Geotechnical engineering investigation collaborative operation deployment method and system

Abstract

The invention relates to the technical field of information and data processing, particularly provides a geotechnical engineering investigation collaborative operation allocation method and system, and solves the problem that the overall efficiency of investigation operation needs to be further improved. The method comprises the following steps: acquiring geological information in all directions by utilizing acquisition equipment; geological feature data are screened from the geological information; fusing the geological feature data of different data sources to obtain fused geological feature data; correcting the fused geological feature data, and correcting errors in the data; the corrected geological feature data are analyzed, geological features are identified and classified, and potential geological disaster risks are predicted; and the collaborative operation platform allocates investigation tasks according to geological features and geological risks, and deploys investigation personnel and equipment resources. The system comprises a data fusion module, a feature recognition module and a collaborative allocation module. According to the invention, efficient collection, accurate analysis and intelligent deployment of data can be realized.

Description

Technical Field

[0001] The present invention relates to the field of information and data processing technology, and in particular to a method and system for coordinating geotechnical engineering survey collaborative operations. Background Art

[0002] Geotechnical engineering investigation refers to a technical activity that provides a scientific basis for engineering design, construction and operation through detailed investigation and analysis of natural conditions such as stratum lithology, geological structure, topography and hydrogeology before engineering construction. Its main purpose is to understand and evaluate the geological environment of the engineering site to ensure the safety, stability and economy of the project. The existing technology for collaborative operation deployment of geotechnical engineering investigation, geographic information system is used for the management and analysis of spatial data to help surveyors better understand geological conditions. Remote sensing technology obtains high-resolution images through satellites or drones to assist geological surveys. BIM technology building information modeling technology is used for three-dimensional modeling and data integration to improve survey efficiency. However, remote sensing images may be affected by factors such as weather and light, resulting in unstable data quality; GIS data may have errors, affecting the accuracy of analysis results; BIM models may deviate from the actual situation in actual applications.

[0003] Prior art 1, Chinese patent, application number: 202310241239.7 discloses a geotechnical engineering survey internal collaborative work system and method. After the staff selects the work mode, the first data based on the file work mode and the database work mode are generated; the work mode is selected according to the first data to generate the second data, and the server establishes interaction with the external application to generate the third data, and the third data includes user account information and permission information; the external application establishes an archiving mechanism and a logging mechanism to generate the fourth data; the server outputs the fourth data. Although a new database-based work mode has been added, this mode can establish interaction with external applications, archive and record the status of engineering survey projects, promote collaborative work between internal data processing personnel, ensure timely update and display of data, realize explicit management and control of the entire process of the project, and improve production efficiency and quality of results. However, there is a lack of effective means of processing data sources, resulting in poor results of collaborative work.

[0004] Prior art 2, Chinese patent, application number 202310059165.5 discloses a digital engineering geological survey method for collaborative indoor and outdoor work, including: pre-processing the initial data to obtain survey data, determining the topographic geological conditions and engineering conditions; conducting indoor geological survey according to the topographic geological conditions and engineering conditions to obtain initial geological survey points and initial geological description data; conducting outdoor geological survey, adjusting the initial geological survey points and initial geological description data, determining geological survey points and geological description data; determining geological survey data according to the geological survey points and geological description data; when the geological survey data is qualified, importing the geological survey data into the survey database, so that the geological personnel can produce results according to the survey database. Although it improves the efficiency of geological survey, reduces the intensity of field work, and realizes the digitization of geological survey data collection, processing and results production. However, it only involves technical means of geological survey, and does not involve collaborative operation deployment, resulting in limited application scope.

[0005] Prior art three, Chinese patent, application number 202410462718.6 discloses a surveying and mapping collaborative operation method and system, including: obtaining environmental basic data of the area to be surveyed through a drone, inputting the environmental basic data into a pre-established surveying and mapping path planning model, and obtaining the surveying and mapping path planning results; performing task allocation according to the surveying and mapping task data and surveying and mapping configuration data of the area to be surveyed, and obtaining the surveying and mapping subtask-surveying and mapping personnel-operation time allocation results; according to the surveying and mapping path planning results and the surveying and mapping subtask-surveying and mapping personnel-operation time allocation results, through a multi-agent surveying and mapping operation collaborative model, obtaining the human-machine collaborative scheduling of the area to be surveyed. Although it not only provides guarantees for the correct execution of surveying and mapping tasks and information in the surveying and mapping process, but also coordinates each member and drone to complete common tasks, improves team data reuse and collaboration efficiency, thereby effectively avoiding the waste of manpower, material resources and financial resources. However, the lack of verification of the basic environmental data has increased the data load pressure of the surveying and mapping operation collaborative model to a certain extent, bringing certain difficulties to collaborative operations.

[0006] At present, the existing technologies 1, 2 and 3 lack technical means for correcting geological data, resulting in poor reliability of geological data; at the same time, they lack the content of allocating survey personnel and equipment resources, resulting in the problem that the overall efficiency of survey operations needs to be further improved. Therefore, the present invention provides a method and system for allocating geotechnical engineering survey collaborative operations. Summary of the invention

[0007] In order to achieve the above object, the present invention adopts the following technical scheme:

[0008] In one aspect of the present invention, a method for coordinating geotechnical engineering survey collaborative operations is provided, comprising the following steps:

[0009] Collect geological information in all directions using acquisition equipment; filter geological characteristic data from geological information; fuse geological characteristic data from different data sources to obtain fused geological characteristic data;

[0010] Correct the fused geological feature data to correct the errors in the data; Analyze the corrected geological feature data to identify and classify the rock and soil layers, geological structures and groundwater, and predict the potential geological disaster risks;

[0011] The collaborative operation platform allocates survey tasks and deploys survey personnel and equipment resources based on geological characteristics and geological risks.

[0012] In an optional implementation, the process of obtaining the fused geological feature data includes the following steps:

[0013] Construct a three-dimensional geological model M, including key geological elements such as stratigraphic interfaces, faults and lithology distribution; perform data cleaning and data standardization preprocessing on the geological data set and geological feature data set; the geological data set is a collection of geological information, and the geological feature data set is a collection of geological feature data;

[0014] Extract key geological features using geological models and geological feature data; map features from different data sources to geological models through geological feature alignment; use a multimodal fusion network based on geological models, combined with attention mechanisms and graph neural networks to fuse geological information, and automatically identify and remove duplicate geological data through comparative learning;

[0015] Adaptive error correction is performed using geological models and generative adversarial networks to identify and process outliers in the fused data; the corrected fused data is output as geological feature data in a unified format.

[0016] In an optional implementation, the process of predicting potential geological disaster risks includes the following steps:

[0017] Using statistics, identify and correct the systematic and random errors in the fused geological feature data; extract key features from the geological data, such as the distribution and occurrence of rock and soil bodies, the development characteristics of geological structures, and groundwater burial conditions;

[0018] The support vector machine classification algorithm is used to classify the extracted features and identify different types of rock and soil layers, geological structures and groundwater;

[0019] Using geological characteristic data and historical geological disaster data, a geological risk assessment model is constructed. The identified and classified geological characteristics are input into the risk assessment model to predict potential geological disaster risks and output risk levels and risk areas.

[0020] In an optional implementation, the process of identifying and correcting the systematic errors and random errors in the fused geological feature data comprises the following steps:

[0021] Use time series analysis to identify long-term trends in the fused geological feature data and determine whether there are systematic deviations; compare the fused geological feature data with the preset benchmark data and identify systematic errors through difference analysis;

[0022] According to the benchmark comparison results, the overall deviation correction is performed; the variance of the fused geological feature data is calculated, the random fluctuations in the fused geological feature data are identified, and whether there are significant random errors; the high-frequency noise in the fused geological feature data is identified by spectrum analysis, and the source and characteristics of the random errors are determined;

[0023] Low-pass filtering is used to remove high-frequency noise in the fused geological feature data, smooth random errors, and smooth the fused geological feature data.

[0024] In an optional embodiment, the process of identifying different types of rock layers, geological structures and groundwater includes the following steps:

[0025] Prepare training data sets, including input feature vectors and corresponding labels; feature vectors correspond to geological feature data, and labels correspond to classification results, including rock formation types and geological structure types;

[0026] The support vector machine is to find an optimal hyperplane that maximizes the classification interval, through the optimization problem description;

[0027] Solve the optimization problem, obtain the normal vector and bias term of the optimal hyperplane, and determine the optimal hyperplane.

[0028] In an optional implementation, the process of constructing a geological risk assessment model comprises the following steps:

[0029] Integrate geological characteristic data and historical geological disaster data to construct a comprehensive data set and a multi-level risk assessment system; use historical geological disaster data to train and verify the geological risk assessment model and adjust the parameters of the geological risk assessment model;

[0030] According to the output results of the geological risk assessment model, different risk levels are divided and risk areas are determined;

[0031] The geological risk assessment model is optimized according to the preset cycle, new geological data and disaster cases are introduced, and the geological risk assessment model parameters are updated; combined with real-time geological monitoring data, the geological risk assessment model is dynamically adjusted and feedback is provided.

[0032] In an optional implementation, the process of training and validating the geological risk assessment model using historical geological disaster data includes the following steps:

[0033] Extract key features from geological feature data, including geological structure, rock and soil type and groundwater, and construct feature vectors; build a multi-level risk assessment system, including geological features, disaster-related features and risk assessment;

[0034] The historical geological disaster data are divided into a training set and a validation set, and the geological risk assessment model is trained using the training set, and the parameters of the geological risk assessment model are optimized through iteration;

[0035] K-fold cross validation was used to evaluate the performance and stability of the geological risk assessment model. The prediction accuracy, recall rate and F1 score indicators of the geological risk assessment model were evaluated through the validation set.

[0036] In an optional implementation, the process of deploying survey personnel and equipment resources includes the following steps:

[0037] Based on the risk assessment results, the collaborative operation platform prioritizes the survey tasks in different areas, with high-risk areas having the highest priority; it refines high-priority tasks to determine specific survey targets and required data types, including rock and soil sampling and groundwater level monitoring;

[0038] According to the task requirements, the collaborative operation platform deploys survey personnel with corresponding professional skills; according to the task type, it deploys survey equipment;

[0039] The collaborative work platform distributes the detailed tasks to the corresponding survey teams, provides detailed geological information and risk assessment reports; monitors the survey progress and data collection in real time, receives feedback from the survey team, and adjusts tasks and resource allocation in a timely manner.

[0040] In an optional implementation, the process of deploying survey personnel and survey equipment with corresponding professional skills includes:

[0041] Obtain the specific content of the task requirements, and select surveyors matching the specific content from the surveyor database based on the task requirements collaborative operation platform. The matching content is the technology that the surveyor is good at;

[0042] Obtain the task type, and based on the task type, the collaborative operation platform selects survey equipment that matches the specific content from the survey equipment data. The matching content is the work content completed by the survey equipment.

[0043] The collaborative work platform sends task requirements and task types through the Internet of Things to the terminal devices of the corresponding surveyors, and lists the survey equipment at the same time.

[0044] Another aspect of the present invention provides a geotechnical engineering investigation collaborative work deployment system for implementing the geotechnical engineering investigation collaborative work deployment method, comprising:

[0045] The data fusion module is responsible for using the acquisition equipment to collect geological information in all directions; filtering geological characteristic data from the geological information; fusing the geological characteristic data from different data sources to obtain the fused geological characteristic data;

[0046] The feature recognition module is responsible for correcting the fused geological feature data and rectifying the errors in the data; analyzing the corrected geological feature data, identifying and classifying geological features including rock and soil layers, geological structures and groundwater, and predicting potential geological disaster risks;

[0047] The collaborative deployment module is responsible for allocating survey tasks and deploying survey personnel and equipment resources based on geological characteristics and geological risks on the collaborative operation platform.

[0048] The present invention collects and fuses geological information in an all-round way by using collection equipment to collect geological information in an all-round way, thereby ensuring the comprehensiveness and accuracy of the information; screens geological feature data from geological information, removes irrelevant information, and improves the accuracy of the data; fuses geological feature data from different data sources to make up for the shortcomings of a single data source, improves the integrity and reliability of the data, and provides more comprehensive basic data for subsequent analysis. Data correction and analysis: correct the fused geological feature data, correct errors and outliers in the data, and improve the accuracy and reliability of the data; analyze the corrected geological feature data, quickly identify and classify geological features such as rock layers, faults, and groundwater levels, and predict potential geological disaster risks, providing a scientific basis for subsequent risk assessment and task allocation. Collaborative operation platform and task allocation: the collaborative operation platform allocates survey tasks according to geological characteristics and geological risks to ensure the rationality and pertinence of task allocation; intelligently allocates survey personnel and equipment resources according to task requirements to ensure the efficient execution of survey tasks, optimize resource allocation, and improve the overall efficiency and effectiveness of survey operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 A flow chart of the geotechnical engineering survey collaborative operation deployment method provided in Example 1 of the present invention;

[0051] Figure 2 A process diagram of obtaining fused geological feature data provided in Example 2 of the present invention;

[0052] Figure 3 A process diagram for predicting potential geological disaster risks provided in Example 3 of the present invention;

[0053] Figure 4 A process diagram for identifying and correcting systematic errors and random errors in fused geological feature data provided in Example 4 of the present invention;

[0054] Figure 5 A process diagram for identifying different types of rock and soil layers, geological structures and groundwater provided in Example 5 of the present invention;

[0055] Figure 6 A process diagram of constructing a geological risk assessment model provided in Example 6 of the present invention;

[0056] Figure 7 A process diagram of training and validating a geological risk assessment model using historical geological disaster data provided in Example 7 of the present invention;

[0057] Figure 8 A process diagram for allocating survey personnel and equipment resources provided in Example 8 of the present invention;

[0058] Fig. 9 A process diagram of deploying survey personnel and survey equipment with corresponding professional skills provided in Example 9 of the present invention;

[0059] Fig.10 A block diagram of a geotechnical engineering survey collaborative operation coordination system provided in Embodiment 10 of the present invention;

[0060] Fig.11 is a block diagram of an electronic device provided in Embodiment 11 of the present invention;

[0061] Fig.12 This is a block diagram of the computer-readable storage medium provided in Example 12 of the present invention. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0063] In the following, the terms "first", "second", etc. are used only for convenience of description and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0064] In the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, "connection" can be a fixed mechanical connection, or a detachable mechanical connection, or integrated; or, "connection" can be a direct connection, or an indirect connection through an intermediate medium. In addition, unless otherwise clearly specified and limited, the term "coupling" should be understood in a broad sense, for example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components, and can also be understood as electrical connection between different components in a circuit structure through physical lines such as copper foil or wires on a printed circuit board (PCB) that can transmit electrical signals to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in an air-spaced / non-contact manner, for example, two components are electrically connected by capacitive coupling to transmit electrical signals.

[0065] In the embodiments of the present invention, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to the change of the orientation of the components in the drawings.

[0066] Embodiment 1:

[0067] like Figure 1 As shown, an embodiment of the present invention provides a method for coordinating geotechnical engineering survey collaborative operations, comprising the following steps:

[0068] Step S100: using a collection device to collect geological information in all directions; screening geological characteristic data from the geological information; fusing geological characteristic data from different data sources to obtain fused geological characteristic data; the collection device includes a remote sensing satellite or an existing geological database storage device;

[0069] Step S200: Correct the fused geological feature data to correct the errors in the data; analyze the corrected geological feature data to identify and classify geological features including rock and soil layers, geological structures and groundwater, and predict potential geological disaster risks;

[0070] Step S300: The collaborative operation platform allocates survey tasks and deploys survey personnel and equipment resources according to geological characteristics and geological risks.

[0071] In the above embodiment, step S100 is all-round acquisition and data fusion, which ensures the comprehensiveness and accuracy of information by using acquisition equipment to collect geological information in an all-round way; geological feature data is screened from geological information, irrelevant information is removed, and the accuracy of data is improved; geological feature data from different data sources are integrated to make up for the shortcomings of a single data source, improve the integrity and reliability of data, and provide more comprehensive basic data for subsequent analysis. Step S200 is data correction and analysis, which corrects the fused geological feature data, corrects errors in the data, and improves the accuracy and reliability of data; analyzes the corrected geological feature data, quickly identifies and classifies geological features such as rock layers, faults, and groundwater levels, and predicts potential geological disaster risks, providing a scientific basis for subsequent risk assessment and task allocation. Step S300 is collaborative operation platform and task allocation, which allocates survey tasks according to geological features and geological risks to ensure the rationality and pertinence of task allocation; intelligently allocates survey personnel and equipment resources according to task requirements to ensure the efficient execution of survey tasks, optimize resource allocation, and improve the overall efficiency and effectiveness of survey operations.

[0072] In summary, the geotechnical engineering survey collaborative operation deployment method of this embodiment can achieve efficient data collection, accurate analysis and intelligent deployment, and provide strong technical support for geotechnical engineering survey and risk management.

[0073] Embodiment 2:

[0074] like Figure 2 As shown, based on Example 1, the process of obtaining the fused geological feature data in step S100 provided in the embodiment of the present invention includes the following steps:

[0075] Step S101: construct a three-dimensional geological model M, including key geological elements such as stratigraphic interfaces, faults and lithology distribution; perform data cleaning and data standardization preprocessing on the geological data set and the geological characteristic data set; the geological data set is a collection of geological information, and the geological characteristic data set is a collection of geological characteristic data;

[0076] Geological data set D = {d1, d2, …, d n};

[0077] Geological feature data set F = {f1,f2,…,f m};

[0078] Data cleaning: removing noise and outliers.

[0079] D clean =NoiseRemoval(D,geological background)

[0080] Data standardization: Use standardized methods related to geological characteristics;

[0081] D norm =Standardize(D clean , geological features)

[0082] Step S102: extract key geological features using geological models and geological feature data; map features of different data sources to the geological model through geological feature alignment; use a multimodal fusion network based on the geological model, combined with an attention mechanism and a graph neural network to fuse geological information, and automatically identify and remove duplicate geological data through comparative learning;

[0083] F extracted =ExtractFeatures(D norm ,M)

[0084] F aligned =AlignFeatures(F extracted ,M)

[0085] F fused =MultiModalFusion(F aligned ,M,Attention,GNN)

[0086] F deduplicated =ContrastiveLearning(F fused , geological features)

[0087] Step S103: using the geological model and the generative adversarial network to perform adaptive error correction, identify and process outliers in the fused data; output the corrected fused data as geological feature data in a unified format;

[0088] F corrected =GANCorrection(F deduplicated ,M)

[0089] F cleaned =AnomalyDetection(F corrected , geological features)

[0090] F′=Output(F cleaned ,M)

[0091] Where D clean represents the cleaned geological data set, NoiseRemoval represents the noise removal function, and D norm represents the standardized geological data set, Standardize represents the standardization function, ExtractFeatures represents the feature extraction function, and F extracted represents the extracted geological feature dataset, Faligned represents the aligned geological feature dataset, AlignFeatures represents the feature alignment function; F fused represents the fused geological feature dataset, MultiModalFusion represents the multimodal fusion function, Attention represents the attention mechanism, GNN represents the graph neural network, and F deduplicated represents the geological feature dataset after deduplication, ContrastiveLearning represents the contrastive learning function, and F corrected represents the corrected geological feature dataset, GANCorrection represents the generative adversarial network correction function, and F cleaned represents the cleaned geological feature dataset, AnomalyDetection represents the anomaly detection function, F′ represents the final output geological feature dataset, and Output represents the output function.

[0092] In the above embodiment, step S101 cleans and standardizes the data, removes noise and outliers in the geological data set, improves the purity and reliability of the data; reduces random errors and systematic errors in the data, making the processed data more accurate and stable; converts geological data of different scales and units into a unified scale to facilitate feature extraction and fusion; eliminates dimensional differences between data, makes different features comparable, and improves the effect of feature extraction and fusion. Step S102: feature extraction and fusion, extracting key geological features from standardized geological data to provide a basis for feature alignment and fusion; identifying and extracting features that are important for geological analysis, reducing data redundancy and improving data validity; mapping features from different data sources to a unified geological model to ensure spatial alignment of features; eliminating spatial differences between different data sources so that features are aligned in the same coordinate system to facilitate subsequent fusion processing; combining attention mechanisms and graph neural networks to fuse geological information of different modalities and enhance key features; improving the expressive power of geological features and enhancing the model's understanding and prediction capabilities for complex geological phenomena; automatically identifying and removing duplicate geological data through comparative learning to reduce data redundancy; improving the purity of the data set, reducing the impact of duplicate data on subsequent analysis, and enhancing the generalization ability of the model. Step S103 error correction and anomaly detection, using generative adversarial networks to perform adaptive error correction to improve data accuracy; reduce systematic errors in data, improve data accuracy and reliability, and enhance the predictive ability of the model; identify and process outliers in fused data to ensure data integrity and consistency; reduce the impact of outliers on analysis results, improve data quality and reliability, and enhance the robustness of the model; output the corrected fused data as geological feature data in a unified format for easy analysis and application; provide high-quality geological feature data to provide reliable data support for geological analysis, prediction, and decision-making.

[0093] In summary, this embodiment improves the accuracy, reliability and effectiveness of geological feature data, ensures that the geological feature data finally outputted can truly reflect geological phenomena, and provides strong support for geological analysis and decision-making. Through a series of steps such as data cleaning, standardization, feature extraction, alignment, fusion, deduplication, correction and anomaly detection, high-quality geological feature data is finally obtained.

[0094] Embodiment 3:

[0095] like Figure 3 As shown, based on Example 1, the process of predicting potential geological disaster risks in step S200 provided in the embodiment of the present invention includes the following steps:

[0096] Step S201: using statistics to identify and correct the systematic errors and random errors in the fused geological feature data; extracting key features from the geological data, including the distribution and occurrence of rock and soil bodies, the development characteristics of geological structures, and groundwater burial conditions;

[0097] Step S202: using a support vector machine classification algorithm to classify the extracted features and identify different types of rock and soil layers, geological structures and groundwater;

[0098] Step S203: Use geological feature data and historical geological disaster data to build a geological risk assessment model, input the identified and classified geological features into the risk assessment model, predict potential geological disaster risks, and output risk levels and risk areas.

[0099] In the above embodiment, step S201 data processing and feature extraction, through statistical methods to identify and correct the systematic errors and random errors in the geological feature data, to ensure the accuracy and reliability of the data; to provide a high-quality data basis for analysis and model building; to extract key features from geological data, such as the thickness of the rock layer, the strike and dip of the fault, the depth of the groundwater level, etc., the key features are an important basis for assessing geological risks, and extracting key features helps to more accurately describe the geological conditions and provide necessary information for risk assessment. Step S202 feature classification, using the support vector machine classification algorithm to classify the extracted features, identify different types of rock and soil layers, geological structures and groundwater, find the optimal classification boundary in high-dimensional space, can effectively handle nonlinear problems, and improve the accuracy and robustness of classification; through the classification algorithm, complex geological features are classified, which helps to more clearly understand the geological structure and conditions, and provide structured data support for risk assessment. Step S203: Risk assessment model construction and prediction. Using geological feature data and historical geological disaster data, a geological risk assessment model is constructed. The model can comprehensively consider multiple geological factors, simulate the occurrence mechanism of geological disasters, and provide a scientific basis for risk prediction. The identified and classified geological features are input into the risk assessment model to predict potential geological disaster risks. The model outputs risk levels and risk areas to provide decision support for the prevention and management of geological disasters. Through model prediction, risk areas are divided into different risk levels, which is helpful for resource allocation and the formulation of emergency plans, and improves the efficiency and effectiveness of disaster response.

[0100] To sum up, the present embodiments together constitute a complete geological risk prediction system, which can comprehensively and accurately assess potential geological risks through data processing, feature extraction, feature classification and construction and prediction of risk assessment models, and provide a scientific basis for the prevention and management of geological disasters.

[0101] Embodiment 4:

[0102] like Figure 4 As shown, based on Example 3, the process of identifying and correcting the systematic errors and random errors in the fused geological feature data in step S201 provided in the embodiment of the present invention includes the following steps:

[0103] Step S2011: using time series analysis to identify the long-term trend in the fused geological feature data and determine whether there is a systematic deviation; comparing the fused geological feature data with the preset benchmark data and identifying the systematic error through difference analysis;

[0104] Step S2012: perform overall deviation correction according to the benchmark comparison result; calculate the variance of the fused geological feature data, identify random fluctuations in the fused geological feature data, and determine whether there are significant random errors; use spectrum analysis to identify high-frequency noise in the fused geological feature data, and determine the source and characteristics of random errors;

[0105] The expression of spectrum analysis is:

[0106]

[0107] Where: represents the spectrum analysis function, represents the spectrum value at frequency f, N represents the total number of data points, represents the total number of samples of the fused geological feature data, X k represents the X-axis component of the fused geological feature data at time point k, Y k represents the Y-axis component of the fused geological feature data at time point k, Z n represents the Z-axis component of the fused geological feature data at time point n, t represents the time variable, and represents the timestamp of the data point. represents the second-order time derivative, represents the second-order derivative with respect to time t, e -i2πkn / N Represents a complex exponential function, which is used for frequency component calculation in Fourier transform. k represents the time point index, ranging from 0 to N-1, and n represents the time point index, ranging from 0 to N-1.

[0108] Step S2013: Use low-pass filtering to remove high-frequency noise in the fused geological feature data, smooth random errors, and smooth the fused geological feature data.

[0109] In the above embodiment, step S2011 identifies the systematic error, identifies the long-term trend in the data by analyzing the time series data, and helps to determine whether there is a systematic deviation; helps to understand the overall trend of the data and ensures that the trend error of the data is identified; compares the fused geological feature data with the preset benchmark data, and identifies the systematic error through difference analysis; can clarify the deviation between the data and the benchmark, and provide a basis for correction. Step S2012 corrects the overall deviation and identifies the random error. According to the benchmark comparison result, the overall deviation correction is performed to ensure the overall accuracy of the data, and the systematic deviation in the data can be eliminated to make the data closer to the actual situation; calculates the variance of the fused geological feature data, identifies the random fluctuations in the data, and determines whether there are significant random errors; through variance analysis, the volatility of the data can be quantified to provide a basis for subsequent random error processing; uses spectrum analysis to identify the high-frequency noise in the fused geological feature data and determine the source and characteristics of the random error; spectrum analysis can help identify the noise component in the data and provide guidance for filtering processing. Step S2013 smoothes random errors, uses low-pass filtering to remove high-frequency noise in the fused geological feature data, smoothes random errors, and smoothes the data; low-pass filtering can effectively remove high-frequency noise in the data, make the data smoother, and improve the reliability and availability of the data.

[0110] In summary, this embodiment can systematically identify and correct systematic errors and random errors in geological feature data, ensure the accuracy and reliability of the data, and provide a solid foundation for geological analysis and decision-making.

[0111] Embodiment 5:

[0112] like Figure 5 As shown, based on Example 3, the process of identifying different types of rock and soil layers, geological structures and groundwater in step S202 provided in this embodiment of the present invention includes the following steps:

[0113] Step S2021: preparing a training data set, including inputting feature vectors (geological feature data) and corresponding labels (i.e., classification results, such as rock and soil layer types, geological structure types, etc.);

[0114] Assume there are m samples, and the feature vector of each sample is x i , labelled y i , where y i ∈{-1,+1} represents different categories;

[0115] The expression of radial basis function (RBF) is:

[0116] K(x i ,x j )=exp(-γ‖x i -xj ‖ 2 )

[0117] Among them, γ is the parameter of the RBF kernel.

[0118] Step S2022: The support vector machine is to find an optimal hyperplane that maximizes the classification interval, which can be described by the following optimization problem:

[0119]

[0120] The constraints are:

[0121] y i (w·φ(x i )+b)≥1-ξ i ,ξ i ≥0,i=1,2,…,n

[0122] Where: w is the normal vector of the hyperplane, b is the bias term, ξ i is a slack variable used to deal with inseparable situations, C is a penalty parameter used to control the degree of penalty for misclassification, and y i is the label of the i-th sample, which takes the value of +1 or -1, φ(x i ) is the feature vector of the i-th sample, φ(x) is the function that maps the input vector x to a high-dimensional space;

[0123] Step S2023: solving the optimization problem, obtaining the normal vector and bias term of the optimal hyperplane, and determining the optimal hyperplane;

[0124] For a new input feature vector x, classification prediction is performed using the following formula:

[0125] Prediction result = sign(w·φ(x)+b)

[0126] Use kernel functions to avoid directly calculating inner products in high-dimensional space. The kernel function K(x i ,x j ) is expressed as:

[0127] K(x i ,x j )=φ(x i )·φ(x j )

[0128] Among them, φ(x i ) is a function that maps the input vector x to a high-dimensional space.

[0129] In the above embodiment, step S2021 prepares a training data set, collects and organizes geological feature data, constructs input feature vectors and corresponding labels, and provides training data for the machine learning model; preprocesses and extracts features of geological data to ensure the quality and applicability of the data, laying a foundation for model training; clarifies the classification results of each sample, and provides necessary label information for supervised learning, so that the model can learn the relationship between different geological features and classification results. Step S2022 supports the vector machine optimization problem, finds an optimal hyperplane through the optimization problem, maximizes the classification interval, and thus improves the generalization ability and classification accuracy of the model; introduces slack variables, allowing sample points to be on the wrong side of the hyperplane in some cases, thereby handling linear inseparable situations and improving the robustness of the model; controls the degree of penalty for misclassification by the model through penalty parameters, balances the complexity and classification accuracy of the model, and avoids overfitting or underfitting. Step S2023 solves the optimization problem and performs classification prediction. By solving the optimization problem, the normal vector and bias term of the optimal hyperplane are obtained, and the optimal hyperplane is determined to provide a basis for classification prediction. For new input feature vectors, the prediction results are determined by calculation to achieve classification of new samples. The kernel function is used to avoid directly calculating the inner product in high-dimensional space, simplify the calculation process, and allow the model to perform effective classification in nonlinear conditions.

[0130] In summary, this embodiment aims to improve the classification accuracy, generalization ability and robustness of the model. From data preparation to model training, and then to classification prediction, each link is closely connected to jointly build an efficient geological feature classification system.

[0131] Embodiment 6:

[0132] like Figure 6 As shown, based on Example 3, the process of constructing a geological risk assessment model in step S203 provided in the embodiment of the present invention includes the following steps:

[0133] Step S2031: Integrate geological feature data and historical geological disaster data to construct a comprehensive data set and a multi-level risk assessment system; use historical geological disaster data to train and verify the geological risk assessment model and adjust the parameters of the geological risk assessment model;

[0134] Step S2032: according to the output results of the geological risk assessment model, different risk levels are divided and risk areas are determined;

[0135] Step S2033: Optimize the geological risk assessment model according to the preset cycle, introduce new geological data and disaster cases, and update the geological risk assessment model parameters; combine real-time geological monitoring data to dynamically adjust and feedback the geological risk assessment model.

[0136] In the above embodiment, step S2031 data fusion and model training, by fusing geological feature data and historical geological disaster data, constructing a comprehensive data set, can fully reflect the complexity and diversity of the geological environment, thereby improving the data basis of the model; constructing a multi-level risk assessment system, it can assess risks from different dimensions (such as geological structure, rock and soil type, climate conditions, etc.), making the assessment results more comprehensive and detailed; using historical geological disaster data to train and verify the model, it can effectively adjust the model parameters and improve the prediction accuracy and reliability of the model. Step S2032 risk level division and regional determination, according to the output results of the model, divide the risks into different levels (such as high risk, medium risk, low risk), which helps decision makers quickly identify and prioritize high-risk areas; determining risk areas can provide a scientific basis for subsequent disaster prevention, emergency response and resource allocation, and improve the pertinence and efficiency of disaster management. Step S2033: Model optimization and dynamic adjustment. The model is optimized according to a preset cycle, and new geological data and disaster cases are introduced. The model can be continuously updated and improved to keep it up to date and adapt to the ever-changing geological environment. Combined with real-time geological monitoring data, the model is dynamically adjusted and feedback is provided to reflect changes in the geological environment in real time, improve the real-time and responsiveness of the model, and ensure the timeliness and accuracy of risk assessment.

[0137] In summary, the geological risk assessment model of this embodiment can not only provide accurate prediction results, but also continuously optimize itself over time to ensure its continued effectiveness in practical applications.

[0138] Embodiment 7:

[0139] like Figure 7 As shown, based on Example 6, the process of training and verifying the geological risk assessment model using historical geological disaster data in step S2031 provided in the embodiment of the present invention includes the following steps:

[0140] Step S20311: extract key features from geological feature data, such as geological structure, rock and soil type, and groundwater level, and construct feature vectors; construct a multi-level risk assessment system, including a base layer (geological features), an intermediate layer (disaster-related features), and a top layer (risk assessment);

[0141] Step S20312: dividing the historical geological disaster data into a training set and a validation set, using the training set to train the geological risk assessment model, and optimizing the parameters of the geological risk assessment model through iteration;

[0142] Step S20313: Use K-fold cross validation to evaluate the performance and stability of the geological risk assessment model; evaluate indicators such as prediction accuracy, recall rate and F1 score of the geological risk assessment model through the validation set.

[0143] In the above embodiment, step S20311 feature extraction and risk assessment system construction, by extracting key features (such as geological structure, rock and soil type, groundwater level, etc.) from geological feature data, constructing feature vectors, helps the model capture the key factors affecting geological disasters and improve the model's interpretability and prediction capabilities; constructing a multi-level risk assessment system including a base layer, an intermediate layer, and a top layer, can systematically integrate information at different levels, so that the model can comprehensively assess geological risks from macro to micro, and enhance the comprehensiveness and accuracy of the model. Step S20312 data division and model training, divide the historical geological disaster data into a training set and a validation set to ensure that the model can learn effective patterns during the training process, and at the same time evaluate the generalization ability of the model through the validation set to avoid overfitting; use the training set to train the geological risk assessment model, and iteratively optimize the model parameters so that the model can better fit the data and improve the prediction accuracy and stability of the model. Step S20313 model performance evaluation uses the K-fold cross-validation method to comprehensively evaluate the performance and stability of the model, ensure that the model performs consistently on different data sets, and improve the robustness of the model; by evaluating the model's prediction accuracy, recall rate, F1 score and other indicators on the validation set, the performance of the model can be quantified, helping to identify the advantages and disadvantages of the model, and providing a basis for further optimization of the model.

[0144] In summary, the geological risk assessment model of this embodiment can not only effectively capture the key characteristics of geological hazards, but also show good stability and predictive ability on different data sets, thereby providing reliable technical support for geological risk assessment in practical applications.

[0145] Embodiment 8:

[0146] like Figure 8 As shown, based on Example 1, the process of allocating survey personnel and equipment resources in step S300 provided in this embodiment of the present invention includes the following steps:

[0147] Step S301: Based on the risk assessment results, the collaborative operation platform prioritizes the survey tasks in different areas, with high-risk areas having the highest priority; the high-priority tasks are refined to determine specific survey targets and required data types, such as rock and soil sampling and groundwater level monitoring;

[0148] Step S302: According to the task requirements, the collaborative operation platform deploys survey personnel with corresponding professional skills; according to the task type, deploys survey equipment;

[0149] Step S303: The collaborative operation platform distributes the detailed tasks to the corresponding survey teams, provides detailed geological information and risk assessment reports; monitors the survey progress and data collection in real time, receives feedback from the survey team, and adjusts tasks and resource allocation in a timely manner.

[0150] In the above embodiment, step S301 is task priority sorting and refinement. Through priority sorting, it is ensured that high-risk areas receive timely attention and processing, and resources are avoided from being wasted in low-risk areas; specific survey objectives and required data types are clarified to ensure the pertinence and accuracy of survey tasks and improve the quality and efficiency of data collection. Step S02 is personnel and equipment deployment. Survey personnel with corresponding professional skills are deployed according to task requirements to ensure the matching degree between personnel and tasks and improve the professionalism and accuracy of survey work; appropriate survey equipment is deployed according to task types to ensure that equipment matches task requirements and improve survey efficiency and data collection accuracy. Step S303 is task distribution and real-time monitoring. Through detailed geological information and risk assessment reports, it is ensured that the survey team has clear task objectives and reduces misunderstandings and deviations; through real-time monitoring of survey progress and data collection, problems are discovered and solved in a timely manner to ensure the smooth progress of survey work; according to the feedback of the survey team, tasks and resource allocation are adjusted in a timely manner to ensure the efficiency and flexibility of survey work.

[0151] In summary, the collaborative work platform of this embodiment can ensure the efficient execution of survey tasks, optimal allocation of resources, and accurate collection and analysis of survey data, thereby improving the overall quality and efficiency of geotechnical engineering surveys.

[0152] Embodiment 9:

[0153] like Fig. 9 As shown, based on Example 8, the process of deploying survey personnel and survey equipment with corresponding professional skills in step S302 provided in this embodiment of the present invention includes the following steps:

[0154] Step S3021: Acquire specific content of the task requirement, and select surveyors matching the specific content from the surveyor database according to the task requirement collaborative operation platform, where the matching content is the technology that the surveyor is good at;

[0155] Step S3022: Obtain the task type, and select the survey equipment matching the specific content from the survey equipment data according to the task type collaborative operation platform, where the matching content is the work content completed by the survey equipment;

[0156] Step S3023: The collaborative work platform sends the task requirements and task types through the Internet of Things to the terminal devices of the corresponding surveyors, and lists the survey equipment at the same time.

[0157] In the above embodiment, step S3021 obtains the specific content of the task requirements. By obtaining the specific content of the task requirements, the nature and technical requirements of the task can be accurately understood; according to the task requirements, the collaborative operation platform selects surveyors who are good at the corresponding technology from the surveyor database to ensure that the task is performed by personnel with professional skills; by matching the technology that the surveyor is good at with the task requirements, the efficiency and quality of task execution are improved. Step S3022 obtains the task type. By obtaining the task type, the system can clarify the specific work content of the task and the required equipment type; according to the task type, the collaborative operation platform selects survey equipment that can complete the corresponding work content from the survey equipment database to ensure that the equipment matches the task requirements; by matching the work content of the survey equipment with the task type, the equipment configuration is optimized to improve the efficiency of equipment use and the quality of task completion. Step S3023 sends the task requirements and task types. Through the Internet of Things technology, the collaborative work platform sends the task requirements and task types to the terminal devices of the corresponding surveyors, realizing real-time information transmission and rapid response to tasks. While sending the task requirements, a list of survey equipment is listed to help surveyors quickly understand the required equipment and ensure the smooth execution of the task. By receiving task information through terminal devices, surveyors can clearly understand the specific requirements and required resources of the task, thereby improving the transparency and collaborative efficiency of task execution.

[0158] In summary, the process of deploying surveyors and survey equipment with corresponding professional skills in this embodiment can achieve accurate analysis of task requirements, optimal matching of surveyors and equipment, and real-time transmission of task information, ensuring efficient execution of survey tasks and rational use of resources.

[0159] Embodiment 10:

[0160] like Fig.10 As shown, based on Embodiment 1 to Embodiment 9, the geotechnical engineering survey collaborative operation deployment system provided by the embodiment of the present invention includes:

[0161] Data fusion module 1 is responsible for collecting geological information in all directions using acquisition equipment; screening geological characteristic data from geological information; fusing geological characteristic data from different data sources to obtain fused geological characteristic data;

[0162] Feature recognition module 2 is responsible for correcting the fused geological feature data and correcting the errors in the data; analyzing the corrected geological feature data, identifying and classifying geological features including rock and soil layers, geological structures and groundwater, and predicting potential geological disaster risks;

[0163] Collaborative deployment module 3 is responsible for allocating survey tasks and deploying survey personnel and equipment resources according to geological characteristics and geological risks on the collaborative operation platform.

[0164] In the above embodiment, the data fusion module 1 collects geological information in all directions through the acquisition equipment to ensure the comprehensiveness and accuracy of the data; selects key geological feature data from the collected geological information to improve the efficiency and accuracy of data processing; fuses the geological feature data from different data sources to form a unified and complete geological feature data set, providing a reliable data basis for subsequent analysis. The feature recognition module 2 corrects the fused geological feature data, corrects the errors in the data, and improves the accuracy and reliability of the data; by analyzing the corrected geological feature data, identifies and classifies geological features such as rock and soil layers, geological structures and groundwater, and provides a basis for the assessment of geological risks; based on the identified geological features, predicts potential geological disaster risks, and provides a scientific basis for the priority sorting and resource allocation of survey tasks. The collaborative allocation module 3 intelligently allocates survey tasks based on geological characteristics and geological risks, and ensures that high-risk areas are given priority; according to task requirements, deploys survey personnel and equipment resources with corresponding professional skills to ensure the efficient completion of tasks; monitors the survey progress and resource usage in real time, and adjusts tasks and resource allocation in a timely manner based on feedback to ensure the smooth progress of survey tasks and the optimal use of resources.

[0165] In summary, through the collaborative work of the above modules, the geotechnical engineering survey collaborative operation deployment system in this embodiment can realize the comprehensive collection, accurate analysis and efficient deployment of geological information, and provide strong technical support for geotechnical engineering survey.

[0166] Embodiment 11:

[0167] Fig.11 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown.

[0168] The electronic device may include a central processing unit / microprocessor / main control chip, etc. 4; a storage medium 5, coupled to the central processing unit / microprocessor / main control chip, etc. 4, and storing computer executable instructions therein, for performing the steps of each method of an embodiment of the present invention when executed by the processor.

[0169] The central processing unit / microprocessor / main control chip 4 may include but is not limited to, for example, one or more processors or microprocessors.

[0170] The storage medium 5 may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disk, floppy disk, solid state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0171] In addition, the electronic device may also include (but not limited to) a data bus 6, an input / output bus / external bus / device bus 7, a display 8, and input / output devices 9 (eg, keyboard, mouse, speaker, etc.).

[0172] The central processing unit / microprocessor / main control chip etc. 4 can communicate with external devices ( 8 , 9 etc.) through the I / O bus 7 via a wired or wireless network (not shown).

[0173] The storage medium 5 may also store at least one computer executable instruction for executing the various functions and / or method steps in the embodiments described in the present technology when executed by the central processing unit / microprocessor / main control chip 4.

[0174] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0175] Fig.12 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0176] like Fig.12 As shown, instructions are stored on a non-transitory computer-readable storage medium 11, and the instructions are, for example, computer-readable instructions 10. When the computer-readable instructions 10 are executed by the processor, the various methods described above can be executed. Non-transitory computer-readable storage media include, but are not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-transitory non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium 11 can be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions 10 stored on the computer-readable storage medium 11, the various methods described above can be performed.

[0177] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0178] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0180] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the various embodiments of the method of the present invention through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0181] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for coordinating geotechnical engineering survey collaborative operations, characterized in that: The following steps are involved: Collect geological information in all directions using acquisition equipment; filter geological characteristic data from geological information; fuse geological characteristic data from different data sources to obtain fused geological characteristic data; Correct the fused geological feature data to correct the errors in the data; analyze the corrected geological feature data to identify and classify the geological features including rock and soil layers, geological structures and groundwater, and predict potential geological disaster risks; The collaborative operation platform allocates survey tasks and deploys survey personnel and equipment resources based on geological characteristics and geological risks.

2. The method for coordinating geotechnical engineering survey collaborative operations according to claim 1, characterized in that: The process of obtaining the fused geological feature data includes the following steps: Construct a three-dimensional geological model M, including key geological elements such as stratigraphic interfaces, faults, and lithology distribution; perform data cleaning and data standardization preprocessing on the geological data set and geological characteristic data set; the geological data set is a collection of geological information, and the geological characteristic data set is a collection of geological characteristic data; Extract key geological features using geological models and geological feature data; map features from different data sources to geological models through geological feature alignment; use a multimodal fusion network based on geological models, combined with attention mechanisms and graph neural networks to fuse geological information, and automatically identify and remove duplicate geological data through comparative learning; Adaptive error correction using geological models and generative adversarial networks to identify and process outliers in fused data; The corrected fused data are exported as geological characteristic data in a unified format.

3. The method for coordinating geotechnical engineering survey collaborative operations according to claim 1, characterized in that: The process of predicting potential geological disaster risks includes the following steps: Using statistics, identify and correct the systematic and random errors in the fused geological feature data; extract key features from the geological data, such as the distribution and occurrence of rock and soil bodies, the development characteristics of geological structures, and groundwater burial conditions; The support vector machine classification algorithm is used to classify the extracted features and identify different types of rock and soil layers, geological structures and groundwater; Using geological characteristic data and historical geological disaster data, a geological risk assessment model is constructed. The identified and classified geological characteristics are input into the risk assessment model to predict potential geological disaster risks and output risk levels and risk areas.

4. The method for coordinating geotechnical engineering survey collaborative operations according to claim 3, characterized in that: The process of identifying and correcting systematic and random errors in the fused geological feature data includes the following steps: Use time series analysis to identify long-term trends in the fused geological feature data and determine whether there are systematic deviations; compare the fused geological feature data with the preset benchmark data and identify systematic errors through difference analysis; According to the benchmark comparison results, the overall deviation correction is performed; the variance of the fused geological feature data is calculated, the random fluctuations in the fused geological feature data are identified, and whether there are significant random errors; the high-frequency noise in the fused geological feature data is identified by spectrum analysis, and the source and characteristics of the random errors are determined; Low-pass filtering is used to remove high-frequency noise in the fused geological feature data, smooth random errors, and smooth the fused geological feature data.

5. The method for coordinating geotechnical engineering survey collaborative operations according to claim 3, characterized in that: The process of identifying different types of rock layers, geological formations and groundwater involves the following steps: Prepare training data sets, including input feature vectors and corresponding labels; feature vectors correspond to geological feature data, and labels correspond to classification results, including rock formation types and geological structure types; The support vector machine is to find an optimal hyperplane that maximizes the classification interval, through the optimization problem description; Solve the optimization problem, obtain the optimal normal vector and bias term of the hyperplane, and determine the optimal hyperplane.

6. The method for coordinating geotechnical engineering survey collaborative operations according to claim 3, characterized in that: The process of building a geological risk assessment model includes the following steps: Integrate geological characteristic data and historical geological disaster data to construct a comprehensive data set and a multi-level risk assessment system; use historical geological disaster data to train and verify the geological risk assessment model and adjust the parameters of the geological risk assessment model; According to the output results of the geological risk assessment model, different risk levels are divided and risk areas are determined; The geological risk assessment model is optimized according to the preset cycle, new geological data and disaster cases are introduced, and the geological risk assessment model parameters are updated; combined with real-time geological monitoring data, the geological risk assessment model is dynamically adjusted and feedback is provided.

7. The method for coordinating geotechnical engineering survey collaborative operations according to claim 6, characterized in that: The process of training and validating the geological risk assessment model using historical geological hazard data includes the following steps: Extract key features from geological feature data, including geological structure, rock and soil type and groundwater level, and construct feature vectors; build a multi-level risk assessment system, including geological features, disaster-related features and risk assessment; The historical geological disaster data are divided into a training set and a validation set, and the geological risk assessment model is trained using the training set, and the parameters of the geological risk assessment model are optimized through iteration; K-fold cross validation was used to evaluate the performance and stability of the geological risk assessment model. The prediction accuracy, recall rate and F1 score indicators of the geological risk assessment model were evaluated through the validation set.

8. The method for coordinating geotechnical engineering survey collaborative operations according to claim 1, characterized in that: The process of deploying survey personnel and equipment resources includes the following steps: Based on the risk assessment results, the collaborative operation platform prioritizes the survey tasks in different areas, with high-risk areas having the highest priority; it refines high-priority tasks to determine specific survey targets and required data types, including rock and soil sampling and groundwater level monitoring; According to the task requirements, the collaborative operation platform deploys survey personnel with corresponding professional skills; according to the task type, it deploys survey equipment; The collaborative work platform distributes the detailed tasks to the corresponding survey teams, provides detailed geological information and risk assessment reports; monitors the survey progress and data collection in real time, receives feedback from the survey team, and adjusts tasks and resource allocation in a timely manner.

9. The method for coordinating geotechnical engineering survey collaborative operations according to claim 8, characterized in that: The process of deploying survey personnel and survey equipment with corresponding professional skills includes: Obtain the specific content of the task requirements, and select surveyors matching the specific content from the surveyor database based on the task requirements collaborative operation platform. The matching content is the technology that the surveyor is good at; Obtain the task type, and based on the task type, the collaborative operation platform selects survey equipment that matches the specific content from the survey equipment data. The matching content is the work content completed by the survey equipment. The collaborative work platform sends task requirements and task types through the Internet of Things to the terminal devices of the corresponding surveyors, and lists the survey equipment at the same time.

10. A geotechnical engineering investigation collaborative work coordination system implementing the geotechnical engineering investigation collaborative work coordination method according to any one of claims 1 to 9, characterized in that: include: The data fusion module is responsible for collecting geological information in all directions using acquisition equipment; Screening geological characteristic data from geological information; Fusing geological characteristic data from different data sources to obtain fused geological characteristic data; The feature recognition module is responsible for correcting the fused geological feature data and rectifying the errors in the data; analyzing the corrected geological feature data, identifying and classifying rock and soil layers, geological structures and groundwater, and predicting potential geological disaster risks; The collaborative deployment module is responsible for allocating survey tasks and deploying survey personnel and equipment resources based on geological characteristics and geological risks on the collaborative operation platform.

Images