Multi-data-source carbon data verification method and device

Abstract

The invention discloses a multi-data-source carbon data verification method and device, and belongs to the field of carbon emission metering. The multi-data-source carbon data verification method comprises the steps that multiple pieces of carbon data in multiple target time periods are obtained, and the multiple pieces of carbon data are data from multiple different data sources; performing pairwise difference calculation on the carbon data from different data sources in the same target time period to obtain a difference matrix; performing clustering analysis on the difference value matrix to obtain a verification result; the verification result comprises normal carbon data and abnormal carbon data. According to the multi-data-source carbon data verification method, the verification of the consistency and accuracy of the multi-data-source carbon data can be improved, and the accuracy of labeling and removing the abnormal carbon data can be improved, so that the accuracy of subsequent carbon emission measurement is improved.

Description

Technical Field

[0001] The present application relates to the field of carbon emission measurement, and in particular to a method and device for verifying carbon data from multiple data sources. Background Art

[0002] In the relevant technologies, in the carbon emission measurement method, the collection of coal quality and coal quantity data includes multiple sources, and coal quality analysis data and coal quantity data are one of the important parameters for carbon emission measurement. The main influencing factors of carbon emission data quality come from the consumption of fossil fuels and the measurement of fossil fuel coal quality data. However, there are certain differences in coal quality parameters, coal consumption and other data from different data sources. It is impossible to accurately test the accuracy and consistency of coal quality and coal consumption from multiple data sources, or to eliminate abnormal carbon data, etc., which affects the subsequent accurate measurement of carbon emissions. Summary of the Invention

[0003] This application aims to solve at least one of the technical problems existing in the related art. To this end, this application proposes a carbon data verification method and device for multiple data sources. The method can automatically separate normal carbon data from abnormal carbon data based on a cluster analysis algorithm, allowing carbon data from different data sources to be verified against each other, thereby improving the consistency and accuracy of carbon data from multiple data sources, as well as the accuracy of labeling and eliminating abnormal carbon data, thereby improving the accuracy of subsequent carbon emissions measurement.

[0004] In a first aspect, the present application provides a method for verifying carbon data from multiple data sources, the method comprising:

[0005] Acquire multiple carbon data within multiple target time periods, where the multiple carbon data are data from multiple different data sources;

[0006] Performing pairwise difference calculations on the carbon data from different data sources within the same target period to obtain a difference matrix;

[0007] Cluster analysis is performed on the difference matrix to obtain a verification result; the verification result includes normal carbon data and abnormal carbon data.

[0008] According to the multi-data source carbon data verification method of the present application, by obtaining multiple carbon data from multiple different data sources within multiple target time periods, and performing pairwise difference calculations on the carbon data from different data sources within the same target time period to obtain a difference matrix, and then performing cluster analysis on the difference matrix to obtain a verification result including normal carbon data and abnormal carbon data, the comparison of carbon data from multiple data sources with data deviations due to different units and calculation methods within each data source can be converted into a comparison of pairwise differences, reducing the influence of the dimension and order of magnitude of the data itself, and improving the intuitiveness of the normal or abnormal conditions of the carbon data from different data sources. In addition, the automatic division of normal carbon data and abnormal carbon data can be achieved based on the cluster analysis algorithm, reducing subjective human intervention and labor costs, so that carbon data from different data sources can be verified with each other, and the accuracy of the verification results can be improved. Therefore, based on the more accurate verification results, the abnormal carbon data can be subsequently labeled and eliminated, and the consistency and accuracy of the carbon data from multiple data sources can be accurately verified, thereby improving the accuracy of the subsequent carbon emissions measurement.

[0009] According to one embodiment of the present application, performing cluster analysis on the difference matrix to obtain a verification result includes:

[0010] The DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix to obtain the verification result.

[0011] According to one embodiment of the present application, the DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix to obtain the verification result, including:

[0012] The domain radius and the minimum number of samples in the DBSCAN clustering algorithm are adjusted, and cluster analysis is performed on the difference matrix to obtain the verification result.

[0013] According to one embodiment of the present application, the obtaining of multiple carbon data within multiple target time periods, wherein the multiple carbon data are data from multiple different data sources, includes:

[0014] Acquire multiple raw coal quality data and / or multiple raw coal quantity data within the multiple target time periods, where the multiple raw coal quality data and / or the multiple raw coal quantity data are data from multiple different data sources;

[0015] Based on a data conversion algorithm corresponding to the data category, data conversion is performed on the multiple coal quality original data and / or the multiple coal quantity original data to generate the multiple carbon data.

[0016] According to one embodiment of the present application, the data conversion algorithm based on the data category corresponding to the data conversion is performed on the multiple coal quality raw data and / or the multiple coal quantity raw data to generate the multiple carbon data, including:

[0017] Calculating and obtaining a plurality of coal quality data based on the calorific value data and the coal consumption data in each of the coal quality original data;

[0018] Unit conversion is performed on each of the original coal quantity data to obtain a plurality of coal quantity data.

[0019] According to one embodiment of the present application, after performing cluster analysis on the difference matrix to obtain a verification result, the method further includes:

[0020] Based on the verification result, consistency verification is performed on the plurality of carbon data, and / or abnormal carbon data is eliminated from the plurality of carbon data.

[0021] In a second aspect, the present application provides a carbon data verification device for multiple data sources, the device comprising:

[0022] A first processing module is configured to obtain a plurality of carbon data within a plurality of target time periods, wherein the plurality of carbon data are data from a plurality of different data sources;

[0023] A second processing module is configured to perform pairwise difference calculation on the carbon data from different data sources within the same target period to obtain a difference matrix;

[0024] The third processing module is used to perform cluster analysis on the difference matrix to obtain a verification result; the verification result includes normal carbon data and abnormal carbon data.

[0025] According to the multi-data source carbon data verification device of the present application, by obtaining multiple carbon data from multiple different data sources within multiple target time periods, and performing pairwise difference calculations on the carbon data from different data sources within the same target time period to obtain a difference matrix, and then performing cluster analysis on the difference matrix to obtain a verification result including normal carbon data and abnormal carbon data, the comparison of carbon data from multiple data sources with data deviations due to different units and calculation methods within each data source can be converted into a comparison of pairwise differences, reducing the influence of the dimension and order of magnitude of the data itself, and improving the intuitiveness of the normal or abnormal conditions of the carbon data from different data sources themselves. In addition, the automatic division of normal carbon data and abnormal carbon data can be achieved based on the cluster analysis algorithm, reducing subjective human intervention and labor costs, so that carbon data from different data sources can be verified with each other, and the accuracy of the verification results can be improved. Therefore, based on more accurate verification results, abnormal carbon data can be marked and eliminated, and the consistency and accuracy of carbon data from multiple data sources can be accurately verified, thereby improving the accuracy of subsequent carbon emissions measurement.

[0026] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for verifying carbon data from multiple data sources as described in the first aspect above is implemented.

[0027] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the carbon data verification method for multiple data sources as described in the first aspect above.

[0028] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the carbon data verification method for multiple data sources as described in the first aspect above.

[0029] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects:

[0030] By obtaining multiple carbon data from multiple different data sources within multiple target time periods, and performing pairwise difference calculations on the carbon data from different data sources within the same target time period to obtain a difference matrix, and then performing cluster analysis on the difference matrix to obtain verification results including normal carbon data and abnormal carbon data, the comparison of carbon data from multiple data sources with data deviations due to different units and calculation methods within each data source can be converted into a comparison of pairwise differences, reducing the influence of the dimension and order of magnitude of the data itself, and improving the intuitiveness of the normal or abnormal conditions of carbon data from different data sources. In addition, the automatic division of normal carbon data and abnormal carbon data can be achieved based on the cluster analysis algorithm, reducing subjective human intervention and labor costs, allowing carbon data from different data sources to be verified with each other, and improving the accuracy of the verification results. This will facilitate the subsequent labeling and elimination of abnormal carbon data based on more accurate verification results, as well as the precise verification of the consistency and accuracy of carbon data from multiple data sources, thereby improving the accuracy of subsequent carbon emissions measurement.

[0031] Furthermore, by adopting the DBSCAN clustering algorithm to perform cluster analysis on the difference matrix and obtain the verification results, anomaly detection based on unsupervised learning methods can be realized without presetting the outlier threshold, reducing human intervention, reducing the possibility of human misjudgment, further improving the accuracy of the verification results, and making the verification method applicable to nonlinear and non-uniformly distributed data, thereby improving the applicability of the verification method.

[0032] Furthermore, by calculating multiple coal quality data based on the calorific value data and coal consumption data in each coal quality original data, and performing unit conversion on each coal quantity original data to obtain multiple coal quantity data, the coal quality original data and coal quantity original data from multiple different data sources can be uniformly converted to obtain more standardized carbon data, so that the carbon data from different data sources can be compared more accurately in the future, thereby further improving the accuracy and reliability of the verification results.

[0033] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0035] Figure 1 This is one of the flow charts of the carbon data verification method for multiple data sources provided in the embodiment of the present application;

[0036] Figure 2 This is the second flow chart of the carbon data verification method for multiple data sources provided in an embodiment of the present application;

[0037] Figure 3 This is a schematic structural diagram of a carbon data verification device with multiple data sources provided in an embodiment of the present application;

[0038] Figure 4 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0040] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0041] The following, in conjunction with the accompanying drawings, describes in detail the multi-data source carbon data verification method, multi-data source carbon data verification device, electronic device, and readable storage medium provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0042] The carbon data verification method for multiple data sources can be applied to a terminal, and can be specifically executed by hardware or software in the terminal.

[0043] The terminal includes but is not limited to portable communication devices such as mobile phones or tablet computers. It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer.

[0044] The carbon data verification method for multiple data sources provided in the embodiments of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the carbon data verification method for multiple data sources. The electronic devices mentioned in the embodiments of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The carbon data verification method for multiple data sources provided in the embodiments of the present application is described below using electronic devices as an example of the execution entity.

[0045] like Figure 1 As shown, the carbon data verification method for multiple data sources includes: step 110, step 120 and step 130.

[0046] Step 110: Acquire multiple carbon data within multiple target time periods, where the multiple carbon data are data from multiple different data sources;

[0047] In this step, the target period can be any fixed time period.

[0048] For example, the target period can be 5 hours, one day, two days, one month, two months, or one year.

[0049] The types of carbon data may include coal quality (calorific value) data or coal quantity data.

[0050] The multiple carbon data within multiple target periods come from different data sources.

[0051] Among them, a target period includes multiple carbon data corresponding to multiple different data sources.

[0052] For example, when the target period is 1 month and multiple carbon data within 3 months are obtained from 3 different data sources, each month includes 3 carbon data, and each carbon data corresponds to one data source.

[0053] The data source can be government statistical data, enterprise-reported data, or third-party testing data.

[0054] In some embodiments, as Figure 2 As shown, the data sources may include data source A: greenhouse gas report, data source B: daily coal quantity and quality report, data source C: monthly report on coal quantity and power consumption, data source D: production and operation indicator report, and data source E: third-party agency inspection report.

[0055] In some embodiments, when the type of carbon data is coal quality data, the data source may include fossil fuel combustion emission tables, daily coal quality detection data of the coal entering the furnace, monthly comprehensive sample coal quality detection reports, monthly power plant production and operation reports, etc.; when the type of carbon data is coal quantity data, the data source may include fossil fuel combustion emission tables, daily coal quantity entering the furnace, monthly coal purchase and sales records, etc.

[0056] Step 120: performing pairwise difference calculations on carbon data from different data sources within the same target period to obtain a difference matrix;

[0057] In this step, it can be understood that pairwise difference calculations can be performed on a plurality of carbon data from different data sources within each target period, thereby obtaining a difference matrix.

[0058] For example, when the target period is 1 month, three carbon data from three different data sources are obtained within the target period. The three different data sources are data source A, data source B and data source C. The carbon data from different data sources are subjected to pairwise difference calculations, which can be the carbon data of data source A minus the carbon data of data source B, the carbon data of data source A minus the carbon data of data source C, and the carbon data of data source B minus the carbon data of data source C, to obtain the various differences within the target period. It can be understood that the order of calculating the differences in this example is from A to B and then to C. Of course, in other embodiments, pairwise difference calculations can also be performed based on other calculation orders, as long as the calculation order within each target period is consistent, and this is not limited here.

[0059] As can be seen from the above example, based on a certain pairwise difference calculation order, by performing pairwise difference calculations on carbon data from different data sources within the same target period, the various differences within the target period can be obtained.

[0060] In the actual implementation process, after performing pairwise difference calculations on the carbon data from different data sources within multiple target time periods, the corresponding differences within the multiple target time periods can be obtained, that is, a difference matrix can be obtained, where different rows of the difference matrix represent different target time periods, and different columns represent different data sources.

[0061] Taking the verification of coal quality data from three different data sources for a power plant within 12 months (each month is a target period), including the fossil fuel combustion emission table, the monthly power plant production and operation report, and the monthly comprehensive sample coal quality test report, as an example, the carbon data from different data sources in the same target period are calculated pairwise. The difference matrix obtained is shown in Table 1.

[0062] Step 130: Perform cluster analysis on the difference matrix to obtain a verification result.

[0063] In this step, the verification result includes normal carbon data and abnormal carbon data.

[0064] Among them, normal carbon data can be data with a small gap with other carbon data.

[0065] Abnormal carbon data may be data that differs significantly from other carbon data.

[0066] In the actual implementation process, cluster analysis is performed on the difference matrix to automatically divide normal carbon data and abnormal carbon data.

[0067] The cluster analysis may be performed based on any feasible clustering algorithm, such as a K-means clustering algorithm or a K-medoids clustering algorithm, which is not limited here.

[0068] During the research and development process, the inventors discovered that in the carbon emission measurement method, due to different units and calculation methods, there are certain differences in carbon data such as coal quality parameters and coal consumption from different data sources. It is impossible to accurately test the accuracy and consistency of coal quality and coal consumption from multiple data sources, or to eliminate abnormal carbon data, thereby affecting the accurate measurement of carbon emissions. In related technologies, carbon data anomaly detection mainly relies on manually set thresholds or rules (such as the 3σ principle), but for coal quality and coal quantity data, due to the multiple sources and large volatility of coal quality and coal quantity data, fixed thresholds are difficult to apply.

[0069] Table 1

[0070]

[0071] In this application, by obtaining multiple carbon data from multiple different data sources within multiple target time periods, and performing pairwise difference calculations on the carbon data from different data sources within the same target time period, a difference matrix is obtained. The comparison of carbon data from multiple data sources with data deviations due to different units and calculation methods within each data source can be converted into a pairwise difference comparison, so that carbon data from different data sources can be verified with each other, and the influence of the dimension and order of magnitude of the data itself can be reduced. The focus is on the differences between the data between each data source and other data sources, and the performance of normal carbon data and abnormal carbon data is enhanced, that is, the performance of abnormal carbon data is improved. The intuitiveness of the normal or abnormal situation of carbon data from the same data source; cluster analysis of the difference matrix can obtain more accurate verification results, including normal carbon data and abnormal carbon data; and the automatic division of normal carbon data and abnormal carbon data can be realized based on the cluster analysis algorithm, reducing the workload of manual comparison, reducing labor costs, improving overall efficiency, and reducing the subjective influence of manual rules, thereby improving the accuracy of the verification results, so that in the future, based on more accurate verification results, abnormal carbon data can be marked and eliminated, and the consistency and accuracy of carbon data from multiple data sources can be evaluated, thereby improving the accuracy of subsequent carbon emissions measurement.

[0072] According to the multi-data source carbon data verification method provided in the embodiment of the present application, by obtaining multiple carbon data from multiple different data sources within multiple target time periods, and performing pairwise difference calculations on the carbon data from different data sources within the same target time period to obtain a difference matrix, and then performing cluster analysis on the difference matrix to obtain a verification result including normal carbon data and abnormal carbon data, the comparison of carbon data from multiple data sources with data deviations due to different units and calculation methods within each data source can be converted into a pairwise difference comparison, thereby reducing the impact of the dimension and order of magnitude of the data itself, and improving the intuitiveness of the normal or abnormal conditions of the carbon data from different data sources. In addition, the automatic division of normal carbon data and abnormal carbon data can be achieved based on the cluster analysis algorithm, reducing subjective human intervention and labor costs, allowing carbon data from different data sources to be verified with each other, and improving the accuracy of the verification results. This facilitates the subsequent labeling and elimination of abnormal carbon data based on more accurate verification results, and the precise verification of the consistency and accuracy of carbon data from multiple data sources, thereby improving the accuracy of subsequent carbon emissions measurement.

[0073] In some embodiments, performing cluster analysis on the difference matrix to obtain a verification result may include:

[0074] The DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix to obtain the verification results.

[0075] In this embodiment, the DBSCAN clustering algorithm is a density-based spatial clustering algorithm that can identify clusters of arbitrary shapes and has good robustness to noise points.

[0076] In actual implementation, the DBSCAN clustering algorithm is a density-based clustering algorithm. Unlike partitioning and hierarchical clustering methods, the DBSCAN clustering algorithm can define a cluster as the largest set of density-connected points. It can divide areas with sufficiently high density into clusters and can find clusters of arbitrary shapes in noisy spatial databases.

[0077] It can be understood that when the DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix, the DBSCAN clustering algorithm can automatically divide the data in the difference matrix that has a smaller gap with other data into a cluster, and divide the data that has a larger gap with other data into a cluster, wherein each cluster can include data at any spatial position in the difference matrix, thereby realizing the judgment of the normal or abnormal situation of the carbon data of a certain target period and a certain data source represented by the difference corresponding to any spatial position of the difference matrix.

[0078] Continuing with the verification of coal quality data from three different data sources for a power plant within 12 months (each month is a target period), including the fossil fuel combustion emission table, the monthly power plant production and operation report, and the monthly comprehensive sample coal quality test report, the pairwise difference calculation of the carbon data from different data sources within the same target period is shown in Table 1. Among them, due to the large deviation between the power plant's December data and the other source data, the DBSCAN clustering algorithm automatically identifies it as abnormal carbon data.

[0079] According to the carbon data verification method for multiple data sources provided in the embodiment of the present application, by adopting the DBSCAN clustering algorithm, the difference matrix is clustered and analyzed to obtain the verification results. This can realize anomaly detection based on an unsupervised learning method, without the need to preset an outlier threshold, reducing human intervention, reducing the possibility of human misjudgment, further improving the accuracy of the verification results, and making the verification method applicable to nonlinear and non-uniformly distributed data, thereby improving the applicability of the verification method.

[0080] In some embodiments, a DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix to obtain a verification result, which may include:

[0081] The domain radius and the minimum number of samples in the DBSCAN clustering algorithm were adjusted, and cluster analysis was performed on the difference matrix to obtain the verification results.

[0082] In this embodiment, the DBSCAN clustering algorithm can define core points by adjusting the neighborhood radius (eps) and the minimum number of samples (MinPts), wherein if the number of points contained in the eps of a point is not less than MinPts, then the point is considered to be a core point.

[0083] In the actual execution process, the DBSCAN clustering algorithm can start from the core point and form a set of points with the largest density connection by continuously searching and adding points that are directly density-reachable, that is, a cluster. In the execution process of the algorithm, new core points will be continuously searched and new clusters will be formed until all points have been visited.

[0084] In some embodiments, a suitable neighborhood radius can be selected through statistical analysis of carbon data distribution, and the minimum number of samples can be adjusted according to the amount of carbon data. That is, the setting of the neighborhood radius and the minimum number of samples can be specifically determined based on the actual carbon data distribution and the amount of carbon data, and is not limited here.

[0085] According to the carbon data verification method for multiple data sources provided in the embodiment of the present application, by adjusting the domain radius and the minimum number of samples in the DBSCAN clustering algorithm, the difference matrix is clustered and analyzed to obtain the verification results. This allows the DBSCAN clustering algorithm to automatically adapt to the actual situation of carbon data distribution and carbon data volume, further improving the accuracy and reliability of the verification results.

[0086] In some embodiments, obtaining multiple carbon data within multiple target time periods, where the multiple carbon data are data from multiple different data sources, may include:

[0087] Acquire multiple raw coal quality data and / or multiple raw coal quantity data within multiple target time periods, where the multiple raw coal quality data and / or multiple raw coal quantity data are data from multiple different data sources;

[0088] Based on the data conversion algorithm corresponding to the data category, data conversion is performed on multiple coal quality original data and / or multiple coal quantity original data to generate multiple carbon data.

[0089] In this embodiment, the data category includes coal quality raw data or coal quantity raw data.

[0090] Among them, the data source corresponding to the coal quality raw data can be consistent with the case where the carbon data is coal quality data, and the data source corresponding to the coal quantity raw data can be consistent with the case where the carbon data is coal quantity data, which will not be elaborated here; the difference is that the coal quality raw data or the coal quantity raw data is the original data that has not undergone any processing, among which the coal quality raw data can include calorific value data and coal consumption data, etc., and the units of the coal quantity raw data from different data sources may be different.

[0091] It should be noted that, based on the data conversion algorithm corresponding to the data category, after data conversion is performed on multiple coal quality raw data, the category of the multiple carbon data generated is coal quality data; similarly, based on the data conversion algorithm corresponding to the data category, data conversion is performed on multiple coal quantity raw data, and the category of the multiple carbon data generated is coal quantity data; in addition, at the same time, based on the data conversion algorithm corresponding to the data category, data conversion is performed on multiple coal quality raw data and / or multiple coal quantity raw data, and the categories of the multiple carbon data generated include coal quality data and coal quantity data.

[0092] Among them, when the category of carbon data includes coal quality data and coal quantity data, the coal quality data and coal quantity data from multiple data sources in multiple target time periods are separately processed for subsequent processing, that is, the coal quality data and coal quantity data from different data sources in the same target time period are calculated pairwise to obtain the difference matrices corresponding to the coal quality data and coal quantity data, and cluster analysis is performed on the difference matrices corresponding to the coal quality data and coal quantity data to obtain the verification results corresponding to the coal quality data and coal quantity data, so as to perform subsequent consistency verification and other processing on the coal quality data and coal quantity data.

[0093] In the actual implementation process, for the same power plant, the raw coal quality data and coal quantity data from different data sources may have data deviations due to different data source units and calculation methods. After the raw coal quality data and coal quantity data from different data sources are converted based on the data conversion algorithm corresponding to the data category, the data deviations between different data sources can be reduced.

[0094] According to the carbon data verification method for multiple data sources provided in an embodiment of the present application, multiple coal quality raw data and / or multiple coal quantity raw data within multiple target time periods are obtained, and the multiple coal quality raw data and / or multiple coal quantity raw data are data from multiple different data sources. Based on the data conversion algorithm corresponding to the data category, the multiple coal quality raw data and / or multiple coal quantity raw data are converted to generate multiple carbon data. This can reduce the data deviation between the multiple carbon data generated from different data sources, thereby improving the accuracy and reliability of subsequent verification of multiple carbon data based on different data sources for the same power plant.

[0095] In some embodiments, based on a data conversion algorithm corresponding to a data category, performing data conversion on a plurality of raw coal quality data and / or a plurality of raw coal quantity data to generate a plurality of carbon data may include:

[0096] Based on the calorific value data and coal consumption data in the original data of each coal quality, multiple coal quality data are calculated;

[0097] The units of the original data of each coal quantity are converted to obtain multiple coal quantity data.

[0098] In this embodiment, the raw coal quality data may include a plurality of calorific value data and a plurality of coal consumption data.

[0099] During the actual implementation process, multiple coal quality data can be calculated based on the calorific value data and coal consumption data in the original data of each coal quality within the target period.

[0100] In some embodiments, coal quality data may be determined by the following formula:

[0101] Q=Q1 / E

[0102] Among them, Q is the coal quality data (weighted average calorific value), Q1 is the sum of the calorific value data in the original coal quality data, and E is the sum of the coal consumption in the original coal quality data.

[0103] In some embodiments, the units of the raw data of coal quantities are converted to a unified time (t) unit.

[0104] According to the carbon data verification method for multiple data sources provided in the embodiment of the present application, multiple coal quality data are calculated based on the calorific value data and coal consumption data in each coal quality original data, and the unit of each coal quantity original data is converted to obtain multiple coal quantity data. The coal quality original data and coal quantity original data from multiple different data sources can be uniformly converted to obtain more standardized carbon data, so that the carbon data from different data sources can be compared more accurately in the future, thereby further improving the accuracy and reliability of the verification results.

[0105] like Figure 2 As shown, in some embodiments, before performing data conversion on a plurality of raw coal quality data and / or a plurality of raw coal quantity data to generate a plurality of carbon data, the method may further include:

[0106] Standardization processing is performed on multiple coal quality raw data and / or multiple coal quantity raw data.

[0107] In this embodiment, the standardization process may include processing missing values and removing unreasonable values.

[0108] Among them, missing values can be 0 values or null values; unreasonable values can be values that are greatly different from other data.

[0109] In the actual implementation process, any feasible method can be used to handle missing values and remove unreasonable values, for example, replacing missing values or unreasonable values with the average value of other reasonable data.

[0110] According to the carbon data verification method for multiple data sources provided in the embodiment of the present application, by performing data conversion on multiple coal quality original data and / or multiple coal quantity original data, and standardizing the multiple coal quality original data and / or multiple coal quantity original data before generating multiple carbon data, the reliability of the coal quality original data and the coal quantity original data can be improved, and the impact of missing values and unreasonable values on subsequent processing can be reduced.

[0111] In some embodiments, after performing cluster analysis on the difference matrix to obtain a verification result, the method may further include:

[0112] Based on the verification result, consistency verification is performed on the multiple carbon data, and / or abnormal carbon data is eliminated from the multiple carbon data.

[0113] In this embodiment, the consistency check performed on the plurality of carbon data may be a consistency check performed on the same carbon data from different data sources.

[0114] During the actual implementation process, if the carbon data for the same target period from different data sources are all normal carbon data, it is considered that the carbon data for the same target period from different data sources can accurately represent the coal quality data and / or coal quantity data of the power plant during the target period.

[0115] It can be understood that when the carbon data for the same target period from different data sources include abnormal carbon data, it is considered that the data source corresponding to the abnormal carbon data has measurement errors, false alarms or misreporting, and the data source can be further investigated to obtain the cause of the abnormal carbon data, or the data source can be reminded to correct the false alarms or misreporting.

[0116] Eliminating abnormal carbon data from multiple carbon data can enable the measurement of subsequent carbon emissions based on normal carbon data, thereby improving the accuracy and reliability of carbon emissions measurement.

[0117] According to the carbon data verification method for multiple data sources provided in the embodiments of the present application, by performing consistency verification on multiple carbon data based on the verification results, and / or eliminating abnormal carbon data from multiple carbon data, it is possible to investigate and remind data sources with false alarms or erroneous reports in different data sources to correct the carbon data; and the other normal carbon data after eliminating the abnormal carbon data can be used to measure the subsequent carbon emissions to improve the accuracy and reliability of the subsequent carbon emissions measurement.

[0118] The multi-data source carbon data verification method provided in the embodiments of the present application can be executed by a multi-data source carbon data verification device. In the embodiments of the present application, the multi-data source carbon data verification device executing the multi-data source carbon data verification method is used as an example to illustrate the multi-data source carbon data verification device provided in the embodiments of the present application.

[0119] The embodiment of the present application also provides a carbon data verification device for multiple data sources.

[0120] like Figure 3 As shown, the carbon data verification device for multiple data sources includes: a first processing module 310 , a second processing module 320 and a third processing module 330 .

[0121] The first processing module 310 is configured to obtain a plurality of carbon data within a plurality of target time periods, where the plurality of carbon data are data from a plurality of different data sources;

[0122] The second processing module 320 is used to perform pairwise difference calculation on carbon data from different data sources within the same target period to obtain a difference matrix;

[0123] The third processing module 330 is used to perform cluster analysis on the difference matrix to obtain a verification result; the verification result includes normal carbon data and abnormal carbon data.

[0124] According to the multi-data source carbon data verification device provided in the embodiment of the present application, by obtaining multiple carbon data from multiple different data sources within multiple target time periods, and performing pairwise difference calculations on the carbon data from different data sources within the same target time period to obtain a difference matrix, and then performing cluster analysis on the difference matrix to obtain a verification result including normal carbon data and abnormal carbon data, the comparison of carbon data from multiple data sources with data deviations due to different units and calculation methods within each data source can be converted into a comparison of pairwise differences, thereby reducing the impact of the dimension and order of magnitude of the data itself, and improving the intuitiveness of the normal or abnormal conditions of the carbon data from different data sources. In addition, the automatic division of normal carbon data and abnormal carbon data can be achieved based on the cluster analysis algorithm, reducing subjective human intervention and labor costs, allowing carbon data from different data sources to be verified with each other, and improving the accuracy of the verification results. Therefore, based on the more accurate verification results, abnormal carbon data can be subsequently labeled and eliminated, and the consistency and accuracy of carbon data from multiple data sources can be accurately verified, thereby improving the accuracy of subsequent carbon emissions measurement.

[0125] In some embodiments, the first processing module 310 may also be used to:

[0126] Acquire multiple raw coal quality data and / or multiple raw coal quantity data within multiple target time periods, where the multiple raw coal quality data and / or multiple raw coal quantity data are data from multiple different data sources;

[0127] Based on the data conversion algorithm corresponding to the data category, data conversion is performed on multiple coal quality original data and / or multiple coal quantity original data to generate multiple carbon data.

[0128] In some embodiments, the first processing module 310 may also be used to:

[0129] Based on the calorific value data and coal consumption data in the original data of each coal quality, multiple coal quality data are calculated;

[0130] The units of the original data of each coal quantity are converted to obtain multiple coal quantity data.

[0131] In some embodiments, the third processing module 330 may also be used to:

[0132] The DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix to obtain the verification results.

[0133] In some embodiments, the third processing module 330 may also be used to:

[0134] The domain radius and the minimum number of samples in the DBSCAN clustering algorithm were adjusted, and cluster analysis was performed on the difference matrix to obtain the verification results.

[0135] In some embodiments, the apparatus may further include a fourth processing module configured to:

[0136] After performing cluster analysis on the difference matrix and obtaining verification results, consistency verification is performed on the plurality of carbon data based on the verification results, and / or abnormal carbon data is eliminated from the plurality of carbon data.

[0137] The carbon data verification device for multiple data sources in the embodiments of the present application may be an electronic device or a component of an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other device other than a terminal.

[0138] The multi-data source carbon data verification device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0139] The multi-data source carbon data verification device provided in the embodiment of the present application can achieve Figures 1 to 2 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0140] In some embodiments, as Figure 4 As shown, an embodiment of the present application also provides an electronic device 400, including a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the program is executed by the processor 401, each process of the above-mentioned multi-data source carbon data verification method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0141] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0142] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the various processes of the above-mentioned carbon data verification method embodiment for multiple data sources and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0143] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0144] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned carbon data verification method for multiple data sources when executed by a processor.

[0145] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0146] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned multi-data source carbon data verification method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0147] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0148] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0149] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0150] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0151] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0152] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A carbon data verification method for multiple data sources, characterized in that: include: Acquire multiple carbon data within multiple target time periods, where the multiple carbon data are data from multiple different data sources; Performing pairwise difference calculations on the carbon data from different data sources within the same target period to obtain a difference matrix; Performing cluster analysis on the difference matrix to obtain a verification result; The verification result includes normal carbon data and abnormal carbon data.

2. The carbon data verification method for multiple data sources according to claim 1, characterized in that: The performing cluster analysis on the difference matrix to obtain a verification result includes: The DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix to obtain the verification result.

3. The carbon data verification method for multiple data sources according to claim 2, characterized in that: The DBSCAN clustering algorithm is used to perform cluster analysis on the difference matrix to obtain the verification result, including: The domain radius and the minimum number of samples in the DBSCAN clustering algorithm are adjusted, and cluster analysis is performed on the difference matrix to obtain the verification result.

4. The carbon data verification method for multiple data sources according to any one of claims 1 to 3, characterized in that: The obtaining of a plurality of carbon data within a plurality of target time periods, wherein the plurality of carbon data is data from a plurality of different data sources, includes: Acquire multiple raw coal quality data and / or multiple raw coal quantity data within the multiple target time periods, where the multiple raw coal quality data and / or the multiple raw coal quantity data are data from multiple different data sources; Based on a data conversion algorithm corresponding to the data category, data conversion is performed on the multiple coal quality original data and / or the multiple coal quantity original data to generate the multiple carbon data.

5. The carbon data verification method for multiple data sources according to claim 4, characterized in that: The data conversion algorithm corresponding to the data category is used to convert the plurality of raw coal quality data and / or the plurality of raw coal quantity data to generate the plurality of carbon data, including: Calculating and obtaining a plurality of coal quality data based on the calorific value data and the coal consumption data in each of the coal quality original data; Unit conversion is performed on each of the original coal quantity data to obtain a plurality of coal quantity data.

6. The carbon data verification method for multiple data sources according to any one of claims 1 to 3, characterized in that: After performing cluster analysis on the difference matrix to obtain a verification result, the method further includes: Based on the verification result, consistency verification is performed on the plurality of carbon data, and / or abnormal carbon data is eliminated from the plurality of carbon data.

7. A carbon data verification device with multiple data sources, characterized in that: include: A first processing module is configured to obtain a plurality of carbon data within a plurality of target time periods, wherein the plurality of carbon data are data from a plurality of different data sources; A second processing module is configured to perform pairwise difference calculation on the carbon data from different data sources within the same target period to obtain a difference matrix; A third processing module is used to perform cluster analysis on the difference matrix to obtain a verification result; The verification result includes normal carbon data and abnormal carbon data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the carbon data verification method for multiple data sources according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for verifying carbon data from multiple data sources according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for verifying carbon data from multiple data sources according to any one of claims 1 to 6 is implemented.

Images