Intelligent management system for mineral resources based on big data analysis

Abstract

This application relates to the field of mining area management technology and discloses a mineral resource intelligent management system based on big data analysis. It includes a data acquisition module for acquiring geological data and mineral resource distribution data of a target area, matching the acquired geological data and mineral resource distribution data with a preset large database to obtain estimated mineral characteristics of the target area; a region division module for dividing the target area into sub-regions based on the acquired geological data, mineral resource distribution data, and estimated mineral characteristics, obtaining a natural number greater than 1; and a data analysis module for obtaining real-time mining data data of the divided sub-regions based on a preset real-time mining data threshold according to the estimated mineral characteristics. By constructing a large database and collecting raw geological and mineral distribution data of the target mining area using various high-precision sensing devices and geological survey instruments, the estimated mineral characteristics of a reference mining area are obtained.

Description

Technical Field

[0001] This application relates to the field of mining area management technology, specifically a mineral resource intelligent management system based on big data analysis. Background Technology

[0002] Intelligent management of mineral resources is a management system that integrates big data, artificial intelligence, the Internet of Things and other technologies to make intelligent decisions and optimize the entire life cycle of mineral resources, including exploration, mining, reserve assessment, production operation and ecological restoration. It plays an important role in the actual mining process through mineral resource potential evaluation. However, in the current technology, mineral mining management mostly relies on human experience and judgment, and insufficient data support makes it difficult to uniformly supervise the working conditions in different regions, and problems such as overloading mining or waste of production capacity occur frequently.

[0003] Therefore, this application proposes a mineral resource intelligent management system based on big data analysis to address the shortcomings of the existing technology. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent management system for mineral resources based on big data analysis, in order to solve the problems mentioned in the background art.

[0005] The objective of this application can be achieved through the following technical solutions: A mineral resource intelligent management system based on big data analysis includes the following modules: The data acquisition module is used to acquire geological data and mineral resource distribution data of the target area, and match the acquired geological data and mineral resource distribution data with a preset large database to obtain the estimated mineral characteristics of the target area. The region division module divides the target area into regions based on the acquired geological data, mineral resource distribution data, and estimated mineral characteristics. Sub-regions It is a natural number greater than 1; The data analysis module presets a real-time mining data threshold based on the estimated mineral characteristics, obtains real-time mining data for multiple sub-regions after division, and performs real-time analysis based on the real-time mining data and the real-time mining data threshold to obtain a real-time mining index. The comprehensive evaluation module performs a comprehensive evaluation of the target area based on the real-time mining index of each sub-region, and implements targeted control measures for each sub-region.

[0006] Preferably, the data acquisition module operates as follows: A large database was built using mining area-related data collected through online big data analytics. Geological data and mineral resource distribution data of the target area are obtained through multiple sensors and surveying equipment; The geological data and mineral resource distribution data of the target area are matched with a large database to obtain similar reference mining areas and their mining area characteristics.

[0007] Preferably, the process of obtaining the reference mining area is as follows: Preprocess the collected geological data and mineral resource distribution data of the target area; The standardized geological data and mineral resource distribution data of the target area are compared with the corresponding geological data and mineral resource distribution data of all mining areas stored in the preset big data database to calculate the data similarity. Select a set of candidate mining areas whose similarity meets the preset similarity standard; The matching similarity values ​​of all candidate mining areas are sorted, and the mining area with the highest similarity is selected as the final reference mining area corresponding to the target area. The characteristics of the mining area include mineral reserves, mineral layer distribution, and mining load.

[0008] Preferably, the method by which the region division module operates is as follows: Based on the geological data, mineral resource distribution data, and estimated mineral characteristics of the target area, the rules for determining the division of the area are set. Based on the regional division rules and mining area zoning standards, the target area is initially divided into high-capacity mining area, conventional and stable mining area, and restricted and controlled mining area. Based on the distribution range of mineral layers and geographical location information of the target area, the three types of functional areas are divided to generate several initial sub-regions; Each initial sub-region is validated, overlapping and invalid regions are removed, and the desired result is obtained. A standard sub-region.

[0009] Preferably, the data analysis module operates as follows: Based on the estimated mineral characteristics of each sub-region, including mineral reserves, ore layer distribution regularity coefficient, and mining load parameters, the real-time mining data thresholds for each sub-region are preset. Real-time collection of mining operation data for each sub-region, obtaining real-time mining data for each sub-region; The real-time mining data of each sub-region is compared with the corresponding real-time mining data threshold, and the data difference is obtained. Based on the comparison results and the data difference, the real-time mining index of each sub-region is calculated and obtained.

[0010] Preferably, the method for obtaining the real-time mining data threshold is as follows: The estimated mineral reserves, ore layer distribution regularity coefficient, and benchmark mining load of the sub-region are obtained, and the average mining threshold of the reference mining area is also obtained. The estimated mineral reserves, the regularity coefficient of ore layer distribution, and the benchmark mining load are respectively corrected and normalized; The basic mining threshold base for each sub-region is obtained by weighting and fusing the corrected and normalized estimated mineral reserves, ore layer distribution regularity coefficient, and benchmark mining load with preset weighting coefficients. By calibrating the base threshold using a dynamic correction coefficient, the real-time mining data threshold for the sub-region is obtained.

[0011] Preferably, the method for obtaining the real-time mining index is as follows: Calculate the ratio of real-time mining data to the real-time mining data threshold for the sub-region to obtain the mining load matching ratio; The mining load matching ratio is corrected based on a constant adjustment coefficient; The corrected mining load matching ratio is fitted and calculated to obtain the real-time mining index of each sub-region.

[0012] Preferably, the comprehensive evaluation module operates by comparing the real-time mining index differences of each sub-region, obtaining the mining load compliance status and operation status of each sub-region, and managing different sub-regions accordingly based on the evaluation results.

[0013] The beneficial effects of this application are: 1. This application constructs a large database and collects raw data on the geology and mineral distribution of the target mining area using various high-precision sensing devices and geological survey instruments. It then obtains the estimated mineral characteristics of the reference mining area, divides the mining area into sub-regions according to division rules and zoning standards, obtains the real-time mining data thresholds for each sub-region, acquires the real-time mining index, and finally manages the mining area accordingly. This effectively improves the standardization, safety, and resource utilization efficiency of mineral resource mining, and promotes the upgrading of mining area management towards intelligence and refinement.

[0014] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1This is a system module diagram of a mineral resource intelligent management system based on big data analysis according to this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] Please see Figure 1 As shown, this application is a mineral resource intelligent management system based on big data analysis, including a data acquisition module, a regional division module, a data analysis module, and a comprehensive evaluation module; The data acquisition module is primarily used to acquire geological data and mineral resource distribution data for the target area. This acquired data is then matched with a pre-set large database to obtain estimated mineral characteristics for the target area. Specifically, it collects massive amounts of mining area-related data through online big data retrieval and industry mining area data aggregation to construct a dedicated, standardized mineral database. This database contains comprehensive data on geological parameters, mineral distribution parameters, and mining operation parameters for mining areas of different regions, mineral types, and mining years. It covers various types of mining areas, including mature operating areas, newly built areas, and depleted areas. The aim is to establish a universal and comprehensive data reference standard, avoiding the judgment biases caused by traditional mining area management relying solely on local experience and limited data. For example, the database includes real operational data on geological structures, ore layer distribution patterns, conventional mining loads, and mineral reserves for small and medium-sized coal mines and metal mines nationwide, providing sufficient sample support for subsequent target mining area matching. In practical applications, various high-precision sensors and professional geological surveying equipment are used to conduct on-site data collection in target mining areas, obtaining specific geological data and mineral resource distribution data for the target region. Commonly used equipment in the industry mainly includes sensing devices such as geological stress sensors, rock layer moisture sensors, geomagnetic detection sensors, and infrared remote sensing sensors, as well as professional surveying instruments such as 3D geological exploration drilling rigs, high-density electrical resistivity tomography (EDT) instruments, geological profile mapping instruments, mineral composition analyzers, and aerial surveying drones for mining areas. Among them, geological stress sensors and EDT instruments are used to collect geological data such as stratigraphic structure, rock layer hardness, and geological stability. Infrared remote sensing equipment and aerial surveying drones can scan a wide area. The geological data includes stratigraphic structure, geological stability, and rock layer properties, which are used to determine the basic conditions for mining in the mining area. The mineral resource distribution data includes the location of mineral layers, resource coverage, and mineral-rich areas, which are used to determine the resource endowment of the mining area. For example, geological surveying instruments collect data on the thickness of strata and the hardness of rock layers in the target area, and remote sensing equipment scans to obtain the actual distribution range of mineral layers, forming a specific original dataset for the target mining area.

[0019] Subsequently, the geological data and mineral resource distribution data of the target area collected on-site are intelligently matched and compared with the massive mining area data in the preset big data database. The most similar reference mining areas are selected, and the core features of the corresponding mining areas are extracted. Finally, the estimated mineral characteristics of the target area are generated. The main purpose is to fill the data gaps of newly built mining areas and mining areas that have not been fully surveyed, and to solve the problem that the survey data of a single mining area is incomplete and cannot directly determine the core parameters of minerals. For example, for newly built mining areas that have just completed preliminary surveys and have not yet explored complete reserves, the mineral reserves and suitable mining load cannot be determined based on the data collected on-site alone. By matching reference mining areas with similar geological structures and ore layer morphology through big data, the three core characteristics of the target mining area—mineral reserves, ore layer distribution, and mining load—can be roughly estimated.

[0020] The method for obtaining reference mining area data involves first preprocessing the geological data and mineral resource distribution data of the target area collected on-site. This includes data cleaning, noise reduction, error correction, and dimensional normalization. Abnormal and redundant data are removed to obtain standardized and comparable core parameters of the target mining area. Then, four types of data—geological structure, rock strata stability, mineral layer coverage, and mineral enrichment—are uniformly mapped to a 0-1 standard interval. Next, based on the preset weights of the geological and mineral distribution data, the squared differences of single-dimensional parameters between the target area and each mining area in the database are calculated. These differences are then summed, squared, and normalized to obtain the final comprehensive data similarity value in the 0-1 interval. This is achieved using the formula: in, This represents the weighted Euclidean distance between the two sets of mining area data. The final data similarity score ranges from 0 to 1, with values ​​closer to 1 indicating a higher degree of matching. For the first The weighting coefficients of the comparison indicators satisfy the following conditions: , For the target area Standardized parameters; For the data inventory of the mining area Standardized parameters The total number of parameters involved in the matching comparison. This is the maximum distance value calculated among all the mining areas compared in this round.

[0021] For example: Select three core comparison indicators: rock hardness, mineral layer coverage, and mineral enrichment, and assign weights based on geological structure. Rock strata stability mineral layer coverage area Mineral enrichment The target region parameters are: The maximum distance in this comparison: ; Calculate the weighted square of the differences for each item:

[0022] In summary, the similarity calculated this time is 0.9, which is close to 1. This means that the four core geological and resource data of this mining area and the target area are highly matched, and it can be included in the candidate mining area set for subsequent screening and ranking.

[0023] After completing the similarity calculation for all mining areas, the system selects all mining areas whose similarity values ​​meet the preset qualified threshold to form a candidate mining area set. Finally, the similarity values ​​of all samples in the candidate mining area set are sorted in descending order, and the mining area with the highest matching degree is selected as the final reference mining area corresponding to the target area.

[0024] The region division module is used to divide the target area into regions based on the acquired geological data, the mineral resource distribution data, and the estimated mineral characteristics. Sub-regions A natural number greater than 1; specifically, based on the geological data, mineral resource distribution data, and estimated mineral characteristics of the target area, regional division judgment rules are established. These rules primarily use mineral reserve scale, the regularity of ore layer distribution, and the upper limit of regional mining load as judgment benchmarks. The overall resource reserve volume of a plot is distinguished by the size of its mineral reserves, thereby defining the basic level of regional production capacity. The continuity and concentration of ore layer arrangement are used to judge the quality of mining operation conditions in a plot. The maximum mining load that the region can bear determines the level of tightness or looseness in mining control. By combining these three judgment conditions, the one-sidedness caused by a single indicator can be avoided, such as an overestimation of the estimated reserves of a single plot. A site with continuous, unbroken ore layers and a high capacity to withstand mining loads can be identified as a site suitable for high-intensity mining. If the reserves are low and the ore layers are scattered and fragmented, the mining conditions are considered limited. The mining zoning standards set quantitative boundaries for three types of mining areas. High-capacity mining areas require high mineral reserves, concentrated and regular ore layer distribution, and strong regional mining load capacity, making them suitable for large-scale mechanized mining. Conventional and stable mining areas have medium mineral reserves, uniform and stable ore layer distribution, and mining loads within a reasonable range, suitable for routine daily mining operations. Restricted and controlled mining areas have low mineral reserves, obvious ore layer fragmentation, and lower upper limits for mining loads corresponding to geological conditions, allowing only small-scale protective mining.

[0025] In the initial delineation of the target area, the geological, resource distribution, and estimated characteristic parameters of all plots within the target area are retrieved. Each plot parameter is compared against the delineation rules, and then matched with the established mining area zoning standards to determine the category of each plot. Finally, the entire target area is divided into three functional zones: high-capacity mining area, conventional and stable mining area, and restricted and controlled mining area. For example, contiguous plots with abundant reserves and complete ore layers in the center of the mining area are classified as high-capacity mining area; plots with moderate reserves and stable geology in the middle of the mining area are classified as conventional and stable mining area; and plots with sparse reserves and complex rock strata at the edge of the mining area are classified as restricted and controlled mining area.

[0026] After completing the functional area classification, based on the actual distribution range of the mineral layers and on-site geographical location information, and according to natural terrain boundaries, mineral layer fault boundaries, and landform dividing lines, the three major functional areas are further subdivided and segmented, forming a number of initial sub-regions. For example, following mountain gullies and underground mineral layer fault zones as dividing lines, a large high-productivity area is divided into multiple independent mining blocks, initially forming a scattered set of initial sub-regions. Then, the initial sub-regions in the initial sub-region set are verified, checking the boundary range and actual resource attributes of each sub-region one by one, comparing the spatial coordinate range of adjacent sub-regions, finding overlapping areas with overlapping ranges and boundaries, obtaining the actual area and mineral resource ratio of a single sub-region, identifying invalid areas that are too small, have no effective mineral reserves, or are not worth mining. For overlapping areas, the boundary lines are re-examined, the block range is adjusted to eliminate the overlapping parts, and invalid areas are directly eliminated, while ensuring that the boundaries of the remaining areas are intact and the resource attributes are consistent. After multiple rounds of correction and optimization, the final number of sub-regions is [number missing]. Each standard sub-region.

[0027] The data analysis module is used to preset real-time mining data thresholds based on the estimated mineral characteristics, acquire real-time mining data for multiple sub-regions after division, and perform real-time analysis based on the real-time mining data and the real-time mining data thresholds to obtain a real-time mining index. Specifically, it first acquires the estimated mineral reserves, ore layer distribution regularity coefficient, and benchmark mining load corresponding to each standard sub-region, and simultaneously retrieves the average mining threshold of a reference mining area as a benchmark reference. Then, it corrects and normalizes the mineral reserves, ore layer distribution regularity coefficient, and benchmark mining load respectively. Subsequently, it performs a weighted fusion calculation on the three normalized parameters according to preset weight coefficients. The weights are allocated based on industry experience in mineral mining and the actual conditions of the mining area. Reserves, ore layer distribution, and mining load each correspond to different weight proportions. After weighted calculation, the basic mining threshold base for each sub-region can be obtained through the formula: in, For the first Real-time mining data thresholds for each sub-region This is the correction coefficient for dynamic mining in the sub-region. Preset dimension weight coefficients and satisfy This application sets out that, , Estimate mineral reserves for sub-regions. This represents the regularity coefficient of the mineral layer distribution in the sub-region. As the benchmark mining load for the sub-region, Here is the range normalization function. It is a nonlinear correction function for the natural logarithm. The average mining threshold is used as a reference for the standard mining area. Select raw parameters for a specific sub-region: Estimated mineral reserves 10,000 tons; ore layer distribution regularity coefficient Regularity of ore layer distribution The benchmark mining load is obtained by weighted fusion of standardized parameters such as ore layer continuity, thickness uniformity, fault density, and block dispersion. tons / hour; All parameters are normalized to [0,1]. This set of parameters is present in the entire sample: The minimum value of the entire region is 2.5, and the maximum value is 5.0. The minimum value of the entire region is 0.2, and the maximum value is 1.0. The minimum value of the entire domain is 4, and the maximum value is 12. Dynamic correction coefficient setting The average mining threshold in the reference mining area is... tons / hour.

[0028] The normalization formula for the range is: , , Substitute the data into the formula: but:

[0029]

[0030] In summary, the basic mining threshold for this sub-region is 0.7590. This value is a comprehensive coefficient that integrates the three characteristics of reserves, ore layer morphology, and mining load. It is also the core intermediate quantity for defining mining standards. After combining the dynamic correction coefficient and the average threshold of the reference mining area, the real-time mining data threshold for this sub-region is approximately 79.69 tons / hour, which is the legal and safe hourly mining limit for this block.

[0031] By setting a baseline for mining operations for each sub-region through a preset basic mining threshold, traditional mining often relies on manual experience to set mining limits, which can easily lead to problems such as over-exploitation of resources and overloading of equipment due to excessive production capacity, or under-exploitation of resources and low production efficiency due to insufficient production capacity. The basic mining threshold is generated by combining the operational data of similar mature reference mining areas with the resource endowment of the region. It can objectively match the resource volume, mining conditions and carrying capacity of the sub-region, regulate mining operation standards from the source, protect mineral resources and prevent disorderly mining, and ensure that mining equipment and geological environment are in a safe operating range in the long term, so that the mining supervision of the entire mining area has a basis.

[0032] After setting the real-time mining data threshold, the real-time mining data is compared with the threshold. Based on various sensors and monitoring equipment deployed at the mining site, mining operation data from all sub-areas is continuously collected and summarized to form the real-time mining data for each sub-area. The real-time mining data for each sub-area is then compared item by item with the corresponding preset real-time mining data threshold to obtain the real-time mining index. The ratio of the real-time mining data to the real-time mining data threshold is calculated to obtain the mining load matching ratio. This ratio is then substituted into a preset constant adjustment coefficient to complete the numerical correction. Finally, a nonlinear fitting conversion is performed using the natural exponential function to obtain the final real-time mining index, expressed by the formula: in, For the first The real-time mining index for each sub-region, where e is the base of the natural index. To preset a constant adjustment coefficient, For the first Real-time mining data for individual sub-regions For the first Real-time mining data thresholds for individual sub-regions; Based on the aforementioned examples: Real-time mining data threshold for sub-regions tons / hour; preset adjustment coefficient: , In normal mining scenarios, real-time mining data Tons per hour, in overloaded mining scenarios, real-time mining data Tons per hour, in low-load mining scenarios, real-time mining data tons / hour; In a normal mining scenario: Load ratio: Substituting the coefficients, we get: 1.2 × 0.9035 − 1.0 ≈ 0.0842, therefore the mining index is: ; In overload mining scenarios: Load ratio: Substituting the coefficients, we get: 1.2 × 1.1043 − 1.0 ≈ 0.3251, therefore the mining index is: ; In low-load mining scenarios: Load ratio: Substituting the coefficients, we get: 1.2 × 0.6902 − 1.0 ≈ −0.1718, therefore the mining index is: .

[0033] In summary, a real-time mining index between 95 and 105 in this application indicates that the mining load matches the standard threshold and the operation is normal. In the above-mentioned normal mining scenario, the real-time mining index is approximately 101.55, which is within a reasonable range. Therefore, the mining scale of this sub-area is compliant and the operation is stable. However, in the overload mining scenario, the index reaches 138.42, which is significantly higher than the benchmark value. This indicates that the real-time mining volume exceeds the set threshold, posing a risk of overload mining. The system can trigger an early warning. In the low-load mining scenario, the index is 84.22, which is lower than the benchmark value. This indicates that the mining capacity has not reached the design standard and the resource utilization efficiency is low.

[0034] Real-time mining index transforms complex mining operations into intuitive numerical values. These values ​​clearly reflect the current mining load level of a sub-region, providing a quantitative representation of the mining status. Managers no longer need to meticulously review cumbersome raw mining data; they can quickly assess the mining conditions of a single sub-region or even the entire mining area simply by observing the index value. This significantly reduces the difficulty of data interpretation and improves management efficiency. Furthermore, it distinguishes between different mining states: when the index is within a reasonable range, it indicates that the mining load in that sub-region is compliant and the operational process is stable and orderly. When the index remains consistently high, it indicates that the real-time mining data exceeds the threshold range, suggesting potential safety hazards such as over-mining, equipment overload, or excessive geological pressure, requiring timely warnings and intervention. When the index remains consistently low, it indicates that the regional production capacity has not reached the design standard, and resource utilization is insufficient, allowing for optimization of mining plans and improvement of operational efficiency based on actual conditions.

[0035] The comprehensive assessment module evaluates the target area based on the real-time mining index of each sub-region and implements targeted control over each sub-region. Specifically, it first summarizes the real-time mining index of all standard sub-regions in the entire region, classifies and compares the values, and, in conjunction with preset operating condition evaluation standards, identifies the mining operation status of each sub-region one by one. When the index is within a reasonable range, it is determined that the mining load in the region is compliant and the production conditions are stable. When the index is significantly high, it identifies safety hazards such as overload mining and equipment overload. When the index is consistently low, it is determined that the region's production capacity is insufficient and the resource utilization efficiency is low.

[0036] After completing the status assessment of a single block, all zone information is integrated to conduct a comprehensive assessment of the overall mining pace, resource utilization, and safety operation status of the entire target mining area, forming a complete mining area operation analysis result. Subsequently, corresponding control measures are implemented based on the assessment conclusions. For normal operating areas, the existing mining plan remains unchanged. For overloaded areas, production reduction and load reduction instructions are issued in a timely manner to avoid geological and equipment safety risks. For low-production areas, operation arrangements are optimized and mining efficiency is improved based on site conditions.

[0037] The above description is merely an example and illustration of the concept of this application. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the inventive concept or exceed the scope defined in the claims, they should all fall within the protection scope of this application.

Claims

1. A mineral resource intelligent management system based on big data analysis, characterized in that, Includes the following modules: The data acquisition module is used to acquire geological data and mineral resource distribution data of the target area, and match the acquired geological data and mineral resource distribution data with a preset large database to obtain the estimated mineral characteristics of the target area. The region division module divides the target area into regions based on the acquired geological data, mineral resource distribution data, and estimated mineral characteristics. Sub-regions It is a natural number greater than 1; The data analysis module presets a real-time mining data threshold based on the estimated mineral characteristics, obtains real-time mining data for multiple sub-regions after division, and performs real-time analysis based on the real-time mining data and the real-time mining data threshold to obtain a real-time mining index. The comprehensive evaluation module performs a comprehensive evaluation of the target area based on the real-time mining index of each sub-region, and implements targeted control measures for each sub-region.

2. The intelligent management system for mineral resources based on big data analysis according to claim 1, characterized in that, The data acquisition module operates as follows: A large database was built using mining area-related data collected through online big data analytics. Geological data and mineral resource distribution data of the target area are obtained through multiple sensors and surveying equipment; The geological data and mineral resource distribution data of the target area are matched with a large database to obtain similar reference mining areas and their mining area characteristics.

3. The intelligent management system for mineral resources based on big data analysis according to claim 2, characterized in that, The process of obtaining the reference mining area is as follows: Preprocess the collected geological data and mineral resource distribution data of the target area; The standardized geological data and mineral resource distribution data of the target area are compared with the corresponding geological data and mineral resource distribution data of all mining areas stored in the preset big data database to calculate the data similarity. Select a set of candidate mining areas whose similarity meets the preset similarity standard; The matching similarity values ​​of all candidate mining areas are sorted, and the mining area with the highest similarity is selected as the final reference mining area corresponding to the target area. The characteristics of the mining area include mineral reserves, mineral layer distribution, and mining load.

4. The intelligent management system for mineral resources based on big data analysis according to claim 1, characterized in that, The method by which the region division module works is as follows: Based on the geological data, mineral resource distribution data, and estimated mineral characteristics of the target area, the rules for determining the division of the area are set. Based on the regional division rules and mining area zoning standards, the target area is initially divided into high-capacity mining area, conventional and stable mining area, and restricted and controlled mining area. Based on the distribution range of mineral layers and geographical location information of the target area, the three types of functional areas are divided to generate several initial sub-regions; Each initial sub-region is validated, overlapping and invalid regions are removed, and the desired result is obtained. A standard sub-region.

5. The intelligent management system for mineral resources based on big data analysis according to claim 1, characterized in that, The data analysis module operates as follows: Based on the estimated mineral characteristics of each sub-region, including mineral reserves, ore layer distribution regularity coefficient, and mining load parameters, the real-time mining data thresholds for each sub-region are preset. Real-time collection of mining operation data for each sub-region, obtaining real-time mining data for each sub-region; The real-time mining data of each sub-region is compared with the corresponding real-time mining data threshold, and the data difference is obtained. Based on the comparison results and the data difference, the real-time mining index of each sub-region is calculated and obtained.

6. The intelligent management system for mineral resources based on big data analysis according to claim 5, characterized in that, The method for obtaining the real-time mining data threshold is as follows: The estimated mineral reserves, ore layer distribution regularity coefficient, and benchmark mining load of the sub-region are obtained, and the average mining threshold of the reference mining area is also obtained. The estimated mineral reserves, the regularity coefficient of ore layer distribution, and the benchmark mining load are respectively corrected and normalized; The basic mining threshold base for each sub-region is obtained by weighting and fusing the corrected and normalized estimated mineral reserves, ore layer distribution regularity coefficient, and benchmark mining load with preset weighting coefficients. By calibrating the base threshold using a dynamic correction coefficient, the real-time mining data threshold for the sub-region is obtained.

7. The intelligent management system for mineral resources based on big data analysis according to claim 6, characterized in that, The method for obtaining the real-time mining index is as follows: Calculate the ratio of real-time mining data to the real-time mining data threshold for the sub-region to obtain the mining load matching ratio; The mining load matching ratio is corrected based on a constant adjustment coefficient; The corrected mining load matching ratio is fitted and calculated to obtain the real-time mining index of each sub-region.

8. The intelligent management system for mineral resources based on big data analysis according to claim 1, characterized in that, The comprehensive evaluation module works by comparing the real-time mining index differences of each sub-region, obtaining the mining load compliance status and operation status of each sub-region, and managing different sub-regions accordingly based on the evaluation results.

Images