Geological disaster data acquisition method and system

Abstract

The invention provides a geological disaster data acquisition method and system, which is used for improving data acquisition and processing efficiency and improving comprehensiveness and accuracy of data survey, and comprises the following steps: acquiring indoor preparation data, performing project data configuration based on the indoor preparation data, and performing project data acquisition based on the configured project data and indoor preparation data. Generating a field survey graph; the method comprises the following steps: performing navigation positioning on a mobile terminal based on a field survey graph, and determining a positioned survey point position after the mobile terminal reaches a survey target position range; at the survey point position, field survey data including point data, line data, surface data and attribute data are collected through the mobile terminal, and a field survey record is formed; and acquiring sensor monitoring data acquired by the low-power-consumption monitoring terminal, and performing space-time correlation matching on the field survey record and the sensor monitoring data to obtain fused survey data. And performing data arrangement and standardized conversion on the fused survey data to obtain geological disaster data in a standard database format.

Description

Technical Field

[0001] This disclosure relates to the field of geological research technology, and in particular to a method and system for acquiring geological disaster data. Background Technology

[0002] Geological hazard investigation is a core and fundamental link in disaster prevention and mitigation. The collection, management, and application of its data directly affect the scientific rigor and timeliness of disaster risk assessment and prevention decisions. Traditional geological hazard investigation work mainly relies on paper-based records and manual data processing, which is no longer adequate for the needs of efficient and accurate investigations in complex field environments, and presents many prominent problems.

[0003] For example, traditional geological hazard surveys are highly inefficient in terms of coordinating indoor data preparation with fieldwork. Office staff must compile massive amounts of paper-based basic data, while field staff must carry heavy maps to the site, spending considerable time comparing maps with the actual terrain, resulting in low efficiency. Furthermore, traditional survey point location relies on manual judgment based on topographical experience, leading to insufficient accuracy in point location and identification. Summary of the Invention

[0004] In view of this, this disclosure provides a method and system for collecting geological disaster data, in order to improve the efficiency of data collection and processing, and to enhance the comprehensiveness and accuracy of data surveys.

[0005] Firstly, a method for collecting geological disaster data is provided, including: Acquire indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data. Based on the field survey map, the mobile device is navigated and positioned, and the location of the survey point is determined after the mobile device reaches the survey target location range. At the survey point location, field survey data, including point data, line data, area data, and attribute data, are collected through the mobile terminal to form a field survey record; The sensor monitoring data collected by the low-power monitoring terminal is acquired, and the field survey records and the sensor monitoring data are spatiotemporally correlated and matched to obtain fused survey data.

[0006] The fused survey data is then processed and standardized to obtain geological disaster data in a standard database format.

[0007] Optionally, the field survey records and the sensor monitoring data are spatiotemporally correlated and matched to obtain fused survey data, including: The field survey data and the sensor monitoring data are spatiotemporally correlated and matched to generate a correlated dataset; A hybrid long short-term memory network model is used to complete the missing data and filter out abnormal noise in the associated dataset to obtain the fused survey data.

[0008] Optionally, the step of acquiring indoor preparation data, configuring project data based on the indoor preparation data, and generating a field survey map based on the configured project data and indoor preparation data includes: Acquire basic geographic data, geological maps, remote sensing images, and geological hazard distribution maps as indoor preparation data, and perform vectorization or rasterization processing on the indoor preparation data to obtain standardized basic data; Based on the standardized basic data, the project's basic information is set, the work area is configured, and the data resources are configured to generate the configured project data. Based on the configured project data and the standardized basic data, a field survey map is generated.

[0009] Optionally, the indoor preparation data is vectorized or rasterized to obtain standardized basic data, including: Based on the indoor preparation data, a raster data compression algorithm is used to compress the raster image data and establish a spatial index to generate compressed raster data. The compressed raster data is processed by a decompression algorithm for fast loading and smooth display, resulting in standardized basic data that can be displayed on mobile devices.

[0010] Optionally, based on the field survey map, the mobile device is navigated and positioned, and after the mobile device reaches the survey target location range, the location of the survey point is determined, including: The GPS or BeiDou satellite positioning signal of the mobile device is acquired, the coordinates of the positioning signal are calculated and the calculation accuracy is optimized to obtain the real-time location coordinates of the mobile device. Based on the field survey map and the real-time location coordinates, real-time dynamic route guidance is provided through point-based navigation or coordinate navigation, and the location of survey points is quickly determined by combining terrain and feature recognition.

[0011] Optionally, based on the field survey map and the real-time location coordinates, real-time dynamic route guidance is provided through point-based navigation or coordinate navigation, and the location of survey points is quickly determined by combining terrain and feature recognition, including: After the mobile terminal reaches the target location range based on the real-time dynamic route guidance, it determines the type of the investigation point based on the real-time location coordinates, and identifies the investigation point as a landslide point, collapse point, debris flow point, or special engineering geological point. Based on the survey point type, perform the corresponding classification and point creation operation to obtain the survey point locations under the survey point type.

[0012] Optionally, field survey data, including point data, line data, area data, and attribute data, are collected through the mobile terminal to form a field survey record, including: The field survey data, including point data, line data, area data, and attribute data, is collected through a mobile data acquisition system. This data is used to enter information into field survey record forms, draw entity sketches, create plan and profile diagrams, and take photos. The system forms the field survey record.

[0013] Optionally, entity delineation can be performed using a mobile data acquisition system, including: Based on the location of the survey points and the field survey map, the boundaries, cracks and lithological observation points are marked by a combination of points, lines and surfaces. The back wall of the landslide, boundary line, sliding direction, deposit, hazard range and debris flow source area, flow area and deposition area are delineated, and vector graphics containing point data, line data and surface data are generated. For the vector graphics, the basic element information of points, lines, and surfaces is entered to obtain entity drawing data that associates spatial vector data and professional attribute data.

[0014] Optionally, it also includes: Based on the line and surface data of the landslide back wall and debris flow source area in the fused survey data, the common edge automatic tracking and island area adjustment algorithm are used for topological correction to generate constraints for three-dimensional modeling. Based on the constraints of the three-dimensional modeling and the elevation data of the digital elevation model (DEM), a triangulation algorithm is used to quickly generate a three-dimensional surface model from the two-dimensional boundary delineation, thus obtaining a three-dimensional model of geological hazards. By associating the geological hazard 3D model with the attribute information of strata lithology and hazard body structure, volume calculation, slope analysis and stability simulation functions are provided to obtain a 3D geological body model that can be visualized and analyzed.

[0015] Optionally, the method further includes: Based on the fused survey data and historical disaster data, the risk level is calculated through the landslide probability prediction model and the debris flow risk prediction model. The risk level is updated every preset time interval and a visual risk heat map is generated to obtain real-time risk assessment results. Based on the real-time risk assessment results, the investigation route is dynamically optimized to generate an optimized investigation path that avoids high-risk areas. When the real-time risk assessment result reaches the extremely dangerous risk level, a mobile audible and visual warning is triggered and the optimal evacuation route is pushed. At the same time, the management center pushes warning information and receives emergency response instructions.

[0016] This disclosure also provides a geological disaster data acquisition method, applied to a cloud management platform, including: Acquire indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data. Send a map of the field survey to the mobile device; The system receives field survey records uploaded by the mobile terminal and obtains sensor monitoring data collected by the low-power monitoring terminal. It performs spatiotemporal correlation matching on the field survey records and the sensor monitoring data to obtain fused survey data. The fused survey data is then processed and standardized to obtain geological disaster data in a standard database format.

[0017] This disclosure also provides a method for collecting geological disaster data, applied to a mobile device, including: Receive the field survey map; perform navigation and positioning based on the field survey map, and determine the location of the survey point after reaching the survey target location range; collect field survey data including point data, line data, area data and attribute data at the survey point location to form a field survey record; upload the field survey record to the cloud management platform.

[0018] This disclosure also provides a geological disaster data acquisition system, including a cloud management platform and a mobile terminal; The cloud management platform is used to acquire indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data, and then send the field survey map to the mobile terminal; receive field survey records uploaded by the mobile terminal; acquire sensor monitoring data collected by a low-power monitoring terminal, perform spatiotemporal correlation matching on the field survey records and the sensor monitoring data to obtain fused survey data; and perform data processing and standardization conversion on the fused survey data to obtain geological disaster data in a standard database format. The mobile terminal is used to receive the field survey map, perform navigation and positioning based on the field survey map, and determine the location of the survey point after reaching the survey target location range; at the survey point location, it collects field survey data including point data, line data, area data and attribute data, forms a field survey record, and uploads it to the cloud management platform.

[0019] This embodiment generates a single map of the field survey based on indoor preparation data, and uses positioning technology to provide real-time dynamic route guidance to mobile devices, eliminating the need for manual on-site determination of survey point locations and thus shortening field data collection time. The mobile device collects field survey data including point data, line data, area data, and attribute data, forming a comprehensive field survey record. Furthermore, by performing spatiotemporal correlation matching between the field survey data and monitoring data from low-power monitoring terminals, the comprehensiveness and accuracy of the fused survey data can be greatly improved. The fused data, after standardization conversion, enters a standard database, avoiding the traditional situation where data is scattered and stored in paper forms or personal devices. This directly supports collaborative access and sharing among multiple departments and positions, improving the overall collaborative efficiency of the survey work. Attached Figure Description

[0020] Figure 1 A flowchart of a geological disaster data acquisition method provided in this embodiment of the disclosure; Figure 2 To present a schematic diagram of the entire process of geological disaster investigation, from indoor preparation to field implementation and then to data processing; Figure 3 This disclosure provides a flowchart of a geological disaster data acquisition method applied to a cloud management platform. Figure 4 This disclosure provides a flowchart of a geological disaster data acquisition method applied to a mobile device. Figure 5 A schematic diagram of a geological disaster data acquisition system provided in this embodiment of the disclosure; Figure 6 This is a schematic diagram of the structure of an electronic device shown as an exemplary embodiment of the present disclosure. Detailed Implementation

[0021] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0022] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0023] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0024] Furthermore, the symbol “ / ” in this disclosure indicates that there is an “or” relationship between the related objects before and after the symbol, or that the related objects have an exemplary relationship that can coexist.

[0025] Research has revealed that in the field of geological disaster investigation, traditional data collection and management models have long faced numerous technical bottlenecks, making it difficult to meet the demands of modern geological disaster prevention and control for data timeliness, completeness, and accuracy. For example, the traditional data collection and management model is highly inefficient in coordinating indoor data preparation with field operations. Specifically, before traditional field surveys, office staff need to compile a massive amount of paper-based basic data (such as geological maps, remote sensing images, and disaster distribution maps), while field staff need to carry heavy maps to the site. This is not only inconvenient to carry, but also results in inconsistent coordinate systems and formats among different data sources, making it difficult to quickly locate target areas during field operations. A significant amount of time must be spent comparing maps with the actual terrain, leading to low operational efficiency. For example, traditional data collection and management models suffer from serious inaccuracies in locating and identifying survey points. Specifically, traditional survey point location relies on manual judgment based on topographical experience or rough positioning using handheld GPS, lacking linkage with basic geographic data and geological hazard distribution data. This easily leads to survey point misalignment, omissions, or duplicate surveys. Furthermore, the lack of standardized guidelines for classifying and identifying different types of survey points such as landslides, collapses, and debris flows results in weak data relevance and significant challenges in subsequent analysis. Additionally, traditional data collection and management models suffer from simplistic data collection methods and inconsistent quality. Specifically, traditional field data collection primarily relies on paper forms, recording only limited attribute data and failing to simultaneously collect spatial vector data such as points, lines, and areas. Manual completion is prone to issues like illegible handwriting, missing information, and inconsistent formatting. Data collection depends entirely on manual operation, lacking supplementary automatic monitoring data, failing to comprehensively reflect the dynamic changes of geological hazard risks, and compromising data integrity and reliability. For example, traditional data collection and management models suffer from a severe lack of multi-source data fusion and management capabilities. Specifically, in the traditional model, data collected manually in the field and data acquired by a limited number of monitoring devices are independent of each other, lacking an effective correlation and matching mechanism. The two types of data are difficult to integrate and utilize, hindering a comprehensive understanding of potential geological hazards. Furthermore, collected data is mostly stored in paper or fragmented electronic file formats, lacking a unified standardized processing procedure. Data formats are chaotic, management is fragmented, and data loss or damage is common, making it difficult to quickly transform into effective data for analysis and decision-making. Additionally, the data processing workflow in traditional data collection and management models is fragmented and inefficient. Specifically, in traditional work, field-collected data must first be brought back indoors for manual entry, processing, and format conversion before subsequent analysis. This results in a lag between indoor and outdoor work, and a long cycle from data collection to usable results. Moreover, manual processing is prone to data errors and duplicate entries, further increasing the workload and failing to meet the real-time data requirements for geological disaster prevention and control.

[0026] To address the aforementioned issues, the solution proposed in this disclosure integrates multi-source indoor basic data to generate a single map for field surveys, avoiding the need for field personnel to carry massive amounts of paper documents. Simultaneously, it leverages mobile terminal navigation and positioning functions to quickly locate survey points, replacing the inefficient traditional manual point-finding method. Data acquisition supports collaborative input of multiple data types, including points, lines, and areas, and, in conjunction with standardized input specifications, significantly reduces the workload of filling out paper forms and manually translating data, thereby improving field operation efficiency. Secondly, it performs spatiotemporal correlation matching between sensor data (such as mountain slope angle, crack displacement, and precipitation data) collected by low-power monitoring terminals and mobile terminal field survey records, achieving data complementarity between manual collection and automatic monitoring. This overcomes the shortcomings of traditional single manual collection, which is prone to omissions and is susceptible to subjective factors. During the fusion process, missing data is supplemented and abnormal noise is filtered, further ensuring data integrity and accuracy, and reducing the risk of data loss or retesting. Furthermore, from indoor data preprocessing and field data collection to the fusion and organization of the data, the entire process follows standardized processing rules, ultimately outputting geological disaster data in a standard database format. This solves the problems of fragmented data management, inconsistent formats, and difficulty in integration and utilization, laying the foundation for subsequent data sharing, analysis, and application. Moreover, based on the navigation and positioning function of a single map for field surveys and the function of classifying and establishing survey points, combined with terrain and feature recognition technology, it ensures accurate positioning of survey points and avoids omissions or duplications in the survey scope. The real-time monitoring data from the low-power monitoring terminal is linked with the field survey data, enabling early detection of dynamic changes in geological disaster hazards and providing indirect protection for the safety of field personnel. Furthermore, the solution of this disclosure achieves closed-loop management of the entire process from indoor data preparation, field data collection, multi-source data fusion to standardized database output, reducing the disconnect between indoor and field work, avoiding the efficiency losses caused by the disconnect between data collection and data processing in traditional work, and ensuring a smooth flow of data from collection to application.

[0027] It should also be noted that, with the development of intelligent robot technology, the "field personnel" mentioned in this embodiment can be mobile robots that can replace field personnel to perform field operations, in addition to human workers.

[0028] The solutions of the present disclosure will be further described in detail below through specific embodiments.

[0029] like Figure 1 As shown, a geological disaster data acquisition method provided in this embodiment includes: S101: Obtain indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data.

[0030] In practice, basic geographic data, geological maps, remote sensing imagery, and geological hazard distribution maps can be acquired as indoor preparation data. This indoor preparation data is then vectorized or rasterized to obtain standardized basic data. Based on this standardized basic data, basic project information is set, work area scope is configured, and data resources are configured to generate the configured project data. Based on the configured project data and the standardized basic data, a field survey map is generated.

[0031] The basic geographic data here includes Digital Line Graphic (DLG), Digital Elevation Model (DEM), Digital Raster Graphic (DRG), and Digital Orthophoto Map (DOM).

[0032] Because the various basic geographic and geological data collected by office staff may have inconsistent formats (e.g., some are paper scans, some are vector files generated by different software), inconsistent accuracy, and redundant information, they cannot be directly used for field surveys. Therefore, they need to be standardized. Vectorization or rasterization can eliminate the format differences of data from different sources (e.g., paper scans, CAD files, Excel spreadsheets), ensuring that the data can be smoothly loaded and accessed in mobile data acquisition systems and web-based management systems. Raster data (e.g., images, scans) is suitable for visually displaying surface landscapes and original map information, while vector data (e.g., feature boundaries, survey routes) is suitable for precise positioning and attribute association. The processing method should be selected according to the actual purpose of the field survey (e.g., navigation, entity delineation, attribute query). In addition, by processing and correcting issues such as coordinate deviation and insufficient resolution of the original data, it is ensured that the data accurately matches the actual terrain and survey point locations, avoiding survey deviations caused by data errors.

[0033] Vectorization refers to converting non-vector data into vector data. For example, raw data may be unstructured spatial information, such as scanned copies of paper geological maps (DRG original scans), feature boundaries in satellite imagery, or hand-drawn survey route maps. This type of data is only visually appealing and cannot directly extract structured information such as feature coordinates, length, and area. It needs to be converted into calculable and associative vector data. In practice, scanned maps and images can be imported into professional Geographic Information System (GIS) software (such as ArcGIS or QGIS). By matching known coordinate points (such as latitude and longitude markers and triangulation points on a map), coordinate deviations in the data are corrected to ensure consistency with the actual location. Then, based on the graphic characteristics of the raw data, key geographic / geological elements are manually or automatically extracted and represented using points (such as historical landslide points, borehole locations, and monitoring equipment deployment points), lines (such as geological boundaries, landslide backwall boundaries, survey routes, and rivers), and area vector symbols (such as debris flow source areas, stratigraphic distribution areas, and work area boundaries). Afterwards, structured attribute information can be added to each vector feature. For example, attributes such as "landslide type, occurrence time, and scale" can be associated with the "landslide point" vector point, and attributes such as "lithology and thickness" can be associated with the "surface layer". Finally, vector data conforming to standard GIS formats (such as shape files SHP and GeoJSON) can be generated, which can be directly used for feature labeling, survey point classification and point establishment, and boundary reference when drawing entities in "one map for field survey".

[0034] Rasterization refers to converting non-raster data into raster data. This is useful for scenarios where the original data is vector data or non-image data, but needs to be displayed in a visually appealing image / drawing format. Examples include converting a vector-format DEM into a raster terrain rendering map, or converting a CAD-format geological map into a raster base map. The core advantages of raster data are its superior visualization and fast loading speed, making it suitable for quickly comparing data with actual terrain during field surveys. In practice, data format conversion can be used to transform vector data (such as DLG and DEM vector files) or non-image data into raster data in pixel matrix form using rasterization algorithms (such as pixel allocation and interpolation). Additionally, the pixel density of the raster data can be adjusted according to the mobile screen resolution (such as 720P / 1080P for tablets) to avoid loading lag due to excessively high resolution or blurry details due to excessively low resolution. Color mapping can be added to geological maps and topographic maps (such as using different colors to represent different strata and grayscale to represent terrain slope) to improve the visibility during field surveys. Finally, raster data compression algorithms (such as JPEG2000 and LZ77) can be used to reduce file size, while spatial indexing (such as quadtree indexing) can be established to ensure fast loading and smooth display when zooming and panning on mobile devices. Ultimately, raster data (such as TIFF and PNG formats) that meets the display requirements of mobile / web devices can be generated as a "single map for field surveys." The background map helps field personnel to visually confirm the location of survey points and topographic features through images / drawings.

[0035] Here, the indoor preparation data is vectorized or rasterized to obtain standardized basic data, which may include: based on the indoor preparation data, using a raster data compression algorithm to compress the raster image data and establish a spatial index to generate compressed raster data; and using a decompression algorithm to perform fast loading and smooth display processing on the compressed raster data to obtain standardized basic data that can be displayed on mobile devices.

[0036] Raster image data (such as DOM and DRG) contains a large amount of pixel information, some of which is redundant (e.g., in continuous vegetation areas, the color and brightness differences between adjacent pixels are minimal). Raster data compression algorithms (such as JPEG2000, LZ77, CCITT G3 / G4, etc.) can remove this redundant information while maintaining image clarity to meet survey requirements, significantly reducing file size. Although compressed raster data is smaller, direct loading still requires reading the entire image file at once, which can cause loading lag on mobile devices with limited hardware performance (e.g., when viewing large-scale images, one must wait for all pixels to be rendered before operation). By establishing a spatial index (commonly quadtree indexes or R-tree indexes), large raster images can be divided into multiple smaller blocks (e.g., 256×256 pixel tiles), and the spatial coordinate range (e.g., latitude and longitude range) of each block can be recorded. When loading on a mobile device, it is not necessary to read the entire file; only the corresponding smaller image block in the currently displayed area needs to be quickly located and read, achieving on-demand loading. For example, when field personnel view images of the area surrounding a landslide site on a tablet computer (PAD), the system only loads 1-2 small image patches containing that landslide site, rather than the entire county's imagery, resulting in a loading speed several times or even tens of times faster. Furthermore, compressed raster data (especially those using lossy compression) cannot be displayed directly; it requires a corresponding decompression algorithm (matched to the compression algorithm, such as the JPEG2000 decompression algorithm) to restore the compressed pixel information to renderable image data.

[0037] S102: Based on the field survey map, navigate and locate the mobile terminal, and determine the location of the survey point after the mobile terminal reaches the survey target location range.

[0038] In practice, GPS or BeiDou satellite positioning signals from the mobile device can be acquired, coordinates can be calculated from the positioning signals and the calculation accuracy can be optimized to obtain the real-time location coordinates of the mobile device. Based on the field survey map and the real-time location coordinates, real-time dynamic route guidance can be provided through point navigation or coordinate navigation, and the location of survey points can be quickly determined by combining terrain and feature recognition.

[0039] Here, after receiving satellite signals, the mobile device needs to convert the satellite signal data into directly usable geographic coordinates through algorithms and optimize the accuracy to obtain real-time location coordinates. Point-based navigation refers to the automatic calculation of the optimal route (avoiding obstacles such as steep slopes and rivers) based on the mobile device's current location coordinates and the coordinates of the survey point when field personnel directly select a target survey point (such as a landslide point) on a map during field investigation. The current location and remaining route are then marked on the map in real time, allowing field personnel to simply follow the route guidance on the map. Coordinate navigation (precise coordinate guidance): If the survey point has been pre-entered with precise coordinates (such as latitude and longitude), field personnel can input these coordinates on the mobile device, directly receiving direction guidance in the form of coordinate differences (e.g., "500 meters from the target point, proceed northeast"). Simultaneously, the straight-line distance and direction from the current location to the target point are displayed on the map. This is suitable for scenarios where the survey point is hidden (such as dense forests or canyons) and where visual navigation is difficult to identify the path.

[0040] Once field personnel arrive at the target location (e.g., within 10-50 meters of the target point) using navigation, they need to further confirm the precise location of the survey point through terrain and feature identification to avoid misidentification due to coordinate errors or similar terrain. Field personnel compare the surrounding features of the survey point marked on a field survey map (e.g., "Landslide point is located 20 meters southeast of a mountain peak, near a gully," "Debris flow point is located at a river bend, next to a large tree") with observed terrain features (e.g., mountain peaks, gullies) and features (e.g., trees, rivers) observed on-site. After successful matching, the current location is confirmed as the target survey point. Simultaneously, based on the survey point type (e.g., landslide, collapse, debris flow), a classification and point creation operation is performed on the mobile device (e.g., selecting the landslide type automatically associates the corresponding survey table and data collection template) to prepare for subsequent data collection.

[0041] In one implementation, after the mobile terminal reaches the target location range based on the real-time dynamic route guidance, the type of the survey point can be determined based on the real-time location coordinates to identify whether the survey point is a landslide point, collapse point, debris flow point, or special engineering geological point; according to the survey point type, the corresponding type of classification and point establishment operation is performed to obtain the location of the survey point under the survey point type.

[0042] In practice, on a single map during a field survey, the coordinate range and type attributes of all preset survey points can be marked in advance (e.g., survey points within a certain coordinate range are preset as "landslide points," and another range as "debris flow points"). When field personnel arrive at the target area, the mobile device will automatically match the current real-time location coordinates with the preset survey point coordinate range on the map, providing preliminary suggestions on the candidate types of survey points in that area (e.g., the current area's preset type: landslide point / collapse point). Field personnel can combine the geological hazard characteristics observed on-site to make a final confirmation of the candidate types. For example, if a mountain has obvious sliding surface, steep back wall, and accumulation body, it is judged as a landslide point; if rock or soil suddenly falls from a steep slope and forms a colluvial cone, it is judged as a collapse point; if a large amount of loose material is observed in the valley and there are traces of flood erosion, it is judged as a debris flow point; if it is a special engineering geological point (such as a point used to monitor the lithology of strata and the stability of the foundation), the type needs to be confirmed by combining the engineering purpose marked on a map of the field survey (such as an engineering geological point in a bridge site selection area) with the actual stratum exposure (such as rock outcrops).

[0043] Different types of geological hazard survey sites require completely different data dimensions (e.g., landslide sites need to focus on recording the sliding direction and crack length, while debris flow sites need to focus on recording the area of ​​the source area and the slope of the flow zone). Categorized site construction can include the process of loading data collection templates and associating them with collection tools, allowing field personnel to start targeted data collection directly after site construction is completed, without having to manually switch templates or configure fields, thus greatly improving efficiency.

[0044] Here, the loaded data collection template has been pre-set according to the geological disaster investigation specifications, containing all the fields that need to be collected for this type of investigation. Associated collection tools, such as automatically activating the dedicated collection tools required for this type of investigation, are convenient for direct use in subsequent data collection. For example, the crack drawing tool (used to draw the line features of landslide cracks), the slope measurement tool (used to measure the slope of the landslide body), and the sliding direction labeling tool (used to mark the sliding direction arrows of the landslide on the map) are automatically activated.

[0045] Optionally, before loading the data acquisition template, the classification and point establishment may include a coordinate calibration process. For example, the mobile device can display the current location coordinates based on real-time GPS / BeiDou signals. Field personnel can fine-tune the coordinates based on the core characteristics of the landslide (such as the back wall of the landslide, the main crack) to ensure that the point falls on the location most representative of the landslide characteristics (such as the midpoint of the main crack), rather than the approximate area reached by navigation. For instance, field personnel can drag a temporary point icon on the map to adjust it from the navigation endpoint to the midpoint of the main crack of the landslide, and the mobile device automatically records the adjusted precise coordinates (error ≤ 1 meter).

[0046] Optionally, basic attributes can be automatically added to the locations, while prompting field personnel to supplement type-specific required attributes (to avoid omitting key information). For example, basic attributes such as location number, establishment time, and investigators can be automatically filled in; for example, a prompt can pop up saying "Please supplement: landslide stability level (preliminary assessment), threatened objects (such as villages / roads)" to ensure that core attributes are not missing.

[0047] After the field staff checks that the coordinates, templates, and attributes are correct, they click "Confirm Point Creation". The system will then save the "precise coordinates + type attributes + associated template" of the point to the local machine and mark it on a map of the field survey (for example, using a "red triangle" as a unique icon for landslide points to distinguish them from other types).

[0048] In this way, through coordinate calibration, template loading, attribute initialization, association with data collection tools, and point confirmation, the vague target area is transformed into standardized survey points with clear attributes and data correlation, laying the foundation for subsequent targeted data collection (such as recording crack displacement for landslide points and marking the source area for debris flow points).

[0049] S103: At the survey point location, field survey data including point data, line data, area data and attribute data are collected through the mobile terminal to form a field survey record.

[0050] In practice, field survey data can be collected through a mobile data acquisition system, including field survey record form information entry, entity delineation, plan and profile drawing, and photo recording. This process collects field survey data, including point data, line data, area data, and attribute data, to form a field survey record.

[0051] Specifically, when entering information into the field survey record form, the information can be standardized and regulated based on the located survey points, in accordance with the technical requirements for geological disaster surveys, to generate structured survey record form data. For fields requiring large amounts of descriptive information, voice input technology is used for speech recognition and text conversion to obtain complete survey record form data containing text descriptions. Based on the complete survey record form data, the Android system's SharedPreferences is used to save the complete survey record form data as a String type, thus obtaining the survey record form data.

[0052] When performing entity delineation, based on the location of the survey points and the field survey map, the boundaries, cracks and lithological observation points can be marked using a combination of points, lines and surfaces. The back wall of the landslide, boundary line, sliding direction, deposit, hazard range and debris flow source area, flow area and deposition area can be delineated, generating vector graphics containing point data, line data and surface data. The basic element information of points, lines and surfaces is entered into the vector graphics to obtain entity delineation data with associated spatial vector data and professional attribute data.

[0053] Here, when obtaining entity delineation data that associates spatial vector data and professional attribute data based on the vector graphics, the vector graphics can be used to automatically track and capture common edges, divide and merge graphics, adjust isolated areas, and blend line and surface layers using graphic editing tools to generate topologically correct vector graphics. For the topologically correct vector graphics, graphic deletion, node movement, node deletion, node addition, surface division, surface merging, surface common edge processing, and attribute modification operations are performed to obtain accurate entity delineation data.

[0054] When drawing plan and profile diagrams, high-precision remote sensing images, geographic base maps, and DEM data can be acquired. A base layer is generated by taking screenshots and extracting topographic lines to obtain the base map data to be drawn. Based on the base map data, it is overlaid with standard drawing grid paper, and the plan and profile diagrams are drawn in detail on a mobile device using professional drawing software to obtain the plan and profile diagram data.

[0055] When taking photos, the mobile device can take photos on-site based on the located survey point, automatically link the survey point with the photo record, and generate photo data containing the photo shooting location, shooting time and GPS coordinates; the mirror direction and photo description information are entered into the photo data to obtain complete photo record data.

[0056] S104: Acquire sensor monitoring data collected by the low-power monitoring terminal, perform spatiotemporal correlation matching on the field survey records and the sensor monitoring data, and obtain fused survey data.

[0057] Here, the low-power monitoring terminal is a miniaturized, low-power automatic monitoring device deployed at geological hazard sites (such as mountain slopes and debris flow gullies). Its core function is to collect key dynamic data on geological hazards on a long-term, stable basis and transmit the data through low-cost communication methods, thus compensating for the shortcomings of manual field surveys in real-time continuous monitoring. The fused data includes both static spatial information (such as landslide boundaries and lithology) and dynamic temporal information (such as crack change trends and precipitation correlations), which can support more in-depth applications. For example, by combining landslide lithology (manual survey) and long-term crack change data (sensors), a stability model can be established to determine whether the landslide has entered an accelerated deformation stage. Furthermore, based on the debris flow source area area (manual survey) and the precipitation-source activation threshold (sensors), the scope of source area clearing and the location of drainage projects can be designed in a targeted manner to avoid blind prevention and control measures.

[0058] In one implementation, acquiring sensor monitoring data collected by a low-power monitoring terminal includes: collecting mountain tilt data monitored by a triaxial accelerometer, crack displacement data monitored by a rope sensor, and precipitation data monitored by a digital rain gauge through a low-power monitoring terminal deployed at the monitoring point, and generating real-time monitoring data; based on the real-time monitoring data and the dynamic and static judgment results of the triaxial accelerometer, triggering an adaptive sampling strategy, using low-frequency sampling when the mountain is stationary, and switching to high-frequency sampling when slight movement is detected, to obtain optimized sensor monitoring data; transmitting the sensor monitoring data through an NB-IoT communication module, automatically caching the data to a NorFlash storage module when the network is interrupted, and resuming the transmission after the network is restored to obtain complete sensor monitoring data.

[0059] In the above steps, the spatiotemporal correlation matching means determining whether a certain sensor monitoring data and a certain field survey record meet the two conditions of being in the same time range and targeting the same spatial location (survey point); if they are met, the two types of data are bound into a set of correlated data.

[0060] In one implementation, spatiotemporal correlation matching is performed on the field survey records and the sensor monitoring data to obtain fused survey data, including: performing spatiotemporal correlation matching on the field survey data and the sensor monitoring data to generate a correlated dataset; and using a hybrid long short-term memory network model to complete missing data and filter abnormal noise in the correlated dataset to obtain the fused survey data.

[0061] Here, the correlated dataset may have issues, such as data loss due to sensor disconnection at a certain time, or abnormal values ​​caused by heavy rain (e.g., suddenly displaying a crack width of 10cm). In such cases, a hybrid long short-term memory network model can be used. On the one hand, it fills in the missing parts based on the patterns of the preceding and following data; on the other hand, it filters out obviously erroneous outliers, ultimately obtaining complete and accurate fused data. Optionally, aberrant noise can be filtered out using a lightweight neural network.

[0062] In practical implementation, a data association network can be constructed using graph theory routing algorithms based on the survey record data and the sensor monitoring data to automatically identify the spatiotemporal correspondence of data from different sources and generate an associated dataset. For missing data in the associated dataset, a trained hybrid long short-term memory network model is used to accurately complete the missing data based on the time series features and spatial correlation of the data, which can control the completion error within 5% to obtain the completed dataset. For the completed dataset, a SimpleNet lightweight neural network is integrated to perform semantic segmentation recognition and filtering of abnormal noise to obtain fused survey data.

[0063] Here, graph theory-based path selection algorithms can transform the data association problem into a network problem of finding the optimal path. Using graph theory logic, they can quickly and accurately find the correspondence between data from different sources (manual survey records and sensor monitoring data). The algorithm connects the two types of data (manual survey records and sensor data) like building a network, automatically identifying data pairs from the same time and location (e.g., "manual crack record at 10 AM on a landslide site" and "crack data from the sensor at the same point at the same time"), forming a preliminary associated dataset to avoid data misalignment. If the associated dataset is incomplete (e.g., the sensor failed to detect data due to a disconnection), a pre-trained hybrid long short-term memory network model is used, combining the temporal variation patterns of the data (e.g., data trends from the same time period in previous days) and spatial correlations (e.g., data from similar locations in the surrounding area), to fill in the missing parts. Even after completion, the data may still contain outliers (e.g., absurd data from sensor false alarms caused by heavy rain). In this case, a lightweight SimpleNet neural network is used to identify and filter out these erroneous data, ultimately obtaining complete and accurate fused data.

[0064] S105: The fused survey data is processed and standardized to obtain geological disaster data in a standard database format.

[0065] Here, organizing and standardizing the merged survey data can solve the problems of data fragmentation and inconsistent formats. Since the merged data may contain various forms such as vector files (e.g., survey point, line, and area data), tabular data (e.g., survey form information), and image data (e.g., field photos), and the formats are often disorganized (e.g., different devices export tables in different formats), organizing and standardizing the data unifies all data into a standard database-compatible format (e.g., SHP format for vector data, CSV format for attribute data), allowing direct storage into a dedicated geological disaster database without repeated manual format adjustments. Simultaneously, the unified data structure facilitates categorized storage and rapid retrieval (e.g., one-click data filtering by "landslide point type" or "survey time"), significantly reducing the manpower and time costs of data management. Furthermore, due to differences in data analysis software and database systems used by different departments (e.g., geological survey teams, emergency command centers), non-standardized data is difficult to share across platforms (e.g., custom tables from department A cannot be directly imported into department B's analysis system). Standardized data follows industry-standard formats and specifications (such as conforming to the national geological disaster database standard), enabling seamless transmission and retrieval across different units and systems. For example, standardized data from survey teams can be directly synchronized to the early warning platform of the emergency command center without secondary processing, achieving data linkage across all stages. Furthermore, non-standardized data (such as poorly formatted tables or uncalibrated coordinate data) cannot be directly used for professional analysis (such as landslide stability simulation or disaster risk assessment) and requires extensive preprocessing. During the standardization and processing, data calibration (such as correcting coordinate deviations), field unification (such as unifying "landslide direction" to "azimuth format"), and logical verification (such as deleting duplicate data) can be performed simultaneously to ensure data quality meets standards. Standardized data can be directly integrated into analysis tools (such as GIS software and risk assessment models) for rapid in-depth analysis (such as comparing landslide crack trends based on multi-period standardized data), providing accurate data support for geological disaster prevention and control plan development and risk early warning. Additionally, during the standardization process, metadata such as source identifiers (such as original survey record IDs and sensor numbers), processing timestamps, and operator information can be added to each data entry, forming a complete data traceability chain. If it is necessary to verify the accuracy of the data in the future (such as finding anomalies in the data of a landslide point), the original data source can be quickly located and the processing process can be traced through metadata to identify the problematic links (such as errors in the original survey or mistakes in the conversion operation). This not only facilitates the correction of errors but also improves the credibility and authority of the data, meeting the industry requirements of traceable geological disaster survey data and verifiable results.

[0066] In practice, based on the fused survey data, field survey forms, photos, plan and profile diagrams, work summaries, and shapefile vector files can be uploaded with one click through a mobile data acquisition system to generate an uploaded data package. The uploaded data package is then received, organized, and standardized through a cloud-based data management system (also known as a web-based data management system) to obtain geological disaster data in a standard database format.

[0067] In one embodiment, the method further includes: based on the line and surface data of the landslide backwall and debris flow source area in the fused survey data, performing topological correction using a common edge automatic tracking and island area adjustment algorithm to generate constraints for three-dimensional modeling; based on the constraints for three-dimensional modeling and the elevation data of the digital elevation model (DEM), using a triangulation algorithm to quickly generate a three-dimensional surface model from the two-dimensional delineated boundary to obtain a three-dimensional geological hazard model; and associating the three-dimensional geological hazard model with the attribute information of stratigraphic lithology and hazard body structure to provide volume calculation, slope analysis, and stability simulation functions to obtain a three-dimensional geological body model that can be visualized and analyzed.

[0068] Here, the triangulation algorithm can be, for example, an improved Delaunay triangulation algorithm. Through algorithmic processing and data association, the planar information collected in the field is transformed into a three-dimensional, usable model, which can provide intuitive and accurate technical support for geological disaster assessment.

[0069] Specifically, line and surface data collected in the field, such as landslide backwalls and debris flow source areas (e.g., hand-drawn landslide boundary lines and source area boundaries), may contain topological errors due to manual drawing (e.g., overlapping boundary lines, missing areas, and unidentified small islands). These errors can be corrected using automatic common edge tracking and island area adjustment algorithms. For example, automatically identifying shared boundaries between adjacent line and surface data (e.g., shared boundaries between the landslide backwall line and adjacent strata) eliminates the problem of duplicate drawing of the same boundary or non-overlapping boundaries, ensuring logical consistency of the line and surface data. Identifying small island areas missed in the data (e.g., undrawn complete small rock blocks within the landslide body) corrects area calculation deviations (e.g., inaccurate source area area due to boundary errors), ensuring the geometric accuracy and logical correctness of the two-dimensional data. Finally, generating topologically error-free and accurate two-dimensional line and surface data serves as a constraint for subsequent three-dimensional modeling (i.e., modeling must strictly adhere to the spatial positions of these two-dimensional boundaries). Based on the corrected two-dimensional constraints and DEM elevation data (basic data recording terrain elevation), a triangulation algorithm can be used to transform planar boundaries into three-dimensional surfaces. For example, the two-dimensional line-plane boundary is divided into countless triangular units. Combining the elevation of each unit in the DEM data, the planar triangles are stretched into three-dimensional triangular patches. After countless patches are stitched together, a three-dimensional surface model is formed (such as the three-dimensional outline of a landslide or the three-dimensional morphology of a debris flow source area). Finally, a three-dimensional geological hazard model that can intuitively reflect the three-dimensional morphology of the hazard body (such as the height, slope, and depositional morphology of the landslide) is obtained. Then, by further associating attribute information and adding analysis functions, the assessment needs can be met. For example, attribute data such as lithology (e.g., sandstone / clay layers) and hazard structure (e.g., the depth of the landslide sliding surface) obtained from field surveys can be bound to corresponding areas of the 3D model (e.g., clicking on a part of the model allows direct viewing of the lithology and thickness of that area). Furthermore, tools such as volume calculation (e.g., quickly calculating the total volume of the landslide), slope analysis (e.g., identifying steep slope areas of the landslide), and stability simulation (e.g., simulating the stability of landslides under different precipitation conditions) can be added to the model, upgrading it from a visual display to an analytical tool, ultimately resulting in a viewable, searchable, and analyzable 3D geological model. This implementation method avoids the problem of disconnect between traditional manual modeling and actual conditions, providing a precise three-dimensional data foundation for subsequent analysis. Compared to the abstract interpretation of two-dimensional drawings, 3D models can intuitively display the three-dimensional morphology of the hazard (e.g., the steep back wall of a landslide, the flow valley of a debris flow), allowing even non-professionals to quickly understand the characteristics of the hazard. Simultaneously, clicking on the model allows viewing attribute information (e.g., the lithology of a certain area), eliminating the need to repeatedly consult paper survey forms and significantly reducing the information acquisition cost for hazard assessment. In addition, the model's integrated functions, such as volume calculation and stability simulation, can directly provide data support for prevention and control strategies.

[0070] In one embodiment, the method further includes: calculating the risk level based on the fused survey data and historical disaster data using a landslide probability prediction model and a debris flow risk prediction model; updating the risk level every preset time interval (e.g., 5 minutes) and generating a visualized risk heat map to obtain a real-time risk assessment result; dynamically optimizing the survey route based on the real-time risk assessment result to generate an optimized survey path that avoids high-risk areas; and triggering a mobile terminal audible and visual warning and pushing the optimal evacuation route when the real-time risk assessment result reaches an extremely dangerous risk level, while the management center pushes warning information and receives emergency response instructions.

[0071] The management center here may include, for example, a cloud management platform and a regional emergency command center.

[0072] This implementation method, combining fused and historical data, updates landslide and debris flow risk levels every 5 minutes. It also uses heat maps to visually display high-risk areas, allowing field personnel to clearly identify danger locations and their severity, avoiding misjudgments caused by relying on static data. Based on real-time risk results, the method automatically adjusts investigation routes to avoid suddenly appearing high-risk areas (such as landslide points with sudden cracks), eliminating the need for repeated manual route planning. This improves investigation efficiency and minimizes safety risks for field personnel. Once an extremely dangerous level is triggered, the mobile device immediately triggers an audible and visual alarm and pushes evacuation routes, simultaneously alerting the management center. This allows field personnel to evacuate immediately, and management can quickly activate emergency measures, reducing delays in responding to sudden disasters.

[0073] like Figure 2The diagram illustrates the entire process of geological hazard investigation, from indoor preparation to field implementation and data processing. In the indoor data preparation stage, the prepared data can be vectorized or rasterized to obtain standardized basic data. Indoor preparation data includes multi-source basic geographic and geological data, such as: topographic maps: DEM (Digital Elevation Model, used for topographic relief analysis), DLG (Digital Line Graph, providing vector boundaries for ground features), DRG (Digital Raster Graph, preserving original map information); geological maps: geological maps (recording geological elements such as strata and structures); remote sensing data: high-precision remote sensing imagery DOM (Digital Orthophoto Map, visually presenting the surface landscape); geological hazard data: existing geological hazard points (historical hazard point data after investigation and remote sensing interpretation); and planning data: planned field survey routes (pre-defined field survey paths). These data, through vectorization and rasterization, are standardized in format and coordinate system, ultimately generating a basic data source for a single map of the field survey, providing accurate support for subsequent mobile navigation and survey point positioning. Field surveys are the practical stage for data collection and spatiotemporal correlation of field survey data. Specific tasks include: Field point location and navigation: Based on a single field survey map and mobile GPS / BeiDou positioning, survey points are quickly reached via point navigation or coordinate navigation. After identifying landslide points, collapse points, etc., based on terrain and feature recognition, point classification and establishment are performed; Survey data collection: Tables are filled out and physical delineation is performed for point (e.g., monitoring points), line (e.g., landslide boundaries), and area (e.g., debris flow source areas), and phenomenon photographs are collected simultaneously; Plan and profile drawing: Plan and profile drawings of the disaster body are drawn based on DEM data and field measurements; Work summary: Key findings and unresolved issues of the day's survey are recorded. Simultaneously, sensor data (e.g., crack displacement, precipitation data) from low-power monitoring terminals needs to be acquired during the field survey to provide dynamic monitoring data for subsequent spatiotemporal correlation matching. Indoor data processing is the process of standardizing data processing and fusing multi-source data. Specific tasks include: Mapping survey points and routes: Vectorizing the survey point and route data collected in the field and importing it into the GIS platform, overlaying it with the basic data prepared indoors; Data entry and fusion: Spatiotemporally matching the survey table data and sensor monitoring data, using a hybrid long short-term memory network to complete missing data and filter outliers, generating fused survey data; Photo processing and map compilation: Classifying and labeling field photos, and combining the fused data to compile geological hazard distribution maps, profile maps, and other output maps, ultimately forming geological hazard data in a standard database format, providing support for in-depth applications such as 3D modeling and risk assessment.

[0074] The geological disaster data acquisition method of this disclosure can be implemented collaboratively through a cloud management platform and a mobile terminal. The cloud management platform is responsible for overall coordination and in-depth data processing, including: integrating multi-source basic data prepared indoors (such as DEM, DLG, DOM, geological maps), fused data collected in the field, and sensor data from low-power monitoring terminals to build a unified geological disaster database, realizing centralized storage, management, and sharing of data; deploying graph theory routing algorithms, hybrid long short-term memory networks, risk prediction models, etc., to complete in-depth analysis work such as data association, missing data completion, anomaly filtering, and risk assessment (such as landslide / debris flow risk level calculation and heat map generation), providing data support for decision-making; and being responsible for the construction and updating of three-dimensional geological body models, dynamically optimizing survey routes, and pushing early warning information to the management center when the risk level reaches extreme danger, triggering emergency response instructions, and realizing global control over the entire survey and prevention process. The mobile terminal is responsible for on-site execution and lightweight operations, including: completing tasks such as classification and point establishment, data entry and recording, phenomenon photography, entity delineation, and drawing plan and profile diagrams at survey points; collecting point, line, surface, and attribute data to form field survey records; providing navigation and positioning based on a single map of the field survey; receiving real-time risk assessment results pushed from the cloud upon arrival at the survey point and dynamically adjusting the survey route; receiving audible and visual warnings and optimal evacuation routes when extremely dangerous risks are triggered; possessing basic data verification and simple visualization functions (such as the distribution of survey points in a local area); and being able to store some basic data offline to ensure basic operations in field environments without network access, with data synchronized before being uploaded to the cloud. In short, the cloud management platform focuses on global data management, in-depth analysis, and decision support, while the mobile terminal focuses on on-site execution, data collection, and real-time interaction. Through data transmission and command interaction, the two form a closed-loop management system from indoor preparation, field survey, office analysis, to risk warning, efficiently supporting the investigation, monitoring, and prevention of geological disasters.

[0075] like Figure 3 As shown in the figure, this disclosure provides a geological disaster data acquisition method, applied to a cloud management platform, including: S301: Obtain indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data. S302: Send a map of the field survey to the mobile device; S303: Receive the field survey record uploaded by the mobile terminal, and obtain the sensor monitoring data collected by the low-power monitoring terminal. Perform spatiotemporal correlation matching on the field survey record and the sensor monitoring data to obtain the fused survey data. S304: The fused survey data is processed and standardized to obtain geological disaster data in a standard database format.

[0076] like Figure 4 As shown in the figure, this disclosure provides a geological disaster data acquisition method applied to a mobile terminal, including: S401: Receive a map from the field survey; S402: Navigate and locate based on the field survey map, and determine the location of the survey point after reaching the survey target location range; S403: At the survey point location, collect field survey data including point data, line data, area data and attribute data to form a field survey record; S404: Upload the field survey records to the cloud management platform.

[0077] like Figure 5 As shown, this embodiment of the disclosure provides a geological disaster data acquisition system 500, including a cloud management platform 501 and a mobile terminal 502; The cloud management platform 501 is used to acquire indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data, and send the field survey map to the mobile terminal; receive field survey records uploaded by the mobile terminal; acquire sensor monitoring data collected by a low-power monitoring terminal, perform spatiotemporal correlation matching on the field survey records and the sensor monitoring data to obtain fused survey data; and perform data processing and standardization conversion on the fused survey data to obtain geological disaster data in a standard database format. The mobile terminal 502 is used to receive the field survey map, navigate and locate the mobile terminal based on the field survey map, and determine the location of the survey point after the mobile terminal reaches the survey target location range; at the survey point location, the mobile terminal collects field survey data including point data, line data, area data and attribute data to form a field survey record and upload it to the cloud management platform.

[0078] This disclosure also provides a geological disaster data acquisition device, which can be deployed on a cloud management platform, including: The acquisition module is used to acquire indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data. The sending module is used to send a map of the field survey to the mobile device; The fusion module is used to receive the field survey records uploaded by the mobile terminal and obtain the sensor monitoring data collected by the low-power monitoring terminal, and perform spatiotemporal correlation matching on the field survey records and the sensor monitoring data to obtain the fused survey data. The data processing module is used to process and standardize the fused survey data to obtain geological disaster data in a standard database format.

[0079] This disclosure also provides a geological disaster data acquisition device, which can be deployed on a mobile device, including: The receiving module is used to receive a map from the field survey. The determination module is used to perform navigation and positioning based on a map of the field survey, and to determine the location of the survey point after reaching the survey target location range; The data acquisition module is used to collect field survey data, including point data, line data, area data and attribute data, at the survey point location, and form a field survey record; The sending module is used to upload the field survey records to the cloud management platform.

[0080] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0081] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0082] Based on the same technical concept, this disclosure also provides an electronic device 600, which can be a server, specifically such as a server for a sports management platform, or a mobile device, specifically such as the mobile terminal, see reference. Figure 6 The diagram shown is a schematic representation of the structure of an electronic device according to an exemplary embodiment of this disclosure, comprising: The processor 610, memory 620, and bus 630 are included. The memory 620 is used to store execution instructions and includes main memory 621 and external memory 622. The main memory 621, also known as internal memory, is used to temporarily store the operation data in the processor 610 and the data exchanged with external memory 622 such as hard disk. The processor 610 exchanges data with external memory 622 through main memory 621.

[0083] In this embodiment, the memory 620 is specifically used to store application code that executes the scheme of this disclosure, and its execution is controlled by the processor 610. That is, when the electronic device 600 is running, the processor 610 communicates with the memory 620 through the bus 630, or the processor 610 communicates with the memory 620 through other means, so that the processor 610 executes the application code stored in the memory 620, and then executes the steps of the geological disaster data acquisition method described in any of the foregoing embodiments.

[0084] The memory 620 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0085] Processor 610 may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0086] It is understood that the structures illustrated in the embodiments of this disclosure do not constitute a specific limitation on the electronic device 600. In other embodiments of this disclosure, the electronic device 600 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0087] This disclosure also provides a computer-readable storage medium including instructions stored thereon, wherein, when executed by a processor, the instructions perform the geological disaster data acquisition method described in any of the preceding embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0088] This disclosure also provides a computer program product, which stores a computer program. When the computer program is run by a processor, it executes the steps of the geological disaster data acquisition method provided in any of the above embodiments of this disclosure. For details, please refer to the above method embodiments, which will not be repeated here.

[0089] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium, which can be a volatile or non-volatile computer-readable storage medium. In another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0090] Furthermore, embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0091] The processing and logic flows described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flows can also be executed by dedicated logic circuits—such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs), and the device can also be implemented as dedicated logic circuits.

[0092] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.

[0093] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0094] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0095] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0096] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0097] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for collecting geological disaster data, characterized in that, include: Acquire indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data. Based on the field survey map, the mobile device is navigated and positioned, and the location of the survey point is determined after the mobile device reaches the survey target location range. At the survey point location, field survey data, including point data, line data, area data, and attribute data, are collected through the mobile terminal to form a field survey record; The sensor monitoring data collected by the low-power monitoring terminal is acquired, and the field survey records and the sensor monitoring data are spatiotemporally correlated and matched to obtain fused survey data. The fused survey data is then processed and standardized to obtain geological disaster data in a standard database format.

2. The method according to claim 1, characterized in that, The field survey records and sensor monitoring data are spatiotemporally correlated and matched to obtain fused survey data, including: The field survey data and the sensor monitoring data are spatiotemporally correlated and matched to generate a correlated dataset; A hybrid long short-term memory network model is used to complete the missing data and filter out abnormal noise in the associated dataset to obtain the fused survey data.

3. The method according to claim 1, characterized in that, The process involves acquiring indoor preparation data, configuring project data based on this data, and generating a field survey map based on the configured project data and indoor preparation data. Acquire basic geographic data, geological maps, remote sensing images, and geological hazard distribution maps as indoor preparation data, and perform vectorization or rasterization processing on the indoor preparation data to obtain standardized basic data; Based on the standardized basic data, the project's basic information is set, the work area is configured, and the data resources are configured to generate the configured project data. Based on the configured project data and the standardized basic data, a field survey map is generated.

4. The method according to claim 3, characterized in that, The indoor preparation data is vectorized or rasterized to obtain standardized basic data, including: Based on the indoor preparation data, a raster data compression algorithm is used to compress the raster image data and establish a spatial index to generate compressed raster data. The compressed raster data is processed by a decompression algorithm for fast loading and smooth display, resulting in standardized basic data that can be displayed on mobile devices.

5. The method according to claim 1, characterized in that, Based on the aforementioned field survey map, navigation and positioning are performed on the mobile device, and after the mobile device reaches the survey target location range, the location of the survey point is determined, including: The GPS or BeiDou satellite positioning signal of the mobile device is acquired, the coordinates of the positioning signal are calculated and the calculation accuracy is optimized to obtain the real-time location coordinates of the mobile device. Based on the field survey map and the real-time location coordinates, real-time dynamic route guidance is provided through point-based navigation or coordinate navigation, and the location of survey points is quickly determined by combining terrain and feature recognition.

6. The method according to claim 5, characterized in that, Based on the aforementioned field survey map and real-time location coordinates, real-time dynamic route guidance is provided through point-based navigation or coordinate navigation methods. Combined with terrain and feature recognition, the location of survey points is quickly determined, including: After the mobile terminal reaches the target location range based on the real-time dynamic route guidance, it determines the type of the investigation point based on the real-time location coordinates, and identifies the investigation point as a landslide point, collapse point, debris flow point, or special engineering geological point. Based on the survey point type, perform the corresponding classification and point creation operation to obtain the survey point locations under the survey point type.

7. The method according to claim 1, characterized in that, Field survey data, including point data, line data, area data, and attribute data, is collected through the mobile terminal to form a field survey record, including: The field survey data, including point data, line data, area data, and attribute data, is collected through a mobile data acquisition system. This data is used to enter information into field survey record forms, draw entity sketches, create plan and profile diagrams, and take photos. The system forms the field survey record.

8. The method according to claim 7, characterized in that, Entity delineation is performed using a mobile data acquisition system, including: Based on the location of the survey points and the field survey map, the boundaries, cracks and lithological observation points are marked by a combination of points, lines and surfaces. The back wall of the landslide, boundary line, sliding direction, deposit, hazard range and debris flow source area, flow area and deposition area are delineated, and vector graphics containing point data, line data and surface data are generated. For the vector graphics, the basic element information of points, lines, and surfaces is entered to obtain entity drawing data that associates spatial vector data and professional attribute data.

9. The method according to claim 1, characterized in that, Also includes: Based on the line and surface data of the landslide back wall and debris flow source area in the fused survey data, the common edge automatic tracking and island area adjustment algorithm are used for topological correction to generate constraints for three-dimensional modeling. Based on the constraints of the three-dimensional modeling and the elevation data of the digital elevation model (DEM), a triangulation algorithm is used to quickly generate a three-dimensional surface model from the two-dimensional boundary delineation, thus obtaining a three-dimensional model of geological hazards. By associating the geological hazard 3D model with the attribute information of strata lithology and hazard body structure, volume calculation, slope analysis and stability simulation functions are provided to obtain a 3D geological body model that can be visualized and analyzed.

10. The method according to claim 1, characterized in that, The method further includes: Based on the fused survey data and historical disaster data, the risk level is calculated through the landslide probability prediction model and the debris flow risk prediction model. The risk level is updated every preset time interval and a visual risk heat map is generated to obtain real-time risk assessment results. Based on the real-time risk assessment results, the investigation route is dynamically optimized to generate an optimized investigation path that avoids high-risk areas. When the real-time risk assessment result reaches the extremely dangerous risk level, a mobile audible and visual warning is triggered and the optimal evacuation route is pushed. At the same time, the management center pushes warning information and receives emergency response instructions.

11. A method for collecting geological disaster data, characterized in that, Applications in cloud management platforms include: Acquire indoor preparation data, configure project data based on the indoor preparation data, and generate a field survey map based on the configured project data and indoor preparation data. Send a map of the field survey to the mobile device; The system receives field survey records uploaded by the mobile terminal and obtains sensor monitoring data collected by the low-power monitoring terminal. It performs spatiotemporal correlation matching on the field survey records and the sensor monitoring data to obtain fused survey data. The fused survey data is then processed and standardized to obtain geological disaster data in a standard database format.

12. A method for collecting geological disaster data, characterized in that, Applied to mobile devices, including: Receive a map from a field survey; Navigation and positioning are performed based on the aforementioned field survey map, and the location of the survey point is determined after reaching the survey target location range; At the survey points, field survey data, including point data, line data, area data, and attribute data, are collected to form a field survey record; The field survey records were uploaded to the cloud management platform.

13. A geological disaster data acquisition system, characterized in that, This includes cloud management platforms and mobile devices; The cloud management platform is used to acquire indoor preparation data, configure project data based on the indoor preparation data, generate a field survey map based on the configured project data and indoor preparation data, and distribute the field survey map to the mobile terminal. Receive field survey records uploaded by the mobile terminal; The system acquires sensor monitoring data collected by a low-power monitoring terminal, performs spatiotemporal correlation matching between the field survey records and the sensor monitoring data to obtain fused survey data, and performs data processing and standardization conversion on the fused survey data to obtain geological disaster data in a standard database format. The mobile terminal is used to receive the field survey map, perform navigation and positioning based on the field survey map, and determine the location of the survey point after reaching the survey target location range; at the survey point location, it collects field survey data including point data, line data, area data and attribute data, forms a field survey record, and uploads it to the cloud management platform.

Images