Multi-dimensional decision-making cross-border path scheme generation method and device, equipment and medium

Abstract

The invention relates to the technical field of multi-dimensional decision-making cross-border path scheme generation, and discloses a multi-dimensional decision-making cross-border path scheme generation method and device, equipment and a medium, and the method comprises the steps: obtaining order data of a to-be-delivered order, analyzing the information of a plurality of preset dimensions, setting a weight for each dimension, and generating a multi-dimensional decision-making cross-border path scheme; and generating a target path optimization engine to generate an optimized path, and generating a cross-border path optimization scheme of the to-be-delivered order based on the optimized path. The method has the beneficial effects that the real-time performance and accuracy of cross-border scheme generation are improved, the problem of single optimization dimension in the existing cross-border distribution scheme generation is effectively solved, the method adapts to dynamically changing market requirements, the efficiency of cross-border logistics is improved, the distribution cost is reduced, the satisfaction degree of users is improved, and in addition, the user experience is improved. And the scheme generation is more intelligent and personalized by integrating a multi-dimensional consideration mode.

Description

Technical Field

[0001] This invention relates to the field of cross-border path generation technology for multidimensional decision-making, and in particular to a method, apparatus, device, and medium for generating cross-border path solutions for multidimensional decision-making. Background Technology

[0002] With globalization and the booming development of cross-border e-commerce, the demand for related logistics and delivery has also increased. Traditional cross-border solution development often focuses on a specific dimension, such as cost, time, or security, lacking a comprehensive consideration of multiple dimensions when generating delivery solutions. This often leads to limitations in practice. For example, some solutions may only pursue the lowest transportation cost, neglecting the necessity of delivery time; or they may choose high-cost logistics methods to ensure fast delivery, failing to balance the relationships between various dimensions. This singular optimization approach cannot fully meet the multiple needs of users, resulting in insufficient flexibility and adaptability of the solutions, which in turn affects delivery efficiency and user satisfaction. Summary of the Invention

[0003] Therefore, it is necessary to propose a method, apparatus, equipment, and medium for generating cross-border path schemes based on multidimensional decision-making, which addresses the existing problem of generating cross-border path schemes based on multidimensional decision-making.

[0004] A method for generating cross-border route solutions through multi-dimensional decision-making, the method comprising: Retrieve order data for orders awaiting delivery; The order data is parsed to obtain dimensional information corresponding to multiple preset dimensions; Dimension weights are set for the corresponding preset dimensions based on the dimensional information; The preset path optimization engine is weighted based on the dimensional weights of each preset dimension to obtain the target path optimization engine; The optimized path for the order data is obtained through the target path optimization engine; Based on the optimized path, a cross-border route optimization scheme for the orders to be delivered is generated.

[0005] Furthermore, before the step of setting weights for the preset path optimization engine based on the dimensional weights of each preset dimension to obtain the target path optimization engine, the method further includes: Obtain multiple target areas related to the order to be delivered; Obtain transit cost data for each of the target areas; A rule-based sub-engine for generating cost calculations is generated based on the various transit cost data. The rule sub-engine is used as a dimensional constraint in the preset path optimization engine.

[0006] Furthermore, after the step of generating the rule sub-engine for cost based on each of the transit cost data, the method further includes: The update status of transit cost data for each of the target areas is monitored through a pre-set API cluster. If transit cost data has been updated, then retrieve the updated transit cost data. Compare the updated transit cost data with the transit cost data before the update; Determine whether the comparison result has reached the preset comparison value; If the preset comparison value is reached, the rule sub-engine is updated in real time based on the updated transit cost data.

[0007] Furthermore, after the step of obtaining transit cost data for each of the target areas, the method further includes: Obtain the data type for each of the aforementioned transit cost data; Obtain the corresponding standardized processing method based on the data type; The transit cost data of the corresponding data type is processed according to the standardization processing method to obtain standardized transit cost data.

[0008] Furthermore, the step of setting the dimension weights corresponding to the preset dimensions based on the dimension information includes: When the preset dimension is a timeliness dimension, determine whether the delivery time contained in the dimension information corresponding to the timeliness dimension is a preset time period; If it is a preset time period, the weight of the timeliness dimension will be set to the first preset weight value.

[0009] Further, the step of setting the dimension weights of the corresponding preset dimensions based on the dimension information includes: When the preset dimension is a compliance dimension, determine whether the product information contained in the dimension information corresponding to the compliance dimension is a sensitive product; If the product is sensitive, the weight of the compliance dimension will be set to the second preset weight value.

[0010] Furthermore, the method is characterized in that, after the step of generating the cross-border route optimization scheme for the order to be delivered based on the optimized route, it further includes: Obtain the multiple cross-border regions involved in the cross-border route optimization scheme; Obtain the declaration templates corresponding to each of the aforementioned cross-border regions; The cross-border information corresponding to each cross-border region in the cross-border route optimization scheme is filled into the corresponding declaration template to obtain the declaration text for each cross-border region.

[0011] A multi-dimensional decision-making cross-border route generation device, the device comprising: The order data acquisition module is used to acquire order data for orders to be delivered. The dimension information acquisition module is used to parse the order data to obtain dimension information corresponding to multiple preset dimensions. The dimension weight setting module is used to set the dimension weight of the corresponding preset dimension based on the dimension information; The target path optimization engine acquisition module is used to set weights for the preset path optimization engine based on the dimension weights of each preset dimension in order to obtain the target path optimization engine. The optimized path acquisition module is used to acquire the optimized path of the order data through the target path optimization engine. The cross-border optimization solution generation module is used to generate a cross-border route optimization solution for the order to be delivered based on the optimized route.

[0012] 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: Retrieve order data for orders awaiting delivery; The order data is parsed to obtain dimensional information corresponding to multiple preset dimensions; Dimension weights are set for the corresponding preset dimensions based on the dimensional information; The preset path optimization engine is weighted based on the dimensional weights of each preset dimension to obtain the target path optimization engine; The optimized path for the order data is obtained through the target path optimization engine; Based on the optimized path, a cross-border route optimization scheme for the orders to be delivered is generated.

[0013] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps: Retrieve order data for orders awaiting delivery; The order data is parsed to obtain dimensional information corresponding to multiple preset dimensions; Dimension weights are set for the corresponding preset dimensions based on the dimensional information; The preset path optimization engine is weighted based on the dimensional weights of each preset dimension to obtain the target path optimization engine; The optimized path for the order data is obtained through the target path optimization engine; Based on the optimized path, a cross-border route optimization scheme for the orders to be delivered is generated.

[0014] The beneficial effects of this invention are as follows: By acquiring order data of orders to be delivered, parsing information from multiple preset dimensions, assigning weights to each dimension, generating a target path optimization engine to generate optimized paths, and generating cross-border path optimization schemes for the orders to be delivered based on the optimized paths. This improves the real-time performance and accuracy of cross-border scheme generation, effectively solves the problem of single optimization dimensions in existing cross-border delivery scheme generation, adapts to dynamically changing market demands, improves the efficiency of cross-border logistics, reduces delivery costs, and increases user satisfaction. Furthermore, the comprehensive multi-dimensional consideration makes scheme generation more intelligent and personalized. Attached Figure Description

[0015] 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.

[0016] in: Figure 1 This is an application environment diagram of a cross-border path scheme generation method for multi-dimensional decision-making in one embodiment; Figure 2 A flowchart of a cross-border path scheme generation method for multi-dimensional decision-making in one embodiment; Figure 3 This is a structural block diagram of a cross-border path scheme generation device for multi-dimensional decision-making in one embodiment; Figure 4 This is a structural block diagram of an electronic device in one embodiment. Detailed Implementation

[0017] 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.

[0018] Figure 1 Generate an application environment graph for cross-border path schemes involving multi-dimensional decision-making in one embodiment. (Refer to...) Figure 1This multi-dimensional decision-making method for generating cross-border route solutions is applied to a multi-dimensional decision-making system for generating cross-border route solutions. 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; a mobile terminal can be at least one of a mobile phone, tablet, or laptop. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to acquire order data for orders to be delivered, and the server 120 is used to generate cross-border route optimization solutions for these orders.

[0019] like Figure 2 As shown, in one embodiment, a method for generating cross-border path schemes based on multi-dimensional decision-making is provided. This method can be applied to both terminals and servers; this embodiment illustrates its application to a terminal. The method specifically includes the following steps: S1: Retrieve order data for orders awaiting delivery; S2: Parse the order data to obtain dimension information corresponding to multiple preset dimensions; S3: Set the dimension weights for the corresponding preset dimensions based on the dimension information; S4: Set weights for the preset path optimization engine based on the dimensional weights of each preset dimension to obtain the target path optimization engine; S5: Obtain the optimized path of the order data through the target path optimization engine; S6: Generate a cross-border route optimization scheme for the orders to be delivered based on the optimized route.

[0020] In cross-border trade, fees vary across regions due to changes in regulations, market demand, and transportation costs. Fees are multifaceted; therefore, when generating optimized solutions for cross-border orders, these diverse fees must be comprehensively considered to ensure the final cost adaptability and reasonableness. Simultaneously, cross-border orders typically have strong time-sensitivity requirements, and consumer expectations are increasingly high. Therefore, when developing delivery solutions, in addition to considering cost factors, timeliness has become a key dimension in the decision-making process. For example, while choosing fast delivery may increase costs, it significantly improves user experience and satisfaction. In this context, it is necessary to dynamically weigh various preset dimensions, including timeliness, cost, security, and compliance, to ensure that the developed solution meets customer needs while controlling logistics costs to achieve corporate profits.

[0021] As described in step S1 above, order data for orders awaiting delivery is obtained. Specifically, this can be received from users or transaction platforms. Order data typically includes key information such as recipient's name, address, contact information, product details, quantity, weight, volume, and delivery time requirements. Order data can be obtained through API interaction with the e-commerce platform or by reading from the backend system's database. It is crucial to ensure the accuracy and completeness of the data, as any omissions or errors may affect the quality of the final delivery plan. Furthermore, during the data acquisition process, the system can perform preliminary data cleaning, including format standardization and error correction, to improve the efficiency and accuracy of subsequent analysis.

[0022] As described in step S2 above, the order data is parsed to obtain dimensional information corresponding to multiple preset dimensions. These dimensions may include, but are not limited to, delivery costs, delivery timeliness, transportability, insurance requirements, product value, and destination logistics restrictions. In a specific embodiment, five preset dimensions are included: cost, timeliness requirements, compliance risks, green compliance, and cultural adaptation. In-depth analysis of order data helps identify specific delivery needs and potential challenges, such as the transportation of certain goods being subject to regulations in specific countries or regions. The parsing process involves natural language processing technology to identify and extract the structured information implicit in the text, or to use a rule engine to determine the applicability of each dimension. Specifically, it can be processed using an LLM model, which is a pre-trained large language model (such as the GPT series). By fine-tuning it to adapt to the order data parsing task, dimensional information is extracted. The order data to be parsed is input into the LLM model. Since the original data may contain various formats and structures, preliminary text preprocessing is required, including noise removal (such as redundant spaces, line breaks, etc.), standardization (such as date and number formatting), and converting the text into a format that the model can understand. This stage ensures data accuracy and consistency, making subsequent processing more efficient. After data processing, the LLM model performs in-depth analysis of the text to identify and extract key information. For example, in order text, the model can identify important fields such as product name, quantity, weight, value, recipient information, and address. Through contextual understanding, LLM can distinguish different types of products, handle complex descriptions, and maintain high accuracy during extraction. This process typically relies on training the model on a large-scale corpus, giving it powerful contextual understanding and information extraction capabilities. After extracting relevant information, LLM uses a discriminative mechanism to evaluate the applicability of this dimensional information. For example, by analyzing the extracted product information, LLM can determine whether certain products belong to sensitive product categories or assess whether related delivery times meet expected standards. At this point, the model performs logical reasoning or conditional judgments based on known compliance standards, cost structures, and background knowledge of market demand to ensure that the final generated solution meets business requirements. After the above processing, LLM generates structured data output, such as JSON or other standard data structures, to facilitate subsequent processing and storage. This output not only contains the extracted key information but also the applicability of each dimension and its related weight information. This structured data can be directly used in backend systems for data processing, optimization algorithms, and decision support.

[0023] As described in step S3 above, dimensional weights are set for the corresponding preset dimensions based on the dimensional information. In this step, weights are assigned to each preset dimension based on the dimensional information parsed in the previous step. The weights are set to reflect the importance of different dimensions in the overall delivery plan. This process typically relies on multiple factors, including corporate strategy, market demand, user preferences, and historical data analysis results. For example, if a user explicitly expresses a high level of concern about delivery speed, the weight of timeliness can be significantly higher than that of cost. Specifically, decision rules or models, such as the Analytic Hierarchy Process (AHP) or machine learning algorithms, can be used to determine the optimal dimensional weights. Adjusting the weights not only makes the system-generated plan more personalized but also enables a rapid response to complex business needs. Through reasonable weight allocation, the final generated plan can more accurately match the user's specific needs and improve user satisfaction.

[0024] As described in step S4 above, the preset path optimization engine is weighted based on the dimensional weights of each preset dimension to obtain the target path optimization engine. The preset path optimization engine is a basic optimization model, while the target path optimization engine is an instantiated engine adjusted by the weight settings. This step adjusts the preset path optimization engine by integrating the previously set dimensional weights to generate the target path optimization engine. The parameters of the optimization algorithm are dynamically adjusted according to the importance of each dimension, and the algorithm parameters of the preset path optimization engine are adjusted through weight adjustments to form the target path optimization engine. Specifically, the system can use different optimization algorithms, such as Dijkstra's algorithm, genetic algorithm, or particle swarm optimization, to calculate the optimal delivery route, and introduce the weights of each dimension during the route calculation process. The dimensional weights can be dynamically calculated using the AHP algorithm or neural network model to adapt to different order scenarios. This flexible adjustment ensures that the algorithm's output is not just the lowest-cost path, but the best path that comprehensively considers multiple factors such as timeliness and safety. In this way, the target path optimization engine can quickly find a dynamic solution suitable for the current order in a rapidly changing environment, improving the intelligence level of decision-making and ultimately enhancing the efficiency of cross-border delivery. The default path optimization engine is specifically an integer programming model. Integer programming (IP) is a special form of linear programming in which at least some or all of the decision variables are restricted to integer values.

[0025] As described in step S5 above, the optimized path for the order data is obtained through the target path optimization engine. Using the target path optimization engine, a practically feasible delivery path is generated. By combining the input order data with preset dimension weights, the optimization engine calculates multiple possible delivery paths based on an algorithm. The system evaluates the performance of each path in terms of cost, time, and feasibility to ultimately determine the optimal path. During this process, factors such as the effectiveness of logistics transshipment, the choice of transportation mode, and potential intermediate stops may also need to be considered. Based on the obtained optimized path, the system will be able to generate specific delivery strategies, such as selecting which logistics company and which transportation tools are needed.

[0026] As described in step S6 above, a cross-border route optimization plan for the order to be delivered is generated based on the optimized route. Based on the generated optimized route, a real-time cross-border delivery plan is created, including specific execution details such as delivery schedules, selected logistics service providers, transportation methods, and corresponding cost estimates. This plan aims to provide comprehensive information to all parties involved, facilitating coordination and cooperation during execution. When generating the plan, the system also considers potential risk factors and provides contingency plans to ensure timely adjustments in unforeseen circumstances. Furthermore, the generated cross-border route optimization plan typically requires real-time feedback on changes in user needs, enabling the plan to flexibly respond to various emergencies. In this way, the final generated plan not only possesses high adaptability and flexibility but also fully meets users' diverse needs for cross-border e-commerce delivery, ensuring improved user experience and increased satisfaction.

[0027] In one embodiment, before step S4, which involves setting weights for the preset path optimization engine based on the dimensional weights of each preset dimension to obtain the target path optimization engine, the method further includes: S301: Obtain multiple target areas related to the order to be delivered; S302: Obtain transit cost data for each of the target areas; S303: A rule sub-engine for generating cost based on the various transit cost data; S304: Use the rule sub-engine as a dimensional constraint in the preset path optimization engine.

[0028] As described in step S301 above, multiple target areas related to the order to be delivered are obtained. In this step, the system first identifies multiple target areas related to the order to be delivered. Target areas typically refer to different geographical locations where the goods ultimately need to be delivered. These areas can be countries, regions, or even specific cities or towns. To accurately obtain these target areas, the system relies on the delivery address information in the order data. Based on Geographic Information System (GIS) technology, these addresses can be parsed, and all related target areas can be further determined. In this process, not only is it necessary to accurately extract the customer's address, but address standardization and verification technologies may also be used to ensure the validity and accuracy of each address. In addition, when obtaining target areas, the system may also consider certain specific logistics restrictions, such as national or regional laws and regulations, as well as differences in market demand in different regions. This step is crucial for subsequent route optimization because it provides basic information for determining the complexity of the delivery route and the required resource allocation.

[0029] As described in step S302 above, transit cost data for each target region is obtained. It is necessary to acquire transit cost data related to each target region. This cost data typically includes expenses incurred by goods transiting through different regions, such as customs duties, transportation costs, handling fees, and insurance premiums. These costs vary depending on factors such as country, region, and delivery method, and may significantly affect the total delivery cost. To obtain this cost data, the system can reference external data sources, such as official websites of various countries, fee standards published by logistics companies, and historical order records. Simultaneously, the data acquisition process must focus on timeliness and accuracy, ensuring that the latest fee standards are used.

[0030] As described in step S303 above, a rule sub-engine for calculating costs is generated based on the various transit cost data. Based on the transit cost data from multiple target areas acquired previously, a rule sub-engine for calculating costs is constructed. The purpose of this engine is to integrate the transit cost data from different areas by setting a series of rules, and calculate the total transit cost accordingly. These rules may include logical judgments, weighted calculations, or conditional branches to handle cost estimations under different circumstances. For example, the system may determine whether special fees apply based on the nature of the goods (such as bulk commodities or perishable goods), or consider special policies such as tariff reductions when calculating cross-border transportation. By implementing an intelligent rule sub-engine, the system can flexibly respond to different order situations and quickly generate corresponding cost estimates. This mechanism not only improves the automation and accuracy of cost calculation but also provides a basis for subsequent route optimization, making the overall solution generation more efficient and reliable.

[0031] As described in step S304 above, the rule sub-engine is used as a dimensional constraint in the preset route optimization engine. The completed rule sub-engine will participate in the target route optimization process as a dimensional constraint in the preset route optimization engine. By considering cost as a key dimension of route optimization, the system can ensure that overall transportation costs are always taken into account when generating optimized routes. When searching for the optimal route, the optimization algorithm considers not only other dimensions such as transportation timeliness and reliability, but also cost as an indispensable constraint, thereby ensuring the economic effectiveness of the generated solution. This choice can be achieved by forcing the optimization algorithm to avoid selecting excessively expensive routes during route calculation, or by automatically adjusting the route selection to balance the relationship between time and cost. The newly introduced dimensional constraint enriches the functionality of the optimization engine, enabling it to find the optimal solution under complex constraints. This design helps improve the delivery efficiency and cost-effectiveness of all orders, laying the foundation for optimizing cross-border logistics management for enterprises.

[0032] In one embodiment, after step S303 of generating the rule sub-engine for cost calculation based on each of the transit cost data, the method further includes: S3041: Monitor the update status of transit cost data for each of the target areas through a preset API cluster; S3042: If transit cost data has been updated, then obtain the updated transit cost data; S3043: Compare the updated transit cost data with the transit cost data before the update; S3044: Determine whether the comparison result has reached the preset comparison value; S3045: If the preset comparison value is reached, the rule sub-engine is updated in real time based on the updated transit cost data.

[0033] As described in step S3041 above, the update status of transit cost data for each target area is monitored through a preset API cluster. A preset API cluster is set up to monitor the real-time updates of transit cost data for each target area. These API interfaces come from multiple logistics service providers, industry associations, etc., allowing the system to obtain the latest cost information. The monitoring mechanism design ensures the timeliness and accuracy of the data, avoiding calculation errors in the rule sub-engine due to information delays or inaccuracies. By using key parameters such as the update frequency and the stability of the data source, the update logic can be optimized to maximize the acquisition of accurate and up-to-date data.

[0034] As described in step S3042 above, if transit cost data is updated, the updated transit cost data is obtained. The system monitors the transit cost data for the target area; if updates are detected, the system automatically retrieves the updated transit cost data, ensuring that the system always uses the latest cost information for calculations, thereby improving the accuracy and timeliness of cost estimation. The method of obtaining updated data also relies on the previously defined API interface. The system sends a request to extract the latest cost information. Updated data is only adopted after the cost is accurate and verified, ensuring data consistency and reliability. In practice, this step may also need to handle network latency, response timeouts, and other issues; therefore, an effective exception handling mechanism is crucial. For example, when real-time data is unavailable, the system can use the latest available data as a backup value or make inferences based on historical data trends.

[0035] As described in step S3043 above, the updated transit cost data is compared with the transit cost data before the update. A detailed comparison is performed between the acquired updated and unupdated transit cost data, involving several key parameters, including changes in cost values, adjustments to exemption policies, and cost differences between regions. Through this comparison, the system can identify which target areas have experienced significant changes in transit costs and which areas have remained stable. The comparison results provide important information for subsequent decision-making. If the transit cost in a certain area increases significantly, it may be necessary to reassess the delivery strategy for that area or consider alternative routes when generating delivery plans. Conversely, if the cost decreases, that area can be prioritized for business expansion in the plan. Through systematic data comparison, users can understand the actual impact of cost changes, helping businesses develop more effective strategies to cope with market changes.

[0036] As described in step S3044 above, it is determined whether the comparison result has reached a preset comparison value. The preset comparison value is typically a quantifiable threshold that determines whether a change in transit cost data is significant enough to trigger an update of the rule sub-engine. For example, the comparison value might be set as a percentage change or a specific change in cost amount. The preset comparison value is dynamically adjusted based on historical data statistics and business rules; specifically, it could be set to a 5% change in transit costs. Through this judgment logic, the system can automatically identify updates that truly require attention, thereby avoiding frequent rule adjustments due to minor changes, which increases computational complexity and system burden. If the comparison result shows that the change exceeds the preset threshold, this indicates that the change in transit costs has a direct impact on business decisions, and the system will proceed to the next step, initiating the rule sub-engine update process.

[0037] As described in step S3045 above, if a preset comparison value is reached, the rule sub-engine is updated in real time based on the updated transit cost data. Once the judgment result reaches the preset comparison value, the rule sub-engine is immediately updated in real time based on the updated transit cost data. This process ensures that the system can quickly adjust its calculation rules to reflect the latest cost information when facing dynamic market changes. The update process may involve adjusting data storage, modifying calculation formulas, or adding new rules to ensure that the rule sub-engine can always perform accurate cost calculations based on the latest data. The updated data is used to update existing rules, while historical data is retained as a reference for trend assessment or anomaly monitoring in subsequent analyses. This real-time update mechanism not only improves the rule sub-engine's responsiveness to market changes but also ensures the accuracy of cost calculations, thus providing a more reliable data foundation for the cross-border delivery solutions generated by the system. After the rule sub-engine is updated, the target route optimization engine is immediately recalculated to ensure real-time performance.

[0038] In one embodiment, after step S302 of obtaining transit cost data for each of the target areas, the method further includes: S3031: Obtain the data type of each of the transit cost data; S3032: Obtain the corresponding standardized processing method according to the data type; S3033: Process the transit cost data of the corresponding data type according to the standardization processing method to obtain standardized transit cost data.

[0039] As described in step S3031 above, the data type of each transit cost data point is obtained. The transit cost data for each target area is analyzed to determine its data type. Transit cost data may include different types of information, such as tariffs, transportation costs, insurance costs, and handling fees. The structure and properties of each data type may differ. Therefore, starting from the data source and format, the characteristics of each data type are determined. This process may involve data parsing and feature extraction to ensure accurate identification of the data type and its attributes. Once the data type is confirmed, it lays the foundation for subsequent data processing and standardization. Obtaining the data type not only helps the system understand the relationship between different costs but also facilitates the application of corresponding standardization methods in subsequent processing, ensuring that various types of information can be easily compared and analyzed. For example, if the transit cost data for one area is presented as a percentage, while that for another area is presented as an absolute amount, the system needs to clearly identify this data type to facilitate subsequent balanced comparison and analysis.

[0040] As described in step S3032 above, the corresponding standardization processing method is obtained based on the data type. For each identified transit cost data type, a corresponding standardization processing method is obtained. Standardization processing refers to transforming data of different formats and properties into a comparable unified standard, making subsequent analysis more accurate. The selection of a standardization method typically depends on the characteristics of the data type. For example, for absolute monetary data, it can be converted into a relative proportion, such as a rate, so that data of different amounts can be compared horizontally. Similarly, for data in different currency units, the system may need to perform exchange rate conversion first, so that all data are expressed in the same currency unit. Furthermore, for some important data with periodic changes, such as seasonal costs, the system may use time series analysis methods for standardization processing. During the process of obtaining the standardization processing method, the system may integrate industry standards and best practices, and formulate suitable standardization rules based on historical data analysis results. The success of this step directly affects the consistency, reliability, and usability of the processed data, ensuring that the final standardized data can be effectively used in various scenarios.

[0041] As described in step S3033 above, the transit cost data of the corresponding data type is processed according to the standardization processing method to obtain standardized transit cost data. Based on the acquired standardization processing method, the transit cost data of the corresponding data type is actually processed to generate standardized transit cost data. This process involves complex data conversion and processing techniques, aiming to eliminate differences between different data types and make all transit cost information intuitively comparable under the same standard. Specifically, the system may use data processing algorithms to input the raw data into a standardization formula and generate standardized results that can be used for subsequent analysis. The standardized transit cost data will have consistency, facilitating comprehensive analysis, comparison, and decision-making in subsequent steps.

[0042] In one embodiment, step S3, which sets the dimension weights corresponding to the preset dimensions based on the dimension information, includes: S311: When the preset dimension is a timeliness dimension, determine whether the delivery time contained in the dimension information corresponding to the timeliness dimension is a preset time period; S312: If it is a preset time period, the weight of the timeliness dimension will be set to the first preset weight value.

[0043] As described in step S311 above, when the preset dimension is a timeliness dimension, it is determined whether the delivery time contained in the dimension information corresponding to the timeliness dimension falls within a preset time period. Specific analysis is performed on the preset dimensions, especially the timeliness dimension. The timeliness dimension primarily focuses on the time required for product delivery, directly impacting consumer satisfaction and decision-making. Therefore, before setting weights, the system needs to determine whether the delivery time information related to the timeliness dimension falls within a defined preset time period. This preset time period can be internally set by the company, such as during peak sales seasons or during merchant promotional periods.

[0044] As described in step S312 above, if it is a preset time period, the weight of the timeliness dimension is set to the first preset weight value. After confirming that the delivery time falls within the preset time period, a specific weight value is set for the timeliness dimension, usually referred to as the first preset weight value. The first preset weight value should be determined by the company's strategic goals and market demand. The first preset weight value is dynamically calculated based on historical order data and user preferences, and its value range is 50%-70%, for example, set to 60%. Then, according to the original weight ratio of other dimensions, the weights of other dimensions are reduced proportionally so that the sum of the weights of all dimensions is 100%. For example, if the company is currently focusing on improving customer satisfaction, then the weight of timeliness is set relatively high, and it is usually given a certain priority to ensure that the choice of delivery plan is more inclined to those routes that can be delivered within the preset time. In one embodiment, if multiple dimensions have high weights at the same time, a multi-objective optimization algorithm (such as Pareto optimality) can be used to balance the dimension priorities.

[0045] In one embodiment, step S3, which sets the dimension weights corresponding to the preset dimensions based on the dimension information, includes: S321: When the preset dimension is a compliance dimension, determine whether the product information contained in the dimension information corresponding to the compliance dimension is a sensitive product; S322: If the product is sensitive, the weight of the compliance dimension is set to the second preset weight value.

[0046] As described in step S321 above, when the preset dimension is a compliance dimension, it is determined whether the product information contained in the dimension information corresponding to the compliance dimension is a sensitive product. This ensures that the delivered products meet the legal and regulatory requirements of each target region. The compliance dimension relates to legal compliance, especially transportation regulations related to sensitive products. Sensitive products may include specific pharmaceuticals, perishable goods, and technical products subject to special supervision. During the determination phase, the system needs to parse the product information related to the order to identify whether it contains elements recognized as sensitive products.

[0047] The system's judgments typically rely on commodity classification databases and regulatory standard libraries. This information, sourced from regulatory agencies and industry associations, provides official definitions and classifications of sensitive goods across different regions. To achieve accurate judgments, the system needs to perform detailed analysis of commodity information, including its classification, description, intended use, and industry affiliation, and match it against a pre-defined list of sensitive goods. If a product is found to belong to a sensitive category, additional compliance restrictions or requirements will arise, impacting subsequent delivery plans and route selections. This judgment not only ensures that companies face no legal risks in terms of compliance but also encourages them to be more cautious when developing delivery plans, contributing to improved overall legal compliance and reduced potential operational risks.

[0048] As described in step S322 above, if the goods are sensitive, the weight of the compliance dimension is set to a second preset weight value. In this step, once it is confirmed that the transported goods are sensitive, a specific weight value is set for the compliance dimension, namely the second preset weight value. This weight value is crucial in the generation of multi-dimensional solutions because compliance is affected by sensitive goods and requires greater attention in the overall decision-making process. The setting of the second preset weight value aims to ensure the importance of the compliance dimension in route selection and delivery methods, preventing legal risks caused by compliance issues. When setting the weight, the system will refer to historical data and industry policies, weighing the relationship between compliance risk and delivery efficiency, for example, setting it to 30%. Through this method, enterprises can ensure effective control over compliance when implementing cross-border delivery solutions, thereby enhancing the reliability and legality of the overall supply chain. This not only protects the company's reputation but also helps enterprises establish a solid compliance foundation in the ever-changing international trade environment, thereby reducing potential operational risks.

[0049] In one embodiment, after step S6 of generating a cross-border route optimization scheme for the order to be delivered based on the optimized route, the method further includes: S701: Obtain the multiple cross-border regions involved in the cross-border route optimization scheme; S702: Obtain the declaration template corresponding to each of the aforementioned cross-border regions; S703: Fill the cross-border information of each cross-border region in the cross-border route optimization scheme into the corresponding declaration template to obtain the declaration text of each cross-border region.

[0050] As described in step S701 above, multiple cross-border regions involved in the cross-border route optimization plan are obtained. These regions typically include the country, region, or other specific geographical location to which the goods need to be delivered. Determining the target region is a crucial step in cross-border delivery because different regions may involve different laws, regulations, and logistics requirements. To accurately obtain these cross-border regions, the system analyzes detailed order information in the cross-border route optimization plan, including the final delivery address, transit candidate locations, and other relevant logistics information. During the process of obtaining cross-border regions, the system may use tools such as Geographic Information Systems (GIS) for address resolution and standardization, converting specific delivery addresses into unified regional identifiers. This process must ensure accuracy to avoid logistics problems caused by incorrect resolution. Furthermore, the system also needs to consider the market dynamics and regulatory requirements of the goods in different regions, such as storage restrictions and quarantine requirements. This information will further affect subsequent declaration and compliance processes. The results at this stage are crucial for the subsequently generated declaration text because the requirements of each cross-border region may differ significantly. Ensuring the accurate acquisition of key data can improve the overall smoothness and compliance of cross-border delivery.

[0051] As described in step S702 above, the declaration templates corresponding to each of the aforementioned cross-border regions are obtained. In this step, the corresponding declaration templates are obtained for each cross-border region. These declaration templates are typically standard format documents formulated according to the requirements and laws and regulations of each target region, used to standardize the declaration process. Different cross-border regions may require different types and formats of declaration information due to differences in country, region, and trade policies. Templates for each region can be pre-established, or the latest declaration templates that comply with local laws can be obtained by accessing the official channels of each region.

[0052] As described in step S703 above, the cross-border information corresponding to each cross-border region in the cross-border route optimization scheme is filled into the corresponding declaration template to obtain the declaration text for each cross-border region. The specific declaration text generation process will then begin. Based on the previously determined cross-border regions and their corresponding declaration templates, the system will fill in the relevant cross-border information from the cross-border route optimization scheme item by item into the corresponding declaration template. This process involves data extraction and organization, requiring that all information accurately correspond to the various fields of the declaration template. Cross-border information typically includes a detailed description of the goods, value, quantity, weight, country of origin, and mode of transport.

[0053] Reference Figure 3 The present invention also provides a multi-dimensional decision-making cross-border route generation device, the device comprising: The order data acquisition module 902 is used to acquire the order data of orders to be delivered; The dimension information acquisition module 904 is used to parse the order data to obtain dimension information corresponding to multiple preset dimensions. The dimension weight setting module 906 is used to set the dimension weight of the corresponding preset dimension based on the dimension information; The target path optimization engine acquisition module 908 is used to set the weights of the preset path optimization engine based on the dimension weights of each preset dimension in order to obtain the target path optimization engine. The optimized path acquisition module 910 is used to acquire the optimized path of the order data through the target path optimization engine. The cross-border optimization scheme generation module 912 is used to generate a cross-border route optimization scheme for the order to be delivered based on the optimized route.

[0054] In one embodiment, the multidimensional decision-making cross-border route generation apparatus further includes: The target area acquisition module is used to acquire multiple target areas related to the order to be delivered; The transit cost data acquisition module is used to acquire transit cost data for each of the target areas; The rule sub-engine generation module is used to generate a rule sub-engine for cost based on each of the aforementioned transit cost data; The optimization module is used to use the rule sub-engine as a dimensional constraint in the preset path optimization engine.

[0055] In one embodiment, the multidimensional decision-making cross-border route generation apparatus further includes: The monitoring module is used to monitor the updates of transit cost data for each of the target areas through a preset API cluster; The transit cost data acquisition module is updated to retrieve the updated transit cost data if the transit cost data has been updated. The comparison module is used to compare the updated transit cost data with the transit cost data before the update; The judgment module is used to determine whether the comparison result has reached the preset comparison value; The real-time update module is used to update the rule sub-engine in real time based on the updated transit cost data when a preset comparison value is reached.

[0056] In one embodiment, the multidimensional decision-making cross-border route generation apparatus further includes: A data type acquisition module is used to acquire the data type of each of the transit cost data. A standardized processing method acquisition module is used to acquire the corresponding standardized processing method based on the data type. The transit cost data processing module is used to process the transit cost data of the corresponding data type according to the standardized processing method to obtain standardized transit cost data.

[0057] In one embodiment, the dimension weight setting module 906 includes: The first judgment submodule is used to determine whether the delivery time contained in the dimension information corresponding to the time-efficiency dimension is a preset time period when the preset dimension is a time-efficiency dimension. The first preset weight value setting submodule is used to set the weight of the timeliness dimension to the first preset weight value if it is a preset time period.

[0058] In one embodiment, the dimension weight setting module 906 includes: The second judgment submodule is used to determine whether the product information contained in the dimension information corresponding to the compliance dimension is a sensitive product when the preset dimension is a compliance dimension. The second preset weight value setting submodule is used to set the weight of the compliance dimension to the second preset weight value if the product is sensitive.

[0059] In one embodiment, the multidimensional decision-making cross-border route generation apparatus further includes: The cross-border region acquisition module is used to acquire multiple cross-border regions involved in the cross-border path optimization scheme; The application template acquisition module is used to acquire the application templates corresponding to each of the aforementioned cross-border regions; The declaration text acquisition module is used to fill the cross-border information of each cross-border region in the cross-border route optimization scheme into the corresponding declaration template to obtain the declaration text of each cross-border region.

[0060] Figure 4 An 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 method for generating cross-border path solutions based on multi-dimensional decision-making. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement the method for generating cross-border path solutions based on multi-dimensional decision-making. Those skilled in the art will understand that... Figure 4The 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.

[0061] 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: Retrieve order data for orders awaiting delivery; The order data is parsed to obtain dimensional information corresponding to multiple preset dimensions; Dimension weights are set for the corresponding preset dimensions based on the dimensional information; The preset path optimization engine is weighted based on the dimensional weights of each preset dimension to obtain the target path optimization engine; The optimized path for the order data is obtained through the target path optimization engine; Based on the optimized path, a cross-border route optimization scheme for the orders to be delivered is generated.

[0062] It improves the real-time performance and accuracy of cross-border solution generation, effectively solves the problem of a single optimization dimension in the existing cross-border delivery solution generation, adapts to dynamically changing market demands, improves the efficiency of cross-border logistics, reduces delivery costs, and increases user satisfaction. In addition, the comprehensive multi-dimensional consideration makes solution generation more intelligent and personalized.

[0063] 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: Retrieve order data for orders awaiting delivery; The order data is parsed to obtain dimensional information corresponding to multiple preset dimensions; Dimension weights are set for the corresponding preset dimensions based on the dimensional information; The preset path optimization engine is weighted based on the dimensional weights of each preset dimension to obtain the target path optimization engine; The optimized path for the order data is obtained through the target path optimization engine; Based on the optimized path, a cross-border route optimization scheme for the orders to be delivered is generated.

[0064] It improves the real-time performance and accuracy of cross-border solution generation, effectively solves the problem of a single optimization dimension in the existing cross-border delivery solution generation, adapts to dynamically changing market demands, improves the efficiency of cross-border logistics, reduces delivery costs, and increases user satisfaction. In addition, the comprehensive multi-dimensional consideration makes solution generation more intelligent and personalized.

[0065] 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.

[0066] 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.

[0067] 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 method for generating cross-border path solutions based on multi-dimensional decision-making, characterized in that, The method includes: Retrieve order data for orders awaiting delivery; The order data is parsed to obtain dimensional information corresponding to multiple preset dimensions; Dimension weights are set for the corresponding preset dimensions based on the dimensional information; The preset path optimization engine is weighted based on the dimensional weights of each preset dimension to obtain the target path optimization engine; The optimized path for the order data is obtained through the target path optimization engine; Based on the optimized path, a cross-border route optimization scheme for the orders to be delivered is generated.

2. The method for generating cross-border path schemes through multi-dimensional decision-making according to claim 1, characterized in that, Before the step of setting weights for the preset path optimization engine based on the dimension weights of each preset dimension to obtain the target path optimization engine, the method further includes: Obtain multiple target areas related to the order to be delivered; Obtain transit cost data for each of the target areas; A rule-based sub-engine for generating cost calculations is generated based on the various transit cost data. The rule sub-engine is used as a dimensional constraint in the preset path optimization engine.

3. The method for generating cross-border path schemes through multi-dimensional decision-making according to claim 2, characterized in that, Following the step of generating a rule sub-engine for cost calculation based on each of the transit cost data, the method further includes: The update status of transit cost data for each of the target areas is monitored through a pre-set API cluster. If transit cost data has been updated, then retrieve the updated transit cost data. Compare the updated transit cost data with the transit cost data before the update; Determine whether the comparison result has reached the preset comparison value; If the preset comparison value is reached, the rule sub-engine is updated in real time based on the updated transit cost data.

4. The method for generating cross-border path schemes through multi-dimensional decision-making according to claim 2, characterized in that, After the step of obtaining transit cost data for each of the target areas, the method further includes: Obtain the data type for each of the aforementioned transit cost data; Obtain the corresponding standardized processing method based on the data type; The transit cost data of the corresponding data type is processed according to the standardization processing method to obtain standardized transit cost data.

5. The method for generating cross-border path schemes through multi-dimensional decision-making according to claim 1, characterized in that, The step of setting the dimension weights corresponding to the preset dimensions based on the dimension information includes: When the preset dimension is a timeliness dimension, determine whether the delivery time contained in the dimension information corresponding to the timeliness dimension is a preset time period; If it is a preset time period, the weight of the timeliness dimension will be set to the first preset weight value.

6. The method for generating cross-border path schemes through multi-dimensional decision-making according to claim 1, characterized in that, The step of setting the dimension weights corresponding to the preset dimensions based on the dimension information includes: When the preset dimension is a compliance dimension, determine whether the product information contained in the dimension information corresponding to the compliance dimension is a sensitive product; If the product is sensitive, the weight of the compliance dimension will be set to the second preset weight value.

7. The method for generating cross-border path schemes through multi-dimensional decision-making according to claim 1, characterized in that, After the step of generating a cross-border route optimization scheme for the order to be delivered based on the optimized route, the method further includes: Obtain the multiple cross-border regions involved in the cross-border route optimization scheme; Obtain the declaration templates corresponding to each of the aforementioned cross-border regions; The cross-border information corresponding to each cross-border region in the cross-border route optimization scheme is filled into the corresponding declaration template to obtain the declaration text for each cross-border region.

8. A multi-dimensional decision-making cross-border route generation device, characterized in that, The device includes: The order data acquisition module is used to acquire order data for orders to be delivered. The dimension information acquisition module is used to parse the order data to obtain dimension information corresponding to multiple preset dimensions. The dimension weight setting module is used to set the dimension weight of the corresponding preset dimension based on the dimension information; The target path optimization engine acquisition module is used to set weights for the preset path optimization engine based on the dimension weights of each preset dimension in order to obtain the target path optimization engine. The optimized path acquisition module is used to acquire the optimized path of the order data through the target path optimization engine. The cross-border optimization solution generation module is used to generate a cross-border route optimization solution for the order to be delivered based on the optimized route.

9. 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 cross-border path scheme generation method for multidimensional decision-making as described in any one of claims 1 to 7.

10. 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 cross-border path scheme generation method for multidimensional decision-making as described in any one of claims 1 to 7.

Images