Visual management system for mineral sample collection

Abstract

The invention relates to the technical field of mineral sample visualization, and discloses a mineral sample collection visual management system which comprises a data collection and storage module, a formatting processing module, a visual chart generation module, a platform integration module and a geographic information integration module. Compared with the prior art, the technical problems that static data storage and manual processing are usually depended on, the sample category is difficult to update and predict in real time, and particularly, efficient data processing and visual data analysis visualization cannot be realized under the conditions of huge data volume and complex category are solved. Due to the fact that the knowledge graph and the sample category prediction model are integrated and data visualization is applied, the problems of manual intervention and data processing lag are avoided, and the mineral sample data real-time updating efficiency and the prediction category accuracy are improved.

Description

Technical Field

[0001] This invention belongs to the field of mineral sample visualization technology, and in particular relates to a mineral sample collection visualization management system. Background Technology

[0002] Currently, mineral sample collection and management systems generally suffer from numerous technical shortcomings. Traditional mineral sample management methods typically rely on static data storage and manual processing, and the data collection and storage methods are mostly unable to meet the management needs of large-scale, high-dimensional mineral samples. In existing technologies, the static data storage methods cannot effectively support the real-time processing and updating of large-scale data streams, and data access and management efficiency is low. Furthermore, as the number of mineral samples collected increases, traditional databases often face performance bottlenecks, failing to achieve rapid data processing and efficient query responses. Especially in the process of real-time updating of mineral samples and predicting sample categories, existing technologies typically rely on manual intervention, making it difficult to achieve automated processing and classification prediction. Particularly when the number of samples is large and the sample categories are complex, existing technologies struggle to meet the needs for efficient data processing and intuitive data visualization. In existing technologies, the classification prediction accuracy of mineral samples is low, and most lack intelligent and automated analysis tools, resulting in data processing lag and an inability to meet the needs of real-time updates. Especially when the data volume is large and the categories are diverse, existing systems cannot effectively automate the classification and category prediction of mineral samples. Therefore, there is an urgent need for a new type of mineral sample collection and management system. This system can achieve automated collection, real-time updating, sample classification and prediction of mineral samples by integrating intelligent algorithm models (such as support vector machines, deep learning, etc.), knowledge graphs, data visualization technologies, etc., and provide users with intuitive data analysis and decision support through a visualization management platform. Summary of the Invention

[0003] To address the aforementioned technical shortcomings, the present invention aims to propose a mineral sample collection visualization management system. This system addresses the technical problems of existing technologies that typically rely on static data storage and manual processing, making it difficult to update and predict sample categories in real time, especially under conditions of large data volumes and complex categories, thus hindering efficient data processing and intuitive data analysis visualization.

[0004] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a mineral sample collection visualization management system, comprising: The data acquisition and storage module is used to collect sample data of mineral samples, including image data, physical property data and metadata, build a cloud database, and transmit sample data to the cloud database through the application of the distributed message queue Apache Kafka; The formatting module is used to clean and preprocess the sample data transmitted to the cloud database to generate standardized sample data; The visualization chart generation module uses a pre-set mineral knowledge graph and a support vector machine to train a mineral sample category prediction model on standardized sample data. The mineral sample category prediction model is then post-processed based on the mineral knowledge graph to obtain an optimized sample category prediction model. The optimized sample category prediction model predicts the mineral sample category and generates interactive data visualization charts using the Plotly library. The platform integration module is used to design an interactive visualization management platform using the Dash framework, and to integrate interactive data visualization charts into the interactive visualization management platform. The geographic information integration module is used to draw geographic heat maps of mineral samples using ArcGIS API and Matplotlib.

[0005] Preferably, in the data acquisition and storage module, the image data of the mineral samples is stored using high-quality image file formats including JPEG and PNG, and the physical property data is stored using standardized formats including CSV and JSON; the physical property data includes weight data, volume data, and composition data; the metadata includes acquisition time, acquisition location, and acquisition equipment information.

[0006] Preferably, the formatting processing module includes the steps of cleaning and preprocessing the sample data transmitted to the cloud database, which include: denoising, cropping, and resizing the image data to ensure consistent image quality; and standardizing the physical attribute data and metadata to ensure that the data of different samples have the same dimensions.

[0007] Preferably, in the visualization chart generation module, the interactive data visualization charts also include physical property-composition scatter plots, used to analyze the relationship between the physical properties and composition of mineral samples; mineral sample composition box plots, used to analyze the statistical characteristics of the distribution of mineral sample composition; and physical property distribution histograms, used to analyze the distribution of the physical properties of mineral samples.

[0008] Preferably, in the visualization chart generation module, the mineral knowledge graph is used to store the association information of mineral samples, and is stored in the graph database Neo4j or RDF format; the mineral knowledge graph The formula is: ,in, Representative mineral sample i, Attribute nodes in mineral samples , Let k be the geographic location node in the mineral sample. This represents the relationship between mineral samples and attribute nodes. This relates to the relationship between mineral samples and geographic location nodes. The formula for mineral samples in a mineral knowledge graph is: ,in, Representative mineral sample i, A unique identifier for mineral sample i. Let i be the name of the mineral sample. Let i be the mineral category of mineral sample i. The hardness of mineral sample i. Let i be the density of mineral sample i. The color of mineral sample i The geographical location where mineral sample i was collected.

[0009] Preferably, in the visualization chart generation module, the post-processing process includes: loading the trained mineral sample category prediction model, comparing the prediction result with the mineral category in the knowledge graph, calculating the similarity between the prediction result and the mineral category in the knowledge graph, and if the similarity is lower than a preset similarity threshold, correcting the prediction result and returning the corrected mineral category.

[0010] Preferably, in the geographic information integration module, the mineral sample geographic heat map supports filtering by selecting different geographic coordinates and mineral categories, and displays the distribution of mineral samples in geographic information.

[0011] The beneficial effects of this invention are as follows: Compared with the prior art, which usually relies on static data storage and manual processing, and is difficult to update and predict sample categories in real time, especially under the condition of large data volume and complex categories, it is impossible to achieve efficient data processing and intuitive data analysis visualization. This application avoids the problems of manual intervention and data processing lag by integrating knowledge graphs, sample category prediction models and data visualization applications, thereby improving the efficiency of real-time update of mineral sample data and the accuracy of predicted categories. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of a module of a mineral sample collection visualization management system provided by the present invention.

[0014] Figure 2This is a schematic diagram of the physical properties of the first embodiment of the present invention – a dispersion plot.

[0015] Figure 3 This is a schematic diagram of a box plot of mineral sample composition provided for the first embodiment of the present invention.

[0016] Figure 4 This is a schematic diagram of the physical property distribution histogram provided for the first embodiment of the present invention.

[0017] Figure 5 This is a schematic diagram of the first embodiment of the present invention after selecting a sample with a hardness greater than 7.

[0018] Figure 6 This is a schematic diagram of a geothermal map of a mineral sample provided for the first embodiment of the present invention.

[0019] Figure 7 This is a schematic diagram of a mineral sample acquisition visualization management system provided by the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Example 1: As Figure 1 The diagram shown is a schematic diagram of the modules of a mineral sample collection visualization management system provided by the present invention, and presents the first embodiment of the mineral sample collection visualization management system of the present invention.

[0022] In the first embodiment, the mineral sample collection visualization management system includes: The data acquisition and storage module is used to collect sample data of mineral samples, including image data, physical property data and metadata, build a cloud database, and transmit sample data to the cloud database through the application of the distributed message queue Apache Kafka; It should be noted that in the data acquisition and storage module, the image data of mineral samples is stored using high-quality image file formats including JPEG and PNG, and the physical property data is stored using standardized formats including CSV and JSON; the physical property data includes weight data, volume data and composition data; the metadata includes acquisition time, acquisition location and acquisition equipment information.

[0023] Understandably, mineral sample image data is stored in high-quality image formats (such as JPEG and PNG) to facilitate subsequent image processing algorithms, such as deep learning models for image data extraction and classification analysis. This image data is standardized to fixed sizes and color formats for processing and analysis with other sample data. Physical property data storage: Physical property data such as weight (e.g., in grams), volume (e.g., cubic centimeters), and mineral composition (e.g., the proportions of elements such as silicon, iron, and aluminum) are stored in CSV and JSON formats. This standardized data format allows for efficient reading and processing by other modules of the system. By comparing the physical property data of different samples, mineral samples can be classified and predicted. Metadata records basic information about the collection of mineral samples, such as collection time, location, and equipment information. This information is crucial for subsequent data analysis and mineral sample management, helping researchers trace the source of samples and ensuring data reliability and accuracy.

[0024] It should be understood that, to ensure the uniformity and comparability of different data types, physical attribute data (such as weight, volume, and composition) is converted to standard formats for storage. The use of CSV and JSON formats not only ensures data readability but also enables the data to be quickly read and parsed by other systems and algorithm modules. High-quality storage methods for image data (such as JPEG and PNG formats) ensure that image details are preserved during subsequent machine learning model training, thereby improving classification accuracy. Image data transmission and storage avoid information loss caused by compression.

[0025] For example, the image data of mineral sample A will be stored in PNG format to ensure lossless image data storage; the physical property data of the sample, including weight (300g), volume (25cm³), and chemical composition (containing 75% silicon and 5% iron), will be stored in JSON format. The metadata records the sample's collection time (February 1, 2025), collection location (mine area X), and collection equipment information (equipment number: 1001), ensuring the integrity and traceability of the sample information.

[0026] The formatting module is used to clean and preprocess the sample data transmitted to the cloud database to generate standardized sample data; It should be noted that the formatting processing module includes steps for cleaning and preprocessing the sample data transmitted to the cloud database, including: denoising, cropping, and resizing the image data to ensure consistent image quality; and standardizing the physical attribute data and metadata to ensure that the data from different samples have the same dimensions.

[0027] Understandably, denoising, cropping, and resizing during image data processing ensure consistent image quality across all samples, which improves the accuracy of subsequent image processing algorithms. For example, by removing background noise and standardizing image size, image feature extraction algorithms can more accurately identify specific mineral features, improving classification accuracy. Dimensional standardization ensures that the physical property data (such as weight and density) of different mineral samples have the same dimension, eliminating differences between different units and scales, facilitating model analysis and prediction. For instance, weight data might be in grams (g), while density data might be in g / cm³. Standardization ensures that these two data points are within the same dimensional range when input to the model, preventing any single feature from dominating model predictions.

[0028] For example, suppose mineral sample A and sample B are stored in images of different sizes and qualities. After processing, all sample images are uniformly adjusted to 256x256 pixels, and background noise is removed. This allows subsequent image feature extraction models to better identify key features of the mineral samples, such as their shape and texture. Mineral sample A weighs 300g, and mineral sample B weighs 0.3kg. After standardization, their weight data are uniformly converted into standardized scores (such as Z-scores) to ensure they have the same dimensions in subsequent analysis, facilitating comparisons between samples and model training.

[0029] The visualization chart generation module uses a pre-set mineral knowledge graph and a support vector machine to train a mineral sample category prediction model on standardized sample data. The mineral sample category prediction model is then post-processed based on the mineral knowledge graph to obtain an optimized sample category prediction model. The optimized sample category prediction model predicts the mineral sample category and generates interactive data visualization charts using the Plotly library. It should be noted that in the visualization chart generation module, the mineral knowledge graph is used to store the association information of mineral samples, and is stored in the graph database Neo4j or RDF format; the mineral knowledge graph The formula is: ,in, Representative mineral sample i, Attribute nodes in mineral samples , Let k be the geographic location node in the mineral sample. This represents the relationship between mineral samples and attribute nodes. This relates to the relationship between mineral samples and geographic location nodes. The formula for mineral samples in a mineral knowledge graph is: ,in, Representative mineral sample i, A unique identifier for mineral sample i. Let i be the name of the mineral sample. Let i be the mineral category of mineral sample i. The hardness of mineral sample i. Let i be the density of mineral sample i. The color of mineral sample i The geographical location where mineral sample i was collected.

[0030] In the visualization chart generation module, the post-processing process includes: loading the trained mineral sample category prediction model, comparing the prediction results with the mineral categories in the knowledge graph, calculating the similarity between the prediction results and the mineral categories in the knowledge graph, and if the similarity is lower than the preset similarity threshold, correcting the prediction results and returning the corrected mineral categories.

[0031] It should be understood that knowledge graphs are not merely storage tools; they provide reasoning capabilities. By comparing model predictions with information in the graph, the correlation information of mineral samples can be fully utilized to correct the model's output, ensuring more reliable and accurate results. For example, suppose the predicted category for mineral sample A is "quartz," but based on its physical properties such as hardness and density, the knowledge graph identifies it more closely as "granite." In this case, after calculating the similarity, the system finds that the predicted category has a low similarity to the actual category. Therefore, based on the information in the graph, the system corrects the category to "granite," ultimately outputting the corrected mineral category.

[0032] The visualization chart generation module includes interactive data visualization charts such as physical property-composition scatter plots, used to analyze the relationship between the physical properties and composition of mineral samples; mineral sample composition box plots, used to analyze the statistical characteristics of the distribution of mineral sample composition; and physical property distribution histograms, used to analyze the distribution of the physical properties of mineral samples.

[0033] It should be understood that physical property-composition scatter plots: These plots allow users to visually see the relationship between the physical properties and chemical composition of a mineral sample. If there are clear trends or correlations between certain physical properties and components, scatter plots will help uncover these potential patterns. Mineral sample composition box plots: Box plots can show the distribution of component data in a sample, highlighting extreme values, upper quartiles, medians, and lower quartiles. Physical property distribution histograms: Histograms allow users to clearly understand the distribution characteristics of a mineral sample in a specific physical property (such as hardness, density, etc.). For example, if hardness data is concentrated within a range, the histogram will show a clear peak, indicating the concentration of the sample.

[0034] For example, such as Figure 2 , 3 As shown in Figure 4, the physical property-dispersion plot displays the relationship between hardness and silicon content (%), helping to analyze whether there is a correlation between these two properties. The mineral sample composition box plot shows the distribution of iron content (%), helping to identify central tendency and outliers in the data. The physical property distribution histogram shows the distribution of hardness data, allowing observation of the distribution of hardness data in the sample.

[0035] The platform integration module is used to design an interactive visualization management platform using the Dash framework, and to integrate interactive data visualization charts into the interactive visualization management platform. It's worth noting that Dash is a framework for building interactive web applications. It boasts powerful visualization capabilities and can be integrated with Python data analysis libraries (such as Pandas and NumPy) to easily transform data into interactive charts. Dash enables the creation of interactive charts that not only dynamically display data but also interact with other charts and controls (such as dropdowns and buttons), updating their content in real time.

[0036] It should be understood that the platform is more than just a visualization tool; it integrates all data into a unified framework, allowing users to obtain real-time feedback through clicks, filtering, and other operations. This makes data management more efficient and enables the handling of large-scale datasets. Whenever a user selects or enters new filter criteria, the relevant charts update dynamically, ensuring that the user can see the latest data analysis results under the current conditions.

[0037] For example, such as Figure 5 As shown, suppose a user selects "hardness" as a filter on the management platform and specifies a hardness range (e.g., mineral samples with a hardness greater than 7). The system will dynamically generate a scatter plot displaying samples with a hardness greater than 7, with data for each sample shown in the chart. Users can further click on a sample to view its detailed physical properties, composition information, and collection location. Through this interactive operation, users can not only analyze mineral sample data more intuitively but also freely explore the data according to different needs, thereby improving the efficiency of mineral sample management and research.

[0038] The geographic information integration module is used to draw geographic heat maps of mineral samples using ArcGIS API and Matplotlib.

[0039] It should be noted that the ArcGIS API is a geographic information data center interface that, when combined with geographic location data, can display the distribution of mineral samples on a map.

[0040] Understandably, heatmaps allow users to visually see the distribution of mineral samples within a specific geographical area. For example, a higher density of mineral samples in a particular area indicates that the minerals are concentrated there. Geographical heatmaps can be dynamically updated based on various conditions; for instance, when a user selects a specific mineral category, the heatmap will only display the distribution of mineral samples belonging to that category.

[0041] It should be understood that heat maps allow users to clearly identify areas of concentrated samples, which is very helpful for mineral resource exploration. Integration with other data: In addition to mineral location, users can combine other sample data (such as hardness, density, etc.) to further analyze the relationship between different physical properties and geographical distribution using heat maps.

[0042] For example, such as Figure 6 As shown in the heat map, mineral sample A (e.g., "granite") has a higher density in one mining area and a lower density in other areas. Users can use this analysis to preliminarily infer that the mining area may have high mineral resource reserves.

[0043] In addition, the present invention also provides a visual management device for mineral sample collection, please refer to... Figure 7A mineral sample acquisition visualization management device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to execute the mineral sample acquisition visualization management system described in Embodiment 1 above. The mineral sample acquisition visualization management device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. This mineral sample acquisition visualization management device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this invention. A mineral sample acquisition visualization management device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of a mineral sample acquisition visualization management device. Processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows a mineral sample acquisition visualization management device to communicate wirelessly or wiredly with other devices to exchange data. Although a mineral sample acquisition visualization management device with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0044] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the mineral sample collection visualization management system described above. The computer program product provided by this invention can solve a technical problem related to the visualization management of mineral sample collection. Compared with the prior art, the beneficial effects of the computer program product provided by this invention are the same as those of the mineral sample collection visualization management system provided in the above embodiments, and will not be repeated here.

[0045] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the system diagram can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined above in the system of the embodiments disclosed in this invention.

[0046] It should be understood that the various parts disclosed in this invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0047] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A visual management system for mineral sample collection, characterized in that, The system includes: The data acquisition and storage module is used to collect sample data of mineral samples, including image data, physical property data and metadata, build a cloud database, and transmit sample data to the cloud database through the application of the distributed message queue Apache Kafka; The formatting module is used to clean and preprocess the sample data transmitted to the cloud database to generate standardized sample data; The visualization chart generation module uses a pre-set mineral knowledge graph and a support vector machine to train a mineral sample category prediction model on standardized sample data. The mineral sample category prediction model is then post-processed based on the mineral knowledge graph to obtain an optimized sample category prediction model. The optimized sample category prediction model predicts the mineral sample category and generates interactive data visualization charts using the Plotly library. The platform integration module is used to design an interactive visualization management platform using the Dash framework, and to integrate interactive data visualization charts into the interactive visualization management platform. The geographic information integration module is used to draw geographic heat maps of mineral samples using ArcGIS API and Matplotlib.

2. The mineral sample acquisition visualization management system as described in claim 1, characterized in that, In the data acquisition and storage module, image data of mineral samples is stored using high-quality image file formats including JPEG and PNG, while physical property data is stored using standardized formats including CSV and JSON. Physical property data includes weight data, volume data, and composition data. Metadata includes acquisition time, acquisition location, and acquisition equipment information.

3. A mineral sample acquisition visualization management system as described in claim 1, characterized in that, The formatting module includes steps for cleaning and preprocessing sample data transmitted to the cloud database, such as: denoising, cropping, and resizing image data to ensure consistent image quality; and standardizing the physical attribute data and metadata to ensure that data from different samples have the same dimensions.

4. A mineral sample acquisition visualization management system as described in claim 1, characterized in that, The visualization chart generation module includes interactive data visualization charts such as physical property-composition scatter plots, used to analyze the relationship between the physical properties and composition of mineral samples; mineral sample composition box plots, used to analyze the statistical characteristics of the distribution of mineral sample composition; and physical property distribution histograms, used to analyze the distribution of the physical properties of mineral samples.

5. A mineral sample acquisition visualization management system as described in claim 1, characterized in that, In the visualization chart generation module, the mineral knowledge graph is used to store the association information of mineral samples, stored in the graph database Neo4j or RDF format; the mineral knowledge graph The formula is: ,in, Representative mineral sample i, Attribute nodes in mineral samples , Let k be the geographic location node in the mineral sample. This represents the relationship between mineral samples and attribute nodes. This relates to the relationship between mineral samples and geographic location nodes. The formula for mineral samples in a mineral knowledge graph is: ,in, Representative mineral sample i, A unique identifier for mineral sample i. Let i be the name of the mineral sample. Let i be the mineral category of mineral sample i. The hardness of mineral sample i. Let i be the density of mineral sample i. The color of mineral sample i The geographical location where mineral sample i was collected.

6. A mineral sample acquisition visualization management system as described in claim 1, characterized in that, In the visualization chart generation module, the post-processing process includes: loading the trained mineral sample category prediction model, comparing the prediction results with the mineral categories in the knowledge graph, calculating the similarity between the prediction results and the mineral categories in the knowledge graph, and if the similarity is lower than the preset similarity threshold, correcting the prediction results and returning the corrected mineral categories.

7. A mineral sample acquisition visualization management system as described in claim 1, characterized in that, In the geographic information integration module, the mineral sample geographic heat map supports filtering by different geographic coordinates and mineral categories, and displays the distribution of mineral samples in geographic information.

Images