Foundation pit data processing method and device, storage medium, program product and processor

Abstract

The invention discloses a data processing method and device for a foundation pit, a storage medium, a program product and a processor. The method comprises the steps that multi-source monitoring data of a foundation pit are obtained, and the multi-source monitoring data are used for determining the deformation degree of the foundation pit; performing feature extraction on the multi-source monitoring data to obtain key feature data; the key feature data are input into a deformation prediction model for prediction, deformation data of the foundation pit at the future moment are obtained, model parameters of the deformation prediction model are obtained through training based on historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters at least comprise penalty factors and kernel function parameters; the deformation data is used for representing the deformation degree of the foundation pit. The technical problem that the accuracy of determining the deformation degree of the foundation pit is low is solved.

Description

Technical Field

[0001] The present application relates to the field of foundation pit engineering, and in particular, to a data processing method, device, storage medium, program product and processor for a foundation pit. Background Art

[0002] At present, with the acceleration of urbanization and the continuous advancement of urban construction, foundation pit projects are becoming more and more common in various construction projects. The scale and complexity of foundation pit projects are showing an increasing trend. In foundation pit projects, ensuring the safety and stability of the foundation pit is of great significance.

[0003] In the related art, the prediction of the deformation degree of the foundation pit usually fails to take into account the interaction between multiple complex factors, and there is a technical problem of low accuracy in determining the deformation degree of the foundation pit.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a data processing method, device, storage medium, program product and processor for a foundation pit, so as to at least solve the technical problem of low accuracy in determining the degree of deformation of the foundation pit.

[0006] According to one aspect of an embodiment of the present application, a data processing method for a foundation pit is provided, which may include: acquiring multi-source monitoring data of a foundation pit, wherein the multi-source monitoring data is used to determine the degree of deformation of the foundation pit; performing feature extraction on the multi-source monitoring data to obtain key feature data; inputting the key feature data into a deformation prediction model for prediction to obtain deformation data of the foundation pit at a future moment, wherein model parameters of the deformation prediction model are obtained by training based on historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the degree of deformation of the foundation pit.

[0007] Optionally, obtaining multi-source monitoring data of the foundation pit includes: using multiple monitoring devices to obtain multi-source monitoring data.

[0008] Optionally, the method may also include: extracting features from historical multi-source monitoring data to obtain historical key feature data; using the historical key feature data to construct an initial deformation prediction model; obtaining multiple initial model parameter groups, wherein the initial model parameter group includes at least an initial penalty factor and an initial kernel function parameter; under the initial model parameter group, determining the initial deformation prediction model to predict the historical multi-source monitoring data to obtain historical prediction results; based on the historical prediction results and historical deformation data, determining a target model parameter group from multiple initial model parameter groups; and using the target model parameter group to update the initial deformation prediction model to obtain a deformation prediction model.

[0009] Optionally, based on historical prediction results and historical deformation data, a target model parameter group is determined among multiple initial model parameter groups, including: determining difference information between historical prediction results and historical deformation data; in response to the difference information satisfying an objective function, determining the initial model parameter group as the target model parameter group, wherein the objective function is used to characterize the degree of difference between the historical prediction results and the historical deformation data.

[0010] Optionally, the method may further include: determining error data between the deformation data and the actual deformation data; in response to the error data being greater than an error threshold, updating model parameters of the deformation prediction model based on the actual deformation data.

[0011] Optionally, the method may further include: in response to the deformation data not meeting the standard deformation data, outputting a prompt message, wherein the prompt message is used to prompt that the safety level of the foundation pit is lower than a safety level threshold.

[0012] According to another aspect of an embodiment of the present application, a data processing device for a foundation pit is also provided, which may include: an acquisition unit, used to acquire multi-source monitoring data of a foundation pit, wherein the multi-source monitoring data is used to determine the degree of deformation of the foundation pit; an extraction unit, used to perform feature extraction on the multi-source monitoring data to obtain key feature data; a prediction unit, used to input the key feature data into a deformation prediction model for prediction to obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the degree of deformation of the foundation pit.

[0013] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the data processing method for the foundation pit of the embodiment of the present application.

[0014] According to another aspect of an embodiment of the present application, a processor is further provided, the processor being used to run a program, wherein when the program is run by the processor, the data processing method for the foundation pit of an embodiment of the present application is executed.

[0015] According to another aspect of an embodiment of the present application, a computer program product is also provided, which includes computer instructions, wherein the computer instructions, when executed by a processor, implement the data processing method for the foundation pit of the embodiment of the present application.

[0016] In an embodiment of the present application, multi-source monitoring data of a foundation pit is obtained, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit; feature extraction is performed on the multi-source monitoring data to obtain key feature data; the key feature data is input into a deformation prediction model for prediction to obtain deformation data of the foundation pit at a future time, wherein the model parameters of the deformation prediction model are obtained based on historical multi-source monitoring data and historical deformation data of the foundation pit for training, and the model parameters at least include a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit. That is to say, in an embodiment of the present application, multi-source monitoring data of a foundation pit is obtained, feature extraction is performed on the multi-source monitoring data to obtain key feature data, and the deformation prediction model is used to predict the key feature data to obtain the deformation data of the foundation pit at a future time, thereby solving the technical problem of low accuracy in determining the deformation degree of the foundation pit and achieving the technical effect of improving the accuracy of determining the deformation degree of the foundation pit. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flow chart of a method for processing foundation pit data according to an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of the structure of a foundation pit deformation intelligent prediction system according to an embodiment of the present application;

[0020] Figure 3 is a flow chart of a method for constructing a deformation prediction model according to an embodiment of the present application;

[0021] Figure 4 is a flow chart of a foundation pit deformation prediction method according to an embodiment of the present application;

[0022] Figure 5 is a schematic diagram of a data processing device for a foundation pit according to an embodiment of the present application;

[0023] Figure 6 is a structural block diagram of a computer terminal according to an embodiment of the present application;

[0024] Figure 7 It is a block diagram of an electronic device for a foundation pit data processing method according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to an embodiment of the present application, an embodiment of a data processing method for a foundation pit is provided. The steps shown in the flowchart of the accompanying drawing can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] In this embodiment, a data processing method for a foundation pit is proposed. The method can obtain multi-source monitoring data of the foundation pit, perform feature extraction on the multi-source monitoring data, obtain key feature data, and use a deformation prediction model to predict the key feature data to obtain the deformation data of the foundation pit at future times, thereby solving the technical problem of low accuracy in determining the degree of deformation of the foundation pit and achieving the technical effect of improving the accuracy of determining the degree of deformation of the foundation pit.

[0029] Figure 1 1 is a flow chart of a method for processing foundation pit data according to an embodiment of the present application. Figure 1 As shown, the method may include the following steps:

[0030] Step S102, acquiring multi-source monitoring data of the foundation pit, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit.

[0031] In the technical solution provided in the above step S102 of the present application, the above multi-source monitoring data may include data collected by different monitoring equipment, for example, it may include data collected by the total station in the instrument layer, and data collected by the ground-based synthetic aperture radar (Ground-Based Synthetic Aperture Radar, referred to as GBSAR) data processor in the instrument layer. The above multi-source monitoring data can be used to determine the degree of deformation of the foundation pit, and may include: geological conditions of the foundation pit, foundation pit depth, support structure type, construction process and other data. It should be noted that this is only an example, and there is no specific limitation on the data type of the multi-source monitoring data.

[0032] Optionally, multi-source monitoring data of the foundation pit and within the target range of the foundation pit can be obtained through a variety of monitoring equipment.

[0033] Optionally, the above foundation pit is a cavity with a certain depth, width and length formed by excavating the ground in order to build underground structures such as basements, underground garages, subway stations, bridge piers, etc. in a construction project. Foundation pit excavation is an important part of civil engineering. Its purpose is to provide working space for underground construction. At the same time, it is necessary to ensure the safety of surrounding buildings and underground structures, and prevent adverse situations such as soil landslides and groundwater infiltration. Foundation pit projects often involve complex geological conditions and groundwater management. Therefore, during the design and construction process, appropriate support structures and construction technologies need to be adopted to ensure the safety of the project and the quality of construction.

[0034] Step S104, extracting features from multi-source monitoring data to obtain key feature data.

[0035] In the technical solution provided in the above step S104 of the present application, the above key characteristic data can be used to reflect the key characteristics of the foundation pit, and can be used to reflect the state of the foundation pit, such as the geological parameters of the foundation pit, water level changes, etc., which can be an important basis for predicting the deformation, stability and safety state of the foundation pit. Optionally, by analyzing the key characteristic data, the real-time status of the foundation pit project can be accurately evaluated and predicted.

[0036] In this embodiment, data collection and preprocessing are key. Data related to various factors including geological conditions, foundation pit depth, and GBSAR monitoring and total station measurement data can be collected to obtain multi-source monitoring data. The data can be cleaned and screened to remove noise and abnormal data to ensure the quality and consistency of the multi-source monitoring data. Furthermore, methods such as principal component analysis can be used to select and extract features from multi-source monitoring data to obtain key feature data, thereby achieving the purpose of reducing data dimensionality.

[0037] Optionally, by analyzing the key characteristic data, the deformation degree of the foundation pit at a future moment can be determined.

[0038] Optionally, the extracted key feature data can also be normalized so that multi-source monitoring data of different magnitudes can be unified into a relatively reasonable range to avoid deviations in model training due to large differences in data magnitudes and improve the stability and accuracy of the model. It should be noted that the above data processing methods and methods for obtaining key feature data are only examples and can be selected according to actual conditions, and are not specifically limited here.

[0039] Step S106, input the key feature data into the deformation prediction model for prediction, and obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the degree of deformation of the foundation pit.

[0040] In the technical solution provided in the above step S106 of the present application, a deformation prediction model can be obtained in advance based on the historical multi-source monitoring data and historical deformation data of the foundation pit. The deformation prediction model can be a foundation pit deformation intelligent prediction model based on PSO-SVM constructed by combining the particle swarm optimization (PSO) algorithm and the support vector machine (SVM), which can be used to predict the deformation degree of the foundation pit at a future time. Further, the key feature data can be input into the deformation prediction model to predict the deformation data of the foundation pit at a future time. Among them, the above deformation data can be used to determine the deformation degree of the foundation pit, for example, it can include the collapse distance of the foundation pit and the sinking status light data. It should be noted that the type of deformation data is not specifically limited here. The model parameters of the above deformation prediction model can be particles, which can at least include a penalty factor and a kernel function parameter. It should be noted that this is only a distance description, and the type of model parameters is not specifically limited.

[0041] In this embodiment, in terms of model construction, a PSO-SVM-based intelligent prediction model for foundation pit deformation is constructed by combining the PSO algorithm and SVM. Among them, the PSO algorithm finds the optimal solution by simulating the foraging behavior of bird flocks, which is used to optimize the parameters of SVM, such as kernel function parameters and penalty factors. SVM can be a machine learning method based on statistical learning theory, which performs classification or regression prediction by finding the optimal hyperplane. In the prediction of foundation pit deformation, the foundation pit deformation data (that is, multi-source monitoring data) can be used as input and the predicted value (that is, deformation data at a future moment) can be output.

[0042] Alternatively, SVM, as a machine learning method based on statistical learning theory, can divide the original samples into positive samples and negative samples by finding an optimal hyperplane, and maximize the distance between each type of sample and the hyperplane. Therefore, applying SVM to the field of foundation pit deformation prediction can effectively improve the prediction accuracy of the model.

[0043] Optionally, the PSO algorithm can be an optimization algorithm based on swarm intelligence, which can be used to find the optimal solution by simulating the foraging behavior of a flock of birds. In this simulation process, massless particles are introduced to represent individuals in the flock of birds. The particles have two properties, position and velocity, which correspond to their direction of movement and speed in the domain of definition. Each particle moves independently in the domain of definition and searches for a solution, while recording the optimal solution it finds as the extreme value of the current particle and sharing it with other particles. Through this information sharing mechanism, the particle swarm can find the current optimal solution for the entire group, and the particles will adjust their position and velocity according to the shared optimal solution.

[0044] In this embodiment, the PSO algorithm is combined with SVM to construct an intelligent prediction model for foundation pit deformation based on PSO-SVM, which can give full play to the advantages of both. SVM provides the ability to classify or regress multi-source monitoring data, while the PSO algorithm can optimize the parameters of SVM, thereby improving the performance of the model, and further improving the accuracy and reliability of foundation pit deformation prediction.

[0045] Through the above steps S102 and S106 of the present application, the multi-source monitoring data of the foundation pit is obtained, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit; feature extraction is performed on the multi-source monitoring data to obtain key feature data; the key feature data is input into the deformation prediction model for prediction to obtain the deformation data of the foundation pit at a future time, wherein the model parameters of the deformation prediction model are obtained based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters at least include a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit. That is to say, in the embodiment of the present application, the multi-source monitoring data of the foundation pit is obtained, feature extraction is performed on the multi-source monitoring data to obtain key feature data, and the deformation prediction model is used to predict the key feature data to obtain the deformation data of the foundation pit at a future time, thereby solving the technical problem of low accuracy in determining the deformation degree of the foundation pit and achieving the technical effect of improving the accuracy of determining the deformation degree of the foundation pit.

[0046] The above method of this embodiment is further introduced below.

[0047] As an optional implementation, step S102, obtaining multi-source monitoring data of the foundation pit, includes: obtaining multi-source monitoring data using multiple monitoring devices.

[0048] In this embodiment, the above-mentioned monitoring equipment may be monitoring equipment in the instrument layer, and may include equipment such as a total station and a GBSAR data processor. It should be noted that this is only an example, and there is no specific limitation on the location and type of the monitoring equipment.

[0049] Figure 2 is a schematic diagram of the structure of a foundation pit deformation intelligent prediction system according to an embodiment of the present application, such as Figure 2 As shown, the system may include: a user layer 201, a server layer 202, a transmission layer 203, a training layer 204 and an instrument layer 205. Among them, the user layer 201 may be deployed with a mobile phone software (APP) and a cloud-based foundation pit monitoring platform. The server layer 202 may include a database, user management and data processing. The transmission layer 203 may be used for data transmission. The training layer 204 may be used for training to obtain a deformation prediction model. The instrument layer 205 may include a total station and a GBSAR data processor.

[0050] Optionally, the total station and GBSAR data processor in the instrument layer can collect multi-source monitoring data. The total station has high-precision measurement capabilities and can accurately obtain the location information of the foundation pit and nearby monitoring points. The GBSAR data processor can obtain the displacement deformation data of the foundation pit.

[0051] Optionally, data monitored by multiple monitoring devices may be combined to obtain multi-source monitoring data, which may provide comprehensive and accurate data support for the deformation prediction model.

[0052] For example, the instrument layer can obtain multi-source monitoring data and transmit it to the server layer through the transport layer. The transport layer can ensure stable data transmission and avoid data loss or damage. The server layer can process and manage the data and store it in the database. The efficient processing capability of the server layer can quickly process and store large amounts of data, providing data guarantee for subsequent model training.

[0053] Optionally, the training layer can obtain historical multi-source monitoring data and historical deformation data from the database to perform PSO-SVM network training to train a deformation prediction model. Using the deformation prediction model, the collected multi-source monitoring data can be effectively learned and analyzed in real time.

[0054] Optionally, the user layer can interact with the server layer through a mobile phone APP and a cloud-based foundation pit monitoring platform to obtain data display and operation functions. Users can conveniently view the prediction results of foundation pit deformation on the mobile phone APP or cloud platform and take corresponding measures in a timely manner according to the results. This convenient interactive method can improve the efficiency of engineering management and the timeliness of decision-making. Among them, the above-mentioned prediction results can be the deformation data of the foundation pit at a future moment.

[0055] As an optional implementation, the method may also include: extracting features from historical multi-source monitoring data to obtain historical key feature data; using the historical key feature data to construct an initial deformation prediction model; obtaining multiple initial model parameter groups, wherein the initial model parameter group includes at least an initial penalty factor and an initial kernel function parameter; under the initial model parameter group, determining the initial deformation prediction model to predict the historical multi-source monitoring data to obtain historical prediction results; based on the historical prediction results and historical deformation data, determining a target model parameter group from multiple initial model parameter groups; and using the target model parameter group to update the initial deformation prediction model to obtain a deformation prediction model.

[0056] In this embodiment, training a deformation prediction model based on historical multi-source monitoring data and historical deformation data may include the following steps: extracting features from historical multi-source monitoring data to obtain historical key feature data; constructing an initial deformation prediction model using the historical key feature data; obtaining multiple initial model parameter groups, which may include at least an initial penalty factor and an initial kernel function parameter. Further, under the initial model parameter group, the initial deformation prediction model may be determined to predict the historical multi-source monitoring data to obtain historical prediction results; based on the historical prediction results and historical deformation data, a target model parameter group may be determined from multiple initial model parameter groups; and the target model parameter group may be used to update the initial deformation prediction model to obtain a deformation prediction model. The initial model parameter group may include at least one initial model parameter, which may be a particle swarm.

[0057] For example, relevant monitoring data of foundation pits at historical moments, such as displacement, geological parameters and other information provided by total stations and GBSAR, are collected to obtain historical multi-source data and determine the historical deformation data corresponding to historical moments. Data cleaning, noise removal and outliers can be performed on historical multi-source data and historical deformation data. Key features are extracted from preprocessed data by methods such as principal component analysis to obtain historical key feature data. The extracted feature data are normalized to ensure that each feature is at the same level to avoid certain features dominating the model training process. An initial foundation pit deformation prediction model (i.e., initial deformation prediction model) is established using SVM, and an initial model parameter group is set. The initial model parameter group may include initial model parameters, such as an initial penalty factor C and an initial kernel function parameter g. The PSO (particle swarm optimization) algorithm can be used to optimize the key parameters in the SVM model to obtain a target model group, wherein the PSO algorithm can simulate the foraging behavior of a flock of birds, iteratively update the position and velocity of particles, and search for the best parameter combination, thereby improving the model prediction performance. The SVM model is trained using the optimized model parameters, and the pattern of foundation pit deformation is learned through the training set data. The accuracy and generalization ability of the model are then evaluated using the validation set data, which can include historical multi-source monitoring data and historical deformation data. The trained prediction model can receive new multi-source monitoring data (referred to as monitoring data) as input, output the predicted foundation pit deformation results, and monitor the safety status of the foundation pit in real time.

[0058] Figure 3 is a flowchart of a method for constructing a deformation prediction model according to an embodiment of the present application. Figure 3 As shown, the deformation prediction model can be constructed by the following steps:

[0059] Step S301, obtaining metadata.

[0060] In this embodiment, the above metadata can be used as basic data, and may include historical multi-source monitoring data and historical deformation data, which can be used for model training and verification, and may include relevant data under various geological conditions, foundation pit depths, support structure types, and construction processes, thereby ensuring that the model can learn rich and diverse information and better adapt to various situations in actual engineering.

[0061] Step S302, training the SVM model.

[0062] In this embodiment, the SVM model may be an initial deformation prediction model.

[0063] Optionally, the SVM model is first trained and then verified. During the training process, the SVM model can classify or regress historical multi-source monitoring data by finding the optimal hyperplane based on its own initial settings. The PSO algorithm can be used to optimize the initial model parameter group of the SVM model, which can include at least parameter c and parameter ε.

[0064] Optionally, the PSO algorithm can quickly search for the optimal solution in a complex parameter space by simulating the foraging behavior of a flock of birds to obtain the optimal target model parameter group.

[0065] Step S303, verifying the trained SVM model.

[0066] In this embodiment, the trained SVM model may be verified using the verification set in the metadata.

[0067] Step S304: Determine the optimization effect using the fitness function.

[0068] In this embodiment, historical prediction results and historical deformation data are obtained, and the historical prediction results and historical deformation data are processed by a fitness function to determine the optimization effect of the deformation prediction model.

[0069] Step S305, determining whether a termination condition is met.

[0070] In this embodiment, whether to stop the optimization can be determined according to the termination condition, and the optimal parameters, that is, the target model parameter group, can be finally obtained. The target model parameter group can be used to update the initial deformation prediction model to obtain the deformation prediction model.

[0071] Optionally, if the termination condition is met, step S307 may be executed. If the termination condition is not met, step S306 may be executed.

[0072] Step S306, continue to optimize the model parameters.

[0073] In this embodiment, if the initial deformation prediction model obtained through training does not meet the termination condition during the verification process, the POS algorithm can be used to continue the optimization.

[0074] Step S307, determining the optimal parameters.

[0075] In this embodiment, if the termination condition is met, the model parameter group at this time can be determined as the target model parameter group (that is, the optimal parameters are obtained).

[0076] Optionally, the above optimization method can effectively overcome the shortcomings of traditional SVM model parameter selection relying on experience or trial and error, and improve the accuracy and generalization ability of the model.

[0077] For example, from metadata containing information such as geological conditions and foundation pit depth, key features can be extracted through principal component analysis to obtain historical key feature data; then, these feature data are used as input to build an SVM model and set initial parameters; then, the PSO algorithm is used to initialize the particle swarm (that is, the initial model parameter group) using the penalty factor C and Gaussian kernel parameter g of the SVM as the position of the particle, and the fitness of each particle, that is, the accuracy of the model prediction, can be evaluated through cross-validation; the particles update the speed and position according to the individual best position and the group best position, and iterate to find the best; finally, PSO finds the optimal C and g parameters, which are used to train the final PSO-SVM model to achieve high-precision prediction of foundation pit deformation. For example, the particle swarm size is set to 30 and the number of iterations is 50. Through multiple iterative optimizations, the model prediction error is significantly reduced, achieving the best prediction effect.

[0078] Optionally, when using PSO to optimize SVM parameters, the penalty factor C of SVM and the kernel function parameter g can be used as the position of the particle to initialize a group of particles. By calculating the accuracy of the SVM model under cross-validation at the position of each particle as the fitness value, the particle updates the speed and position according to the personal best position (pbest) and the global best position (gbest), and finds the optimal parameter combination to improve the model prediction performance. For example, the particle swarm size is set to 50 and the number of iterations is 100. Through multiple iterations, the particle swarm searches in the parameter space of C and g, and finally the particle swarm converges to the parameter combination that makes the SVM model prediction accuracy the highest.

[0079] It should be noted that the above method of constructing a deformation prediction model is only for illustration and is not specifically limited here. The construction process can be supplemented or adjusted according to actual conditions.

[0080] As an optional implementation, based on historical prediction results and historical deformation data, a target model parameter group is determined from multiple initial model parameter groups, including: determining difference information between historical prediction results and historical deformation data; in response to the difference information satisfying an objective function, determining the initial model parameter group as the target model parameter group, wherein the objective function is used to characterize the degree of difference between the historical prediction results and the historical deformation data.

[0081] In this embodiment, the objective function may be an adaptive function, a pre-set function, or may be determined based on the difference between the prediction performance of the model and the actual result. For example, the objective function may be a mean square error or a classification accuracy.

[0082] Optionally, the model is trained with the parameter set represented by the particle; then, the trained model is used to predict the validation data set; finally, the prediction result is compared with the true value, and indicators such as MSE are calculated, which is the fitness value of the particle, which is used to evaluate the quality of the parameter set to guide the iterative optimization of the PSO algorithm.

[0083] Figure 4 is a flow chart of a method for predicting foundation pit deformation according to an embodiment of the present application. Figure 4 As shown, the method may include data processing, model building, parameter optimization, and final prediction and error analysis. Optionally, the method may include the following steps:

[0084] Step S401: data normalization processing.

[0085] In this embodiment, the collected foundation pit deformation related data (for example, historical multi-source monitoring data) is normalized to ensure the consistency of data magnitude and provide high-quality data for subsequent model training.

[0086] Step S402, establishing a SVM training model.

[0087] In this embodiment, a SVM model is constructed based on the preprocessed data set and preliminary training is performed.

[0088] Optionally, an SVM training model is established. The SVM model can effectively learn and analyze the input foundation pit deformation data, providing a basis for subsequent prediction.

[0089] Step S403, initializing the population and speed.

[0090] In this embodiment, the above population and speed related parameters may include the number of PSO iterations, population size, k parameter, etc. Reasonable setting of these parameters can ensure that the PSO algorithm has sufficient search space in the process of searching for the optimal solution and can quickly converge to the vicinity of the optimal solution, thereby improving the efficiency of the algorithm.

[0091] Optionally, algorithm parameters such as population size, number of iterations, etc. are set, and the particle swarm is initialized, where each particle represents a set of SVM parameters (which may be an initial model parameter set).

[0092] Step S404, evaluating the fitness of each particle.

[0093] In this embodiment, the fitness of each particle can be evaluated, and the fitness of the particle can be calculated by combining the established SVM model with the training data. The fitness evaluation method based on actual data and model can accurately reflect the quality of the particle and provide a reliable basis for the update of the particle.

[0094] Optionally, the fitness value of each particle, that is, the accuracy of the model prediction, is calculated by the SVM model and the current data set.

[0095] Step S405, updating relevant parameters.

[0096] In this embodiment, relevant parameters such as pbest and gbest can be updated, as well as particle speed and position. By continuously updating these parameters, the particles can move in a better direction and gradually approach the optimal solution.

[0097] Optionally, based on the calculated fitness value, the position and velocity of each particle are updated to approach the optimal parameters.

[0098] Step S406, determining whether a termination condition is met.

[0099] In this embodiment, it can be determined whether the termination condition is met, if not, then return to step S404 and continue iteration, if met, then proceed to step S407. The termination condition may be a pre-set condition.

[0100] Optionally, the above iteration mechanism can ensure that the algorithm continues searching before achieving a satisfactory optimization effect, thereby avoiding premature stopping and resulting in a suboptimal solution.

[0101] For example, it can be checked whether the number of iterations is reached or the fitness value satisfies a preset condition to decide whether to terminate the optimization.

[0102] Step S407, obtaining optimized SVM parameters.

[0103] In this embodiment, a target model parameter group is obtained.

[0104] Optionally, after the optimization is completed, the particle parameters with the highest fitness value can be selected as the optimal parameters of the SVM.

[0105] Optionally, optimized SVM parameters c and ε are obtained. The above optimized parameters can make the SVM model better adapt to the characteristics of foundation pit deformation data and improve prediction accuracy.

[0106] Step S408: establishing a deformation prediction model.

[0107] In this embodiment, the obtained optimization parameters are used to establish a foundation pit displacement prediction model, which can accurately predict the displacement of the foundation pit based on the input relevant data.

[0108] Step S409: performing error analysis on the deformation prediction model.

[0109] In this embodiment, an error analysis is performed on the constructed prediction model to determine whether further optimization is required.

[0110] Step S410: updating the model parameters.

[0111] In this embodiment, if the model parameters need to be further updated, the PSO iteration steps, population size and K parameter optimization can be set to obtain the adjusted model parameters.

[0112] Optionally, in terms of parameter optimization, this embodiment determines the optimal search range of particles in the PSO algorithm. For example, the kernel function parameters should avoid the problems of "over-learning" and "under-learning", and their value range is determined within a reasonable interval, while also determining the value range of the penalty factor.

[0113] Optionally, the parameters are optimized through the steps of initializing the PSO particles, calculating the difference of the objective functions of adjacent nodes, and judging the termination of the algorithm, and finally the best parameter combination is obtained.

[0114] As an optional implementation, the method may further include: determining error data between the deformation data and the actual deformation data; in response to the error data being greater than an error threshold, updating model parameters of the deformation prediction model based on the actual deformation data.

[0115] In this embodiment, after acquiring the deformation data, the deformation data and the actual deformation data can be compared to determine the error data between the deformation data and the actual deformation data. If the error data is greater than the error threshold, the model parameters of the deformation prediction model can be updated again based on the actual deformation data, and the updated deformation prediction model can be used to predict the state of the foundation pit.

[0116] Optionally, the constructed deformation prediction model can also be subjected to error analysis. If further optimization is required, the optimization can be restarted, otherwise the optimization can be terminated. Error analysis can timely identify problems existing in the model and perform targeted optimization to further improve the performance of the model.

[0117] In this embodiment, the prediction results can also be compared with the actual monitoring data to analyze the prediction error. If necessary, the model parameters can be adjusted again through the PSO algorithm to achieve dynamic optimization of the model and improve the real-time and accuracy of the prediction.

[0118] As an optional implementation, the method may further include: in response to the deformation data not meeting the standard deformation data, outputting a prompt message, wherein the prompt message is used to indicate that the safety of the foundation pit is lower than a safety threshold.

[0119] In this embodiment, if the deformation data does not meet the standard deformation data, it can be determined that the safety (or stability) of the foundation pit is lower than the safety threshold, and a prompt message can be output to prompt the user or operator. The prompt message can be text, voice, image and other information, and the type of the prompt message is not specifically limited here.

[0120] In an embodiment of the present application, multi-source monitoring data of a foundation pit is acquired, feature extraction is performed on the multi-source monitoring data to obtain key feature data, and a deformation prediction model is used to predict the key feature data to obtain deformation data of the foundation pit at future times, thereby solving the technical problem of low accuracy in determining the degree of deformation of the foundation pit and achieving the technical effect of improving the accuracy of determining the degree of deformation of the foundation pit.

[0121] The present application is further described below with reference to another embodiment.

[0122] At present, with the acceleration of urbanization and the continuous advancement of urban construction, foundation pit projects are becoming more and more common in various construction projects. The scale and complexity of foundation pit projects are showing an increasing trend. In foundation pit projects, ensuring their safety and stability is crucial, and accurate prediction of foundation pit deformation is the key to achieving this goal. Foundation pit deformation is affected by a variety of factors, including geological conditions, foundation pit depth, support structure type, and construction technology. Due to the complex interactions between these factors, and each factor itself has multiple possibilities and variability, an intelligent prediction model that can comprehensively and comprehensively consider multiple factors is needed to achieve accurate prediction of foundation pit deformation.

[0123] In the relevant technologies, there are several problems in predicting the deformation degree of foundation pits: it is usually difficult to accurately consider the interaction of multiple complex factors, resulting in insufficient prediction accuracy; when processing large-scale data, the computational efficiency is low and cannot meet the real-time prediction needs; it is sensitive to changes in data distribution and noise, the prediction performance is unstable, and there is a problem of poor data adaptability; SVM parameter selection relies on experience or trial and error, and parameter selection lacks scientific methods, making it difficult to achieve optimal performance; intelligent prediction models are prone to fall into local optimality during training, affecting generalization ability and accuracy.

[0124] In order to solve the above problems and improve the accuracy and reliability of foundation pit deformation prediction, in this embodiment, the parameters of SVM are optimized by PSO algorithm, which can better adapt to the characteristics of foundation pit deformation data, thereby achieving the purpose of improving the prediction accuracy of the model. The optimized model can better handle foundation pit engineering data of different types and scales, achieving the purpose of improving the generalization ability of the prediction model. The PSO algorithm can quickly search for the optimal parameters, reduce the time cost of model training, and achieve the purpose of improving calculation efficiency.

[0125] Optionally, the deformation prediction model constructed by the above method has strong adaptive ability, and can automatically adjust parameters according to changes in actual data to adapt to different working conditions and environments. In addition, the above deformation prediction model can comprehensively consider the influence of multiple factors such as geological conditions, foundation pit depth, and support structure type on foundation pit deformation, and can provide more comprehensive prediction results.

[0126] Optionally, the above deformation prediction model can timely predict the deformation of the foundation pit and provide real-time guidance and early warning for engineering construction. By optimizing the model through the above method, the prediction error is reduced and the reliability of the prediction result is improved.

[0127] In an embodiment of the present application, multi-source monitoring data of a foundation pit is acquired, feature extraction is performed on the multi-source monitoring data to obtain key feature data, and a deformation prediction model is used to predict the key feature data to obtain deformation data of the foundation pit at future times, thereby solving the technical problem of low accuracy in determining the degree of deformation of the foundation pit and achieving the technical effect of improving the accuracy of determining the degree of deformation of the foundation pit.

[0128] It should be noted that the embodiments of the present application can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. A person of ordinary skill in the art will appreciate that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present application can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0129] The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed in the present application and within the spirit and principles of the present application should be covered within the protection scope of the present application.

[0130] According to an embodiment of the present application, a data processing device for a foundation pit is also provided. It should be noted that the data processing device for a foundation pit of this embodiment can be used to execute the data processing method for a foundation pit of the above embodiment of the present application.

[0131] Figure 5Schematic diagram of a data processing device for a foundation pit according to an embodiment of the present application. Figure 5 As shown, the data processing device 50 of the foundation pit may include: an acquisition unit 502 , an extraction unit 504 and a prediction unit 506 .

[0132] The acquisition unit 502 is used to acquire multi-source monitoring data of the foundation pit, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit.

[0133] The extraction unit 504 is used to extract features from multi-source monitoring data to obtain key feature data.

[0134] The prediction unit 506 is used to input the key feature data into the deformation prediction model for prediction, and obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit.

[0135] The data processing device for the foundation pit of this embodiment obtains multi-source monitoring data of the foundation pit through an acquisition unit, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit; performs feature extraction on the multi-source monitoring data through an extraction unit to obtain key feature data; and inputs the key feature data into a deformation prediction model for prediction through a prediction unit to obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit, thereby solving the technical problem of low accuracy in determining the deformation degree of the foundation pit and achieving the technical effect of improving the accuracy of determining the deformation degree of the foundation pit.

[0136] The embodiment of the present application may provide a computer terminal, which may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced by a terminal device such as a mobile terminal.

[0137] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0138] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the data processing method of the foundation pit: obtaining multi-source monitoring data of the foundation pit, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit; performing feature extraction on the multi-source monitoring data to obtain key feature data; inputting the key feature data into the deformation prediction model for prediction to obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit.

[0139] Optionally, Figure 6 is a structural block diagram of a computer terminal according to an embodiment of the present application, such as Figure 6 As shown, the computer terminal 608 may include: one or more (only one is shown in the figure) processors 602 , a memory 604 , and a transmission device 606 .

[0140] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the data processing method and device of the foundation pit in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the data processing method of the foundation pit mentioned above. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 608 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0141] The processor can call the information and application programs stored in the memory through the transmission device to execute the following steps: obtain multi-source monitoring data of the foundation pit, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit; perform feature extraction on the multi-source monitoring data to obtain key feature data; input the key feature data into the deformation prediction model for prediction to obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit.

[0142] It can be understood by those skilled in the art that Figure 6The structure shown is for illustration only, and the computer terminal 608 may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, referred to as MID), a PAD, or other terminal devices. Figure 6 The structure of the computer terminal 608 is not limited. For example, the computer terminal 608 may also include Figure 6 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 6 Different configurations are shown.

[0143] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0144] According to an embodiment of the present application, a computer-readable storage medium is also provided, which includes a stored program, wherein the program executes the data processing method of the foundation pit in the above embodiment.

[0145] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the mobile terminals in a mobile terminal group.

[0146] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining multi-source monitoring data of a foundation pit, wherein the multi-source monitoring data is used to determine the degree of deformation of the foundation pit; performing feature extraction on the multi-source monitoring data to obtain key feature data; inputting the key feature data into a deformation prediction model for prediction to obtain deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the degree of deformation of the foundation pit.

[0147] Optionally, the computer-readable storage medium may also execute program code for the following steps: utilizing multiple monitoring devices to acquire multi-source monitoring data.

[0148] Optionally, the computer-readable storage medium can also execute the program code of the following steps: extract features from historical multi-source monitoring data to obtain historical key feature data; use the historical key feature data to construct an initial deformation prediction model; obtain multiple initial model parameter groups, wherein the initial model parameter group includes at least an initial penalty factor and an initial kernel function parameter; under the initial model parameter group, determine the initial deformation prediction model to predict the historical multi-source monitoring data to obtain historical prediction results; based on the historical prediction results and historical deformation data, determine the target model parameter group from multiple initial model parameter groups; use the target model parameter group to update the initial deformation prediction model to obtain a deformation prediction model.

[0149] Optionally, the computer-readable storage medium may also execute program code for the following steps: determining difference information between historical prediction results and historical deformation data; in response to the difference information satisfying an objective function, determining the initial model parameter group as a target model parameter group, wherein the objective function is used to characterize the degree of difference between the historical prediction results and the historical deformation data.

[0150] Optionally, the computer-readable storage medium may also execute program code for the following steps: determining error data between the deformation data and the actual deformation data; in response to the error data being greater than an error threshold, updating model parameters of the deformation prediction model based on the actual deformation data.

[0151] Optionally, the computer-readable storage medium may also execute program code of the following steps: in response to the deformation data not meeting the standard deformation data, outputting prompt information, wherein the prompt information is used to prompt that the safety of the foundation pit is lower than a safety threshold.

[0152] In this embodiment, multi-source monitoring data of the foundation pit is acquired, features are extracted from the multi-source monitoring data to obtain key feature data, and the key feature data is predicted using a deformation prediction model to obtain the deformation data of the foundation pit at future times, thereby solving the technical problem of low accuracy in determining the degree of deformation of the foundation pit and achieving the technical effect of improving the accuracy of determining the degree of deformation of the foundation pit.

[0153] According to an embodiment of the present application, a processor is also provided, which is used to run a program, wherein when the program is run by the processor, the data processing method for the foundation pit in the above embodiment is executed.

[0154] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0155] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the data processing method of the foundation pit: obtaining multi-source monitoring data of the foundation pit, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit; performing feature extraction on the multi-source monitoring data to obtain key feature data; inputting the key feature data into the deformation prediction model for prediction to obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit.

[0156] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the data processing method and device of the foundation pit in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the data processing method of the foundation pit mentioned above. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0157] The processor can call the information and application programs stored in the memory through the transmission device to execute the following steps: obtain multi-source monitoring data of the foundation pit, wherein the multi-source monitoring data is used to determine the deformation degree of the foundation pit; perform feature extraction on the multi-source monitoring data to obtain key feature data; input the key feature data into the deformation prediction model for prediction to obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the deformation degree of the foundation pit.

[0158] Optionally, the processor may also execute program code of the following steps: utilizing multiple monitoring devices to obtain multi-source monitoring data.

[0159] Optionally, the processor may also execute the program code of the following steps: extract features from historical multi-source monitoring data to obtain historical key feature data; construct an initial deformation prediction model using the historical key feature data; obtain multiple initial model parameter groups, wherein the initial model parameter group includes at least an initial penalty factor and an initial kernel function parameter; under the initial model parameter group, determine the initial deformation prediction model to predict the historical multi-source monitoring data to obtain historical prediction results; based on the historical prediction results and historical deformation data, determine the target model parameter group from multiple initial model parameter groups; and use the target model parameter group to update the initial deformation prediction model to obtain a deformation prediction model.

[0160] Optionally, the processor may also execute program code for the following steps: determining difference information between historical prediction results and historical deformation data; in response to the difference information satisfying an objective function, determining the initial model parameter group as a target model parameter group, wherein the objective function is used to characterize the degree of difference between historical prediction results and historical deformation data.

[0161] Optionally, the processor may also execute program code of the following steps: determining error data between the deformation data and the actual deformation data; in response to the error data being greater than an error threshold, updating model parameters of the deformation prediction model based on the actual deformation data.

[0162] Optionally, the processor may also execute program code of the following steps: in response to the deformation data not meeting the standard deformation data, outputting a prompt message, wherein the prompt message is used to prompt that the safety of the foundation pit is lower than a safety threshold.

[0163] By adopting the embodiment of the present application, multi-source monitoring data of the foundation pit is obtained, and features are extracted from the multi-source monitoring data to obtain key feature data. The key feature data is predicted using a deformation prediction model to obtain the deformation data of the foundation pit at future times, thereby solving the technical problem of low accuracy in determining the degree of deformation of the foundation pit and achieving the technical effect of improving the accuracy of determining the degree of deformation of the foundation pit.

[0164] According to an embodiment of the present application, a computer program product is also provided. The computer program product includes computer instructions, wherein when the computer instructions are executed by a processor, the data processing method for the foundation pit in the above embodiment is implemented.

[0165] An embodiment of the present application may provide an electronic device, which may include a memory and a processor.

[0166] Figure 7It is a block diagram of an electronic device for a data processing method of a foundation pit according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0167] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 to a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0168] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0169] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as a verification method for data. For example, in some embodiments, the verification method for data may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the data verification method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the data verification method in any other appropriate manner (e.g., by means of firmware).

[0170] According to an embodiment of the present application, a method for processing data of a foundation pit is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0171] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor that may be a dedicated or general purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0172] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0173] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0174] To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or an LCD (liquid crystal display, monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a path ball) through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0175] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a Local Area Network (LAN), a Wide Area Network (WAN), and the Internet.

[0176] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0177] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0178] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0179] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, 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 units or modules, which can be electrical or other forms.

[0180] 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 over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0181] In addition, each functional unit in each embodiment of the present application 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.

[0182] 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 application, 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, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0183] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for processing foundation pit data, characterized in that: include: Acquiring multi-source monitoring data of a foundation pit, wherein the multi-source monitoring data is used to determine the degree of deformation of the foundation pit; Extracting features from the multi-source monitoring data to obtain key feature data; The key feature data is input into a deformation prediction model for prediction to obtain deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are trained based on historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the degree of deformation of the foundation pit.

2. The method according to claim 1, characterized in that The method of obtaining multi-source monitoring data of foundation pits includes: The multi-source monitoring data is acquired using a plurality of monitoring devices.

3. The method according to claim 1, characterized in that The method further comprises: Extracting features from the historical multi-source monitoring data to obtain historical key feature data; Using the historical key feature data, an initial deformation prediction model is constructed; Acquire multiple initial model parameter groups, wherein the initial model parameter groups at least include an initial penalty factor and an initial kernel function parameter; Under the initial model parameter group, determining the initial deformation prediction model to predict the historical multi-source monitoring data to obtain a historical prediction result; Based on the historical prediction results and the historical deformation data, determining a target model parameter group from a plurality of the initial model parameter groups; The initial deformation prediction model is updated using the target model parameter group to obtain the deformation prediction model.

4. The method according to claim 3, characterized in that: The step of determining a target model parameter group from among the plurality of initial model parameter groups based on the historical prediction results and the historical deformation data includes: Determining difference information between the historical prediction result and the historical deformation data; In response to the difference information satisfying an objective function, the initial model parameter group is determined as the target model parameter group, wherein the objective function is used to characterize the degree of difference between the historical prediction result and the historical deformation data.

5. The method according to claim 1, characterized in that The method further comprises: determining error data between the deformation data and actual deformation data; In response to the error data being greater than an error threshold, model parameters of the deformation prediction model are updated based on the actual deformation data.

6. The method according to claim 1, characterized in that The method further comprises: In response to the deformation data not meeting the standard deformation data, a prompt message is output, wherein the prompt message is used to prompt that the safety level of the foundation pit is lower than a safety level threshold.

7. A data processing device for a foundation pit, characterized in that: include: An acquisition unit, used for acquiring multi-source monitoring data of a foundation pit, wherein the multi-source monitoring data is used for determining the deformation degree of the foundation pit; An extraction unit, used for extracting features from the multi-source monitoring data to obtain key feature data; A prediction unit is used to input the key feature data into a deformation prediction model for prediction, so as to obtain the deformation data of the foundation pit at a future moment, wherein the model parameters of the deformation prediction model are obtained by training based on the historical multi-source monitoring data and historical deformation data of the foundation pit, and the model parameters include at least a penalty factor and a kernel function parameter, and the deformation data is used to represent the degree of deformation of the foundation pit.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 6.

9. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 6.

10. A processor, characterized in that: The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 6 when being run by the processor.

Images