Transportation strategy optimization method and device based on carbon emission, equipment and medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a transportation strategy optimization method and device based on carbon emission, equipment and a medium, and the method comprises the steps: obtaining cargo attributes and constraint conditions of specified to-be-transported cargos, generating a plurality of transportation schemes, calculating the carbon emission data of each transportation scheme, and calculating the carbon emission data of each transportation scheme; inputting the transportation scheme and the corresponding carbon emission data into a preset carbon tax knowledge graph to obtain carbon tax data; and inputting the various transportation schemes and the corresponding carbon emission data and carbon tax data into a preset mixed integer nonlinear programming model to generate a transportation strategy of the specified to-be-transported goods. The beneficial effects of the invention are that the dual goals of environmental protection and economic benefit are realized, and in combination with the carbon tax knowledge graph, the cost can be effectively controlled when the enterprise optimizes the transportation strategy, the extra tax caused by non-compliance is avoided, the transportation cost and the carbon emission are balanced, and the maximization of the transportation efficiency is realized.

Description

Technical Field

[0001] This invention relates to the field of carbon emission-based transportation strategy optimization technology, and in particular to a carbon emission-based transportation strategy optimization method, apparatus, equipment and medium. Background Technology

[0002] With the development of global economic integration, cross-border logistics has become a crucial link in international trade. However, the carbon emissions problem in cross-border logistics is becoming increasingly prominent, especially against the backdrop of increasingly stringent requirements for environmental protection and sustainable development in various countries. While existing technologies offer some methods for assessing and managing carbon emissions in logistics, they often neglect the balance between cost, cargo attributes, and constraints. For example, while some green transportation solutions can significantly reduce carbon emissions, they may lead to a substantial increase in transportation costs, thereby impacting a company's competitiveness and customer acceptance. Furthermore, the varying transportation requirements and handling methods for different types of goods, coupled with a failure to adapt transportation strategies to local conditions, exacerbates this problem. Summary of the Invention

[0003] Therefore, it is necessary to propose a method, apparatus, equipment and medium for optimizing existing carbon emission-based transportation strategies.

[0004] A carbon emission-based transportation strategy optimization method, the method comprising: Obtain the cargo attributes and constraints of the specified goods to be transported; Multiple transportation plans are generated based on the cargo attributes and the constraints. Based on the various transportation options and the corresponding cargo attributes, calculate the carbon emission data for each transportation option; The various transportation schemes and their corresponding carbon emission data are input into a preset carbon tax knowledge graph to obtain carbon tax data for each of the transportation schemes. Various transportation options, along with corresponding carbon emission and carbon tax data, are input into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported.

[0005] Furthermore, the step of calculating the carbon emission data for each of the various transportation schemes and the corresponding cargo attributes includes: Real-time collection of environmental data related to each transportation plan; Carbon emission data for each transportation scheme is calculated based on the environmental data and cargo attributes.

[0006] Furthermore, before the step of inputting the various transportation schemes and their corresponding carbon emission data into a preset carbon tax knowledge graph to obtain the carbon tax data for the various transportation schemes, the method further includes: Collect carbon tax policy texts from multiple countries; Extract the tax base, exemption clauses, and deduction rules from various carbon tax policy texts to form a carbon tax triad; The preset carbon tax knowledge graph is generated based on the carbon tax triplet.

[0007] Furthermore, after the step of generating the preset carbon tax knowledge graph based on the carbon tax triplet, the method further includes: Check whether the carbon tax policy texts of various countries have been updated; If a country's carbon tax policy text has been updated, then obtain the updated target carbon tax policy text; The preset carbon tax knowledge graph is updated based on the target carbon tax policy text.

[0008] Furthermore, before the step of inputting various transportation schemes and corresponding carbon emission data and carbon tax data into a preset mixed-integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported, the method further includes: Obtain the decision variables, constraints, and objective function; The decision variables, constraints, and objective function are input into the initial mixed-integer nonlinear programming model to obtain the preset mixed-integer nonlinear programming model.

[0009] Furthermore, after the step of inputting various transportation schemes and corresponding carbon emission data and carbon tax data into a preset mixed-integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported, the method further includes: Obtain carbon emission standards; The transportation strategy and the carbon emission standards are input into a preset natural language processing model to generate a transportation report; The transportation report is uploaded to a preset database for storage.

[0010] Furthermore, after the step of inputting various transportation schemes and corresponding carbon emission data and carbon tax data into a preset mixed-integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported, the method further includes: Real-time monitoring of risk information related to the transportation strategy; The risk information is input into a preset risk analysis model to obtain the corresponding risk probability; Determine whether the risk probability is greater than a risk threshold; If the risk probability is greater than the risk threshold, then risk constraints are generated based on the risk information. The risk constraints are input into the preset mixed integer nonlinear programming model, and the transportation strategy is regenerated.

[0011] The present invention also provides a transportation strategy optimization device based on carbon emissions, the device comprising: The acquisition module is used to acquire the cargo attributes and constraints of the specified cargo to be transported; The first generation module is used to generate multiple transportation plans based on the cargo attributes and the constraints. The calculation module is used to calculate the carbon emission data for each of the various transportation schemes and the corresponding cargo attributes. The input module is used to input the various transportation schemes and their corresponding carbon emission data into a preset carbon tax knowledge graph to obtain the carbon tax data for the various transportation schemes. The second generation module is used to input various transportation schemes and corresponding carbon emission data and carbon tax data into a preset mixed integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported.

[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: Obtain the cargo attributes and constraints of the specified goods to be transported; Multiple transportation plans are generated based on the cargo attributes and the constraints. Based on the various transportation options and the corresponding cargo attributes, calculate the carbon emission data for each transportation option; The various transportation schemes and their corresponding carbon emission data are input into a preset carbon tax knowledge graph to obtain carbon tax data for each of the transportation schemes. Various transportation options, along with corresponding carbon emission and carbon tax data, are input into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported.

[0013] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps: Obtain the cargo attributes and constraints of the specified goods to be transported; Multiple transportation plans are generated based on the cargo attributes and the constraints. Based on the various transportation options and the corresponding cargo attributes, calculate the carbon emission data for each transportation option; The various transportation schemes and their corresponding carbon emission data are input into a preset carbon tax knowledge graph to obtain carbon tax data for each of the transportation schemes. Various transportation options, along with corresponding carbon emission and carbon tax data, are input into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported.

[0014] The beneficial effects of this invention are as follows: By systematically acquiring cargo attributes and constraints, it ensures that transportation solutions are optimized while meeting actual needs and regulatory requirements. It can generate multiple transportation solutions and evaluate their carbon emission data, thereby achieving the dual goals of environmental protection and economic benefits. Combined with a carbon tax knowledge graph, it enables enterprises to effectively control costs when optimizing transportation strategies and avoid additional taxes due to non-compliance. In addition, by applying a mixed-integer nonlinear programming model, it is possible to balance transportation costs and carbon emissions in multi-objective optimization and maximize transportation efficiency. 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 a diagram illustrating the application environment of a carbon emission-based transportation strategy optimization method in one embodiment. Figure 2 This is a flowchart of a carbon emission-based transportation strategy optimization method in one embodiment; Figure 3 This is a structural block diagram of a carbon emission-based transportation strategy optimization device 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 This is a diagram illustrating the application environment of a carbon emission-based transportation strategy optimization in one embodiment. (Refer to...) Figure 1This carbon emission-based transportation strategy optimization method is applied to a carbon emission-based transportation strategy optimization 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 device. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to obtain cargo attributes and constraints, while the server 120 is used to generate transportation strategies.

[0019] like Figure 2 As shown, in one embodiment, a carbon emission-based transportation strategy optimization method is provided. This method can be applied to both terminals and servers; this embodiment illustrates its application to terminals. The carbon emission-based transportation strategy optimization method specifically includes the following steps: S1: Obtain the cargo attributes and constraints of the specified cargo to be transported; S2: Generate multiple transportation plans based on the cargo attributes and the constraints; S3: Calculate the carbon emission data for each of the various transportation schemes and the corresponding cargo attributes; S4: Input the various transportation schemes and their corresponding carbon emission data into a preset carbon tax knowledge graph to obtain the carbon tax data for the various transportation schemes; S5: Input various transportation schemes and corresponding carbon emission data and carbon tax data into a preset mixed integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported.

[0020] As described in step S1 above, various attribute information and related constraints of the goods to be transported are obtained. These goods attributes include, but are not limited to, the type, weight, volume, value, storage conditions (such as temperature requirements, perishability, etc.), and packaging methods. Meanwhile, constraints may include transportation laws and regulations, special requirements of the destination, the destination and origin, time restrictions, avoidance areas, carrying capacity, and the availability of transportation modes. Data can be obtained by extracting data from the enterprise's logistics management system, communicating with relevant parties in the supply chain to obtain information, or obtaining real-time transportation requirement information through a data sharing platform.

[0021] As described in step S2 above, multiple transportation plans are generated based on the cargo attributes and constraints. These plans can be generated by establishing a corresponding neural network model. This model is trained using various historical orders (containing cargo attributes and constraints). The generation of transportation plans needs to consider available transportation modes (including sea, air, road, and rail transport), routes, and the selection of transportation equipment (such as container type and vehicle specifications). Furthermore, based on the characteristics of the cargo and transportation requirements, time costs and transportation efficiency also need to be considered. For example, perishable goods may require faster transportation methods, while heavy goods may require specialized vehicles. Transportation plans should be as diverse as possible while satisfying all constraints to provide multiple options and flexibility. Specifically, the guiding principles of operations research and combinatorial optimization can be applied. Based on existing transportation networks, historical transportation data, and field investigation results, more reasonable transportation plans can be designed, providing multiple options for subsequent carbon emission calculations.

[0022] As described in step S3 above, carbon emission data for each transportation scheme is calculated based on the various transportation options and their corresponding cargo attributes. Specifically, a modeling approach can be used, combining the generated transportation schemes to calculate the carbon emission data for each scheme. Different transportation modes and routes have a significant impact on carbon emissions. Therefore, based on factors such as the selected transportation mode, estimated transportation distance, and load weight, existing carbon emission calculation models are used to quantify the carbon emissions of each scheme. It should be noted that quantification requires collecting data on the average carbon emission coefficient per unit of cargo for each transportation mode and performing a weighted calculation. Furthermore, specific traffic conditions, weather factors, and transportation efficiency should also be considered, as these factors may lead to discrepancies between actual and theoretical emissions.

[0023] As described in step S4 above, the various transportation schemes and their corresponding carbon emission data are input into a preset carbon tax knowledge graph to obtain carbon tax data for each transportation scheme. After calculating the carbon emission data, this information is combined with the preset carbon tax knowledge graph to derive the carbon tax data payable for each transportation scheme. The carbon tax system aims to encourage enterprises to make more environmentally conscious decisions and reduce carbon emissions by taxing each unit of carbon emissions, thereby achieving coordinated economic and environmental development. Specifically, the carbon emissions of the transportation schemes are mapped to the carbon knowledge graph to calculate the corresponding carbon tax fees. The knowledge graph may contain information such as carbon tax calculation methods, tax rates, and relevant regulations to ensure the accuracy and compliance of data processing.

[0024] As described in step S5 above, various transportation options, along with corresponding carbon emission and carbon tax data, are input into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported. The mixed-integer nonlinear programming model is an optimization tool capable of handling multiple objectives and complex constraints to achieve optimal values. In this model, the objective is not only to minimize transportation costs, carbon emissions, and carbon taxes, but also to ensure transportation efficiency and flexibility. Through a combination of linear and nonlinear variable design, the model can effectively analyze and derive the optimal solution, considering the application scenarios and conditions of various options, thus providing decision support for logistics companies. The pre-defined mixed-integer nonlinear programming model is established using Pyomo or Gekko in Python, combining transportation information such as transportation plans and route costs to create an initial framework. Then, based on minimizing transportation costs, carbon emissions, and carbon taxes, the efficiency and flexibility of transportation are transformed into mathematical forms, including objective functions and constraints. Next, the variable types are selected, distinguishing between continuous and integer variables, and a solver is chosen. Different solvers support different algorithms and performance levels, such as Bonmin and Baron, which can be selected according to the actual situation. This completes the construction of the pre-defined mixed-integer nonlinear programming model. The generated transportation strategy can help enterprises achieve the dual goals of economic benefits and environmental protection, promoting cross-border logistics towards sustainable development.

[0025] In one embodiment, step S3, which calculates the carbon emission data for each of the various transportation schemes and the corresponding cargo attributes, includes: S301: Real-time collection of environmental data related to various transportation plans; S302: Calculate the carbon emission data for each transportation scheme based on the environmental data and the cargo attributes.

[0026] As described in steps S301-S302 above, real-time environmental data collection is required. This data includes temperature, humidity, air quality, traffic conditions, wind speed, and precipitation. These elements all have direct or indirect impacts on carbon emissions. For example, during transportation, traffic congestion reduces vehicle operating efficiency, thereby increasing fuel consumption and carbon emissions. Specifically, ship AIS data can be accessed to analyze the speed / load ratio, and NOAA weather API can be used to calculate fuel consumption losses due to headwinds. IoT sensors can be used to collect railway locomotive traction energy consumption, dynamically correcting the difference in carbon emission coefficients between electrified sections and diesel-powered sections. Climate conditions, such as temperature and humidity, can also affect the performance of transportation vehicles. For example, excessively high temperatures may increase energy consumption in cold chain transportation. This data can be acquired in real-time using sensors, satellite remote sensing technology, and IoT devices. Specifically, carbon emission data can be set as: Baseline Emissions × (1 + Real-time Congestion Index) × Weather Correction Factor. The real-time congestion index can be calculated based on traffic conditions, while the weather correction factor is calculated using other environmental data. Based on the collected environmental data and the attributes of the goods to be transported, carbon emission data for each transportation option is calculated. First, a carbon emission model is established, taking into account the attributes of the goods, such as weight, volume, properties (e.g., perishability, refrigeration requirements), and environmental conditions. For example, different transportation modes (such as sea, land, and air transport) will have different energy consumption and carbon emission characteristics under different environmental conditions. The carbon emissions for each transportation mode are dynamically adjusted based on a standard carbon emission factor and real-time environmental data. In one specific embodiment, linear regression, nonlinear regression, or machine learning-based predictive models can be used to process these data, thereby ensuring the accuracy and scientific rigor of the calculations. By combining environmental data with transportation schemes and cargo attributes, it is possible to better understand the operational efficiency and carbon emission characteristics of each transportation scheme under specific conditions, thereby obtaining more accurate carbon emission data. This provides key information for subsequent carbon tax assessments, cost analysis, and strategy optimization, enabling enterprises to make more environmentally friendly and economical transportation decisions.

[0027] In one embodiment, before step S4, which involves inputting the various transportation schemes and their corresponding carbon emission data into a preset carbon tax knowledge graph to obtain carbon tax data for the various transportation schemes, the method further includes: S311: Collect carbon tax policy texts from multiple countries; S312: Extract the tax base, exemption clauses, and deduction rules from each carbon tax policy text to form a carbon tax triplet; S313: Generate the preset carbon tax knowledge graph based on the carbon tax triplet.

[0028] As described in steps S311-S313 above, carbon tax policy texts from multiple countries are collected. Specifically, based on the company's business, the carbon tax policy texts of countries that may be involved are collected. Since carbon tax policies vary from country to country, the details and requirements involved may significantly impact the carbon emission costs of transportation solutions. The collection method utilizes web scraping technology to obtain relevant documents from multiple channels, including national government official websites, international organizations, environmental protection agencies, academic research, and professional literature databases. The carbon tax knowledge graph is updated in real-time via API connection to the tax systems of various countries, with a delay of ≤1 hour after policy changes; that is, the preset carbon tax knowledge graph is only updated when there are changes in carbon tax policies. The text data may include carbon tax implementation details, relevant laws and regulations, policy guidance, and subsidy measures. Furthermore, considering the different languages ​​and expressions of various countries, the texts are translated into a unified language and standardized for subsequent text analysis and information extraction.

[0029] Information extraction is performed on previously collected carbon tax policy texts. The main objective is to identify and extract key elements related to carbon tax from the texts, including the tax base, exemption clauses, and deduction rules, and structure them into carbon tax triplets. The tax base refers to the quantitative standard used to calculate the carbon tax, such as emissions per ton of carbon dioxide. Exemption clauses specify which specific situations or industries are exempt from the carbon tax, while deduction rules indicate the tax reductions that companies can receive under certain conditions. This process typically relies on Natural Language Processing (NLP) techniques, using text mining and information extraction systems to extract structured data from large-scale policy texts. Named Entity Recognition (NER), syntactic analysis, and keyword extraction techniques can be used to ensure the accuracy, completeness, and representativeness of the extracted data. By organizing the extracted triplets, a knowledge graph can clearly demonstrate the relationships and hierarchical structure between carbon tax policies of different countries. For example, a portion of the graph can show how a country's tax base, exemption clauses, and deduction rules are interconnected, forming a visual framework. Furthermore, knowledge graphs should possess a degree of dynamism and scalability to quickly adapt to the inclusion of carbon tax policies from more countries or to policy updates in the future. Storing and managing this information using graph databases (such as Neo4j) enables efficient querying and analysis. Simultaneously, the constructed knowledge graph can support subsequent carbon tax data analysis, facilitate carbon tax calculations for different transportation options, and help companies quickly understand and adapt to the carbon tax policies of various countries.

[0030] In one embodiment, after step S313 of generating the preset carbon tax knowledge graph based on the carbon tax triplet, the method further includes: S3141: Check whether the carbon tax policy texts of various countries have been updated; S3142: If the carbon tax policy text of a country is updated, obtain the updated target carbon tax policy text; S3143: Update the preset carbon tax knowledge graph based on the target carbon tax policy text.

[0031] As described in steps S3141-S3143 above, carbon tax policy texts from various countries should be periodically checked to determine if there are any updates. This ensures that companies can quickly adjust their transportation strategies and decision-making processes when faced with changes in carbon taxes and policies. Update detection methods can include setting up a periodic automated checking mechanism, using web crawling technology or API interfaces to regularly obtain carbon tax policy information published on government websites, international organizations, and relevant research institutions. Furthermore, machine learning or document comparison techniques can be used to compare currently retained policy texts with newly acquired texts to identify changes. During the detection process, changes in the policy context, such as policy revisions, additions, and revocations, should also be captured to ensure the system accurately reflects policy developments. This dynamic monitoring mechanism, established through these methods, can identify and report policy updates in a timely manner, providing a valid basis for further analysis and knowledge graph updates.

[0032] When the system detects that a country's carbon tax policy text has been updated, it will initiate a data acquisition process to obtain the updated target carbon tax policy text. This acquisition strategy can involve re-calling web crawlers, APIs, or directly accessing the policy databases of government and related agencies to ensure the acquisition of the latest and most complete regulatory information. The system will identify the tax base, exemption clauses, and deduction rules involved in the new text and integrate them into the existing knowledge graph structure. Text analysis and information extraction techniques can be used to review and compare the content of the old and new texts one by one, combining the newly acquired data with the existing carbon tax triplet. If there are significant modifications in the new policy, the knowledge graph will be adjusted and supplemented accordingly to reflect these changes. Furthermore, knowledge graph updates may also involve adjusting the graph's relationships and attributes to ensure it aligns with the latest policy trends. Through dynamic maintenance of the knowledge graph, companies can more accurately respond to policy changes and conduct compliance reviews, ultimately maintaining the ability to flexibly respond to market changes while ensuring reduced carbon tax expenditures in operations and improved environmental sustainability.

[0033] In one embodiment, before step S5, which involves inputting various transportation schemes and corresponding carbon emission and carbon tax data into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported, the method further includes: S401: Obtain the decision variables, constraints, and objective function; S402: Input the decision variables, the constraints, and the objective function into the initial mixed-integer nonlinear programming model to obtain the preset mixed-integer nonlinear programming model.

[0034] As described in steps S401-S402 above, defining the decision variables, constraints, and objective function forms the foundation of the mixed-integer nonlinear programming model. First, the decision variables are the variables to be optimized in the model, typically related to the selection and implementation of transportation options. For example, decision variables may include the choice of different transportation modes (e.g., sea, air, or land transport), the choice of transportation routes, the amount of cargo allocated to each mode, the implementation time of each option, the choice of transit hubs, and the amount of carbon credits purchased. Second, constraints refer to a series of restrictions that must be followed during optimization. These include laws and regulations, budget constraints, time constraints, capacity constraints, cross-border customs clearance time thresholds, maximum vehicle capacity, and geopolitical risk indices. For example, some transportation modes may be restricted from use in specific areas due to legal limitations, or low-emission transportation modes may be required due to environmental regulations. There may also be price caps or transportation capacity restrictions to ensure that actual operation does not exceed the set limits. Finally, the objective function reflects the ultimate goal of the decision-making process. This application adopts the method of minimizing costs: Min total cost = Σ(freight cost + carbon tax - deduction revenue) + λ·time-sensitivity penalty term + μ·carbon emission premium, where λ is the time-sensitivity sensitivity coefficient in yuan / hour, trained using historical orders from enterprises, and μ is the carbon emission penalty coefficient in yuan / ton, obtained from the monthly average price of the carbon exchange. The obtained decision variables, constraints, and objective function are assembled into a complete mixed-integer nonlinear programming initial model: Time-sensitivity penalty term = max(actual time-sensitivity - promised time-sensitivity, 0) × default rate; Carbon emission premium = (actual emissions - standard emissions) × carbon market unit price × 1.5 (penalty coefficient).

[0035] In one embodiment, after step S5, which involves inputting various transportation schemes and corresponding carbon emission and carbon tax data into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported, the method further includes: S601: Obtaining carbon emission standards; S602: Input the transportation strategy and the carbon emission standard into a preset natural language processing model to generate a transportation report; S603: Upload the transport report to a preset database for storage.

[0036] As described in steps S601-S603 above, carbon emission standards relevant to the transportation industry are obtained, such as CBAM (Carbon Border Adjustment Mechanism). These standards can come from government agencies, international organizations, industry associations, and standardization bodies, and typically include specific emission limits, assessment methods, monitoring, and reporting requirements. The transportation strategy and corresponding carbon emission standards are input into a pre-defined Natural Language Processing (NLP) model (e.g., GPT, Deepseek) to generate a detailed transportation report. The NLP model transforms complex data and information into clear and understandable report text. This model may employ speech generation algorithms (such as text summarization, content generation, etc.) to combine key information from the transportation strategy with relevant carbon emission standards to form a comprehensive report. The generated transportation report is uploaded to a pre-defined database for storage to ensure information traceability and standardized management. The upload process typically requires a secure interface and database management system (such as MySQL, MongoDB, etc.) to ensure data integrity and security. A blockchain notarization module can also be embedded to ensure the data is tamper-proof as required by German supply chain law.

[0037] In one embodiment, after step S5, which involves inputting various transportation schemes and corresponding carbon emission and carbon tax data into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported, the method further includes: S611: Real-time monitoring of risk information related to the transportation strategy; S612: Input the risk information into a preset risk analysis model to obtain the corresponding risk probability; S613: Determine whether the risk probability is greater than the risk threshold; S614: If the risk probability is greater than the risk threshold, then generate risk constraints based on the risk information; S615: Input the risk constraints into the preset mixed integer nonlinear programming model and regenerate the transportation strategy.

[0038] As described in steps S611-S615 above, a real-time monitoring system is established to detect risk information related to transportation strategies. These risks may originate from multiple sources, including natural disasters (such as blizzards and floods), market fluctuations (such as rising fuel prices), compliance risks (such as changing regulations and policies), and supply chain disruptions (such as supplier delays). Specifically, sensors, monitoring software, market analysis tools, and external data sources (such as weather stations and financial market monitoring agencies) can be used to ensure timely collection and analysis of this information. The real-time monitored risk information is input into a pre-set risk analysis model to calculate the probability associated with these risks. This risk analysis model typically utilizes the principles of statistics and probability theory, combining historical data and current monitoring information to assess the likelihood of different risk events occurring. The model may employ various methods, such as Monte Carlo simulation, decision tree analysis, and sensitivity analysis, to quantify the degree and uncertainty of the risk. Finally, it is determined whether the calculated risk probability exceeds a pre-set risk threshold. A risk threshold is a standard determined by a company based on its risk tolerance, market environment, and legal requirements. For example, setting a risk threshold of 0.7, based on the 70th percentile risk value in the company's logistics accident statistics over the past five years, reflects the company's definition of unacceptable risk. If the risk probability is higher than the threshold, the next step is taken; otherwise, the current transportation strategy can continue. When the risk probability exceeds the set threshold, the company needs to generate targeted risk constraints based on the monitored risk information. For example, "When the typhoon risk > 0.7, generate the constraint: Shipping route ∉ {Typhoon radius 50 nautical miles}". The newly generated risk constraints are input into the established pre-set mixed integer nonlinear programming model to regenerate the transportation strategy. Incorporating risk constraints into the model helps optimize existing transportation plans and ensures that the new strategy can effectively address the identified risks. This process requires corresponding adjustments to the model to ensure that it meets the new constraints while maintaining the optimization objective. For example, if a transportation route is deemed unsafe due to weather conditions, the model will need to consider other feasible alternative routes or transportation methods to replace the original plan. By resolving the model, companies can obtain the optimal transportation strategy under new risk conditions, ensuring the rationality and safety of the overall transportation process. The regenerated transportation strategy needs to balance the relationship between transportation costs, time efficiency, and risk management, ensuring that it not only meets operational requirements but also aligns with risk control objectives. The efficient execution of this process will provide necessary support for companies to adapt to changes and meet challenges in a dynamic market environment, ultimately achieving safe and efficient logistics operations.

[0039] Reference Figure 3 The present invention also provides a transportation strategy optimization device based on carbon emissions, the device comprising: The acquisition module 902 is used to acquire the cargo attributes and constraints of the specified cargo to be transported; The first generation module 904 is used to generate multiple transportation plans based on the cargo attributes and the constraints. The calculation module 906 is used to calculate the carbon emission data for each of the various transportation schemes and the corresponding cargo attributes. Input module 908 is used to input various transportation schemes and corresponding carbon emission data into a preset carbon tax knowledge graph to obtain carbon tax data for various transportation schemes; The second generation module 910 is used to input various transportation schemes and corresponding carbon emission data and carbon tax data into a preset mixed integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported.

[0040] Furthermore, the computing module 906 includes: The environmental data acquisition submodule is used to collect environmental data related to each transportation plan in real time. The carbon emission data calculation submodule is used to calculate the carbon emission data of each transportation scheme based on the environmental data and the cargo attributes.

[0041] In one embodiment, the carbon emission-based transportation strategy optimization device further includes: The carbon tax policy text collection module is used to collect carbon tax policy texts from multiple countries. The carbon tax tripartite formation module is used to extract the tax base, exemption clauses, and deduction rules from various carbon tax policy texts to form a carbon tax tripartite. A preset carbon tax knowledge graph generation module is used to generate the preset carbon tax knowledge graph based on the carbon tax triplet.

[0042] In one embodiment, the carbon emission-based transportation strategy optimization device further includes: The carbon tax policy text detection module is used to detect whether the carbon tax policy texts of various countries have been updated. The target carbon tax policy text acquisition module is used to acquire the updated target carbon tax policy text if the carbon tax policy text of a country is updated. The preset carbon tax knowledge graph update module is used to update the preset carbon tax knowledge graph based on the target carbon tax policy text.

[0043] In one embodiment, the carbon emission-based transportation strategy optimization device further includes: The decision variable acquisition module is used to acquire decision variables, constraints, and objective functions; The decision variable input module is used to input the decision variables, the constraints, and the objective function into the mixed integer nonlinear programming initial model to obtain the preset mixed integer nonlinear programming model.

[0044] In one embodiment, the carbon emission-based transportation strategy optimization device further includes: The carbon emission standard acquisition module is used to acquire carbon emission standards. A carbon emission standard input module is used to input the transportation strategy and the carbon emission standard into a preset natural language processing model to generate a transportation report; The transportation report storage module is used to upload the transportation report to a preset database for storage.

[0045] In one embodiment, the carbon emission-based transportation strategy optimization device further includes: The risk information monitoring module is used to monitor risk information related to the transportation strategy in real time. The risk information input module is used to input the risk information into a preset risk analysis model to obtain the corresponding risk probability; The risk probability judgment module is used to determine whether the risk probability is greater than a risk threshold; The risk constraint generation module is used to generate risk constraints based on the risk information if the risk probability is greater than the risk threshold. The risk constraint input module is used to input the risk constraints into the preset mixed integer nonlinear programming model and regenerate the transportation strategy.

[0046] 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 carbon emission-based transportation strategy optimization method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement the carbon emission-based transportation strategy optimization method. 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.

[0047] 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: Obtain the cargo attributes and constraints of the specified goods to be transported; Multiple transportation plans are generated based on the cargo attributes and the constraints. Based on the various transportation options and the corresponding cargo attributes, calculate the carbon emission data for each transportation option; The various transportation schemes and their corresponding carbon emission data are input into a preset carbon tax knowledge graph to obtain carbon tax data for each of the transportation schemes. Various transportation options, along with corresponding carbon emission and carbon tax data, are input into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported.

[0048] By systematically acquiring cargo attributes and constraints, the system ensures that transportation solutions are optimized while meeting actual needs and regulatory requirements. It can generate multiple transportation solutions and assess their carbon emission data, thereby achieving the dual goals of environmental protection and economic benefits. Combined with a carbon tax knowledge graph, it enables enterprises to effectively control costs when optimizing transportation strategies and avoid additional taxes due to non-compliance. In addition, the application of a mixed-integer nonlinear programming model can balance transportation costs and carbon emissions in multi-objective optimization, thereby maximizing transportation efficiency.

[0049] 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: Obtain the cargo attributes and constraints of the specified goods to be transported; Multiple transportation plans are generated based on the cargo attributes and the constraints. Based on the various transportation options and the corresponding cargo attributes, calculate the carbon emission data for each transportation option; The various transportation schemes and their corresponding carbon emission data are input into a preset carbon tax knowledge graph to obtain carbon tax data for each of the transportation schemes. Various transportation options, along with corresponding carbon emission and carbon tax data, are input into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported.

[0050] By systematically acquiring cargo attributes and constraints, the system ensures that transportation solutions are optimized while meeting actual needs and regulatory requirements. It can generate multiple transportation solutions and assess their carbon emission data, thereby achieving the dual goals of environmental protection and economic benefits. Combined with a carbon tax knowledge graph, it enables enterprises to effectively control costs when optimizing transportation strategies and avoid additional taxes due to non-compliance. In addition, the application of a mixed-integer nonlinear programming model can balance transportation costs and carbon emissions in multi-objective optimization, thereby maximizing transportation efficiency.

[0051] 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.

[0052] 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.

[0053] 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 optimizing transportation strategies based on carbon emissions, characterized in that, The method includes: Obtain the cargo attributes and constraints of the specified goods to be transported; Multiple transportation plans are generated based on the cargo attributes and the constraints. Based on the various transportation options and the corresponding cargo attributes, calculate the carbon emission data for each transportation option; The various transportation schemes and their corresponding carbon emission data are input into a preset carbon tax knowledge graph to obtain carbon tax data for each of the transportation schemes. Various transportation options, along with corresponding carbon emission and carbon tax data, are input into a preset mixed-integer nonlinear programming model to generate a transportation strategy for the specified goods to be transported.

2. The carbon emission-based transportation strategy optimization method according to claim 1, characterized in that, The step of calculating carbon emission data for each of the various transportation schemes and the corresponding cargo attributes includes: Real-time collection of environmental data related to each transportation plan; Carbon emission data for each transportation scheme is calculated based on the environmental data and cargo attributes.

3. The carbon emission-based transportation strategy optimization method according to claim 1, characterized in that, Before the step of inputting the various transportation schemes and their corresponding carbon emission data into a preset carbon tax knowledge graph to obtain the carbon tax data for the various transportation schemes, the method further includes: Collect carbon tax policy texts from multiple countries; Extract the tax base, exemption clauses, and deduction rules from various carbon tax policy texts to form a carbon tax triad; The preset carbon tax knowledge graph is generated based on the carbon tax triplet.

4. The carbon emission-based transportation strategy optimization method according to claim 3, characterized in that, After the step of generating the preset carbon tax knowledge graph based on the carbon tax triplet, the method further includes: Check whether the carbon tax policy texts of various countries have been updated; If a country's carbon tax policy text has been updated, then obtain the updated target carbon tax policy text; The preset carbon tax knowledge graph is updated based on the target carbon tax policy text.

5. The carbon emission-based transportation strategy optimization method according to claim 1, characterized in that, Before the step of inputting various transportation schemes and corresponding carbon emission and carbon tax data into a preset mixed-integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported, the method further includes: Obtain the decision variables, constraints, and objective function; The decision variables, constraints, and objective function are input into the initial mixed-integer nonlinear programming model to obtain the preset mixed-integer nonlinear programming model.

6. The carbon emission-based transportation strategy optimization method according to claim 1, characterized in that, After the step of inputting various transportation schemes and corresponding carbon emission and carbon tax data into a preset mixed-integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported, the method further includes: Obtain carbon emission standards; The transportation strategy and the carbon emission standards are input into a preset natural language processing model to generate a transportation report; The transportation report is uploaded to a preset database for storage.

7. The carbon emission-based transportation strategy optimization method according to claim 1, characterized in that, After the step of inputting various transportation schemes and corresponding carbon emission and carbon tax data into a preset mixed-integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported, the method further includes: Real-time monitoring of risk information related to the transportation strategy; The risk information is input into a preset risk analysis model to obtain the corresponding risk probability; Determine whether the risk probability is greater than a risk threshold; If the risk probability is greater than the risk threshold, then risk constraints are generated based on the risk information. The risk constraints are input into the preset mixed integer nonlinear programming model, and the transportation strategy is regenerated.

8. A transportation strategy optimization device based on carbon emissions, characterized in that, The device includes: The acquisition module is used to acquire the cargo attributes and constraints of the specified cargo to be transported; The first generation module is used to generate multiple transportation plans based on the cargo attributes and the constraints. The calculation module is used to calculate the carbon emission data for each of the various transportation schemes and the corresponding cargo attributes. The input module is used to input the various transportation schemes and their corresponding carbon emission data into a preset carbon tax knowledge graph to obtain the carbon tax data for the various transportation schemes. The second generation module is used to input various transportation schemes and corresponding carbon emission data and carbon tax data into a preset mixed integer nonlinear programming model to generate the transportation strategy for the specified goods to be transported.

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 carbon emission-based transportation strategy optimization method 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 carbon emission-based transportation strategy optimization method as described in any one of claims 1 to 7.

Images