Carbon emission prediction method, device, equipment and medium based on electric carbon factor

Abstract

The present invention discloses a carbon emission prediction method, device, equipment and medium based on an electric carbon factor. The method obtains the electric carbon factor normal distribution and the factor weight normal distribution for each object to be determined, determines the estimated electric carbon factor according to the electric carbon factor normal distribution, the factor weight normal distribution, the preset factor extraction number and the preset weight extraction number, and then determines the target electric carbon factor of the target object according to the reference electric carbon factor and each estimated electric carbon factor, thereby achieving accurate determination of the electric carbon factor, and further determines the expected carbon emissions of the target object according to the determined target electric carbon factor, thereby achieving accurate determination of carbon emissions, solving the problems of low accuracy, low efficiency and high cost of manual analysis of carbon emissions in the prior art, and avoiding the influence of extreme values ​​on the estimated electric carbon factor by presetting the factor extraction number and the preset weight extraction number, thereby improving the accuracy of the electric carbon factor.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission technology, and in particular to a method, device, equipment and medium for predicting carbon emissions based on an electric carbon factor. Background Art

[0002] With economic growth and social progress, people are increasingly concerned about the harmonious development of humanity and nature, and the need for the coexistence of environmental protection and sustainable development has reached a new level. Today, every aspect of business production involves energy consumption and the resulting carbon emissions. Studies have shown that carbon-related gases such as carbon dioxide have a significant impact on the global climate, contributing to numerous global risks such as extreme weather events and rising sea levels. Addressing carbon-related climate issues requires significant human and material resources.

[0003] To most effectively address energy issues, carbon emissions must be reduced, maximizing the neutralization of carbon emissions from consumption. Therefore, it's necessary to analyze carbon emissions across industries and businesses to develop carbon reduction plans for each. Existing technologies typically require manual analysis of carbon emissions across industries and businesses. However, this manual analysis method fails to accurately determine carbon emissions, is inefficient, and incurs high costs in terms of manpower and resources.

[0004] In the process of implementing the present invention, it was found that the prior art has at least the following technical problems: low accuracy of the analyzed carbon emissions, low analysis efficiency, and high analysis cost. Summary of the Invention

[0005] The present invention provides a carbon emission prediction method, device, equipment and medium based on the electric carbon factor to solve the problems of low accuracy, low efficiency and high cost in the prior art of manual analysis of carbon emissions.

[0006] According to one aspect of the present invention, a method for predicting carbon emissions based on an electric carbon factor is provided, comprising:

[0007] For each object to be determined, obtaining the normal distribution of the electric-carbon factor and the normal distribution of the factor weights of the object to be determined, and determining the estimated electric-carbon factor of the object to be determined based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weights, the preset number of factor extractions, and the preset number of weight extractions;

[0008] Obtaining reference carbon factors corresponding to at least two reference objects respectively, and determining a target carbon factor corresponding to each target object in the to-be-determined objects based on each of the reference carbon factors and each of the estimated carbon factors;

[0009] Based on the target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object, the expected carbon emissions corresponding to the target object are determined.

[0010] Optionally, the method further includes:

[0011] For each of the objects to be determined, determining a first sub-object and a second sub-object corresponding to the object to be determined;

[0012] Obtaining the electric carbon factor weights corresponding to each of the first sub-objects, and the sub-electric carbon factors corresponding to each of the second sub-objects;

[0013] The factor weight normal distribution of the object to be determined is constructed based on the weight of each of the electric-carbon factors, and the electric-carbon factor normal distribution of the object to be determined is constructed based on each of the sub-electric-carbon factors.

[0014] Optionally, constructing a normal distribution of factor weights of the object to be determined based on the weights of each of the electric-carbon factors, and constructing a normal distribution of the electric-carbon factors of the object to be determined based on each of the sub-electric-carbon factors, includes:

[0015] Based on the weights of the electro-carbon factors, calculating the weight mean and weight variance corresponding to the object to be determined, and constructing a normal distribution of factor weights corresponding to the object to be determined according to the weight mean and weight variance;

[0016] Based on each of the sub-electric-carbon factors, the electric-carbon factor mean and the electric-carbon factor variance corresponding to the object to be determined are calculated, and a normal distribution of the electric-carbon factor corresponding to the object to be determined is constructed according to the electric-carbon factor mean and the electric-carbon factor variance.

[0017] Optionally, determining the estimated electric-carbon factor of the object to be determined based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weight, the preset number of factor extractions, and the preset number of weight extractions includes:

[0018] Determine the initial weight and initial electro-carbon factor;

[0019] Determine at least one current random weight based on the normal distribution of the factor weights and the preset weight extraction quantity, and determine at least one target random weight and the quantity of the target random weights in each current random weight according to each current random weight, the initial weight, and a preset weight threshold;

[0020] Determine each target random factor based on the number of the target random weights, the normal distribution of the electro-carbon factor, and the number of the preset factor extractions, wherein the number of the target random factors is the same as the number of the target random weights;

[0021] Based on each of the target random weights, each of the target random factors and the initial electric-carbon factor, an estimated electric-carbon factor of the object to be determined is determined.

[0022] The determining of at least one current random weight based on the normal distribution of the factor weights and the preset weight extraction quantity includes:

[0023] Determine the preset extraction rounds;

[0024] For each round of extraction in the preset extraction rounds, the preset weight extraction number of weights to be screened are extracted from the factor weight normal distribution, and the current random weight is determined based on each of the weights to be screened.

[0025] The step of extracting the preset number of weights to be screened from the normal distribution of the factor weights, and determining the current random weight based on each of the weights to be screened, includes:

[0026] Determine each preset slave node, and determine a single-round weight extraction quantity for each preset slave node based on the number of the preset slave nodes and the preset weight extraction quantity;

[0027] Extracting the single-round weight extraction quantity of weights to be screened from the factor weight normal distribution through each of the preset slave nodes;

[0028] The current random weight is determined based on the preset weights to be screened extracted from the nodes.

[0029] The determining of each target random factor based on the number of the target random weights, the normal distribution of the electric carbon factor, and the number of the preset factor extractions includes:

[0030] Determine the factor extraction rounds based on the number of the target random weights, and determine the number of single-round factor extractions for each of the preset slave nodes based on the number of the preset slave nodes and the preset number of factor extractions;

[0031] For each round of factor extraction in the factor extraction round, the number of factors to be screened for the single-round factor extraction is extracted from the normal distribution of the electric-carbon factor through each of the preset slave nodes, and the target random factor corresponding to the current round is determined based on the factors to be screened extracted from each of the preset slave nodes.

[0032] According to another aspect of the present invention, there is provided a carbon emission prediction device based on an electric carbon factor, comprising:

[0033] An estimated factor determination module is used to obtain, for each object to be determined, the normal distribution of the electric carbon factor and the normal distribution of the factor weight of the object to be determined, and determine the estimated electric carbon factor of the object to be determined based on the normal distribution of the electric carbon factor, the normal distribution of the factor weight, the preset number of factor extractions, and the preset number of weight extractions;

[0034] a target factor determination module, configured to obtain reference carbon factors corresponding to at least two reference objects, and determine a target carbon factor corresponding to each target object in the objects to be determined based on the reference carbon factors and the estimated carbon factors;

[0035] The carbon emission calculation module is used to determine the expected carbon emissions corresponding to the target object based on the target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object.

[0036] According to another aspect of the present invention, an electronic device is provided, comprising:

[0037] at least one processor; and

[0038] a memory communicatively connected to the at least one processor; wherein,

[0039] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the carbon emission prediction method based on the electric carbon factor described in any embodiment of the present invention.

[0040] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the carbon emission prediction method based on the electric carbon factor described in any embodiment of the present invention when executed.

[0041] The technical solution of the embodiment of the present invention obtains the normal distribution of the electric carbon factor and the normal distribution of the factor weights of each object to be determined, and determines the estimated electric carbon factor of the object to be determined according to the normal distribution of the electric carbon factor, the normal distribution of the factor weights, the preset factor extraction number and the preset weight extraction number, and then determines the target electric carbon factor of the target object according to the reference electric carbon factor of the reference object and each estimated electric carbon factor, thereby achieving accurate determination of the electric carbon factor, and further determines the expected carbon emissions of the target object according to the determined target electric carbon factor and the actual electricity consumption, thereby achieving accurate determination of the carbon emissions without manual analysis, solving the problems of low accuracy, low efficiency and high cost of manual analysis of carbon emissions in the prior art, and, by presetting the factor extraction number and the preset weight extraction number, avoiding the situation of extracting extreme values ​​due to a small number of extractions, ensuring the accuracy of the estimated electric carbon factor, and thus ensuring the accuracy of the electric carbon factor, and realizing carbon emissions prediction for objects with unknown electric carbon factors.

[0042] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 This is a flow chart of a carbon emission prediction method based on an electric carbon factor provided in Example 1 of the present invention;

[0045] Figure 2 This is a flow chart of a carbon emission prediction method based on an electric carbon factor provided in the second embodiment of the present invention;

[0046] Figure 3 This is a flow chart of a carbon emission prediction method based on an electric carbon factor provided in the third embodiment of the present invention;

[0047] Figure 4 This is a structural diagram of a carbon emission prediction device based on an electric carbon factor provided in a fourth embodiment of the present invention;

[0048] Figure 5 This is a structural diagram of an electronic device provided in Example 5 of the present invention. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0050] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0051] Example 1

[0052] Figure 1 This is a flow chart of a carbon emission prediction method based on electric carbon factors provided in the first embodiment of the present invention. This embodiment can be applied to determine the electric carbon factors of other enterprises with unknown electric carbon factors based on enterprises with known electric carbon factors, and then predict the carbon emissions of enterprises based on the electric carbon factors, or determine the electric carbon factors of other industries with unknown electric carbon factors based on industries with known electric carbon factors, and then predict the carbon emissions of industries based on the electric carbon factors. This method can be executed by a carbon emission prediction device based on electric carbon factors. The carbon emission prediction device based on electric carbon factors can be implemented in the form of hardware and / or software. The carbon emission prediction device based on electric carbon factors can be configured in electronic devices such as computers, mobile phones, smart tablets or servers. Figure 1 As shown, the method includes:

[0053] S110. For each object to be determined, obtain the normal distribution of the electric-carbon factor and the normal distribution of the factor weight of the object to be determined, and determine the estimated electric-carbon factor of the object to be determined based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weight, the preset number of factor extractions, and the preset number of weight extractions.

[0054] In this embodiment, the electricity carbon factor can be the ratio of carbon emissions from electricity consumption to carbon emissions from all energy consumption, where the carbon emissions from all energy consumption can include carbon emissions from water, electricity, natural gas, coal gas, and other energy sources. For example, the electricity carbon factor can be expressed by the following formula:

[0055] ρ = carbon emissions from electricity consumption / carbon emissions from energy consumption;

[0056] The object to be determined may be an industry with an unknown industry carbon factor, or may be an enterprise with an unknown enterprise carbon factor. If the object to be determined is an industry with an unknown industry carbon factor, such as the fuel production industry, the automobile production industry, the chemical production industry, etc., the target carbon factor of a certain industry can be determined among the industries with unknown industry carbon factors by determining the estimated carbon factors of the industries with unknown industry carbon factors. If the object to be determined is an enterprise with an unknown enterprise carbon factor, the target carbon factor of a certain industry can be determined among the enterprises with unknown enterprise carbon factors by determining the estimated carbon factors of the enterprises with unknown enterprise carbon factors.

[0057] In this embodiment, the normal distribution of the electric carbon factor may be the normal distribution of the estimated sub-electric carbon factors corresponding to each sub-object in the object to be determined. The normal distribution of the factor weight may be the normal distribution of the estimated electric carbon factor weights corresponding to each sub-object in the object to be determined.

[0058] For example, the normal distribution of the carbon factor and the normal distribution of the factor weights of each reference object can be determined, and the normal distribution of the carbon factor and the factor weights of the object to be determined can be obtained based on the normal distribution of the carbon factor and the factor weights of the reference object. Alternatively, the normal distribution of the carbon factor of the object to be determined can be determined based on the energy consumption data of a sub-object of the object to be determined with known energy consumption data, and the normal distribution of the factor weights can be determined based on the production data of a sub-object of the object to be determined with known production data.

[0059] Specifically, a preset number of factor extraction values ​​can be extracted from the normal distribution of the electric carbon factor according to the preset number of factor extractions, and the factor average value can be obtained according to the extracted values; and a preset number of weight extraction values ​​can be extracted from the normal distribution of the factor weight according to the preset number of weight extractions, and the weight average value can be obtained according to the extracted factor weight; then the factor average value is multiplied by the weight average value, and it is determined whether the sum of all the obtained weight average values ​​reaches the preset weight threshold. If not, the process returns to continue to execute the steps of extracting values ​​from the normal distribution of the electric carbon factor according to the preset number of factor extractions to obtain the factor average value, and extracting values ​​from the normal distribution of the factor weight according to the preset number of weight extractions to obtain the weight average value, until the sum of all the obtained weight average values ​​reaches the preset weight threshold. At this time, the sum of the multiplication results of all the weight average values ​​and the factor average value is used as the estimated electric carbon factor. Among them, the preset weight threshold can be 1, that is, the sum of all the obtained weight average values ​​should be as small as possible.

[0060] It should be noted that the estimated carbon factor corresponding to the object to be determined is not the accurate carbon factor of the object to be determined. Since the estimated carbon factor is obtained based on sampling, the estimated carbon factor can be used as an estimated value of the carbon factor for the object to be determined. Subsequent processing is required to obtain the accurate carbon factor.

[0061] In a specific embodiment, based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weight, the preset number of factor extractions, and the preset number of weight extractions, determining the estimated electric-carbon factor of the object to be determined includes the following steps:

[0062] Step 1, determine the initial weight and initial electric carbon factor;

[0063] Step 2: Based on the normal distribution of factor weights and the preset number of weight extractions, determine at least one current random weight; and according to each current random weight, the initial weight, and the preset weight threshold, determine at least one target random weight and the number of target random weights in each current random weight;

[0064] Step 3: Determine each target random factor based on the number of target random weights, the normal distribution of the electro-carbon factor, and the number of preset factor extractions, wherein the number of target random factors is the same as the number of target random weights;

[0065] Step 4: Based on the random weights of each target, the random factors of each target, and the initial electric-carbon factor, the estimated electric-carbon factor of the object to be determined is determined.

[0066] Among them, the initial weight and the initial electro-carbon factor can be 0. In the above step 2, based on the normal distribution of the factor weights and the preset weight extraction number, determining at least one current random weight can be: extracting a preset weight extraction number of values ​​from the normal distribution of the factor weights, taking the average of all the extracted values ​​as the current random weight, and further, repeating the step of extracting a preset weight extraction number of values ​​from the normal distribution of the factor weights and taking the average of all the extracted values ​​as the current random weight, to obtain multiple current random weights.

[0067] Optionally, in the above step 2, based on the normal distribution of factor weights and the preset number of weight extractions, at least one current random weight is determined, which can be: determining a preset extraction round; for each round of extraction in the preset extraction round, extracting a preset number of weights to be screened from the normal distribution of factor weights, and determining the current random weight based on each weight to be screened.

[0068] The preset number of extraction rounds can be used to specify the number of current random weights, that is, each round of extraction can obtain a current random weight. In each round of extraction, the average of the preset number of weights to be screened is the current random weight obtained in the current round.

[0069] It should be noted that the advantage of obtaining each current random weight based on a preset extraction round is that there is no need to determine whether to stop extracting the weight each time the current random weight is obtained. Instead, all current random weights are obtained at one time to filter out the target random weight. This is suitable for node task deployment in a distributed cluster. Each node can return all the extracted current random weights to the master node at one time. There is no need to return the current random weight to the master node after each extraction is completed, and there is no need to perform logical judgment, which improves processing efficiency.

[0070] Furthermore, in the above step 2, based on each current random weight, the initial weight and the preset weight threshold, at least one target random weight and the number of target random weights are determined in each current random weight. This can be: in the generation order of each current random weight value from early to late, on the basis of the initial weight, each target random weight is added in sequence until the result of the addition is greater than or equal to the preset weight threshold, the added current random weight is determined as the target random weight, and the number of target random weights is obtained.

[0071] For example, according to the generation order of the current random weight values ​​from early to late, the current random weights are 0.1, 0.2, 0.4, 0.2, 0.3, 0.4, 0.1, 0.4, and 0.2 respectively; the initial weight is 0, then when 0+0.1+0.2+0.4+0.2+0.3=1.2, the target random weights are determined to be 0.1, 0.2, 0.4, 0.2, and 0.3 respectively, and the number of target random weights is 5.

[0072] The above step 2 realizes the determination of each target random weight. Furthermore, in the above step 3, each target random factor can be determined according to the number of target random weights. Specifically, a preset number of factor extraction values ​​can be extracted from the normal distribution of the electric carbon factor, and the average value of the extraction is used as the current random factor. The operation of extracting a preset number of factor extraction values ​​from the normal distribution of the electric carbon factor is repeatedly performed until the number of current random factors is equal to the number of target random weights. At this time, each current random factor is used as the target random factor.

[0073] Furthermore, each target random factor and each target random weight can be weighted to obtain the estimated electric carbon factor. in, ...are random weights for each target, …are the random factors of each target, and ρ is the estimated electric carbon factor.

[0074] It should be noted that the advantage of using steps 1-3 above to first determine multiple current random weights and then determine the target random weight and the number of target random weights from the multiple current random weights is that the computer can complete the extraction of weights in one go, without having to determine whether it exceeds the preset weight threshold each time it is extracted, thereby improving the efficiency of determining each estimated electric carbon factor. For example, if the weight extraction task is deployed on the nodes in a distributed cluster, each node can execute a simple extraction logic without having to determine the preset weight threshold. The master node can intercept each target random factor through the current random factors returned by each node, thereby improving the processing efficiency of each node.

[0075] In addition, the advantage of setting the preset number of factor extractions and the preset number of weight extractions in this embodiment is that the estimated electric carbon factor can be determined by the mean of a large number of extracted factors and the mean of a large number of weights, thereby avoiding the influence of the extraction of extreme values ​​on the accuracy of the estimated electric carbon factor when only one value is extracted in each round, thereby improving the accuracy of the estimated electric carbon factor.

[0076] S120: Obtain reference carbon factors corresponding to at least two reference objects respectively, and determine a target carbon factor corresponding to a target object in each to-be-determined object based on the reference carbon factors and the estimated carbon factors.

[0077] The reference object can be an industry with a known industry carbon factor, or an enterprise with a known enterprise carbon factor. It should be noted that the object to be determined and the reference object are objects of the same level. If the object to be determined is an industry, the reference object is also the industry; if the object to be determined is an enterprise, the reference object is also the enterprise.

[0078] Specifically, after obtaining the reference carbon factors corresponding to at least two reference objects, the target carbon factor corresponding to the target object can be determined from each object to be determined based on each reference carbon factor and each estimated carbon factor.

[0079] Exemplarily, an object can be randomly selected from each object to be determined as the target object, and based on the reference electric-carbon factors corresponding to each reference object, the average value of the reference electric-carbon factors between any two reference objects is calculated. Furthermore, based on the difference between each average value and the estimated electric-carbon factor of the target object, the average value with the smallest difference is used as the target electric-carbon factor of the target object.

[0080] In a specific embodiment, based on each reference electric-carbon factor and the estimated electric-carbon factor corresponding to each object to be determined, the target electric-carbon factor corresponding to the target object in each object to be determined is determined, including: determining a reference mean factor based on each reference electric-carbon factor; determining the target object in each object to be determined according to the reference mean factor and the estimated electric-carbon factor corresponding to each object to be determined; and using the reference mean factor as the target electric-carbon factor corresponding to the target object.

[0081] The reference mean factor can be the mean of all reference carbon factors, or the mean of any two reference carbon factors. Specifically, after calculating the reference mean factor, the object to be determined whose estimated carbon factor is closest to the reference mean factor can be determined as the target object, and then the reference mean factor can be determined as the target carbon factor of the target object; or, a target object can be randomly selected from the objects to be determined, and the reference mean factor closest to the estimated carbon factor can be determined from the reference mean factors according to the estimated carbon factor of the target object, and the reference mean factor can be determined as the target carbon factor corresponding to the target object.

[0082] The advantage of calculating the reference mean factor and determining the target object based on the reference mean factor and each estimated electric carbon factor is that the difference between each object to be determined and the reference object, such as enterprise differences or industry differences, can be determined through the reference mean factor and each estimated electric carbon factor, and then the object to be determined with the smallest difference can be determined as the target object, so as to realize the prediction of the electric carbon factors of other industries that are strongly related to the industry based on the electric carbon factor of the industry, or, based on the electric carbon factor of the enterprise, the prediction of the electric carbon factors of other enterprises that are strongly related to the enterprise, thereby ensuring the accuracy of the predicted electric carbon factors.

[0083] Optionally, the target object is determined among the objects to be determined based on the reference mean factor and the estimated electric-carbon factor corresponding to each object to be determined, including: calculating the electric-carbon factor difference corresponding to each object to be determined based on the reference mean factor and the estimated electric-carbon factor corresponding to each object to be determined; and determining the object to be determined with the smallest electric-carbon factor difference as the target object based on the electric-carbon factor difference corresponding to each object to be determined.

[0084] The carbon factor difference corresponding to the object to be determined may be the absolute value of the difference between the reference mean factor and the estimated carbon factor corresponding to the object to be determined. Specifically, after calculating the carbon factor differences of each object to be determined, the object to be determined with the smallest carbon factor difference is determined as the target object, and the reference mean factor is then used as the target carbon factor of the target object.

[0085] By calculating the difference in electric carbon factors corresponding to each object to be determined, and then determining the target object based on the difference in electric carbon factors, the target object can be accurately determined. The electric carbon factors of other industries or enterprises closest to the industry or enterprise with known electric carbon factors can be determined based on the industry or enterprise with known electric carbon factors, ensuring the accuracy of the estimated electric carbon factors of industries or enterprises, and avoiding predicting the electric carbon factors of another industry with a large difference from the industry based on the electric carbon factors of one industry, such as predicting the electric carbon factors of the food processing industry based on the electric carbon factors of the equipment manufacturing industry.

[0086] It should be noted that the carbon emission prediction method based on the electricity-carbon factor provided in this embodiment can determine a target electricity-carbon factor of an object to be determined each time it is executed.

[0087] S130: Determine the estimated carbon emissions corresponding to the target object based on the target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object.

[0088] Specifically, after obtaining the target electricity-carbon factor of the target object, the actual electricity consumption of the target object can be obtained, and then the expected carbon emissions of the target object can be determined based on the actual electricity consumption and the target electricity-carbon factor.

[0089] For example, the actual electricity consumption of the target object within a set time period, such as the actual electricity consumption in the past three months, can be obtained, and the actual electricity consumption can be divided by the target electricity carbon factor to obtain the expected carbon emissions of the target object.

[0090] The technical solution of this embodiment obtains the normal distribution of the electric carbon factor and the normal distribution of the factor weights of each object to be determined, and determines the estimated electric carbon factor of the object to be determined based on the normal distribution of the electric carbon factor, the normal distribution of the factor weights, the preset factor extraction number and the preset weight extraction number. Then, based on the reference electric carbon factor of the reference object and each estimated electric carbon factor, the target electric carbon factor of the target object is determined, thereby achieving accurate determination of the electric carbon factor. Further, based on the determined target electric carbon factor and the actual electricity consumption, the expected carbon emissions of the target object are determined, thereby achieving accurate determination of carbon emissions without manual analysis, solving the problems of low accuracy, low efficiency and high cost of manual analysis of carbon emissions in the prior art. Moreover, by presetting the number of factor extractions and the preset number of weight extractions, the situation of extracting extreme values ​​due to a small number of extractions is avoided, thereby ensuring the accuracy of the estimated electric carbon factor, thereby ensuring the accuracy of the electric carbon factor, and realizing carbon emission prediction for objects with unknown electric carbon factors.

[0091] Example 2

[0092] Figure 2 This is a flow chart of a carbon emission prediction method based on the electric carbon factor provided by the second embodiment of the present invention. Based on the above embodiments, this embodiment provides an exemplary explanation of extracting a preset number of weights to be screened from the normal distribution of factor weights and determining the current random weight based on each weight to be screened. Figure 2 As shown, the method includes:

[0093] S210 . For each object to be determined, obtain the normal distribution of the electric-carbon factor and the normal distribution of the factor weight of the object to be determined.

[0094] S220. Determine the initial weight and the initial electric carbon factor, determine the preset extraction rounds, determine each preset slave node for each extraction round in the preset extraction rounds, and determine the single-round weight extraction number of each preset slave node based on the number of preset slave nodes and the preset weight extraction number.

[0095] The preset slave node may be a slave node in a distributed cluster.

[0096] Based on the number of preset slave nodes and the preset number of weight extractions, the number of weight extractions per round for each preset slave node can be determined by taking the ratio of the preset number of weight extractions to the number of preset slave nodes as the number of weight extractions per round for each preset slave node. That is, the number of weight extractions per round is evenly distributed among the preset slave nodes so that each preset slave node extracts the number of weights to be screened per round of weight extractions, and the sum of the number of weights to be screened extracted by all preset slave nodes is the preset number of weight extractions.

[0097] For example, the preset number of weight extractions is 10,000, the preset number of slave nodes is 10, and the preset number of single-round weight extractions of the slave nodes is 1,000.

[0098] S230 , extracting a single-round weight extraction number of weights to be screened from the factor weight normal distribution through each preset slave node, and determining the current random weight based on the weights to be screened extracted from each preset slave node.

[0099] Specifically, each preset slave node can extract a single round of weight extraction number of weights to be screened from the normal distribution of factor weights and send each extracted weight to be screened to the master node. Furthermore, the master node can determine the current random weight based on all the weights to be screened.

[0100] Optionally, in each of the preset extraction rounds, each preset slave node can simultaneously extract to obtain the number of weights to be screened equal to the number of weight extractions in a single round, thereby further determining the current random weight corresponding to the current round. The above method is repeated to obtain the current random weight corresponding to each round. That is, the number of current random weights is equal to the preset extraction rounds.

[0101] It should be noted that after each preset slave node has completed the extraction of the weights to be screened for all preset extraction rounds, it can send the weights to be screened for all rounds to the master node in the form of a sequence or array. The master node can determine the weights to be screened corresponding to each round based on the order of the values ​​in the received sequence or array. The advantage of presetting the slave node to send the weights to be screened for all rounds at once is that it reduces the number of data transmissions between the slave node and the master node, further improving the efficiency of determining the estimated carbon factor.

[0102] S240: Determine at least one target random weight and the number of target random weights in each current random weight according to each current random weight, the initial weight, and a preset weight threshold.

[0103] S250. Determine each target random factor based on the number of target random weights, the normal distribution of the electric-carbon factor, and the number of preset factor extractions, wherein the number of target random factors is the same as the number of target random weights.

[0104] Specifically, after the factor weights are extracted, the electro-carbon factor can be extracted. Specifically, the number of target random factors to be extracted should be equal to the number of target random weights.

[0105] Exemplarily, each target random factor is determined based on the number of target random weights, the normal distribution of the electric-carbon factor, and the preset number of factor extractions, including: determining the factor extraction round based on the number of target random weights, and determining the single-round factor extraction number of each preset slave node based on the number of preset slave nodes and the preset number of factor extractions; for each round of extraction in the factor extraction round, a single-round factor extraction number of factors to be screened is extracted from the normal distribution of the electric-carbon factor through each preset slave node, and determining the target random factor corresponding to the current round based on the factors to be screened extracted from each preset slave node.

[0106] Specifically, the ratio between the preset number of factor extractions and the number of preset slave nodes can be used to determine the number of factors extracted per round for each preset slave node. That is, the preset number of factors to be screened that need to be extracted in each round can be allocated to each preset slave node for extraction. For example, if the preset number of factors to be extracted is 5000 and the number of preset slave nodes is 10, then the number of factors extracted per round for each preset slave node is 500. Each preset slave node will obtain 500 factors to be screened in each round of extraction.

[0107] Furthermore, each preset slave node can send all the factors to be screened in all rounds to the master node at once after the factors to be screened in all rounds are extracted. The master node can determine the target random factor for each round based on the mean of the factors to be screened in each round.

[0108] In the above embodiment, by collaboratively extracting the preset factors from each preset slave node to extract a number of factors to be screened, the extraction efficiency of the preset factors in each round is improved, thereby improving the efficiency of determining the estimated electric carbon factor.

[0109] S260: Determine the estimated electric-carbon factor of the object to be determined based on the random weights of each target, the random factors of each target, and the initial electric-carbon factor.

[0110] S270. Obtain reference electric-carbon factors corresponding to at least two reference objects respectively, determine the target electric-carbon factor corresponding to the target object in each object to be determined based on each reference electric-carbon factor and each estimated electric-carbon factor, and determine the estimated carbon emissions corresponding to the target object based on the target electric-carbon factor corresponding to the target object and the actual electricity consumption of the target object.

[0111] The technical solution of this embodiment extracts a single-round weight extraction number of weights to be screened in each round through each preset slave node, so as to deploy the task of obtaining a preset number of weight extractions to be screened in each round to each preset slave node, thereby greatly improving the efficiency of extracting the weights to be screened. While a large number of samplings are performed through the preset weight extraction number to avoid the influence of extreme values ​​on the estimated electric carbon factor, the influence of a large number of samplings on the determination efficiency of the estimated electric carbon factor is reduced, thereby improving the efficiency of determining the estimated electric carbon factor.

[0112] Example 3

[0113] Figure 3 This is a flow chart of a carbon emission prediction method based on the electric carbon factor provided by the third embodiment of the present invention. This embodiment, based on the above embodiments, exemplifies the process of constructing the normal distribution of factor weights and the normal distribution of electric carbon factors. Figure 3 As shown, the method includes:

[0114] S310: For each object to be determined, determine a first sub-object and a second sub-object corresponding to the object to be determined.

[0115] The first sub-object may be a sub-object with known output data. For example, if the object to be determined is an industry, the first sub-object may be an enterprise within that industry for which output data is available. If the object to be determined is an enterprise, the first sub-object may be a unit within that enterprise for which output data is available. The output data may be the gross output value of the first sub-object within a set time period, such as the gross output value for 12 months.

[0116] The second sub-object can be a sub-object with known energy usage data. For example, if the object to be determined is an industry, the second sub-object is an enterprise within that industry for which energy usage data is available; if the object to be determined is an enterprise, the second sub-object is an entity within that enterprise for which energy usage data is available. Energy usage data can be the second sub-object's usage data for various energy sources within a set time period, such as electricity, water, and gas usage for a 12-month period.

[0117] S320. Obtain the electric-carbon factor weights corresponding to each first sub-object and the sub-electric-carbon factors corresponding to each second sub-object, construct a normal distribution of factor weights of the object to be determined based on the electric-carbon factor weights, and construct a normal distribution of electric-carbon factors of the object to be determined based on the sub-electric-carbon factors.

[0118] In this embodiment, after determining each first sub-object and each second sub-object in the object to be determined, the carbon factor weight of each first sub-object and the sub-carbon factor of each second sub-object can be obtained. The carbon factor weight of each first sub-object and the sub-carbon factor of each second sub-object can be pre-set or calculated from output data and energy consumption data, respectively.

[0119] In a specific embodiment, obtaining the electric carbon factor weight corresponding to each first sub-object and the sub-electric carbon factor corresponding to each second sub-object includes: obtaining the output data corresponding to each first sub-object, and determining the electric carbon factor weight corresponding to each first sub-object based on the output data corresponding to each first sub-object; obtaining the energy consumption data corresponding to each second sub-object, and determining the sub-electric carbon factor corresponding to each second sub-object based on the energy consumption data corresponding to each second sub-object.

[0120] Specifically, for each first sub-object, the carbon factor weight of the first sub-object can be calculated based on the output data of the first sub-object and the output data of the object to be determined to which the first sub-object belongs. For example, see the following formula:

[0121]

[0122] Among them, α i The electric carbon factor weight of the first sub-object of the i-th class.

[0123] Specifically, for each second sub-object, the carbon emissions of the usage corresponding to each energy type in the energy consumption data can be calculated based on the usage of each energy type in the energy consumption data of the second sub-object, and the carbon emission conversion rate corresponding to each energy type (which can be viewed according to the published conversion standards), and then the carbon emissions of electricity consumption can be divided by the carbon emissions of all energy consumption to obtain the sub-electricity carbon factor of the second sub-object.

[0124] It should be noted that the first sub-object that can calculate the electric carbon factor weight and the second sub-object that can calculate the sub-electric carbon factor can be the same sub-object or different sub-objects. The first sub-object and the second sub-object are selected based on whether each sub-object in the object to be determined has output data and energy consumption data.

[0125] In this embodiment, the electric carbon factor weight corresponding to the first sub-object is calculated through the output data of the first sub-object, and the sub-electric carbon factor corresponding to the second sub-object is calculated through the energy consumption data of the second sub-object, thereby achieving accurate determination of the electric carbon factor weight and the sub-electric carbon factor, and further achieving accurate determination of the estimated electric carbon factor, so that the estimated electric carbon factor is as close as possible to the actual industry situation.

[0126] Furthermore, in a specific embodiment, the factor weight normal distribution of the object to be determined is constructed based on the weight of each electric-carbon factor, and the electric-carbon factor normal distribution of the object to be determined is constructed based on each sub-electric-carbon factor. It can be: based on the weight of each electric-carbon factor, the weight mean and weight variance corresponding to the object to be determined are calculated, and the factor weight normal distribution corresponding to the object to be determined is constructed according to the weight mean and weight variance; based on each sub-electric-carbon factor, the electric-carbon factor mean and electric-carbon factor variance corresponding to the object to be determined are calculated, and the electric-carbon factor normal distribution corresponding to the object to be determined is constructed according to the electric-carbon factor mean and electric-carbon factor variance.

[0127] The weight mean may be the average value of all carbon factor weights, and the weight variance may be the variance of all carbon factor weights. For example, the weight mean and weight variance are calculated as follows:

[0128]

[0129] in, is the weight mean corresponding to the wth object to be determined, α wi is the electric carbon factor weight corresponding to the i-th first sub-object in the w-th object to be determined, k is the number of the first sub-objects in the w-th object to be determined, is the weight variance corresponding to the wth object to be determined. The factor weight normal distribution constructed based on the weight mean and weight variance can be

[0130] The mean of the carbon factor can be the average of all sub-carbon factors, and the variance of the carbon factor can be the variance of all sub-carbon factors. For example, the calculation formulas for the mean of the carbon factor and the variance of the carbon factor are as follows:

[0131]

[0132] in, is the mean value of the electric carbon factor corresponding to the wth object to be determined, ρ wi is the sub-electro-carbon factor corresponding to the i-th second sub-object in the w-th object to be determined, m is the number of second sub-objects in the w-th object to be determined, is the variance of the electric carbon factor corresponding to the wth object to be determined. The normal distribution of the electric carbon factor constructed based on the mean value and variance of the electric carbon factor can be

[0133] In the above embodiment, the factor weight normal distribution and the electric carbon factor normal distribution of each object to be determined can be constructed respectively.

[0134] The factor weight normal distribution is constructed by the weight mean and weight variance of the electric carbon factor weights corresponding to each first sub-object, and the electric carbon factor normal distribution is constructed by the electric carbon factor mean and electric carbon factor variance of the sub-electric carbon factors corresponding to each second sub-object. This can ensure that the factor weight normal distribution and the electric carbon factor normal distribution are as close as possible to the actual situation of the object to be determined, thereby improving the accuracy of the estimated electric carbon factor.

[0135] S330. For each object to be determined, obtain the normal distribution of the electric-carbon factor and the normal distribution of the factor weight of the object to be determined, and determine the estimated electric-carbon factor of the object to be determined based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weight, the preset number of factor extractions, and the preset number of weight extractions.

[0136] S340: Obtain reference carbon factors corresponding to at least two reference objects respectively, and determine a target carbon factor corresponding to a target object in each to-be-determined object based on the reference carbon factors and the estimated carbon factors.

[0137] S350: Determine the estimated carbon emissions corresponding to the target object based on the target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object.

[0138] The technical solution of this embodiment constructs a normal distribution of factor weights through the electric-carbon factor weights corresponding to the first sub-object of the object to be determined, and constructs a normal distribution of electric-carbon factors through the sub-electric-carbon factors corresponding to the second sub-object of the object to be determined. This can make the normal distribution of factor weights and the normal distribution of electric-carbon factors as close as possible to the actual usage of the object to be determined, thereby improving the accuracy of the estimated electric-carbon factor.

[0139] It should be noted that, taking the industry as an example of the to-be-determined and target objects, the carbon emissions prediction method based on the electricity-carbon factor provided in this embodiment does not require the number or list of enterprises within the industry with known gross domestic product, nor does it require the number or list of enterprises within the industry with known energy consumption data, thus making it widely applicable. Furthermore, if a company is a composite enterprise, meaning it belongs to multiple industries at the same time, then the company's energy consumption data or gross domestic product can be reused, and the company's electricity-carbon factor weights or sub-electricity-carbon factors can be used to predict electricity-carbon factors for multiple industries.

[0140] Example 4

[0141] Figure 4 This is a structural diagram of a carbon emission prediction device based on electric carbon factor provided by the fourth embodiment of the present invention. Figure 4 As shown, the apparatus includes an estimation factor determination module 410 , a target factor determination module 420 and a carbon emission calculation module 430 .

[0142] An estimated factor determination module 410 is configured to obtain, for each object to be determined, a normal distribution of the electric carbon factor and a normal distribution of factor weights of the object to be determined, and determine an estimated electric carbon factor of the object to be determined based on the normal distribution of the electric carbon factor, the normal distribution of the factor weights, a preset number of factor extractions, and a preset number of weight extractions;

[0143] The target factor determination module 420 is configured to obtain reference carbon factors corresponding to at least two reference objects, and determine a target carbon factor corresponding to each target object in the to-be-determined objects based on the reference carbon factors and the estimated carbon factors.

[0144] The carbon emission calculation module 430 is configured to determine the estimated carbon emission corresponding to the target object based on the target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object.

[0145] The technical solution of this embodiment obtains the normal distribution of the electric carbon factor and the normal distribution of the factor weights of each object to be determined, and determines the estimated electric carbon factor of the object to be determined based on the normal distribution of the electric carbon factor, the normal distribution of the factor weights, the preset factor extraction number and the preset weight extraction number. Then, based on the reference electric carbon factor of the reference object and each estimated electric carbon factor, the target electric carbon factor of the target object is determined, thereby achieving accurate determination of the electric carbon factor. Further, based on the determined target electric carbon factor and the actual electricity consumption, the expected carbon emissions of the target object are determined, thereby achieving accurate determination of carbon emissions without manual analysis, solving the problems of low accuracy, low efficiency and high cost of manual analysis of carbon emissions in the prior art. Moreover, by presetting the number of factor extractions and the preset number of weight extractions, the situation of extracting extreme values ​​due to a small number of extractions is avoided, thereby ensuring the accuracy of the estimated electric carbon factor, thereby ensuring the accuracy of the electric carbon factor, and realizing carbon emission prediction for objects with unknown electric carbon factors.

[0146] Based on the above embodiment, optionally, the apparatus further includes a sub-object determining unit and a normal distribution constructing unit, wherein:

[0147] The sub-object determination unit is configured to determine, for each of the objects to be determined, a first sub-object and a second sub-object corresponding to the object to be determined; obtain the electric carbon factor weight corresponding to each of the first sub-objects, and the sub-electric carbon factor corresponding to each of the second sub-objects;

[0148] The normal distribution construction unit is used to construct the factor weight normal distribution of the object to be determined based on the weight of each of the electric-carbon factors, and to construct the electric-carbon factor normal distribution of the object to be determined based on each of the sub-electric-carbon factors.

[0149] Based on the above embodiment, optionally, the normal distribution construction unit is specifically configured to:

[0150] Based on the weight of each of the electric-carbon factors, the weight mean and weight variance corresponding to the object to be determined are calculated, and the factor weight normal distribution corresponding to the object to be determined is constructed according to the weight mean and the weight variance; based on each of the sub-electric-carbon factors, the electric-carbon factor mean and electric-carbon factor variance corresponding to the object to be determined are calculated, and the electric-carbon factor normal distribution corresponding to the object to be determined is constructed according to the electric-carbon factor mean and the electric-carbon factor variance.

[0151] Based on the above embodiment, optionally, the estimation factor determination module 410 includes an initial information determination unit, a weight extraction unit, a factor extraction unit, and an estimation factor calculation unit, wherein:

[0152] The initial information determination unit is used to determine the initial weight and the initial electric carbon factor;

[0153] The weight extraction unit is configured to determine at least one current random weight based on the normal distribution of the factor weights and the preset weight extraction quantity, and determine at least one target random weight and the quantity of the target random weights in each current random weight according to each current random weight, the initial weight, and a preset weight threshold;

[0154] The factor extraction unit is used to determine each target random factor based on the number of the target random weights, the normal distribution of the electro-carbon factor, and the preset factor extraction number, wherein the number of the target random factors is the same as the number of the target random weights;

[0155] The estimated factor calculation unit is used to determine the estimated electric-carbon factor of the object to be determined based on each of the target random weights, each of the target random factors and the initial electric-carbon factor.

[0156] Based on the above embodiment, optionally, the weight extraction unit is further configured to:

[0157] Determine a preset extraction round; for each extraction round in the preset extraction round, extract the preset weight extraction number of weights to be screened from the factor weight normal distribution, and determine the current random weight based on each of the weights to be screened.

[0158] Based on the above embodiment, optionally, the weight extraction unit is further configured to:

[0159] Determine each preset slave node, and based on the number of the preset slave nodes and the preset weight extraction number, determine the single-round weight extraction number of each preset slave node; extract the single-round weight extraction number of weights to be screened from the factor weight normal distribution through each preset slave node; determine the current random weight based on the weights to be screened extracted from each preset slave node.

[0160] Based on the above embodiment, optionally, the factor extraction unit is further configured to:

[0161] The factor extraction round is determined based on the number of the target random weights, and the single-round factor extraction number of each preset slave node is determined based on the number of the preset slave nodes and the preset factor extraction number; for each round of extraction in the factor extraction round, the single-round factor extraction number of factors to be screened are extracted from the normal distribution of the electric-carbon factor through each preset slave node, and the target random factor corresponding to the current round is determined based on the factors to be screened extracted from each preset slave node.

[0162] The carbon emission prediction device based on the electric-carbon factor provided in the embodiment of the present invention can execute the carbon emission prediction method based on the electric-carbon factor provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0163] Example 5

[0164] Figure 5 1 is a structural diagram of an electronic device provided in Example 5 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0165] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0166] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0167] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the carbon emissions prediction method based on the electric carbon factor.

[0168] In some embodiments, the carbon emission prediction method based on the electric carbon factor can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the carbon emission prediction method based on the electric carbon factor described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the carbon emission prediction method based on the electric carbon factor in any other appropriate manner (for example, by means of firmware).

[0169] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] The computer programs for implementing the carbon emission prediction method based on the electric carbon factor of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] Example 6

[0172] Embodiment 6 of the present invention further provides a computer-readable storage medium storing computer instructions, the computer instructions being used to cause a processor to execute a carbon emission prediction method based on an electric carbon factor, the method comprising:

[0173] For each object to be determined, obtaining the normal distribution of the electric-carbon factor and the normal distribution of the factor weights of the object to be determined, and determining the estimated electric-carbon factor of the object to be determined based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weights, the preset number of factor extractions, and the preset number of weight extractions;

[0174] Obtaining reference carbon factors corresponding to at least two reference objects respectively, and determining a target carbon factor corresponding to each target object in the to-be-determined objects based on each of the reference carbon factors and each of the estimated carbon factors;

[0175] Based on the target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object, the expected carbon emissions corresponding to the target object are determined.

[0176] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0177] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0178] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0179] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0180] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0181] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A carbon emission prediction method based on electric carbon factor, characterized in that: include: For each object to be determined, obtaining the normal distribution of the electric-carbon factor and the normal distribution of the factor weights of the object to be determined, and determining the estimated electric-carbon factor of the object to be determined based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weights, the preset number of factor extractions, and the preset number of weight extractions; Obtaining reference carbon factors corresponding to at least two reference objects respectively, and determining a target carbon factor corresponding to each target object in the to-be-determined objects based on each of the reference carbon factors and each of the estimated carbon factors; Determining the estimated carbon emissions corresponding to the target object based on the target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object; The electricity carbon factor is the ratio of the carbon emissions of electricity consumption to the carbon emissions of all energy consumption. The electricity carbon factor normal distribution is the normal distribution of the sub-electricity carbon factors corresponding to each sub-object in the object to be determined. The factor weight normal distribution is the normal distribution of the electricity carbon factor weights corresponding to each sub-object in the object to be determined. The method of determining the estimated electric-carbon factor of the object to be determined based on the normal distribution of the electric-carbon factor, the normal distribution of the factor weight, the preset number of factor extractions, and the preset number of weight extractions includes: Determine the initial weight and initial electro-carbon factor; Determine at least one current random weight based on the normal distribution of the factor weights and the preset weight extraction quantity, and determine at least one target random weight and the quantity of the target random weights in each current random weight according to each current random weight, the initial weight, and a preset weight threshold; Determine each target random factor based on the number of the target random weights, the normal distribution of the electro-carbon factor, and the number of the preset factor extractions, wherein the number of the target random factors is the same as the number of the target random weights; Based on each of the target random weights, each of the target random factors and the initial electric-carbon factor, an estimated electric-carbon factor of the object to be determined is determined.

2. The method according to claim 1, characterized in that The method further comprises: For each of the objects to be determined, determining a first sub-object and a second sub-object corresponding to the object to be determined; Obtaining the electric carbon factor weights corresponding to each of the first sub-objects, and the sub-electric carbon factors corresponding to each of the second sub-objects; The factor weight normal distribution of the object to be determined is constructed based on the weight of each of the electric-carbon factors, and the electric-carbon factor normal distribution of the object to be determined is constructed based on each of the sub-electric-carbon factors.

3. The method according to claim 2, characterized in that The constructing of the factor weight normal distribution of the object to be determined based on the weight of each of the electric-carbon factors, and the constructing of the electric-carbon factor normal distribution of the object to be determined based on each of the sub-electric-carbon factors, include: Based on the weights of the electro-carbon factors, calculating the weight mean and weight variance corresponding to the object to be determined, and constructing a normal distribution of factor weights corresponding to the object to be determined according to the weight mean and weight variance; Based on each of the sub-electric-carbon factors, the electric-carbon factor mean and the electric-carbon factor variance corresponding to the object to be determined are calculated, and a normal distribution of the electric-carbon factor corresponding to the object to be determined is constructed according to the electric-carbon factor mean and the electric-carbon factor variance.

4. The method according to claim 1, wherein The determining of at least one current random weight based on the normal distribution of the factor weights and the preset weight extraction quantity includes: Determine the preset extraction rounds; For each round of extraction in the preset extraction rounds, the preset weight extraction number of weights to be screened are extracted from the factor weight normal distribution, and the current random weight is determined based on each of the weights to be screened.

5. The method according to claim 4, characterized in that The step of extracting the preset number of weights to be screened from the normal distribution of the factor weights, and determining the current random weight based on each of the weights to be screened, includes: Determine each preset slave node, and determine a single-round weight extraction quantity for each preset slave node based on the number of the preset slave nodes and the preset weight extraction quantity; Extracting the single-round weight extraction quantity of weights to be screened from the factor weight normal distribution through each of the preset slave nodes; The current random weight is determined based on the preset weights to be screened extracted from the nodes.

6. The method according to claim 5, characterized in that The determining of each target random factor based on the number of the target random weights, the normal distribution of the electric carbon factor, and the number of the preset factor extractions includes: Determine the factor extraction rounds based on the number of the target random weights, and determine the number of single-round factor extractions for each of the preset slave nodes based on the number of the preset slave nodes and the preset number of factor extractions; For each round of factor extraction in the factor extraction round, the number of factors to be screened for the single-round factor extraction is extracted from the normal distribution of the electric-carbon factor through each of the preset slave nodes, and the target random factor corresponding to the current round is determined based on the factors to be screened extracted from each of the preset slave nodes.

7. A carbon emission prediction device based on electric carbon factor, characterized in that: include: An estimated factor determination module is used to obtain, for each object to be determined, the normal distribution of the electric carbon factor and the normal distribution of the factor weight of the object to be determined, and determine the estimated electric carbon factor of the object to be determined based on the normal distribution of the electric carbon factor, the normal distribution of the factor weight, the preset number of factor extractions, and the preset number of weight extractions; a target factor determination module, configured to obtain reference carbon factors corresponding to at least two reference objects, and determine a target carbon factor corresponding to each target object in the objects to be determined based on the reference carbon factors and the estimated carbon factors; a carbon emissions calculation module, configured to determine an estimated carbon emissions corresponding to the target object based on a target electricity-carbon factor corresponding to the target object and the actual electricity consumption of the target object; The electricity carbon factor is the ratio of the carbon emissions of electricity consumption to the carbon emissions of all energy consumption. The electricity carbon factor normal distribution is the normal distribution of the sub-electricity carbon factors corresponding to each sub-object in the object to be determined. The factor weight normal distribution is the normal distribution of the electricity carbon factor weights corresponding to each sub-object in the object to be determined. The estimation factor determination module includes: an initial information determination unit for determining an initial weight and an initial electric carbon factor; a weight extraction unit, configured to determine at least one current random weight based on the normal distribution of the factor weights and the preset weight extraction quantity, and determine at least one target random weight and the quantity of the target random weights in each current random weight according to each current random weight, the initial weight, and a preset weight threshold; a factor extraction unit, configured to determine each target random factor based on the number of the target random weights, the normal distribution of the electro-carbon factor, and the preset number of factor extractions, wherein the number of the target random factors is the same as the number of the target random weights; An estimated factor calculation unit is used to determine the estimated electric-carbon factor of the object to be determined based on each of the target random weights, each of the target random factors and the initial electric-carbon factor.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the carbon emission prediction method based on the electric carbon factor according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the carbon emission prediction method based on the electric carbon factor according to any one of claims 1 to 6 when executed.

Images