Carbon emission electric carbon measuring and calculating method and device, electronic equipment, medium and program product

Abstract

The invention relates to the technical field of carbon emission, in particular to a carbon emission electricity carbon measuring and calculating method and device, electronic equipment, a medium and a program product, and the method comprises the steps: collecting enterprise historical checking library data and power consumption data of a plurality of enterprises, so as to obtain carbon emission cases of the plurality of enterprises; constructing a portrait rule base, and establishing an enterprise portrait base based on the portrait rule base; and determining an enterprise portrait of the target enterprise according to the attribute of the target enterprise and an enterprise portrait library, and determining an electricity-carbon relation function of a to-be-predicted case of the target enterprise through the enterprise portrait so as to predict a carbon emission value of the to-be-predicted case. According to the method, enterprise portrait and electricity-carbon correlation analysis can be carried out by utilizing the enterprise power data, a relation model of enterprise power consumption and carbon emission is established, real-time carbon emission data of the enterprise can be calculated according to real-time power consumption data of the enterprise, the implementation process is simple and does not depend on additional equipment, and the implementation efficiency is improved. And meanwhile, the system has extremely high landing application capability and is convenient to popularize.

Description

Technical Field

[0001] The present application relates to the field of carbon emission technology, and in particular to a carbon emission and electricity carbon calculation method, device, electronic equipment, medium and program product. Background Art

[0002] While corporate carbon emissions statistics have matured in recent years, they also have significant flaws. For example, compiling corporate carbon emissions data from the previous year in the next year results in a significant time lag; companies lack the ability to compile real-time carbon emissions data; and carbon emissions data cannot fully guide energy conservation and emissions reduction efforts. With the passage of time, the frequency of traditional data collection is no longer sufficient to meet the dual carbon management needs of companies. Consequently, some companies have begun implementing carbon emissions monitoring, using this data to calculate carbon emissions.

[0003] Among related technologies, enterprises' carbon emissions monitoring mostly adopts Internet of Things monitoring technology, which monitors the consumption of energy such as electricity, gas, coal, and oil and converts it into carbon emissions, thereby understanding the carbon emissions of enterprises.

[0004] However, the relevant technology requires the installation of monitoring equipment to convert energy consumption into carbon emissions, which can easily lead to difficulties in achieving coverage and promotion due to the high cost of installing online monitoring. At the same time, after installing online monitoring equipment, companies need to make continuous investment in operation and maintenance. The operation and maintenance costs are too high and difficult to sustain, which needs to be solved urgently. Summary of the Invention

[0005] The present application provides a carbon emission and electricity carbon measurement method, device, electronic device, medium and program product to solve the problem in related technologies that converting energy consumption into carbon emissions requires the installation of monitoring equipment, which easily leads to high costs for installing online monitoring and difficulty in achieving coverage and promotion; at the same time, after installing online monitoring equipment, enterprises need continuous operation and maintenance investment, and the operation and maintenance costs are too high and difficult to sustain.

[0006] The first embodiment of the present application provides a carbon emission and electricity-carbon calculation method, comprising the following steps: collecting enterprise historical verification library data and electricity consumption data of multiple enterprises to obtain carbon emission cases of the multiple enterprises; constructing a portrait rule library for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission cases, and establishing an enterprise portrait library based on the portrait rule library; determining the enterprise portrait of the target enterprise according to the attributes of the target enterprise and the enterprise portrait library, and determining the electricity-carbon relationship function of the case to be predicted of the target enterprise through the enterprise portrait, so as to use the electricity-carbon relationship function to predict the carbon emission value of the case to be predicted.

[0007] Optionally, in one embodiment of the present application, the construction of a portrait rule library for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case includes: calculating the minimum support of the original portrait rule for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case; determining the effective portrait rule for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case based on the minimum support; and constructing the portrait rule library based on the effective portrait rule.

[0008] Optionally, in one embodiment of the present application, the construction of a portrait rule base for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case includes: determining the regression function corresponding to the carbon emission case based on the regression curve of electricity and carbon emissions in the carbon emission case; and constructing the portrait rule base based on the carbon emission case and the regression function.

[0009] Optionally, in one embodiment of the present application, determining the electricity-carbon relationship function of the case to be predicted of the target enterprise through the enterprise portrait includes: searching the portrait rule library corresponding to the enterprise portrait to determine at least one matching portrait rule corresponding to the case to be predicted; and determining the electricity-carbon relationship function based on a subset of carbon emission cases corresponding to the at least one matching portrait rule.

[0010] Optionally, in one embodiment of the present application, the electricity-carbon relationship function is determined based on the subset of carbon emission cases corresponding to the at least one matching portrait rule, including: calculating the matching degree between the case to be predicted and multiple carbon emission cases in the subset of carbon emission cases; based on the subset of carbon emission cases, determining the case whose matching degree is less than a matching threshold to obtain the regression function corresponding to the case; based on the at least one matching rule, determining the weight of the regression function corresponding to the case to determine the electricity-carbon relationship function based on the weight of the regression function corresponding to the case.

[0011] The second aspect of the present application provides a carbon emission and electricity-carbon calculation device, including: an acquisition module for collecting enterprise historical verification library data and power consumption data of multiple enterprises to obtain carbon emission cases of the multiple enterprises; a construction module for constructing a portrait rule library for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission cases, and establishing an enterprise portrait library based on the portrait rule library; a prediction module for determining the enterprise portrait of the target enterprise according to the attributes of the target enterprise and the enterprise portrait library, and determining the electricity-carbon relationship function of the case to be predicted of the target enterprise through the enterprise portrait, so as to use the electricity-carbon relationship function to predict the carbon emission value of the case to be predicted.

[0012] Optionally, in one embodiment of the present application, the construction module includes: a calculation unit for calculating the minimum support of the original portrait rule for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case; a first determination unit for determining the effective portrait rule for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case based on the minimum support; and a first construction unit for constructing the portrait rule library based on the effective portrait rule.

[0013] Optionally, in one embodiment of the present application, the construction module includes: a second determination unit, used to determine the regression function corresponding to the carbon emission case based on the regression curve of electricity and carbon emissions in the carbon emission case; and a second construction unit, used to construct the portrait rule base based on the carbon emission case and the regression function.

[0014] Optionally, in one embodiment of the present application, the prediction module includes: a round-robin unit for round-robin searching the portrait rule library corresponding to the enterprise portrait to determine at least one matching portrait rule corresponding to the case to be predicted; and a third determination unit for determining the electricity-carbon relationship function based on a subset of carbon emission cases corresponding to the at least one matching portrait rule.

[0015] Optionally, in one embodiment of the present application, the third determination unit includes: a calculation subunit, used to calculate the matching degree between the case to be predicted and multiple carbon emission cases in the carbon emission case subset; a first determination subunit, used to determine the case whose matching degree is less than the matching threshold based on the carbon emission case subset, so as to obtain the regression function corresponding to the case; and a second determination subunit, used to determine the weight of the regression function corresponding to the case based on the at least one matching rule, so as to determine the electricity-carbon relationship function based on the weight of the regression function corresponding to the case.

[0016] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the carbon emission and electricity carbon estimation method as described in the above embodiment.

[0017] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above carbon emission and electricity carbon estimation method.

[0018] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above carbon emission and electricity carbon estimation method.

[0019] The embodiment of the present application can generate a portrait rule library and a corporate portrait library based on the corporate data of multiple enterprises, which can reflect the mapping relationship between electricity and carbon emissions in the carbon emission cases of the enterprises. Finally, the corresponding corporate portrait is constructed through the corporate data of the target enterprise. Then, based on the corporate portrait and the corporate portrait library, when the target enterprise only provides the case to be predicted, the corresponding carbon emissions are predicted by the electricity consumption of the enterprise in the case to be predicted. Thus, it is realized that the characteristics of the enterprise electricity data that are easy to collect and feedback in real time are realized. Based on the historical electricity consumption and carbon emission data of key enterprises in the industry, these enterprises are subjected to corporate portrait and electricity-carbon correlation analysis, thereby establishing a portrait rule for enterprise electricity consumption and carbon emissions, and realizing the calculation of the real-time carbon emission data of the enterprise based on the real-time electricity consumption data of the enterprise. The implementation process is simple, does not rely on additional equipment, effectively saves manpower and material costs, and has a strong landing application capability, which is easy to promote. Thus, it solves the problem that the conversion of energy consumption into carbon emissions in the related technology requires the installation of monitoring equipment, which is easy to cause the high cost of installing online monitoring and is difficult to achieve coverage promotion; at the same time, after installing the online monitoring equipment, the enterprise needs to continue to invest in operation and maintenance, and the operation and maintenance costs are too high, which is difficult to sustain.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 This is a flow chart of a carbon emission and electricity carbon calculation method provided according to an embodiment of the present application;

[0023] Figure 2 This is a schematic diagram of the framework of an electric carbon sensing algorithm and system for an office, scientific research enterprise, according to one embodiment of the present application;

[0024] Figure 3 This is a structural diagram of a carbon emission and electric carbon calculation device provided according to an embodiment of the present application;

[0025] Figure 4 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application.

[0026] Reference numerals:

[0027] 10-Carbon emission electric carbon measurement device: 100-acquisition module, 200-construction module and 300-prediction module; 401-memory, 402-processor and 403-communication interface. DETAILED DESCRIPTION

[0028] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0029] The following describes the carbon emission electricity carbon calculation method, device, electronic device, medium and program product of the embodiment of the present application with reference to the accompanying drawings. In view of the fact that the related technologies mentioned in the above background technology need to install monitoring equipment to convert energy consumption into carbon emissions, which easily leads to the result that it is difficult to achieve coverage and promotion due to the high cost of installing online monitoring; at the same time, after installing online monitoring equipment, enterprises need to make continuous operation and maintenance investments, and the operation and maintenance costs are too high and difficult to sustain, the present application provides a carbon emission electricity carbon calculation method, in which a portrait rule library and an enterprise portrait library that can reflect the mapping relationship between electricity and carbon emissions in the carbon emission cases of enterprises can be generated based on the enterprise data of multiple enterprises, and finally a corresponding enterprise portrait is constructed through the enterprise data of the target enterprise, and then based on the enterprise portrait and the enterprise portrait library, when the target enterprise only provides the case to be predicted, the corresponding carbon emissions are predicted by the electricity consumption of the enterprise in the case to be predicted. As a result, it is possible to utilize the characteristics of enterprise electricity data that are easy to collect and feedback in real time. Based on the historical electricity consumption and carbon emission data of key enterprises in the industry, these enterprises are profiled and the electricity-carbon correlation analysis is performed on these enterprises, thereby establishing a profiling rule for enterprise electricity consumption and carbon emissions, and calculating the real-time carbon emission data of the enterprise based on its real-time electricity consumption data. The implementation process is simple and does not rely on additional equipment. It effectively saves manpower and material costs while having strong practical application capabilities, making it easy to promote. This solves the problem that in related technologies, the conversion of energy consumption into carbon emissions requires the installation of monitoring equipment, which easily leads to the difficulty of achieving coverage and promotion due to the high cost of installing online monitoring; at the same time, after installing online monitoring equipment, the enterprise needs to continue to invest in operation and maintenance, and the operation and maintenance costs are too high, making it difficult to sustain.

[0030] Specifically, Figure 1 This is a flow chart of a carbon emission and electricity carbon calculation method provided in an embodiment of the present application.

[0031] like Figure 1 As shown, the carbon emission electricity carbon calculation method includes the following steps:

[0032] In step S101 , enterprise historical verification database data and power consumption data of multiple enterprises are collected to obtain carbon emission cases of the multiple enterprises.

[0033] It is understandable that for enterprises, electricity data has significant characteristics such as high timeliness, wide coverage, and strong objectivity, and is the most frequently available data for their carbon emissions statistical accounting. Based on this, the embodiments of this application can take advantage of the fact that enterprise electricity data is easy to collect and feedback in real time to analyze the relationship between the historical electricity consumption and carbon emissions data of all key enterprises in the industry, and calculate their real-time carbon emissions data based on their real-time electricity consumption data.

[0034] In some embodiments, the present application may collect enterprise historical verification database data and power consumption data of multiple enterprises to obtain carbon emission cases of the multiple enterprises.

[0035] Among them, the enterprise historical verification database data here includes but is not limited to relevant data that can identify enterprise information reported by the enterprise (enterprise identification data), such as enterprise number, enterprise name, enterprise industry affiliation, taxpayer identification number, etc.; and relevant data that can identify enterprise attributes (enterprise attribute data), such as enterprise scale, enterprise main products, enterprise annual sales, etc.

[0036] Electricity consumption data includes but is not limited to the company's annual electricity consumption value, the company's current electricity consumption value, the company's annual carbon emissions value and the company's current carbon emissions value.

[0037] Figure 2 This is a schematic diagram of the framework of the electric carbon sensing algorithm and system for office, scientific research and enterprise according to one embodiment of the present application. Figure 2 As shown, after obtaining the enterprise historical verification database data and power consumption data, to ensure data validity, embodiments of the present application may, but are not limited to, normalize the data according to the data rules of the case database and perform data cleansing to remove outliers, supplement missing values, and obtain data in a standard format. The cleaned data may then be divided into multiple carbon emission cases based on, but not limited to, transaction details, customs declaration details, and case units, and stored in the case database.

[0038] Among them, in order to ensure the accuracy of calculations in subsequent processes, the current electricity consumption value of the enterprise should be set to empty in the part of the case library used to store the processed enterprise historical verification library data; the current carbon emission value of the enterprise should be set to empty in the part used to store electricity consumption data.

[0039] The embodiment of the present application can utilize the historical verification database data and electricity consumption data of multiple enterprises to obtain carbon emission cases of multiple enterprises. In this way, it effectively recycles the characteristics of electricity data, which has significant characteristics such as high timeliness, wide coverage, and strong objectivity, and is the highest frequency data that can be obtained in carbon emission statistical accounting, providing strong data support for the carbon emission forecast of enterprises.

[0040] Step S102: construct a portrait rule library for reflecting the mapping relationship between electricity and carbon emissions in carbon emission cases, and establish an enterprise portrait library based on the portrait rule library.

[0041] In other embodiments, in order to facilitate the calculation of electricity carbon for different scenarios and different enterprises, such as Figure 2 As shown, the present application can construct a portrait rule library based on the data information stored in the case library to reflect the mapping relationship between electricity and carbon emissions in carbon emission cases, and establish an enterprise portrait library based on the portrait rule library.

[0042] The profile rule library and the enterprise profile library can both be stored in the rule library. Furthermore, the case library and rule library in the embodiment of the present application are regularly updated. Cases in the case library maintain their validity for a certain period of time. Expired cases or non-local cases are regularly cleared, and specific profile rules are regenerated based on the cleared cases. The rule library is then updated based on a comparison with the original profile rules.

[0043] For example, the embodiment of the present application generates certain cases based on enterprise verification data and power consumption data, for example, the production of 1 ton of chemicals on X-month-X-year consumes 5000kWh and generates carbon emissions of 3 tons of CO2, etc.

[0044] Then, this application can, but is not limited to, use the Apriori method to generate a portrait rule based on the case to reflect the mapping relationship between electricity and carbon emissions in the carbon emission case. Among them, the portrait rule here can be understood as a logical rule extracted from historical verification data and power consumption data for generating portrait labels, usually in the form of "condition → label". For example, a portrait rule is: If the average power consumption of an enterprise exceeds X in a certain period of time, and the production link is A, then the carbon emission intensity in that period exceeds Y.

[0045] In this way, the embodiment of the present application can convert the enterprise verification data and power consumption data of the enterprise into understandable and actionable portrait rules. By collecting the portrait rules of each enterprise, a portrait rule library can be established.

[0046] Furthermore, based on these portrait rules, the embodiment of the present application can also apply the generated portrait rules to the enterprise's electricity consumption and carbon emission data, and combine the enterprise's industry affiliation, main products and other data in the enterprise's historical verification library data to label the enterprise accordingly, such as "high-power consumption and high-carbon emission enterprises in sea transportation", "low-power consumption and low-carbon emission enterprises in land transportation", etc., to achieve a multi-faceted portrait of the enterprise, which is convenient for later identification of corresponding portrait rules and cases based on the enterprise's corporate portrait.

[0047] By aggregating and storing all corporate portraits, we can generate a corporate portrait library, which will help to obtain more effective carbon emission predictions based on the corporate portraits of the companies to be tested in later practical applications. It will also enable the companies to be tested to compare more accurately with various types of companies and improve the diverse regression of their electricity-carbon perception.

[0048] Optionally, in one embodiment of the present application, a portrait rule library is constructed to reflect the mapping relationship between electricity and carbon emissions in carbon emission cases, including: calculating the minimum support of the original portrait rule for reflecting the mapping relationship between electricity and carbon emissions in carbon emission cases; determining the effective portrait rule for reflecting the mapping relationship between electricity and carbon emissions in carbon emission cases based on the minimum support; and constructing a portrait rule library based on the effective portrait rule.

[0049] In certain embodiments, when constructing a portrait rule base for reflecting the mapping relationship between electricity and carbon emissions in carbon emission cases, in order to ensure the validity of the portrait rules in the portrait rule base, the present application can calculate the minimum support of each original portrait rule, thereby selecting effective portrait rules that meet a certain minimum support from the original portrait rules, and then using these effective portrait rules to construct a portrait rule base.

[0050] Among them, the original portrait rule here can be understood as the portrait rule that is directly constructed without screening based on the carbon emission case. The minimum support here refers to an important parameter used in the Apriori algorithm to screen frequent item sets. In the embodiment of the present application, the setting of the minimum support is to ensure that only those data patterns with a sufficiently high frequency will be selected as the basis of association rules (portrait rules). This can avoid incorporating low-frequency and unrepresentative data patterns into the analysis, thereby improving the accuracy and practicality of the portrait rules in the portrait rule library.

[0051] Among them, the calculation rules of the minimum support can be flexibly adjusted by professional and technical personnel in this technical field according to the actual application scenario and data characteristics. For example, when the present application adopts the Apriori method to generate the portrait rules, it can be, but not limited to, using the median of the number of enterprises corresponding to all attributes divided by the number of enterprises in the current industry as the minimum support calculation principle in the embodiment of the present application. The embodiments of the present application are only for illustrative purposes and are not specifically limited.

[0052] The embodiments of the present application can effectively reduce unnecessary calculations by reasonably setting the minimum support, while effectively ensuring that the extracted portrait rules used to reflect the mapping relationship between electricity and carbon emissions in carbon emission cases have high reliability and universal applicability, and help identify the key factors that have the greatest impact on the company's electricity-carbon perception, thereby guiding the formulation of more accurate energy-saving and emission reduction strategies.

[0053] Optionally, in one embodiment of the present application, a portrait rule library is constructed to reflect the mapping relationship between electricity and carbon emissions in carbon emission cases, including: determining the regression function corresponding to the carbon emission case based on the regression curve of electricity and carbon emissions in the carbon emission case; and constructing a portrait rule library based on the carbon emission case and the regression function.

[0054] During the actual implementation process, the carbon emissions corresponding to electricity consumption in different situations are different. In order to accurately predict the carbon emissions corresponding to electricity consumption in different situations, the present application can, but is not limited to, draw a corresponding regression curve based on the different electricity consumption and corresponding carbon emissions in each case, and then determine the regression function corresponding to each case based on the regression curve. On the basis of the portrait rules, the carbon emission relationship corresponding to electricity consumption in different situations is accurately expressed through the regression function, and then each case and its corresponding regression function are saved together in the rule base.

[0055] Given that different cases may correspond to the same portrait rule, the embodiment of the present application can construct a case subset based on each portrait rule in the portrait rule library, and each case in the case subset corresponds to a regression function.

[0056] Specifically, the process of constructing a profile rule base and an enterprise rule base from the enterprise historical verification database data and power consumption data can be represented as follows, but is not limited to:

[0057] (1) The enterprise historical verification database data is based on the classification of enterprises by industry, and the attribute sets of the managed enterprises are collected to form the enterprise attribute database Among them, d1, d2, ..., d s is the attribute value, d t is the target value, i.e. carbon dioxide emissions, d s =(h1,h2,h3,……,h i ), h i For attribute d s The corresponding values ​​are as follows: B is the enterprise serial number, n is the serial number corresponding to enterprise B, and the enterprise cases in the current enterprise attribute library are the existing enterprise historical production and corresponding carbon emission verification data;

[0058] (2) Determine the minimum support in the process of generating the portrait rule. In the embodiment of the present application, the minimum support can be, but is not limited to, expressed as follows:

[0059]

[0060] Where mld(T(x)) represents D Bn The median number of companies corresponding to all attributes, N is the number of companies in the current industry;

[0061] (3) Determine the current confidence and Len parameter values ​​as needed; where confidence and Len are the core parameters in the Apriori method, an itemset is a set of items in a data set, and Len is the number of sets; confidence is a reliability parameter for measuring association rules (such as the profiling rule generated based on the mapping relationship between electricity and carbon emissions in the carbon emission case), and the formula can be, but is not limited to, expressed as:

[0062]

[0063] This formula represents the probability that a transaction containing X also contains Y.

[0064] (4) Execute the Apriori method to generate the portrait rules and the portrait rule base, where the target attribute d t The following points should be noted during the calculation process: First, the data in the enterprise database should be divided by industry, and the attribute sets of enterprises in each industry do not need to be consistent. Second, the algorithm cannot identify the numerical meaning of the current attribute, so each numerical data needs to be quantified. The specific quantile method is generally to use the upper and lower deciles and the middle range quantile.

[0065] (5) Based on the portrait rule library generated in step (4), an enterprise portrait system is established, the number of enterprise cases under each portrait rule is searched, and the carbon emissions corresponding to different electricity consumption in each case are used as the objective function value. The regression curve of different electricity consumption and corresponding carbon emissions is drawn, and then the regression function f corresponding to each case is determined based on the regression curve. (x) Including but not limited to: linear regression f 1(x) , polynomial regression f 2(x) , exponential regression f 3(x) , logarithmic regression f 4(x) , hyperbolic regression f 5(x) , exponential reciprocal regression f 6(x) ; In which, when determining the regression function of each case, the weight coefficient ω can be used, but is not limited to, to measure the importance of different regression formulas, and then the final regression function is determined based on the importance.

[0066] The weight coefficient ω can be but is not limited to the performance evaluation index based on the regression model (such as mean square error MSE, R 2 Assume that a case can be represented by multiple regression functions M1, M2, ..., Mn. For each regression function, its performance score S on the training set can be calculated first. i , and then assign weights according to the scores. The formula can be, but is not limited to, expressed as follows:

[0067]

[0068] This ensures that each case can get a better regression function with a greater weight in the final prediction, thus improving the overall prediction accuracy;

[0069] (6) Based on the results of step (5), case subsets under different profiling rules are established, including but not limited to the number of cases n corresponding to the profiling rule, and the regression function f corresponding to each case in the case subset. (x) , the loss value corresponding to the regression function is recorded as L;

[0070] (7) Delete all monotonically decreasing functions, and for each case subset under each profiling rule, only retain the t regression functions and cases with the smallest loss values.

[0071] The embodiment of the present application can explore the most suitable electric-carbon perception regression method for an enterprise through a variety of nonlinear regression fitting methods and regression combined with multiple regression curves, thereby ensuring the correspondence and accuracy of carbon emission cases and regression functions, and further ensuring the accuracy of the enterprise's electric-carbon perception, and also providing a data basis for the differences in electric-carbon coefficients of different enterprises.

[0072] Step S103: determine the corporate profile of the target enterprise based on the attributes of the target enterprise and the corporate profile library, and determine the electricity-carbon relationship function of the case to be predicted of the target enterprise through the corporate profile, so as to use the electricity-carbon relationship function to predict the carbon emission value of the case to be predicted.

[0073] As a possible implementation method, after constructing the portrait rule library and the enterprise portrait library, the embodiment of the present application can use the portrait rule library and the enterprise portrait library to predict the carbon emissions corresponding to a case to be predicted of the target enterprise.

[0074] The target enterprise here can be understood as a related enterprise with a certain correlation between electricity consumption and carbon emissions. The case to be predicted here can be understood as an enterprise case that needs to estimate carbon emissions through electricity consumption. The difference between the case to be predicted and the case in the enterprise case library is only d t The carbon emission value is unknown.

[0075] Specifically, the embodiment of the present application can first determine the industry attributes of the target enterprise based on the target enterprise's corporate history verification database, and then match the most appropriate corporate portrait of the target enterprise in the corporate portrait library based on the target enterprise's industry attributes and corporate history verification database data.

[0076] After determining the corporate portrait of the target enterprise, the embodiment of the present application can determine the electricity-carbon relationship function of the target enterprise's case to be predicted based on the corporate portrait corresponding to the target enterprise, and then use the electricity-carbon relationship function to calculate the carbon emission value corresponding to the electricity consumption in the case to be predicted.

[0077] The embodiment of the present application can identify the corporate portrait of the target enterprise based on the existing data information of the target enterprise, and then based on the corporate portrait, when the target enterprise only provides cases to be predicted, the corresponding carbon emissions can be predicted by the power consumption of the enterprise in the cases to be predicted, without relying on other energy consumption in the region for calculation, saving manpower and material resources while making the operation more convenient and easy to implement.

[0078] Optionally, in one embodiment of the present application, the electricity-carbon relationship function of the case to be predicted of the target enterprise is determined through the enterprise portrait, including: searching the portrait rule library corresponding to the enterprise portrait to determine at least one matching portrait rule corresponding to the case to be predicted; and determining the electricity-carbon relationship function based on a subset of carbon emission cases corresponding to at least one matching portrait rule.

[0079] In certain embodiments, the electricity-carbon relationship function process of the target enterprise's case to be predicted is determined through the enterprise portrait. The present application can perform reverse thinking based on the process of constructing the enterprise portrait, that is, the present application can match the portrait rule library under the enterprise portrait according to the enterprise portrait of the target enterprise, so as to determine at least one matching portrait rule corresponding to the case to be predicted based on the case to be predicted of the target enterprise by searching the portrait rule library under the enterprise portrait.

[0080] Among them, when searching the portrait rule base under the enterprise portrait, the embodiment of the present application can, but is not limited to, adopt algorithms such as depth-first search (DFS), breadth-first search (BFS), or heuristic search algorithms. In addition, during the search process of the embodiment of the present application, based on the characteristics of the rule base, optimization strategies such as greedy algorithm or simulated annealing algorithm can be added to the Apriori algorithm, so that the best matching portrait rule for the case to be predicted can be quickly located from the portrait rule base corresponding to the enterprise portrait, and the search path can be dynamically adjusted to adapt to the continuously updated rule base.

[0081] Furthermore, the embodiment of the present application can determine the electricity-carbon relationship function applicable to the case to be predicted from the subset of carbon emission cases under the matching portrait rule, and then use the electricity-carbon relationship function to calculate the carbon emissions corresponding to the electricity consumption in the case to be predicted.

[0082] Optionally, in one embodiment of the present application, the electricity-carbon relationship function is determined based on a subset of carbon emission cases corresponding to at least one matching portrait rule, including: calculating the matching degree between the case to be predicted and multiple carbon emission cases in the carbon emission case subset; based on the carbon emission case subset, determining the case with a matching degree less than a matching threshold to obtain the regression function corresponding to the case; based on at least one matching rule, determining the weight of the regression function corresponding to the case, to determine the electricity-carbon relationship function based on the weight of the regression function.

[0083] Based on the relevant descriptions of other embodiments, it can be understood that the carbon emission case subset under each portrait rule includes the number of cases and the regression function corresponding to different carbon emission cases. The regression function can accurately represent the relationship between electricity consumption and carbon emissions in the carbon emission cases.

[0084] During actual implementation, this application can use the regression function of existing carbon emission cases to determine the electricity-carbon relationship function of the case to be predicted, so as to calculate the carbon emissions corresponding to the electricity consumption in the case to be predicted.

[0085] Given that the corresponding matching portrait rules are determined based on the cases to be predicted of the target enterprise, and the carbon emission case subset under each portrait rule contains the number of cases and regression functions corresponding to different carbon emission cases, the embodiment of the present application can first determine the existing carbon emission case that is most similar to the case to be predicted.

[0086] In the process of determining the existing carbon emission case that is most similar to the case to be predicted, the embodiment of the present application can first calculate the matching degree between the case to be predicted and multiple carbon emission cases in the carbon emission case subset under the matching portrait rule, and then determine the most similar existing carbon emission case among the existing cases whose matching degree meets the matching threshold.

[0087] The matching degree reflects the degree of similarity between the case to be predicted and the cases in the existing case library. In the embodiments of the present application, the matching degree can be calculated based on, but not limited to, data comparisons across multiple dimensions, including but not limited to the industry type, scale, and energy consumption level of the enterprise. For example, the embodiments of the present application can quantify the matching degree by calculating, but not limited to, the Euclidean distance or cosine similarity between two cases.

[0088] The matching threshold here can be understood as a preset matching standard, and the matching results below this matching standard will be deemed invalid. For example, cases in the subset of carbon emission cases with a matching degree lower than 85% are deemed invalid. It should be noted that the specific matching threshold can be determined by professional and technical personnel in this technical field based on the empirical value of historical data or through cross-validation methods. For example, a threshold that can optimize the model performance (such as the highest classification accuracy) can be selected as the final matching threshold. The embodiments of this application are only for illustrative purposes and are not specifically limited.

[0089] For example, the case to be predicted P1 is searched in the matching profile rule library, and the following format vector can be obtained, but is not limited to:

[0090] Rn(Rule&conclusion,s,m,f 1(x) ,ω 1m ,L1,f 2(x) ,ω 2m ,L2,…,f t(x) ,ω tm ,L t ),

[0091] Among them, m represents the rule number corresponding to the case to be predicted, Rule&conclusion is the portrait rule body, L is the loss value corresponding to the regression function, s is the matching degree, ω tm For the current rule in f t(x) The corresponding weights can be calculated as follows, but are not limited to:

[0092]

[0093] Where h is the correction parameter of L.

[0094] In addition to the basic matching degree, professional and technical personnel in this technical field can also consider introducing dynamic variables such as time series analysis and seasonal factors based on actual application scenarios, as well as the impact of changes in the external environment (such as policy adjustments and market fluctuations), and integrate these factors into the matching degree calculation formula through weighted average or other statistical methods.

[0095] Then the electricity-carbon relationship function of the case to be predicted can be expressed as, but not limited to:

[0096]

[0097] Among them, F (x) It represents the estimated electric carbon value of the case to be predicted, that is, the carbon emission value corresponding to the electricity consumption in the case to be predicted; M represents the number of rules corresponding to the case to be predicted, and T is the maximum value of t.

[0098] The embodiment of the present application can identify the corporate portrait of the target enterprise from multiple classification options based on the historical verification library data of the target enterprise, and then realize the regression fitting of the case to be predicted with the existing carbon emission cases and regression functions on this basis, and give the case to be predicted the option of loading and selecting the most appropriate electricity-carbon relationship function, so as to realize the confirmation of the electricity-carbon relationship and the estimation of the carbon emission amount of the enterprise based on the corporate portrait and historical data regression of the case to be predicted.

[0099] According to the carbon emission and electricity carbon calculation method proposed in the embodiment of the present application, a portrait rule library and a corporate portrait library that can reflect the mapping relationship between electricity and carbon emissions in the carbon emission cases of the enterprises can be generated based on the corporate data of multiple enterprises. Finally, the corresponding corporate portrait is constructed through the corporate data of the target enterprise. Then, based on the corporate portrait and the corporate portrait library, when the target enterprise only provides the case to be predicted, the corresponding carbon emissions are predicted by the electricity consumption of the enterprise in the case to be predicted. Thus, it is realized that the characteristics of the enterprise electricity data that are easy to collect and feedback in real time are realized. Based on the historical electricity consumption and carbon emission data of key enterprises in the industry, these enterprises are subjected to corporate portrait and electricity-carbon correlation analysis, thereby establishing a portrait rule for the enterprise electricity consumption and carbon emissions, and realizing the calculation of the real-time carbon emission data of the enterprise based on the real-time electricity consumption data of the enterprise. The implementation process is simple, does not rely on additional equipment, effectively saves manpower and material costs, and has a strong landing application capability, which is easy to promote. Thus, it solves the problem that the conversion of energy consumption into carbon emissions in the related technology requires the installation of monitoring equipment, which easily leads to the high cost of installing online monitoring and is difficult to achieve coverage and promotion; at the same time, after installing the online monitoring equipment, the enterprise needs to continue to invest in operation and maintenance, and the operation and maintenance costs are too high and difficult to sustain.

[0100] Next, the carbon emission and electricity carbon estimation device proposed in accordance with the embodiment of the present application will be described with reference to the accompanying drawings.

[0101] Figure 3 It is a structural schematic diagram of the carbon emission and electric carbon calculation device in an embodiment of the present application.

[0102] like Figure 3 As shown, the carbon emission electricity carbon estimation device 10 includes: a collection module 100, a construction module 200 and a prediction module 300.

[0103] The collection module 100 is used to collect enterprise historical verification database data and power consumption data of multiple enterprises to obtain carbon emission cases of the multiple enterprises.

[0104] Construction module 200 is used to construct a portrait rule library for reflecting the mapping relationship between electricity and carbon emissions in carbon emission cases, and to establish an enterprise portrait library based on the portrait rule library.

[0105] The prediction module 300 is used to determine the corporate portrait of the target enterprise based on the attributes of the target enterprise and the corporate portrait library, and determine the electricity-carbon relationship function of the case to be predicted of the target enterprise through the corporate portrait, so as to use the electricity-carbon relationship function to predict the carbon emission value of the case to be predicted.

[0106] Optionally, in one embodiment of the present application, the construction module 200 includes: a calculation unit, a first determination unit and a first construction unit.

[0107] The calculation unit is used to calculate the minimum support of the original portrait rule used to reflect the mapping relationship between electricity and carbon emissions in the carbon emission case.

[0108] The first determination unit is used to determine, according to the minimum support, an effective portrait rule for reflecting the mapping relationship between electricity and carbon emissions in a carbon emission case.

[0109] The first construction unit is used to construct a portrait rule library based on effective portrait rules.

[0110] Optionally, in one embodiment of the present application, the construction module 200 includes: a second determining unit and a second construction unit.

[0111] The second determining unit is configured to determine a regression function corresponding to the carbon emission case based on a regression curve of electricity and carbon emissions in the carbon emission case;

[0112] The second construction unit is used to build a portrait rule library based on carbon emission cases and regression functions.

[0113] Optionally, in one embodiment of the present application, the prediction module 300 includes: a round-robin unit and a third determination unit.

[0114] Among them, the round-robin unit is used to round-robin the portrait rule library corresponding to the enterprise portrait to determine at least one matching portrait rule corresponding to the case to be predicted.

[0115] The third determination unit is used to determine the electricity-carbon relationship function based on a subset of carbon emission cases corresponding to at least one matching portrait rule.

[0116] Optionally, in one embodiment of the present application, the third determining unit includes: a calculating subunit, a first determining subunit and a second determining subunit.

[0117] Among them, the calculation subunit is used to calculate the matching degree between the case to be predicted and multiple carbon emission cases in the carbon emission case subset.

[0118] The first determining subunit is configured to determine, based on the carbon emission case subset, cases whose matching degree is less than a matching threshold, so as to obtain a regression function corresponding to the case.

[0119] The second determining subunit is configured to determine a weight of a regression function corresponding to the case based on at least one matching rule, so as to determine an electricity-carbon relationship function based on the weight of the regression function.

[0120] It should be noted that the above explanation of the embodiment of the carbon emission and electricity-to-carbon calculation method is also applicable to the carbon emission and electricity-to-carbon calculation device of this embodiment, and will not be repeated here.

[0121] According to the carbon emission and electricity-carbon calculation device proposed in the embodiment of the present application, a portrait rule library and a corporate portrait library can be generated based on the corporate data of multiple enterprises, which can reflect the mapping relationship between electricity and carbon emissions in the carbon emission cases of the enterprises. Finally, the corresponding corporate portrait is constructed through the corporate data of the target enterprise. Then, based on the corporate portrait and the corporate portrait library, when the target enterprise only provides the case to be predicted, the corresponding carbon emissions are predicted by the electricity consumption of the enterprise in the case to be predicted. Thus, it is realized that the characteristics of easy real-time collection and feedback of corporate electricity data are realized. Based on the historical electricity consumption and carbon emission data of key enterprises in the industry, these enterprises are subjected to corporate portrait and electricity-carbon correlation analysis, thereby establishing portrait rules for corporate electricity consumption and carbon emissions, and realizing the calculation of real-time carbon emission data based on the real-time electricity consumption data of the enterprise. The implementation process is simple, does not rely on additional equipment, effectively saves manpower and material costs, and has strong landing application capabilities, which is easy to promote. Thus, it solves the problem that the conversion of energy consumption into carbon emissions in the related technology requires the installation of monitoring equipment, which is easy to cause the high cost of installing online monitoring and is difficult to achieve coverage and promotion; at the same time, after installing the online monitoring equipment, the enterprise needs to continue to invest in operation and maintenance, and the operation and maintenance costs are too high, making it difficult to sustain.

[0122] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0123] Memory 401 , processor 402 , and computer programs stored in the memory 401 and executable on the processor 402 .

[0124] When the processor 402 executes the program, the carbon emission and electricity carbon estimation method provided in the above embodiment is implemented.

[0125] Furthermore, the electronic device further includes:

[0126] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0127] The memory 401 is used to store computer programs that can be run on the processor 402 .

[0128] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0129] If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0130] Optionally, in a specific implementation, if the memory 401 , the processor 402 and the communication interface 403 are integrated on a chip, the memory 401 , the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0131] The processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0132] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned carbon emission and electricity carbon estimation method.

[0133] An embodiment of the present application also provides a computer program product, including a computer program, which can run computer instructions. When the computer instructions are executed by a processor, the carbon emission and electricity carbon calculation method provided in the embodiment of the present application is implemented.

[0134] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0135] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0136] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0137] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0138] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0139] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0140] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0141] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for calculating carbon emissions, characterized in that: The following steps are involved: Collecting enterprise historical verification database data and power consumption data of multiple enterprises to obtain carbon emission cases of the multiple enterprises; Constructing a profile rule library for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case, and establishing an enterprise profile library based on the profile rule library; The corporate portrait of the target enterprise is determined based on the attributes of the target enterprise and the corporate portrait library, and the electricity-carbon relationship function of the case to be predicted of the target enterprise is determined through the corporate portrait, so as to use the electricity-carbon relationship function to predict the carbon emission value of the case to be predicted.

2. The method according to claim 1, characterized in that The construction of a profile rule library for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case includes: Calculating the minimum support of the original portrait rule for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case; Determining, based on the minimum support, an effective profiling rule for reflecting a mapping relationship between electricity and carbon emissions in the carbon emission case; The portrait rule library is constructed according to the effective portrait rules.

3. The method according to claim 1, characterized in that The construction of a profile rule library for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case includes: Determining a regression function corresponding to the carbon emission case based on a regression curve of electricity and carbon emissions in the carbon emission case; Based on the carbon emission cases and the regression function, the portrait rule library is constructed.

4. The method according to claim 1, wherein The step of determining the electricity-carbon relationship function of the target enterprise's case to be predicted through the enterprise portrait includes: Searching the portrait rule library corresponding to the enterprise portrait to determine at least one matching portrait rule corresponding to the case to be predicted; The electricity-carbon relationship function is determined based on a subset of carbon emission cases corresponding to the at least one matching profile rule.

5. The method according to claim 4, characterized in that The determining the electricity-carbon relationship function based on the subset of carbon emission cases corresponding to the at least one matching profile rule includes: Calculating a matching degree between the case to be predicted and a plurality of carbon emission cases in the carbon emission case subset; Based on the carbon emission case subset, determining the cases whose matching degree is less than a matching threshold, so as to obtain a regression function corresponding to the cases; Based on the at least one matching rule, a weight of the regression function corresponding to the case is determined, so as to determine the electricity-carbon relationship function based on the weight of the regression function corresponding to the case.

6. A carbon emission and electric carbon calculation device, characterized in that: include: A collection module, configured to collect enterprise historical verification database data and power consumption data of multiple enterprises to obtain carbon emission cases of the multiple enterprises; A construction module is used to construct a portrait rule library for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case, and to establish an enterprise portrait library based on the portrait rule library; A prediction module is used to determine the corporate portrait of the target enterprise based on the attributes of the target enterprise and the corporate portrait library, and to determine the electricity-carbon relationship function of the case to be predicted of the target enterprise through the corporate portrait, so as to use the electricity-carbon relationship function to predict the carbon emission value of the case to be predicted.

7. The device according to claim 6, characterized in that The building blocks include: a calculation unit, configured to calculate the minimum support of the original portrait rule for reflecting the mapping relationship between electricity and carbon emissions in the carbon emission case; a determining unit, configured to determine, based on the minimum support, an effective profiling rule for reflecting a mapping relationship between electricity and carbon emissions in the carbon emission case; A construction unit is used to construct the portrait rule library according to the effective portrait rules.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the carbon emission and electricity carbon estimation method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the carbon emission and electric carbon estimation method as described in any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed, it is used to implement the carbon emission and electricity carbon estimation method according to any one of claims 1 to 5.

Images