Electrician equipment manufacturing industry product carbon footprint accounting system based on large model

Abstract

The invention discloses an electrical equipment manufacturing industry product carbon footprint accounting system based on a large model. The system comprises a data integration module, a large model intelligent carbon footprint analysis module, a carbon footprint optimization module and a cross-system collaboration and data sharing module. The data integration module is used for collecting and integrating life cycle data generated in the electrical equipment manufacturing process from a plurality of sources; the large-model intelligent carbon footprint analysis module is used for automatically processing and analyzing the integrated data and accurately calculating the carbon footprint of the product through advanced big data analysis and artificial intelligence technologies; the carbon footprint optimization module is used for providing targeted emission reduction suggestions and optimization schemes based on the carbon footprint analysis result; and the cross-system collaboration and data sharing module is used for promoting seamless connection and data sharing among different systems and ensuring smooth collaboration of links in the carbon footprint accounting process.

Description

Technical Field

[0001] The present application relates to data analysis and database technology, which can be applied to the field of carbon footprint accounting, and more specifically, to a carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model. Background Art

[0002] my country has elevated the response to climate change to a national strategic level and incorporated it into the overall layout of ecological civilization construction. All walks of life are actively exploring carbon reduction paths and implementation plans. However, in the manufacturing of electrical equipment, which is a typical discrete industry, its design and manufacturing are often based on the specific requirements of contract orders. The structure and composition of different batches of the same product may be different. In addition, there are many types of parts and complex processes, making the calculation of carbon footprint extremely complicated.

[0003] At present, manual calculation or the use of LCA software on the market to model and calculate the carbon footprint of products often requires manual collection and organization of a large amount of data and product modeling in the early stage. This not only leads to a long work cycle and low efficiency, but also requires re-modeling and data collection every time the product is replaced, and the degree of intelligence is low. Summary of the invention

[0004] In order to improve the accuracy of carbon emission accounting, the present application provides a carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model.

[0005] In order to achieve the above-mentioned purpose, the embodiment of the present application proposes a carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model, including: a data integration module, a large model intelligent carbon footprint analysis module, a carbon footprint optimization module, and a cross-system collaboration and data sharing module; wherein,

[0006] The data integration module is used to collect and integrate life cycle data generated during the manufacturing process of electrical equipment from multiple sources, including energy consumption, raw material procurement, production and manufacturing, and logistics and transportation; this ensures the integrity and accuracy of the data and provides a basis for subsequent carbon footprint accounting;

[0007] The large-model intelligent carbon footprint analysis module is used to automatically process and analyze the integrated data through advanced big data analysis and artificial intelligence technology to accurately calculate the carbon footprint of the product; it identifies key carbon emission links through intelligent algorithms to provide a scientific basis for subsequent carbon footprint optimization;

[0008] The carbon footprint optimization module is used to provide targeted emission reduction suggestions and optimization solutions based on the carbon footprint analysis results, helping enterprises to implement effective carbon emission reduction measures in various links such as production, operation, and supply chain management, reduce product carbon footprint, and improve the environmental performance of enterprises;

[0009] The cross-system collaboration and data sharing module is used to promote seamless connection and data sharing between different systems, ensuring smooth collaboration in all aspects of the carbon footprint accounting process. Through open API interfaces and data exchange standards, it can achieve integration with internal enterprise systems such as ERP, MES, SCM, and share external data with other enterprises or institutions, promoting the standardization and collaboration of carbon footprint accounting.

[0010] Wherein, the system further comprises: a carbon footprint visualization module;

[0011] The carbon footprint visualization module is used to convert complex carbon footprint data into intuitive and easy-to-understand charts and graphs.

[0012] The data integration module can integrate multiple data sources, including the company's internal R&D and design system, production system, supply chain management system, and external public databases, to fully cover the entire product life cycle from raw material procurement to waste disposal;

[0013] Among them, the data integration module uses regular expression matching, logical verification, data completion and other technical means to clean the original data, remove duplicate, erroneous, invalid or abnormal data items, ensure the accuracy and consistency of the data, standardize the data, and eliminate format differences between different data sources.

[0014] According to the preset data standards, the data formats from different data sources are uniformly converted into the standard format within the system, including but not limited to: data type, timestamp format, unit conversion;

[0015] The data integration module uses the distributed storage system Hadoop HDFS to store massive carbon footprint data; and uses the real-time stream processing framework Apache Kafka to process real-time data streams.

[0016] The large-model intelligent carbon footprint analysis module is used to build a product carbon footprint prediction and analysis model based on machine learning and deep learning algorithms; the large-model intelligent carbon footprint analysis module not only learns the laws and characteristics of carbon emissions at various stages of the product life cycle by training historical carbon emission data, but also introduces a variety of deep learning architectures to enhance the data feature extraction and pattern recognition capabilities; in the model training process, the deep learning architecture is used in combination with the ensemble learning method to gradually adjust the model parameters, minimize the prediction error and improve the prediction performance and robustness of the model; the deep learning architecture includes: recurrent neural network RNN, deep neural network DNN; the ensemble learning methods include: gradient boosting tree GBDT and random forest Random Forest;

[0017] In terms of feature engineering, the large-model intelligent carbon footprint analysis module first uses a deep learning model to automatically learn and extract high-level features from the original data, and then uses a random forest to evaluate the importance of these features and screen out the features that have the greatest impact on the prediction target. Afterwards, these selected features are used as input to train the gradient boosting tree model;

[0018] In terms of model fusion, in addition to using stacking technology combined with random forests and gradient boosting trees, the prediction results of deep learning models are also introduced as additional features;

[0019] In the parallel and serial combination strategy, the deep learning model is used for preliminary feature extraction and prediction, and its results are then used to weight or filter samples to optimize the training of the gradient boosting tree model;

[0020] The entire model is trained using a historical carbon emissions dataset through supervised learning, and its parameters are continuously optimized through multiple iterations of training;

[0021] Among them, the introduction of the deep learning architecture of the large-model intelligent carbon footprint analysis module significantly enhances the model's ability to capture complex patterns and nonlinear relationships.

[0022] Among them, the carbon footprint optimization module is used to analyze possible emission reduction strategies and measures based on the carbon footprint accounting results and combined with industry best practices and expertise; and use recommendation algorithms to automatically generate personalized emission reduction optimization suggestions based on the company's actual situation and goals, including but not limited to: production process improvements, energy structure optimization, and logistics efficiency improvements.

[0023] Among them, the cross-system collaboration and data sharing module is used to provide a standard API interface, support the connection with the company's existing ERP, MES, SCM and other systems, establish a cross-system collaboration and data sharing mechanism, and realize automatic transmission and sharing of data; wherein the cross-system collaboration and data sharing module is also used to provide flexible data access permission settings, and adopt blockchain technology to ensure data security and privacy protection.

[0024] Among them, the carbon footprint visualization module is used to display the total carbon emissions of the product throughout its life cycle, the emission proportion of each link, and trend change information; and the carbon footprint visualization module has interactive analysis tools to enable users to deeply explore carbon footprint data through screening, sorting, and comparison operations to discover potential emission reduction opportunities.

[0025] The beneficial effects of the above technical solution of the present application are as follows: The above technical solution enables enterprises to not only clearly understand the carbon footprint of products, but also to grasp the changing trend of carbon emissions in real time, providing strong support for the formulation and implementation of effective carbon reduction measures. Enterprises can optimize product design, adjust production processes, choose more environmentally friendly transportation methods, etc. according to the analysis results of the system, so as to reduce carbon footprint. In addition, the application of this system will also help promote data sharing and collaboration between enterprises and upstream and downstream industrial chains, and jointly explore new green and low-carbon profit models. For example, enterprises can share carbon footprint data with suppliers to jointly find more environmentally friendly materials and components; or share product carbon footprint information with customers to provide them with a more comprehensive selection of environmentally friendly products. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic diagram of a large model application technology route of an embodiment of the present application;

[0027] Figure 2 A schematic diagram of the carbon footprint calculation process of an embodiment of the present application;

[0028] Figure 3 This is a schematic diagram of the full life cycle carbon element feature extraction of an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the technical problems, technical solutions and advantages to be solved by the present application clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0030] This application discloses a carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model, which can accurately, efficiently and intelligently calculate the carbon footprint of products in the electrical equipment manufacturing industry to support the green, low-carbon transformation and sustainable development of enterprises. The carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model in the embodiment of this application includes: a data integration module, a large model intelligent carbon footprint analysis module, a carbon footprint visualization module, a carbon footprint optimization module, and a cross-system collaboration and data sharing module; among them,

[0031] The data integration module is used to collect and integrate life cycle data generated during the manufacturing process of electrical equipment from multiple sources, including energy consumption, raw material procurement, production and manufacturing, and logistics and transportation; this ensures the integrity and accuracy of the data and provides a basis for subsequent carbon footprint accounting;

[0032] The large-model intelligent carbon footprint analysis module is used to automatically process and analyze integrated data through advanced big data analysis and artificial intelligence technology to accurately calculate the carbon footprint of products. It identifies key carbon emission links through intelligent algorithms to provide a scientific basis for subsequent carbon footprint optimization.

[0033] Carbon footprint visualization module, which converts complex carbon footprint data into intuitive and easy-to-understand charts and graphs, so that managers and stakeholders can understand the carbon footprint distribution of products at a glance, facilitate rapid identification of emission reduction potential, and improve communication efficiency;

[0034] The carbon footprint optimization module is used to provide targeted emission reduction suggestions and optimization solutions based on the carbon footprint analysis results, helping enterprises to implement effective carbon emission reduction measures in various links such as production, operation, and supply chain management, reduce product carbon footprint, and improve the environmental performance of enterprises;

[0035] The cross-system collaboration and data sharing module is used to promote seamless connection and data sharing between different systems, ensuring smooth collaboration in all aspects of the carbon footprint accounting process. Through open API interfaces and data exchange standards, it can achieve integration with internal enterprise systems such as ERP, MES, SCM, and share external data with other enterprises or institutions, promoting the standardization and collaboration of carbon footprint accounting.

[0036] Furthermore, the data integration module can integrate multiple data sources, including the company's internal R&D and design systems, production systems, supply chain management systems, and external public databases, such as emission factors and industry average data from authoritative databases such as IPCC, CLCD, and Ecoinvent, comprehensively covering the entire life cycle of products from raw material procurement to waste disposal.

[0037] Use regular expression matching, logical verification, data completion and other technical means to clean the original data, remove duplicate, erroneous, invalid or abnormal data items, ensure the accuracy and consistency of the data, standardize the data, and eliminate format differences between different data sources.

[0038] According to the preset data standards, the data formats from different data sources are uniformly converted into the standard format within the system, including data type, timestamp format, unit conversion, etc., to facilitate subsequent processing and analysis.

[0039] The distributed storage system Hadoop HDFS is used to store massive carbon footprint data to improve data access efficiency and scalability. The real-time stream processing framework Apache Kafka is used to process real-time data streams to ensure the instant capture and analysis of carbon emission data in the production process.

[0040] Among them, the large-model intelligent carbon footprint analysis module builds a product carbon footprint prediction and analysis model based on machine learning and deep learning algorithms. This model not only learns the laws and characteristics of carbon emissions at each stage of the product life cycle by training historical carbon emission data, but also specifically introduces a variety of deep learning architectures to enhance the feature extraction and pattern recognition capabilities of the data. In the model training process, deep learning architectures (recurrent neural network RNN, deep neural network DNN) and ensemble learning methods (gradient boosted tree GBDT and random forest Random Forest) are cleverly combined. By gradually adjusting the model parameters, it aims to minimize the prediction error and improve the prediction performance and robustness of the model.

[0041] The specific strategies used include:

[0042] In terms of feature engineering, we first use deep learning models to automatically learn and extract high-level features from raw data, and then use random forests to evaluate the importance of these features and select the features that have the greatest impact on the prediction target. After that, these selected features are used as input to train the gradient boosting tree model. This method not only reduces the dimensionality and noise of the input features, but also significantly improves the training efficiency and prediction performance of the gradient boosting tree model.

[0043] In terms of model fusion, in addition to using stacking technology combined with random forest and gradient boosting tree, the prediction results of deep learning models are also introduced as additional features. This hybrid method can more effectively integrate the advantages of various models and further reduce the risk of overfitting.

[0044] In the parallel and serial combination strategy, the deep learning model is used for preliminary feature extraction and prediction, and its results are then used to weight or screen samples to optimize the training of the gradient boosting tree model. This strategy combines the fast feature extraction capability of the deep learning model with the high-precision prediction of the gradient boosting tree.

[0045] The entire model is trained using historical carbon emission data sets through supervised learning, and its parameters are continuously optimized through multiple iterations of training. This enables the model to accurately identify and learn the carbon emission patterns of different types of products at different production stages and scales.

[0046] It is worth mentioning that the introduction of deep learning architecture significantly enhances the model's ability to capture complex patterns and nonlinear relationships. This makes the model more accurate in predicting the carbon footprint of a given product over its life cycle. At the same time, the model also demonstrates strong analytical capabilities, able to distinguish and quantify in detail the contribution of different production stages to the total carbon footprint, providing strong support for the formulation of subsequent emission reduction strategies.

[0047] The carbon footprint visualization module designs intuitive and easy-to-understand multi-dimensional carbon footprint reports, showing the total carbon emissions of the product throughout its life cycle, the proportion of emissions in each link, trend changes, etc. It provides interactive analysis tools, allowing users to deeply explore carbon footprint data through filtering, sorting, comparison and other operations to discover potential emission reduction opportunities.

[0048] The carbon footprint optimization module analyzes possible emission reduction strategies and measures based on the carbon footprint calculation results, combined with industry best practices and expertise. Using the recommendation algorithm, it automatically generates personalized emission reduction optimization suggestions based on the actual situation and goals of the enterprise, including production process improvement, energy structure optimization, logistics efficiency improvement and other aspects.

[0049] The cross-system collaboration and data sharing module provides a standard API interface to support the connection with the company's existing ERP, MES, SCM and other systems to achieve automatic data transmission and sharing. A cross-system collaboration and data sharing mechanism is established to ensure that carbon footprint data between various departments within the company and external partners can be seamlessly connected and shared. At the same time, flexible data access permission settings are provided, and blockchain technology is used to ensure data security and privacy protection.

[0050] In order to meet this challenge and improve the carbon management capabilities and intelligence level of enterprises, the present invention proposes a carbon footprint accounting system and system for electrical equipment manufacturing products based on large models. The core of the system lies in its integration of advanced large model technology, which enables the system to accurately quantify the carbon footprint of the product throughout its life cycle, from raw material procurement, production and manufacturing, transportation and distribution to use and consumption, and waste disposal. Specifically, the system ensures the timeliness and accuracy of carbon footprint data through real-time data stream processing and dynamic adjustment mechanisms. Whether it is a BOM change in the product design stage, or a change in energy consumption or adjustment of transportation methods during the production and manufacturing process, the system can capture these data changes in real time and dynamically update the carbon footprint calculation results.

[0051] At the same time, the system of the present invention is integrated with the LCA background database. The system can make full use of the industry average data and environmental impact factor data in the LCA background database. These data provide a more accurate and comprehensive basis for carbon footprint accounting. Since the system can automatically obtain and update relevant data from the LCA background database, the efficiency and accuracy of the accounting are improved.

[0052] Through the implementation of the present invention, enterprises can not only clearly understand the carbon footprint of their products, but also grasp the changing trends of carbon emissions in real time, providing strong support for the formulation and implementation of effective carbon reduction measures. Enterprises can optimize product design, adjust production processes, choose more environmentally friendly transportation methods, etc. according to the analysis results of the system, so as to achieve a reduction in carbon footprint. In addition, the application of this system will also help promote data sharing and collaboration between enterprises and upstream and downstream industrial chains, and jointly explore new green and low-carbon profit models. For example, enterprises can share carbon footprint data with suppliers to jointly find more environmentally friendly materials and parts; or share product carbon footprint information with customers to provide them with a more comprehensive selection of environmentally friendly products.

[0053] In order to verify the effectiveness and practicality of the carbon footprint accounting system for electrical equipment products based on a large model proposed by the present invention, we selected a typical high-voltage switchgear as an implementation example to calculate the carbon footprint. This high-voltage switchgear involves multiple complex links in the production process, including raw material procurement, precision processing, and long-distance transportation, so it is very suitable for demonstrating the application effect of the present invention.

[0054] Step 1: Clarify accounting objectives and scope

[0055] In order to accurately calculate the carbon footprint of the entire life cycle of high-voltage switchgear, we first clarify the calculation target, that is, to analyze the carbon footprint of the equipment from raw material collection to delivery. We set the system boundary as "from cradle to gate", covering the raw material collection, processing, manufacturing, and distribution stages of the product. This step ensures the comprehensiveness and systematicness of the calculation, laying a solid foundation for subsequent work.

[0056] Step 2: Data Acquisition

[0057] Data acquisition is one of the key steps in carbon footprint accounting. We collect data in the following ways:

[0058] Connecting to enterprise information systems: Using API interfaces, relevant data can be automatically extracted from the enterprise's ERP (Enterprise Resource Planning), MES (Manufacturing Execution System) and SCM (Supply Chain Management) systems. These data include raw material procurement records, energy consumption during the production process, product transportation and distribution information, etc.

[0059] Access carbon footprint background database: Obtain emission factors and industry average data required for high-voltage switchgear production from authoritative databases (such as IPCC, CLCD, Ecoinvent, etc.).

[0060] Manual input and verification: Data that cannot be obtained through automatic means, such as detailed information of certain specific production processes, needs to be manually input and verified.

[0061] Step 3: Carbon footprint calculation

[0062] Once all the data is collected, start calculating your carbon footprint:

[0063] Data preprocessing: Cleaning and standardizing the data to ensure its quality and consistency.

[0064] This may include removing duplicate, erroneous or anomalous data items, as well as converting the data format to a standard format within the system.

[0065] Calculation using a large model: Based on the previously trained large model, massive amounts of data are processed and analyzed to accurately calculate the carbon footprint of the product. The model identifies key carbon emission links and provides a scientific basis for subsequent carbon footprint optimization.

[0066] Result verification and adjustment: After the calculation is completed, the results need to be verified and adjusted to ensure their accuracy and reliability.

[0067] Step 4: Visualize your carbon footprint

[0068] Generate multi-dimensional reports: Through intuitive and easy-to-understand multi-dimensional carbon footprint reports, the total carbon emissions of the product throughout its life cycle, the emission proportion of each link, trend changes and other information can be displayed.

[0069] Interactive analysis: Through interactive analysis tools, deep mining of carbon footprint data through filtering, sorting, and comparison can help discover potential emission reduction opportunities and identify major sources of carbon emissions.

[0070] Customized visualization: Customized personalized visualization solutions such as dynamic charts, heat maps, etc. can be provided according to specific needs to help managers better understand carbon footprint data.

[0071] Step 5: Carbon footprint optimization suggestions

[0072] Based on the carbon footprint calculation results, we will provide targeted emission reduction suggestions and optimization solutions:

[0073] Analyze emission reduction strategies: Combine industry best practices and expertise to analyze possible emission reduction strategies and measures, including improving production processes, increasing energy efficiency, and using more environmentally friendly raw materials.

[0074] Generate optimization suggestions: Using recommendation algorithms, we automatically generate personalized emission reduction optimization suggestions based on the actual situation and goals of the enterprise. These suggestions will be specific and feasible, and will help enterprises implement effective carbon reduction measures in various links such as production and operation.

[0075] Continuous monitoring and updating: Regularly recalculate carbon footprint and adjust optimization suggestions based on actual conditions. This will ensure that the company's emission reduction strategy is always consistent with the latest industry standards and best practices.

[0076] Step 6: Cross-system collaboration and data sharing

[0077] In order to achieve cross-system collaboration and data sharing, we will take the following measures:

[0078] API interface: Through the standard API interface, it supports seamless connection with the company's existing ERP, MES, SCM and other systems, ensuring smooth collaboration and data consistency in all links of the carbon footprint accounting process.

[0079] Data sharing: The cross-system data sharing mechanism established through blockchain technology allows carbon footprint data to be securely shared and accessed between internal departments and external partners of the enterprise.

[0080] Set data access permissions: Provide flexible data access permission settings to ensure that only authorized users can access sensitive data. This will help protect the data security and privacy of the enterprise.

[0081] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage medium such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0082] A person skilled in the art may understand that the various numerical numbers such as first and second involved in the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application, and also indicate the order of precedence.

[0083] At least one in the present application can also be described as one or more, and a plurality can be two, three, four or more, which is not limited in the present application. In the embodiments of the present application, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no order of precedence or size between the technical features described by the "first", "second", "third", "A", "B", "C" and "D".

[0084] The corresponding relationships shown in each table in the present application can be configured or predefined. The values ​​of the information in each table are only examples and can be configured as other values, which are not limited by the present application. When configuring the corresponding relationship between the information and each parameter, it is not necessarily required to configure all the corresponding relationships illustrated in each table. For example, in the table in the present application, the corresponding relationships shown in some rows may not be configured. For another example, appropriate deformation adjustments can be made based on the above table, such as splitting, merging, etc. The names of the parameters shown in the titles of the above tables can also use other names that can be understood by the communication device, and the values ​​or representations of the parameters can also be other values ​​or representations that can be understood by the communication device. When implementing the above tables, other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables.

[0085] The predefined in the present application may be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0086] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0087] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model, characterized in that: include: Data integration module, large model intelligent carbon footprint analysis module, carbon footprint optimization module, cross-system collaboration and data sharing module; among them, Data integration module, used to collect and integrate life cycle data generated in the manufacturing process of electrical equipment from multiple sources, including: energy consumption, raw material procurement, production and manufacturing, logistics and transportation; Large-model intelligent carbon footprint analysis module, which uses advanced big data analysis and artificial intelligence technology to automatically process and analyze integrated data to accurately calculate the carbon footprint of products; The carbon footprint optimization module is used to provide targeted emission reduction suggestions and optimization solutions based on the carbon footprint analysis results, helping enterprises to implement effective carbon emission reduction measures in various links such as production, operation, and supply chain management, reduce product carbon footprint, and improve the environmental performance of enterprises; The cross-system collaboration and data sharing module is used to promote seamless connection and data sharing between different systems, ensuring smooth collaboration in all links of the carbon footprint accounting process; through open API interfaces and data exchange standards, it can achieve integration with internal enterprise systems such as ERP, MES, SCM, and external data sharing with other enterprises or institutions.

2. The carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model according to claim 1 is characterized in that: The system also includes: a carbon footprint visualization module; The carbon footprint visualization module is used to convert complex carbon footprint data into intuitive and easy-to-understand charts and graphs.

3. The carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model according to claim 1 is characterized in that: The data integration module can integrate multiple data sources, including the company's internal R&D and design system, production system, supply chain management system, and external public databases, to fully cover the entire product life cycle from raw material procurement to waste disposal; The data integration module uses regular expression matching, logic verification, data completion and other technical means to clean the original data, remove duplicate, erroneous, invalid or abnormal data items, ensure the accuracy and consistency of the data, standardize the data, and eliminate format differences between different data sources; According to the preset data standards, the data formats from different data sources are uniformly converted into the standard format within the system, including but not limited to: data type, timestamp format, unit conversion; The data integration module uses the distributed storage system Hadoop HDFS to store massive carbon footprint data; and uses the real-time stream processing framework Apache Kafka to process real-time data streams.

4. The carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model according to claim 1 is characterized in that: The large-model intelligent carbon footprint analysis module is used to build a product carbon footprint prediction and analysis model based on machine learning and deep learning algorithms; wherein the large-model intelligent carbon footprint analysis module not only learns the laws and characteristics of carbon emissions at various stages of the product life cycle by training historical carbon emission data, but also introduces a variety of deep learning architectures to enhance the data feature extraction and pattern recognition capabilities; wherein, during the model training process, the deep learning architecture is used in combination with the ensemble learning method to gradually adjust the model parameters, minimize the prediction error and improve the prediction performance and robustness of the model; wherein, the deep learning architecture includes: recurrent neural network RNN, deep neural network DNN; wherein, the ensemble learning method includes: gradient boosting tree GBDT and random forest Random Forest; In terms of feature engineering, the large-model intelligent carbon footprint analysis module first uses a deep learning model to automatically learn and extract high-level features from the original data, and then uses a random forest to evaluate the importance of these features and screen out the features that have the greatest impact on the prediction target; then, these selected features are used as input to train the gradient boosting tree model; In terms of model fusion, in addition to using stacking technology combined with random forests and gradient boosting trees, the prediction results of deep learning models are also introduced as additional features; In the parallel and serial combination strategy, the deep learning model is used for preliminary feature extraction and prediction, and its results are then used to weight or screen samples to optimize the training of the gradient boosting tree model; The entire model is trained using a historical carbon emissions dataset through supervised learning, and its parameters are continuously optimized through multiple iterations of training; Among them, the introduction of the deep learning architecture of the large-model intelligent carbon footprint analysis module significantly enhances the model's ability to capture complex patterns and nonlinear relationships.

5. The carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model according to claim 1 is characterized in that: in, The carbon footprint optimization module is used to analyze possible emission reduction strategies and measures based on the carbon footprint calculation results and in combination with industry best practices and expertise; and to use a recommendation algorithm to automatically generate personalized emission reduction optimization suggestions based on the actual situation and goals of the enterprise, including but not limited to: production process improvement, energy structure optimization, and logistics efficiency improvement.

6. The carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model according to claim 1 is characterized in that: in, The cross-system collaboration and data sharing module is used to provide a standard API interface, support the connection with the company's existing ERP, MES, SCM and other systems, establish a cross-system collaboration and data sharing mechanism, and realize automatic transmission and sharing of data; wherein the cross-system collaboration and data sharing module is also used to provide flexible data access permission settings, and adopt blockchain technology to ensure data security and privacy protection.

7. The carbon footprint accounting system for products in the electrical equipment manufacturing industry based on a large model according to claim 2 is characterized in that: The carbon footprint visualization module is used to display the total carbon emissions of the product throughout its life cycle, the emission proportion of each link, and trend change information; and the carbon footprint visualization module has an interactive analysis tool to enable users to deeply explore carbon footprint data through screening, sorting, and comparison operations to discover potential emission reduction opportunities.

Images