Natural resource auditing method and system

Abstract

The invention relates to the technical field of resource auditing, in particular to a natural resource auditing method and system. The method comprises the following steps: acquiring remote sensing data of a monitoring area and sensing data of the monitoring area, and carrying out resource data atlas combination to obtain a resource atlas of the monitoring area; carrying out resource consumption modeling based on the monitoring area resource map to obtain an area resource consumption prediction model; performing monitoring area resource consumption risk area division on the monitoring area resource map according to the area resource consumption prediction model to obtain resource consumption risk area data; performing low-efficiency development link identification on the resource consumption risk area data according to the monitoring area resource map to obtain risk area low-efficiency development link efficiency data; and performing regional natural resource auditing compliance analysis based on the risk area low-efficiency development link efficiency data and the regional resource consumption trend prediction data so as to obtain a natural resource management compliance report. According to the method, the comprehensiveness and efficiency of natural resource auditing can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of resource auditing, and in particular to an auditing method and system for natural resources. Background Art

[0002] In order to effectively supervise and rationally utilize natural resources, auditing, as an important link in resource management, plays a crucial role. Natural resource auditing aims to evaluate the development and utilization of resources, monitor resource consumption and loss through auditing means, and ensure that resource management complies with the sustainable development goals of the country and region. Traditional auditing methods have problems of incomplete and inaccurate data collection. The efficiency of traditional auditing methods is relatively low. Manual auditing usually relies on on-site inspections and manual records, which not only consumes a large amount of time, but also is difficult to complete the auditing work of a large number of resources in a short time. In addition, differences in the experience of auditors are likely to lead to inconsistencies in judgment and deviations in audit results. In traditional auditing, data is usually collected manually, which is easily restricted by environmental conditions, personnel quality, and technical means. Especially in large-scale natural resource auditing, it is impossible to comprehensively obtain specific information on resource distribution, resulting in limitations in audit conclusions. These data deficiencies and deviations greatly reduce the credibility and accuracy of audit results. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide an auditing method and system for natural resources to solve at least one of the above technical problems.

[0004] To achieve the above object, an auditing method for natural resources includes the following steps:

[0005] Step S1: Obtain remote sensing data and sensing data of the monitoring area, and perform data enhancement on the remote sensing data and sensing data of the monitoring area respectively, so as to obtain enhanced remote sensing data and enhanced sensing data of the area; perform resource data map combination based on the enhanced remote sensing data and enhanced sensing data of the area, so as to obtain a resource map of the monitoring area;

[0006] Step S2: Identify the resource consumption pattern based on the resource map of the monitoring area, so as to obtain regional resource consumption pattern data; perform resource consumption modeling according to the regional resource consumption pattern data, so as to obtain a regional resource consumption prediction model;

[0007] Step S3: Predict the regional resource consumption trend of the resource map of the monitoring area according to the regional resource consumption prediction model, so as to obtain regional resource consumption trend prediction data; divide the monitoring area resource consumption risk area based on the regional resource consumption trend prediction data, so as to obtain resource consumption risk area data;

[0008] Step S4: evaluating the efficiency of resource development links in the risk area according to the resource map of the monitored area, thereby obtaining efficiency data of resource development links in the risk area; identifying inefficient development links in the efficiency data of resource development links in the risk area, thereby obtaining efficiency data of inefficient development links in the risk area;

[0009] Step S5: Conduct regional natural resource audit compliance analysis based on the efficiency data of inefficient development links in risk areas and regional resource consumption trend forecast data to obtain a natural resource management compliance report.

[0010] The synergistic effect of each step in the present invention significantly improves the comprehensiveness, accuracy and efficiency of natural resource auditing, and overcomes the problems of incomplete, inaccurate and inefficient data collection in traditional auditing methods. By acquiring remote sensing data and sensor data of the monitoring area and performing data enhancement, a refined perception of resource distribution and dynamics is achieved. The enhanced data is combined with the resource map to build a more complete spatial and attribute information of the resource data, providing a reliable data basis for subsequent analysis. Based on the resource map, resource consumption pattern recognition and modeling can accurately capture the consumption law and trend of resources, providing support for scientific prediction of resource consumption status. Through resource consumption trend prediction and risk area division, not only can possible high-risk areas be identified in advance, but also resource development and utilization strategies can be optimized in a targeted manner to effectively avoid resource waste and loss. The efficiency evaluation of the resource development link in the risk area can help the audit process identify bottlenecks and inefficient links in resource development, thereby guiding the improvement of development methods and improving resource utilization efficiency. Combined with the specific data of the inefficient development link, it is possible to further lock the problem link and analyze its cause, providing a basis for the resource management department to optimize the development plan. In addition, compliance analysis based on data on inefficient development links and regional resource consumption trend data can not only comprehensively review the actual situation of natural resource management, but also promptly identify potential non-compliance issues and ensure that resource development activities are in line with sustainable development goals. The resulting natural resource management compliance report is scientific, comprehensive and timely, providing strong decision-making support for the supervision and management of natural resources. This method not only improves audit efficiency and reduces human errors, but also lays the foundation for the efficient development and sustainable use of natural resources.

[0011] Optionally, step S1 specifically includes:

[0012] Step S11: Acquire remote sensing data of the monitoring area and sensor data of the monitoring area;

[0013] Step S12: preprocessing the remote sensing data of the monitored area and the sensor data of the monitored area respectively, so as to obtain the remote sensing data of the area to be analyzed and the sensor data of the area to be analyzed;

[0014] Step S13: Perform remote sensing data enhancement on the remote sensing data of the area to be analyzed, so as to obtain area-enhanced remote sensing data;

[0015] Step S14: Perform sensor data enhancement on the sensor data of the area to be analyzed, so as to obtain area-enhanced sensor data;

[0016] Step S15: Perform resource data map combination based on the enhanced area remote sensing data and the enhanced area sensor data, so as to obtain the resource map of the monitoring area.

[0017] Through the acquisition and preprocessing of remote sensing data and sensor data of the monitoring area, the present invention constructs a high-quality data foundation covering spatial distribution characteristics and temporal dynamic information, laying a solid technical support for subsequent analysis. In the data enhancement process, the remote sensing data and the sensor data respectively utilize advanced image processing technology and multi-source sensor fusion technology, significantly improving the detail richness and expression accuracy of the data, making the representation of resource distribution and state more accurate and reliable. The resource data map generated based on the enhanced data combines the advantages of remote sensing and sensing, not only improving the spatial resolution of resource attribute data, but also effectively making up for the deficiencies of a single data source in regional coverage and multi-dimensional representation. This data map can comprehensively reflect the spatio-temporal distribution, dynamic changes and correlations of resources, providing a clear and intuitive analysis basis for the assessment of the current situation and potential problems of the development and utilization of natural resources. At the same time, the construction of the resource data map further promotes the transformation of natural resource auditing towards automation and intelligence, reducing errors and efficiency bottlenecks in manual operations, and providing strong technical support and decision-making basis for the reasonable management and efficient utilization of natural resources.

[0018] Optionally, step S13 is specifically:

[0019] Extract the band reflectance of the remote sensing data of the area to be analyzed, so as to obtain the regional remote sensing band reflectance data, and perform multi-spectral band enhancement on the regional remote sensing band reflectance data, so as to obtain the remotely sensed enhanced band reflectance data;

[0020] Perform remote sensing image transformation enhancement on the remote sensing data of the area to be analyzed, so as to obtain image transformation enhanced remote sensing data;

[0021] Perform radiation enhancement on the remote sensing data of the area to be analyzed, so as to obtain radiation enhanced remote sensing data;

[0022] Perform Gaussian noise natural interference simulation on the remote sensing data of the area to be analyzed, so as to obtain noise remote sensing data;

[0023] Perform regional remote sensing enhanced data fusion based on the remotely sensed enhanced band reflectance data, the image transformation enhanced remote sensing data, the radiation enhanced remote sensing data and the noise remote sensing data, so as to obtain area-enhanced remote sensing data.

[0024] Through band reflectance extraction and multispectral band enhancement, the present invention greatly enriches the spectral information dimension of data, making the expression of resource attribute characteristics more delicate and comprehensive, and contributing to the accurate identification of resource types and states. Through remote sensing image transformation enhancement, the spatial characteristics of the original data are optimized, the edge features and spatial resolution of the image are improved, and the spatial distribution characteristics of resources are made clearer, providing more intuitive data support for subsequent regional division and analysis. In the process of radiation enhancement, by strengthening the optical characteristics of the image, some effects such as uneven illumination are eliminated, further improving the adaptability of the data under different illumination conditions and ensuring the stability and universality of the audit results. At the same time, through the simulation of Gaussian noise natural interference, the noise interference simulation and restoration enhancement of remote sensing data in the real environment are carried out, improving the adaptability and anti-interference ability of the data to complex natural environments and ensuring that the data analysis results are closer to the actual situation. By fusing the remotely sensed data after different enhancement processes, the multispectral characteristics, spatial characteristics, radiation characteristics and noise immunity are effectively integrated to construct high-precision regional enhanced remotely sensed data. This data fusion not only improves the all-round expression ability of remotely sensed data in resource distribution, dynamic changes and environmental adaptability, but also provides more reliable and efficient basic data support for subsequent natural resource management and analysis, thus further promoting the scientific and intelligent development of natural resource audits.

[0025] Optionally, step S15 is specifically as follows:

[0026] Step S151: Perform data spatio-temporal alignment on the enhanced regional remotely sensed data and the enhanced regional sensing data to obtain regionally aligned remotely sensed data and regionally aligned sensing data;

[0027] Step S152: Integrate the regional resource distribution characteristics of the regionally aligned remotely sensed data to obtain regional resource distribution data;

[0028] Step S153: Perform spatio-temporal clustering analysis on the hot spots of the regionally aligned sensing data to obtain regional hot spot data, and perform attribute classification on the regional hot spot data to obtain regional hot spot attribute data;

[0029] Step S154: Build a resource relationship model based on the regional resource distribution data to obtain resource relationship data;

[0030] Step S155: Construct and integrate a resource map according to the resource relationship data and the regional hot spot attribute data to obtain a resource map of the monitored area.

[0031] Through data spatio-temporal alignment, the present invention solves the problem of inconsistency in the acquisition spatio-temporal dimensions between remote sensing data and sensing data, laying a unified data foundation for subsequent analysis and ensuring the organic integration of information from different data sources. By integrating the regional resource distribution characteristics of the aligned remote sensing data, the spatial distribution characteristics of resources in the monitored area are accurately characterized, providing a reliable basis for subsequent resource utilization analysis and planning. During the spatio-temporal clustering analysis of sensing data for hot spots, the key nodes of resource consumption and high-frequency activity areas in the region are mined, and combined with attribute classification, the functional characteristics and resource attributes of different hot spots are further revealed, providing clear guidance for resource regulation and key area management. The resource relationship modeling based on resource distribution data systematically expresses the interactions and dynamic connections between resources, making the analysis of resource utilization efficiency more scientific and systematic. Through the construction and integration of a resource atlas, multi-source data, resource distribution characteristics, hot spot area information, and resource relationships are integrated into a comprehensive and dynamic resource atlas of the monitored area.

[0032] Optionally, step S2 is specifically as follows:

[0033] Step S21: Perform regional partitioning of resource attribute characteristics based on the resource atlas of the monitored area to obtain a regional partition resource atlas;

[0034] Step S22: Perform principal component analysis on the resource consumption characteristics of the regional partition resource atlas to obtain partition resource consumption data;

[0035] Step S23: Perform time series analysis based on the partition resource consumption data to obtain partition time series resource consumption data;

[0036] Step S24: Identify the resource consumption pattern of the partition time series resource consumption data to obtain regional resource consumption pattern data;

[0037] Step S25: Screen the resource consumption pattern characteristics of the regional resource consumption pattern data to obtain resource consumption impact factors, and construct a regional resource consumption prediction model based on the resource consumption impact factors.

[0038] Through data spatio-temporal alignment, the present invention solves the problem of inconsistency in the acquisition spatio-temporal dimensions between remote sensing data and sensing data, laying a unified data foundation for subsequent analysis and ensuring the organic integration of information from different data sources. By integrating the regional resource distribution characteristics of the aligned remote sensing data, the spatial distribution characteristics of resources in the monitored area are accurately characterized, providing a reliable basis for subsequent resource utilization analysis and planning. In the process of performing spatio-temporal clustering analysis on sensing data for hotspot areas, the key nodes of resource consumption and high-frequency activity areas within the region are mined, and combined with attribute classification, the functional characteristics and resource attributes of different hotspot areas are further revealed, providing clear guidance for resource regulation and key area management. The resource relationship modeling carried out based on the resource distribution data systematically expresses the interaction and dynamic connection between resources, making the analysis of resource utilization efficiency more scientific and systematic. Through the construction and integration of the resource map, multi-source data, resource distribution characteristics, hotspot area information, and resource relationships are integrated into one, forming a comprehensive and dynamic resource map of the monitored area. This resource map provides powerful data support and analysis tools for natural resource audits, enabling the full presentation of the spatial distribution characteristics, consumption dynamics, and correlation relationships of resources, promoting the precision and intelligence of resource management. This not only solves the pain points of data isolation and insufficient analysis in traditional audits but also improves the reliability and scientificity of resource audit results, providing an important guarantee for achieving the goal of sustainable resource management.

[0039] Optionally, step S3 is specifically as follows:

[0040] Step S31: Use the regional resource consumption prediction model to predict the regional resource consumption trend of the resource map of the monitored area, thereby obtaining regional resource consumption trend prediction data;

[0041] Step S32: Convert the regional resource consumption trend prediction data into a spatio-temporal mapping diagram, thereby obtaining a regional resource consumption spatio-temporal mapping diagram;

[0042] Step S33: Conduct spatio-temporal dynamic analysis of the regional resource consumption spatio-temporal mapping diagram, thereby obtaining spatio-temporal dynamic data of resource consumption;

[0043] Step S34: Select risk factors based on the spatio-temporal dynamic data of resource consumption, thereby obtaining a set of resource consumption risk factors;

[0044] Step S35: Based on the set of resource consumption risk factors, divide the resource consumption risk areas of the regional partitioned resource map of the monitored area, thereby obtaining resource consumption risk area data.

[0045] Through the prediction of the regional resource consumption trend, the present invention can dynamically master the change trend of resource consumption in terms of time and space, so as to better understand the regularity and distribution characteristics of resource use. The transformation of the spatio-temporal mapping diagram integrates the resource consumption data in two dimensions of space and time, providing more intuitive dynamic information on resource distribution and consumption, which helps to better identify potential hot spots of resource consumption. By dynamically analyzing the spatio-temporal mapping diagram of resource consumption, the small changes in resource consumption at different times and in different spaces can be captured, so as to better warn of the instability and abnormal conditions of resource consumption. By selecting resource consumption risk factors based on dynamic data, the key factors that have a greater impact on resource consumption can be identified, so as to carry out targeted resource management and regulation. Finally, by dividing the risk areas of the partitioned resource atlas, the areas with greater risks of resource consumption can be clarified, so as to take targeted management measures to effectively reduce resource waste and protect the sustainability of resources. The whole process not only improves the comprehensiveness and accuracy of resource audit data, but also realizes the intelligence and systematization of resource consumption prediction, risk warning and management strategy optimization, thus ensuring the realization of the coordinated and sustainable development goal between resource development and protection.

[0046] Optionally, step S33 is specifically as follows:

[0047] Step S331: Perform spatio-temporal deconstruction processing on the spatio-temporal mapping diagram of regional resource consumption to obtain resource consumption time series layer data and resource consumption spatial distribution layer data;

[0048] Step S332: Identify the hot spots of resource consumption in the resource consumption spatial distribution layer data to obtain the resource consumption spatial hot spot area data; identify the hot spots of resource consumption time in the resource consumption spatial distribution layer data to obtain the resource consumption hot spot time data;

[0049] Step S333: Perform spatio-temporal clustering based on the resource consumption spatial hot spot area data and the resource consumption hot spot time data to obtain the resource consumption hot spot spatio-temporal data;

[0050] Step S334: Detect abnormal hot spots in the resource consumption hot spot spatio-temporal to obtain spatio-temporal abnormal hot spot data;

[0051] Step S335: Perform spatio-temporal autoregression based on the spatio-temporal abnormal hot spot data to obtain the resource consumption spatio-temporal dynamic data.

[0052] The present invention performs spatio-temporal deconstruction processing on the spatio-temporal mapping diagram of resource consumption, which can decompose resource consumption information into data at two levels of time and space, so as to more clearly analyze the distribution law of resources in time and space. By identifying hot spots and hot times for the data of the spatial distribution layer of resource consumption, the key hot spots of resource consumption can be accurately located, so as to carry out targeted resource management and monitoring. Spatio-temporal clustering analysis further integrates the hot spot information of resource consumption into spatio-temporal data, so as to realize the comprehensive management and prediction of hot spot areas and time periods of resource consumption. The abnormal hot spot detection technology can timely discover the abnormal phenomena existing in resource consumption, so as to warn of potential risks of resource waste, resource shortage or over-consumption. Finally, through spatio-temporal autoregressive modeling, dynamic modeling and prediction can be carried out based on the detected spatio-temporal abnormal hot spot data, so as to provide a more forward-looking and operable resource consumption management strategy. These steps not only enhance the data accuracy of resource auditing and monitoring, but also realize the dynamic prediction and risk control of resource consumption in two dimensions of time and space, thus ensuring the efficient achievement of the goal of sustainable development and management of resources.

[0053] Optionally, step S35 is specifically as follows:

[0054] Step S351: Perform factor screening and standardization on the resource consumption risk factor set to obtain a screened risk factor set;

[0055] Step S352: Perform multi-dimensional factor mapping construction on the regional partition resource map according to the screened risk factor set to obtain a multi-dimensional factor map;

[0056] Step S353: Extract partition feature vectors from the multi-dimensional factor map to obtain partition feature vector data, and perform partition mode clustering according to the partition feature vector data to obtain multi-dimensional factor partition clustering data;

[0057] Step S354: Perform consumption amount feature extraction and consumption fluctuation feature extraction based on the multi-dimensional factor partition clustering data to obtain clustering partition consumption amount data and clustering partition consumption fluctuation data;

[0058] Step S355: Construct a partition risk level division rule according to the clustering partition consumption amount data and the clustering partition consumption fluctuation data;

[0059] Step S356: Construct a risk area division model based on the regional partition resource map and the partition risk level division rule, and perform resource consumption risk area division according to the risk area division model to obtain resource consumption risk area data.

[0060] The present invention screens and standardizes the resource consumption risk factor set, which can eliminate redundant factors and improve the comparability of factors, so as to obtain a more reliable risk factor set. Based on these screened factors, by constructing the regional partition resource map and multi-dimensional factor mapping, the risk factors can be deeply integrated with the resource distribution, so as to obtain a factor map with a more multi-dimensional perspective. By extracting the partition feature vectors of the multi-dimensional factor map and performing cluster analysis, the patterns of resource distribution and risk factors can be efficiently integrated and identified, so as to form clearer partition clustering data. By extracting the consumption and consumption fluctuation data of the clustering partitions, the consumption trend and fluctuation law of resources in different partitions can be revealed, so as to better evaluate the stability and risk of resources. According to these data, by constructing the partition risk level division rules, the resource consumption risk can be systematically and quantitatively divided into levels, so as to provide a more operable risk management standard. By constructing a risk area division model based on the partition resource map and risk level division rules, the risk distribution information can be efficiently mapped to the actual regional distribution, realizing the intelligent division and early warning of resource consumption risk. This not only improves the intelligence and efficiency of resource management and auditing, but also helps to achieve the goals of sustainable development and long-term safety management of resources, thus better supporting the sustainable development strategy.

[0061] Optionally, step S4 is specifically as follows:

[0062] Step S41: Obtain the resource development process data of the monitoring area, and perform spatial association on the resource development process data of the monitoring area and the regional partition resource map, so as to obtain the regional partition resource development process data;

[0063] Step S42: Extract the high-risk area development process from the regional partition resource development process data according to the resource consumption risk area data, so as to obtain the high-risk area development process data;

[0064] Step S43: Decompose the high-risk area development process data into links, so as to obtain the high-risk area development link data;

[0065] Step S44: Evaluate the efficiency of the high-risk area resource development links according to the partition resource consumption data and the high-risk area development link data, so as to obtain the efficiency data of the high-risk area resource development links;

[0066] Step S45: Identify the inefficient development links from the efficiency data of the high-risk area resource development links, so as to obtain the efficiency data of the inefficient development links in the high-risk area.

[0067] The present invention spatially correlates the data of the resource development process in the monitored area with the resource atlas of the regional partition, which can achieve a closer integration between resource development activities and resource distribution, thereby providing a more comprehensive understanding of the spatial characteristics and correlations of regional resource development. By extracting the development process in high-risk areas, it is possible to accurately identify the regional development links with relatively high resource consumption risks, and thus carry out targeted risk control. By decomposing these development processes into links, the risk analysis can be refined, and the specific situations of each link in terms of resource consumption and development efficiency can be gradually clarified. By combining the partitioned resource consumption data with the development link data in high-risk areas for resource development link efficiency evaluation, the efficiency level in the resource development process can be quantified, and the phenomena of resource waste and inefficient utilization can be identified, thereby optimizing the development process. By identifying inefficient links from the efficiency data of resource development links in risk areas, the key nodes with efficiency problems in development can be intuitively located, which helps to take more effective improvement measures. This not only improves the efficiency and economy of resource development links, but also reduces resource waste and environmental impacts, thereby supporting the sustainable development goal. Through systematic process analysis and risk identification, these steps contribute to the intelligent control of resource development and management, improve the safety, sustainability and long-term management effect of resource development, and thus provide a more scientific and efficient decision-making basis for resource management and sustainable development strategies.

[0068] Optionally, this specification also provides an audit system for natural resources, which is used to execute the audit method for natural resources as described above. The audit system for natural resources includes:

[0069] A resource data atlas combination module, which is used to obtain remote sensing data and sensing data of the monitored area, and perform data enhancement on the remote sensing data and sensing data of the monitored area respectively, so as to obtain enhanced remote sensing data and enhanced sensing data of the area; based on the enhanced remote sensing data and enhanced sensing data of the area, perform resource data atlas combination to obtain a resource atlas of the monitored area;

[0070] A resource consumption modeling module, which is used to identify resource consumption patterns based on the resource atlas of the monitored area to obtain regional resource consumption pattern data; perform resource consumption modeling based on the regional resource consumption pattern data to obtain a regional resource consumption prediction model;

[0071] A resource consumption risk area division module, which is used to predict the regional resource consumption trend of the resource atlas of the monitored area according to the regional resource consumption prediction model to obtain regional resource consumption trend prediction data; perform division of the resource consumption risk area of the monitored area based on the regional resource consumption trend prediction data to obtain resource consumption risk area data;

[0072] The development link efficiency evaluation module is used to evaluate the efficiency of the resource development link in the risk area data of the resource consumption risk area according to the resource atlas of the monitoring area, so as to obtain the efficiency data of the resource development link in the risk area; identify the inefficient development link for the efficiency data of the resource development link in the risk area, so as to obtain the efficiency data of the inefficient development link in the risk area.

[0073] The audit compliance analysis module is used to conduct regional natural resource audit compliance analysis based on the efficiency data of the inefficient development link in the risk area and the regional resource consumption trend prediction data, so as to obtain a natural resource management compliance report.

[0074] The audit system of natural resources of the present invention can implement any audit method of natural resources of the present invention, and is used as a medium for coordinating the operations and signal transmissions between various modules to complete the audit method of natural resources. The internal modules of the system cooperate with each other, thereby improving the comprehensiveness, accuracy and efficiency of natural resource audits. Brief Description of the Drawings

[0075] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objectives and advantages of the present invention will become more obvious:

[0076] Figure 1 It is a schematic flow chart of the steps of the audit method of natural resources of the present invention;

[0077] Figure 2 It is a detailed schematic flow chart of step S1 in the present invention;

[0078] Figure 3 It is a detailed schematic flow chart of step S2 in the present invention;

[0079] The realization, functional characteristics and advantages of the objectives of the present invention will be further described in conjunction with the embodiments with reference to the drawings. Detailed Embodiments

[0080] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0081] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0082] It should be understood that although terms such as "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0083] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides an audit method for natural resources, and the method includes the following steps:

[0084] Step S1: Obtain remote sensing data and sensing data of the monitoring area, and perform data enhancement on the remote sensing data and sensing data of the monitoring area respectively, so as to obtain enhanced remote sensing data and enhanced sensing data of the area; perform resource data map combination based on the enhanced remote sensing data and enhanced sensing data of the area, so as to obtain a resource map of the monitoring area;

[0085] In this embodiment, when obtaining the remote sensing data of the monitoring area, hyperspectral remote sensing image acquisition technology is used to obtain multispectral data covering the monitoring area, and feature extraction and optimization are performed on the remote sensing image through a multispectral band enhancement algorithm. For example, the infrared band is enhanced for vegetation cover analysis, and the blue band is enhanced for water body distribution extraction. At the same time, when obtaining the sensing data of the monitoring area, multi-sensor fusion technology is used, including temperature and humidity sensors, soil monitoring sensors, etc., and the quality and integrity of the data are improved through denoising and interpolation algorithms. The enhanced remote sensing data is used to extract the topographic features and resource distribution of the area, and combined with the dynamic environmental parameters in the sensing data, a resource map of the monitoring area is constructed based on the topological relationship model, specifically including a mineral distribution map, a vegetation resource distribution map, etc.

[0086] Step S2: Identify the resource consumption pattern based on the resource map of the monitoring area, so as to obtain regional resource consumption pattern data; perform resource consumption modeling according to the regional resource consumption pattern data, so as to obtain a regional resource consumption prediction model;

[0087] In this embodiment, based on the resource atlas of the monitoring area, a clustering analysis algorithm is used to identify the regional resource consumption patterns. Specifically, the K-means clustering method can be used to extract the high-frequency areas and abnormal change areas of resource utilization, such as identifying the high-consumption areas of farmland irrigation water and the seasonal fluctuation trends. Resource consumption modeling is established through a time series model (such as LSTM) to predict the dynamic resource consumption. For example, for agricultural areas, by integrating the soil humidity, climate parameters in the sensor data and the vegetation growth index of remote sensing images, an agricultural water consumption prediction model is constructed to quantify the irrigation demand trend in the region for the next year.

[0088] Step S3: According to the regional resource consumption prediction model, predict the regional resource consumption trend of the resource atlas of the monitoring area to obtain the regional resource consumption trend prediction data; based on the regional resource consumption trend prediction data, divide the resource consumption risk areas of the monitoring area to obtain the resource consumption risk area data;

[0089] In this embodiment, according to the regional resource consumption prediction model, predict the trends of the key regional resources in the resource atlas of the monitoring area. Specifically, a prediction model based on regression analysis can be used. For example, in industrial areas, using the energy consumption data recorded by factory sensors and combining with the historical data of regional electricity consumption, predict the industrial electricity consumption trend and generate the regional resource consumption trend prediction data. Based on the trend prediction results, use geographic information system (GIS) to conduct spatial analysis on the risk areas to identify the high-risk areas with abnormal growth in consumption, such as areas with excessive industrial electricity loads and areas with shortages of irrigation water. Finally, generate the resource consumption risk area data and display the risk level through regional grading.

[0090] Step S4: According to the resource atlas of the monitoring area, evaluate the efficiency of the resource development links in the resource consumption risk areas to obtain the efficiency data of the resource development links in the risk areas; identify the inefficient development links from the efficiency data of the resource development links in the risk areas to obtain the efficiency data of the inefficient development links in the risk areas;

[0091] In this embodiment, perform partitioned resource development efficiency analysis on the data of the resource consumption risk areas. Specifically, an efficiency evaluation algorithm based on principal component analysis is used. For example, in the water resource development process in high-risk areas, for the three links of pumping, conveying and irrigation, evaluate the equipment operation efficiency, energy consumption ratio and water loss rate respectively. For the identification of inefficient links, by introducing an effectiveness threshold determination method, mark the links with actual operation efficiency lower than the set value. For example, if it is found that a certain water conveyance pipeline has a high leakage problem during long-term conveyance, it is determined as an inefficient development link. After marking the inefficient links, the output efficiency data is used for subsequent optimization suggestions.

[0092] Step S5: Conduct regional natural resources audit compliance analysis based on the efficiency data of inefficient development links in the risk area and the predicted data of regional resource consumption trends, so as to obtain a natural resources management compliance report.

[0093] In this embodiment, based on the efficiency data of inefficient development links in the risk area and the predicted data of regional resource consumption trends, an audit analysis of the regional natural resources management is carried out. For example, for the water resources development in the agricultural area, using GIS analysis combined with audit compliance standards (such as the norms for water resources development), a compliance review is carried out on high-risk areas with excessive extraction or illegal occupation; combined with the predicted data to verify whether resource overload may occur due to development behaviors in a certain period in the future. Finally, a natural resources management compliance report is generated, including a list of specific problems (such as high-loss development caused by failure to update equipment according to regulations) and optimization suggestions, such as suggesting the adoption of efficient water pumps or optimizing the pipeline layout, so as to improve the compliance and sustainability of regional natural resources development.

[0094] Optionally, step S1 is specifically:

[0095] Step S11: Obtain remote sensing data of the monitoring area and sensing data of the monitoring area;

[0096] In this embodiment, a multi-spectral remote sensing image acquisition device is used to obtain high-resolution remote sensing data covering the monitoring area. For example, satellite images are used to capture terrain changes and vegetation coverage. At the same time, various types of sensors are deployed in the monitoring area, such as temperature and humidity sensors, carbon dioxide concentration sensors, and groundwater level monitoring sensors, to regularly collect the environmental dynamic data in the area. The remote sensing data is stored in the GeoTIFF format, and the sensing data is uploaded to the data center through the Internet of Things gateway to form a complete original data set.

[0097] Step S12: Perform data preprocessing on the remote sensing data of the monitoring area and the sensing data of the monitoring area respectively, so as to obtain the remote sensing data of the area to be analyzed and the sensing data of the area to be analyzed;

[0098] In this embodiment, when preprocessing the remote sensing data, first, a radiation correction method is used to remove atmospheric interference. For example, a correction algorithm based on the 6S model is used to improve the image brightness and contrast; then a noise filtering algorithm (such as median filtering) is used to remove the random noise in the image. When processing the sensing data, data interpolation technology is used to fill in the missing values, the moving average algorithm is used to smooth the time series data, and outliers (such as sensor readings exceeding the threshold) are corrected. The finally obtained remote sensing data and sensing data of the area to be analyzed are stored in the GeoJSON format and the CSV format respectively.

[0099] Step S13: Perform remote sensing data enhancement according to the remote sensing data of the area to be analyzed, so as to obtain enhanced remote sensing data of the area;

[0100] In this embodiment, when enhancing the remote sensing data of the area to be analyzed, an image enhancement algorithm is adopted. For example, histogram equalization technology is used to improve the dynamic range and contrast of the image; combined with a convolutional neural network (CNN) for target enhancement processing, such as improving the resolvability of NDVI (Normalized Difference Vegetation Index) for vegetation-covered areas. In addition, through band operation, topographic features (such as elevation and slope) are extracted to optimize the available information volume of the remote sensing image, thereby generating regionally enhanced remote sensing data for subsequent analysis.

[0101] Step S14: Enhance the sensing data according to the sensing data of the area to be analyzed, so as to obtain regionally enhanced sensing data;

[0102] In this embodiment, for the sensing data of the area to be analyzed, a time series pattern extraction algorithm is used to enhance the data. For example, the sensor time series signal is decomposed by wavelet transform to extract the low-frequency components related to resource changes; the dynamic time warping (DTW) method is used to align the data of different sensors in time to enhance their time correlation. In addition, a weighted fusion method is used to combine the monitoring data of multiple sensors into a unified format, such as synthesizing soil moisture, temperature, and rainfall data into comprehensive index data reflecting irrigation status.

[0103] Step S15: Combine the enhanced regional remote sensing data and the enhanced regional sensing data to obtain the resource data map of the monitoring area.

[0104] In this embodiment, when constructing the resource data map based on the enhanced regional remote sensing data and sensing data, a topological analysis method based on a geographic information system (GIS) is adopted. First, the topographic map generated from the remote sensing data is spatially registered with the dynamic environmental data collected by the sensor, such as precisely matching the farmland boundary in the remote sensing image with the location of the soil moisture monitoring point. Then, data fusion technology (such as the weight assignment method) is used to merge the data from different sources to generate the resource data map of the monitoring area, specifically including the soil fertility distribution map, the vegetation coverage map, and the water resource monitoring network map, providing a basis for subsequent resource consumption analysis.

[0105] Optionally, step S13 is specifically:

[0106] Extract the band reflectance of the remote sensing data of the area to be analyzed to obtain the regional remote sensing band reflectance data, and perform multi-spectral band enhancement on the regional remote sensing band reflectance data to obtain the remotely sensed enhanced band reflectance data;

[0107] In this embodiment, when extracting the band reflectance, the Flaash (atmospheric correction module) algorithm is used to perform radiometric correction and atmospheric correction on the original remote sensing image. The atmospheric scattering and absorption effects are eliminated through spectral calibration methods to obtain the band reflectance data. The extracted bands include visible light bands (such as red, green, blue) and near-infrared bands, which are used to distinguish the characteristic reflectances of vegetation cover, soil, and water bodies. Taking the Sentinel-2 satellite image as an example, 12-band data with a 10m resolution are extracted and saved in a multi-layer raster format (GeoTIFF). For the extracted band reflectance data, the principal component analysis (PCA) method is used for dimensionality reduction, and the important bands are enhanced. For example, the band weight of NDVI (Normalized Difference Vegetation Index) is increased to highlight the vegetation health information; the color of the water body band is enhanced by combining the interactive spectral matching method to make different water quality characteristics more clearly distinguishable. Specifically, when implementing, the enhanced band reflectance data are generated through the multi-spectral tool in the ArcGIS software to improve the distinguishability of surface features.

[0108] Perform remote sensing image transformation enhancement on the remote sensing data of the area to be analyzed, so as to obtain the remotely sensed data of image transformation enhancement;

[0109] In this embodiment, geometric transformation algorithms are used to enhance the remote sensing image, including histogram matching (matching the color and brightness distributions of the reference image) and local contrast enhancement (CLAHE algorithm), to optimize the overall visual effect and detail level of the image. In addition, the dynamic range of the gray values of the image is compressed to eliminate the overexposure phenomenon in the highlight area. The results are saved in the GeoTIFF format and can be directly used for spatial analysis.

[0110] Perform radiometric enhancement on the remote sensing data of the area to be analyzed, so as to obtain the remotely sensed data of radiometric enhancement;

[0111] In this embodiment, two methods of linear stretching and exponential stretching are used to enhance the gray range of the image, making the details in the low reflectance area more prominent. Especially for the desert surface in arid regions, the visibility is improved by enhancing the highlight part of the reflectance value. Combining with the radiometric enhancement module of the ENVI software, an adjusted image is further generated to enhance the distinguishability of the image in the extreme reflectance area.

[0112] Perform Gaussian noise natural interference simulation on the remote sensing data of the area to be analyzed, so as to obtain the remotely sensed data of noise;

[0113] In this embodiment, a Gaussian random noise generation algorithm is used to simulate natural interferences in the real environment (such as sensor noise, atmospheric condition changes). The noise parameters are set to a mean of 0 and a standard deviation of 0.05 to ensure that the intensity of the noise is similar to the natural interferences in the actual remote sensing image. After processing, the generated remotely sensed data of noise are used for the robustness test of the model.

[0114] Regional remote sensing enhanced data fusion is performed based on remote sensing enhanced band reflectance data, image transformation enhanced remote sensing data, radiation enhanced remote sensing data, and noise remote sensing data, thereby obtaining regional enhanced remote sensing data.

[0115] In this embodiment, a multi-source data fusion method based on weight assignment is adopted. Through a weighted superposition algorithm (the weight ratio is 40% for band reflectance data, 30% for image transformation data, 20% for radiation enhanced data, and 10% for noise data), comprehensive enhanced remote sensing data is generated. In specific implementation, Python and GDAL tools are used for multi-layer data fusion processing. The output enhanced data can simultaneously highlight the characteristics of vegetation, soil, and water bodies, and retain the authenticity verification effect of Gaussian noise. The final result is stored in the GeoTIFF format with a resolution of 10m and can be directly used for spatial analysis and resource assessment.

[0116] Optionally, step S15 is specifically as follows:

[0117] Step S151: Perform data spatio-temporal alignment on the enhanced regional remote sensing data and the enhanced regional sensing data, thereby obtaining regional aligned remote sensing data and regional aligned sensing data;

[0118] In this embodiment, the remote sensing data and the sensing data are aligned by using a spatio-temporal interpolation method to ensure that the data timestamps and spatial ranges of both are consistent. For the remote sensing data, a linear temporal interpolation method is adopted to unify the image acquisition time to the time node of the sensing data; for spatial alignment, a raster interpolation method is used to make the geographical resolutions of both consistent. Taking Sentinel-2 satellite data as an example, with a resolution of 10m, aligned data is generated after matching with the temperature and humidity data collected by the sensor.

[0119] Step S152: Integrate the regional resource distribution characteristics of the regional aligned remote sensing data, thereby obtaining regional resource distribution data;

[0120] In this embodiment, a geographically weighted regression (GWR) model is used to perform integrated analysis on the aligned remote sensing data, and resource characteristics such as land type, vegetation coverage rate, and water body distribution within the region are extracted. The integration method includes calculating the vegetation coverage rate by using the normalized difference vegetation index (NDVI), identifying the water body distribution area through the normalized difference water index (NDWI), and finally generating a resource distribution map. The result is output in the vector data format (Shapefile), which is convenient for spatial analysis and overlay.

[0121] Step S153: Perform spatio-temporal clustering analysis on the hotspots of the regional aligned sensing data, thereby obtaining regional hotspot data, and perform attribute classification on the regional hotspot data, thereby obtaining regional hotspot attribute data;

[0122] In this embodiment, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to perform spatio-temporal clustering analysis on the high-value regions in the sensing data to identify hotspots with intensive resource consumption or significant environmental changes. Based on the clustering results, a support vector machine (SVM) model is combined to classify the attributes of the hotspots (such as high-temperature areas, wetlands, infertile soil areas) to generate hotspot attribute data. Specifically, clustering and classification calculations are performed through the scikit-learn library in Python to generate the classified hotspot region data.

[0123] Step S154: Based on the regional resource distribution data, perform resource relationship modeling to obtain resource relationship data;

[0124] In this embodiment, a graph theory modeling method is used to model the resource nodes (such as water bodies, vegetation, cultivated land) in the resource distribution data and their mutual relationships (such as distance, resource flow paths). The specific steps include defining node weights (such as water body area, vegetation coverage) and edge weights (such as resource transportation cost) to generate a resource relationship graph. The resource relationship data constructed through the NetworkX library is stored in JSON format for further integration and analysis.

[0125] Step S155: According to the resource relationship data and the regional hotspot attribute data, perform resource atlas construction and integration to obtain the monitoring area resource atlas.

[0126] In this embodiment, a fusion algorithm is used to integrate the resource relationship data and the hotspot attribute data to generate a unified resource atlas. The specific process includes: associating the node attributes (such as resource type, distribution characteristics) of the resource relationship graph with the classification attributes (such as peak resource consumption, environmentally sensitive areas) of the hotspot regions, and improving the retrieval efficiency of the atlas through a graph structure optimization algorithm (such as minimum spanning tree). The result is output in GeoJSON format, providing a comprehensive and intuitive representation of the regional resources and can be used for subsequent dynamic monitoring and analysis.

[0127] Optionally, step S2 is specifically:

[0128] Step S21: Based on the monitoring area resource atlas, perform regional partitioning of resource attribute characteristic regions to obtain a regional partition resource atlas;

[0129] In this embodiment, through clustering analysis of the spatial characteristics of resource attributes (such as land use type, vegetation coverage rate, water body distribution, etc.) in the monitoring area resource atlas, the regional partition range is delimited. The K-means algorithm is used for unsupervised clustering of different resource characteristic data, and the partitioning criteria include similar resource attributes, terrain proximity, etc. For example, agricultural land, forest land, and water areas are respectively divided into independent regional partitions, and finally a regional partition resource atlas is generated and stored in vector data format.

[0130] Step S22: Perform principal component analysis on the resource consumption characteristics of the regional partition resource atlas to obtain partition resource consumption data;

[0131] In this embodiment, the principal component analysis (PCA) technique is used to perform dimensionality reduction on the resource consumption data (such as water resource usage, land development intensity, etc.) of the regional partition, and the main influencing characteristics of resource consumption are extracted. First, standardize the resource consumption data, and then determine the principal components with a cumulative variance contribution rate of more than 95% through PCA. For example, the extracted principal components may include the water resource supply-demand balance index, land use intensity coefficient, etc., to generate a partition resource consumption data table.

[0132] Step S23: Perform time series analysis based on the partition resource consumption data to obtain partition time series resource consumption data;

[0133] In this embodiment, the partition resource consumption data is serially analyzed in the time dimension, and the autoregressive integrated moving average (ARIMA) model is used to predict the time series trend of resource consumption. The resource consumption data of each partition is sampled at daily, monthly, or annual time intervals, and a time series modeling tool (such as the statsmodels library in Python) is used to fit the consumption trend. For example, for the water resource consumption data of a certain agricultural area, the water consumption demand trend in the next quarter can be predicted, and the partition time series resource consumption data is output.

[0134] Step S24: Identify the resource consumption pattern for the partition time series resource consumption data to obtain the regional resource consumption pattern data;

[0135] In this embodiment, a machine learning algorithm (such as support vector machine SVM or random forest RF) is combined to identify the pattern of the partition time series resource consumption data and extract the consumption rules. The specific analysis includes the consumption characteristics during peak and trough periods, as well as the identification of abnormal consumption events. Taking a certain urban area as an example, through pattern recognition, it is found that the water consumption in the industrial area increases significantly in winter, or abnormal short-term high-energy-consuming events are detected, and the regional resource consumption pattern data is generated.

[0136] Step S25: Screen the resource consumption pattern characteristics of the regional resource consumption pattern data to obtain the resource consumption influencing factors, and construct a regional resource consumption prediction model based on the resource consumption influencing factors.

[0137] In this embodiment, feature screening algorithm (such as LASSO regression or Recursive Feature Elimination, RFE) is used to screen the features of the regional resource consumption pattern data, and key factors affecting the consumption pattern are extracted, such as seasonality, industrial type, policy adjustment, etc. Based on the extracted influencing factors, a resource consumption prediction model is constructed using regression analysis or deep learning model (such as LSTM network). During implementation, historical consumption data and influencing factors are used as training data to input into the model, and the resource consumption prediction results are output, such as predicting the water resource demand of each sub-region in the next year. The model results are stored in JSON or visual chart format.

[0138] Optionally, step S3 is specifically as follows:

[0139] Step S31: Use the regional resource consumption prediction model to predict the regional resource consumption trend of the monitored regional resource atlas, so as to obtain the regional resource consumption trend prediction data;

[0140] In this embodiment, the constructed resource consumption prediction model is used to combine with the spatial distribution information of the monitored regional resource atlas to predict the change trend of resource consumption in the future for a period of time. For example, based on prediction factors such as land use intensity and water resource utilization rate, the regression analysis model is used to predict the change trend of water resource demand in each region in the next five years, and generate consumption trend prediction data in units of sub-regions. The results may include the increase and decrease of resource consumption in each time period within the region and possible consumption peaks.

[0141] Step S32: Convert the regional resource consumption trend prediction data into a spatio-temporal mapping diagram, so as to obtain the regional resource consumption spatio-temporal mapping diagram;

[0142] In this embodiment, the regional resource consumption trend prediction data is combined with the geographical information of the monitored region, and the geographical information system (GIS) technology is used to generate an intuitive spatio-temporal mapping diagram. In the specific implementation process, the regional resource consumption trend prediction data is visualized by stratification in the time dimension, and the change trend of the consumption amount is represented by the color gradient or the size of the marked points. For example, different colors are used to represent the increase or decrease trend of water consumption, and a dynamically changing mapping diagram is generated for analysis.

[0143] Step S33: Conduct spatio-temporal dynamic analysis on the regional resource consumption spatio-temporal mapping diagram, so as to obtain the spatio-temporal dynamic data of resource consumption;

[0144] In this embodiment, based on the spatio-temporal mapping diagram of regional resource consumption, spatio-temporal analysis techniques (such as Geographically Weighted Regression (GWR) or spatio-temporal hot spot analysis) are used to analyze the dynamic change law of resource consumption. For example, identify the rapidly changing areas (hot spots) and consumption-reducing areas (cold spots) of consumption in a specific area during a certain time period, summarize the spatio-temporal change laws within different time cycles, and generate spatio-temporal dynamic data of resource consumption, including indicators such as consumption hot spots and trend fluctuations.

[0145] Step S34: Select risk factors according to the spatio-temporal dynamic data of resource consumption, so as to obtain a set of resource consumption risk factors;

[0146] In this embodiment, by analyzing the spatio-temporal dynamic data of resource consumption and combining statistical analysis with expert experience, key risk factors that have a significant impact on resource consumption are extracted. For example, based on the resource consumption growth pattern in hot spots, factors that may lead to resource shortages are screened out, such as excessive population density, rapid industrial development, or the impact of natural disasters. The risk factor selection uses stepwise regression or correlation analysis to ensure that the selected factors have a high interpretability for risk zone division. The risk factors are selected according to the spatio-temporal dynamic data of resource consumption to obtain a set of resource consumption risk factors. First, key characteristic indicators related to the change in resource consumption are extracted from the spatio-temporal dynamic data of regional resource consumption, such as population growth rate, change in industrial water consumption, change in land use pattern, and climate anomaly data. Then, combined with regional economic and social data (such as socio-economic indicators of the statistical bureau and climate change data of the meteorological department) and environmental monitoring data (such as water quality and water volume monitoring data), a unified multi-dimensional data set is formed. On this basis, correlation analysis is carried out, and statistical methods (such as Pearson correlation coefficient or Spearman rank correlation coefficient) are used to quantify the relationship between each potential factor and resource consumption fluctuations, and factors significantly related to the resource consumption trend are screened out. For example, analysis shows that the correlation coefficient between the growth of industrial water demand and the total water resource consumption in a certain region reaches 0.85, indicating that industrial expansion is an important driving factor for resource consumption. Then, principal component analysis (PCA) is used for multiple related factors to reduce the data dimension and extract the main driving factors. For example, agricultural irrigation area, proportion of agricultural land, and agricultural water consumption are combined into the "agricultural expansion" principal component. In addition, the analytic hierarchy process (AHP) or entropy method is used to calculate the weights of the selected factors, and corresponding weights are assigned according to the contribution degree of the factors to the resource consumption risk. For example, the weight analysis shows that the weight of "population growth rate" is 0.35, and the weight of "increase in industrial water consumption" is 0.25. Finally, according to the analysis results, a set of resource consumption risk factors is constructed, recording the specific description, weight value, and data source of each factor to ensure the scientificity and practicality of the results. For example, the risk factors include "population growth rate", "increase in industrial water consumption", "variation coefficient of precipitation", etc., and the weights of each factor are 0.35, 0.25, 0.20 in turn, and the data sources are marked as data from the National Bureau of Statistics, regional economic reports, and meteorological monitoring departments. The finally output set of risk factors will be used in the subsequent analysis of resource consumption risk zone division.

[0147] Step S35: Based on the set of resource consumption risk factors, the resource consumption risk zones of the regional partition resource map are divided to obtain resource consumption risk zone data.

[0148] In this embodiment, by combining the resource consumption risk factor set and the regional partition resource atlas, a spatial analysis tool (such as ArcGIS) is used to divide the resource consumption risk areas. The weighted overlay analysis method is adopted to generate the regional risk assessment results according to the influence weights of each factor, and the monitoring area is divided into high, medium, and low risk areas. For example, areas with high water demand and ecological sensitivity are marked as high risk areas, and the risk area data is output and stored in the form of a vector layer or a table for further decision-making analysis and management planning.

[0149] Optionally, step S33 is specifically as follows:

[0150] Step S331: Perform spatio-temporal deconstruction processing on the regional resource consumption spatio-temporal mapping diagram to obtain resource consumption time series layer data and resource consumption spatial distribution layer data;

[0151] In this embodiment, when deconstructing the regional resource consumption spatio-temporal mapping diagram, the data characteristics of the time dimension and the spatial dimension are first extracted. For example, a time series decomposition algorithm (such as a sliding window decomposition method or Fourier transform) is used to extract the daily total resource consumption change trend from the spatio-temporal mapping diagram to generate time series layer data, such as the daily average power consumption value of a certain area, accurate to hours or minutes. At the same time, using geographic information system (GIS) technology and raster analysis tools, the spatial dimension is analyzed, the area is divided into multiple grid cells, the resource consumption intensity in each cell is calculated, and spatial distribution layer data is generated, such as the unit water resource consumption per square kilometer in a certain area. Further, a complete resource consumption distribution map is generated by combining spatial interpolation methods (such as Kriging interpolation) to support subsequent analysis.

[0152] Step S332: Identify the resource consumption hot spot areas from the resource consumption spatial distribution layer data to obtain the resource consumption spatial hot spot area data; identify the resource consumption hot spot times from the resource consumption spatial distribution layer data to obtain the resource consumption hot spot time data;

[0153] In this embodiment, a hot spot analysis method, such as the Getis-Ord Gi* statistic, is used for the resource consumption spatial distribution layer data to identify high resource consumption areas. In the specific operation, an analysis window (such as 5 square kilometers) is selected, and it is calculated whether the resource consumption value in each window is significantly higher than the neighborhood mean. For example, when analyzing the water consumption data of a certain city, it is identified that the commercial area and the industrial area are the spatial hot spot areas with the highest average annual water consumption. For the time series layer data, an anomaly detection algorithm (such as a moving average or quantile analysis method) is used to determine the significant peak periods. For example, the analysis shows that July to August is the peak period of summer electricity consumption, and the consumption from 12:00 to 15:00 every day is much higher than other periods.

[0154] Step S333: Perform spatio-temporal clustering based on the resource consumption spatial hotspot area data and the resource consumption hotspot time data, so as to obtain the resource consumption hotspot spatio-temporal data;

[0155] In this embodiment, the spatio-temporal clustering algorithm combines the spatial hotspot area and the time hotspot data. For example, using the spatio-temporal K-means algorithm, input the spatial hotspots and time peak information of resource consumption, cluster the high-consumption areas and high-consumption periods, and output the hotspot groups. For example, the electricity consumption in a certain industrial park surges in summer, forming a spatio-temporal hotspot, whose characteristics are "from July to August, the electricity consumption on weekdays is significantly higher than that on weekends". The clustering results also show that the peak time of resource consumption in this industrial park overlaps with that of the nearby residential areas, providing data support for optimizing resource allocation.

[0156] Step S334: Detect abnormal hotspots in the resource consumption hotspot spatio-temporal, so as to obtain the spatio-temporal abnormal hotspot data;

[0157] In this embodiment, when detecting the resource consumption hotspot spatio-temporal data, the Local Outlier Factor (LOF) algorithm is used to analyze whether the hotspot deviates from the normal pattern. In specific operations, calculate the neighborhood characteristics (such as the mean and standard deviation of the time series) of each spatio-temporal hotspot, and then compare and detect the outliers. For example, it is found that the water resource consumption in a certain area suddenly surges in the non-production season. After analysis, it is determined that the anomaly is caused by a broken water supply pipe network. Timely repair avoids resource waste. In addition, an abnormal peak is identified in the electricity consumption hotspot. After verification, it is an illegal electricity consumption behavior, ensuring the safety of energy management.

[0158] Step S335: Perform spatio-temporal autoregression based on the spatio-temporal abnormal hotspot data, so as to obtain the resource consumption spatio-temporal dynamic data.

[0159] In this embodiment, a STARIMA (Spatio-Temporal Autoregressive Integrated Moving Average) model is constructed, and the spatio-temporal abnormal hotspot data is used to predict the dynamic trend of resource consumption. First, input the abnormal hotspot data into the model for training to determine its spatio-temporal dependence relationship and influencing factors. Then generate the future spatio-temporal dynamic map through prediction. For example, the model prediction shows that the industrial electricity consumption in a certain area will continue to rise in the next two months due to the continuous high temperature weather, which may lead to a tight power supply. At this time, a load distribution plan can be formulated in advance in combination with the dynamic data to optimize resource scheduling. Through this autoregressive prediction, not only can future high-consumption spatio-temporal hotspots be identified, but also a decision-making basis can be provided for emergency management.

[0160] Optionally, step S35 is specifically:

[0161] Step S351: Screen and standardize the resource consumption risk factor set, so as to obtain the screened risk factor set;

[0162] In this embodiment, the resource consumption risk factor set is screened. Specifically, it includes performing correlation analysis (such as Pearson correlation coefficient) on the original factors to remove redundant factors. For example, factors highly correlated with power demand, climate conditions, population density, industrial activity intensity, etc. are retained from the dataset. Then, the screened risk factors are standardized using the Z-score standardization method to convert the values of each factor into data with zero mean and unit standard deviation. For example, if the average value of the power consumption factor in a certain region is 100 MW and the standard deviation is 20 MW, the power factor values of each region are converted into standard scores. This standardization ensures that all factors are comparable and provides a standardized input for subsequent data mapping and clustering analysis.

[0163] Step S352: Based on the screened risk factor set, perform multi-dimensional factor mapping construction on the regional partition resource map to obtain a multi-dimensional factor map.

[0164] In this embodiment, based on the screened risk factor set, these factors are mapped into the regional partition resource map using multi-dimensional space mapping techniques (such as multi-dimensional interpolation method). Specifically, within each partition unit, the risk factors are combined with the resource distribution data. For example, in the industrial area distribution map, factors such as power consumption, temperature, climate, population density, etc. are mapped into each partition unit one by one to generate a multi-dimensional factor map. This can visually represent the resource risk characteristics of each partition, such as the relationship between power demand distribution and climate change.

[0165] Step S353: Extract the partition feature vectors from the multi-dimensional factor map to obtain partition feature vector data, and perform partition pattern clustering based on the partition feature vector data to obtain multi-dimensional factor partition clustering data.

[0166] In this embodiment, principal component analysis (PCA) is used to reduce the dimension of the multi-dimensional factor map, and the partition feature vectors are extracted therefrom. For example, PCA dimensionality reduction is performed on multiple risk factors within each regional partition, and the data after dimensionality reduction is represented as a feature vector containing main factors such as power consumption, climate conditions, and equipment failure rate. Then, through the K-means clustering algorithm, these feature vectors are divided into different clustering groups. Specifically, high-risk partitions (such as industrial areas with excessive power consumption and high failure rates) are divided into one clustering group, while low-risk partitions (such as residential areas with normal operation and stable consumption) are divided into another clustering group, thereby obtaining multi-dimensional factor partition clustering data. The principal component analysis (PCA) dimensionality reduction technique is used to reduce multiple factors to 2-3 main components. For example, power consumption, failure rate, and factory density are reduced to two main components: the first represents the power consumption intensity, and the second represents the equipment failure distribution. Then, the K-means clustering algorithm (K-Means) is used to cluster the feature vectors after dimensionality reduction, and the partitions are divided into multiple clusters. For example, it can be divided into three types of partitions: high-risk, medium-risk, and low-risk. In high-risk partitions, both power consumption and failure rate are relatively high. In medium-risk partitions, consumption fluctuates greatly. In low-risk partitions, equipment operates stably.

[0167] Step S354: Based on the multi-dimensional factor partition clustering data, extract the consumption characteristics and consumption fluctuation characteristics, so as to obtain the clustering partition consumption data and the clustering partition consumption fluctuation data;

[0168] In this embodiment, for the partition clustering data, the consumption characteristics and fluctuation characteristics are extracted respectively. Specifically, statistical indicators such as the average value, peak value, and standard deviation are calculated for the power consumption data within each clustering partition. For example, in a high-consumption industrial partition, it is found that there is an obvious periodic fluctuation between the power consumption peak value and time, and the periodic component can be extracted through the Fourier transform method, thereby obtaining the clustering partition consumption data and the clustering partition consumption fluctuation data. This helps to identify which regions have large fluctuations in resource consumption at specific times, thereby providing guidance for resource allocation. Specifically, within each clustering partition, statistical indicators such as the mean value, maximum value, and minimum value are used to calculate features such as power and resource consumption. For example, in a high-power consumption area, the peak value can be calculated as 1000 MW, the average value as 800 MW, and the minimum value as 600 MW. For the consumption fluctuation characteristics, the Fourier transform (FFT) or standard deviation calculation method is used to extract the time series fluctuation characteristics. For example, in the peak area of factory equipment, the weekly consumption data shows periodic fluctuations, and the partitions with large consumption fluctuations can be identified through the standard deviation calculation.

[0169] Step S355: Construct partition risk level classification rules according to the clustering partition consumption data and the clustering partition consumption fluctuation data;

[0170] In this embodiment, a partition risk level division rule is constructed based on the consumption data of the clustering partitions and the consumption fluctuation data of the clustering partitions. Specifically, a decision tree algorithm (such as CART, Random Forest) can be used to construct the partition risk level division rule. For example, if the standard deviation of power consumption within a partition exceeds 1.5 times the average value, it is classified as a high risk. If the difference between the consumption peak and the average value is large, it is classified as a medium risk. The system will automatically apply these division rules on the data platform, evaluate the risk levels of each partition in real time, and visually display the risk level of each partition through a chart interface.

[0171] Step S356: Construct a risk area division model based on the regional partition resource map and the partition risk level division rule, and perform resource consumption risk area division according to the risk area division model, so as to obtain resource consumption risk area data.

[0172] In this embodiment, a risk area division model is constructed based on the regional partition resource map and the partition risk level division rule. Specifically, it includes using spatial computing and a decision support system (DSS) to automatically label the risk level in each regional partition. For example, on the urban power resource distribution map, industrial areas with large peak power demands are classified as "high-risk areas", and a dynamic warning system is set up on the management platform. Once it is detected that the power demand exceeds the preset threshold, the system will automatically issue an alarm to notify the management staff to adjust the resource scheduling. In addition, simulation technology can be used to predict the future resource consumption trend based on the data of different risk level divided areas, provide a decision-making basis, and achieve efficient resource allocation and risk control.

[0173] Optionally, step S4 is specifically as follows:

[0174] Step S41: Obtain the resource development process data of the monitoring area, and perform spatial association on the resource development process data of the monitoring area and the regional partition resource map, so as to obtain the regional partition resource development process data;

[0175] In this embodiment, data on the resource development process within the region is obtained through data collection devices such as sensors and SCADA systems, including information such as equipment status, resource collection volume, time nodes, and process steps. These data are spatially matched with the regional partition resource map through a data integration platform. For example, information such as resource collection points, production factories, and transportation routes is mapped onto the specific partition map through GIS tools. Then, spatial association algorithms (such as spatial autocorrelation coefficient, K-nearest neighbor analysis, etc.) are used to perform spatial association between the resource development process and the regional distribution, so as to generate the resource development process data of each regional partition. For example, in a certain mining area, the location of mining equipment can be matched with the resource distribution map to generate a detailed partition development path and resource consumption data.

[0176] Step S42: Extract the development process data of the high-risk area from the regional partition resource development process data according to the resource consumption risk area data, so as to obtain the development process data of the high-risk area;

[0177] In this embodiment, the partitions with relatively high risks are identified through the risk assessment model, such as the areas with large fluctuations in power consumption, high failure rates, and high degrees of equipment aging. Using methods such as logistic regression and risk matrix calculation, the nodes and links related to high risks are extracted from the regional partition resource development process data, such as equipment usage frequency, failure rate, resource consumption peak, etc. For example, in the oilfield development area, the development nodes related to oil well failure rate, pipeline corrosion risk, and resource extraction intensity can be extracted, so as to determine the development process data of the high-risk area and generate a detailed risk development path and node report.

[0178] Step S43: Decompose the development process data of the high-risk area to obtain the development link data of the high-risk area;

[0179] In this embodiment, the development process data of the high-risk area is decomposed into more refined process steps, such as mining, transportation, processing, storage, etc. Adopt process decomposition algorithms, such as hierarchical modeling, decomposition tree structure, etc., to conduct a detailed analysis of each process link. For example, in the mine development process, it is decomposed into links such as transportation routes, processing stations, and storage warehouses, and data analysis of equipment status, resource consumption, and failure frequency is carried out for each link. These decomposed data can help identify key indicators such as resource consumption intensity, equipment service life, and failure probability of each link.

[0180] Step S44: Evaluate the efficiency of the resource development links in the high-risk area according to the partition resource consumption data and the development link data of the high-risk area, so as to obtain the efficiency data of the resource development links in the risk area;

[0181] In this embodiment, by analyzing the efficiency of the data of each development link, for example, in the transmission link, the utilization rate of transport vehicles, transport distance, time consumption, etc. can be calculated. Use the data envelopment analysis (DEA) method to measure the resource input and output efficiency of each link. In the processing link, parameters such as processing time, equipment power, and production speed can be analyzed. For example, in a large chemical plant, the DEA model is used to evaluate the equipment usage efficiency of each production line, the relationship between production volume and power consumption, so as to find out the differences between high efficiency and low efficiency.

[0182] Step S45: Identify the inefficient development links in the efficiency data of the resource development links in the risk area, so as to obtain the efficiency data of the inefficient development links in the risk area.

[0183] In this embodiment, through data mining techniques such as clustering algorithms (K-Means), anomaly detection (IsolationForest), etc., the efficiency data of the development link is analyzed. Identify those links where the resource consumption is disproportionate to the output, the equipment failure frequency is relatively high, and the production time is unstable. For example, in a certain mine development link, it is found that the transportation node consumes a relatively high amount of electricity but has a low output, and the processing link has frequent failures, etc. The system automatically marks these links as inefficient nodes, generates a detailed report, and at the same time proposes optimization suggestions, such as introducing more efficient transportation equipment, more reliable processing technologies, or distributed equipment replacement plans, so as to improve the efficiency and resource utilization effect of the entire development link.

[0184] Optionally, this specification also provides an audit system for natural resources, which is used to execute the audit method for natural resources as described above. The audit system for natural resources includes:

[0185] A resource data map combination module, which is used to obtain remote sensing data of the monitoring area and sensing data of the monitoring area, and perform data enhancement on the remote sensing data of the monitoring area and the sensing data of the monitoring area respectively, so as to obtain enhanced remote sensing data of the area and enhanced sensing data of the area; based on the enhanced remote sensing data of the area and the enhanced sensing data of the area, perform resource data map combination to obtain a resource map of the monitoring area;

[0186] A resource consumption modeling module, which is used to identify the resource consumption pattern based on the resource map of the monitoring area to obtain regional resource consumption pattern data; perform resource consumption modeling according to the regional resource consumption pattern data to obtain a regional resource consumption prediction model;

[0187] A resource consumption risk area division module, which is used to predict the regional resource consumption trend of the resource map of the monitoring area according to the regional resource consumption prediction model to obtain regional resource consumption trend prediction data; based on the regional resource consumption trend prediction data, perform division of the resource consumption risk area of the monitoring area to obtain resource consumption risk area data;

[0188] A development link efficiency evaluation module, which is used to evaluate the efficiency of the resource development link in the risk area according to the resource map of the monitoring area to obtain the efficiency data of the resource development link in the risk area; identify the inefficient development link in the risk area according to the efficiency data of the resource development link in the risk area to obtain the efficiency data of the inefficient development link in the risk area;

[0189] An audit compliance analysis module, which is used to perform regional natural resource audit compliance analysis based on the efficiency data of the inefficient development link in the risk area and the regional resource consumption trend prediction data to obtain a natural resource management compliance report.

[0190] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Thus, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0191] The above description is only a specific implementation manner of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A natural resource audit method, characterized in that: The following steps are involved: Step S1: acquiring remote sensing data of the monitoring area and sensor data of the monitoring area, and performing data enhancement on the remote sensing data of the monitoring area and the sensor data of the monitoring area, respectively, so as to obtain enhanced area remote sensing data and enhanced area sensor data; Combine resource data maps based on enhanced regional remote sensing data and enhanced regional sensor data to obtain a resource map of the monitored area; Step S2: performing resource consumption pattern recognition based on the resource map of the monitoring area, thereby obtaining regional resource consumption pattern data; performing resource consumption modeling based on the regional resource consumption pattern data, thereby obtaining a regional resource consumption prediction model; Step S3: predicting the regional resource consumption trend of the monitored regional resource map according to the regional resource consumption prediction model, thereby obtaining regional resource consumption trend prediction data; Based on the regional resource consumption trend forecast data, the resource consumption risk area of ​​the monitoring area is divided to obtain the resource consumption risk area data; Step S4: evaluating the efficiency of resource development in the risk area based on the resource consumption risk area data according to the resource map of the monitored area, thereby obtaining efficiency data of resource development in the risk area; Identify inefficient development links based on the efficiency data of resource development links in risk areas, thereby obtaining efficiency data of inefficient development links in risk areas; Step S5: Conduct regional natural resource audit compliance analysis based on the efficiency data of inefficient development links in risk areas and regional resource consumption trend forecast data to obtain a natural resource management compliance report.

2. The natural resource auditing method according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: Acquire remote sensing data of the monitoring area and sensor data of the monitoring area; Step S12: preprocessing the remote sensing data of the monitored area and the sensor data of the monitored area respectively, so as to obtain the remote sensing data of the area to be analyzed and the sensor data of the area to be analyzed; Step S13: performing remote sensing data enhancement according to the remote sensing data of the area to be analyzed, thereby obtaining regional enhanced remote sensing data; Step S14: performing sensor data enhancement according to the sensor data of the area to be analyzed, thereby obtaining regional enhanced sensor data; Step S15: Combining resource data maps based on enhanced regional remote sensing data and enhanced regional sensor data to obtain a resource map of the monitored area.

3. The natural resource auditing method according to claim 2, characterized in that: Step S13 is specifically as follows: Extract the band reflectance of the remote sensing data of the area to be analyzed, so as to obtain the regional remote sensing band reflectance data, and perform multi-spectral band enhancement on the regional remote sensing band reflectance data, so as to obtain the remote sensing enhanced band reflectance data; Perform remote sensing image transformation and enhancement on the remote sensing data of the area to be analyzed, so as to obtain image transformation enhanced remote sensing data; Perform radiation enhancement on the remote sensing data of the area to be analyzed, thereby obtaining radiation enhanced remote sensing data; The remote sensing data of the area to be analyzed is simulated by natural interference of Gaussian noise to obtain the noisy remote sensing data; Regional remote sensing enhanced data fusion is performed based on remote sensing enhanced band reflectance data, image transformation enhanced remote sensing data, radiation enhanced remote sensing data and noise remote sensing data to obtain regional enhanced remote sensing data.

4. The natural resource auditing method according to claim 2, characterized in that: Step S15 is specifically as follows: Step S151: performing spatial and temporal data alignment on the enhanced regional remote sensing data and the enhanced regional sensor data, thereby obtaining regional aligned remote sensing data and regional aligned sensor data; Step S152: integrating regional resource distribution characteristics of the regional aligned remote sensing data to obtain regional resource distribution data; Step S153: performing a hotspot region spatiotemporal clustering analysis on the regional aligned sensing data to obtain regional hotspot region data, and performing attribute classification on the regional hotspot region data to obtain regional hotspot attribute data; Step S154: performing resource relationship modeling based on the regional resource distribution data, thereby obtaining resource relationship data; Step S155: construct and integrate a resource map based on the resource relationship data and the regional hotspot attribute data, thereby obtaining a resource map of the monitored area.

5. The natural resource auditing method according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: performing resource attribute feature regional partitioning based on the monitoring area resource map, thereby obtaining a regional partition resource map; Step S22: performing principal component analysis of resource consumption characteristics on the regional partition resource map to obtain partition resource consumption data; Step S23: performing time series analysis according to the partition resource consumption data, thereby obtaining the partition time series resource consumption data; Step S24: performing resource consumption pattern recognition on the partition time series resource consumption data, thereby obtaining regional resource consumption pattern data; Step S25: screening the regional resource consumption pattern data for resource consumption pattern characteristics, thereby obtaining resource consumption influencing factors, and constructing a regional resource consumption prediction model based on the resource consumption influencing factors.

6. The natural resource auditing method according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: predicting the regional resource consumption trend of the monitored regional resource map using a regional resource consumption prediction model, thereby obtaining regional resource consumption trend prediction data; Step S32: converting the regional resource consumption trend prediction data into a spatiotemporal map, thereby obtaining a regional resource consumption spatiotemporal map; Step S33: performing a spatiotemporal dynamic analysis of resource consumption on the regional spatiotemporal resource consumption map, thereby obtaining spatiotemporal dynamic data of resource consumption; Step S34: selecting risk factors according to the spatiotemporal dynamic data of resource consumption, thereby obtaining a resource consumption risk factor set; Step S35: Based on the resource consumption risk factor set, the regional partition resource map is divided into resource consumption risk zones in the monitoring area, thereby obtaining resource consumption risk zone data.

7. The natural resource auditing method according to claim 6, characterized in that: Step S33 is specifically as follows: Step S331: performing spatiotemporal deconstruction processing on the regional resource consumption spatiotemporal map to obtain resource consumption time series layer data and resource consumption spatial distribution layer data; Step S332: identifying resource consumption hotspot areas on the resource consumption spatial distribution layer data, thereby obtaining resource consumption spatial hotspot area data; identifying resource consumption hotspot time on the resource consumption spatial distribution layer data, thereby obtaining resource consumption hotspot time data; Step S333: performing spatiotemporal clustering based on the resource consumption spatial hotspot area data and the resource consumption hotspot time data, thereby obtaining the resource consumption hotspot spatiotemporal data; Step S334: performing abnormal hotspot detection on the resource consumption hotspot time and space, thereby obtaining abnormal hotspot data in time and space; Step S335: Perform spatiotemporal autoregression based on the spatiotemporal anomaly hotspot data to obtain spatiotemporal dynamic data of resource consumption.

8. The natural resource auditing method according to claim 6, characterized in that: Step S35 is specifically as follows: Step S351: screening and standardizing the resource consumption risk factor set to obtain a screened risk factor set; Step S352: constructing a multidimensional factor mapping of the regional partition resource map according to the screened risk factor set, thereby obtaining a multidimensional factor map; Step S353: extracting partition feature vectors from the multidimensional factor graph to obtain partition feature vector data, and performing partition pattern clustering based on the partition feature vector data to obtain multidimensional factor partition clustering data; Step S354: performing consumption feature extraction and consumption fluctuation feature extraction based on the multi-dimensional factor partition clustering data, thereby obtaining cluster partition consumption data and cluster partition consumption fluctuation data; Step S355: constructing a partition risk level classification rule based on the cluster partition consumption data and the cluster partition consumption fluctuation data; Step S356: construct a risk zone division model based on the regional zoning resource map and the zoning risk level division rules, and divide the resource consumption risk zones according to the risk zone division model, so as to obtain resource consumption risk zone data.

9. The natural resource auditing method according to claim 1, characterized in that: Step S4 is specifically as follows: Step S41: Acquire the monitoring area resource development process data, and spatially associate the monitoring area resource development process data with the regional partition resource map, thereby obtaining the regional partition resource development process data; Step S42: extracting the high-risk area development process from the regional partition resource development process data according to the resource consumption risk area data, thereby obtaining the high-risk area development process data; Step S43: Decomposing the high-risk area development process data into links, thereby obtaining high-risk area development link data; Step S44: Evaluate the efficiency of resource development in high-risk areas according to the resource consumption data of the sub-areas and the data of development in high-risk areas, so as to obtain the efficiency data of resource development in risk areas; Step S45: Identify inefficient development links based on the efficiency data of resource development links in risk areas, thereby obtaining efficiency data of inefficient development links in risk areas.

10. A natural resource audit system, characterized in that: For executing the natural resource audit method as claimed in claim 1, the natural resource audit system comprises: The resource data map combination module is used to obtain the remote sensing data of the monitoring area and the sensor data of the monitoring area, and respectively enhance the remote sensing data of the monitoring area and the sensor data of the monitoring area, so as to obtain the enhanced area remote sensing data and the sensor data of the enhanced area; and combine the resource data map based on the enhanced area remote sensing data and the sensor data of the enhanced area, so as to obtain the resource map of the monitoring area; The resource consumption modeling module is used to identify resource consumption patterns based on the resource map of the monitoring area, thereby obtaining regional resource consumption pattern data; perform resource consumption modeling based on the regional resource consumption pattern data, thereby obtaining a regional resource consumption prediction model; The resource consumption risk zone division module is used to predict the regional resource consumption trend of the resource map of the monitored area according to the regional resource consumption prediction model, so as to obtain regional resource consumption trend prediction data; based on the regional resource consumption trend prediction data, the monitoring area resource consumption risk zone is divided, so as to obtain resource consumption risk zone data; The development link efficiency evaluation module is used to evaluate the efficiency of the resource development link in the risk area based on the resource map of the monitored area, so as to obtain the efficiency data of the resource development link in the risk area; identify the inefficient development link in the efficiency data of the resource development link in the risk area, so as to obtain the efficiency data of the inefficient development link in the risk area; The audit compliance analysis module is used to conduct regional natural resource audit compliance analysis based on the efficiency data of inefficient development links in risk areas and regional resource consumption trend forecast data, so as to obtain a natural resource management compliance report.

Images