Product carbon emission accounting method and system based on cloud configuration

Abstract

The invention belongs to the field of carbon emission data processing, and provides a product carbon emission accounting method and system based on cloud configuration. The method comprises the following steps: constructing a cloud configuration product standard database; based on the constructed product standard database, configuring a carbon emission behavior list corresponding to each link of the whole life cycle of the product; obtaining an activity data list of the product, and configuring the data to the activity data list by using a pre-constructed non-intrusive activity data model; for each link of the full life cycle of the product, calculating activity data corresponding to each carbon emission behavior in the corresponding link in the activity data list, and performing weighted summation on the activity data and the corresponding carbon emission factor to obtain the carbon emission of the corresponding link; and recommending a corresponding emission reduction scheme according to a comparison result of the carbon emission of each link and the average value of the carbon emission of the corresponding link of the same type of products.

Description

Technical Field

[0001] The present invention belongs to the field of carbon emission data processing, and in particular relates to a product carbon emission accounting method and system based on cloud configuration. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Through carbon emission accounting, enterprises can gain an in-depth understanding of the carbon emissions of their products during the production and operation process, and then formulate targeted emission reduction strategies, and then achieve a win-win situation of energy conservation, emission reduction and economic benefits through measures such as optimizing configuration, reasonably adjusting production structure, improving process flow, and adopting low-carbon technology. However, the current carbon emission accounting cannot fully cover all aspects of the product life cycle, and thus cannot reveal the full picture of the carbon emissions of its related products, thereby guiding the formulation of actual emission reduction strategies. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a product carbon emission accounting method and system based on cloud configuration, which can improve accounting accuracy and efficiency, reduce the cost of data acquisition and processing, and enhance the adaptability and scalability of the accounting method.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A first aspect of the present invention provides a product carbon emission accounting method based on cloud configuration.

[0007] In one or more embodiments, a method for calculating carbon emissions of a product based on cloud configuration is provided, including:

[0008] Build a cloud configuration product standard database, which includes a carbon emission factor standard database, a product life cycle standard database, a product feature element record database, and a carbon emission behavior record database;

[0009] Based on the constructed product standard database, configure the carbon emission behavior list corresponding to each link of the product life cycle; the carbon emission behavior list includes each link of the product life cycle, the carbon emission behavior name, factor name and carbon emission factor data corresponding to each link;

[0010] Obtain the product's activity data list, and configure the data into the activity data list using a pre-built non-intrusive activity data model; the activity data list is consistent with the carbon emission behavior list, and the time series activity data corresponding to each carbon emission behavior is added;

[0011] For each link in the product life cycle, calculate the weighted sum of the activity data corresponding to each carbon emission behavior in the corresponding link in the activity data list and its corresponding carbon emission factor to obtain the carbon emissions of the corresponding link;

[0012] Based on the comparison results of the carbon emissions in each link and the average carbon emissions in the corresponding links of the same type of products, the corresponding emission reduction plan is recommended.

[0013] A second aspect of the present invention provides a product carbon emission accounting system based on cloud configuration.

[0014] In one or more embodiments, a cloud-based product carbon emission accounting system includes:

[0015] A standard database construction module is used to construct a cloud configuration product standard database, which includes a carbon emission factor standard database, a product life cycle link standard database, a product feature element record database, and a carbon emission behavior record database;

[0016] The carbon emission behavior list configuration module is used to configure the carbon emission behavior list corresponding to each link of the product life cycle based on the constructed product standard database; the carbon emission behavior list contains each link of the product life cycle, the carbon emission behavior name, factor name and carbon emission factor data corresponding to each link;

[0017] An activity data list configuration module is used to obtain the activity data list of the product and configure these data into the activity data list using a pre-built non-intrusive activity data model; wherein the activity data list is consistent with the carbon emission behavior list, and the time series activity data corresponding to each carbon emission behavior is added;

[0018] The carbon emission calculation module is used to calculate the weighted sum of the activity data corresponding to each carbon emission behavior in the corresponding link in the activity data list and the corresponding carbon emission factor for each link in the product life cycle to obtain the carbon emission of the corresponding link;

[0019] The emission reduction plan recommendation module is used to recommend corresponding emission reduction plans based on the comparison results of the carbon emissions of each link with the average carbon emissions of the corresponding links of the same type of products.

[0020] A third aspect of the present invention provides a computer-readable storage medium.

[0021] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the cloud-based product carbon emission accounting method as described above.

[0022] A fourth aspect of the present invention provides an electronic device.

[0023] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the product carbon emission accounting method based on cloud configuration as described above are implemented.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] (1) The present invention provides a product carbon emission accounting method and system based on cloud configuration, which utilizes the flexible configuration, modular design and high integration characteristics of configuration technology, rationally uses existing carbon emission factors, optimizes the carbon emission accounting process, improves the accounting accuracy and efficiency, reduces the cost of data acquisition and processing, enhances the adaptability and scalability of the accounting method, and provides a more scientific, accurate and efficient solution for carbon emission management.

[0026] (2) The present invention constructs a cloud configuration product standard database and reduces the product carbon emission accounting time through in-depth analysis, thereby greatly improving work efficiency and reducing the time and cost of manual on-site operations.

[0027] (3) The present invention adopts a non-intrusive load model, which saves hardware and maintenance costs for users and reduces interference, and achieves accurate measurement of carbon emission behavior in each link, making it easier to promote and apply.

[0028] (4) The present invention can accurately identify the main sources of carbon emissions by refining them to specific equipment, processes or production links, thereby optimizing resource allocation in a targeted manner, reducing unnecessary carbon emissions, and formulating more scientific and reasonable energy-saving and emission reduction strategies.

[0029] (5) The invention helps promote the standardization and regularization of carbon emission accounting in various industries by constructing a standard tool for carbon emission accounting, thereby reducing the cost of carbon emission accounting within the industry and improving accounting efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0031] Figure 1 It is a flowchart of a product carbon emission accounting method based on cloud configuration according to an embodiment of the present invention;

[0032] Figure 2 It is a schematic diagram of the structure of a product carbon emission accounting system based on cloud configuration according to an embodiment of the present invention;

[0033] Figure 3is a schematic diagram of an electronic device according to an embodiment of the present invention;

[0034] Figure 4 is a non-intrusive load decomposition structure diagram of an embodiment of the present invention;

[0035] Figure 5 is the encoding-decoding network structure of the generator of an embodiment of the present invention;

[0036] Figure 6 is the discriminator training process of the embodiment of the present invention;

[0037] Figure 7 is the generator training process of an embodiment of the present invention;

[0038] Figure 8 This is a structural diagram of the division of each link of the product life cycle of an embodiment of the present invention;

[0039] Fig. 9 is a parameter setting of the generator of an embodiment of the present invention;

[0040] Fig.10 is the parameter setting of the discriminator in the embodiment of the present invention;

[0041] FIG. 11( a ) is a comparison of the predicted and actual decomposition results of the electric load data of an embodiment of the present invention on February 1, 2018;

[0042] FIG. 11( b ) is a comparison of the predicted and actual decomposition results of the electric load data of an embodiment of the present invention on May 1, 2018;

[0043] FIG. 11( c ) is a comparison of the predicted and actual electric load decomposition results of the electric load data of an embodiment of the present invention on August 1, 2018;

[0044] FIG11( d ) is a comparison of the predicted and actual electric load decomposition results of the electric load data of an embodiment of the present invention on November 1, 2018. DETAILED DESCRIPTION

[0045] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0046] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0047] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0048] Figure 1 is a flow chart of a product carbon emission accounting method based on cloud configuration in an embodiment of the present invention, such as Figure 1 The product carbon emission accounting method based on cloud configuration in the present embodiment shown may include:

[0049] S101, construct a cloud configuration product standard database, which includes a carbon emission factor standard database, a product full life cycle standard database, a product characteristic element record database and a carbon emission behavior record database.

[0050] Specifically, the process of constructing the carbon emission factor standard database EF is as follows:

[0051] (1) Data collection: Collect data from published carbon emission factor inventories.

[0052] (2) Classification: According to the characteristic factors EF of carbon emission factors f , and classify the database. The database is divided into two categories: product consumption and emission behavior. Product consumption is further divided into industrial products, energy products, and daily necessities; emission behavior includes waste treatment, transportation services, and carbon sinks.

[0053] (3) Data entry and verification: The collected data are entered into the database and verified to ensure the accuracy and completeness of the data.

[0054] (4) Database maintenance: Update the database regularly to ensure the timeliness and accuracy of the data.

[0055] The process of building a standard library S for the entire product life cycle is as follows:

[0056] Divide the product life cycle into planning and design, raw material procurement, production and manufacturing, installation and commissioning, operation and maintenance, and scrapping;

[0057] Each stage is further divided into specific links i , and clarify the definition and boundaries of each link;

[0058] Establish a relationship diagram for each link in the product life cycle and clarify the logical relationship and dependency between each link.

[0059] The product characteristic element recording database PE is used to record characteristic elements of products to determine whether products belong to the same type.

[0060] The carbon emission behavior record database B is configured as follows:

[0061] Record PE of each type of product j In each link L i Available carbon emission factors EF i and its characteristic elements;

[0062] In the same link L i In this case, the carbon emission factors are automatically sorted from small to large to facilitate subsequent analysis and optimization.

[0063] S102, based on the constructed product standard database, configure a list of carbon emission behaviors corresponding to each link in the product life cycle; wherein the carbon emission behavior list includes each link in the product life cycle, and the carbon emission behavior name, factor name and carbon emission factor data corresponding to each link.

[0064] The automatic configuration process is as follows:

[0065] (1) Select product type: Select products of the same type in the system.

[0066] (2) Load the default list: The system automatically loads all links of this type of product using B i List as default configuration.

[0067] In other embodiments, the carbon emission behavior column may also be configured manually:

[0068] (1) Manually increase carbon emission behavior B i .

[0069] (2) Select carbon emission factors: Select the required carbon emission factors from the EF database and add the selected carbon emission factors to the EF of the corresponding link. i list.

[0070] (3) Save configuration: Save the results of manual configuration.

[0071] S103, obtaining a product activity data list, and configuring these data into an activity data list using a pre-built non-intrusive activity data model; wherein the activity data list is consistent with the carbon emission behavior list, and time series activity data corresponding to each carbon emission behavior is newly added.

[0072] If the data inventory corresponds to carbon emission behavior. i For each carbon emission factor in the list, configure the corresponding activity data AD iActivity data should reflect the actual volume of production or consumption activities at that link.

[0073] According to the activity data AD i Calculate sequence to subsequence (S2SS), the calculation formula is:

[0074]

[0075] Among them, X(t) is set as the signal value of the AD sequence at time t; X(t) is the signal value of a certain AD sequence at time t; W is the time window length of the AD sequence interception; W′ is the window width of the output sequence, and its value is the number of signal points contained in the window. The predicted subsequence position is defined in the middle of the window. By adjusting the specific value of W′, the trade-off between the difficulty of network convergence and the amount of calculation can be adjusted to enhance the flexibility and adaptability of the model. Y is the subsequence.

[0076] The non-intrusive activity data model is constructed using a deep convolutional generative adversarial network (DCGAN); the total AD sequence is recorded as AD a , the real AD sequence is recorded as AD t , the AD sequence generated by the generator is recorded as AD v The AD decomposition process is as follows:

[0077] (1) AD a Input generator, get output AD v ;

[0078] (2) AD a and AD t In the discriminator, the loss is calculated by the loss function 1 ;

[0079] (3) AD a and AD v Input to the discriminator, and calculate the loss function to get loss 2 ;

[0080] (4) Freeze the parameters of the generator, based on the loss obtained 1 and loss 2 Update the discriminator until convergence;

[0081] (5) Freeze the updated discriminator parameters and set AD a Input generator, get AD v , input the discriminator, and get loss 2 , AD v With ADa L1 norm and loss of the difference 2 Superposition is used as a loss function to guide the generator parameter update until convergence

[0082] Among them, the loss function formula of the generator in the deep convolutional generative adversarial network is:

[0083]

[0084] Among them, min G max D V L1 (G, D) represents the loss function of the generator in the deep convolutional generative adversarial network; G represents the generator, D represents the discriminator; x is AD a Sequence, y is AD t sequence; V(D,G) is the output of the discriminator; AD t The L1 norm of the difference between the data generated by the generator under the supervision of x; λ is a hyperparameter that adjusts the proportional relationship between the two, balancing the importance of the discriminator and the L1 norm to adapt to different production environments; G(z|x) represents the generated data of the generator under the supervision of x; z represents the convergence parameter; ρ z (z) represents the convergence trend and is the set value; ρ data (y) represents the sequence trend of y, which is the set value.

[0085] (6) Reselect data and proceed to the next round of iteration.

[0086] Generator design:

[0087] (1) Use the encoding-decoding network based on the U-Net network structure as the main body of the generator, responsible for accepting AD a And generate AD v .

[0088] (2)AD a As input data, it passes through 8 encoders and 8 decoders in sequence, and finally obtains the output data P av In the encoder, AD a After convolution operation, regularization and ReLU activation function processing, in the decoder, it is deconvolution operation, regularization and ReLU activation function processing to obtain the final data AD v .

[0089] Discriminator design:

[0090] The discriminator is constructed using the Fully Convolutional Network (FCN) algorithm to evaluate the quality of the generated data.

[0091] (1)AD a With AD t Splice to AD 1 , A.D. a With AD v Splice to AD 2 .

[0092] (2) The concatenated sequence is processed by several encoder structures in turn to form a vector.

[0093] (3) When the input is AD 1 When , the output value of the discriminator is expected to tend to be "true", and when the input is AD 2 , the output value of the discriminator is expected to be inclined to "false". The final output of the discriminator can be a scalar value, the larger the value, the more inclined to "true", and vice versa.

[0094] The training of the discriminator and the generator is an alternating process, which aims to improve the performance of both through continuous iterative optimization.

[0095] (1) Alternating training strategy. In each round of iteration, the discriminator is trained first, with the goal of improving its ability to distinguish between real data and generated data, so that it can distinguish between the two as accurately as possible. Then, the generator is trained, with the goal of improving the quality of its generated data, in order to deceive the discriminator and make it difficult to distinguish between generated data and real data.

[0096] (2) Discriminator training. The discriminator trains AD 1 and AD 2 The results are processed and the comparison results are superimposed and input into the optimizer. The optimizer applies the Stochastic Gradient Descent (SGD) optimization algorithm to update the discriminator weights and complete the discriminator training process.

[0097] (3) Generator training. a Input to the generator to get AD v . a With AD v Input to the discriminator, then compared with "false", and then with AD a With AD v The L1 norm of the difference is summed and used to guide the optimizer to optimize the generator weights. The optimizer is constructed using the Adaptive Moment Estimation (Adam) algorithm to complete the training process of the generator.

[0098] The performance of the model is tested by using three models: normalized signal aggregate error (SAE), mean absolute error (MAE) and estimated accuracy (Acc.). The calculation formula is as follows:

[0099]

[0100] Among them, x t is the true value at time t; y t is the calculated prediction value of the convolutional neural network at time t; MAE is x t With y t The mean of the error at each time point; d is the total energy consumption of the total input sequence; d′ is the total energy consumption of the predicted result sequence; SAE is the total error over a period of time; Acc. is a measure of the accuracy of load decomposition.

[0101] S104, for each link in the product life cycle, calculate the activity data corresponding to each carbon emission behavior in the corresponding link in the activity data list and its corresponding carbon emission factor, and perform weighted summation to obtain the carbon emission amount of the corresponding link.

[0102] The calculation formula for carbon emissions in each link is as follows:

[0103]

[0104] Among them, MCl i for l i Carbon emission model of the AD link; a The amount of production or consumption activity that results in carbon emissions for activity a; EF a a is the carbon emission factor corresponding to the activity level data; n is the number of activities.

[0105] S105, recommending a corresponding emission reduction plan based on the comparison result of the carbon emissions of each link with the average carbon emissions of the corresponding links of the same type of products.

[0106] Among them, the recommended process for the corresponding emission reduction plan is:

[0107] Calculate the average carbon emissions of each stage and link of the same type of products respectively, and compare the carbon emissions of the corresponding stage and link of the current product with the corresponding average value;

[0108] If the carbon emissions of the corresponding stage and link of the current product are greater than the corresponding average value, traverse the carbon emission behavior list of the current link, and obtain the average carbon emission behavior of the carbon emissions of each stage and link of the same type of products, which has the same carbon emission factor characteristic elements as the current carbon emission behavior and has the smallest carbon emission factor value.

[0109] The following takes the product list (American standard forged steel ball valve) provided by a machinery manufacturing company as an example, and uses the carbon emission accounting method of cloud configuration technology to calculate the carbon emission of this product. The specific implementation method is as follows:

[0110] First, relevant data on American Standard forged steel ball valve products from 2014 to 2018 were collected, including raw material lists, electrical load lists, water consumption lists, material transportation lists, and fuel lists.

[0111] According to each link of the product life cycle, a list of carbon emission behaviors is configured, as shown in Table 1.

[0112] Table 1 List of carbon emission behaviors of ball valve products

[0113]

[0114]

[0115] Configure activity data. The configuration is shown in Table 2.

[0116] Among them, the raw material list, water consumption list, material transportation list and fuel list in the activity data configuration table are consistent with the carbon emission behavior list.

[0117] Table 2 Activity data configuration table

[0118]

[0119]

[0120]

[0121] In this embodiment, the electricity load list includes carbon emission behaviors in multiple links.

[0122] Leverage pre-built, non-intrusive active data models configured to active data lists.

[0123] The input and output setting process of the non-intrusive activity data model is as follows:

[0124] (1) Set the total sequence AD ​​of the input model power load a The length is 1024, set the output model power load sequence AD v The length is 512. If the response time is too long, you can increase the AD aWith AD v Length.

[0125] (2) Hyperparameter settings of the deep neural network in the generator are shown in Fig. 9 , select 512 data points in the middle to construct the output data sequence, and set the output size of the last layer to 1024*1*1.

[0126] (3) Hyperparameter settings of the deep neural network in the discriminator are shown in Fig.10 , set AD separately t With AD v The length is 1024*1*1.

[0127] (4) Set λ = 100, which can be adjusted later based on the simulation results.

[0128] The dataset setup process for the non-intrusive activity data model is:

[0129] (1) Set the data from 2014 to 2017 as sample data and the data from 2018 as test data. The sample selection is shown in the following table:

[0130] Table 3 Data collection table

[0131]

[0132]

[0133] (2) Missing value processing: The electricity load is processed on a daily basis, using a forward filling method to improve the integrity of the sequence data.

[0134] (3) Outlier processing: According to the data distribution range, outlier data that exceeds the range are marked by deletion, mean value correction, nearest data point correction, or no processing.

[0135] (4) Timestamp alignment. The sampling frequency is unified to 1 / 60 Hz, a new power load sequence is constructed, the data records in the total load sequence are read in sequence, and the value of the power load sequence closest to the record timestamp is inserted into the new power load sequence.

[0136] (5) Data sharding. The sliding window method is used. The window size is 1024, and the distance of each slide is a random value in the range of 1 to 512. t The value of the middle position of the window in the power load sequence is selected. Construct several AD a With AD t One-to-one corresponding samples constitute a sample set.

[0137] The evaluation indicators of the non-intrusive activity data model are:

[0138] The electricity load data from 2014 to 2017 are used as training samples, and the electricity load data from 2018 are used as test samples. The daily electricity load decomposition results are constructed, and the SAE, MAE and ACC indicators are calculated.

[0139] Table 4 Evaluation indicators

[0140]

[0141]

[0142] like Figure 11(a)-Figure 11(d) The figures are the comparison of the predicted and actual electric load decomposition results of the electric load data on February 1, May 1, August 1, and November 1, 2018. The red curve is the predicted electric load decomposition result using the non-intrusive activity data model, and the blue curve is the actual result of the electric load decomposition.

[0143] According to the calculation results: the carbon emissions of raw material procurement - procurement - transportation of polytetrafluoroethylene materials and nitrile rubber materials, as well as manufacturing - production and processing - fuel consumption of heat treatment furnaces are higher than the average value of the same type of products. By querying the carbon emission factors with the same characteristic elements under the same type of products, the carbon emission factors with smaller values ​​are recommended to users, as shown in Table 5:

[0144] Table 5 Recommended emission reduction plans

[0145]

[0146]

[0147] Figure 2 This is a schematic diagram of the structure of a product carbon emission accounting system based on cloud configuration in an embodiment of the present invention. Figure 1 The carbon emission accounting method of cloud-based products corresponds to Figure 2 As shown, the cloud-based product carbon emission accounting system in this embodiment may include:

[0148] A standard database construction module 201 is used to construct a cloud configuration product standard database, which includes a carbon emission factor standard database, a product life cycle link standard database, a product feature element record database, and a carbon emission behavior record database;

[0149] A carbon emission behavior list configuration module 202 is used to configure a carbon emission behavior list corresponding to each link of the product life cycle based on the constructed product standard database; wherein the carbon emission behavior list includes each link of the product life cycle, and the carbon emission behavior name, factor name and carbon emission factor data corresponding to each link;

[0150] The activity data list configuration module 203 is used to obtain the activity data list of the product and configure these data into the activity data list using the pre-built non-intrusive activity data model; wherein the activity data list is consistent with the carbon emission behavior list, and the time series activity data corresponding to each carbon emission behavior is added;

[0151] The carbon emission calculation module 204 is used to calculate the weighted sum of the activity data corresponding to each carbon emission behavior in the corresponding link in the activity data list and the corresponding carbon emission factor for each link in the product life cycle to obtain the carbon emission of the corresponding link;

[0152] The emission reduction scheme recommendation module 205 is used to recommend a corresponding emission reduction scheme based on the comparison result of the carbon emission of each link with the average carbon emission of the corresponding link of the same type of product.

[0153] It should be noted here that Figure 2 The various modules in the cloud-based product carbon emission accounting system are Figure 1 The various steps in the cloud-based product carbon emission accounting method correspond one to one, and the specific implementation process is the same, so it will not be repeated here.

[0154] Reference Figure 3 , a schematic diagram of an electronic device is given. It should be noted that, Figure 3 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0155] like Figure 3 As shown, electronic device 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage part 308 into a random access memory (RAM) 303. In RAM 303, various programs and data required for system operation are also stored. Central processing unit 301, ROM 302 and RAM 303 are connected to each other via bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0156] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a local area network (LAN) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0157] When the central processing unit 301 in the electronic device of this embodiment executes the program, the following is achieved: Figure 1 The steps in the carbon emission accounting method of cloud-based products are shown.

[0158] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, the computer program including a computer program for executing Figure 1 In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit 301, various functions defined in the apparatus of the present application are executed.

[0159] in, Figure 1 The computer program instructions corresponding to the method shown may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0160] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0161] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A product carbon emission accounting method based on cloud configuration, characterized in that: include: Build a cloud configuration product standard database, which includes a carbon emission factor standard database, a product life cycle standard database, a product feature element record database, and a carbon emission behavior record database; Based on the constructed product standard database, configure the carbon emission behavior list corresponding to each link of the product life cycle; the carbon emission behavior list includes each link of the product life cycle, the carbon emission behavior name, factor name and carbon emission factor data corresponding to each link; Obtain the product's activity data list, and configure the data into the activity data list using a pre-built non-intrusive activity data model; the activity data list is consistent with the carbon emission behavior list, and the time series activity data corresponding to each carbon emission behavior is added; For each link in the product life cycle, calculate the weighted sum of the activity data corresponding to each carbon emission behavior in the corresponding link in the activity data list and its corresponding carbon emission factor to obtain the carbon emissions of the corresponding link; Based on the comparison results of the carbon emissions in each link and the average carbon emissions in the corresponding links of the same type of products, the corresponding emission reduction plan is recommended.

2. The product carbon emission accounting method based on cloud configuration as claimed in claim 1, characterized in that: The process of building a standard library for the entire product life cycle is as follows: Divide the product life cycle into planning and design, raw material procurement, production and manufacturing, installation and commissioning, operation and maintenance, and scrapping; Further refine each stage into specific links and clarify the definition and boundaries of each link; Establish a relationship diagram for each link in the product life cycle and clarify the logical relationship and dependency between each link.

3. The product carbon emission accounting method based on cloud configuration as claimed in claim 1, characterized in that: The product characteristic element recording database is used to record the characteristic elements of products to determine whether the products belong to the same type.

4. The method for calculating carbon emissions of products based on cloud configuration according to claim 1, characterized in that: The carbon emission behavior record database is configured as follows: Record the carbon emission factors and their characteristic elements that can be used in each link for each type of product; In the same link, the values ​​of carbon emission factors are automatically sorted from small to large.

5. The method for calculating carbon emissions of products based on cloud configuration according to claim 1, characterized in that: The non-intrusive activity data model is constructed using a deep convolutional generative adversarial network.

6. The method for calculating carbon emissions of products based on cloud configuration according to claim 1, characterized in that: The calculation formula for carbon emissions in each link is as follows: Among them, MCl i for l i Carbon emission model of the AD link; a The amount of production or consumption activity that results in carbon emissions for activity a; EF a a is the carbon emission factor corresponding to the activity level data; n is the number of activities.

7. The method for calculating carbon emissions of products based on cloud configuration according to claim 1, characterized in that: The recommended process for the corresponding emission reduction plan is: Calculate the average carbon emissions of each stage and link of the same type of products respectively, and compare the carbon emissions of the corresponding stage and link of the current product with the corresponding average value; If the carbon emissions of the corresponding stage and link of the current product are greater than the corresponding average value, traverse the carbon emission behavior list of the current link, and obtain the average carbon emission behavior of the carbon emissions of each stage and link of the same type of products, which has the same carbon emission factor characteristic elements as the current carbon emission behavior and has the smallest carbon emission factor value.

8. A product carbon emission accounting system based on cloud configuration, characterized in that: include: A standard database construction module is used to construct a cloud configuration product standard database, which includes a carbon emission factor standard database, a product life cycle link standard database, a product feature element record database, and a carbon emission behavior record database; The carbon emission behavior list configuration module is used to configure the carbon emission behavior list corresponding to each link of the product life cycle based on the constructed product standard database; the carbon emission behavior list contains each link of the product life cycle, the carbon emission behavior name, factor name and carbon emission factor data corresponding to each link; An activity data list configuration module is used to obtain the activity data list of the product and configure these data into the activity data list using a pre-built non-intrusive activity data model; wherein the activity data list is consistent with the carbon emission behavior list, and the time series activity data corresponding to each carbon emission behavior is added; The carbon emission calculation module is used to calculate the weighted sum of the activity data corresponding to each carbon emission behavior in the corresponding link in the activity data list and the corresponding carbon emission factor for each link in the product life cycle to obtain the carbon emission of the corresponding link; The emission reduction plan recommendation module is used to recommend corresponding emission reduction plans based on the comparison results of the carbon emissions of each link with the average carbon emissions of the corresponding links of the same type of products.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the cloud-based product carbon emission accounting method as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the cloud-based product carbon emission accounting method as described in any one of claims 1-7 are implemented.

Images