Carbon emission optimization method and system based on green supply chain management

Abstract

The invention provides a carbon emission optimization method and system based on green supply chain management, and relates to the technical field of data processing, M key links are positioned based on historical carbon emission data and called to obtain M local carbon emission data, and the M local carbon emission data are adopted to construct a carbon emission prediction model; environment data acquisition is carried out on the M key links, acquisition results are synchronized to a carbon emission prediction model to carry out carbon emission trend prediction, M pieces of carbon emission trend information are obtained, and then a real-time emission reduction strategy is output to execute carbon emission optimization management. The technical problem that in the prior art, targeted emission reduction management cannot be carried out on a supply chain, so that the execution effectiveness of environment management measures is weak is solved. The technical effects of accurately identifying the key carbon emission link in the supply chain and predicting the carbon emission trend of the key carbon emission link with high precision are achieved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a carbon emission optimization method and system based on green supply chain management. Background Art

[0002] In existing supply chain management practices, companies face multiple challenges, especially in terms of environmental management and carbon emission control. Specifically, traditional supply chain management systems usually focus on cost, efficiency and time optimization, while the management of environmental impacts is relatively rough, especially in the precise measurement and control of carbon emissions.

[0003] At the same time, due to insufficient data integration and analysis capabilities, existing environmental management strategies are often unable to respond to changes in supply chain operations in real time, resulting in inefficient execution and making it difficult to meet increasingly stringent environmental protection requirements.

[0004] In summary, existing technologies have the technical problem of being unable to carry out targeted emission reduction management in the supply chain, resulting in weak effectiveness of the implementation of environmental management measures. Summary of the invention

[0005] The present application provides a carbon emission optimization method and system based on green supply chain management, which is used to solve the technical problem that the existing technology is unable to carry out targeted emission reduction management of the supply chain, resulting in weak effectiveness of the implementation of environmental management measures.

[0006] In view of the above problems, the present application provides a carbon emission optimization method and system based on green supply chain management.

[0007] The first aspect of the present application provides a carbon emission optimization method based on green supply chain management, the method comprising: calling to obtain historical carbon emission data of the supply chain to be optimized; identifying and locating M key links of the supply chain to be optimized based on the historical carbon emission data, wherein the M key links have M carbon emission baseline identifiers; calling to obtain M local carbon emission data of the M key links from the historical carbon emission data, and using the M local carbon emission data to build a carbon emission prediction model; collecting environmental data for the M key links, and synchronizing the collected results to the carbon emission prediction model to perform carbon emission trend prediction, and obtain M carbon emission trend information; using the M carbon emission baselines to traverse the M carbon emission trend information, and outputting a real-time emission reduction strategy; and executing carbon emission optimization management of the supply chain to be optimized according to the real-time emission reduction strategy.

[0008] The second aspect of the present application provides a carbon emission optimization system based on green supply chain management, the system comprising: a historical data calling module, used to call and obtain historical carbon emission data of the supply chain to be optimized; a key link identification module, used to identify and locate M key links of the supply chain to be optimized based on the historical carbon emission data, wherein the M key links have M carbon emission baseline identifiers; a prediction model construction module, used to call and obtain M local carbon emission data of the M key links from the historical carbon emission data, and use the M local carbon emission data to build a carbon emission prediction model; a trend prediction execution module, used to collect environmental data for the M key links, and synchronize the collected results to the carbon emission prediction model to perform carbon emission trend prediction, and obtain M carbon emission trend information; an emission reduction strategy output module, used to traverse the M carbon emission trend information using the M carbon emission baselines, and output a real-time emission reduction strategy; an optimization management execution module, used to execute carbon emission optimization management of the supply chain to be optimized according to the real-time emission reduction strategy.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The method provided in the embodiment of the present application obtains the historical carbon emission data of the supply chain to be optimized by calling; based on the historical carbon emission data, the key links of the supply chain to be optimized are identified and located as M key links, wherein the M key links have M carbon emission baseline identifiers; the M local carbon emission data of the M key links are obtained by calling the historical carbon emission data, and the carbon emission prediction model is constructed using the M local carbon emission data; environmental data is collected for the M key links, and the collected results are synchronized to the carbon emission prediction model to predict the carbon emission trend and obtain M carbon emission trend information; the M carbon emission baselines are used to traverse the M carbon emission trend information and output a real-time emission reduction strategy; and the carbon emission optimization management of the supply chain to be optimized is executed according to the real-time emission reduction strategy. While achieving the technical effect of accurately identifying the key carbon emission links in the supply chain and being able to predict the carbon emission trends of the key carbon emission links with high precision, it also achieves the technical effect of enhancing the monitoring and analysis capabilities of carbon emission data and ensuring the timely and effective implementation of environmental management measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flow chart of the carbon emission optimization method based on green supply chain management provided for this application;

[0012] Figure 2 A schematic diagram of the process of constructing a carbon emission prediction model in the carbon emission optimization method based on green supply chain management provided in this application;

[0013] Figure 3 A schematic diagram of the structure of the carbon emission optimization system based on green supply chain management provided for this application.

[0014] Explanation of the reference numerals: historical data calling module 11, key link identification module 12, prediction model building module 13, trend prediction execution module 14, emission reduction strategy output module 15, optimization management execution module 16. DETAILED DESCRIPTION

[0015] This application provides a carbon emission optimization method and system based on green supply chain management, which is used to solve the technical problem that the existing technology cannot carry out targeted emission reduction management of the supply chain, resulting in weak effectiveness of environmental management measures. While achieving the technical effect of accurately identifying the key carbon emission links in the supply chain and being able to predict the carbon emission trends of the key carbon emission links with high precision, it also achieves the technical effect of enhancing the monitoring and analysis capabilities of carbon emission data and ensuring the timely and effective implementation of environmental management measures.

[0016] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0017] Embodiment 1, as Figure 1 As shown, the present application provides a carbon emission optimization method based on green supply chain management, the method comprising:

[0018] A100: Call to obtain historical carbon emission data of the supply chain to be optimized.

[0019] Specifically, in this embodiment, the supply chain to be optimized is the entire product or service production and distribution chain that needs to reduce carbon emissions through improvement measures, including all links from raw material procurement, production and processing to product transportation and final sales.

[0020] The historical carbon emission data is extracted by interacting with the enterprise resource planning (ERP) system of the enterprise where the supply chain to be optimized is located, and the historical carbon emission data covers the carbon emission data of the supply chain links constituting the entire supply chain to be optimized.

[0021] The historical carbon emission data provides the necessary information basis for identifying the key links of carbon emission and formulating emission reduction strategies. This embodiment elaborates on the data composition of the historical carbon emission data in the subsequent description.

[0022] A200: Based on the historical carbon emission data, identify and locate M key links of the supply chain to be optimized, wherein the M key links have M carbon emission baseline identifiers.

[0023] In one embodiment, based on the historical carbon emission data, the key links of the supply chain to be optimized are identified and M key links are located, wherein the M key links have M carbon emission baseline identifiers, and the method step A200 provided in the present application further includes:

[0024] A210: Analyze the components of the supply chain to be optimized to obtain multiple supply chain links.

[0025] A220: Taking the multiple supply chain links as constraints, the historical carbon emission data is called to obtain multiple local carbon emission data.

[0026] A230: Conduct supply chain link improvement evaluation based on the multiple local carbon emission data, and locate the M key links in the multiple supply chain links based on the improvement evaluation.

[0027] A240: Interactively obtain the M carbon emission standards of the M key links.

[0028] A250: Obtain the M local carbon emission data from the multiple local carbon emission data, and obtain M carbon emission baselines by analyzing the M carbon emission standards and the M local carbon emission data.

[0029] In one embodiment, the plurality of local carbon emission data include a plurality of carbon emission sequences, a plurality of control factor sequences and a plurality of environmental factor sequences.

[0030] In one embodiment, supply chain improvement evaluation is performed based on the multiple local carbon emission data, and the M key links are located in the multiple supply chain links based on the improvement evaluation. Step A230 of the method provided by the present application further includes:

[0031] A231: Quantitatively analyze the multiple carbon emission sequences and the multiple control factor sequences to obtain multiple groups of associated control factors and multiple groups of associated control intervals.

[0032] A232: Based on the multiple groups of related control factors and the multiple groups of related control intervals, supply chain link improvement evaluation is performed to obtain multiple control improvement coefficients.

[0033] A233: Serialize the multiple control improvement coefficients, and locate the M key links in the multiple supply chain links based on the sorting results.

[0034] Specifically, in this embodiment, the component analysis of the supply chain to be optimized is performed to identify multiple supply chain links included in the entire supply chain, and the multiple supply chain links include but are not limited to one or more raw material procurement, production and processing, transportation, distribution, and recycling, etc. The purpose of the component analysis of the supply chain to be optimized is to provide a clear structural framework for subsequent data calling and key link identification.

[0035] After identifying the components of the supply chain, the multiple supply chain links are used as constraints to extract local carbon emission data directly related to each link from the historical carbon emission data to obtain multiple local carbon emission data of the multiple supply chain links.

[0036] In this embodiment, each of the plurality of local carbon emission data has the same data structure, including a carbon emission sequence, a control factor sequence, and an environmental factor sequence.

[0037] Among them, the carbon emission sequence is a time series record of carbon emission data generated in the supply chain, which may come from direct emission measurements, such as direct monitoring of CO2 during fuel combustion, or indirect calculations, such as calculations based on electricity consumption and the average emission factor of the power grid. Among them, the control factor sequence includes the time series records of operational variable data that affect carbon emissions, such as energy consumption, production rate, machine operation efficiency, etc. Among them, the environmental factor sequence refers to the time series records of external environmental parameters that may affect energy consumption and carbon emission efficiency.

[0038] At the same time, the above carbon emission sequence, control factor sequence and environmental factor sequence are synchronized in specific time dimensions.

[0039] By conducting a detailed quantitative analysis of carbon emission sequences, control factors and environmental factors, we can identify key links with high carbon emissions and potential for optimization, and then formulate and implement effective emission reduction measures for these links to optimize the environmental performance of the entire supply chain.

[0040] The specific method for locating the M key links in the multiple supply chain links is as follows:

[0041] For the carbon emission sequence and control factor sequence of each link, linear and nonlinear regression analysis is used to explore the relationship between control factors (such as energy utilization efficiency and production rate) and carbon emissions, and a set of associated control intervals corresponding to a set of associated control factors in each supply chain link is obtained.

[0042] It should be understood that the associated control factors are control factors whose numerical changes cause changes in carbon emissions in the supply chain, and the associated control intervals are specific operable parameter adjustment intervals of the control factors.

[0043] A method for evaluating supply chain improvement on the first supply chain link and obtaining multiple control improvement coefficients is to extract the number of control factors and the span of control parameter values ​​for the first group of associated control factors and the first group of associated control intervals in the first supply chain link to obtain the number of control factors and multiple spans of control factor values.

[0044] After taking values ​​of multiple control factors with the same dimension, the mean is calculated, and the calculation result is multiplied by the number of control factors as the first control improvement coefficient.

[0045] By analogy, supply chain improvement evaluation is performed based on the multiple groups of associated control factors and the multiple groups of associated control intervals to obtain multiple control improvement coefficients.

[0046] The multiple control improvement coefficients are serialized from large to small, and the M key links corresponding to the multiple supply chain links at the first M control improvement coefficients are extracted based on the sorting result.

[0047] This embodiment scientifically identifies the links in the supply chain that have a greater impact on carbon emissions in the above manner, achieving the technical effect of providing a basis for subsequently implementing effective emission reduction measures for these links to optimize the environmental performance of the entire supply chain.

[0048] By interacting with the standard setting organization, M carbon emission standards for the M key links are obtained, and the carbon emission standard refers to the industry-recognized carbon emission limit or target for a specific supply chain link.

[0049] Based on the foregoing, it can be known that the data structure of each of the multiple local carbon emission data is the same, including a carbon emission sequence, a control factor sequence and an environmental factor sequence. This embodiment obtains the M local carbon emission data by calling the multiple local carbon emission data, and extracts M carbon emission sequences representing the historical carbon emission performance of M key links from the M local carbon emission data.

[0050] The M carbon emission sequences are standardized, for example, energy consumption is converted into standard CO2 emissions to obtain M standard carbon emission sequences, and then the average values ​​of the M standard carbon emission sequences are calculated to obtain M average carbon emissions.

[0051] A carbon emission deviation threshold is preset, and M carbon emission deviations between M average carbon emissions and the M carbon emission standards are calculated. If the carbon emission deviation of a key link falls within the carbon emission deviation threshold, the carbon emission baseline of the key link is the corresponding carbon emission standard. If it does not fall within the carbon emission deviation threshold, the carbon emission baseline of the key link is the average of the carbon emission standard and the carbon emission deviation. By analogy, M carbon emission baselines of M key links are obtained.

[0052] This embodiment achieves the technical effect of providing a basis for the formulation and evaluation of subsequent carbon emission monitoring and emission reduction measures by analyzing and determining the key links of the supply chain to be optimized and the carbon emission baselines of the key links.

[0053] A300: Obtain M local carbon emission data of the M key links from the historical carbon emission data, and construct a carbon emission prediction model using the M local carbon emission data.

[0054] In one embodiment, Figure 2 As shown, the M local carbon emission data of the M key links are obtained by calling the historical carbon emission data, and the carbon emission prediction model is constructed by using the M local carbon emission data. The method step A300 provided in the present application also includes:

[0055] A310: Decompose the M local carbon emission data to obtain M carbon emission sequences and M environmental factor sequences.

[0056] A320: Perform data alignment of the M carbon emission sequences and the M environmental factor sequences according to the carbon emission monitoring window to obtain M groups of associated carbon emission data, wherein each group of associated carbon emission data in the M groups includes multiple sample carbon emissions and multiple sample environmental factors.

[0057] A330: Construct a standard prediction model based on a back-propagation neural network, and use the M groups of associated carbon emission data as training data to optimize the parameters of the standard prediction model to obtain M carbon emission prediction branches.

[0058] A340: Connect the M carbon emission prediction branches in parallel to complete the construction of the carbon emission prediction model.

[0059] Specifically, in this embodiment, the carbon emission monitoring window refers to the shortest duration during which the carbon emissions remain unchanged or change very little. M carbon emission sequences are extracted based on the M local carbon emission data, and statistical change point detection methods (such as Cusum detection or change point detection based on a regression model) are applied to identify significant changes in the carbon emission data, determine the time points when major changes occur in the M carbon emission sequences, and obtain M groups of change nodes.

[0060] The time between adjacent change nodes of M groups of change nodes is calculated to obtain M groups of change time distances, and the shortest time distance is extracted from the M groups of change time distances as the carbon emission monitoring window. The carbon emission monitoring window is the shortest duration during which carbon emissions do not change.

[0061] The M local carbon emission data are disassembled to obtain M carbon emission sequences and M environmental factor sequences. After the M carbon emission sequences and the M environmental factor sequences are aligned in time, the instantaneous data intervals of the M carbon emission sequences and the M environmental factor sequences are collected based on the carbon emission monitoring window to obtain the M groups of associated carbon emission data, wherein each group of associated carbon emission data in the M groups of associated carbon emission data includes multiple sample carbon emissions and multiple sample environmental factors.

[0062] A standard prediction model is constructed based on a back propagation neural network, wherein the input data of the standard prediction model is environmental factors and the output result is a carbon emission prediction. The conventional training method of the back propagation neural network is adopted, and the M groups of associated carbon emission data are used as training data to perform parameter optimization of the standard prediction model to obtain M carbon emission prediction branches.

[0063] The M carbon emission prediction branches constructed in the A330 are connected in parallel and integrated into a complete carbon emission prediction model. Such parallel connection enables the model to integrate data from multiple key links and provide a more accurate overall carbon emission prediction.

[0064] The method provided in this embodiment combines time series data processing, statistical analysis and neural network prediction, achieving the technical effect of effectively improving the accuracy of carbon emission data monitoring and the ability to predict carbon emissions.

[0065] A400: Collect environmental data for the M key links, and synchronize the collected results to the carbon emission prediction model to predict the carbon emission trend, so as to obtain M carbon emission trend information.

[0066] In one embodiment, before collecting environmental data for the M key links, the method step A400 provided in the present application further includes:

[0067] A410: Interactively obtain M associated environment data of the M key links.

[0068] A420: Perform sensor configuration based on the M associated environmental data as constraints to obtain M carbon emission monitoring nodes.

[0069] A430: Perform carbon emission change analysis based on the M local carbon emission data to obtain a carbon emission monitoring window.

[0070] A440: The M carbon emission monitoring nodes collect environmental data for the M key links based on the emission monitoring window to obtain M environmental related time series data.

[0071] In one embodiment, the sensor configuration is performed based on the M associated environmental data as constraints to obtain M carbon emission monitoring nodes. Step A420 of the method provided by the present application further includes:

[0072] A421: Perform extreme value calls on the M environment-related time series data to obtain M groups of environment-related extreme values.

[0073] A422: Interactively obtain multiple sample fitness data of multiple sample sensors.

[0074] A423: Group the plurality of sample sensors based on sensor type to obtain a plurality of groups of sample sensors corresponding to the plurality of sensors.

[0075] A424: The multiple sensors, multiple groups of sample sensors and multiple sample adaptability data are stored in association with each other based on the knowledge graph to generate a sensor information library.

[0076] A425: Use the M groups of environment-related extreme values ​​to traverse the sensor information database to obtain M groups of adapted sensors.

[0077] A426: Integrate the M groups of adaptive sensors to obtain the M carbon emission monitoring nodes.

[0078] Specifically, in this embodiment, the M local carbon emission data are disassembled to obtain M carbon emission sequences and M environmental factor sequences, and then the M environmental factor sequences are aggregated based on the environmental factor types to obtain M associated environmental data, wherein each environmental associated data includes multiple environmental factor measured values ​​of multiple environmental factor types.

[0079] The M environment-related time series data are extreme value called to obtain M groups of environment-related extreme values, each group of environment-related extreme values ​​including maximum values ​​and minimum values ​​of environmental factors of multiple types of environmental factors.

[0080] Interactively obtain multiple sample adaptability data of multiple sample sensors. Group the multiple sample sensors based on sensor type to obtain multiple groups of sample sensors corresponding to multiple sensors. Based on the knowledge graph, the multiple sensors, multiple groups of sample sensors and multiple sample adaptability data are associated and stored to establish a comprehensive sensor information library to support sensor selection and configuration. Use the M groups of environmental association extreme values ​​to traverse the sensor information library to obtain M groups of adapted sensors, wherein each adapted sensor corresponds to the maximum value and minimum value of the environmental factor that adapt to the type of environmental factor collected. Integrate the M groups of adapted sensors to obtain the M carbon emission monitoring nodes.

[0081] Based on the M local carbon emission data, M carbon emission sequences are extracted, and a statistical change point detection method (such as Cusum detection or change point detection based on a regression model) is applied to identify significant changes in the carbon emission data, determine the time points when major changes occur in the M carbon emission sequences, and obtain M groups of change nodes.

[0082] The time between adjacent change nodes of M groups of change nodes is calculated to obtain M groups of change time distances, and the shortest time distance is extracted from the M groups of change time distances as the carbon emission monitoring window. The carbon emission monitoring window is the shortest duration during which carbon emissions do not change.

[0083] The M carbon emission monitoring nodes take the emission monitoring window as a constraint, intermittently collect environmental data for the M key links, and obtain M environmental-related time series data as collection results.

[0084] According to the mapping relationship between M environment-related time series data and M key links, the M environment-related time series data are mapped and synchronized to the M carbon emission prediction branches of the carbon emission prediction model to perform carbon emission trend predictions respectively, and M carbon emission trend information are obtained, wherein the carbon emission trend information is the expected change in carbon emissions in a certain period in the future (the time span of the emission monitoring window).

[0085] This embodiment has the technical effect of predicting carbon emission trends based on building a carbon emission prediction model, providing guidance for subsequent carbon emission optimization management of the supply chain to be optimized.

[0086] A500: Use the M carbon emission baselines to traverse the M carbon emission trend information and output a real-time emission reduction strategy.

[0087] A600: Execute carbon emission optimization management of the supply chain to be optimized according to the real-time emission reduction strategy.

[0088] Specifically, in this embodiment, the M carbon emission baselines are used to traverse the M carbon emission trend information, and K key links whose carbon emission trends exceed the corresponding carbon emission baselines are screened out. The K key links constitute the real-time emission reduction strategy.

[0089] The carbon emission optimization management of the supply chain to be optimized is executed with reference to the real-time emission reduction strategy, and specific carbon emission optimization measures are executed, involving production line adjustments of K key links, logistics route optimization and other measures.

[0090] This embodiment achieves the technical effect of accurately identifying key carbon emission links in the supply chain and predicting the carbon emission trends of key carbon emission links with high precision, while also achieving the technical effect of enhancing the monitoring and analysis capabilities of carbon emission data and ensuring the timely and effective implementation of environmental management measures.

[0091] Embodiment 2 is based on the same inventive concept as the carbon emission optimization method based on green supply chain management in the above embodiment. Figure 3 As shown, the present application provides a carbon emission optimization system based on green supply chain management, wherein the system includes:

[0092] The historical data calling module 11 is used to call and obtain the historical carbon emission data of the supply chain to be optimized.

[0093] The key link identification module 12 is used to identify and locate M key links of the supply chain to be optimized based on the historical carbon emission data, wherein the M key links have M carbon emission baseline identifiers.

[0094] The prediction model building module 13 is used to obtain the M local carbon emission data of the M key links from the historical carbon emission data, and use the M local carbon emission data to build a carbon emission prediction model.

[0095] The trend prediction execution module 14 is used to collect environmental data for the M key links, and synchronize the collection results to the carbon emission prediction model to perform carbon emission trend prediction, so as to obtain M carbon emission trend information.

[0096] The emission reduction strategy output module 15 is used to traverse the M carbon emission trend information using the M carbon emission baselines and output a real-time emission reduction strategy.

[0097] The optimization management execution module 16 is used to execute the carbon emission optimization management of the supply chain to be optimized according to the real-time emission reduction strategy.

[0098] In one embodiment, the trend prediction execution module 14 further includes:

[0099] Interactively obtain M associated environmental data of the M key links; configure sensors with the M associated environmental data as constraints to obtain M carbon emission monitoring nodes; perform carbon emission change analysis based on the M local carbon emission data to obtain a carbon emission monitoring window; the M carbon emission monitoring nodes collect environmental data for the M key links with the emission monitoring window as a constraint to obtain M environmental associated time series data.

[0100] In one embodiment, the trend prediction execution module 14 further includes:

[0101] Perform extreme value calls on the M environment-related time series data to obtain M groups of environment-related extreme values; interactively obtain multiple sample adaptability data of multiple sample sensors; group the multiple sample sensors based on sensor type to obtain multiple groups of sample sensors corresponding to multiple sensors; store the multiple sensors, multiple groups of sample sensors and multiple sample adaptability data based on the knowledge graph association to generate a sensor information library; use the M groups of environment-related extreme values ​​to traverse the sensor information library to obtain M groups of adapted sensors; integrate the M groups of adapted sensors to obtain the M carbon emission monitoring nodes.

[0102] In one embodiment, the key link identification module 12 further includes:

[0103] Perform component analysis on the supply chain to be optimized to obtain multiple supply chain links; use the multiple supply chain links as constraints to call the historical carbon emission data to obtain multiple local carbon emission data; evaluate supply chain link improvements based on the multiple local carbon emission data, and locate the M key links in the multiple supply chain links based on the improvement evaluation; interactively obtain M carbon emission standards for the M key links; obtain the M local carbon emission data by calling the multiple local carbon emission data, and obtain M carbon emission baselines by analyzing the M carbon emission standards and the M local carbon emission data.

[0104] In one embodiment, the key link identification module 12 further includes:

[0105] The multiple local carbon emission data include multiple carbon emission sequences, multiple control factor sequences and multiple environmental factor sequences.

[0106] In one embodiment, the key link identification module 12 further includes:

[0107] Quantitatively analyze the multiple carbon emission sequences and the multiple control factor sequences to obtain multiple groups of associated control factors and multiple groups of associated control intervals; evaluate supply chain link improvements based on the multiple groups of associated control factors and multiple groups of associated control intervals to obtain multiple control improvement coefficients; serialize the multiple control improvement coefficients, and locate the M key links in the multiple supply chain links based on the sorting results.

[0108] In one embodiment, the prediction model building module 13 further includes:

[0109] Disassemble the M local carbon emission data to obtain M carbon emission sequences and M environmental factor sequences; perform data alignment of the M carbon emission sequences and the M environmental factor sequences according to the carbon emission monitoring window to obtain M groups of associated carbon emission data, wherein each group of associated carbon emission data in the M groups of associated carbon emission data includes multiple sample carbon emissions and multiple sample environmental factors; construct a standard prediction model based on a back propagation neural network, and use the M groups of associated carbon emission data as training data to perform parameter optimization of the standard prediction model to obtain M carbon emission prediction branches; connect the M carbon emission prediction branches in parallel to complete the construction of the carbon emission prediction model.

[0110] Any of the methods or steps described above may be stored as computer instructions or programs in various types of computer memories, and the computer instructions or programs may be recognized by various types of computer processors to implement any of the methods or steps described above.

[0111] Based on the above specific embodiments of the present invention, any improvements and modifications made to the present invention by those skilled in the art without departing from the principles of the present invention shall fall within the patent protection scope of the present invention.

Claims

1. A carbon emission optimization method based on green supply chain management, characterized in that: The method comprises: Call to obtain historical carbon emission data of the supply chain to be optimized; Based on the historical carbon emission data, identify and locate M key links of the supply chain to be optimized, wherein the M key links have M carbon emission baseline identifiers; Obtaining M local carbon emission data of the M key links from the historical carbon emission data, and constructing a carbon emission prediction model using the M local carbon emission data; Collect environmental data for the M key links, and synchronize the collected results to the carbon emission prediction model to perform carbon emission trend prediction, so as to obtain M carbon emission trend information; Using the M carbon emission baselines to traverse the M carbon emission trend information, and outputting a real-time emission reduction strategy; Carbon emission optimization management of the supply chain to be optimized is performed according to the real-time emission reduction strategy.

2. The method according to claim 1, characterized in that Before collecting environmental data for the M key links, the method further includes: Interactively obtain M associated environment data of the M key links; Perform sensor configuration based on the M associated environmental data as constraints to obtain M carbon emission monitoring nodes; Perform carbon emission change analysis based on the M local carbon emission data to obtain a carbon emission monitoring window; The M carbon emission monitoring nodes collect environmental data for the M key links based on the emission monitoring window, and obtain M environmental related time series data.

3. The method according to claim 2, characterized in that The sensor configuration is performed with the M associated environmental data as constraints to obtain M carbon emission monitoring nodes, and the method further includes: Perform extreme value calling on the M environment-related time series data to obtain M groups of environment-related extreme values; interactively obtaining a plurality of sample adaptability data of a plurality of sample sensors; grouping the plurality of sample sensors based on sensor type to obtain a plurality of groups of sample sensors corresponding to a plurality of sensors; The plurality of sensors, the plurality of groups of sample sensors and the plurality of sample adaptability data are stored in association based on the knowledge graph to generate a sensor information library; Using the M groups of environment-related extreme values ​​to traverse the sensor information database, obtaining M groups of matching sensors; Integrate the M groups of adaptive sensors to obtain the M carbon emission monitoring nodes.

4. The method according to claim 2, characterized in that Based on the historical carbon emission data, the key links of the supply chain to be optimized are identified and M key links are located, wherein the M key links have M carbon emission baseline identifiers, and the method further includes: Analyzing the components of the supply chain to be optimized to obtain multiple supply chain links; Taking the multiple supply chain links as constraints, calling the historical carbon emission data to obtain multiple local carbon emission data; Performing supply chain link improvement evaluation based on the multiple local carbon emission data, and locating the M key links in the multiple supply chain links based on the improvement evaluation; Interactively obtain M carbon emission standards of the M key links; The M local carbon emission data are obtained by calling from the multiple local carbon emission data, and M carbon emission baselines are obtained by analyzing the M carbon emission standards and the M local carbon emission data.

5. The method according to claim 4, characterized in that The multiple local carbon emission data include multiple carbon emission sequences, multiple control factor sequences and multiple environmental factor sequences.

6. The method according to claim 5, characterized in that Based on the multiple local carbon emission data, supply chain link improvement evaluation is performed, and based on the improvement evaluation, the M key links are located in the multiple supply chain links, and the method further includes: Quantitatively analyzing the multiple carbon emission sequences and the multiple control factor sequences to obtain multiple groups of associated control factors and multiple groups of associated control intervals; Based on the multiple groups of associated control factors and the multiple groups of associated control intervals, an improvement evaluation of the supply chain link is performed to obtain multiple control improvement coefficients; The multiple control improvement coefficients are serialized, and the M key links are located in the multiple supply chain links based on the sequencing results.

7. The method according to claim 5, characterized in that The M local carbon emission data of the M key links are obtained by calling the historical carbon emission data, and the carbon emission prediction model is constructed by using the M local carbon emission data. The method further includes: Decomposing the M local carbon emission data to obtain M carbon emission sequences and M environmental factor sequences; Performing data alignment of the M carbon emission sequences and the M environmental factor sequences according to the carbon emission monitoring window to obtain M groups of associated carbon emission data, wherein each group of associated carbon emission data in the M groups of associated carbon emission data includes multiple sample carbon emissions and multiple sample environmental factors; Building a standard prediction model based on a back propagation neural network, and using the M groups of associated carbon emission data as training data to perform parameter optimization on the standard prediction model to obtain M carbon emission prediction branches; The M carbon emission prediction branches are connected in parallel to complete the construction of the carbon emission prediction model.

8. The carbon emission optimization system based on green supply chain management is characterized by: The system for implementing the carbon emission optimization method based on green supply chain management according to any one of claims 1 to 7 comprises: A historical data calling module is used to call and obtain the historical carbon emission data of the supply chain to be optimized; A key link identification module, used to identify and locate M key links of the supply chain to be optimized based on the historical carbon emission data, wherein the M key links have M carbon emission baseline identifiers; A prediction model building module, used to obtain M local carbon emission data of the M key links from the historical carbon emission data, and to build a carbon emission prediction model using the M local carbon emission data; A trend prediction execution module is used to collect environmental data for the M key links, and synchronize the collected results to the carbon emission prediction model to perform carbon emission trend prediction, so as to obtain M carbon emission trend information; An emission reduction strategy output module, configured to use the M carbon emission baselines to traverse the M carbon emission trend information and output a real-time emission reduction strategy; The optimization management execution module is used to execute the carbon emission optimization management of the supply chain to be optimized according to the real-time emission reduction strategy.

Images