Product carbon neutralization service management system based on product carbon neutralization authentication

Abstract

The invention discloses a product carbon neutralization service management system based on product carbon neutralization authentication, and belongs to the technical field of product carbon neutralization, and the system comprises a data collection module which is used for collecting the real-time data of the whole life cycle carbon emission of a product; the data processing module is used for processing the full-life-cycle carbon emission real-time data of the product and determining full-life-cycle carbon emission characteristic data of the product; the product carbon accounting module is used for constructing a carbon emission accounting model to analyze the product full-life-cycle carbon emission characteristic data and determining a product carbon emission accounting result; and the service management module is used for performing product carbon neutralization and emission reduction management and authentication display according to the product carbon emission accounting result. According to the invention, the problem of poor product carbon neutralization emission reduction management effect caused by incapability of effective product carbon neutralization service management based on product carbon neutralization authentication in the prior art is solved. According to the invention, effective product carbon neutralization service management can be carried out based on product carbon neutralization authentication, and the product carbon neutralization emission reduction management effect can be improved.

Description

Technical Field

[0001] This invention relates to the field of product carbon neutrality technology, specifically to a product carbon neutrality and service management system based on product carbon neutrality certification. Background Technology

[0002] Carbon neutrality refers to the reduction of anthropogenic greenhouse gas emissions to the maximum extent possible through two measures: energy conservation and emission reduction, and the removal of anthropogenic atmospheric greenhouse gases. This aims to offset the remaining emissions that cannot be avoided by existing energy conservation and emission reduction measures with negative carbon emissions, thereby achieving net-zero emissions of anthropogenic greenhouse gas carbon footprint and a relative dynamic balance in the atmospheric carbon cycle.

[0003] Chinese patent application CN114266570A discloses a blockchain-based product carbon neutrality traceability system. It uses carbon sink certificates on the blockchain to achieve carbon neutrality traceability. Leveraging the traceability and immutability of blockchain, the system ensures reliable and convenient traceability. The trading of carbon sink certificates allows for market-based regulation of carbon sequestration, reducing the carbon neutrality burden on energy-efficient companies and giving them a competitive advantage, thus promoting overall carbon emission reduction in production lines. Furthermore, the use of a monetary adjustment factor increases the burden on companies with high carbon emissions, expanding the competitive advantage of carbon-saving production lines. However, this patent has the following drawbacks:

[0004] Existing technologies cannot effectively manage product carbon neutrality and services based on product carbon neutrality certification, resulting in poor product carbon neutrality and emission reduction management. Summary of the Invention

[0005] The purpose of this invention is to provide a product carbon neutrality and service management system based on product carbon neutrality certification. This system can effectively manage product carbon neutrality and services based on product carbon neutrality certification, improve the effectiveness of product carbon neutrality and emission reduction management, and solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A product carbon neutrality and service management system based on product carbon neutrality certification includes:

[0008] The data acquisition module is used to collect carbon emissions throughout the entire product lifecycle and obtain real-time carbon emission data throughout the product lifecycle.

[0009] The data processing module is used to process real-time carbon emission data throughout the product lifecycle, extract features related to product carbon neutrality and service management, and determine the carbon emission characteristic data throughout the product lifecycle.

[0010] The product carbon accounting module is used to build a carbon emission accounting model and analyze the carbon emission characteristics data of the entire product life cycle to determine the product carbon emission accounting results.

[0011] The service management module is used to manage and display product carbon neutrality and emission reduction based on product carbon emission accounting results.

[0012] Preferably, collect carbon emissions throughout the entire product lifecycle, obtain real-time carbon emission data throughout the product lifecycle, and perform the following operations:

[0013] Carbon emission data of product procurement is obtained by collecting carbon emissions from raw material procurement during the entire product lifecycle using IoT devices.

[0014] Based on the collection of carbon emissions during the production and manufacturing process of products throughout their entire life cycle using IoT devices, we can obtain carbon emission data for product production.

[0015] Based on the collection of carbon emissions during transportation throughout the entire product lifecycle using IoT devices, we can obtain carbon emission data for product transportation.

[0016] Carbon emission data of product use is obtained by collecting carbon emissions from products throughout their entire lifecycle using IoT devices.

[0017] Carbon emission data of product processing is obtained by collecting carbon emissions during waste disposal throughout the entire product lifecycle using IoT devices.

[0018] Based on carbon emission data from product procurement, production, transportation, use, and disposal, real-time carbon emission data for the entire product lifecycle is generated.

[0019] Preferably, the data processing module includes:

[0020] The data cleaning unit is used to clean the real-time carbon emission data of the entire product life cycle, remove noise from the real-time carbon emission data of the entire product life cycle, and process missing and outlier values ​​in the real-time carbon emission data of the entire product life cycle.

[0021] This includes checking real-time carbon emission data throughout the product's lifecycle, identifying missing and outlier values ​​in the real-time carbon emission data throughout the product's lifecycle, and evaluating the missing and outlier values ​​in the real-time carbon emission data throughout the product's lifecycle.

[0022] When missing or outlier values ​​in real-time carbon emission data throughout the product lifecycle are valuable for product carbon neutrality and service management, the median is used to fill in the missing values ​​in the real-time carbon emission data throughout the product lifecycle, and the mean is used to replace the outlier values ​​in the real-time carbon emission data throughout the product lifecycle.

[0023] When missing or outlier values ​​in the real-time carbon emission data of a product's entire lifecycle are of no value to the product's carbon neutrality and service management, then these missing or outlier values ​​should be removed from the real-time carbon emission data of the product's entire lifecycle.

[0024] Preferably, the data processing module further includes:

[0025] The data conversion unit is used to convert real-time carbon emission data throughout the product life cycle, remove the dimensional differences between real-time carbon emission data throughout the product life cycle, and form standardized real-time carbon emission data throughout the product life cycle.

[0026] The feature extraction unit is used to extract features from real-time carbon emission data throughout the product lifecycle. It extracts features related to product carbon neutrality and service management from the real-time carbon emission data throughout the product lifecycle to determine the carbon emission feature data throughout the product lifecycle.

[0027] Preferably, the product carbon accounting module includes:

[0028] The model building unit is used to build a carbon emission accounting model based on product carbon neutrality certification;

[0029] Based on the product carbon neutrality certification and service management requirements, historical carbon emission accounting data is collected and divided into training set and test set.

[0030] The machine learning model is trained using a training set, enabling it to learn carbon emission accounting behavior autonomously from the training set and automatically calculate the carbon emissions throughout the product's life cycle, thus determining a carbon emission accounting model based on product carbon neutrality certification.

[0031] The carbon emission accounting model based on product carbon neutrality certification was tested using a test set to evaluate its generalization performance. Based on the model test evaluation, the carbon emission accounting model based on product carbon neutrality certification was adjusted and optimized to determine the optimal carbon emission accounting model.

[0032] Preferably, the product carbon accounting module further includes:

[0033] The analysis and accounting unit is used to calculate the carbon emissions throughout the product's entire life cycle.

[0034] The carbon emission characteristics data of the entire product life cycle are input into the carbon emission accounting model. The carbon emission accounting model is used to analyze the carbon emission characteristics data of the entire product life cycle and automatically calculate the carbon emission of the entire product life cycle to determine the carbon emission accounting result of the product.

[0035] Preferably, the service management module includes:

[0036] The emission reduction management unit is used to formulate product emission reduction management plans based on the product carbon emission accounting results.

[0037] This includes setting emission reduction targets and adopting corresponding emission reduction measures, coordinating emission reduction through improved production processes and the use of green energy, and managing carbon emission allowances and carbon credit assets throughout their entire lifecycle for carbon trading and carbon offsetting. For residual emissions that cannot be reduced, they are offset by purchasing verified carbon credits.

[0038] Preferably, the service management module further includes:

[0039] The certification display module is used to conduct product carbon neutrality certification and display it in a visual format;

[0040] Conduct product carbon neutrality certification throughout the entire product lifecycle after emission reduction management, generate product carbon neutrality verification reports that meet the requirements of product carbon neutrality certification bodies, and present the product carbon neutrality verification reports in a visual format.

[0041] Preferred methods for constructing carbon emission accounting models include:

[0042] Obtain a training set for the carbon emission accounting model; the training set includes carbon emission data from product procurement, production, transportation, use, and processing; perform empirical mode decomposition on the time series of each type of data to obtain intrinsic mode components and residual components, screen highly correlated mode components and bind corresponding dimensional marginal emission factors, construct a feature matrix and then perform dimensionality reduction processing, while simultaneously filling in data gaps;

[0043] Based on the training set and extracted features, an initial carbon emission accounting model is constructed. The carbon emission accounting model includes a carbon emission accounting sub-model for the procurement stage, a carbon emission accounting sub-model for the production stage, a carbon emission accounting sub-model for the transportation stage, a carbon emission accounting sub-model for the usage stage, and a carbon emission accounting sub-model for the treatment stage. Each sub-model calculates the initial carbon emissions for the corresponding stage.

[0044] A multi-dimensional coupling correction layer is constructed, and a graph neural network (GNN) is used to learn the coupling relationship between stages and output the coupling coefficient matrix. Based on the coupling coefficient matrix, the initial carbon emissions output by the initial carbon emission accounting model are corrected to obtain the corrected total carbon emissions.

[0045] The initial carbon emission accounting model is trained sequentially using the training set to obtain a trained carbon emission accounting model.

[0046] Preferably, the emission reduction management unit includes:

[0047] The acquisition submodule is used to acquire industry carbon emission standard data;

[0048] Generating subunits, used for:

[0049] Based on the product carbon emission accounting results and industry carbon emission standards, the carbon emission reduction gap and its causes are calculated, and a gap-cause correspondence table is obtained.

[0050] Based on the aforementioned gap-cause correspondence table, multiple candidate emission reduction schemes are generated according to the dimensions of product procurement, product generation, product transportation, product use, and product disposal. Each candidate emission reduction scheme includes implementation measures, technical support, expected emission reduction amount, and implementation cost, and different candidate schemes differ in the combination of dimensions or the priority of measures.

[0051] Analog sub-units, used for:

[0052] Multi-scenario carbon emission simulation analysis was performed on the multiple candidate emission reduction schemes to generate simulation analysis results for each candidate scheme under the baseline scenario, optimistic scenario and conservative scenario.

[0053] Based on a pre-set quantitative indicator system, the simulation analysis results of each candidate scheme under various scenarios are weighted and comprehensively scored, and the candidate scheme with the highest comprehensive score is determined as the first emission reduction management scheme.

[0054] Real-time adjustment of sub-units, used for:

[0055] Establish a real-time monitoring platform for carbon emissions throughout the product lifecycle, and perform real-time data collection and carbon footprint tracking based on the first emission reduction management plan;

[0056] The first emission reduction management scheme is dynamically adjusted based on the tracking feedback data, and when the preset global reassessment conditions are met, the generation sub-unit and simulation sub-unit are triggered to regenerate and verify the new emission reduction scheme.

[0057] Compared with the prior art, the beneficial effects of the present invention are:

[0058] This invention collects carbon emission data throughout the entire product lifecycle, from raw material procurement, manufacturing, transportation, use to waste disposal, obtaining real-time carbon emission data for the entire product lifecycle. This data is processed to extract features related to product carbon neutrality and service management, identifying characteristic data of carbon emissions throughout the product lifecycle. Based on a constructed carbon emission accounting model, this characteristic data is analyzed, and the total carbon emissions throughout the product lifecycle are automatically calculated. The resulting carbon emission accounting results are then used to formulate a product emission reduction management plan. Furthermore, carbon neutrality certification is applied to the product throughout its lifecycle after emission reduction management, generating a carbon neutrality verification report that meets the requirements of a carbon neutrality certification body. This report is then presented in a visual format. Effective product carbon neutrality and service management can be achieved based on carbon neutrality certification, improving the effectiveness of product carbon neutrality and emission reduction management. Attached Figure Description

[0059] Figure 1 This is a block diagram of the product carbon neutrality and service management system based on product carbon neutrality certification of the present invention. Detailed Implementation

[0060] 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.

[0061] To address the current issue of ineffective product carbon neutrality and service management based on product carbon neutrality certification, resulting in poor product carbon neutrality and emission reduction management, please refer to [link to relevant documentation]. Figure 1 This embodiment provides the following technical solution:

[0062] The product carbon neutrality certification-based product carbon neutrality and service management system includes: a data acquisition module, a data processing module, a product carbon accounting module, and a service management module.

[0063] Specifically, through the interactive communication between the data acquisition module, data processing module, product carbon accounting module, and service management module, effective product carbon neutrality and service management can be carried out based on product carbon neutrality certification, thereby improving the effectiveness of product carbon neutrality and emission reduction management.

[0064] The data acquisition module is used to collect carbon emissions throughout the entire product lifecycle and obtain real-time carbon emission data for the entire product lifecycle.

[0065] In this embodiment, carbon emissions throughout the entire product lifecycle are collected to obtain real-time carbon emission data for the entire product lifecycle, and the following operations are performed:

[0066] Carbon emission data of product procurement is obtained by collecting carbon emissions from raw material procurement during the entire product lifecycle using IoT devices.

[0067] Based on the collection of carbon emissions during the production and manufacturing process of products throughout their entire life cycle using IoT devices, we can obtain carbon emission data for product production.

[0068] Based on the collection of carbon emissions during transportation throughout the entire product lifecycle using IoT devices, we can obtain carbon emission data for product transportation.

[0069] Carbon emission data of product use is obtained by collecting carbon emissions from products throughout their entire lifecycle using IoT devices.

[0070] Carbon emission data of product processing is obtained by collecting carbon emissions during waste disposal throughout the entire product lifecycle using IoT devices.

[0071] Based on carbon emission data from product procurement, production, transportation, use, and disposal, real-time carbon emission data for the entire product lifecycle is generated.

[0072] Specifically, by collecting carbon emissions data throughout the entire product lifecycle, from raw material procurement, production, transportation, use to waste disposal, real-time carbon emission data can be obtained. This facilitates better carbon emission accounting for products, enabling effective carbon neutrality certification. It can provide enterprises with carbon emission management solutions for the entire product lifecycle, helping them achieve sustainable development goals.

[0073] The data processing module is used to process real-time carbon emission data throughout the product's lifecycle, extract features related to product carbon neutrality and service management, and determine the carbon emission characteristic data throughout the product's lifecycle.

[0074] In this embodiment, the data processing module includes: a data cleaning unit, a data conversion unit, and a feature extraction unit.

[0075] The data cleaning unit is used to clean the real-time carbon emission data of the entire product life cycle, remove noise from the real-time carbon emission data of the entire product life cycle, and process missing and outlier values ​​in the real-time carbon emission data of the entire product life cycle.

[0076] Specifically, the real-time carbon emission data of the entire product life cycle is examined to identify missing and outlier values ​​in the real-time carbon emission data of the entire product life cycle, and the missing and outlier values ​​in the real-time carbon emission data of the entire product life cycle are evaluated.

[0077] When missing or outlier values ​​in real-time carbon emission data throughout the product lifecycle are valuable for product carbon neutrality and service management, the median is used to fill in the missing values ​​in the real-time carbon emission data throughout the product lifecycle, and the mean is used to replace the outlier values ​​in the real-time carbon emission data throughout the product lifecycle.

[0078] When missing or outlier values ​​in the real-time carbon emission data of a product's entire lifecycle are of no value to the product's carbon neutrality and service management, then these missing or outlier values ​​should be removed from the real-time carbon emission data of the product's entire lifecycle.

[0079] Specifically, by cleaning the real-time carbon emission data throughout the product's lifecycle and removing noise from it, the interference of noise data on product carbon neutrality and service management can be reduced. By identifying and processing missing and outlier values ​​in the real-time carbon emission data throughout the product's lifecycle, the data quality of the real-time carbon emission data throughout the product's lifecycle can be improved, making product carbon emission accounting more accurate.

[0080] The data conversion unit is used to convert real-time carbon emission data throughout the product lifecycle, remove the dimensional differences between real-time carbon emission data throughout the product lifecycle, and form standardized real-time carbon emission data throughout the product lifecycle.

[0081] The feature extraction unit is used to extract features from real-time carbon emission data throughout the product lifecycle, extracting features related to product carbon neutrality and service management from the real-time carbon emission data throughout the product lifecycle, and determining the carbon emission feature data throughout the product lifecycle.

[0082] Specifically, by converting and extracting features from real-time carbon emission data throughout the product's entire lifecycle, effective carbon emission accounting can be performed based on the carbon emission characteristics data throughout the product's entire lifecycle.

[0083] The product carbon accounting module is used to build a carbon emission accounting model and analyze the carbon emission characteristics data of the entire product life cycle to determine the product carbon emission accounting results.

[0084] In this embodiment, the product carbon accounting module includes: a model building unit and an analysis and accounting unit.

[0085] Among them, the model building unit is used to build a carbon emission accounting model based on product carbon neutrality certification;

[0086] Based on the product carbon neutrality certification and service management requirements, historical carbon emission accounting data is collected and divided into training set and test set.

[0087] Among them, the historical data of carbon emission accounting is divided into training set and test set in a 7:3 ratio;

[0088] The machine learning model is trained using a training set, enabling it to learn carbon emission accounting behavior autonomously from the training set and automatically calculate the carbon emissions throughout the product's life cycle, thus determining a carbon emission accounting model based on product carbon neutrality certification.

[0089] The carbon emission accounting model based on product carbon neutrality certification was tested using a test set to evaluate its generalization performance and determine whether it could achieve the expected effect of automatically calculating the carbon emissions of the product throughout its entire life cycle. The model test evaluation results were then determined.

[0090] When the carbon emission accounting model based on product carbon neutrality certification fails to achieve the expected effect of automatically calculating the carbon emissions of the product throughout its entire life cycle, the parameters of the carbon emission accounting model based on product carbon neutrality certification will be adjusted and iteratively optimized until the carbon emission accounting model based on product carbon neutrality certification can achieve the expected effect of automatically calculating the carbon emissions of the product throughout its entire life cycle. In this way, the optimal carbon emission accounting model will be determined for calculating the carbon emissions of the product throughout its entire life cycle.

[0091] The analysis and accounting unit is used to calculate the carbon emissions throughout the product's entire life cycle.

[0092] The carbon emission characteristics data of the entire product life cycle are input into the carbon emission accounting model. The carbon emission accounting model analyzes the carbon emission characteristics data of the entire product life cycle and automatically calculates the carbon emission amount of the entire product life cycle, thus determining the carbon emission accounting result of the product. This facilitates subsequent carbon neutrality and emission reduction management and certification display of the product based on the carbon emission accounting result.

[0093] The service management module is used to manage and display product carbon neutrality and emission reduction based on the product carbon emission accounting results.

[0094] In this embodiment, the service management module includes an emission reduction management unit and an authentication display module.

[0095] Among them, the emission reduction management unit is used to formulate product emission reduction management plans based on the product carbon emission accounting results;

[0096] This includes setting emission reduction targets and adopting corresponding emission reduction measures, coordinating emission reduction through improved production processes and the use of green energy, and managing carbon emission allowances and carbon credit assets throughout their entire lifecycle for carbon trading and carbon offsetting. For residual emissions that cannot be reduced, they are offset by purchasing verified carbon credits.

[0097] The certification display module is used to conduct product carbon neutrality certification and display it in a visual format.

[0098] Conduct product carbon neutrality certification throughout the entire product lifecycle after emission reduction management, generate product carbon neutrality verification reports that meet the requirements of product carbon neutrality certification bodies, and present the product carbon neutrality verification reports in a visual format.

[0099] In this embodiment, the method for constructing the carbon emission accounting model includes:

[0100] Obtain a training set for the carbon emission accounting model; the training set includes carbon emission data from product procurement, production, transportation, use, and processing; perform empirical mode decomposition on the time series of each type of data to obtain intrinsic mode components and residual components, screen highly correlated mode components and bind corresponding marginal emission factors, construct a feature matrix and then perform dimensionality reduction processing, while filling in data gaps;

[0101] Based on the training set and extracted features, an initial carbon emission accounting model is constructed. The carbon emission accounting model includes a carbon emission accounting sub-model for the procurement stage, a carbon emission accounting sub-model for the production stage, a carbon emission accounting sub-model for the transportation stage, a carbon emission accounting sub-model for the usage stage, and a carbon emission accounting sub-model for the treatment stage. Each sub-model calculates the initial carbon emissions for the corresponding stage.

[0102] A multi-dimensional coupling correction layer is constructed, and a graph neural network (GNN) is used to learn the coupling relationship between stages and output the coupling coefficient matrix. Based on the coupling coefficient matrix, the initial carbon emissions output by the initial carbon emission accounting model are corrected to obtain the corrected total carbon emissions.

[0103] The initial carbon emission accounting model is trained sequentially using the training set to obtain a trained carbon emission accounting model.

[0104] In this embodiment, the time-series data of five categories of carbon emission data—procurement, production, transportation, use, and treatment—are systematically processed. First, the data collection dimensions for each stage are defined. Procurement data covers raw material types / usage, supplier regions, raw material purity, supplier energy structure, and carbon emission audit reports. Production data includes production energy consumption, waste rate, real-time load, equipment depreciation rate, and sensor calibration records. Transportation data covers transportation distance, load weight, transportation mode, empty load rate, and GPS trajectory matching with energy consumption. Usage data includes product power, usage duration, regional power structure, usage frequency, ambient temperature and humidity, and consistency between user logs and electricity meters. Treatment data involves recycled material types / weight, disposal machinery energy consumption, material recovery rate, disposal process, and recycling company monitoring reports. Then, a standardized process is executed: data is unified to the International System of Units (SI), asynchronous data is aligned to daily granularity using a 72-hour sliding window, and isolated data is addressed using the 3σ principle. A forest algorithm (with an outlier ratio set at 5%) is used to collaboratively clean up outliers. Then, Empirical Mode Decomposition (EMD) is performed on the daily sequence to generate 6-8 Intrinsic Mode Components (IMFs) and 1 residual component. Highly correlated components are selected using Spearman correlation coefficient (threshold 0.3) and P-value (threshold 0.05), and all IMFs are retained if the criteria are not met. The key innovation lies in dynamically binding dimensional marginal emission factors to the IMFs: the production energy consumption IMF is linked to the real-time marginal emission factors of the regional power grid released by the Ministry of Ecology and Environment (prioritizing operational marginal factors, and using combined marginal factors when the region is missing); the transportation distance IMF is linked to vehicle marginal emission factors corrected by fuel type (diesel / gasoline) and driving area; and the environmental parameter IMF is linked to regional temperature and humidity correction coefficients. This constructs a feature matrix of "time node × [IMF + marginal factor + correlated parameter]", which is compressed using principal component analysis (PCA) to a cumulative variance contribution > 90%. For data gaps, short-term missing data (<7 days) is corrected by merging adjacent daily averages with marginal factors and the 7-day trend slope. Long-term missing data (≥7 days) is mapped to similar product data in the industry through the maximum mean difference (MMD) migration algorithm. When historical data is less than 30 days, it automatically switches to the industry benchmark system. The raw material regional factor is determined based on the energy structure of the production area, and the energy factor strictly refers to the default value standard for fossil fuel combustion.

[0105] In this embodiment, based on the training dataset and extracted features, the system constructs five carbon emission accounting sub-models covering the entire product lifecycle (carbon emission accounting sub-model for the procurement stage, carbon emission accounting sub-model for the production stage, carbon emission accounting sub-model for the transportation stage, carbon emission accounting sub-model for the usage stage, and carbon emission accounting sub-model for the disposal stage). Each sub-model calculates the initial carbon emissions for its corresponding stage, and the specific calculation method is as follows:

[0106] The initial carbon emissions during the procurement phase employ a two-tier supplier accounting mechanism, comprising Tier 1 supplier accounting and Tier 2 supplier accounting. Tier 1 supplier carbon emissions are calculated through... Calculate, where, Carbon emissions of Tier 1 suppliers; Let i be the purchase quantity of the i-th type of raw material. For the i-th type of raw material, the marginal emission factor of the region, The raw material purity correction factor ( ), For raw material utilization rate; This indicates the total number of raw material categories. This calculation method fully integrates the purity differences of raw materials during the procurement stage with actual utilization efficiency, avoiding the problems of inaccurate effective usage and inflated carbon emissions caused by neglecting substandard raw material purity in traditional accounting. This makes the initial carbon emission calculation related to Tier 1 suppliers more closely reflect the actual carbon emission level contributed by raw materials, improving the accuracy of the basic raw material portion of the initial carbon emission calculation during the procurement stage. The carbon emissions of Tier 2 suppliers are calculated through... Calculate carbon emissions from energy-related raw materials, among which, Carbon emissions of Tier 2 suppliers; For the purchase volume of energy raw materials of type j, As the marginal emission factor for energy, For the supplier's energy structure coefficient, For energy transmission efficiency; This represents the total quantity of energy raw materials. This calculation method fully incorporates the differences in energy structure and transmission loss characteristics of energy raw material suppliers during the procurement stage, filling the gap in traditional accounting that neglects the impact of emissions at the back end of the energy raw material supply chain. By accurately quantifying carbon emission fluctuations in the supply chain through energy structure coefficients and transmission efficiency, it makes the initial carbon emission calculation related to second-tier suppliers more comprehensive, ensuring that the initial carbon emission calculation at the procurement stage fully covers the carbon emission contribution of the entire energy raw material supply chain. The two results are weighted according to normalization. and Weighted total procurement emissions are calculated by fully decomposing and hierarchically calculating the carbon emission contributions of Tier 1 suppliers (basic raw materials) and Tier 2 suppliers (energy raw materials) in the procurement stage. This expands the initial carbon emissions in the procurement stage from a single supplier dimension to a full supply chain dimension, ensuring that the initial carbon emissions in the procurement stage can comprehensively and accurately reflect the actual carbon emissions of the entire procurement chain. This complements the three-dimensional accounting system in the production stage and provides complete support for the accurate calculation of initial carbon emissions throughout the entire life cycle.

[0107] The initial carbon emissions during the production phase are calculated using a three-dimensional accounting system, separately calculating carbon emissions from production energy consumption, production machinery, and production waste. Among these, carbon emissions from production energy consumption... ,in, For production energy consumption and carbon emissions; Let be the energy consumption of the k-th type of production at time t. Let k be the energy emission factor. This is a real-time production load correction factor. Let t be the energy utilization rate; Indicates the production cycle; This represents the total number of energy categories used in production. This calculation method integrates time-varying energy consumption with real-time load correction, fully coupling the dynamic changes in energy consumption during the production phase with real-time production load status. It also incorporates the correction effect of energy utilization rate, effectively avoiding carbon emission deviations caused by neglecting time-dimensional energy consumption fluctuations and load differences in traditional static accounting. This makes the initial carbon emission calculation related to energy consumption more closely reflect actual production conditions, improving the accuracy of the energy consumption contribution portion of the initial carbon emission calculation; among which, mechanical carbon emissions... ,in, Carbon emissions from production machinery; The number of shifts using the s-th type of energy for the q-th type of machinery. Energy consumption per machine shift. For the s-th type of energy emission factor, The mechanical aging coefficient; Indicates the total number of energy types; This represents the total number of machinery categories. This calculation method quantifies the impact of equipment aging on energy consumption, fully linking the aging status of machinery during the production stage with carbon emission accounting. It fills the gap in traditional accounting methods that ignore the impact of equipment lifecycle status changes on energy consumption and carbon emissions. Through an aging coefficient, it accurately quantifies the increase in energy consumption and corresponding carbon emissions caused by equipment aging, making the initial carbon emission accounting related to machinery more comprehensive and ensuring that the initial carbon emissions accurately reflect the actual contribution of equipment operating status to carbon emissions. Among these, waste carbon emissions... Based on actual waste volume Dynamic calculation, in which, Carbon emissions from production waste. To improve the recycling rate of production waste, This is the waste disposal coefficient; The marginal emission factor for the i-th type of raw material region; Indicates the actual amount of waste; For raw material utilization rate; This method calculates the total number of raw material categories. It fully integrates the entire process of raw material consumption, utilization rate, and waste disposal during the production stage with the initial carbon emission calculation. The actual amount of waste generated serves as the core dynamic calculation basis, rather than using a fixed estimation ratio. It also incorporates the impact of waste recovery rate and disposal coefficient, making the initial carbon emission calculation related to waste more dynamic and accurate. This avoids distortion of initial carbon emissions due to errors in waste quantity estimation and improves the coverage of initial carbon emissions across the entire production process. Furthermore, it fully decomposes and accurately calculates the three core carbon emission sources during the production stage: energy consumption, machinery, and waste. This upgrades the initial carbon emission calculation from a single dimension to a multi-dimensional, full-process calculation, ensuring that the initial carbon emission comprehensively, accurately, and truthfully reflects the actual carbon emission level during the production stage. This provides reliable basic data support for subsequent carbon emission control strategy formulation and emission reduction potential assessment.

[0108] Initial carbon emissions during the transportation phase are determined using a multimodal transport model, calculating carbon emissions for road transport, rail transport, and sea transport separately: Road transport via... The coefficient accurately reflects the nonlinear amplification effect of the no-load rate on emissions, specifically: ;in, Carbon emissions from road transport; For the first Batch product shipping weight For transportation distance, For marginal emission factors of road transport, This is the no-load rate correction factor; Batch number; This represents the total number of batches. The impact of empty load rates in road transport during the transportation phase is fully quantified and incorporated into the initial carbon emission calculation. A dedicated correction coefficient accurately captures the non-linear amplification effect of empty load rates on carbon emissions, avoiding the underestimation or overestimation of emissions caused by the linear conversion of empty load rates in traditional calculations. This makes the initial carbon emission calculation related to road transport more closely reflect actual transportation conditions, improving the accuracy of the road transport portion of the initial carbon emission calculation during the transportation phase. Rail and sea transport use isomorphic models with added loading and unloading energy consumption. The energy consumption and carbon emissions of loading and unloading in rail and sea transport are fully incorporated, filling the gap in traditional transportation carbon emission calculations that only focus on emissions during transport and ignore emissions from key loading and unloading stages. This achieves complete coverage of carbon emissions throughout the entire rail and sea transport process, making the initial carbon emission calculation related to rail and sea transport more comprehensive and ensuring that the initial carbon emission calculation during the transportation phase truly reflects the full-process carbon emission contribution of both transportation modes. Emissions for each mode are weighted according to transport volume. The initial carbon emissions of the transportation phase are determined by weighted aggregation. The carbon emission contributions of the three core transportation modes—road, rail, and sea—are fully decomposed and classified for calculation. By weighting the transport volume, the emissions of each mode are scientifically integrated. This expands the initial carbon emissions of the transportation phase from a single transportation mode dimension to the full dimensions of multimodal transport. It ensures that the initial carbon emissions of the transportation phase can comprehensively and accurately reflect the actual carbon emissions of the entire multimodal transport chain, forming a complete closed loop with the accounting system of the production and procurement phases, and further consolidating the foundation for accurate calculation of initial carbon emissions throughout the entire life cycle.

[0109] The initial carbon emissions during the usage phase are calculated using a dual-channel design: the first channel calculates the baseline carbon emissions. ,in, Based on the use of carbon emissions, The rated power of the product. For daily usage time, Let t be the marginal emission factor of the regional power grid combination. To utilize frequency correction factors, this calculation method integrates real-time grid marginal factors with user behavior corrections, fully merging real-time grid emission fluctuations during the usage phase with actual user behavior. This avoids emission biases caused by using fixed grid emission factors and average usage duration in traditional accounting, making the initial carbon emission calculation related to basic emissions more closely aligned with real-world user scenarios and improving the accuracy of calculating the core energy consumption contribution portion of the initial carbon emissions during the usage phase. The second channel calculates carbon emissions coupled to the environment. ,in, Carbon emissions are coupled with environmental factors. For environmental parameters, Environmental impact factor; The amount of power change caused by the environment; This is a production energy category number, calculated based on changes in power. By establishing a physical link between environmental parameters and energy consumption, the correlation between changes in environmental parameters during the usage phase and energy consumption and carbon emissions is fully quantified. This fills the gap in traditional accounting that ignores the impact of environmental factors on product energy consumption. By establishing a physical link through power changes, the environmental impact is accurately calculated, making the initial carbon emission calculation related to environmental coupling more scientific and ensuring that the initial carbon emission during the usage phase fully covers the additional carbon emission contribution from environmental variables. The basic energy consumption emissions and environmentally coupled emissions during the usage phase are fully decomposed and collaboratively calculated, expanding the initial carbon emission during the usage phase from a single energy consumption dimension to a dual dimension of "basic usage + environmental impact". This ensures that the initial carbon emission during the usage phase can comprehensively and accurately reflect the actual carbon emission situation in all product usage scenarios, forming a closed loop throughout the entire life cycle with the accounting system of production, procurement, and transportation phases, providing complete and comprehensive support for the accurate calculation of initial carbon emissions throughout the entire process.

[0110] The initial carbon emissions during the treatment phase are calculated using a closed-loop accounting method: disassembling carbon emissions. ,in, To reduce carbon emissions, The number of shifts using the qth type of energy for the p-th type of dismantling machinery. Energy consumption per machine shift. For the qth type of energy emission factor, The mechanical automation coefficient; Indicates the total number of categories of dismantled machinery; This represents the total energy consumption. This calculation method considers the impact of automation levels on energy consumption, fully linking the automation level of dismantling machinery in the processing stage with energy consumption and carbon emissions. It fills the gap in traditional accounting methods that ignore the impact of automation levels on dismantling energy consumption. Through an automation coefficient, it accurately quantifies the differences in carbon emissions caused by machinery with different levels of automation, making the initial carbon emission calculation related to dismantling more closely reflect actual dismantling conditions and improving the accuracy of the initial carbon emission calculation for the dismantling stage in the processing stage; it also recovers carbon emissions. ,in, For the recovery / disposal of carbon emissions; Let i be the amount of material of type i being recycled. For the i-th type of raw material, the marginal emission factor of the region, The energy consumption coefficient for material recycling. To address the energy recovery factor; Let j be the energy emission factor; To recover energy; The total number of energy categories recovered; This represents the total number of categories of recycled materials. This calculation method innovatively deducts energy recovery revenue, achieving precise measurement across the entire chain from dismantling to recycling. It fully integrates energy recovery revenue from the processing stage with carbon emission accounting, breaking the limitations of traditional accounting that only measures energy consumption for recycling and disposal while ignoring energy recovery emission reduction benefits. Through a "forward measurement + reverse deduction" approach, it achieves precise carbon emission accounting across the entire dismantling-recycling chain, avoiding overestimation of initial carbon emissions due to missed recovery revenue, and ensuring that the initial carbon emissions at the processing stage truly reflect the net carbon emission level of the recycling and disposal process. Each sub-model shares parameters (such as...). , This forms a data closed loop, providing high-precision initial emission values ​​for subsequent coupling correction layers. The carbon emission accounting model is divided into sub-models for five stages: procurement, production, transportation, use, and treatment. It can model and calculate separately for the characteristics and influencing factors of each stage. This staged accounting method is more detailed and accurate, and can more accurately reflect the carbon emission situation of products at different stages throughout their entire life cycle, providing detailed data support for enterprises and relevant departments to formulate targeted emission reduction strategies.

[0111] In this embodiment, the multi-dimensional coupling correction layer innovatively introduces a graph neural network (GNN) to model the implicit correlation of carbon emissions throughout the product's lifecycle: the five stages of procurement, production, transportation, use, and disposal are abstracted as graph structure nodes, and the feature vector of each node consists of the initial carbon emissions of that stage and the first two principal components after PCA dimensionality reduction; the inherent data feedback relationships between stages (such as the impact of the quality of procured raw materials on the production waste rate, and the constraint of product usage intensity on disposal difficulty) are defined as graph edges. The GNN model uses the absolute error between the corrected total emissions and the measured carbon emission label as the core supervision signal, and adopts a composite loss function. Training was conducted, including... Train the loss function value for the GNN; This is the corrected total carbon emissions; This is to measure the carbon emissions of the product. The coupling coefficients are defined by a regularization term that forces sparsity in the coupling coefficients to avoid overfitting. This effectively binds the accuracy requirements of the measured total carbon emissions with the stability of the model training. The core supervision signal ensures that the corrected total carbon emissions closely match the actual measured values. Simultaneously, the regularization term avoids correction bias caused by model overfitting, improving the reliability and generalization ability of the corrected total carbon emissions results. Furthermore, Sigmoid activation and scaling are used to further reduce the coupling coefficients. Strictly constrained within the physically reasonable range of [0, 0.3], ensuring the first... Phase 1 to the first The impact of each stage aligns with the carbon emission transmission law. The range of values ​​for the cross-stage coupling coefficients is sufficiently physically limited to ensure that the impact of stage i on stage j conforms to the actual carbon emission transmission law. This avoids excessive amplification or reduction of cross-stage impact due to abnormal coupling coefficient values, thereby preventing distortion of total carbon emissions and ensuring the rationality of total carbon emission correction. After training, the GNN outputs a 5×5 coupling coefficient matrix, which is used to dynamically correct the initial emissions for each stage. ,in, This represents the carbon emissions after the correction for stage j. This represents the initial carbon emissions for stage j. Let be the average of the historical initial carbon emissions for stage i; this formula uses a relative deviation amplification mechanism to make high-anomaly stages ( Significant deviation from historical mean This system generates adaptive correction forces for the correlation stages; it fully and dynamically adapts the abnormal fluctuations in initial carbon emissions at each stage to the cross-stage correlation effects, and achieves accurate identification and correlation correction of highly abnormal stages through a relative deviation amplification mechanism. This makes the corrected emissions at each stage more consistent with the overall emission conditions throughout the entire life cycle, thereby ensuring that the total carbon emissions accurately reflect the actual emission levels under the synergistic effects of each stage, and improving the accuracy of the total carbon emissions; ultimately, the corrected total emissions... It not only integrates the independent accounting results of each stage, but also accurately captures the cross-stage emission coupling effect, effectively solving the problem of duplicate or omitted carbon emissions caused by the fragmentation of system boundaries in traditional segmented accounting. This ensures that the final total carbon emissions can cover the independent emission contributions of each stage and accurately capture the cross-stage emission coupling effect, achieving a comprehensive, accurate, and true accounting of the total carbon emissions throughout the entire life cycle. This provides the most core and reliable decision-making basis for formulating carbon emission control strategies throughout the product life cycle.

[0112] The working principle and beneficial effects of the above technical solution are as follows: By processing the time series of various carbon emission data through empirical mode decomposition, complex time series can be decomposed into multiple intrinsic mode components and residual components. This decomposition method helps to reveal the inherent change patterns and laws of the data, and to uncover the hidden feature information within the data. Dimensionality reduction of the feature matrix reduces redundant information in the data, lowers the computational complexity of the model, and improves the training efficiency and running speed of the model. Simultaneously, it avoids overfitting problems that may result from excessively high data dimensionality, enhancing the model's generalization ability. Dividing the carbon emission accounting model into five sub-models—procurement, production, transportation, use, and treatment—allows for tailoring the model to the characteristics and impacts of each stage. The system models and calculates influencing factors separately; this phased calculation method is more detailed and accurate, and can more accurately reflect the carbon emissions of products at different stages throughout their entire life cycle, providing detailed data support for enterprises and relevant departments to formulate targeted emission reduction strategies; a multi-dimensional coupling correction layer is constructed, and a graph neural network (GNN) is used to learn the coupling relationship between stages and output the coupling coefficient matrix; this innovation considers the mutual influence and correlation between each stage of the product life cycle, avoiding the limitation of simply adding the emissions of each stage in the traditional calculation method; the initial carbon emissions are corrected by the coupling coefficient matrix, so that the model can more realistically reflect the actual total carbon emissions of the product, improving the accuracy and credibility of the calculation results.

[0113] In this embodiment, the emission reduction management unit includes:

[0114] The acquisition submodule is used to acquire industry carbon emission standard data;

[0115] Generating subunits, used for:

[0116] Based on the product carbon emission accounting results and industry carbon emission standards, the carbon emission reduction gap and its causes are calculated, and a gap-cause correspondence table is obtained.

[0117] Based on the aforementioned gap-cause correspondence table, multiple candidate emission reduction schemes are generated according to the dimensions of product procurement, product generation, product transportation, product use, and product disposal. Each candidate emission reduction scheme includes implementation measures, technical support, expected emission reduction amount, and implementation cost, and different candidate schemes differ in dimension combination or measure priority.

[0118] Analog sub-units, used for:

[0119] Multi-scenario carbon emission simulation analysis was performed on the multiple candidate emission reduction schemes to generate simulation analysis results for each candidate scheme under the baseline scenario, optimistic scenario and conservative scenario.

[0120] Based on a pre-set quantitative indicator system, the simulation analysis results of each candidate scheme under various scenarios are weighted and comprehensively scored, and the candidate scheme with the highest comprehensive score is determined as the first emission reduction management scheme.

[0121] Real-time adjustment of sub-units, used for:

[0122] Establish a real-time monitoring platform for carbon emissions throughout the product lifecycle, and perform real-time data collection and carbon footprint tracking based on the first emission reduction management plan;

[0123] The first emission reduction management scheme is dynamically adjusted based on the tracking feedback data, and when the preset global reassessment conditions are met, the generation sub-unit and simulation sub-unit are triggered to regenerate and verify the new emission reduction scheme.

[0124] In this embodiment, industry carbon emission standard data is analyzed to determine the carbon emission limits for each stage of the product. The carbon emission accounting results of the product are compared with the carbon emission limits to calculate the carbon emission reduction gap for each stage. Based on a pre-trained association rule mining model, the causes of the carbon emission reduction gap are analyzed, high carbon emission links in each stage are identified, and the gap-cause correspondence table is generated.

[0125] Based on the aforementioned gap-cause correspondence table, the system generates multiple candidate emission reduction schemes according to five key dimensions of the product's entire lifecycle (procurement, production, transportation, use, and disposal). Candidate Scheme 1, in the procurement dimension, replaces high-carbon raw materials with low-carbon materials and collaborates with suppliers, using association rule mining models to match alternative solutions and blockchain to verify low-carbon attributes. In the production dimension, it sets an idling energy consumption threshold for manufacturing equipment to achieve automatic shutdown and schedules high-energy-consuming equipment to operate during off-peak hours. In the transportation dimension, it applies a GRU model to predict congestion and plan optimal routes to avoid peak hours, while optimizing transportation batches to a large-batch, small-batch mode, and recording the effects through GPS and infrared fuel consumption sensors. In the usage dimension, it provides energy-saving tips through the product's app. The system includes: alerts, energy consumption rankings, and personalized suggestions; marking recyclable components in the processing dimension, cooperating with door-to-door recycling services, and using smart weighing sensors to quantify the carbon reduction from recycling; while Candidate Solution 2 differentiates itself by prioritizing renewable materials in the procurement dimension to reduce carbon emission weight; optimizing process temperature and providing real-time alarms from smart meters in the generation dimension; replacing power tools in the transportation dimension to reduce the carbon emission base; implementing dynamic energy consumption algorithm optimization through remote firmware upgrades in the usage dimension; and extending product lifespan through modular design in the processing dimension to reduce processing frequency. Each candidate emission reduction solution is a unique combination of the above-mentioned measures, fully covering implementation measures, technical support, expected emission reductions, and implementation cost data, ensuring the feasibility of the solution and the basis for quantitative evaluation.

[0126] In this embodiment, the system constructs a full lifecycle emission reduction simulation system based on a cloud computing center. After inputting the implementation parameters of each candidate emission reduction scheme, simulations are performed under baseline, optimistic, and conservative scenarios, respectively, outputting the total carbon emissions, implementation costs, and implementation period data for each scheme in each scenario. Subsequently, the distance between the carbon emission results of each scheme in each scenario and the preset emission reduction target is calculated using the Euclidean distance formula. Only when the distance value of a scheme in all three scenarios is less than the preset threshold is it marked as a valid scheme. Then, for each valid scheme, its performance in the following scenarios is calculated based on a preset quantitative indicator system (including a weighted allocation of 40% for emission reduction effect, 30% for cost controllability, 20% for implementation difficulty, and 10% for sustainability). The specific indicator scores for each scenario—where the emission reduction effect score is determined by the formula (1 - carbon emission distance / baseline carbon emission), the cost controllability score is determined by (1 - actual cost / budgeted cost), the implementation difficulty score is determined by expert evaluation, and the sustainability score is generated through a historical data regression model—are weighted and aggregated according to a probability weight of 60% for the baseline scenario, 20% for the optimistic scenario, and 20% for the conservative scenario to obtain a comprehensive score. Finally, the system selects the effective solution with the highest comprehensive score as the first emission reduction management solution. If no solution meets the effectiveness criteria, it automatically backtracks to the gap-cause correspondence table to regenerate new candidate solutions, ensuring that the selected solution has both robustness and optimality under multiple uncertainties.

[0127] In this embodiment, the system establishes a real-time carbon emission monitoring platform covering the entire product lifecycle. This platform consists of a four-layer architecture: a data acquisition layer that reuses existing IoT devices from each stage and adds new monitoring points for implementation; a communication network layer that uses 5G and edge computing technologies to ensure millisecond-level data transmission; a data analysis layer that calculates carbon emission deviations at each stage in real time; and a data output layer that generates an intuitive carbon emission dashboard through visualization tools. Based on this platform, the system continuously tracks the carbon footprint and accurately locates the source of deviations, automatically generating a "deviation-source" tracking report. When a single carbon emission deviation exceeds the ±15% threshold dynamically set based on industry standards, or when monthly adjustment measures accumulate to more than three times in the same stage, a local optimization process is triggered, generating targeted adjustment measures and pushing them out. The system then transmits data to the relevant execution terminals. Simultaneously, it incorporates a global reassessment mechanism. When the total carbon emission deviation exceeds the product's carbon emission standard by 10% for two consecutive months, the user negative feedback rate exceeds 20%, or a change in external conditions (such as an industry standard update) triggers a system alarm, the system automatically activates the generation and simulation sub-units. Based on the latest gap-cause correspondence table, it regenerates multiple candidate solutions. After verification through multi-scenario simulation analysis, the new solution with the highest comprehensive score replaces the original solution. Furthermore, the system integrates deviation analysis, adjustment effects, and user feedback monthly to generate an implementation report for optimizing details. If the report identifies structural defects (such as persistent failure in a single dimension), a global reassessment is immediately triggered to ensure that emission reduction management is always in a dynamically optimal state.

[0128] The working principle and beneficial effects of the above technical solution are as follows: The acquisition submodule acquires industry carbon emission standard data, providing a scientific reference standard for subsequent emission reduction management; the generation subunit calculates the carbon emission reduction gap and its causes based on the product carbon emission accounting results and industry carbon emission standards, and obtains a gap-cause correspondence table; the generation subunit generates multiple candidate emission reduction schemes according to the dimensions of product procurement, production, transportation, use and disposal, and each scheme includes detailed information such as implementation measures, technical support, expected emission reduction amount and implementation cost; the simulation subunit conducts multi-scenario (baseline scenario, optimistic scenario and conservative scenario) carbon emission simulation analysis on multiple candidate emission reduction schemes, and performs weight allocation and comprehensive scoring based on a preset quantitative indicator system; the real-time adjustment subunit builds a real-time monitoring platform for carbon emissions throughout the product's entire life cycle, and performs real-time data collection and carbon footprint tracking for the first emission reduction management scheme; the first emission reduction management scheme is dynamically adjusted according to the tracking feedback data, and a new emission reduction scheme is regenerated and verified when the preset global reassessment conditions are met.

[0129] In summary, by collecting carbon emissions data throughout the entire product lifecycle—from raw material procurement, manufacturing, transportation, use to waste disposal—real-time carbon emission data is obtained and processed to determine the characteristic data of carbon emissions throughout the product lifecycle. This data is then analyzed using a carbon emission accounting model, and the total carbon emissions throughout the product lifecycle are automatically calculated. The carbon emission accounting results are then used to develop product emission reduction management plans. Furthermore, carbon neutrality certification is conducted for the product throughout its lifecycle after emission reduction management, generating a carbon neutrality verification report that meets the requirements of a carbon neutrality certification body. This report is then presented in a visual format. Effective product carbon neutrality and service management can be implemented based on carbon neutrality certification, thereby improving the effectiveness of product carbon neutrality and emission reduction management.

[0130] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0131] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A product carbon neutrality and service management system based on product carbon neutrality certification, characterized in that, include: The data acquisition module is used to collect carbon emissions throughout the entire product lifecycle and obtain real-time carbon emission data throughout the product lifecycle. The data processing module is used to process real-time carbon emission data throughout the product lifecycle, extract features related to product carbon neutrality and service management, and determine the carbon emission characteristic data throughout the product lifecycle. The product carbon accounting module is used to build a carbon emission accounting model and analyze the carbon emission characteristics data of the entire product life cycle to determine the product carbon emission accounting results. The service management module is used to manage and display product carbon neutrality and emission reduction based on product carbon emission accounting results.

2. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 1, characterized in that, Collect carbon emissions data throughout the entire product lifecycle, obtain real-time carbon emission data throughout the product lifecycle, and perform the following operations: Carbon emission data of product procurement is obtained by collecting carbon emissions from raw material procurement during the entire product lifecycle using IoT devices. Based on the collection of carbon emissions during the production and manufacturing process of products throughout their entire life cycle using IoT devices, we can obtain carbon emission data for product production. Based on the collection of carbon emissions during transportation throughout the entire product lifecycle using IoT devices, we can obtain carbon emission data for product transportation. Carbon emission data of product use is obtained by collecting carbon emissions from products throughout their entire lifecycle using IoT devices. Carbon emission data of product processing is obtained by collecting carbon emissions during waste disposal throughout the entire product lifecycle using IoT devices. Based on carbon emission data from product procurement, production, transportation, use, and disposal, real-time carbon emission data for the entire product lifecycle is generated.

3. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 2, characterized in that, The data processing module includes: The data cleaning unit is used to clean the real-time carbon emission data of the entire product life cycle, remove noise from the real-time carbon emission data of the entire product life cycle, and process missing and outlier values ​​in the real-time carbon emission data of the entire product life cycle. This includes checking real-time carbon emission data throughout the product's lifecycle, identifying missing and outlier values ​​in the real-time carbon emission data throughout the product's lifecycle, and evaluating the missing and outlier values ​​in the real-time carbon emission data throughout the product's lifecycle. When missing or outlier values ​​in real-time carbon emission data throughout the product lifecycle are valuable for product carbon neutrality and service management, the median is used to fill in the missing values ​​in the real-time carbon emission data throughout the product lifecycle, and the mean is used to replace the outlier values ​​in the real-time carbon emission data throughout the product lifecycle. When missing or outlier values ​​in the real-time carbon emission data of a product's entire lifecycle are of no value to the product's carbon neutrality and service management, then these missing or outlier values ​​should be removed from the real-time carbon emission data of the product's entire lifecycle.

4. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 3, characterized in that, The data processing module further includes: The data conversion unit is used to convert real-time carbon emission data throughout the product life cycle, remove the dimensional differences between real-time carbon emission data throughout the product life cycle, and form standardized real-time carbon emission data throughout the product life cycle. The feature extraction unit is used to extract features from real-time carbon emission data throughout the product lifecycle. It extracts features related to product carbon neutrality and service management from the real-time carbon emission data throughout the product lifecycle to determine the carbon emission feature data throughout the product lifecycle.

5. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 4, characterized in that, The product carbon accounting module includes: The model building unit is used to build a carbon emission accounting model based on product carbon neutrality certification; Based on the product carbon neutrality certification and service management requirements, historical carbon emission accounting data is collected and divided into training set and test set. The machine learning model is trained using a training set, enabling it to learn carbon emission accounting behavior autonomously from the training set and automatically calculate the carbon emissions throughout the product's life cycle, thus determining a carbon emission accounting model based on product carbon neutrality certification. The carbon emission accounting model based on product carbon neutrality certification was tested using a test set to evaluate its generalization performance. Based on the model test evaluation, the carbon emission accounting model based on product carbon neutrality certification was adjusted and optimized to determine the optimal carbon emission accounting model.

6. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 5, characterized in that, The product carbon accounting module also includes: The analysis and accounting unit is used to calculate the carbon emissions throughout the product's entire life cycle. The carbon emission characteristics data of the entire product life cycle are input into the carbon emission accounting model. The carbon emission accounting model is used to analyze the carbon emission characteristics data of the entire product life cycle and automatically calculate the carbon emission of the entire product life cycle to determine the carbon emission accounting result of the product.

7. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 6, characterized in that, The service management module includes: The emission reduction management unit is used to formulate product emission reduction management plans based on the product carbon emission accounting results. This includes setting emission reduction targets and adopting corresponding emission reduction measures, coordinating emission reduction through improved production processes and the use of green energy, and managing carbon emission allowances and carbon credit assets throughout their entire lifecycle for carbon trading and carbon offsetting. For residual emissions that cannot be reduced, they are offset by purchasing verified carbon credits.

8. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 7, characterized in that, The service management module also includes: The certification display module is used to conduct product carbon neutrality certification and display it in a visual format; Conduct product carbon neutrality certification throughout the entire product lifecycle after emission reduction management, generate product carbon neutrality verification reports that meet the requirements of product carbon neutrality certification bodies, and present the product carbon neutrality verification reports in a visual format.

9. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 5, characterized in that, Methods for constructing carbon emission accounting models include: Obtain a training set for the carbon emission accounting model; the training set includes carbon emission data from product procurement, production, transportation, use, and processing; perform empirical mode decomposition on the time series of each type of data to obtain intrinsic mode components and residual components, screen highly correlated mode components and bind corresponding dimensional marginal emission factors, construct a feature matrix and then perform dimensionality reduction processing, while simultaneously filling in data gaps; Based on the training set and extracted features, an initial carbon emission accounting model is constructed. The carbon emission accounting model includes a carbon emission accounting sub-model for the procurement stage, a carbon emission accounting sub-model for the production stage, a carbon emission accounting sub-model for the transportation stage, a carbon emission accounting sub-model for the usage stage, and a carbon emission accounting sub-model for the treatment stage. Each sub-model calculates the initial carbon emissions for the corresponding stage. A multi-dimensional coupling correction layer is constructed, and a graph neural network (GNN) is used to learn the coupling relationship between stages and output the coupling coefficient matrix. Based on the coupling coefficient matrix, the initial carbon emissions output by the initial carbon emission accounting model are corrected to obtain the corrected total carbon emissions. The initial carbon emission accounting model is trained sequentially using the training set to obtain a trained carbon emission accounting model.

10. The product carbon neutrality and service management system based on product carbon neutrality certification according to claim 7, characterized in that, The emission reduction management unit includes: The acquisition submodule is used to acquire industry carbon emission standard data; Generating subunits, used for: Based on the product carbon emission accounting results and industry carbon emission standards, the carbon emission reduction gap and its causes are calculated, and a gap-cause correspondence table is obtained. Based on the aforementioned gap-cause correspondence table, multiple candidate emission reduction schemes are generated according to the dimensions of product procurement, product generation, product transportation, product use, and product disposal. Each candidate emission reduction scheme includes implementation measures, technical support, expected emission reduction amount, and implementation cost, and different candidate schemes differ in the combination of dimensions or the priority of measures. Analog sub-units, used for: Multi-scenario carbon emission simulation analysis was performed on the multiple candidate emission reduction schemes to generate simulation analysis results for each candidate scheme under the baseline scenario, optimistic scenario and conservative scenario. Based on a pre-set quantitative indicator system, the simulation analysis results of each candidate scheme under various scenarios are weighted and comprehensively scored, and the candidate scheme with the highest comprehensive score is determined as the first emission reduction management scheme. Real-time adjustment of sub-units, used for: Establish a real-time monitoring platform for carbon emissions throughout the product lifecycle, and perform real-time data collection and carbon footprint tracking based on the first emission reduction management plan; The first emission reduction management scheme is dynamically adjusted based on the tracking feedback data, and when the preset global reassessment conditions are met, the generation sub-unit and simulation sub-unit are triggered to regenerate and verify the new emission reduction scheme.

Images