Environment-friendly low-carbon management method and system for enterprise

Abstract

The invention provides a green low-carbon management method and system for an enterprise, and relates to the technical field of low carbon, and the method comprises the steps: obtaining a plurality of departments of a target enterprise, obtaining the historical energy consumption data of the plurality of departments, obtaining a plurality of historical carbon emission data of the plurality of departments according to the historical energy consumption data in combination with a corresponding carbon emission coefficient, and carrying out the calculation of the historical carbon emission data. And constructing a carbon emission prediction function based on the plurality of historical environmental data and the plurality of historical carbon emission data, inputting the real-time energy consumption data and environmental data of the plurality of departments into the carbon emission prediction function to obtain carbon emission prediction data of the plurality of departments, and executing low-carbon management of the target enterprise according to the carbon emission prediction data. The technical problem that in the prior art, carbon emission management lacks dynamic prediction and real-time optimization capacity, and consequently an enterprise is difficult to effectively control carbon emission is solved. The technical effects of dynamically predicting carbon emission based on historical and real-time energy consumption and environmental data and effectively controlling enterprise carbon emission through an intelligent optimization strategy are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of low-carbon management, and in particular to a green low-carbon management method and system for an enterprise. Background Art

[0002] In recent years, with the popularization of the concept of green economy, many enterprises have begun to explore green and low-carbon management methods. The existing low-carbon management model for enterprises is often limited to statistical analysis and extensive regulation of post-event data, which makes it difficult to effectively capture and predict the dynamic trend of energy consumption in various departments and their corresponding carbon emissions, thus limiting the refinement and efficiency of low-carbon management. In addition, the fluctuation of environmental factors, such as weather changes and light intensity, has an impact on energy consumption that cannot be ignored. At present, enterprises generally lack scientific prediction mechanisms based on these real-time environmental data, making it difficult for enterprises to plan in advance and take precise energy-saving and emission reduction measures.

[0003] Carbon emission management in existing technologies lacks dynamic prediction and real-time optimization capabilities, which leads to technical problems that make it difficult for companies to effectively control carbon emissions and formulate precise energy-saving strategies. Summary of the invention

[0004] The present application provides a green and low-carbon management method and system for an enterprise, which is used to solve the technical problem that carbon emission management in the existing technology lacks dynamic prediction and real-time optimization capabilities, making it difficult for enterprises to effectively control carbon emissions and formulate accurate energy-saving strategies.

[0005] In view of the above problems, the present application provides a green and low-carbon management method and system for an enterprise.

[0006] The first aspect of the present application provides a green and low-carbon management method for an enterprise, the method comprising: obtaining multiple departments of a target enterprise according to the enterprise structure of the target enterprise; obtaining historical energy consumption data of the multiple departments, the historical energy consumption data including electricity consumption, heating energy consumption, and cooling energy consumption; obtaining multiple historical carbon emission data of the multiple departments according to the historical energy consumption data in combination with corresponding carbon emission coefficients; obtaining multiple historical environmental data of the target enterprise, and constructing a carbon emission prediction function based on the multiple historical environmental data and the multiple historical carbon emission data, each of the multiple historical environmental data including weather data and light data; inputting the real-time energy consumption data and environmental data of multiple departments into the carbon emission prediction function to obtain carbon emission prediction data for multiple departments; and performing low-carbon management of the target enterprise according to the carbon emission prediction data.

[0007] The second aspect of the present application provides a green and low-carbon management system for an enterprise, the system comprising: an enterprise department acquisition module, the enterprise department acquisition module is used to obtain multiple departments of a target enterprise according to the enterprise architecture of the target enterprise; a historical energy consumption data acquisition module, the historical energy consumption data acquisition module is used to obtain historical energy consumption data of the multiple departments, the historical energy consumption data includes electricity consumption, heating energy consumption, and cooling energy consumption; a historical carbon emission data acquisition module, the historical carbon emission data acquisition module is used to obtain multiple historical carbon emission data of the multiple departments according to the historical energy consumption data and the corresponding carbon emission coefficient; a carbon emission forecast module A carbon emission prediction function construction module, the carbon emission prediction function construction module is used to obtain multiple historical environmental data of the target enterprise, and construct a carbon emission prediction function based on the multiple historical environmental data and the multiple historical carbon emission data, each of the multiple historical environmental data includes weather data and light data; a carbon emission prediction data acquisition module, the carbon emission prediction data acquisition module is used to input real-time energy consumption data and environmental data of multiple departments into the carbon emission prediction function, and obtain carbon emission prediction data for multiple departments; a low-carbon management execution module, the low-carbon management execution module is used to execute low-carbon management of the target enterprise according to the carbon emission prediction data.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The method provided in the embodiment of the present application obtains multiple departments of the target enterprise according to the enterprise architecture of the target enterprise, obtains historical energy consumption data of the multiple departments, and the historical energy consumption data includes electricity consumption, heating energy consumption, and cooling energy consumption; according to the historical energy consumption data, combined with the corresponding carbon emission coefficient, obtains multiple historical carbon emission data of the multiple departments, obtains multiple historical environmental data of the target enterprise, and constructs a carbon emission prediction function based on the multiple historical environmental data and the multiple historical carbon emission data, inputs the real-time energy consumption data and environmental data of the multiple departments into the carbon emission prediction function, obtains the carbon emission prediction data of multiple departments, and executes the low-carbon management of the target enterprise according to the carbon emission prediction data. The technical effect of dynamically predicting carbon emissions based on historical and real-time energy consumption and environmental data and effectively controlling the carbon emissions of enterprises through intelligent optimization strategies is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1A flow chart of a green and low-carbon management method for an enterprise provided in this application;

[0012] Figure 2 A structural diagram of a green and low-carbon management system for an enterprise provided for this application.

[0013] Explanation of the reference numerals: enterprise department acquisition module 11, historical energy consumption data acquisition module 12, historical carbon emission data acquisition module 13, carbon emission prediction function construction module 14, carbon emission prediction data acquisition module 15, low-carbon management execution module 16. DETAILED DESCRIPTION

[0014] This application provides a green and low-carbon management method and system for an enterprise, which is used to solve the technical problem that the existing technology of carbon emission management lacks dynamic prediction and real-time optimization capabilities, making it difficult for enterprises to effectively control carbon emissions. It achieves the technical effect of dynamically predicting carbon emissions based on historical and real-time energy consumption and environmental data, and effectively controlling corporate carbon emissions through intelligent optimization strategies.

[0015] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a green and low-carbon management method for an enterprise, the method comprising:

[0017] According to the corporate structure of the target enterprise, multiple departments of the target enterprise are obtained.

[0018] Specifically, first clarify the target enterprise's enterprise architecture information. The enterprise architecture refers to the hierarchical structure of various organizational units within the enterprise, reflecting the relationship and division of responsibilities between different departments. There are multiple different business units within the enterprise, and the energy consumption requirements and carbon emissions of each department may be different. By accessing the target enterprise's enterprise architecture, detailed department information of the target enterprise can be obtained. Department information includes department names and department responsibilities of multiple departments, such as production departments, administrative departments, technical support departments, etc. By obtaining multiple departments of the target enterprise, a clear department segmentation basis is provided for the entire green and low-carbon management, so that subsequent data processing and optimization predictions can be accurate to the department level, thereby realizing personalized low-carbon management.

[0019] The historical energy consumption data of the multiple departments are obtained, wherein the historical energy consumption data includes electricity consumption, heating energy consumption, and cooling energy consumption.

[0020] Specifically, by accessing the target enterprise's energy management database or the energy consumption monitoring equipment within the enterprise, such as smart meters, monitoring records of heating and cooling systems, etc., the historical energy consumption data of each department of the target enterprise is extracted. The historical energy consumption data includes electricity consumption, heating energy consumption, and cooling energy consumption. It is an important basis for evaluating and optimizing the carbon emissions of enterprises, including complete energy consumption records in the past period, so as to conduct long-term analysis and prediction of energy consumption patterns. Among them, electricity consumption includes the electricity consumed by the target enterprise in the process of production, office, lighting, equipment operation, etc. Heating energy consumption refers to the energy used by the enterprise to maintain a suitable working environment in winter or cold environments. Cooling energy consumption refers to the energy used to keep the temperature of equipment and working environment stable in summer or warm climates. By obtaining the historical energy consumption data of each department, it is possible to accurately understand the energy consumption of each department, thereby providing data support for low-carbon management.

[0021] According to the historical energy consumption data and in combination with corresponding carbon emission coefficients, multiple historical carbon emission data of the multiple departments are obtained.

[0022] Furthermore, based on the historical energy consumption data and in combination with the corresponding carbon emission coefficients, multiple historical carbon emission data of the multiple departments are obtained, including: dividing the historical energy consumption data of the multiple departments according to quarters to obtain multiple historical quarterly energy consumption data of the multiple departments; based on the multiple historical quarterly energy consumption data, respectively calculating the quarterly electricity carbon emissions, quarterly heating carbon emissions and quarterly cooling carbon emissions of the multiple departments in each quarter, wherein quarterly electricity carbon emissions = quarterly electricity consumption × electricity carbon emission coefficient; quarterly heating carbon emissions = quarterly heating energy consumption × heating carbon emission coefficient; quarterly cooling carbon emissions = quarterly cooling energy consumption × cooling carbon emission coefficient; integrating multiple quarterly electricity carbon emissions, quarterly heating carbon emissions and quarterly heating carbon emissions to obtain multiple historical carbon emission data of the multiple departments, wherein each of the multiple historical carbon emission data includes electricity carbon emissions, heating carbon emissions and cooling carbon emissions.

[0023] Specifically, the historical energy consumption data of each department is first divided by quarter. The quarterly division helps to capture the changes in energy consumption of enterprises in different time periods, especially in scenarios with large seasonal impacts, such as winter heating and summer cooling. According to the division results, multiple historical quarterly energy consumption data of each department are obtained. Multiple historical quarterly energy consumption data refer to the historical quarterly energy consumption data of each quarter. Then, according to the historical energy consumption data of each quarter, the quarterly electricity carbon emissions, quarterly heating carbon emissions and quarterly cooling carbon emissions of each department are calculated respectively. The specific calculation formula is: quarterly electricity carbon emissions = quarterly electricity consumption × electricity carbon emission coefficient, where the electricity carbon emission coefficient is determined according to the energy structure of the power grid where the target enterprise is located; quarterly heating carbon emissions = quarterly heating energy consumption × heating carbon emission coefficient, and the heating carbon emission coefficient depends on the type of heating energy used (such as natural gas, fuel oil, etc.); quarterly cooling carbon emissions = quarterly cooling energy consumption × cooling carbon emission coefficient, and the cooling carbon emission coefficient is determined according to the energy efficiency and electricity consumption of the refrigeration equipment. After obtaining the electricity carbon emissions, heating carbon emissions and cooling carbon emissions for each quarter according to the above formula, the various carbon emissions of each quarter are integrated to obtain the annual historical carbon emissions data of each department. The historical carbon emissions data of each department includes electricity carbon emissions, heating carbon emissions and cooling carbon emissions. The relationship between energy consumption and carbon emissions is refined through quarterly division, so that carbon emission data can reflect the fluctuation of energy consumption with seasonal changes, improve the accuracy of subsequent carbon emission forecasts, and provide more reliable data support for subsequent optimization and adjustment.

[0024] A plurality of historical environmental data of a target enterprise is obtained, and a carbon emission prediction function is constructed based on the plurality of historical environmental data and the plurality of historical carbon emission data, wherein each of the plurality of historical environmental data includes weather data and light data.

[0025] Furthermore, multiple historical environmental data of the target enterprise are obtained, including: obtaining the geographical location of the target enterprise, and using the geographical location as a location constraint; determining the time range for each quarter based on the multiple historical carbon emission data, and using the time range as a time constraint; using the location constraint and the time constraint to obtain the multiple historical environmental data corresponding to the geographical location and the time range.

[0026] Specifically, first, the precise geographic location of the target enterprise is determined through GPS positioning or other geographic information data sources, and the geographic location is used as a location constraint. Geographic location is a key factor affecting environmental conditions, because environmental parameters such as weather, climate, and light in different regions will significantly affect the energy use of enterprises. For example, heating demand is higher in the north, while cooling demand is greater in the south in summer.

[0027] Then, the time range for each quarter is determined based on the multiple historical carbon emission data that have been obtained. Since the energy consumption of each quarter is also closely related to environmental conditions, the environmental data and energy consumption data can be accurately matched by determining the quarterly time period. According to the carbon emission characteristics of the target enterprise in each quarter, the start and end time of each quarter are determined, and these time ranges are used as time constraints. Time constraints can help filter out environmental data within a specific time period.

[0028] After determining the location constraints and time constraints, the location constraints and time constraints are used to obtain the corresponding historical environmental data from the meteorological database or environmental data source, such as the National Meteorological Bureau, environmental monitoring stations, etc. The historical environmental data includes meteorological data and light data, wherein the meteorological data includes temperature and humidity, precipitation, wind speed, etc., and the light data includes solar radiation intensity, sunshine time, etc. By obtaining the target enterprise's geographical location and accurate environmental data in different seasons, a more comprehensive and accurate input is provided for the subsequent carbon emission prediction model, thereby improving the model's prediction ability and the enterprise's carbon emission management effect.

[0029] Furthermore, a carbon emission prediction function is constructed based on the multiple historical environmental data and the multiple historical carbon emission data, including: aligning the multiple historical environmental data and the multiple historical carbon emission data according to a time series; normalizing the multiple historical environmental data and the multiple historical carbon emission data to obtain a standard historical environmental data set and a standard historical carbon emission data set; using the standard historical environmental data set and the standard historical carbon emission data set to train and verify a machine learning model; when the training model meets preset conditions, using the trained model as a carbon emission prediction function.

[0030] Specifically, according to the continuity of the time series, the multiple historical environmental data and the multiple historical carbon emission data are aligned to ensure the time synchronization between environmental variables and carbon emissions, that is, at the same time point or time interval, the environmental conditions used can accurately reflect the corresponding carbon emissions. Then, in order to eliminate the influence of different dimensions and magnitudes on model training, the multiple historical environmental data and the multiple historical carbon emission data are processed by a normalization method and converted into a unified scale range (such as between 0 and 1), thereby obtaining a standard historical environmental data set and a standard historical carbon emission data set. This process not only simplifies the calculation, but also improves the convergence speed and prediction accuracy of subsequent models.

[0031] Next, the machine learning model is trained using a standardized data set, with the standard historical environmental data set as input and the standard historical carbon emission data set as the target output. Through multiple iterations of training, a mapping relationship between carbon emissions and environmental conditions is established, and accurate carbon emission predictions can be made under new environmental conditions. Machine learning models such as linear regression, decision trees, neural networks, etc. During the model training process, the performance of the training model is evaluated by preset conditions, including the threshold of the prediction error, the number of iterations of the model training, or the performance indicators on the validation set. When the training model meets the preset conditions, it indicates that the training model has sufficient generalization ability and prediction accuracy. The trained model is used as a carbon emission prediction function. The carbon emission prediction function can predict future carbon emissions based on real-time environmental data and energy consumption, provide accurate carbon emission predictions for enterprises, and provide data support for enterprises to formulate energy-saving and emission reduction measures, thereby realizing intelligent low-carbon management and effectively controlling corporate carbon emissions.

[0032] Furthermore, constructing a carbon emission prediction function based on the multiple historical environmental data and the multiple historical carbon emission data also includes: defining a time window, the time window containing fixed time period data; using the time window as a constraint condition and adding it to the carbon emission prediction function; according to the time window, collecting real-time energy consumption data of multiple departments, obtaining multiple carbon emission data, and obtaining multiple environmental data; inputting the collected multiple carbon emission data and the multiple environmental data into the carbon emission prediction function, continuously performing optimization calculations until the end of the time window, and starting collection and optimization of the next time window.

[0033] Specifically, first, based on the business needs of the enterprise and the requirements of prediction accuracy, the time window is defined, and the specific length and starting point of the time window are clarified. The time window is a key constraint condition, which defines a fixed time period data set for analyzing and predicting carbon emissions. By setting the time window, relevant environmental data and carbon emission data can be centrally processed and analyzed within a specific time period, reducing data redundancy and noise interference. Then, the time window is added to the carbon emission prediction function as a constraint condition. The constraint condition ensures that the data collected in each time window is closed, that is, only calculations are performed between the start and end of the window, avoiding confusion across multiple time periods, and being able to clearly distinguish the carbon emission change trends between different time windows, which is conducive to dynamic adjustment of energy consumption management.

[0034] In each time window, the real-time energy consumption data and multiple environmental data of each department of the target enterprise are collected according to the real-time situation, and multiple carbon emission data are obtained according to the real-time energy consumption data. The multiple carbon emission data and the multiple environmental data are used as input data for carbon emission prediction and input into the carbon emission prediction function. The carbon emission prediction function uses a machine learning algorithm and combines the rules and trends in historical data to predict the carbon emissions in the current time window, and continuously optimizes the calculation. The purpose of continuous optimization is to dynamically adjust the prediction results of the model according to the real-time data in each time window, thereby improving the prediction accuracy. In this process, as new data is input, the prediction function is continuously optimized and adjusted according to the continuous inflow of real-time data to improve the accuracy of carbon emission prediction. When the time window ends, the calculation of the current window will automatically end, and the data collection and optimization process of the next time window will start. This time window design not only ensures the timeliness of data processing, but also can be dynamically adjusted according to the latest data, making carbon emission prediction and energy consumption management more accurate and flexible. By introducing the time window as a constraint condition for the carbon emission prediction function, it can respond to environmental changes in real time, dynamically adjust the prediction results, improve the accuracy and reliability of the prediction results, and ensure that the target enterprises can effectively control their carbon emissions through intelligent optimization strategies.

[0035] The real-time energy consumption data and environmental data of multiple departments are input into the carbon emission prediction function to obtain the carbon emission prediction data of multiple departments.

[0036] Furthermore, the real-time energy consumption data and environmental data of multiple departments are input into the carbon emission prediction function to obtain the carbon emission prediction data of multiple departments, including: summarizing the actual carbon emission data within the time window, and comparing the actual carbon emission data with the carbon emission prediction data to calculate the difference; performing statistical analysis on the difference within the entire time window to identify the source of error; using an incremental training method to gradually update the carbon emission prediction function; clustering the error sources, and correcting the carbon emission prediction function according to the clustering results.

[0037] Specifically, the real-time energy consumption data and environmental data collected in each time window are input into the trained carbon emission prediction function to predict the carbon emissions of each department and obtain the carbon emission prediction data of each department. The carbon emission data actually generated by each department in the time window is summarized, and the actual carbon emission data is compared with the carbon emission prediction data obtained by function prediction, and the difference between the two is calculated. This difference reflects the prediction error of the carbon emission prediction function in actual application, and then the difference in the entire time window is statistically analyzed. By analyzing the error distribution of different departments or different time periods, the source of error is identified. The source of error may be, for example, the setting of model parameters is not accurate enough, the change of environmental data is too drastic, or the energy consumption pattern is unstable. By identifying the source of error, it is possible to analyze in which aspects of the carbon emission prediction function need to be further optimized.

[0038] In order to improve the prediction accuracy, the incremental training method is used to gradually update the carbon emission prediction function. Incremental training is an online learning method that allows the model to gradually adjust its own parameters after receiving new data without retraining the entire model. This allows the model to continuously improve over time and adapt to real-time changing energy consumption and environmental conditions, thereby improving the accuracy of the prediction. On the basis of error analysis, the error sources are clustered by clustering algorithms. Clustering is to classify errors with similar characteristics into one category. Different types of error patterns can be understood by analyzing these clusters. Clustering algorithms such as K-means clustering. Different types of error patterns can be obtained through clustering. For example, some errors may mainly come from energy consumption fluctuations under specific weather conditions, while other errors may be due to changes in equipment operating efficiency. Finally, according to the clustering results, the carbon emission prediction function is targeted and corrected, including adjusting model parameters or optimizing prediction methods under specific conditions. Through this incremental learning and error correction mechanism, the carbon emission prediction model will be continuously optimized, which can reflect the actual carbon emissions of various departments of the enterprise in real time and provide enterprises with more accurate and reliable low-carbon management suggestions.

[0039] According to the carbon emission forecast data, low-carbon management of the target enterprise is implemented.

[0040] Furthermore, based on the carbon emission prediction data, low-carbon management of the target enterprise is performed, including: setting carbon emission thresholds for multiple departments based on the overall low-carbon target data of the target enterprise and the multiple historical carbon emission data; comparing the carbon emission prediction data with the carbon emission threshold, and if there is one or more departments whose carbon emission prediction data is greater than the carbon emission threshold, sending an energy-saving and low-carbon adjustment strategy to the one or more departments; and performing low-carbon management of the target enterprise based on the energy-saving and low-carbon adjustment strategy.

[0041] Specifically, first, according to the overall low-carbon target data of the enterprise and the historical carbon emission data of each department, a reasonable carbon emission threshold is set for each department. The carbon emission threshold refers to the maximum carbon emissions allowed by each department within a time range. Exceeding this value means that energy-saving measures need to be taken. The predicted carbon emission forecast data is compared with the carbon emission threshold of each department. If the predicted carbon emission data exceeds the set threshold, an energy-saving and low-carbon adjustment strategy will be automatically sent to the department that exceeds the standard. The energy-saving and low-carbon adjustment strategy includes reducing the operating time of the equipment, adjusting the working efficiency of the temperature control equipment, or switching to a more efficient energy source. According to the energy-saving strategy issued, the relevant personnel of each department perform the corresponding adjustments, so as to effectively control the carbon emissions of the enterprise through intelligent optimization strategies and realize the low-carbon management of the enterprise.

[0042] Embodiment 2, based on the same inventive concept as the green and low-carbon management method of an enterprise in the above embodiment, Figure 2 As shown, the present application provides a green and low-carbon management system for an enterprise, wherein the system comprises:

[0043] An enterprise department acquisition module 11 is used to obtain multiple departments of a target enterprise according to the enterprise structure of the target enterprise; a historical energy consumption data acquisition module 12 is used to obtain historical energy consumption data of the multiple departments, and the historical energy consumption data includes electricity consumption, heating energy consumption, and cooling energy consumption; a historical carbon emission data acquisition module 13 is used to obtain multiple historical carbon emission data of the multiple departments according to the historical energy consumption data and the corresponding carbon emission coefficient; a carbon emission prediction function construction module 14 is used to construct a carbon emission prediction function. The function construction module 14 is used to obtain multiple historical environmental data of the target enterprise, and to construct a carbon emission prediction function based on the multiple historical environmental data and the multiple historical carbon emission data, wherein each of the multiple historical environmental data includes weather data and light data; a carbon emission prediction data acquisition module 15, wherein the carbon emission prediction data acquisition module 15 is used to input the real-time energy consumption data and environmental data of multiple departments into the carbon emission prediction function to obtain carbon emission prediction data for multiple departments; a low-carbon management execution module 16, wherein the low-carbon management execution module 16 is used to execute low-carbon management of the target enterprise according to the carbon emission prediction data.

[0044] Furthermore, the historical carbon emission data acquisition module 13 is used to perform the following steps: divide the historical energy consumption data of the multiple departments according to quarters to obtain multiple historical quarterly energy consumption data of the multiple departments; based on the multiple historical quarterly energy consumption data, respectively calculate the quarterly electricity carbon emissions, quarterly heating carbon emissions and quarterly cooling carbon emissions of the multiple departments in each quarter, wherein, quarterly electricity carbon emissions = quarterly electricity consumption × electricity carbon emission coefficient; quarterly heating carbon emissions = quarterly heating energy consumption × heating carbon emission coefficient; quarterly cooling carbon emissions = quarterly cooling energy consumption × cooling carbon emission coefficient; integrate multiple quarterly electricity carbon emissions, quarterly heating carbon emissions and quarterly heating carbon emissions to obtain multiple historical carbon emission data of the multiple departments, wherein each of the multiple historical carbon emission data includes electricity carbon emissions, heating carbon emissions and cooling carbon emissions.

[0045] Furthermore, the carbon emission prediction function construction module 14 is used to perform the following steps: obtain the geographical location of the target enterprise, and use the geographical location as a location constraint; determine the time range for each quarter based on the multiple historical carbon emission data, and use the time range as a time constraint; use the location constraint and the time constraint to obtain the multiple historical environmental data corresponding to the geographical location and the time range.

[0046] Furthermore, the carbon emission prediction function construction module 14 is also used to perform the following steps: align the multiple historical environmental data and the multiple historical carbon emission data according to the time series; normalize the multiple historical environmental data and the multiple historical carbon emission data to obtain a standard historical environmental data set and a standard historical carbon emission data set; use the standard historical environmental data set and the standard historical carbon emission data set to train and verify the machine learning model; when the training model meets the preset conditions, use the trained model as the carbon emission prediction function.

[0047] Furthermore, the carbon emission prediction function construction module 14 is also used to perform the following steps: define a time window, which contains fixed time period data; use the time window as a constraint condition and add it to the carbon emission prediction function; according to the time window, collect real-time energy consumption data of multiple departments, obtain multiple carbon emission data, and obtain multiple environmental data; input the collected multiple carbon emission data and the multiple environmental data into the carbon emission prediction function, continue to perform optimization calculations until the end of the time window, and start collecting and optimizing the next time window.

[0048] Furthermore, the carbon emission prediction data acquisition module 15 is used to perform the following steps: summarize the actual carbon emission data within the time window, and compare the actual carbon emission data with the carbon emission prediction data to calculate the difference; perform statistical analysis on the difference within the entire time window to identify the source of error; use an incremental training method to gradually update the carbon emission prediction function; cluster the error sources and correct the carbon emission prediction function according to the clustering results.

[0049] Furthermore, the low-carbon management execution module 16 is used to perform the following steps: setting carbon emission thresholds for multiple departments based on the overall low-carbon target data of the target enterprise and the multiple historical carbon emission data; comparing the carbon emission forecast data with the carbon emission threshold, and if there is one or more departments whose carbon emission forecast data is greater than the carbon emission threshold, sending an energy-saving and low-carbon adjustment strategy to the one or more departments; and performing low-carbon management of the target enterprise based on the energy-saving and low-carbon adjustment strategy.

[0050] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0051] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A green and low-carbon management method for an enterprise, characterized in that: The method comprises: Obtain multiple departments of the target enterprise according to its corporate structure; Acquire historical energy consumption data of the multiple departments, wherein the historical energy consumption data includes electricity consumption, heating energy consumption, and cooling energy consumption; According to the historical energy consumption data, combined with the corresponding carbon emission coefficients, a plurality of historical carbon emission data of the plurality of departments are obtained; Obtaining a plurality of historical environmental data of the target enterprise, and constructing a carbon emission prediction function based on the plurality of historical environmental data and the plurality of historical carbon emission data, wherein each of the plurality of historical environmental data includes weather data and light data; Input the real-time energy consumption data and environmental data of multiple departments into the carbon emission prediction function to obtain the carbon emission prediction data of multiple departments; According to the carbon emission forecast data, low-carbon management of the target enterprise is implemented.

2. The green and low-carbon management method for an enterprise as claimed in claim 1, characterized in that: According to the historical energy consumption data, combined with the corresponding carbon emission coefficient, multiple historical carbon emission data of the multiple departments are obtained, including: Dividing the historical energy consumption data of the multiple departments by quarter to obtain multiple historical quarterly energy consumption data of the multiple departments; Based on the multiple historical quarterly energy consumption data, the quarterly electricity carbon emissions, quarterly heating carbon emissions and quarterly cooling carbon emissions of multiple departments are calculated for each quarter, wherein: Quarterly electricity carbon emissions = quarterly electricity consumption × electricity carbon emission coefficient; Quarterly heating carbon emissions = quarterly heating energy consumption × heating carbon emission coefficient; Quarterly refrigeration carbon emissions = quarterly refrigeration energy consumption × refrigeration carbon emission coefficient; Multiple quarterly electricity carbon emissions, quarterly heating carbon emissions, and quarterly cooling carbon emissions are integrated to obtain multiple historical carbon emission data of multiple departments, wherein each of the multiple historical carbon emission data includes electricity carbon emissions, heating carbon emissions, and cooling carbon emissions.

3. The green and low-carbon management method for an enterprise as claimed in claim 2, characterized in that: Obtain multiple historical environmental data of the target enterprise, including: Obtaining a geographic location of a target enterprise, and using the geographic location as a location constraint; Determine a time range for each quarter based on the plurality of historical carbon emission data, and use the time range as a time constraint; The plurality of historical environment data corresponding to the geographic location and the time range are obtained by utilizing the location constraint and the time constraint.

4. The green and low-carbon management method for an enterprise as claimed in claim 1, characterized in that: Constructing a carbon emission prediction function based on the plurality of historical environmental data and the plurality of historical carbon emission data includes: According to the time series, aligning the plurality of historical environmental data with the plurality of historical carbon emission data; Normalizing the plurality of historical environmental data and the plurality of historical carbon emission data to obtain a standard historical environmental data set and a standard historical carbon emission data set; Using the standard historical environmental data set and the standard historical carbon emission data set to train and verify the machine learning model; When the training model meets the preset conditions, the trained model is used as the carbon emission prediction function.

5. The green and low-carbon management method for an enterprise as claimed in claim 4, characterized in that: Constructing a carbon emission prediction function based on the plurality of historical environmental data and the plurality of historical carbon emission data further includes: Defining a time window, wherein the time window includes fixed time period data; Taking the time window as a constraint condition, adding the carbon emission prediction function; According to the time window, real-time energy consumption data of multiple departments are collected, multiple carbon emission data are obtained, and multiple environmental data are obtained; The collected multiple carbon emission data and the multiple environmental data are input into the carbon emission prediction function, and the optimization calculation is continuously performed until the time window ends, and the collection and optimization of the next time window are started.

6. The green and low-carbon management method for an enterprise as claimed in claim 5, characterized in that: Input the real-time energy consumption data and environmental data of multiple departments into the carbon emission prediction function to obtain carbon emission prediction data of multiple departments, including: Summarizing the actual carbon emission data within the time window, and comparing the actual carbon emission data with the carbon emission forecast data to calculate the difference; Perform statistical analysis on the differences within the entire time window to identify the source of error; Using an incremental training method to gradually update the carbon emission prediction function; The error sources are clustered, and the carbon emission prediction function is corrected according to the clustering results.

7. The green and low-carbon management method for an enterprise as claimed in claim 1, characterized in that: According to the carbon emission forecast data, implement low-carbon management of the target enterprise, including: Setting carbon emission thresholds for multiple departments based on the overall low-carbon target data of the target enterprise and the multiple historical carbon emission data; Compare the carbon emission prediction data with the carbon emission threshold, and if there are one or more departments whose carbon emission prediction data is greater than the carbon emission threshold, send energy-saving and low-carbon adjustment strategies to the one or more departments; According to the energy-saving and low-carbon adjustment strategy, low-carbon management of the target enterprise is carried out.

8. A green and low-carbon management system for an enterprise, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: An enterprise department acquisition module, wherein the enterprise department acquisition module is used to acquire multiple departments of a target enterprise according to the enterprise structure of the target enterprise; A historical energy consumption data acquisition module, wherein the historical energy consumption data acquisition module is used to acquire the historical energy consumption data of the multiple departments, wherein the historical energy consumption data includes electricity consumption, heating energy consumption, and cooling energy consumption; A historical carbon emission data acquisition module, wherein the historical carbon emission data acquisition module is used to obtain a plurality of historical carbon emission data of the plurality of departments according to the historical energy consumption data and in combination with corresponding carbon emission coefficients; A carbon emission prediction function construction module, the carbon emission prediction function construction module is used to obtain a plurality of historical environmental data of the target enterprise, and construct a carbon emission prediction function based on the plurality of historical environmental data and the plurality of historical carbon emission data, each of the plurality of historical environmental data including weather data and light data; A carbon emission prediction data acquisition module, wherein the carbon emission prediction data acquisition module is used to input the real-time energy consumption data and environmental data of multiple departments into a carbon emission prediction function to obtain carbon emission prediction data of multiple departments; A low-carbon management execution module is used to execute low-carbon management of the target enterprise according to the carbon emission prediction data.

Images