Enterprise carbon emission determination method, device, equipment and medium

Abstract

The embodiment of the invention provides an enterprise carbon emission determination method and device, equipment and a medium. The method comprises the following steps: acquiring machine account information of an enterprise, and determining a multi-dimensional power load characteristic item of the enterprise and predicted proportion data of a carbon emission source of the enterprise based on the machine account information; performing coupling processing on the multi-dimensional power load characteristic item and the predicted proportion data of the carbon emission source to obtain an electricity-carbon coupling model; acquiring a real-time production plan of the enterprise, and correcting the electricity-carbon coupling model based on the real-time production plan to obtain a corrected electricity-carbon coupling model; and determining the total amount of electric energy carbon emission of the enterprise based on the corrected electric-carbon coupling model, and determining a carbon emission optimization strategy of the enterprise based on the total amount of electric energy carbon emission. According to the method, the total electric energy carbon emission amount of the enterprise can be accurately quantified according to the real-time production plan, and a carbon emission optimization strategy fitting the production rhythm of the enterprise is formulated.

Description

Technical Field

[0001] This application relates to the field of industrial carbon emission management technology, and in particular to methods, apparatus, equipment and media for corporate carbon emission management. Background Technology

[0002] The industrial sector is the main consumer of energy and emitter of carbon in my country, accounting for more than one-third of the country's total carbon emissions. Controlling the total amount and intensity of carbon emissions from industrial enterprises has become a core aspect of achieving green and low-carbon development. Against this backdrop, enterprises are demanding higher accuracy and timeliness in carbon emission data, while existing carbon emission accounting methods face significant challenges.

[0003] In related technologies, carbon emission accounting is mainly conducted through manual auditing and model prediction. While manual auditing, as a traditional and authoritative method, yields relatively accurate results, its accounting cycle is lengthy, typically on an annual basis, and data disclosure lags significantly behind actual production activities by six months to a year, failing to provide real-time data support for enterprises' daily carbon management and energy-saving decisions. On the other hand, model prediction heavily relies on large-scale, high-quality historical data, but industrial enterprise data often contains significant gaps and noise, affecting model reliability. It fails to deeply analyze the complex energy consumption scenarios within enterprises (such as differentiating between production and manufacturing, auxiliary systems, and office and living environments), ignoring the dynamic correlation mechanism between different electricity consumption links and carbon emissions. This results in insufficient prediction accuracy in complex and fluctuating actual production environments, making it difficult to meet the needs of refined carbon management. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and medium for determining corporate carbon emissions, as well as a computer program product. By constructing an electric-carbon coupling model and combining it with a real-time production plan dynamic correction model, it can accurately quantify the total carbon emissions from electricity and formulate an efficient carbon emission optimization strategy that fits the actual production rhythm of the enterprise.

[0005] In a first aspect, embodiments of this application provide a method for determining corporate carbon emissions, comprising: acquiring the company's ledger information, and determining, based on the ledger information, the predicted proportion data of the company's multidimensional electricity load characteristics and carbon emission sources; coupling the multidimensional electricity load characteristics and the predicted proportion data of carbon emission sources to obtain an electricity-carbon coupling model; acquiring the company's real-time production plan, and revising the electricity-carbon coupling model based on the real-time production plan to obtain a revised electricity-carbon coupling model; determining the company's total electricity carbon emissions based on the revised electricity-carbon coupling model, and determining the company's carbon emission optimization strategy based on the total electricity carbon emissions.

[0006] In one possible implementation, the step of coupling the multidimensional electricity load characteristics with the predicted proportion data of the carbon emission sources to obtain an electricity-carbon coupling model includes: determining at least one target electricity load characteristic that matches the energy consumption scenario corresponding to the carbon emission source, so as to establish a correlation between the energy consumption scenario and the target electricity load characteristic; determining the contribution weight coefficient of the target electricity load characteristic to the carbon emission source in the correlation; and obtaining the electricity-carbon coupling model based on the contribution weight coefficient, the correlation, and the predicted proportion data of the carbon emission sources.

[0007] In one possible implementation, the method further includes: determining a carbon emission factor corresponding to the carbon emission source, and determining at least one target power load characteristic item corresponding to the carbon emission factor based on the energy consumption scenario, wherein the carbon emission factor is used to represent the activity intensity of the carbon emission source; acquiring historical carbon emission data, and using the historical carbon emission data as input parameters of a preset neural network model, so as to determine the contribution weight coefficient between the target power load characteristic item and the activity intensity of the carbon emission source based on the preset neural network model.

[0008] In one possible embodiment, the step of modifying the electro-carbon coupling model based on the real-time production plan to obtain a modified electro-carbon coupling model includes: determining the carbon emission characteristics in the real-time production plan, the carbon emission characteristics including production carbon emission intensity and production shifts; updating the contribution weight coefficient based on the production carbon emission intensity and the production shifts to obtain an updated contribution weight coefficient; and modifying the electro-carbon coupling model based on the updated contribution weight coefficient to obtain the modified electro-carbon coupling model.

[0009] In one possible implementation, the aforementioned ledger information includes electricity consumption data, and the method further includes: performing multi-dimensional time-series analysis on the electricity consumption data using a preset time-series decomposition model to obtain a multi-dimensional electricity characteristic time-series diagram; and determining the multi-dimensional electricity load characteristic items of the enterprise based on the multi-dimensional electricity characteristic time-series diagram.

[0010] In one possible implementation, the method further includes: determining the enterprise's carbon emission sources and the corresponding carbon emissions based on the ledger information; determining the enterprise's historical carbon emission source proportion data based on the carbon emission sources and the carbon emissions; and determining the enterprise's predicted carbon emission source proportion data based on the historical carbon emission source proportion data.

[0011] In one possible implementation, the method further includes: determining real-time consumption data and production cycle load items of non-electric energy based on the ledger information, and determining the basic carbon emission parameters corresponding to the non-electric energy based on the real-time consumption data; determining the dynamic correction coefficient corresponding to the basic carbon emission parameters based on the production cycle load items; determining the non-electric carbon emission amount based on the dynamic correction coefficient and the basic carbon emission parameters, and determining the enterprise's total comprehensive carbon emissions based on the non-electric carbon emission amount and the electrical carbon emission amount output by the corrected electrical-carbon coupling model.

[0012] Secondly, embodiments of this application provide an apparatus for determining enterprise carbon emissions. The apparatus includes: an acquisition module, used to acquire enterprise ledger information and determine, based on the ledger information, the predicted proportion data of the enterprise's multidimensional electricity load characteristics and carbon emission sources; a coupling module, used to couple the multidimensional electricity load characteristics and the predicted proportion data of carbon emission sources to obtain an electricity-carbon coupling model; a correction module, used to acquire the enterprise's real-time production plan and correct the electricity-carbon coupling model based on the real-time production plan to obtain a corrected electricity-carbon coupling model; and a determination module, used to determine the enterprise's total electricity carbon emissions based on the corrected electricity-carbon coupling model and determine the enterprise's carbon emission optimization strategy based on the total electricity carbon emissions.

[0013] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0014] The memory stores computer-executed instructions;

[0015] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0017] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0018] The enterprise carbon emission accounting method, apparatus, equipment, and medium provided in this application establish a predicted proportion relationship between multi-dimensional electricity load characteristics and carbon emission sources using enterprise ledger information, constructing a preliminary electricity-carbon coupling model. This effectively overcomes the drawbacks of traditional model prediction methods that simply fit total electricity consumption to total carbon emissions, achieving refined analysis of different energy consumption scenarios within the enterprise. Furthermore, real-time production planning is introduced to dynamically correct the model, enabling it to overcome the annual lag of manual auditing methods and respond in real-time to changes in production arrangements, equipment start-up and shutdown, and energy efficiency fluctuations, significantly improving the timeliness and accuracy of carbon emission calculations. Ultimately, based on the total electricity carbon emissions calculated by this high-precision, near-real-time electricity-carbon coupling model, enterprises can formulate carbon emission optimization strategies closely related to specific production activities and implementable, accurately identifying high-carbon emission links, optimizing production shifts and energy efficiency management. This reduces the accounting threshold and cost while providing strong decision support for industrial enterprises to achieve refined carbon management and energy conservation and carbon reduction. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] Figure 1 This is a schematic diagram illustrating a scenario for determining corporate carbon emissions provided in an exemplary embodiment of this application;

[0021] Figure 2 Flowchart of the method for determining corporate carbon emissions provided in this application Figure 1 ;

[0022] Figure 3 Flowchart of the method for determining corporate carbon emissions provided in this application Figure 2 ;

[0023] Figure 4 A schematic diagram of the enterprise carbon emission determination device provided in this application;

[0024] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0025] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0027] First, let me explain the terms used in this application:

[0028] Carbon emissions from industrial enterprises refer to the total amount of greenhouse gases (measured in carbon dioxide equivalents) emitted directly or indirectly throughout the entire process of producing goods or providing services. This is not limited to smoke from factory chimneys; it encompasses three main levels: first, direct emissions, from the combustion of fossil fuels within the factory premises (such as coal / gas combustion in boilers and kilns), industrial processes (such as chemical reactions in cement production and metal smelting), and vehicle operation; second, indirect emissions, mainly from the consumption of purchased electricity and heat in production—these emissions actually occur at power plants but are triggered by the enterprise's electricity consumption behavior; and third, other indirect emissions, including emissions throughout the entire supply chain, from raw material extraction and transportation to product use and waste disposal. Therefore, carbon emissions from industrial enterprises are a comprehensive indicator for measuring the impact of their production activities on climate change.

[0029] The electricity-carbon coupling model is an innovative analytical framework for accurately measuring carbon emissions from industrial enterprises. Its core lies in breaking away from the traditional crude estimation method that treats electricity consumption and carbon emissions as a simple linear relationship. By establishing a refined mathematical correlation between the enterprise's multi-dimensional dynamic electricity load characteristics (such as the power of main production equipment, energy consumption of auxiliary systems, and office electricity load) and different carbon emission sources (such as production processes, office electricity consumption, and non-electric energy consumption), and by introducing dynamic variables such as real-time energy efficiency coefficients and production plans for correction, it can achieve real-time, accurate source tracing and quantification of carbon emissions under different energy consumption scenarios. This provides reliable data and decision support for enterprises to carry out refined carbon management and optimize production energy efficiency.

[0030] Please see Figure 1 , Figure 1This is a schematic diagram illustrating a scenario for determining enterprise carbon emissions according to an exemplary embodiment of this application. Server 120 obtains ledger information from enterprise system 110, including the enterprise's multidimensional electricity load characteristics and predicted proportion data of the enterprise's carbon emission sources. Then, server 120 couples the multidimensional electricity load characteristics with the predicted proportion data of carbon emission sources to obtain an electricity-carbon coupling model. Next, server 120 obtains real-time production technology from enterprise system 110 and modifies the electricity-carbon coupling model based on the real-time production plan to obtain a modified electricity-carbon coupling model. Finally, based on the modified electricity-carbon coupling model, the total electricity carbon emissions of the enterprise are determined, and the enterprise's carbon emission optimization strategy is determined based on the total electricity carbon emissions. This achieves refined accounting of enterprise carbon emissions, providing strong decision support for industrial enterprises to achieve refined carbon management and energy conservation and carbon reduction.

[0031] Figure 1 The server 120 shown can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. There are no restrictions on these options.

[0032] In related technologies, carbon emission accounting is mainly conducted through manual auditing and model prediction. While manual auditing, as a traditional and authoritative method, yields relatively accurate results, its accounting cycle is lengthy, typically on an annual basis, and data disclosure lags significantly behind actual production activities by six months to a year, failing to provide real-time data support for enterprises' daily carbon management and energy-saving decisions. On the other hand, model prediction heavily relies on large-scale, high-quality historical data, but industrial enterprise data often contains significant gaps and noise, affecting model reliability. It fails to deeply analyze the complex energy consumption scenarios within enterprises (such as differentiating between production and manufacturing, auxiliary systems, and office and living environments), ignoring the dynamic correlation mechanism between different electricity consumption links and carbon emissions. This results in insufficient prediction accuracy in complex and fluctuating actual production environments, making it difficult to meet the needs of refined carbon management.

[0033] To address the aforementioned problems, embodiments of this application provide a method for determining corporate carbon emissions, an apparatus for determining corporate carbon emissions, an electronic device, a computer-readable storage medium, and a computer program product. These embodiments will be described in detail below.

[0034] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0035] Figure 2 Flowchart of the method for determining corporate carbon emissions provided in this application Figure 1 ,like Figure 2 As shown, the process for determining the company's carbon emissions includes at least steps S201 to S204, which are detailed below:

[0036] Step S201: Obtain the enterprise's ledger information and determine the enterprise's multidimensional power load characteristics and the predicted proportion of the enterprise's carbon emission sources based on the ledger information.

[0037] For example, a comprehensive collection of enterprise ledger information forms the data foundation for model construction. This information mainly includes equipment lists, product process files, energy purchase and sales records, and historical production reports. Subsequently, based on this ledger data, a deep deconstruction and mapping analysis of the enterprise's energy consumption structure is conducted. Specifically, by analyzing the electricity consumption records of different terminals such as major production equipment, auxiliary power systems, environmental control, and office facilities, multi-dimensional power load feature items that can characterize their operational characteristics are extracted. These include, for example, a baseline load item representing the total load of the core production line and a production cycle load item representing the power consumption of production auxiliary systems. At the same time, the carbon emission sources of enterprises are comprehensively identified from the ledger, including direct emission sources (such as coal-fired boilers and fuel vehicles) and indirect emission sources (such as purchased electricity and heat). Based on the enterprise's energy consumption records, production reports and other ledger data, the actual carbon emissions corresponding to each carbon emission source are calculated. By summarizing the emission data of carbon emission sources in various historical periods, the historical carbon emission source proportion data is calculated. Then, combined with the influencing factors such as industry development trends, enterprise production plan adjustments, and energy structure optimization, a pre-set neural network model is used to train and learn the historical proportion data. This model will capture the evolution pattern of carbon emission source proportion and predict future trends, and finally determine the predicted proportion data of enterprise carbon emission sources, thus providing key data support for the subsequent construction of an electricity-carbon coupling model and the formulation of carbon emission optimization strategies.

[0038] Step S202: Couple the multidimensional electricity load characteristics with the predicted proportion of carbon emission sources to obtain the electricity-carbon coupling model.

[0039] For example, feature items that comprehensively reflect the characteristics of power load can be extracted from multidimensional power load data, such as load values, load change rates, and load peak-valley differences at different time scales (hours, days, months, etc.). At the same time, relevant data on carbon emission sources are collected and appropriate prediction methods, such as time series analysis and machine learning algorithms, are used to obtain the predicted proportion of each component of carbon emission sources in the future. Then, these multidimensional power load feature items and the predicted proportion of carbon emission sources are coupled with the predicted proportion of carbon emission sources in a specific way, such as establishing data association mapping relationships and performing data fusion processing, so that the various features of power load and the proportion of carbon emission sources are correlated and interact with each other, and finally an electricity-carbon coupling model that can reflect the intrinsic relationship between power load and carbon emissions is constructed.

[0040] Step S203: Obtain the enterprise's real-time production plan and modify the electro-carbon coupling model based on the real-time production plan to obtain the modified electro-carbon coupling model.

[0041] For example, obtaining a company's real-time production plan requires integrating dynamic information such as production scheduling, equipment operating status, and production task adjustments. By mapping these real-time data with multi-dimensional power load characteristics (such as baseline load, production cycle load, and environmentally sensitive load), the impact of production plan changes on power load characteristics can be identified. For instance, peak production periods may increase the weight of the production cycle load or change its cyclical pattern. Simultaneously, by combining carbon emission source prediction data (such as the proportion of direct emissions from the production process and the proportion of indirect emissions from electricity consumption), the impact of production plan adjustments on the dynamic proportion of each emission source can be analyzed. For instance, increased output may push up the proportion of indirect emissions from electricity consumption. Then, relevant parameters (such as weighting coefficients and trend correction factors) are dynamically adjusted in the electricity-carbon coupling model, enabling the model to reflect in real-time changes in the relationship between power load and carbon emissions caused by production plan changes. Ultimately, a corrected electricity-carbon coupling model that accurately matches the company's real-time production status and supports intelligent carbon management is formed.

[0042] Step S204: Determine the total carbon emissions of an enterprise based on the modified electricity-carbon coupling model, and determine the enterprise's carbon emission optimization strategy based on the total carbon emissions of electricity.

[0043] For example, when determining a company's total carbon emissions from electricity based on the modified electricity-carbon coupling model, it is necessary to first dynamically integrate real-time production plans with multi-dimensional electricity load characteristics (such as baseline load, production cycle load, and environmentally sensitive loads) through the model, and combine this with predicted carbon emission source proportion data (such as the proportion of indirect emissions from production electricity consumption and the proportion of electricity consumption in office and living areas). The carbon emissions from each detailed emission source are then calculated in real time and summed to obtain the total emissions. Subsequently, based on this total, the carbon emission composition is analyzed to identify high-emission links (such as excessively high production electricity consumption and abnormal office air conditioning energy consumption) and abnormal energy consumption patterns (such as equipment idling on non-working days and seasonal load surges). Targeted optimization strategies are then developed, such as adjusting production shifts to reduce electricity costs through off-peak electricity use, optimizing equipment operating parameters to improve energy efficiency, promoting energy-saving equipment to reduce non-production electricity consumption, and adjusting air conditioning temperature setpoints based on environmentally sensitive load items to reduce office and living area electricity emissions. Simultaneously, the strategy priorities are dynamically adjusted in conjunction with carbon emission targets and production plans. Ultimately, a refined carbon management solution covering all scenarios of production, office, and living is formed, supporting companies in achieving energy conservation and emission reduction goals and improving carbon management efficiency.

[0044] Optionally, in some feasible embodiments, when determining a company's carbon emission optimization strategy based on total electricity carbon emissions, it is necessary to first conduct a multi-dimensional breakdown analysis of this total amount to identify the specific contribution ratio and fluctuation characteristics of each detailed emission source (such as direct emissions from the production process, indirect emissions from production electricity consumption, indirect emissions from office / living electricity consumption, and emissions from non-electric energy consumption). This allows for the identification of high-carbon emission links (such as low energy efficiency of production equipment, equipment idling during non-production periods, and seasonal surges in air conditioning load) and abnormal energy consumption patterns (such as mismatch between production plans and electricity load, equipment operating parameters deviating from the optimal range, and unreasonable control of environmentally sensitive loads). Subsequently, combined with the company's real-time production plan, equipment operating status, carbon emission targets, and external policy requirements, targeted optimization strategies are formulated. Examples include adjusting production shifts to achieve off-peak electricity consumption to reduce electricity costs and decrease peak-hour emissions, optimizing equipment operating parameters (such as motor frequency and lighting brightness) to improve energy efficiency, and promoting energy-saving equipment (such as high-efficiency motors and LED lighting) to replace high-energy-consuming equipment. By dynamically adjusting air conditioning / heating temperature setpoints based on environmentally sensitive loads to reduce electricity emissions from office and residential use, utilizing carbon finance tools (such as carbon allowance pledging financing) to support energy-saving renovation projects, and applying for green enterprise certification to enhance the market value of carbon management, a dynamic carbon emission monitoring and strategy feedback mechanism will be established. Based on actual emission data and the effectiveness of strategy implementation, the priorities of measures will be continuously adjusted and optimized to ultimately form a refined carbon management solution covering all aspects of production, office, and living, supporting enterprises in achieving their goals of total carbon emission control, energy efficiency improvement, and carbon asset appreciation.

[0045] In the embodiments provided in this application, by accurately extracting multi-dimensional power load characteristics and carbon emission source prediction proportion data from the enterprise ledger and constructing an electricity-carbon coupling model, and combining it with a real-time production plan dynamic correction model, the total amount of electricity carbon emissions can be accurately quantified and an efficient carbon emission optimization strategy that fits the actual production rhythm of the enterprise can be formulated.

[0046] Based on the above embodiments, in one exemplary embodiment provided in this application, the specific implementation process of coupling the above-mentioned multidimensional electricity load characteristic items with the predicted proportion data of carbon emission sources to obtain the electricity-carbon coupling model may further include steps S301 to S303, which are described in detail below:

[0047] Step S301: Based on the energy consumption scenario corresponding to the carbon emission source, determine at least one target power load characteristic item that matches the energy consumption scenario, so as to establish the correlation between the energy consumption scenario and the target power load characteristic item.

[0048] For example, when constructing the correlation between energy consumption scenarios and target electricity load characteristics, it is necessary to accurately match scenarios with characteristics based on the enterprise's carbon emission source energy consumption scenarios (such as production workshops, office areas, and living areas), combined with daily electricity consumption data from historical electricity consumption data and decomposed multi-dimensional electricity load characteristics (including baseline load, production cycle load, environmentally sensitive load, holiday / special event load, and random fluctuation items). For instance, production workshop scenarios are typically strongly correlated with production cycle load (reflecting the daily / weekly / monthly periodic fluctuations of the production line) and environmentally sensitive load (related to the impact of external factors such as temperature and humidity on equipment operating energy consumption). Office area scenarios mainly match environmentally sensitive load (such as seasonal changes in air conditioning / lighting energy consumption) and holiday / special event load (such as load decreases due to reduced use of office equipment on weekends or holidays). Living area scenarios focus on environmentally sensitive load (such as the impact of temperature fluctuations on dormitory / canteen air conditioning and heating demand).

[0049] Subsequently, through correlation analysis between historical carbon emission source proportion data and electricity load characteristics (such as the correlation study between indirect emissions from production electricity consumption and production cycle load items), the contribution weight coefficient of each target electricity load characteristic item to carbon emission sources is quantified. For example, the contribution weight of the production cycle load item to indirect emissions from production electricity consumption may reach 65%, while the contribution weight of environmentally sensitive load items to office electricity emissions is approximately 35%. Finally, the correlation between energy consumption scenarios and characteristic items, contribution weight coefficients, and predicted proportion data of carbon emission sources (such as the proportion of direct emissions from production processes and the proportion of indirect emissions from production electricity consumption) are deeply integrated. Through weighted combination and trend superposition, a dynamic mapping relationship is established, forming a correlation network that can reflect the intrinsic relationship between electricity load characteristics and carbon emission source proportions under different energy consumption scenarios in real time. This provides accurate scenario-based support for the electricity-carbon coupling model, helping enterprises to achieve scenario-based and source-based carbon emission quantification and optimization management.

[0050] Step S302: Determine the contribution weight coefficient of the target power load characteristic item to the carbon emission source in the correlation relationship;

[0051] Step S303: Based on the contribution weight coefficient, correlation relationship and predicted proportion data of carbon emission sources, the electric carbon coupling model is obtained.

[0052] For example, when determining the contribution weight coefficient of target electricity load characteristics to carbon emission sources, it is necessary to conduct a correlation analysis between the enterprise's historical electricity consumption data and carbon emissions. This involves statistically analyzing the fluctuation synchronicity and causal relationship between electricity load characteristics (such as production cycle load items and environmentally sensitive load items) and corresponding carbon emission sources (such as indirect emissions from production electricity consumption and office electricity consumption) under various energy consumption scenarios. Methods such as correlation coefficients and contribution analysis are then used to quantify the degree of influence of these characteristics on emission sources. For instance, because production cycle load items are directly related to production line operation, their contribution weight to indirect emissions from production electricity consumption may reach 60%-80% based on historical data. Meanwhile, environmentally sensitive load items, significantly affected by temperature fluctuations, contribute approximately 40%-50% to emissions from office air conditioning electricity consumption. Subsequently, the correlation between energy consumption scenarios and characteristic items, the contribution weight coefficients of each characteristic item, and the predicted proportion of carbon emission sources (such as direct emissions from the production process accounting for 35% and indirect emissions from electricity consumption accounting for 45%) are integrated in multiple dimensions. By constructing a weighted coupling matrix, superimposing dynamic trends, or training machine learning models, a nonlinear mapping relationship between electricity load characteristic items and carbon emission sources is established, forming an electricity-carbon coupling model that can respond in real time to adjustments in production plans, changes in equipment operating status, and the impact of external policies.

[0053] In addition, the model can not only accurately quantify the specific contribution of electricity load characteristics to carbon emissions under different scenarios, but also dynamically predict the changing trend of emission source proportions, providing data support for enterprises to formulate carbon emission reduction strategies based on different scenarios and sources. At the same time, through model verification and iterative optimization (such as comparing actual emission data with model predictions), the accuracy and applicability of the model can be continuously improved.

[0054] In the embodiments provided in this application, by accurately matching the energy consumption scenarios of carbon emission sources with the characteristics of target power load and establishing a correlation, and by combining the contribution weight coefficient and the predicted proportion data to construct an electricity-carbon coupling model, a deep coupling between dynamic quantification of carbon emissions and power load characteristics can be achieved, providing enterprises with scenario-based and highly accurate carbon management decision support.

[0055] Based on the above embodiments, in one exemplary embodiment provided in this application, the specific implementation process of the above-mentioned method for determining enterprise carbon emissions may further include steps S401 and S402, which are described in detail below:

[0056] Step S401: Determine the carbon emission factor corresponding to the carbon emission source, and determine at least one target power load characteristic item corresponding to the carbon emission factor based on the energy consumption scenario. The carbon emission factor is used to represent the activity intensity of the carbon emission source.

[0057] Step S402: Obtain historical carbon emission data and use the historical carbon emission data as input parameters of a preset neural network model to determine the contribution weight coefficient between the target power load characteristic item and the activity intensity of carbon emission sources based on the preset neural network model.

[0058] For example, the process of determining carbon emission factors and their corresponding target electricity load characteristics and quantifying contribution weight coefficients requires integrating energy consumption scenario characteristics, historical emission data, and neural network models: First, based on the energy consumption types (such as electricity, raw coal, and natural gas) of the enterprise's energy consumption scenarios (such as production workshops, office areas, and living areas), the carbon emission factors corresponding to each carbon emission source are clarified. For example, the carbon emission factor for electricity consumption can be dynamically adjusted according to the average emission factor of the power grid or the proportion of green electricity purchased by the enterprise, while the emission factor for raw coal used in production needs to be calculated in combination with the lower heating value, carbon content per unit calorific value, and oxidation rate. Subsequently, target electricity load characteristics are matched according to the characteristics of the energy consumption scenario. For example, the production workshop scenario is associated with production cycle load items (reflecting the daily / weekly / monthly periodic fluctuations of the production line) and environmentally sensitive load items (equipment energy consumption affected by temperature and humidity); the office area scenario is associated with environmentally sensitive load items (air conditioning / lighting energy consumption) and holiday / special event load items (load reduction on weekends / holidays); and the living area scenario focuses on environmentally sensitive load items (dormitory / canteen air conditioning and heating demand).

[0059] Next, historical carbon emission data of enterprises (such as daily electricity consumption and carbon emissions from various sources) are collected and used as input parameters for a pre-set neural network model (such as a Long Short-Term Memory (LSTM) network or a Transformer). The model learns the nonlinear mapping relationship between electricity load characteristics (such as production cycle load and environmentally sensitive load) and the intensity of carbon emission source activities (such as electricity consumption in production and raw coal consumption). For example, the model can identify a strong correlation between fluctuations in production cycle load and indirect emissions from production electricity consumption, or the correlation between changes in environmentally sensitive load and emissions from office air conditioning. Finally, based on the model training results, the contribution weight coefficient of each target electricity load characteristic to the intensity of carbon emission source activities is determined. For example, the contribution weight of production cycle load to emissions from production electricity consumption may reach 70%, while the contribution weight of environmentally sensitive load to emissions from office areas may be approximately 40%. These weighting coefficients, together with the correlation between energy consumption scenarios and characteristic items, and the predicted proportion of carbon emission sources, will jointly construct an electricity-carbon coupling model to achieve dynamic coupling between electricity load characteristics and carbon emission intensity. This will support enterprises in accurately quantifying the emission contribution of each scenario and formulating targeted emission reduction strategies. At the same time, by continuously inputting new data to iterate the model, the accuracy and adaptability of the weighting coefficients will be improved.

[0060] In the embodiments provided in this application, by clarifying the correspondence between carbon emission factors and target power load characteristics and introducing historical carbon emission data to drive the neural network model, the dynamic impact of power load characteristics on the intensity of carbon emission source activities can be accurately quantified, thereby providing core parameter support for building a high-precision, scenario-adaptive electricity-carbon coupling analysis system.

[0061] Based on the above embodiments, in one exemplary embodiment provided in this application, the specific implementation process of obtaining the modified electro-carbon coupling model based on the real-time production plan may further include steps S501 to S503, which are described in detail below:

[0062] Step S501: Determine the carbon emission characteristics in the real-time production plan. The carbon emission characteristics include production carbon emission intensity and production shifts.

[0063] Step S502: Based on the carbon emission intensity of production and production shifts, update the contribution weight coefficient to obtain the updated contribution weight coefficient.

[0064] Step S503: Based on the updated contribution weight coefficients, the electro-carbon coupling model is corrected to obtain the corrected electro-carbon coupling model.

[0065] For example, when determining carbon emission characteristics in real-time production planning (such as production carbon intensity, carbon emissions per unit output, and production shifts, such as morning / afternoon / night shift scheduling patterns), it is necessary to combine the company's real-time production scheduling data with a historical carbon emission characteristic database. This involves comparative analysis to identify the fluctuation patterns of production carbon intensity with product type and process parameter adjustments (e.g., carbon intensity increases by 15% during batch production of high-energy-consuming products), and the impact of production shift changes on electricity load characteristics (e.g., night shift production may shift production cycle load items later due to off-peak electricity prices, while environmentally sensitive load items decrease due to lower nighttime temperatures). Subsequently, based on real-time data on production carbon intensity and production shifts, the contribution weighting coefficients of target electricity load characteristics (such as production cycle load items and environmentally sensitive load items) to carbon emission sources (such as indirect emissions from production electricity use and direct emissions from the production process) are dynamically adjusted. For example, when the carbon emission intensity of production decreases due to the addition of high-efficiency equipment, the contribution weight of the production cycle load item to production electricity emissions may drop from 70% to 65%, while the correlation of environmentally sensitive load items weakens due to improved equipment energy efficiency, and the contribution weight is adjusted accordingly. Finally, the updated contribution weight coefficients are deeply integrated with the correlation between energy consumption scenarios and characteristic items, as well as the predicted proportion of carbon emission sources. Through retraining and parameter optimization of the neural network model (such as adjusting the hidden layer weights of the LSTM model), the nonlinear mapping relationship in the electricity-carbon coupling model is corrected, enabling the model to respond in real time to adjustments in production plans (such as shift changes and output fluctuations) and changes in carbon emission characteristics, accurately quantifying the dynamic contribution of electricity load characteristics to carbon emissions under various scenarios. Simultaneously, continuous iterative optimization through model validation (such as comparing the corrected model predictions with actual emission data) ensures that the electricity-carbon coupling model maintains high accuracy and strong adaptability, supporting enterprises in achieving precise control and optimization decisions regarding carbon emissions in the production process.

[0066] In the embodiments provided in this application, by combining the production carbon emission intensity and the contribution weight coefficient of the production shift in the real-time production plan, and thereby modifying the electricity-carbon coupling model, the model can be accurately adapted to the actual production rhythm changes of enterprises, significantly improving the real-time performance of carbon emission prediction and the accuracy of management decisions.

[0067] Based on the above embodiments, in one exemplary embodiment provided in this application, the ledger information includes electricity consumption data, and the specific implementation process of the above-mentioned method for determining enterprise carbon emissions may further include steps S601 and S602, which are described in detail below:

[0068] Step S601: Perform multi-dimensional time series analysis on electricity consumption data using a preset time series decomposition model to obtain a multi-dimensional electricity characteristic time series diagram.

[0069] Step S602: Determine the multidimensional power load characteristic items of the enterprise based on the multidimensional power characteristic time series diagram.

[0070] For example, when conducting multi-dimensional time-series analysis of electricity consumption data using a pre-defined time-series decomposition model, it is necessary to first collect and preprocess the company's daily electricity consumption data over the years to form a standardized time series (such as a combination of electricity consumption and corresponding dates). Then, using an enhanced time-series decomposition model (such as an improved Prophet model) that incorporates semantic information from production plans and equipment operation logs, the electricity load is decomposed into a baseline load (reflecting the company's long-term stable basic operating load), a production cycle load (capturing the daily, weekly, and monthly periodic operating patterns of the production line), an environmentally sensitive load (corresponding to the impact of external factors such as temperature and humidity on energy consumption for air conditioning and heating), a holiday / special event item (quantifying the short-term impact of non-periodic events such as national statutory holidays and equipment maintenance on the load), and a random fluctuation item (representing unexplained noise). By visualizing the time-series changes of each decomposition item, a multi-dimensional electricity characteristic time-series graph is formed. Finally, based on this graph, the fluctuation patterns, peak characteristics, and interrelationships of each characteristic item are analyzed to accurately determine the company's multi-dimensional electricity load characteristics, providing crucial data support for subsequent construction of an electricity-carbon coupling model and the formulation of carbon emission optimization strategies.

[0071] In the embodiments provided in this application, a feature time series graph is generated by performing multi-dimensional time series analysis on electricity consumption data through a preset time series decomposition model. This can accurately capture the periodicity, trend and volatility characteristics of electricity load, thereby providing a quantitative basis for determining multi-dimensional electricity load feature items and effectively improving the depth of enterprise electricity data analysis and the accuracy of carbon management decisions.

[0072] Based on the above embodiments, in one exemplary embodiment provided in this application, the specific implementation process of the above-mentioned method for determining enterprise carbon emissions may further include steps S701 to S703, which are described in detail below:

[0073] Step S701: Determine the enterprise's carbon emission sources and the corresponding carbon emissions based on the ledger information.

[0074] Step S702: Determine the historical carbon emission source ratio data of the enterprise based on the carbon emission source and carbon emission amount.

[0075] Step S703: Determine the predicted carbon emission source proportion data of enterprises based on historical carbon emission source proportion data.

[0076] For example, carbon emission sources are systematically identified from data sources such as annual enterprise ledgers, monthly statistical reports, energy purchase invoices, and production material records. These sources cover energy consumption (e.g., emissions from the combustion of fossil fuels such as raw coal, natural gas, and diesel, and indirect emissions from electricity consumption), production processes (e.g., emissions from raw material gas emissions from chemical enterprises and coke oven gas emissions from steel enterprises), waste treatment (e.g., methane emissions from wastewater treatment), and auxiliary activities (e.g., fuel emissions from office vehicles and emissions from employee commuting). Detailed data for each emission source is collected, including parameters such as energy consumption type, consumption volume, lower heating value, carbon content per unit calorific value, and oxidation rate, as well as indicators such as raw material gas usage, utilization rate, collection and removal rates of waste gas treatment devices, and Global Warming Potential (GWP). Subsequently, carbon emissions are calculated for each emission source according to common greenhouse gas accounting standards or industry-specific accounting standards, ultimately summarizing the total carbon emissions of the enterprise and the specific values ​​for each emission source. Alternatively, based on historical 3-5 year records, the proportion of carbon emissions from each emission source to the company's total emissions can be statistically analyzed annually to form a historical carbon emission source proportion dataset. This dataset can then be analyzed to determine its fluctuation trends (e.g., the proportion of emissions from the production process increases year by year with capacity expansion, while the proportion of emissions from electricity consumption decreases year by year due to energy-saving renovations). Finally, a time series forecasting model (such as the Prophet model incorporating holiday effects and seasonal adjustments, or the LSTM model capturing long-term dependencies) can be used. Using historical proportion data as input, and combining external variables such as company production plans, equipment renovation plans, and energy policies as covariates, the dynamic proportion of each emission source in the target year can be predicted. For example, it can be predicted that the proportion of emissions from the production process will increase by 5% in the next year due to new production lines, while the proportion of emissions from electricity consumption will decrease by 3% due to green electricity procurement. This provides accurate emission source structure input for the electricity-carbon coupling model, supporting companies in formulating carbon reduction strategies for each emission source.

[0077] In the embodiments provided in this application, by accurately identifying carbon emission sources and their corresponding carbon emissions from the ledger information, and combining historical data to construct the evolution law of carbon emission source proportion, a reliable basis can be provided for predicting the future carbon emission structure, thereby improving the accuracy of corporate carbon emission prediction and the pertinence of carbon management strategies.

[0078] Based on the above embodiments, in one exemplary embodiment provided in this application, the specific implementation method of the above-mentioned enterprise carbon emission determination method may further include steps S801 to S803, which are described in detail below:

[0079] Step S801: Based on the ledger information, determine the real-time consumption data and production cycle load items of non-electric energy, and determine the basic carbon emission parameters corresponding to non-electric energy based on the real-time consumption data.

[0080] Step S802: Based on the production cycle load item, determine the dynamic correction coefficient corresponding to the basic carbon emission parameters.

[0081] For example, based on enterprise ledger information, the first step is to extract real-time consumption data of non-electric energy (such as raw coal, natural gas, and diesel) from annual ledgers, monthly statistical reports, energy purchase invoices, and production material records. This data includes key parameters such as energy purchase volume, usage volume, lower heating value, carbon content per unit calorific value, and oxidation rate. Simultaneously, by combining production scheduling records and power load monitoring data, the specific fluctuation characteristics of production cycle load items are clarified (e.g., the periodic load change patterns of the production line on a daily / weekly / monthly basis). Then, based on industry emission standards or IPCC guidelines, the basic carbon emission parameters for non-electric energy are calculated. For example, for raw coal, the emission factor needs to be determined by combining lower heating value, carbon content per unit calorific value, and oxidation rate; for natural gas, the emission coefficient needs to be adjusted considering differences in combustion efficiency to ensure that the parameters accurately reflect the activity intensity. Next, based on the dynamic change characteristics of production cycle load items (e.g., increased load during peak periods corresponds to increased production intensity), a mapping relationship between load fluctuations and non-electric energy consumption is established through historical data regression analysis, thereby determining the dynamic correction coefficients for the basic carbon emission parameters. For example, the peak period of the production cycle load item is positively correlated with non-electric energy consumption. The emission factor can be adjusted by the load fluctuation range to reflect the impact of the actual production rhythm on carbon emissions.

[0082] Step S803: Determine the non-electric carbon emissions based on the dynamic correction coefficient and the basic carbon emission parameters, and determine the enterprise's total comprehensive carbon emissions based on the non-electric carbon emissions and the electric carbon emissions output by the corrected electric-carbon coupling model.

[0083] For example, the basic carbon emission parameter is corrected by a dynamic correction coefficient. For instance, when the load increases by 10% during peak production periods, the emission factor is adjusted through historical data regression analysis, ensuring the basic parameter accurately reflects the impact of actual production rhythm on carbon emissions. The corrected basic carbon emission parameter is then applied to real-time consumption data to calculate non-electricity carbon emissions. Simultaneously, the corrected electricity-carbon coupling model updates the contribution weight coefficients based on carbon emission characteristics in the real-time production plan (such as production carbon intensity and production shifts), and dynamically outputs electricity carbon emissions by combining electricity load characteristics (such as production cycle load and environmentally sensitive load) with predicted carbon emission source proportions. Finally, the non-electricity carbon emissions and electricity carbon emissions are summed to obtain the company's total comprehensive carbon emissions. This process not only achieves accurate quantification of carbon emissions from multiple energy sources but also dynamically responds to changes in production plans (such as shift changes and output fluctuations), external policy impacts (such as changes in the proportion of green electricity procurement), and equipment energy efficiency improvements. Continuous data validation and model iteration improve calculation accuracy, supporting companies in formulating comprehensive and dynamic carbon emission management strategies and optimization decisions.

[0084] In the embodiments provided in this application, non-electric energy consumption data and production cycle load items are accurately extracted from ledger information to determine basic carbon emission parameters. The dynamic characteristics of the load are used to generate correction coefficients to achieve refined accounting of non-electric carbon emissions. Combined with the carbon emissions of electricity output by the corrected electricity-carbon coupling model, a comprehensive carbon emission total accounting system covering all energy types can be constructed to provide enterprises with multi-dimensional and dynamic carbon management decision-making basis.

[0085] Please see Figure 3 , Figure 3 Flowchart of the method for determining corporate carbon emissions provided in this application Figure 2 ,like Figure 3 As shown, the process involves acquiring enterprise ledger information and determining the predicted proportion of the enterprise's multi-dimensional electricity load characteristics and carbon emission sources based on this information. Based on the energy consumption scenarios corresponding to the carbon emission sources, at least one target electricity load characteristic matching the energy consumption scenario is identified to establish a correlation between the energy consumption scenario and the target electricity load characteristic. The contribution weight coefficient of the target electricity load characteristic to the carbon emission source in the correlation is determined. Based on the contribution weight coefficient, the correlation, and the predicted proportion of the carbon emission source, an electricity-carbon coupling model is obtained. The carbon emission characteristics in the real-time production plan are determined, including production carbon emission intensity and production shifts. Based on the production carbon emission intensity and production shifts, the contribution weight coefficient is updated to obtain the updated contribution weight coefficient. Based on the updated contribution weight coefficient, the electricity-carbon coupling model is corrected to obtain the corrected electricity-carbon coupling model. On the other hand, based on the ledger information, real-time consumption data and production cycle load items of non-electric energy are determined, and the basic carbon emission parameters corresponding to non-electric energy are determined based on the real-time consumption data; the dynamic correction coefficients corresponding to the basic carbon emission parameters are dynamically determined based on the production cycle load items; the non-electric carbon emissions are determined based on the dynamic correction coefficients and the basic carbon emission parameters; and the total comprehensive carbon emissions of the enterprise are determined based on the non-electric carbon emissions and the electrical carbon emissions output by the corrected electric-carbon coupling model. For detailed implementation processes, please refer to the descriptions in the aforementioned embodiments; they will not be repeated here.

[0086] Figure 4 A schematic diagram of the structure of the enterprise carbon emission determination device provided in this application is shown below. Figure 4As shown, the enterprise carbon emission determination device 40 provided in this embodiment includes: an acquisition module 410, used to acquire enterprise ledger information and determine the predicted proportion data of the enterprise's multidimensional electricity load characteristics and carbon emission sources based on the ledger information; a coupling module 420, used to couple the multidimensional electricity load characteristics and carbon emission source predicted proportion data to obtain an electricity-carbon coupling model; a correction module 430, used to acquire the enterprise's real-time production plan and correct the electricity-carbon coupling model based on the real-time production plan to obtain a corrected electricity-carbon coupling model; and a determination module 440, used to determine the enterprise's total electricity carbon emissions based on the corrected electricity-carbon coupling model and determine the enterprise's carbon emission optimization strategy based on the total electricity carbon emissions.

[0087] In one possible implementation, the coupling module 420 is further configured to: establish a correlation between the energy consumption scenario and the target power load feature based on the energy consumption scenario corresponding to the carbon emission source; determine the contribution weight coefficient of the target power load feature to the carbon emission source in the correlation; and obtain an electric-carbon coupling model based on the contribution weight coefficient, the correlation, and the predicted proportion data of the carbon emission source.

[0088] In one possible implementation, the coupling module 420 is further configured to: determine the carbon emission factor corresponding to the carbon emission source; and determine at least one target power load characteristic item corresponding to the carbon emission factor based on the energy consumption scenario, wherein the carbon emission factor is used to represent the activity intensity of the carbon emission source; acquire historical carbon emission data and use the historical carbon emission data as input parameters of a preset neural network model to determine the contribution weight coefficient between the target power load characteristic item and the activity intensity of the carbon emission source based on the preset neural network model.

[0089] In one possible implementation, the correction module 430 is further configured to: determine the carbon emission characteristics in the real-time production plan, including the carbon emission intensity of production and the number of production shifts; update the contribution weight coefficient based on the carbon emission intensity of production and the number of production shifts to obtain the updated contribution weight coefficient; and correct the electric-carbon coupling model based on the updated contribution weight coefficient to obtain the corrected electric-carbon coupling model.

[0090] In one possible implementation, the acquisition module 410 is further configured to perform multi-dimensional time-series analysis on electricity consumption data through a preset time-series decomposition model to obtain a multi-dimensional electricity characteristic time-series diagram; and determine the multi-dimensional electricity load characteristic items of the enterprise based on the multi-dimensional electricity characteristic time-series diagram.

[0091] In one possible implementation, the acquisition module 410 is further configured to: determine the enterprise's carbon emission sources and the corresponding carbon emissions based on the ledger information; determine the enterprise's historical carbon emission source proportion data based on the carbon emission sources and carbon emissions; and determine the enterprise's predicted carbon emission source proportion data based on the historical carbon emission source proportion data.

[0092] In one possible implementation, the determining module 440 is further configured to: determine real-time consumption data and production cycle load items of non-electric energy based on ledger information, and determine the basic carbon emission parameters corresponding to non-electric energy based on real-time consumption data; determine the dynamic correction coefficient corresponding to the basic carbon emission parameters based on the production cycle load items; determine the non-electric carbon emission amount based on the dynamic correction coefficient and the basic carbon emission parameters, and determine the enterprise's total comprehensive carbon emissions based on the non-electric carbon emission amount and the electrical carbon emission amount output by the corrected electric-carbon coupling model.

[0093] The enterprise carbon emission determination device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0094] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 510 and a memory 520. Optionally, the device 50 further includes a communication component 530. The processor 510, memory 520, and communication component 530 are connected via a bus 540.

[0095] In a specific implementation, at least one processor 510 executes computer execution instructions stored in memory 520, causing at least one processor 510 to perform the above-described method.

[0096] The specific implementation process of processor 510 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0097] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0098] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0099] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0100] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0101] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0102] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0103] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0104] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0105] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0106] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0107] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0108] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0109] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for determining a company's carbon emissions, characterized in that, include: Obtain the enterprise's ledger information, and determine the enterprise's multidimensional power load characteristics and the predicted proportion of the enterprise's carbon emission sources based on the ledger information; The multidimensional electricity load characteristics are coupled with the predicted proportion of carbon emission sources to obtain an electricity-carbon coupling model. Obtain the enterprise's real-time production plan, and revise the electro-carbon coupling model based on the real-time production plan to obtain the revised electro-carbon coupling model; The total carbon emissions from electricity of the enterprise are determined based on the modified electricity-carbon coupling model, and the carbon emission optimization strategy of the enterprise is determined based on the total carbon emissions from electricity.

2. The method as described in claim 1, characterized in that, The process of coupling the multidimensional electricity load characteristics with the predicted proportion of carbon emission sources to obtain an electricity-carbon coupling model includes: Based on the energy consumption scenario corresponding to the carbon emission source, at least one target power load characteristic item matching the energy consumption scenario is determined to establish the correlation between the energy consumption scenario and the target power load characteristic item; Determine the contribution weighting coefficient of the target electricity load characteristic item to the carbon emission source in the correlation relationship; Based on the contribution weight coefficients, the correlation relationships, and the predicted proportion of carbon emission sources, an electrocarbon coupling model is obtained.

3. The method as described in claim 2, characterized in that, The method further includes: Determine the carbon emission factor corresponding to the carbon emission source, and determine at least one target electricity load characteristic item corresponding to the carbon emission factor based on the energy consumption scenario, wherein the carbon emission factor is used to represent the activity intensity of the carbon emission source; Historical carbon emission data is acquired and used as input parameters for a preset neural network model to determine the contribution weight coefficient between the target electricity load characteristic and the activity intensity of the carbon emission source based on the preset neural network model.

4. The method as described in claim 3, characterized in that, The process of revising the electro-carbon coupling model based on the real-time production plan to obtain the revised electro-carbon coupling model includes: Determine the carbon emission characteristics in the real-time production plan, including production carbon emission intensity and production shifts; Based on the production carbon emission intensity and the production shift, the contribution weight coefficient is updated to obtain the updated contribution weight coefficient. The modified electro-carbon coupling model is obtained by correcting the updated contribution weight coefficients.

5. The method as described in claim 1, characterized in that, The ledger information includes electricity consumption data, and the method further includes: The electricity consumption data is analyzed in multiple dimensions using a preset time series decomposition model to obtain a multi-dimensional time series diagram of electricity characteristics. The multidimensional power load characteristic items of the enterprise are determined based on the multidimensional power characteristic time series diagram.

6. The method as described in claim 1, characterized in that, The method further includes: Based on the ledger information, determine the enterprise's carbon emission sources and the corresponding carbon emissions from those sources; Based on the carbon emission sources and the carbon emission amounts, determine the historical carbon emission source proportion data of the enterprise; The predicted carbon emission source proportion data of the enterprise is determined based on the historical carbon emission source proportion data.

7. The method as described in claim 1, characterized in that, The method further includes: Based on the ledger information, the real-time consumption data and production cycle load items of non-electric energy are determined, and the basic carbon emission parameters corresponding to the non-electric energy are determined based on the real-time consumption data. Based on the production cycle load term, the dynamic correction coefficient corresponding to the basic carbon emission parameter is determined by dynamically determining the basic carbon emission parameter. The non-electric carbon emissions are determined based on the dynamic correction coefficient and the basic carbon emission parameters, and the total comprehensive carbon emissions of the enterprise are determined based on the non-electric carbon emissions and the electrical carbon emissions output by the corrected electric-carbon coupling model.

8. A device for determining enterprise carbon emissions, characterized in that, The device includes: The acquisition module is used to acquire the enterprise's ledger information and determine the enterprise's multidimensional power load characteristics and the predicted proportion of the enterprise's carbon emission sources based on the ledger information. The coupling module is used to couple the multidimensional electricity load characteristics with the predicted proportion data of the carbon emission sources to obtain an electricity-carbon coupling model. The correction module is used to obtain the real-time production plan of the enterprise and correct the electro-carbon coupling model based on the real-time production plan to obtain the corrected electro-carbon coupling model. The determination module is used to determine the total carbon emissions of the enterprise based on the modified electric-carbon coupling model, and to determine the enterprise's carbon emission optimization strategy based on the total carbon emissions of the enterprise.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.

Images