Smart park carbon emission monitoring method and system based on multi-factor emission factors

Abstract

The present invention discloses a smart park carbon emissions monitoring method and system based on multi-factor emission factors, relating to data processing-related fields. The method includes: constructing a dynamic emission factor library containing one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; connecting to a smart park monitoring network to obtain park monitoring data; matching and converting the park monitoring data with the dynamic emission factor library to determine carbon emission analysis data; and mapping a three-dimensional map with the carbon emission analysis data to generate a carbon emission distribution heat map. This method solves the technical problem of inaccurate monitoring results in existing park carbon emissions monitoring systems, achieving the technical effect of accurately monitoring park carbon emissions.

Description

Technical Field

[0001] The present application relates to data processing related fields, and in particular to a smart park carbon emission monitoring method and system based on multi-factor emission factors. Background Art

[0002] In the context of global efforts to address climate change and promote green and low-carbon development, accurate monitoring of industrial park carbon emissions is crucial for developing scientific emission reduction strategies and achieving sustainable development goals. Currently, the main approach to addressing industrial park carbon emission monitoring is to use fixed emission factors for estimation. Carbon emissions are calculated by combining preset fixed emission factors for various energy sources and activities with basic data such as industrial park energy consumption. However, current methods fail to fully consider factors such as real-time changes in industrial park energy structure, differences in equipment operating status, fluctuations in environmental conditions, and spatiotemporal dynamics. Consequently, carbon emission monitoring results deviate significantly from actual conditions, making it difficult to accurately reflect the true state of industrial park carbon emissions.

[0003] Among the current related technologies, there is a technical problem of inaccurate monitoring results in industrial park carbon emission monitoring. Summary of the Invention

[0004] This application provides a smart park carbon emission monitoring method and system based on multi-factor emission factors. It adopts the method of building a dynamic emission factor library containing multiple factors (energy structure, equipment operation parameters, environmental parameters, spatiotemporal dynamic factors, indirect emission factors, etc.), connecting the smart park monitoring network to obtain monitoring data, matching and converting the monitoring data with the dynamic emission factor library to obtain carbon emission analysis data, mapping the three-dimensional map with the carbon emission analysis data, and generating a carbon emission distribution heat map. These technical means solve the technical problem of inaccurate monitoring results in existing park carbon emission monitoring and achieve the technical effect of accurately monitoring park carbon emissions.

[0005] The present application provides a smart park carbon emission monitoring method based on multi-factor emission factors, including: constructing a dynamic emission factor library, including one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; connecting to the smart park monitoring network to obtain park monitoring data; using the park monitoring data to match and convert with the dynamic emission factor library to determine carbon emission analysis data; mapping a three-dimensional map with the carbon emission analysis data to generate a carbon emission distribution heat map.

[0006] In a possible implementation, the dynamic emission factor library is constructed and the following processing is performed: the operation plan data of the smart park is obtained; the carbon emission factor of the operation plan data is parsed according to the preset multi-factor type to obtain the carbon emission parsing factor, and the preset multi-factor type includes the energy structure data, equipment operation parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; the dynamic emission factor library is constructed according to the mapping relationship between the carbon emission parsing factor and the preset multi-factor type.

[0007] In a possible implementation, before performing carbon emission factor analysis on the operation plan data according to the preset multi-factor type, the following processing is performed: obtaining a historical emission monitoring sample set, including a sample data cluster of the preset multi-factor type; performing multi-level carbon emission factor extraction on the sample data cluster of each preset multi-factor type according to the sample carbon emission identification sensitivity and analysis granularity, and establishing an emission factor gradient for each factor type; and configuring the multi-level analysis features of the preset multi-factor type according to the emission factor gradient of each factor type.

[0008] In a possible implementation, the following processing is performed: the analysis granularity includes: direct process emissions, indirect associated emissions, and implicit coupled carbon emissions, and the analysis granularity is used to describe the difficulty of identifying carbon emission factors.

[0009] In a possible implementation, according to the sample carbon emission identification sensitivity and parsing granularity, multi-level carbon emission factor extraction is performed on each of the preset multi-factor type sample data clusters, and an emission factor gradient for each factor type is established, and the following processing is performed: according to the carbon emission identification result of the sample data cluster, the identification path and the accuracy probability of the identification result are determined; according to the identification path and the accuracy probability of the identification result, the identification sensitivity and parsing granularity are configured; according to the configured identification sensitivity and parsing granularity, the corresponding carbon emission factor is extracted according to the corresponding identification path; according to the identification sensitivity and parsing granularity, a gradient sequence of extracted carbon emission factors is established to obtain the emission factor gradient for each factor type.

[0010] In a possible implementation, recognition sensitivity and analytical granularity are configured according to the accuracy probability of the recognition path and the recognition result, and the following processing is performed: a three-dimensional gradient space is constructed, and a weight assignment mechanism for the recognition path and the recognition result is configured, wherein the weight assignment mechanism includes the number of nodes in the recognition path and the correlation between the nodes, the consecutive accurate times of the recognition result and the weighting rules of the accuracy probability, which are used to convert the recognition path and the recognition result into corresponding sensitivity and analytical granularity weight coefficients; based on the weight assignment mechanism, the weight coefficients of the recognition path and the recognition result are converted to obtain the recognition sensitivity and analytical granularity configuration.

[0011] In a possible implementation, the recognition path and recognition result are converted into weight coefficients based on the weight assignment mechanism to obtain the recognition sensitivity and resolution granularity configuration, and the following processing is performed: the number of path nodes of the recognition path, and the consecutive accurate times and accuracy probability of the recognition result are obtained; a conversion relationship between the consecutive accurate times and accuracy probability and the recognition sensitivity, as well as a conversion relationship between the number of path nodes and the resolution granularity is established; the recognition path and recognition result are converted into a relationship using the conversion relationship to obtain the weight coefficients of the recognition sensitivity and resolution granularity.

[0012] In a possible implementation, based on the identification sensitivity and parsing granularity, a gradient sequence for extracting carbon emission factors is established to obtain the emission factor gradients of each element type, and the following processing is performed: gradient weighted calculation is performed based on the weight coefficients of the identification sensitivity and parsing granularity to obtain the gradient sequence of the carbon emission factors; according to the correspondence between the carbon emission factors and the element types, the gradient sequences of the carbon emission factors of each element type are clustered and arranged in sequence to establish the emission factor gradients of each element type.

[0013] In a possible implementation, the park monitoring data is matched and converted with the dynamic emission factor library to determine the carbon emission analysis data, and the following processing is performed: a collection relationship model between the multi-level analysis features and the smart park monitoring network is established, and the collection relationship model includes: direct collection links and indirect inference mapping; according to the collection relationship model, the park monitoring data is dynamically matched with the dynamic emission factor library to realize the feature fusion and result conversion of the carbon emission factor, and determine the carbon emission analysis data.

[0014] The present application also provides a smart park carbon emission monitoring system based on multi-factor emission factors, including: a dynamic emission factor library construction module, used to construct a dynamic emission factor library, including one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; a park monitoring data acquisition module, used to connect to the smart park monitoring network and obtain park monitoring data; a carbon emission analysis data determination module, used to use the park monitoring data and the dynamic emission factor library for matching and conversion to determine the carbon emission analysis data; a carbon emission distribution heat map generation module, used to map the three-dimensional map with the carbon emission analysis data to generate a carbon emission distribution heat map.

[0015] The proposed smart park carbon emissions monitoring method and system based on multi-factor emission factors first constructs a dynamic emission factor library, including one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors. It then connects to the smart park monitoring network to obtain park monitoring data. This data is then matched and converted with the dynamic emission factor library to determine carbon emission analysis data. Finally, a three-dimensional map is mapped with the carbon emission analysis data to generate a heat map of carbon emission distribution. This achieves the technical effect of accurately monitoring park carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A flow chart of a smart park carbon emission monitoring method based on multi-factor emission factors provided in an embodiment of the present application.

[0018] Figure 2 A schematic diagram of the structure of a smart park carbon emission monitoring system based on multi-factor emission factors provided in an embodiment of the present application.

[0019] Explanation of the reference numerals: dynamic emission factor library construction module 10 , park monitoring data acquisition module 20 , carbon emission analysis data determination module 30 , carbon emission distribution heat map generation module 40 . DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments” which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict. The terms “including” and “having” and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0023] The present application embodiment provides a smart park carbon emission monitoring method based on multi-factor emission factors, such as Figure 1 As shown, the method includes:

[0024] Step S100: construct a dynamic emission factor library, including one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors.

[0025] Specifically, the dynamic emission factor library is a comprehensive data resource that stores various factors related to carbon emissions. These factors change dynamically based on different conditions (such as energy type, equipment operating status, and environmental conditions) and are used to calculate and assess carbon emissions generated by different activities or processes. The dynamic emission factor library includes at least one of five types of data. Energy structure data refers to the use of various energy sources within the park, including information such as energy type, amount, and source. It is one of the basic data sets for calculating carbon emissions. Equipment operating parameters refer to parameters generated during the operation of various equipment within the park, such as power, operating hours, and efficiency, and are used to determine the carbon emissions of these equipment. Environmental parameters refer to environmental conditions within the park, such as temperature, humidity, and wind speed. These parameters affect the diffusion and distribution of carbon emissions. Spatiotemporal dynamic elements refer to the temporal and spatial variations in carbon emission data, including the distribution of carbon emissions over different time periods and regions. Indirect emission elements refer to carbon emissions related to park operations that are unrelated to direct production activities in the park, such as those generated by processes such as raw material procurement and product transportation.

[0026] Energy structure data includes carbon emission factors for different energy sources (such as coal, natural gas, and electricity). These factors change dynamically based on energy sources (such as the proportion of clean energy) and usage patterns. Equipment operating parameters include carbon emission factors for different equipment (such as boilers, air conditioners, and production equipment) under different operating conditions. These factors adjust dynamically based on factors such as equipment power, operating efficiency, and usage time. Environmental parameters include factors that influence environmental conditions (such as temperature, humidity, and wind speed) on carbon emissions. These factors change dynamically based on real-time environmental monitoring data. Spatiotemporal dynamic factors include factors that affect carbon emissions over time and space. For example, carbon emission factors may vary between different time periods (such as daytime and nighttime) or different regions. Indirect emission factors include carbon emission factors that are unrelated to direct production activities but are related to them, such as carbon emission factors from processes such as raw material procurement and product transportation. These factors adjust dynamically based on changes in the supply chain.

[0027] Use the campus's energy management system (EMS) interface to obtain consumption data for various energy sources (such as electricity, coal, and natural gas), including information such as energy type, amount, and usage time. Use a database management system (such as MySQL or Oracle) to establish an energy structure database and categorize, store, and manage the data.

[0028] Leveraging the Industrial Internet of Things (IIoT) platform, sensors are installed on various equipment within the park (such as boilers, air conditioners, and production equipment) to collect real-time operating parameters such as power, operating hours, and efficiency. These parameters are transmitted to the server via a data collection gateway and stored in a device operating parameter database.

[0029] Environmental monitoring sensors, such as temperature sensors, humidity sensors, and wind speed sensors, are strategically placed throughout the park to monitor environmental conditions in real time. These sensors transmit data to an environmental parameter database via wireless communication modules (such as LoRa and NB-IoT), enabling dynamic recording of environmental parameters.

[0030] Using Geographic Information System (GIS) technology, combined with the park's geographic spatial data (such as building distribution and road layout), we conduct a spatiotemporal analysis of carbon emissions data. Using time series analysis algorithms (such as the ARIMA model), we model the changing trends of carbon emissions data over different time periods. Simultaneously, using spatial analysis algorithms (such as spatial interpolation), we predict and simulate the distribution of carbon emissions across different areas within the park, thereby determining the impact of spatiotemporal dynamics on carbon emissions.

[0031] Based on internationally accepted carbon emission accounting standards (such as the Greenhouse Gas Protocol), combined with the park's supply chain data (such as raw material procurement, product transportation, etc.) and energy consumption data, indirect emissions are quantified using calculation formulas and models (such as the life cycle assessment (LCA) method), and the results are stored in the indirect emission factor database.

[0032] The factors in the dynamic emission factor library can be adjusted dynamically based on real-time data and scenarios. For example, if a park increases the proportion of solar power generation, the carbon emission factor related to electricity will decrease accordingly. If a piece of equipment undergoes energy-saving modifications and its operating efficiency improves, the carbon emission factor of that equipment will decrease accordingly. In hot weather, the operating hours of air-conditioning equipment may increase, and its carbon emission factor will be dynamically adjusted based on actual operating parameters. The carbon emission factors for different time periods will be adjusted according to the schedule of production activities. For example, if production activities are reduced at night, the carbon emission factor will also be reduced accordingly. An example of a dynamic emission factor library is shown in Table 1.

[0033] Table 1: Example of a dynamic emission factor library

[0034]

[0035] In one possible implementation, step S100 of constructing a dynamic emission factor library further includes step S110: obtaining the smart park's operational plan data. Specifically, the smart park's operational plan data, including production plans, equipment operation plans, energy usage plans, and logistics and transportation plans, is obtained through the park management system's interface. This data is stored in a spreadsheet (such as Excel) or a database file (such as SQL Server). The collected operational plan data is preprocessed, including data cleaning (removing duplicate data and correcting erroneous data) and data formatting (converting data to a unified format) to ensure data accuracy and usability. Examples of operational plan data are shown in Table 2.

[0036] Table 2: Example of smart park operation plan data

[0037]

[0038] Step S120: Carbon emission factor parsing is performed on the operation plan data according to preset multi-factor types, including the energy mix data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors, to obtain carbon emission parsing factors. Specifically, a parsing algorithm is used to decompose the operation plan data into corresponding carbon emission factors based on the preset multi-factor types (energy mix data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors). The parsed carbon emission factors are mapped and associated with the preset multi-factor types to ensure that each factor accurately corresponds to the corresponding factor type. Examples of carbon emission factor parsing results are shown in Table 3.

[0039] Table 3: Example of carbon emission factor analysis results

[0040]

[0041] Step S130 constructs the dynamic emission factor library based on the mapping relationship between the carbon emission analysis factors and pre-set multi-factor types. Specifically, the dynamic emission factor library is constructed using a relational database (such as MySQL) or a non-relational database (such as MongoDB). Within the database, a corresponding data table is created for each pre-set multi-factor type, and the carbon emission analysis factors are stored in the corresponding table. A data update mechanism is established to dynamically update the data in the emission factor library based on real-time operating data and environmental monitoring data. For example, when equipment operating parameters change, the data in the equipment operating parameter table is promptly updated; when environmental parameters change, the data in the environmental parameter table is updated. An example of the dynamic emission factor library structure is shown in Table 4.

[0042] Table 4: Example of dynamic emission factor library structure

[0043]

[0044] In one possible implementation, before performing carbon emission factor analysis on the operation plan data according to the preset multi-factor type, step S100 further includes step S140, obtaining a historical emission monitoring sample set, including a sample data cluster of the preset multi-factor type. Specifically, historical emission monitoring data is collected from the historical monitoring system of the park, including historical data of multi-factor types such as energy consumption, equipment operation, environmental conditions, spatiotemporal dynamics, and indirect emissions. These data are stored in a database or data warehouse. The collected historical data are sorted and classified according to the preset multi-factor type to form a sample data cluster. For example, energy consumption data is divided into subsets such as electricity and natural gas; equipment operation data is divided into different equipment types, etc.

[0045] Step S150 extracts multi-level carbon emission factors from each of the preset multi-factor type sample data clusters based on the sample carbon emission identification sensitivity and analysis granularity, establishing an emission factor gradient for each factor type. The analysis granularity includes direct process emissions, indirect associated emissions, and implicitly coupled carbon emissions, and describes the difficulty of identifying carbon emission factors.

[0046] Specifically, sensitivity analysis is performed on sample data for each factor type to determine which factors have the greatest impact on carbon emissions. For example, regression analysis or machine learning algorithms (such as random forests) can be used to assess the impact of different energy types and equipment operating parameters on carbon emissions. Based on the sensitivity analysis results, multi-level carbon emission factors are extracted from the sample data. For highly sensitive factors, more fine-grained factors are extracted; for less sensitive factors, coarser-grained factors are extracted. For example, for electricity consumption, hourly energy consumption data can be extracted; for equipment operation, factors such as equipment operating efficiency and operating time can be extracted.

[0047] The granularity of analysis refers to the level of detail used when extracting carbon emission factors, and it reflects the difficulty of identifying carbon emission factors. The higher the granularity of analysis, the more detailed the identification of carbon emission factors, and the greater the difficulty. Among them, direct process emissions are the most basic first-level granularity of analysis, which mainly focuses on the carbon emissions directly generated by the equipment during operation. For example, carbon emissions from the boiler combustion process can be calculated by real-time monitoring of parameters such as combustion efficiency. The carbon emission factors of such direct process emissions are relatively easy to identify because they are directly related to the operating status of the equipment and can be accurately measured through online monitoring equipment such as CEMS (continuous emissions monitoring system) and TDLAS (tunable diode laser absorption spectroscopy) laser analyzers, with an error rate that can be controlled within ±3%.

[0048] Indirectly linked emissions, a second-level granularity, encompass carbon emissions not directly related to the direct production process. Examples include energy losses during transmission, carbon emissions from employee commuting, and embodied carbon in buildings. These emissions are relatively difficult to identify because they are influenced by multiple factors and have a weak correlation with the direct production process. To calculate these indirect emissions, the Leontief input-output model can be used to analyze the carbon footprint of the supply chain, with data updated daily.

[0049] Implicitly coupled carbon emissions are the most complex of the three levels of granularity, accounting for interactions between multiple energy systems and system-level coupling effects. For example, virtual power plants participating in carbon trading may trigger changes in marginal emissions. This type of emission factor is the most challenging to identify because it involves complex system interactions and market factors. To accurately extract these factors, a mixed integer programming model can be used to calculate the carbon-energy coupling coefficient, with a weekly analysis window.

[0050] By extracting carbon emission factors at different resolution granularities, we establish emission factor gradients for each factor type. This emission factor gradient refers to the range and trend of carbon emission factors at different resolution granularities. By extracting carbon emission factors at multiple levels, we can establish emission factor gradients for each factor type, thereby better quantifying the impact of different factors on carbon emissions.

[0051] Step S160 configures the multi-level parsing features for the pre-set multiple factor types based on the emission factor gradients for each factor type. Specifically, corresponding parsing features are configured for each factor type based on the emission factor gradients. These features include parsing granularity, data update frequency, and tools and techniques used. A rules engine is developed to dynamically parse carbon emission factors from the operational plan data based on the configured parsing features. The rules engine can rapidly extract and calculate carbon emission factors based on real-time data and pre-set rules.

[0052] In one possible implementation, multi-level carbon emission factor extraction is performed for each of the preset multi-factor type sample data clusters based on the sample carbon emission identification sensitivity and granularity, and an emission factor gradient for each factor type is established. Step S150 further includes step S151, where, based on the carbon emission identification results of the sample data clusters, the identification path and the accuracy probability of the identification results are determined. Specifically, different carbon emission identification methods (such as online monitoring and model calculation) are evaluated to determine their accuracy and applicability. Through statistical analysis, the accuracy probability of each identification method is calculated to provide a basis for configuring sensitivity and granularity. For example, using CEMS online monitoring, the accuracy probability is 97%; using the Leontief input-output model, the accuracy probability is 90%; and using the mixed integer programming model, the accuracy probability is 85%.

[0053] Step S152 configures the identification sensitivity and analysis granularity based on the identification path and the accuracy probability of the identification result. Specifically, the impact of different factor types on carbon emissions is assessed and their sensitivity is determined. Based on the sensitivity and accuracy probability, the corresponding analysis granularity is configured. Factor types with high sensitivity and high accuracy probability use a finer-grained analysis. For example, direct process emissions have high sensitivity, with an analysis granularity of seconds. Indirectly associated emissions have medium sensitivity, with an analysis granularity of days. Implicitly coupled carbon emissions have low sensitivity, with an analysis granularity of weeks.

[0054] Step S153 utilizes the configured identification sensitivity and parsing granularity to extract the corresponding carbon emission factor according to the corresponding identification path. A gradient sequence for extracting the carbon emission factor is established based on the identification sensitivity and parsing granularity to obtain emission factor gradients for each element type. Specifically, carbon emission factors for different element types are extracted based on the configured parsing granularity. Based on the identification sensitivity and parsing granularity, an emission factor gradient sequence is established to reflect the range and trend of carbon emission factors.

[0055] In one possible implementation, based on the recognition path and the accuracy probability of the recognition result, recognition sensitivity and resolution granularity are configured. Step S152 further includes step S1521, constructing a three-dimensional gradient space and configuring a weight assignment mechanism for the recognition path and recognition result. The weight assignment mechanism includes weighting rules for the number of nodes in the recognition path and the correlation between nodes, the number of consecutive accurate recognition results, and the accuracy probability, and is used to convert the recognition path and recognition result into corresponding sensitivity and resolution granularity weight coefficients. Specifically, a three-dimensional gradient space is constructed to configure the weight assignment mechanism for the recognition path and recognition result. This three-dimensional gradient space includes three dimensions: the number of nodes in the recognition path and the correlation between nodes, the number of consecutive accurate recognition results, and the accuracy probability of the recognition result. Through these dimensions, the recognition path and recognition result are converted into corresponding sensitivity and resolution granularity weight coefficients. The number of nodes and correlation refers to the evaluation of the complexity of the recognition path, including the number of nodes in the path and the correlation between nodes. The greater the number of nodes and the stronger the correlation, the higher the complexity of the path. The number of consecutive accurate results is a statistical measure of the number of consecutive accurate recognition results, reflecting the stability and reliability of the recognition method. The accuracy probability is an assessment of the probability of accurate recognition results, reflecting the accuracy of the recognition method. Weights are assigned based on the complexity of the path, with complex paths receiving higher weights. Weights are assigned based on the stability of the recognition results; a higher number of consecutive accurate results is associated with a higher weight. Weights are assigned based on the accuracy of the recognition results; a higher accuracy probability is associated with a higher weight.

[0056] For example, the direct process emissions identification path is simple, with a small number of nodes and weak correlations; the consecutive accuracy rate is high, and the accuracy probability is high. The indirect correlation emissions identification path is moderately complex, with a medium number of nodes and medium correlations; the consecutive accuracy rate is medium, and the accuracy probability is medium. The implicit coupling carbon emissions identification path is complex, with a large number of nodes and strong correlations; the consecutive accuracy rate is low, and the accuracy probability is low.

[0057] Step S1522 converts the recognition path and recognition result into weight coefficients based on the weight assignment mechanism to obtain the recognition sensitivity and resolution granularity configuration. Specifically, a weight coefficient is calculated for each element type based on the weight assignment mechanism. The weight coefficient reflects a comprehensive evaluation of the recognition path and recognition result. Based on the weight coefficient, the recognition sensitivity and resolution granularity configuration for each element type is determined. A high weight coefficient corresponds to high sensitivity and fine-grained resolution, while a low weight coefficient corresponds to low sensitivity and coarse-grained resolution.

[0058] In one possible implementation, the identification path and identification results are converted into weight coefficients based on the weight assignment mechanism to obtain the identification sensitivity and analysis granularity configuration. Step S1522 further includes step S15221, which obtains the number of path nodes in the identification path, as well as the number of consecutive accurate identification results and the accuracy probability. Specifically, the number of nodes in the identification path is counted to evaluate the complexity of the path. The number of consecutive accurate identification results is counted to evaluate the stability of the identification method. The accuracy probability of the identification result is calculated to evaluate the precision of the identification method. For example, the number of path nodes for direct process emissions is 3, the number of consecutive accurate identification results is 95%, and the accuracy probability is 97%. The number of path nodes for indirect related emissions is 5, the number of consecutive accurate identification results is 85%, and the accuracy probability is 90%. The number of path nodes for implicitly coupled carbon emissions is 7, the number of consecutive accurate identification results is 70%, and the accuracy probability is 85%.

[0059] Step S15222: Establish a conversion relationship between the consecutive accurate times and the accuracy probability and the recognition sensitivity, as well as a conversion relationship between the number of path nodes and the resolution granularity. Specifically, different sensitivity weights are assigned based on the number of consecutive accurate times. For example, the higher the consecutive accurate times, the higher the sensitivity weight. Different sensitivity weights are assigned based on the accuracy probability. For example, the higher the accuracy probability, the higher the sensitivity weight. Different resolution granularity weights are assigned based on the number of path nodes. For example, the greater the number of path nodes, the coarser the resolution granularity.

[0060] Step S15223 uses the conversion relationship to transform the recognition path and recognition result to obtain the weight coefficients for the recognition sensitivity and resolution granularity. Specifically, the weight coefficient for recognition sensitivity is calculated based on the conversion relationship between the number of consecutive accurate results and the accuracy probability. The weight coefficient for resolution granularity is calculated based on the conversion relationship between the number of path nodes. An example of the conversion relationship is shown in Table 5.

[0061] Table 5: Example of conversion relationship

[0062]

[0063] In one possible implementation, a gradient sequence for extracting carbon emission factors is established based on the identification sensitivity and parsing granularity to obtain the emission factor gradients for each element type. Step S153 further includes step S1531, performing a gradient weighted calculation based on the weight coefficients of the identification sensitivity and parsing granularity to obtain the gradient sequence of carbon emission factors. Specifically, a weighted calculation is performed on the carbon emission factor of each element type based on its identification sensitivity and parsing granularity. The higher the weight coefficient, the greater the weight of the corresponding carbon emission factor in the gradient sequence.

[0064] Step S1532: Cluster and sequentially arrange the gradient sequences of carbon emission factors for each factor type based on the correspondence between carbon emission factors and factor types to establish emission factor gradients for each factor type. Specifically, cluster the gradient sequences of carbon emission factors using a clustering algorithm (e.g., K-means or hierarchical clustering), grouping similar factors together. The clustered factors are then sequentially arranged according to their gradient weights to form emission factor gradients.

[0065] Step S200: Connect to the smart park monitoring network to obtain park monitoring data.

[0066] Specifically, various monitoring devices within the park (such as sensors, smart electricity meters, and smart water meters) are connected to the smart park monitoring network through wired (e.g., Ethernet) and wireless (e.g., Wi-Fi, 4G / 5G, etc.) communication technologies. Data collection software (e.g., collector software, middleware, etc.) is used to collect data generated by the monitoring devices in real time, including energy consumption data, environmental monitoring data, and equipment operating status data. This data is then transmitted to a data processing server. On the data processing server, the collected raw data undergoes preprocessing, including data cleaning (removing erroneous and duplicate data), data conversion (converting data in different formats to a unified format), and data aggregation (aggregating scattered data according to specific rules). Data preprocessing is performed using data processing tools (e.g., the Pandas library in Python and MATLAB) to ensure data accuracy and availability. The preprocessed data is stored in a distributed database (e.g., the Hadoop Distributed File System (HDFS) or the distributed database Cassandra) for subsequent data query and analysis. Furthermore, a data management system is established to classify, index, and back up the data to ensure data security and traceability.

[0067] For example, smart meters within the campus are connected to the smart campus monitoring network via Ethernet, collecting real-time electricity usage data for each area, including hourly power consumption, voltage, current, and other parameters. The collector software collects this data and transmits it to the data processing server. A preprocessor on the server cleans the data, removing abnormal data caused by equipment failures. The data is then converted into a unified JSON format, aggregated by region and time, and stored in HDFS. Environmental monitoring sensors, such as air quality sensors, collect data on pollutant concentrations such as PM2.5, PM10, and sulfur dioxide, and transmit it to the monitoring network via NB-IoT wireless communication modules. After receiving this data, the data collection software performs preprocessing, integrating data from different sensors and storing it in a distributed database for subsequent correlation analysis with carbon emissions data. The data management system categorizes the stored data, for example, dividing energy data into electricity and heat data to support different types of carbon emissions calculations. Furthermore, the data is indexed to facilitate quick queries for data for specific time periods or regions. Regular data backups are performed to prevent data loss.

[0068] Step S300: Match and convert the park monitoring data with the dynamic emission factor library to determine carbon emission analysis data.

[0069] Specifically, data matching algorithms (such as rule-based and fuzzy matching algorithms) are used to match park monitoring data with data in the dynamic emission factor library. Based on information such as the type, source, and timestamp of the monitoring data, corresponding emission factors are found to achieve precise data matching. For example, for energy consumption data for a particular piece of equipment, the corresponding emission factor for that device is matched from the dynamic emission factor library based on the device type and operating parameters.

[0070] Establish a carbon emissions calculation model. Based on the matched emission factors and monitoring data, calculate carbon emissions using the carbon emissions calculation formula (e.g., direct emissions = energy consumption × emission factor). For complex carbon emissions calculations, numerical methods (such as the finite element method and Monte Carlo method) can be used to simulate and improve accuracy. The calculated carbon emissions data is stored in a carbon emissions analysis database.

[0071] Calculated carbon emissions analysis data is verified, and anomalies are detected through methods such as data consistency checks (e.g., checking whether the sum of carbon emissions from different energy types is consistent with the park's total carbon emissions) and data rationality checks (e.g., checking whether carbon emissions are within a reasonable range). Anomalous data is corrected using data correction algorithms (e.g., interpolation correction based on historical data, model-based prediction correction, etc.) to ensure the accuracy and reliability of carbon emissions analysis data.

[0072] For example, using a data matching algorithm, a dynamic emission factor library matches the coal consumption data for a factory within the industrial park to an emission factor of 2.5 kg CO2 / kg coal. Using the carbon emission calculation model, the factory's direct carbon emissions from coal are calculated as coal consumption multiplied by the emission factor: 10,000 kg coal x 2.5 kg CO2 / kg coal = 25,000 kg CO2. This calculation result is stored in the carbon emission analysis database.

[0073] In one possible implementation, the park monitoring data is matched and converted with the dynamic emission factor library to determine the carbon emission analysis data. Step S300 further includes step S310, establishing a collection relationship model between the multi-level analysis features and the smart park monitoring network. The collection relationship model includes: direct collection links and indirect inference mapping. Specifically, real-time data is directly collected through sensors and monitoring equipment in the smart park monitoring network. These data include energy consumption, equipment operating status, environmental parameters, etc. The collected data is transmitted to the data processing center through a wired or wireless communication network. For data that cannot be collected directly, it is inferred through existing data and models. A mapping relationship between the inferred data and the actual monitoring data is established to ensure the accuracy of the inferred results.

[0074] Step S320 dynamically matches the park monitoring data with the dynamic emission factor library based on the acquisition relationship model, achieving feature fusion and result conversion of carbon emission factors to determine the carbon emission analysis data. Specifically, the park monitoring data is matched with the data in the dynamic emission factor library in real time to ensure data consistency and accuracy. The matched data is converted into carbon emission analysis data to generate the final carbon emissions report. A verification mechanism is used to ensure the accuracy and reliability of the conversion results.

[0075] Step S400 : Mapping the three-dimensional map with the carbon emission analysis data to generate a carbon emission distribution heat map.

[0076] Specifically, using GIS technology and 3D modeling software (such as ArcGIS and 3ds Max), combined with the park's geospatial data and 3D building model data, a 3D map of the park was constructed. This 3D map displays information such as the park's topography, building layout, and road network, providing a foundation for visualizing carbon emissions distribution. Data mapping algorithms (such as spatial interpolation and geographically weighted regression) were used to map carbon emissions analysis data to the geographic locations in the 3D map. Different colors or patterns were used to visualize carbon emissions on the 3D map, creating a heat map of carbon emissions distribution. Visualization tools (such as QGIS and Tableau) were used to create and display the heat map, providing a direct view of carbon emissions distribution across different areas within the park.

[0077] Develop interactive features for the carbon emissions heat map, allowing users to view detailed carbon emissions data and historical trends for different regions by clicking and dragging their mouse. Leveraging web development technologies (such as HTML5, JavaScript, and CSS), embed the carbon emissions heat map into the park's management platform or website, facilitating real-time query and analysis.

[0078] For example, during the 3D map construction process, ArcGIS software was used to import the park's geospatial data and 3D building model data to create a 3D map of the park. The map clearly shows the park's various buildings, roads, and green spaces. For the mapping and visualization of carbon emission analysis data, assuming a certain area within the park has high carbon emissions, a spatial interpolation algorithm was used to map the carbon emission data for that area onto the 3D map, with high-carbon emission areas indicated in red and low-carbon emission areas in green. A carbon emission heat map was generated using QGIS software to showcase the distribution of carbon emissions within the park. In terms of interactive functionality, users can click on a building within the park to display detailed carbon emission data, such as the source and amount of emissions. Furthermore, users can use the time slider to view changes in carbon emission distribution over different time periods, providing strong support for the park's carbon emission management.

[0079] The embodiment of the present application adopts technical means such as constructing a dynamic emission factor library containing multiple factors (energy structure, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, indirect emission factors, etc.), connecting to the smart park monitoring network to obtain monitoring data, matching and converting the monitoring data with the dynamic emission factor library, obtaining carbon emission analysis data, mapping the three-dimensional map with the carbon emission analysis data, and generating a carbon emission distribution heat map. This solves the technical problem of inaccurate monitoring results in existing park carbon emission monitoring and achieves the technical effect of accurately monitoring park carbon emissions.

[0080] In the above, refer to Figure 1 The carbon emission monitoring method of a smart park based on multi-factor emission factors according to an embodiment of the present invention is described in detail. Figure 2 The present invention describes a smart park carbon emission monitoring system based on multi-factor emission factors according to an embodiment of the present invention.

[0081] The smart park carbon emissions monitoring system based on multi-factor emission factors according to an embodiment of the present invention is designed to address the technical issue of inaccurate monitoring results in existing park carbon emissions monitoring systems, achieving the technical effect of accurately monitoring park carbon emissions. The smart park carbon emissions monitoring system based on multi-factor emission factors includes: a dynamic emission factor library construction module 10, a park monitoring data acquisition module 20, a carbon emissions analysis data determination module 30, and a carbon emissions distribution heat map generation module 40.

[0082] The dynamic emission factor library construction module 10 is used to construct a dynamic emission factor library, including one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic elements, and indirect emission elements; the park monitoring data acquisition module 20 is used to connect to the smart park monitoring network to obtain park monitoring data; the carbon emission analysis data determination module 30 is used to use the park monitoring data to match and convert the dynamic emission factor library to determine the carbon emission analysis data; the carbon emission distribution heat map generation module 40 is used to map the three-dimensional map with the carbon emission analysis data to generate a carbon emission distribution heat map.

[0083] The specific configuration of the dynamic emission factor library construction module 10 will be described in detail below. As described above, to construct a dynamic emission factor library, the dynamic emission factor library construction module 10 may further include: an operation plan data acquisition unit for acquiring the operation plan data of the smart park; a carbon emission factor parsing unit for performing carbon emission factor parsing on the operation plan data according to preset multi-factor types to obtain carbon emission parsing factors, wherein the preset multi-factor types include the energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; and a dynamic emission factor library construction unit for constructing the dynamic emission factor library based on the mapping relationship between the carbon emission parsing factors and the preset multi-factor types.

[0084] Among them, before performing carbon emission factor analysis on the operation plan data according to the preset multi-factor type, the dynamic emission factor library construction module 10 may further include: a historical emission monitoring sample set acquisition unit for obtaining a historical emission monitoring sample set, including a sample data cluster of the preset multi-factor type; a multi-level carbon emission factor extraction unit for performing multi-level carbon emission factor extraction on the sample data clusters of each preset multi-factor type according to the sample carbon emission identification sensitivity and analysis granularity, and establishing an emission factor gradient for each factor type; a multi-level analysis feature configuration unit for configuring the multi-level analysis features of the preset multi-factor type according to the emission factor gradient of each factor type.

[0085] Among them, the multi-level carbon emission factor extraction unit may further include: the analysis granularity includes: direct process emissions, indirect related emissions, and implicit coupled carbon emissions, and the analysis granularity is used to describe the difficulty of identifying the carbon emission factor.

[0086] Among them, according to the sample carbon emission identification sensitivity and analysis granularity, multi-level carbon emission factor extraction is performed on each of the preset multi-factor type sample data clusters, and an emission factor gradient of each factor type is established. The multi-level carbon emission factor extraction unit may further include: a carbon emission identification result analysis subunit for determining the identification path and the accuracy probability of the identification result according to the carbon emission identification result of the sample data cluster; a configuration subunit for configuring the identification sensitivity and analysis granularity according to the identification path and the accuracy probability of the identification result; an emission factor gradient acquisition subunit for extracting the corresponding carbon emission factor according to the corresponding identification path using the configured identification sensitivity and analysis granularity, and establishing a gradient sequence for extracting carbon emission factors according to the identification sensitivity and analysis granularity to obtain the emission factor gradient of each factor type.

[0087] Among them, according to the accuracy probability of the identification path and the identification result, the identification sensitivity and the analysis granularity are configured, and the configuration subunit may further include: a three-dimensional gradient space construction component is used to construct a three-dimensional gradient space, and configure the weight assignment mechanism of the identification path and the identification result, wherein the weight assignment mechanism includes the number of nodes in the identification path and the correlation between the nodes, the consecutive accurate times of the identification results and the weighting rules of the accuracy probability, which is used to convert the identification path and the identification result into the corresponding sensitivity and analysis granularity weight coefficients; the weight coefficient conversion component is used to convert the weight coefficients of the identification path and the identification result based on the weight assignment mechanism to obtain the identification sensitivity and analysis granularity configuration.

[0088] Among them, based on the weight assignment mechanism, the weight coefficients of the identification path and the identification result are converted to obtain the identification sensitivity and the resolution granularity configuration. The weight coefficient conversion component may further include: a path node number acquisition subcomponent for obtaining the number of path nodes of the identification path, as well as the consecutive accurate times and accurate probabilities of the identification results; a conversion relationship establishment subcomponent for establishing a conversion relationship between the consecutive accurate times and accurate probabilities and the identification sensitivity, as well as a conversion relationship between the number of path nodes and the resolution granularity; a relationship conversion subcomponent for using the conversion relationship to perform relationship conversion on the identification path and the identification result to obtain the weight coefficients of the identification sensitivity and the resolution granularity.

[0089] Among them, according to the identification sensitivity and analysis granularity, a gradient sequence for extracting carbon emission factors is established to obtain the emission factor gradients of each element type. The emission factor gradient acquisition subunit may further include: a gradient weighted calculation component for performing gradient weighted calculations according to the weight coefficients of the identification sensitivity and analysis granularity to obtain the gradient sequence of the carbon emission factors; a sequential arrangement component for clustering and sequentially arranging the gradient sequences of carbon emission factors of each element type according to the correspondence between the carbon emission factors and the element types to establish the emission factor gradients of each element type.

[0090] The specific configuration of the carbon emission analysis data determination module 30 will be described in detail below. As described above, the carbon emission analysis data is determined by matching and converting the park monitoring data with the dynamic emission factor library. The carbon emission analysis data determination module 30 may further include: an acquisition relationship model establishment unit for establishing an acquisition relationship model between the multi-level analysis features and the smart park monitoring network, the acquisition relationship model including: direct acquisition links and indirect inference mapping; a dynamic matching unit for dynamically matching the park monitoring data with the dynamic emission factor library based on the acquisition relationship model, realizing feature fusion and result conversion of carbon emission factors, and determining the carbon emission analysis data.

[0091] The smart park carbon emission monitoring system based on multi-factor emission factors provided by the embodiment of the present invention can execute the smart park carbon emission monitoring method based on multi-factor emission factors provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0092] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0093] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A smart park carbon emission monitoring method based on multi-factor emission factors is characterized by: include: Construct a dynamic emission factor library, including one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; Connect to the smart park monitoring network to obtain park monitoring data; Using the park monitoring data and the dynamic emission factor library to match and convert, to determine carbon emission analysis data; Mapping the three-dimensional map with the carbon emission analysis data to generate a carbon emission distribution heat map; The construction of a dynamic emission factor library includes: Obtain operational planning data for the smart park; Performing carbon emission factor analysis on the operation plan data according to preset multi-factor types to obtain a carbon emission analysis factor, wherein the preset multi-factor types include the energy structure data, equipment operation parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; Constructing the dynamic emission factor library according to the mapping relationship between the carbon emission analysis factors and the preset multi-factor types; The carbon emission factor analysis of the operation plan data is performed according to the preset multi-factor type, which previously included: Obtaining a historical emission monitoring sample set, including the sample data cluster of the preset multi-factor type; According to the sample carbon emission identification sensitivity and analysis granularity, multi-level carbon emission factor extraction is performed on each of the preset multi-factor type sample data clusters, and an emission factor gradient for each factor type is established; Configuring the multi-level analytical features of the preset multi-factor type according to the emission factor gradient of each factor type; According to the sample carbon emission identification sensitivity and analysis granularity, multi-level carbon emission factors are extracted from the sample data clusters of each preset multi-factor type, and an emission factor gradient for each factor type is established, including: Determining an identification path and an accuracy probability of the identification result based on the carbon emission identification result of the sample data cluster, including: evaluating the carbon emission identification method to determine its accuracy and applicability; According to the recognition path and the accuracy probability of the recognition result, the recognition sensitivity and analysis granularity are configured; Utilizing the configured identification sensitivity and parsing granularity, extracting the corresponding carbon emission factor according to the corresponding identification path, establishing a gradient sequence for extracting the carbon emission factor based on the identification sensitivity and parsing granularity, and obtaining the emission factor gradient of each element type; Based on the recognition path and the accuracy probability of the recognition result, the recognition sensitivity and analysis granularity are configured, including: Construct a three-dimensional gradient space and configure a weight assignment mechanism for the identification path and the identification result, wherein the weight assignment mechanism includes weighting rules for the number of nodes in the identification path and the correlation between the nodes, the number of consecutive accurate identification results, and the accuracy probability, for converting the identification path and the identification result into corresponding sensitivity and analytical granularity weight coefficients; The recognition path and the recognition result are converted into weight coefficients based on the weight assignment mechanism to obtain the recognition sensitivity and analysis granularity configuration.

2. The smart park carbon emission monitoring method based on multi-factor emission factors according to claim 1 is characterized in that: The analysis granularity includes: direct process emissions, indirect associated emissions, and implicit coupled carbon emissions. The analysis granularity is used to describe the difficulty of identifying carbon emission factors.

3. The smart park carbon emission monitoring method based on multi-factor emission factors according to claim 1 is characterized in that: The recognition path and the recognition result are converted into weight coefficients based on the weight assignment mechanism to obtain the recognition sensitivity and analysis granularity configuration, including: Obtain the number of path nodes of the identification path, as well as the number of consecutive accurate identification results and the accuracy probability; Establishing a conversion relationship between the number of consecutive accurate times and accurate probability and recognition sensitivity, as well as a conversion relationship between the number of path nodes and analysis granularity; The recognition path and the recognition result are transformed using the transformation relationship to obtain the weight coefficients of the recognition sensitivity and the analysis granularity.

4. The smart park carbon emission monitoring method based on multi-factor emission factors according to claim 3 is characterized in that: Based on the identification sensitivity and analytical granularity, a gradient sequence for extracting carbon emission factors is established to obtain the emission factor gradients for each element type, including: Performing gradient weighted calculation according to the weight coefficients of the identification sensitivity and analytical granularity to obtain a gradient sequence of the carbon emission factor; According to the correspondence between the carbon emission factors and the element types, the gradient sequences of the carbon emission factors of each element type are clustered and arranged in sequence to establish the emission factor gradients of each element type.

5. The smart park carbon emission monitoring method based on multi-factor emission factors according to claim 2 is characterized in that: The park monitoring data is matched and converted with the dynamic emission factor library to determine carbon emission analysis data, including: Establishing a collection relationship model between the multi-level analytical features and the smart park monitoring network, the collection relationship model includes: direct collection links and indirect inference mapping; According to the acquisition relationship model, the park monitoring data is dynamically matched with the dynamic emission factor library to achieve feature fusion and result conversion of carbon emission factors, and determine the carbon emission analysis data.

6. The smart park carbon emission monitoring system based on multi-factor emission factors is characterized by: The system is used to implement the smart park carbon emission monitoring method based on multi-factor emission factors according to any one of claims 1 to 5, and the system includes: A dynamic emission factor library construction module is used to construct a dynamic emission factor library, including one or more of energy structure data, equipment operating parameters, environmental parameters, spatiotemporal dynamic factors, and indirect emission factors; The park monitoring data acquisition module is used to connect to the smart park monitoring network and obtain park monitoring data; A carbon emission analysis data determination module is used to match and convert the park monitoring data with the dynamic emission factor library to determine carbon emission analysis data; The carbon emission distribution heat map generation module is used to map the three-dimensional map with the carbon emission analysis data to generate a carbon emission distribution heat map.

Images