with the relevant order information, the model will formulate a specific customs clearance strategy for each order. This process not only takes into account the mutual influence between orders but also predicts potential bottlenecks or resource shortages within a specific range, thus providing a scientific basis for subsequent multi-objective optimization.

[0079] As described in step S6 above, the mathematical model employs a multi-objective optimization strategy for collaborative decision-making, tiering and scheduling logistics for each cargo order. When formulating logistics schedules, the system considers not only minimizing customs clearance time but also other objectives, such as rational resource allocation, transportation timeliness to various destinations, transportation costs, and customer satisfaction. The collaborative decision-making process requires finding the optimal balance between different objectives. For example, for high-value goods, the system may prioritize customs clearance or utilize dedicated channels. Through this complex optimization process, the system generates multiple alternatives and selects a logistics schedule that achieves superior performance across multiple indicators. This not only improves operational efficiency but also effectively reduces the negative impact and additional costs caused by cultural events.

[0080] In one embodiment, before step S5, which involves inputting the predicted customs clearance time window and the cargo order information into a preset mathematical model, the method further includes:

[0081] S401: Based on the destination of each goods order in the logistics order information set, determine the corresponding target area;

[0082] S402: Obtain the regulatory information of each target region and the spatiotemporal label of the regulatory information;

[0083] S403: Map each of the aforementioned regulatory information and the spatiotemporal label to a preset mathematical space to form multiple constraints in the preset mathematical space, thereby obtaining the mathematical model.

[0084] As described in step S401 above, the corresponding target region is determined based on the destination of each goods order in the logistics order information set. Destination information typically includes the region, destination, and possible warehousing location. The system needs to utilize a Geographic Information System (GIS) or a backend database to match the destination of each order to determine one or more corresponding target regions. A target region refers to the rules and regulatory environment applicable to a specific good at its final destination. For example, different countries and regions have their unique legal and regulatory requirements, involving various import and export restrictions, inspection and quarantine standards, etc. Through such regional division, the system can clearly define the specific regulations that each good needs to follow during customs clearance, thereby laying the foundation for improving the accuracy and practicality of predictions.

[0085] As described in step S402 above, regulatory information for each target region and its spatiotemporal tags are obtained. The regulatory information comes from multiple channels, including relevant websites, announcements, and industry regulations, covering content such as customs declaration requirements, cargo classification, declaration procedures, and quarantine standards. Furthermore, the regulatory information must also have spatiotemporal tags, indicating the applicability of these regulations in time and space. For example, some regulations may be adjusted due to special holidays or emergencies, and are only effective within a specific time period. By integrating regulatory information related to each target region and its spatiotemporal changes, the system can establish a complete legal compliance system, thereby improving the compliance of the entire logistics scheduling process. The regulatory information includes the import and export regulations and quarantine standards of the destination country; the spatiotemporal tags include the effective date and geographical scope of the regulations.

[0086] As described in step S403 above, each piece of regulatory information and the spatiotemporal label is mapped to a preset mathematical space, forming multiple constraints in the preset mathematical space, thereby obtaining the mathematical model. Regulatory clauses are transformed into templated constraints, such as expressing "a certain type of goods must meet specific quarantine standards" or "no additional tariffs may be added during a specific period" in inequality form. The spatiotemporal labels also need to be transformed into mathematical expressions so that their applicability can be accurately reflected during calculation. This process involves constructing various constraints for the mathematical model, forming a multi-dimensional constraint set. All customs clearance decisions must be made under these constraints.

[0087] In one embodiment, after step S403, which maps each of the regulatory information and the spatiotemporal label to a preset mathematical space to form multiple constraints in the preset mathematical space, thereby obtaining the mathematical model, the method further includes:

[0088] S4041: Introduce a soft time window constraint into the mathematical model to increase the penalty cost for scheduling schemes that exceed the predicted customs clearance time window, thereby obtaining an optimized mathematical model.

[0089] As described in step S404 above, a soft time window constraint is introduced into the mathematical model. This adds a penalty cost to scheduling plans that exceed the predicted customs clearance time window, thus obtaining an optimized mathematical model. By introducing the soft time window constraint, the established mathematical model is further optimized. The concept of a soft time window aims to provide flexibility in customs clearance time, rather than forcing each order to strictly adhere to the previous predicted customs clearance time window. In practice, the customs clearance time of goods may be affected by various factors, such as unforeseen events, the workload of relevant agencies, and cultural activities. Therefore, to adapt to these changes, the system needs to set a range of "allowable deviations," within which delays are acceptable. Specifically, once the scheduling plan for a certain goods order exceeds the predicted customs clearance time window, the system will add a corresponding penalty based on the set penalty cost. This can be achieved by introducing an additional cost function. For example, each day exceeding the estimated customs clearance time can accumulate a certain economic cost. At the same time, other potential costs, such as cargo demurrage fees and losses caused by customer dissatisfaction, should also be taken into account. This mechanism not only prompts decision-makers to prioritize solutions that meet the time window, but also effectively balances the relationship between multiple objectives. When multiple cargo orders compete for limited resources, soft time window constraints ensure the coordination and optimization of logistics scheduling and improve overall operational efficiency.

[0090] In one embodiment, step S4, which generates a predicted customs clearance time window for each cargo order based on the association rule and the cargo order information, includes:

[0091] S411: Match each of the goods order information with the association rule to obtain the target cultural event factor of each of the goods order information;

[0092] S412: Input the goods order information into the preset customs clearance time prediction model to obtain the baseline customs clearance time under the influence of no cultural events;

[0093] S413: Based on the target cultural event factor, the baseline clearance time is corrected to generate a clearance time window that includes the earliest predicted clearance time window and the latest predicted clearance time window.

[0094] As described in step S411 above, each of the goods order information is matched with the association rules to obtain the target cultural event factors for each goods order information. These association rules are reliable patterns extracted from cultural event-related data and historical customs clearance operation logs based on a large language model. Cultural event-related data includes, but is not limited to, holiday calendars, event schedules, and news event data, obtained through public APIs or databases. Through the matching process, the system identifies the target cultural event factors affecting specific goods orders, including specific holidays, local events, or other short-term cultural events. For example, if the destination of a goods order happens to be affected by a cultural event that hinders customs clearance operations, such as a local holiday, the system considers this a key factor that can affect the customs clearance time of the order. The cultural event factor is specifically the influence weight of the cultural event on the customs clearance operation, obtained through historical data regression analysis.

[0095] As described in step S412 above, the goods order information is input into a preset customs clearance time prediction model to obtain a baseline customs clearance time under the influence of no cultural events. This customs clearance time prediction model is usually built based on historical data, with the aim of providing a baseline customs clearance time unaffected by current cultural events. The customs clearance time prediction model is a regression model or time series model trained based on historical customs clearance data. This baseline customs clearance time is crucial because it provides a clear starting point for subsequent time window adjustments. The prediction model may employ various algorithms, such as regression models, time series analysis, or machine learning methods, to ensure that the customs clearance time prediction is as accurate as possible.

[0096] As described in step S413 above, the baseline clearance time is adjusted based on the target cultural event factor to generate a clearance time window that includes the earliest predicted clearance time window and the latest predicted clearance time window. This adjustment process typically involves applying the impact weight related to a specific cultural event to the baseline time. For example, if the target cultural event factor points to a holiday that will lead to a reduction in the number of staff in relevant institutions, the system may increase the baseline clearance time by several hours or days to reflect this reduction in human resources. Through this adjustment, the system generates a specific predicted clearance time window, which includes two important parameters: the earliest predicted clearance time and the latest predicted clearance time. The earliest predicted clearance time represents the time when the goods can be cleared under the current conditions and if everything goes smoothly; while the latest predicted clearance time represents the time when the goods can still be cleared even if the maximum delay caused by the cultural event is taken into account. This two-way time window provides logistics managers with a certain degree of flexibility, which helps to conduct comprehensive risk assessment and decision-making when formulating and adjusting logistics schedules, thereby improving overall clearance efficiency.

[0097] In one embodiment, step S2, which involves inputting the cultural event-related data and historical customs clearance operation logs into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations, includes:

[0098] S201: Extract abnormal customs clearance events such as customs clearance delays and increased inspection rates that occurred during historical and cultural events from the historical customs clearance operation log using a preset large language model;

[0099] S202: Analyze the cultural event-related data using the large language model to identify event characteristics that are strongly correlated with the abnormal customs clearance event;

[0100] S203: Associate the event features with customs clearance operation parameters to generate association rules with the event features as input and the expected customs clearance impact as output.

[0101] As described in step S201 above, a pre-defined large language model is used to extract abnormal customs clearance events, such as customs clearance delays and increased inspection rates, that occurred during historical and cultural events from the historical customs clearance operation logs. This large language model possesses powerful natural language processing and pattern recognition capabilities, enabling it to extract and identify anomalies such as customs clearance delays and changes in inspection rates related to historical and cultural events from massive amounts of data. First, the system compares each record in the customs clearance operation log with known historical and cultural events, filtering out those that exhibit significant anomalies in customs clearance operations during specific events. For example, during a country's traditional festivals or major events, customs clearance delays may increase significantly, and inspection rates may rise sharply.

[0102] As described in step S202 above, the system analyzes the cultural event-related data using the large language model to identify event features strongly correlated with the abnormal customs clearance events. Leveraging the capabilities of the large language model, the system can extract potential features from multi-dimensional data of cultural events (such as event type, time, scale of participation, and social impact). For example, during festivals, increased participation, media exposure, or temporary adjustments to local regulations can directly impact the customs clearance process. Based on abnormal events identified in historical customs clearance logs, the system uses algorithms to calculate the correlation between various cultural event features and customs clearance performance. The generated event features not only provide specific data related to changes in customs clearance delays and inspection rates but also provide important context for subsequent association rule generation. The correlation strength between event features and customs clearance anomalies is determined using Pearson correlation coefficients or machine learning feature importance scores. Then, a correlation strength threshold is set, for example, 0.8, and event features exceeding this threshold are considered strongly correlated event features.

[0103] As described in step S203 above, the event features are mapped to customs clearance operation parameters to generate association rules that take the event features as input and the expected customs clearance impact as output. A direct association will be established between customs clearance operation-related parameters (such as clearance time, inspection rate, and customs clearance convenience) and identified event features (such as staffing during holidays and policy adjustments). This process may include the application of statistical analysis or machine learning algorithms to ensure that the generated association rules are operable and have high confidence. The generated rules can be defined as "if-then" type relationships, such as "if during traditional holidays, an increase in the inspection rate is expected to increase clearance time." These association rules will provide important basis for subsequent customs clearance timeliness prediction and optimization decisions, enabling the system to flexibly adjust relevant strategies based on the characteristics of cultural events in future logistics operations to improve overall customs clearance efficiency.

[0104] In one embodiment, after step S6, which involves collaborative decision-making through a multi-objective optimization strategy in the mathematical model to hierarchically schedule logistics for each of the goods order information, the method further includes:

[0105] S701: Clear customs for each cargo order in the logistics order information set according to the hierarchical logistics scheduling scheme;

[0106] S702: Real-time acquisition of the actual customs clearance progress of each of the aforementioned goods orders;

[0107] S703: Determine whether the deviation between the actual customs clearance progress and the theoretical customs clearance progress of the tiered logistics schedule is greater than a preset threshold.

[0108] S704: When the deviation between the actual customs clearance progress and the theoretical customs clearance progress exceeds a preset threshold, obtain the set of target orders that have not yet been cleared.

[0109] S705: Reschedule the goods orders in the target order set according to the mathematical model.

[0110] As described in step S701 above, customs clearance is performed on each cargo order in the logistics order information set according to the tiered logistics scheduling scheme. The tiered logistics scheduling scheme has been divided into different levels according to cargo category, destination, transportation priority, etc., to optimize customs clearance resources and reduce transportation costs. During this process, the system coordinates various relevant units and links, including relevant agencies, freight forwarders, and warehousing facilities, to ensure that each cargo order passes customs clearance smoothly according to the optimized schedule. For example, it integrates with the customs clearance system through a RESTful API to obtain real-time customs clearance progress. During the customs clearance process, the status of each order is continuously monitored to detect any abnormal situations affecting the progress, such as inspection, fee issues, or other unforeseen delays.

[0111] As described in step S702 above, the actual customs clearance progress of each of the aforementioned goods orders is obtained in real time. This process may involve obtaining real-time customs clearance progress information through an API interface, such as completed procedures, pending items, the status of inspections, or possible reasons for delays. Real-time acquisition of customs clearance progress is crucial, as it helps managers understand whether the customs clearance process is progressing as expected. If there are deviations in the actual progress, the system will react promptly, facilitating further countermeasures. Furthermore, this information not only helps complete the customs clearance of the current order but also provides an important basis for future decisions, improving the scientific nature of time prediction and scheduling decisions for subsequent orders.

[0112] As described in step S703 above, the system determines whether the deviation between the actual customs clearance progress and the theoretical customs clearance progress of the tiered logistics schedule exceeds a preset threshold. The theoretical customs clearance progress is the expected completion time based on a previously preset timetable, taking into account cultural events, regulations, and other factors. By comparing these two, the system can clearly identify whether the actual customs clearance progress meets expectations. If the deviation exceeds the preset threshold, the system will determine that measures need to be taken to avoid exceeding the acceptable range and causing more serious consequences (such as cargo delays, customer complaints, etc.).

[0113] As described in step S704 above, when the deviation between the actual customs clearance progress and the theoretical customs clearance progress exceeds a preset threshold, a set of target orders that have not yet been cleared is obtained. These orders may be logistics orders that have failed to be cleared in a timely manner according to the tiered logistics scheduling plan due to various reasons. During this process, the system will automatically extract the information of the goods orders that have not been cleared, including the specific data of each order, the relevant responsible unit, the current status, etc. Analyzing the characteristics and current status of these orders can help managers understand the reasons for the delays, such as regulatory issues, order processing errors, or the impact of cultural events.

[0114] As described in step S705 above, the goods orders in the target order set are rescheduled according to the mathematical model. The model reconsiders the priority and constraints of these orders in the new business environment, which may include actual customs clearance progress, the impact of new time windows of cultural events, changes in regulations, or dynamic changes in other resources. By comprehensively considering these factors, a new scheduling scheme is generated to ensure that all outstanding customs orders can be processed within a reasonable time. Through this adjustment, the system can not only improve the efficiency of outstanding customs orders but also optimize the overall logistics operation, better adapt to the real-time changing market environment, and improve customer satisfaction and business reliability. If the customs clearance progress deviation exceeds a threshold, rescheduling is performed; if rejection feedback is received, the goods classification is adjusted first.

[0115] In one embodiment, after step S6, which involves collaborative decision-making through a multi-objective optimization strategy in the mathematical model to hierarchically schedule logistics for each of the goods order information, the method further includes:

[0116] S711: Based on the scheduling results of each goods order, send scheduling confirmation instructions to each relevant terminal;

[0117] S712: Receive feedback information from each of the relevant terminals;

[0118] S713: Determine whether each feedback message is a rejection;

[0119] S714: If the feedback information is rejection, then obtain the corresponding target goods order information;

[0120] S715: Adjust the cargo level information in the target cargo order information and re-classify and schedule the logistics for each cargo order information.

[0121] As described in step S711 above, scheduling confirmation instructions are sent to relevant terminals based on the scheduling results of each cargo order. These terminals may include freight forwarders, warehouse managers, customs clearance personnel, and drivers. Each instruction will contain detailed order information, such as estimated arrival time, cargo type, destination, and confirmation of whether processing can proceed according to the schedule. This process is crucial for logistics scheduling, ensuring that all relevant parties are aware of and agree to the logistics timeline, thus improving synergy between different stages.

[0122] As described in step S712 above, feedback information is received from each of the relevant terminals. Feedback information may include responses confirming the schedule, such as "confirmed," "temporarily unable to confirm," or "rejected." Feedback may also include information on changes in the cargo status, such as delays during transport, customs clearance issues, or storage capacity problems. By receiving this feedback in real time, the system can obtain the latest information related to cargo orders, providing crucial information for subsequent decision-making.

[0123] As described in step S713 above, determine whether each feedback message is a rejection. That is, identify and extract records containing "rejection", "unable to satisfy" or similar information from the feedback from multiple terminals.

[0124] As described in step S714 above, if the feedback information is a rejection, the corresponding target goods order information is obtained. The purpose of obtaining this information is to conduct in-depth analysis of the reasons for the rejection and to investigate key variables affecting order execution. For example, the system may query the goods' grade, destination, characteristics, or carrying capacity. In addition, the system may also determine at this stage whether the target goods order is affected by cultural events or policy adjustments and decide on further adjustments. Through focused analysis of the target goods order, the system can quickly respond to scheduling changes and formulate response strategies to ensure that other unaffected orders can be executed smoothly according to the established plan, thereby reducing overall operational risks.

[0125] As described in step S715 above, the cargo level information in the target cargo order information is adjusted, and the logistics scheduling of each cargo order information is re-tiered. By adjusting the cargo level in a timely manner, the system can improve the flexibility and adaptability of the entire logistics process. Then, in the re-evaluation phase, the system will use the established mathematical model and optimization strategy to re-tier the logistics scheduling of the adjusted cargo orders. The goal of the new scheduling is to ensure that core orders are prioritized while also taking into account overall operational efficiency. Through this process, the system can dynamically adjust the scheduling plan according to the actual situation, ensuring that even if rejection occurs during the order confirmation process, a solution can be found quickly, effectively reducing the risk of cargo delays and achieving higher-quality logistics services. If the customs clearance progress deviation exceeds the threshold, re-scheduling is executed; if rejection feedback is received, the cargo level is adjusted first.

[0126] Reference Figure 3 The present invention also provides a logistics scheduling device based on cultural events, the device comprising:

[0127] The historical customs clearance operation log acquisition module 902 is used to acquire data related to cultural events and historical customs clearance operation logs in real time.

[0128] The association rule generation module 904 is used to input the cultural event-related data and historical customs clearance operation logs into a preset large language model for parsing, so as to generate association rules between cultural events and customs clearance operations.

[0129] The logistics order information set acquisition module 906 is used to acquire a logistics order information set to be processed; wherein the logistics order information set contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information.

[0130] The predicted customs clearance time window generation module 908 is used to generate a predicted customs clearance time window for each of the cargo order information based on the association rules and the cargo order information.

[0131] The input module 910 is used to input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo order information into a preset mathematical model;

[0132] The hierarchical logistics scheduling module 912 is used to perform collaborative decision-making through a multi-objective optimization strategy in the mathematical model, and to perform hierarchical logistics scheduling for each of the goods order information.

[0133] In one embodiment, the logistics scheduling device based on cultural events further includes:

[0134] The target area determination module is used to determine the corresponding target area based on the destination of each goods order in the logistics order information set;

[0135] The spatiotemporal tag acquisition module is used to acquire regulatory information for each of the target regions and the spatiotemporal tags of the regulatory information.

[0136] The mathematical model acquisition module is used to map the various regulatory information and the spatiotemporal labels to a preset mathematical space, thereby forming multiple constraints in the preset mathematical space and obtaining the mathematical model.

[0137] In one embodiment, the logistics scheduling device based on cultural events further includes:

[0138] An introduction module is used to introduce soft time window constraints into the mathematical model, which adds penalty costs to scheduling schemes that exceed the predicted customs clearance time window, thereby obtaining an optimized mathematical model.

[0139] In one embodiment, the predicted customs clearance time window generation module 908 includes:

[0140] The matching submodule is used to match each of the goods order information with the association rules to obtain the target cultural event factors of each of the goods order information;

[0141] The input submodule is used to input the goods order information into a preset customs clearance time prediction model to obtain the baseline customs clearance time under the influence of no cultural events.

[0142] The correction submodule is used to correct the baseline customs clearance time based on the target cultural event factor, and generate a customs clearance time window that includes the earliest predicted customs clearance time window and the latest predicted customs clearance time window.

[0143] In one embodiment, the association rule generation module 904 includes:

[0144] The extraction submodule is used to extract abnormal customs clearance events such as customs clearance delays and increased inspection rates that occurred during the historical and cultural events in the historical customs clearance operation logs using a preset large language model.

[0145] The identification submodule is used to analyze the cultural event-related data using the large language model and identify event features that are strongly correlated with the abnormal customs clearance event.

[0146] The mapping submodule is used to associate and map the event features with customs clearance operation parameters to generate association rules with the event features as input and the expected customs clearance impact as output.

[0147] In one embodiment, the logistics scheduling device based on cultural events further includes:

[0148] The customs clearance module is used to clear customs for each cargo order in the logistics order information set according to the hierarchical logistics scheduling scheme;

[0149] The real-time customs clearance progress acquisition module is used to acquire the real-time customs clearance progress of each of the aforementioned goods orders.

[0150] The first judgment module is used to determine whether the deviation between the actual customs clearance progress and the theoretical customs clearance progress of the tiered logistics schedule is greater than a preset threshold.

[0151] The target order set acquisition module is used to acquire the target order set that has not yet been cleared when the deviation between the actual clearance progress and the theoretical clearance progress exceeds a preset threshold.

[0152] The scheduling module is used to reschedule the goods orders in the target order set according to the mathematical model.

[0153] In one embodiment, the logistics scheduling device based on cultural events further includes:

[0154] The instruction confirmation module is used to send scheduling confirmation instructions to relevant terminals based on the scheduling results of each goods order.

[0155] The feedback information receiving module is used to receive feedback information from each of the relevant terminals;

[0156] The second judgment module is used to determine whether each feedback message is a rejection.

[0157] The target goods order information acquisition module is used to acquire the corresponding target goods order information if the feedback information is rejection.

[0158] The adjustment module is used to adjust the cargo level information in the target cargo order information and re-arrange the hierarchical logistics for each cargo order information.

[0159] Figure 4An internal structural diagram of an electronic device in one embodiment is shown. This electronic device can specifically be a terminal or a server, and more specifically, a computer device. Figure 4 As shown, the electronic device includes a processor, a memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a logistics scheduling method based on cultural events. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement a logistics scheduling method based on cultural events. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0160] In one embodiment, an electronic device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0161] Real-time acquisition of data related to cultural events and historical customs clearance operation logs;

[0162] The data related to the cultural events and the historical customs clearance operation logs are input into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations;

[0163] Obtain a set of logistics order information to be processed; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information.

[0164] Based on the association rules and the cargo order information, a predicted customs clearance time window is generated for each cargo order information;

[0165] Input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model;

[0166] In the mathematical model, a multi-objective optimization strategy is used for collaborative decision-making, and the logistics scheduling of each of the goods order information is carried out in a hierarchical manner.

[0167] By introducing a large language model to analyze cultural events, we can gain a deep understanding of their actual impact on customs clearance operations. By quantifying cultural event factors into association rules, we can anticipate and respond to the risks of customs clearance delays or process changes caused by these events. This allows for multi-objective optimization of scheduling, resulting in a tiered logistics scheduling solution. This effectively avoids congestion of high-priority goods during the peak impact period of events, and achieves dynamic matching of logistics resources with the operational capabilities of relevant institutions. This reduces the risk of cargo delays, destination congestion, and cargo damage caused by scheduling mismatches at the source.

[0168] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following steps:

[0169] Real-time acquisition of data related to cultural events and historical customs clearance operation logs;

[0170] The data related to the cultural events and the historical customs clearance operation logs are input into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations;

[0171] Obtain a set of logistics order information to be processed; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information.

[0172] Based on the association rules and the cargo order information, a predicted customs clearance time window is generated for each cargo order information;

[0173] Input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model;

[0174] In the mathematical model, a multi-objective optimization strategy is used for collaborative decision-making, and the logistics scheduling of each of the goods order information is carried out in a hierarchical manner.

[0175] By introducing a large language model to analyze cultural events, we can gain a deep understanding of their actual impact on customs clearance operations. By quantifying cultural event factors into association rules, we can anticipate and respond to the risks of customs clearance delays or process changes caused by these events. This allows for multi-objective optimization of scheduling, resulting in a tiered logistics scheduling solution. This effectively avoids congestion of high-priority goods during the peak impact period of events, and achieves dynamic matching of logistics resources with the operational capabilities of relevant institutions. This reduces the risk of cargo delays, destination congestion, and cargo damage caused by scheduling mismatches at the source.

[0176] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0177] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0178] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A logistics scheduling method based on cultural events, characterized in that, The method includes: Real-time acquisition of data related to cultural events and historical customs clearance operation logs; The data related to the cultural events and the historical customs clearance operation logs are input into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations; Obtain a set of logistics order information to be processed; wherein the set of logistics order information contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information. Based on the association rules and the cargo order information, a predicted customs clearance time window is generated for each cargo order information; Based on the destination of each cargo order in the logistics order information set, the corresponding target area is determined; Obtain regulatory information for each of the target regions and the spatiotemporal labels of the regulatory information; The various regulatory information and the spatiotemporal labels are mapped to a preset mathematical space to form multiple constraints in the preset mathematical space, thereby obtaining a mathematical model; A soft time window constraint is introduced into the mathematical model to increase the penalty cost for scheduling schemes that exceed the predicted customs clearance time window, thereby obtaining the optimized mathematical model. Input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model; In the mathematical model, a multi-objective optimization strategy is used for collaborative decision-making, and the logistics scheduling of each of the goods order information is carried out in a hierarchical manner.

2. The logistics scheduling method based on cultural events according to claim 1, characterized in that, The step of generating a predicted customs clearance time window for each cargo order based on the association rules and the cargo order information includes: Each of the aforementioned goods order information is matched with the association rule to obtain the target cultural event factor for each of the aforementioned goods order information; The cargo order information is input into a preset customs clearance time prediction model to obtain the baseline customs clearance time under the influence of no cultural events. Based on the target cultural event factors, the baseline customs clearance time is corrected to generate a customs clearance time window that includes the earliest predicted customs clearance time window and the latest predicted customs clearance time window.

3. The logistics scheduling method based on cultural events according to claim 1, characterized in that, The step of inputting the cultural event-related data and historical customs clearance operation logs into a preset large language model for parsing to generate association rules between cultural events and customs clearance operations includes: The abnormal customs clearance events, such as customs clearance delays and increased inspection rates, that occurred during historical and cultural events are extracted from the historical customs clearance operation logs using a pre-defined large language model. By analyzing the cultural event-related data using the large language model, event characteristics that are strongly correlated with the abnormal customs clearance event are identified; The event features are associated with customs clearance operation parameters to generate association rules that take the event features as input and the expected customs clearance impact as output.

4. The logistics scheduling method based on cultural events according to claim 1, characterized in that, After the step of collaborative decision-making through a multi-objective optimization strategy in the mathematical model to hierarchically schedule logistics for each of the goods order information, the method further includes: Customs clearance is performed on each cargo order in the aforementioned logistics order information set according to the tiered logistics scheduling scheme; Real-time acquisition of the actual customs clearance progress of each of the aforementioned goods orders; Determine whether the deviation between the actual customs clearance progress and the theoretical customs clearance progress of the tiered logistics schedule is greater than a preset threshold. When the deviation between the actual customs clearance progress and the theoretical customs clearance progress exceeds a preset threshold, the set of target orders that have not yet been cleared is obtained. The goods orders in the target order set are rescheduled according to the mathematical model.

5. The logistics scheduling method based on cultural events according to claim 1, characterized in that, After the step of collaborative decision-making through a multi-objective optimization strategy in the mathematical model to hierarchically schedule logistics for each of the goods order information, the method further includes: Based on the scheduling results of each goods order, a scheduling confirmation instruction is sent to each relevant terminal; Receive feedback information from each of the relevant terminals; Determine whether each feedback message indicates a rejection; If the feedback is a rejection, then obtain the corresponding target goods order information; The cargo level information in the target cargo order information is adjusted, and the logistics scheduling of each cargo order information is re-arranged according to its level.

6. A logistics scheduling device based on cultural events, characterized in that, The device includes: The historical customs clearance operation log acquisition module is used to acquire data related to cultural events and historical customs clearance operation logs in real time. The association rule generation module is used to input the cultural event-related data and historical customs clearance operation logs into a preset large language model for parsing, so as to generate association rules between cultural events and customs clearance operations. The logistics order information set acquisition module is used to acquire a set of logistics order information to be processed; wherein the logistics order information set contains multiple goods order information, and each goods order information includes at least goods category, destination and goods grade information. The predicted customs clearance time window generation module is used to generate a predicted customs clearance time window for each of the cargo order information based on the association rules and the cargo order information. The target area determination module is used to determine the corresponding target area based on the destination of each goods order in the logistics order information set; The spatiotemporal tag acquisition module is used to acquire regulatory information for each of the target regions and the spatiotemporal tags of the regulatory information. The mathematical model acquisition module is used to map each of the aforementioned regulatory information and the spatiotemporal labels to a preset mathematical space, thereby forming multiple constraints in the preset mathematical space and obtaining a mathematical model. An introduction module is used to introduce soft time window constraints into the mathematical model, adding penalty costs to scheduling schemes that exceed the predicted customs clearance time window, thereby obtaining an optimized mathematical model. The input module is used to input the predicted customs clearance time window and the cargo order information of each of the aforementioned cargo orders into a preset mathematical model; The hierarchical logistics scheduling module is used to make collaborative decisions in the mathematical model through multi-objective optimization strategies, and to perform hierarchical logistics scheduling for each of the goods order information.

7. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, causes the processor to perform the steps of the logistics scheduling method based on cultural events as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, The device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the logistics scheduling method based on cultural events as described in any one of claims 1 to 5.

Images