A carbon emission monitoring method based on big data analysis
By using a carbon emission monitoring method based on big data analysis and combining it with a data fusion system based on deep learning, the problems of data silos from multiple sources, inefficient manual calculation, and difficulties in data sharing have been solved. This has enabled accurate carbon emission calculation and scientific early warning for management, thereby improving the accuracy of carbon emission monitoring and management efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- EASTERN LIAONING UNIV
- Filing Date
- 2026-05-08
- Publication Date
- 2026-08-04
AI Technical Summary
Existing carbon emission monitoring methods suffer from problems such as data silos from multiple sources, low efficiency of manual statistics, lack of big data analysis capabilities, lag in anomaly identification, difficulty in data sharing, and difficulty in quantifying control performance, which cannot meet the needs of modern low-carbon management.
By employing big data analytics, through multi-channel data collection, standardized processing, in-depth analysis, anomaly identification and early warning, and performance evaluation, we can achieve accurate carbon emission accounting and cross-platform data sharing. Combined with a deep learning-based heterogeneous environmental monitoring data fusion system, we can break down barriers between multiple systems and improve management collaboration.
It has improved the accuracy and timeliness of carbon emission monitoring, upgraded its scientific nature and management efficiency, shifted towards early warning, and helped to make low-carbon governance decisions more scientific.
Smart Images
Figure CN122509933A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of carbon emission monitoring technology, specifically a carbon emission monitoring method based on big data analysis. Background Technology
[0002] Existing carbon emission monitoring methods have significant shortcomings: First, multi-source carbon emission data are scattered and in inconsistent formats, forming data silos that cannot be unified and integrated; second, they rely on manual statistical calculations, which are inefficient and prone to errors, making real-time monitoring impossible; third, they lack the ability to conduct in-depth big data analysis, making it difficult to uncover carbon emission trends and related influencing factors; fourth, abnormal carbon emissions cannot be automatically identified and traced, resulting in delayed risk warnings; fifth, the performance of carbon emission control cannot be quantitatively assessed, leading to a lack of data support for management decisions; and sixth, the monitoring system is poorly integrated with environmental and government management systems, making data sharing difficult and failing to meet the needs of modern low-carbon management. Therefore, it is necessary to design a carbon emission monitoring method based on big data analysis. Summary of the Invention: The purpose of this invention is to provide a carbon emission monitoring method based on big data analysis to solve the problems mentioned in the background art.
[0003] To address the above problems, the present invention provides a technical solution: A carbon emission monitoring method based on big data analysis includes the following steps: Step S101: Access carbon emission related data from multiple channels, complete data source adaptation and real-time collection, and temporarily cache and store the raw data; Step S102: Perform format normalization, time-series calibration, and anomaly screening on the collected carbon emission data to achieve data standardization and normalization processing; Step S103: Utilize big data algorithms to analyze carbon emission trends and related factors, and complete the accurate calculation of total carbon emissions; Step S104: Determine the carbon emission data as abnormal according to the standard, locate the source of the abnormality, and complete the classification and labeling of the abnormality type; Step S105: Calculate the various performance indicators for carbon emission control, assess the management level, and analyze the optimization direction for performance improvement; Step S106: Set the carbon emission early warning threshold. When the data exceeds the limit, an early warning will be automatically triggered and instructions will be pushed to the control terminal. Step S107: Classify and store the data from the entire process of carbon emission collection, analysis, and evaluation to ensure data integrity and traceability; Step S108: Automatically generate standardized carbon emission monitoring reports based on monitoring and analysis data to support management decisions; Step S109: Configure system access and operation permissions, control the scope of data viewing and use, and ensure the security of monitoring data; Step S110: Complete the multi-system connection through interface adaptation and protocol conversion to achieve cross-platform synchronous sharing of carbon emission data.
[0004] A heterogeneous environmental monitoring data fusion system based on deep learning, applied to the aforementioned carbon emission monitoring method based on big data analysis, includes a multi-source carbon emission data acquisition module, a carbon emission data standardization module, a big data carbon emission analysis module, a carbon emission anomaly identification module, a carbon emission performance evaluation module, a carbon emission early warning and control module, a carbon emission data storage module, a carbon emission report generation module, a system access management module, and a multi-system interface adaptation module. The multi-source carbon emission data acquisition module and the carbon emission data standardization module are connected; the carbon emission data standardization module and the big data carbon emission analysis module are connected; and the big data carbon emission analysis module and the carbon emission anomaly identification module are connected. The system is connected to the carbon emission performance evaluation module, the carbon emission early warning and control module, the carbon emission anomaly identification module, the carbon emission early warning and control module, the carbon emission early warning and control module, the carbon emission report generation module, the big data carbon emission analysis module, the carbon emission data storage module, and the multi-system interface adaptation module. The multi-system interface adaptation module includes an interface adaptation unit, a data synchronization unit, and a protocol conversion unit. This module breaks down data barriers between multiple systems, enables data sharing, adapts to the smart environmental protection management system, and improves control coordination. The multi-source carbon emission data acquisition module and the system permission management module are also connected.
[0005] Preferably, the multi-source carbon emission data acquisition module includes a data source adaptation unit, a real-time acquisition unit, and a data caching unit, wherein the data source adaptation unit and the real-time acquisition unit are connected, and the real-time acquisition unit and the data caching unit are connected. The data source adaptation unit is used to be compatible with various carbon emission data access methods; the real-time acquisition unit is used to synchronously acquire dynamic carbon emission data; and the data caching unit is used to temporarily store the acquired raw carbon emission data.
[0006] Preferably, the carbon emission data standardization module includes a format normalization unit, a time series calibration unit, and an anomaly screening unit, wherein the format normalization unit and the time series calibration unit are connected, and the time series calibration unit and the anomaly screening unit are connected. The format normalization unit is used to unify the carbon emission data storage format; the timing calibration unit is used to align the carbon emission data acquisition time; and the anomaly removal unit is used to remove invalid carbon emission data.
[0007] Preferably, the big data carbon emission analysis module includes a trend analysis unit, a correlation analysis unit, and a quantitative accounting unit, wherein the trend analysis unit and the correlation analysis unit are connected, and the correlation analysis unit and the quantitative accounting unit are connected. The trend analysis unit is used to uncover patterns in carbon emission data changes; the correlation analysis unit is used to analyze the relationships between factors influencing carbon emissions; and the quantitative calculation unit is used to accurately calculate the total amount of carbon emissions.
[0008] Preferably, the carbon emission anomaly identification module includes an anomaly determination unit, a source tracing and positioning unit, and a type marking unit, wherein the anomaly determination unit and the source tracing and positioning unit are connected, and the source tracing and positioning unit and the type marking unit are connected. The anomaly determination unit is used to identify abnormal fluctuations in carbon emission data; the source tracing and positioning unit is used to locate the source of the carbon emission anomaly; and the type marking unit is used to mark the category to which the carbon emission anomaly belongs.
[0009] Preferably, the carbon emission performance evaluation module includes an indicator calculation unit, a rating unit, and an optimization analysis unit, wherein the indicator calculation unit and the rating unit are connected, and the rating unit and the optimization analysis unit are connected. The indicator calculation unit is used to calculate carbon emission control performance indicators; the rating unit is used to rate carbon emission management performance levels; and the optimization analysis unit is used to analyze directions for performance improvement and optimization.
[0010] Preferably, the carbon emission early warning and control module includes a threshold setting unit, an early warning triggering unit, and an instruction push unit, wherein the threshold setting unit and the early warning triggering unit are connected, and the early warning triggering unit and the instruction push unit are connected. The threshold setting unit is used to set the carbon emission warning threshold; the warning triggering unit is used to automatically activate the warning when the threshold is exceeded; and the instruction push unit is used to push the warning instruction to the control terminal.
[0011] The beneficial effects of this invention are as follows: This invention relates to a carbon emission monitoring method based on big data analysis, which features multi-source carbon emission data integration, standardized processing, in-depth big data analysis, intelligent anomaly identification, performance quantitative evaluation, and proactive early warning and control. In practical application, compared with traditional carbon emission monitoring methods based on big data analysis, this carbon emission monitoring method based on big data analysis has the following beneficial effects: First, the accuracy and timeliness of carbon emission monitoring have been significantly improved. Multi-source data collection and standardized processing break down data silos, and the big data analysis module enables accurate carbon emission accounting and trend mining, completely solving the problems of fragmented monitoring data and delayed accounting in traditional monitoring. Secondly, the scientific nature and management efficiency of carbon emission control have been comprehensively upgraded. Automatic anomaly identification, proactive early warning, and quantitative performance evaluation align with administrative management needs, shifting carbon emission control from post-event handling to pre-event early warning, and contributing to more scientific decision-making in low-carbon governance. Attached image description: For ease of explanation, the present invention will be described in detail below with reference to specific embodiments and accompanying drawings.
[0012] Figure 1 This is a diagram illustrating the working steps of the present invention; Figure 2 This is a system schematic diagram of the present invention; Figure 3 For the present invention Figure 2 Schematic diagram of the multi-source carbon emission data acquisition module; Figure 4 For the present invention Figure 2 Schematic diagram of the carbon emission data standardization module; Figure 5 For the present invention Figure 2 Schematic diagram of the big data carbon emission analysis module; Figure 6 For the present invention Figure 2 Schematic diagram of the carbon emission anomaly identification module; Figure 7 For the present invention Figure 2 Schematic diagram of the carbon emission performance evaluation module; Figure 8 For the present invention Figure 2 Schematic diagram of the carbon emission early warning and control module.
[0013] The diagram shows: 1. Multi-source carbon emission data acquisition module; 2. Carbon emission data standardization module; 3. Big data carbon emission analysis module; 4. Carbon emission anomaly identification module; 5. Carbon emission performance evaluation module; 6. Carbon emission early warning and control module; 7. Carbon emission data storage module; 8. Carbon emission report generation module; 9. System permission management module; 10. Multi-system interface adaptation module; 111. Data source adaptation unit; 112. Real-time acquisition unit; 113. Data caching unit; 221. Format normalization unit; 222. Time series calibration unit; 223. Anomaly screening unit; 331. Trend analysis unit; 332. Correlation analysis unit; 333. Quantitative accounting unit; 441. Anomaly judgment unit; 442. Source tracing and positioning unit; 443. Type marking unit; 551. Indicator accounting unit; 552. Level assessment unit; 553. Optimization analysis unit; 661. Threshold setting unit; 662. Early warning triggering unit; 663. Command push unit. Detailed implementation method: like Figures 1-8 As shown, the specific implementation adopts the following technical solution: Example: A carbon emission monitoring method based on big data analysis includes the following steps: Step S101: Access carbon emission related data from multiple channels, complete data source adaptation and real-time collection, and temporarily cache and store the raw data; Step S102: Perform format normalization, time-series calibration, and anomaly screening on the collected carbon emission data to achieve data standardization and normalization processing; Step S103: Utilize big data algorithms to analyze carbon emission trends and related factors, and complete the accurate calculation of total carbon emissions; Step S104: Determine the carbon emission data as abnormal according to the standard, locate the source of the abnormality, and complete the classification and labeling of the abnormality type; Step S105: Calculate the various performance indicators for carbon emission control, assess the management level, and analyze the optimization direction for performance improvement; Step S106: Set the carbon emission early warning threshold. When the data exceeds the limit, an early warning will be automatically triggered and instructions will be pushed to the control terminal. Step S107: Classify and store the data from the entire process of carbon emission collection, analysis, and evaluation to ensure data integrity and traceability; Step S108: Automatically generate standardized carbon emission monitoring reports based on monitoring and analysis data to support management decisions; Step S109: Configure system access and operation permissions, control the scope of data viewing and use, and ensure the security of monitoring data; Step S110: Complete the multi-system connection through interface adaptation and protocol conversion to achieve cross-platform synchronous sharing of carbon emission data.
[0014] A heterogeneous environmental monitoring data fusion system based on deep learning, applied to the aforementioned carbon emission monitoring method based on big data analysis, includes a multi-source carbon emission data acquisition module 1, a carbon emission data standardization module 2, a big data carbon emission analysis module 3, a carbon emission anomaly identification module 4, a carbon emission performance evaluation module 5, a carbon emission early warning and control module 6, a carbon emission data storage module 7, a carbon emission report generation module 8, a system access control module 9, and a multi-system interface adaptation module 10. The multi-source carbon emission data acquisition module 1 and the carbon emission data standardization module 2 are connected; the carbon emission data standardization module 2 and the big data carbon emission analysis module 3 are connected; the big data carbon emission analysis module 3 and the carbon emission anomaly identification module 4 are connected; and the big data carbon emission analysis module 3 and the carbon emission anomaly identification module 4 are connected. The carbon emission performance evaluation module 5 is connected, the carbon emission early warning and control module 6 is connected, the carbon emission anomaly identification module 4 is connected, the carbon emission early warning and control module 6 is connected, the carbon emission early warning and control module 6 is connected, the carbon emission report generation module 8 is connected, the big data carbon emission analysis module 3 is connected, the carbon emission data storage module 7 is connected, the carbon emission data storage module 7 is connected, and the multi-system docking and adaptation module 10 is connected. The multi-system docking and adaptation module 10 includes an interface adaptation unit, a data synchronization unit, and a protocol conversion unit. The multi-system docking and adaptation module 10 breaks down data barriers between multiple systems, realizes data sharing, adapts to the smart environmental protection management system, and improves management and control coordination. The multi-source carbon emission data acquisition module 1 and the system permission management module 9 are connected.
[0015] The multi-source carbon emission data acquisition module 1 includes a data source adaptation unit 111, a real-time acquisition unit 112, and a data cache unit 113. The data source adaptation unit 111 is connected to the real-time acquisition unit 112, and the real-time acquisition unit 112 is connected to the data cache unit 113. The data source adaptation unit 111 is used to be compatible with various carbon emission data access; the real-time acquisition unit 112 is used to synchronously acquire dynamic carbon emission data; and the data caching unit 113 is used to temporarily store the acquired raw carbon emission data.
[0016] The carbon emission data standardization module 2 includes a format normalization unit 221, a time series calibration unit 222, and an anomaly screening unit 223. The format normalization unit 221 and the time series calibration unit 222 are connected, and the time series calibration unit 222 and the anomaly screening unit 223 are connected. The format normalization unit 221 is used to unify the carbon emission data storage format; the timing calibration unit 222 is used to align the carbon emission data acquisition time; and the anomaly removal unit 223 is used to remove invalid carbon emission data.
[0017] The big data carbon emission analysis module 3 includes a trend analysis unit 331, a correlation analysis unit 332, and a quantitative accounting unit 333. The trend analysis unit 331 and the correlation analysis unit 332 are connected, and the correlation analysis unit 332 and the quantitative accounting unit 333 are connected. The trend analysis unit 331 is used to explore the changing patterns of carbon emission data; the correlation analysis unit 332 is used to analyze the relationships between factors affecting carbon emission; and the quantitative calculation unit 333 is used to accurately calculate the total carbon emission value.
[0018] The carbon emission anomaly identification module 4 includes an anomaly determination unit 441, a source tracing and positioning unit 442, and a type marking unit 443. The anomaly determination unit 441 and the source tracing and positioning unit 442 are connected, and the source tracing and positioning unit 442 and the type marking unit 443 are connected. The anomaly determination unit 441 is used to identify abnormal fluctuations in carbon emission data; the source tracing and positioning unit 442 is used to locate the source of the carbon emission anomaly; and the type marking unit 443 is used to mark the category to which the carbon emission anomaly belongs.
[0019] The carbon emission performance evaluation module 5 includes an indicator calculation unit 551, a rating unit 552, and an optimization analysis unit 553. The indicator calculation unit 551 and the rating unit 552 are connected, and the rating unit 552 and the optimization analysis unit 553 are connected. The indicator calculation unit 551 is used to calculate carbon emission control performance indicators; the rating unit 552 is used to rate the carbon emission management performance level; and the optimization analysis unit 553 is used to analyze the direction of performance improvement and optimization.
[0020] The carbon emission early warning and control module 6 includes a threshold setting unit 661, an early warning triggering unit 662, and an instruction push unit 663. The threshold setting unit 661 and the early warning triggering unit 662 are connected, and the early warning triggering unit 662 and the instruction push unit 663 are connected. The threshold setting unit 661 is used to set the carbon emission warning threshold standard; the warning triggering unit 662 is used to automatically activate the warning when the standard is exceeded; the instruction push unit 663 is used to push the warning instruction to the control terminal.
[0021] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the present invention. Various changes and modifications can be made to the present invention without departing from its spirit and scope. All such changes and modifications fall within the scope of the present invention as claimed, which is defined by the appended claims and their equivalents.
Claims
1. A carbon emission monitoring method based on big data analysis, characterized in that: The specific steps include: Step S101: Access carbon emission related data from multiple channels, complete data source adaptation and real-time collection, and temporarily cache and store the raw data; Step S102: Perform format normalization, time-series calibration, and anomaly screening on the collected carbon emission data to achieve data standardization and normalization processing; Step S103: Utilize big data algorithms to analyze carbon emission trends and related factors, and complete the accurate calculation of total carbon emissions; Step S104: Determine the carbon emission data as abnormal according to the standard, locate the source of the abnormality, and complete the classification and labeling of the abnormality type; Step S105: Calculate the various performance indicators for carbon emission control, assess the management level, and analyze the optimization direction for performance improvement; Step S106: Set the carbon emission early warning threshold. When the data exceeds the limit, an early warning will be automatically triggered and instructions will be pushed to the control terminal. Step S107: Classify and store the data from the entire process of carbon emission collection, analysis, and evaluation to ensure data integrity and traceability; Step S108: Automatically generate standardized carbon emission monitoring reports based on monitoring and analysis data to support management decisions; Step S109: Configure system access and operation permissions, control the scope of data viewing and use, and ensure the security of monitoring data; Step S110: Complete the multi-system connection through interface adaptation and protocol conversion to achieve cross-platform synchronous sharing of carbon emission data.
2. A heterogeneous environmental monitoring data fusion system based on deep learning, applied to the carbon emission monitoring method based on big data analysis as described in claim 1, comprising a multi-source carbon emission data acquisition module (1), a carbon emission data standardization module (2), a big data carbon emission analysis module (3), a carbon emission anomaly identification module (4), a carbon emission performance evaluation module (5), a carbon emission early warning and control module (6), a carbon emission data storage module (7), a carbon emission report generation module (8), a system permission management module (9), and a multi-system interface adaptation module (10), characterized in that: The multi-source carbon emission data acquisition module (1) and the carbon emission data standardization module (2) are connected. The carbon emission data standardization module (2) and the big data carbon emission analysis module (3) are connected. The big data carbon emission analysis module (3) and the carbon emission anomaly identification module (4) are connected. The big data carbon emission analysis module (3) and the carbon emission performance evaluation module (5) are connected. The carbon emission performance evaluation module (5) and the carbon emission early warning and control module (6) are connected. The carbon emission anomaly identification module (4) and the carbon emission early warning and control module (6) are connected. The carbon emission early warning and control module (6) and the carbon emission... The report generation module (8) is connected, the big data carbon emission analysis module (3) and the carbon emission data storage module (7) are connected, the carbon emission data storage module (7) and the multi-system docking and adaptation module (10) are connected, the multi-system docking and adaptation module (10) includes an interface adaptation unit, a data synchronization unit and a protocol conversion unit, the multi-system docking and adaptation module (10) breaks down the data barriers of multiple systems, realizes data sharing, adapts to the smart environmental protection management system, and improves the coordination of control, the multi-source carbon emission data acquisition module (1) and the system permission management module (9) are connected.
3. The heterogeneous environmental monitoring data fusion system based on deep learning according to claim 2, characterized in that: The multi-source carbon emission data acquisition module (1) includes a data source adaptation unit (111), a real-time acquisition unit (112), and a data cache unit (113). The data source adaptation unit (111) and the real-time acquisition unit (112) are connected, and the real-time acquisition unit (112) and the data cache unit (113) are connected. The data source adaptation unit (111) is used to be compatible with various carbon emission data access; the real-time acquisition unit (112) is used to synchronously acquire dynamic carbon emission data; and the data caching unit (113) is used to temporarily store the acquired raw carbon emission data.
4. The heterogeneous environmental monitoring data fusion system based on deep learning according to claim 2, characterized in that: The carbon emission data standardization module (2) includes a format normalization unit (221), a time series calibration unit (222), and an anomaly screening unit (223). The format normalization unit (221) and the time series calibration unit (222) are connected, and the time series calibration unit (222) and the anomaly screening unit (223) are connected. The format normalization unit (221) is used to unify the carbon emission data storage format; the timing calibration unit (222) is used to align the carbon emission data acquisition time; and the anomaly removal unit (223) is used to remove invalid carbon emission acquisition data.
5. A heterogeneous environmental monitoring data fusion system based on deep learning according to claim 2, characterized in that: The big data carbon emission analysis module (3) includes a trend analysis unit (331), a correlation analysis unit (332), and a quantitative accounting unit (333). The trend analysis unit (331) and the correlation analysis unit (332) are connected, and the correlation analysis unit (332) and the quantitative accounting unit (333) are connected. The trend analysis unit (331) is used to explore the changing patterns of carbon emission data; the correlation analysis unit (332) is used to analyze the relationships between factors affecting carbon emission; and the quantitative calculation unit (333) is used to accurately calculate the total carbon emission value.
6. The heterogeneous environmental monitoring data fusion system based on deep learning according to claim 2, characterized in that: The carbon emission anomaly identification module (4) includes an anomaly determination unit (441), a source tracing and positioning unit (442), and a type marking unit (443). The anomaly determination unit (441) and the source tracing and positioning unit (442) are connected, and the source tracing and positioning unit (442) and the type marking unit (443) are connected. The anomaly determination unit (441) is used to identify abnormal fluctuations in carbon emission data; the source tracing and positioning unit (442) is used to locate the source of carbon emission anomalies; and the type marking unit (443) is used to mark the category to which the carbon emission anomaly belongs.
7. A heterogeneous environmental monitoring data fusion system based on deep learning according to claim 2, characterized in that: The carbon emission performance evaluation module (5) includes an indicator calculation unit (551), a rating unit (552), and an optimization analysis unit (553). The indicator calculation unit (551) and the rating unit (552) are connected, and the rating unit (552) and the optimization analysis unit (553) are connected. The indicator calculation unit (551) is used to calculate carbon emission control performance indicators; the rating unit (552) is used to rate the carbon emission management performance level; and the optimization analysis unit (553) is used to analyze the direction of performance improvement and optimization.
8. A heterogeneous environmental monitoring data fusion system based on deep learning according to claim 2, characterized in that: The carbon emission early warning and control module (6) includes a threshold setting unit (661), an early warning triggering unit (662), and an instruction push unit (663). The threshold setting unit (661) and the early warning triggering unit (662) are connected, and the early warning triggering unit (662) and the instruction push unit (663) are connected. The threshold setting unit (661) is used to set the carbon emission warning threshold; the warning triggering unit (662) is used to automatically start the warning when the threshold is exceeded; the instruction push unit (663) is used to push the warning instruction to the control terminal.