Comprehensive prediction method, device, equipment and storage medium for geotechnical engineering monitoring

Abstract

The present invention relates to artificial intelligence technology and discloses a comprehensive prediction method, device, equipment and storage medium for geotechnical engineering monitoring. The method includes: obtaining historical displacement information of a target slope within a preset time period, using a pre-built extrapolation integrated model to perform multi-algorithm parallel prediction on the historical displacement information, and obtaining a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model; obtaining a set of true measurement values of the target slope after the preset time period, calculating the error sequence and standard error between the prediction value set of each type of extrapolation algorithm and the true measurement value set, and calculating the error convergence of each type of extrapolation algorithm; extracting the extrapolation algorithm with the smaller standard error and higher error convergence as the optimal extrapolation algorithm, and outputting and displaying the set of prediction values corresponding to the optimal extrapolation method. The present invention can improve the accuracy of prediction results in the process of geotechnical engineering monitoring.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a geotechnical engineering monitoring comprehensive prediction method, device, equipment and computer-readable storage medium. Background Art

[0002] Geotechnical engineering monitoring is to understand the movement of rock and soil, discover signs of damage to geotechnical engineering (such as slopes, foundation pits, mines, etc.), and monitor their deformation, speed, direction, etc., to prevent collapse, landslides, collapses, etc. caused by construction or other factors, and to protect the lives and property of the people.

[0003] Currently, geotechnical engineering monitoring methods primarily use artificial intelligence (AI) to predict geotechnical deformation trends. This AI primarily uses extrapolation to calculate future slope or foundation displacement, facilitating the estimation of geotechnical deformation. However, different extrapolation methods are often suitable for different data trends, local geological conditions, and engineering conditions. Using a single extrapolation method, the prediction results are inaccurate. Summary of the Invention

[0004] The present invention provides a geotechnical engineering monitoring comprehensive prediction method, device, equipment and storage medium, the main purpose of which is to improve the accuracy of prediction results in the geotechnical engineering monitoring process.

[0005] To achieve the above objectives, the present invention provides a comprehensive prediction method for geotechnical engineering monitoring, comprising:

[0006] Obtaining historical displacement information of the target slope within a preset time period, performing multi-algorithm parallel prediction on the historical displacement information using a pre-built extrapolation integrated model, and obtaining a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model;

[0007] Obtaining a set of true measurement values of the target slope after the preset time period, calculating error sequences and standard errors between predicted value sets of various extrapolation algorithms and the true measurement value sets, and calculating error convergence of various extrapolation algorithms based on the error sequences;

[0008] According to the preset balanced screening strategy, the extrapolation algorithm with less standard error and higher error convergence is extracted as the optimal extrapolation algorithm, and the prediction value set corresponding to the optimal extrapolation algorithm is output and displayed.

[0009] Optionally, extracting the extrapolation algorithm with the smaller standard error and higher convergence as the optimal extrapolation algorithm according to a preset balanced screening strategy includes:

[0010] Extracting the extrapolation algorithm whose standard error is less than a preset qualified threshold as a candidate extrapolation algorithm;

[0011] Obtain the error convergence corresponding to each of the candidate extrapolation algorithms, perform a normalization operation on the error convergence to obtain a convergence score, calculate the ratio of the standard error to the convergence score, and extract the effective extrapolation algorithm with the smallest ratio as the optimal extrapolation algorithm.

[0012] Optionally, extracting the extrapolation algorithm with the smaller standard error and higher convergence as the optimal extrapolation algorithm according to a preset balanced screening strategy may further include:

[0013] Calculating the similarity of the fitting curves between each of the predicted value sets and the true measurement value set to obtain a similarity score set;

[0014] Performing a goodness of fit analysis on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and screening a set of effective extrapolation algorithms based on the goodness of fit analysis results;

[0015] Extracting an effective extrapolation algorithm whose standard error is less than a preset qualification threshold from the effective extrapolation algorithm set as a candidate extrapolation algorithm;

[0016] If there are multiple valid extrapolation algorithms whose standard error is less than the qualified threshold, the error convergences of the candidate extrapolation algorithms are compared, and the candidate extrapolation algorithm with the highest error convergence is extracted as the optimal extrapolation algorithm.

[0017] Optionally, performing a goodness of fit analysis on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and screening a set of effective extrapolation algorithms based on the goodness of fit analysis results, includes:

[0018] Extracting the extrapolation algorithm with a similarity score greater than a preset first effective threshold as a primary effective extrapolation algorithm;

[0019] Performing an evaluation operation based on algorithm fit and significance on the primary effective extrapolation algorithm to obtain a goodness of fit evaluation index and a significance test index respectively;

[0020] The absolute value of the difference between the goodness of fit evaluation index and the preset target value is calculated, and the primary effective extrapolation algorithm whose absolute value is less than the preset second effective threshold and whose significance is greater than the preset third effective threshold is extracted as the effective extrapolation algorithm to obtain a set of effective extrapolation algorithms.

[0021] Optionally, the use of a pre-built extrapolation integrated model to perform multi-algorithm parallel prediction on the historical displacement information to obtain a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model includes:

[0022] quantifying the historical displacement information using a pre-built extrapolation integration model to obtain a displacement information vector;

[0023] Performing feature extraction on the displacement information vector to obtain a feature sequence set;

[0024] Utilizing activation functions based on various types of extrapolation algorithms, thread-by-thread asynchronous prediction is performed on the feature sequence set to obtain a set of prediction values corresponding to various types of extrapolation algorithms.

[0025] In order to solve the above problems, the present invention further provides a geotechnical engineering monitoring and comprehensive prediction device, which includes:

[0026] A multi-algorithm identification module is used to obtain historical displacement information of the target slope within a preset time period, and use a pre-built extrapolation integrated model to perform multi-algorithm parallel prediction on the historical displacement information to obtain a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model;

[0027] an error calculation module, configured to obtain a set of true measurement values of the target slope after the preset time period, calculate an error sequence and a standard error between a set of predicted values of various extrapolation algorithms and the set of true measurement values, and calculate error convergence of various extrapolation algorithms based on the error sequence;

[0028] The optimal algorithm extraction module is used to extract the extrapolation algorithm with less standard error and higher error convergence as the optimal extrapolation algorithm according to the preset balanced screening strategy, and output and display the prediction value set corresponding to the optimal extrapolation algorithm.

[0029] Optionally, extracting the extrapolation algorithm with the smaller standard error and higher convergence as the optimal extrapolation algorithm according to a preset balanced screening strategy includes:

[0030] Extracting the extrapolation algorithm whose standard error is less than a preset qualified threshold as a candidate extrapolation algorithm;

[0031] Obtain the error convergence corresponding to each of the candidate extrapolation algorithms, perform a normalization operation on the error convergence to obtain a convergence score, calculate the ratio of the standard error to the convergence score, and extract the effective extrapolation algorithm with the smallest ratio as the optimal extrapolation algorithm.

[0032] Optionally, extracting the extrapolation algorithm with the smaller standard error and higher convergence as the optimal extrapolation algorithm according to a preset balanced screening strategy may further include:

[0033] Calculating the similarity of the fitting curves between each of the predicted value sets and the true measurement value set to obtain a similarity score set;

[0034] Performing a goodness of fit analysis on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and screening a set of effective extrapolation algorithms based on the goodness of fit analysis results;

[0035] Extracting an effective extrapolation algorithm whose standard error is less than a preset qualification threshold from the effective extrapolation algorithm set as a candidate extrapolation algorithm;

[0036] If there are multiple valid extrapolation algorithms whose standard error is less than the qualified threshold, the error convergences of the candidate extrapolation algorithms are compared, and the candidate extrapolation algorithm with the highest error convergence is extracted as the optimal extrapolation algorithm.

[0037] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0038] at least one processor; and,

[0039] a memory communicatively connected to the at least one processor; wherein,

[0040] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned geotechnical engineering monitoring comprehensive prediction method.

[0041] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned comprehensive prediction method for geotechnical engineering monitoring.

[0042] The embodiment of the present invention uses multiple algorithms in parallel to simultaneously predict the historical displacement information of the target slope using multiple types of extrapolation algorithms to obtain various sets of predicted values. The error sequence and standard error between the predicted value sets of each type of extrapolation algorithm and the true measurement value set are then calculated. Based on the error sequence, the error convergence of each type of extrapolation algorithm is calculated, and the extrapolation algorithm with the smaller standard error and higher error convergence is extracted as the optimal extrapolation algorithm. A smaller standard error indicates that the prediction accuracy of the current algorithm is feasible, while a higher error convergence can always ensure that the adaptability of the algorithm to the geographical environment during geotechnical engineering detection is matched. Therefore, the embodiment of the present invention provides a comprehensive prediction method, device, equipment and storage medium for geotechnical engineering monitoring, which can improve the accuracy of prediction results during geotechnical engineering monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a flow chart of a geotechnical engineering monitoring and comprehensive prediction method provided by an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of a detailed flow chart of multi-algorithm parallel calculation in a geotechnical engineering monitoring and comprehensive prediction method provided by an embodiment of the present invention;

[0045] Figure 3 A detailed flowchart of the optimal algorithm screening process in the geotechnical engineering monitoring comprehensive prediction method provided by one embodiment of the present invention;

[0046] Figure 4 A detailed flowchart of another optimal algorithm screening process in the geotechnical engineering monitoring comprehensive prediction method provided by one embodiment of the present invention;

[0047] Figure 5 A functional module diagram of a geotechnical engineering monitoring and comprehensive prediction device provided by one embodiment of the present invention;

[0048] Figure 6 A schematic structural diagram of an electronic device for implementing the geotechnical engineering monitoring comprehensive prediction method provided by one embodiment of the present invention.

[0049] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0051] An embodiment of the present application provides a comprehensive prediction method for geotechnical engineering monitoring. In an embodiment of the present application, the execution subject of the comprehensive prediction method for geotechnical engineering monitoring includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the comprehensive prediction method for geotechnical engineering monitoring can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0052] Reference Figure 1 FIG. 1 is a flow chart of a geotechnical engineering monitoring and comprehensive prediction method according to an embodiment of the present invention. In this embodiment, the geotechnical engineering monitoring and comprehensive prediction method includes:

[0053] S1. Obtain historical displacement information of the target slope within a preset time period, use a pre-built extrapolation integrated model to perform multi-algorithm parallel prediction on the historical displacement information, and obtain a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model.

[0054] In this embodiment of the present invention, the target slope is the edge of the monitored rock and soil, such as a foundation pit or mountain. The historical displacement information is the rock and soil position information of the target slope within a preset time period, such as the past few months of the current year. For example, at the end of November, the historical displacement information may consist of slope position records from January to July, while the predicted value set may consist of predicted rock and soil position information from August to November. The unit time interval for rock and soil monitoring may be daily, weekly, or monthly.

[0055] Furthermore, the extrapolation method integrated model is a neural network model based on N extrapolation methods, wherein the embodiment of the present invention configures N to be 6, and the activation function of the extrapolation method integrated model includes six extrapolation algorithms: exponential curve method, modified exponential curve method, three-sum method, Compertz curve, Logistic curve (growth curve) and polynomial curve.

[0056] It should be noted that the extrapolation method is a commonly used prediction technique in geotechnical engineering design. It is used to calculate the displacement of slope or foundation settlement in the future using relatively little data, facilitating the estimation of geotechnical engineering deformation. However, because different extrapolation methods are often applicable to different data development trends, and the deformation development trends of geotechnical engineering structures under different geological and engineering conditions are often different, the accuracy of the prediction results obtained using a single extrapolation method is often low. Therefore, the embodiment of the present invention uses six extrapolation methods to operate simultaneously, and periodically selects the extrapolation method that is most suitable for the target slope for prediction.

[0057] For more details, please refer to Figure 2 As shown, in the embodiment of the present invention, the pre-built extrapolation integrated model is used to perform multi-algorithm parallel prediction on the historical displacement information to obtain a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model, including:

[0058] S11. quantifying the historical displacement information using a pre-built extrapolation integration model to obtain a displacement information vector;

[0059] S12, performing feature extraction on the displacement information vector to obtain a feature sequence set;

[0060] S13. Perform thread-based asynchronous prediction on the feature sequence set using activation functions based on various types of extrapolation algorithms to obtain prediction value sets corresponding to various types of extrapolation algorithms.

[0061] In an embodiment of the present invention, an encoder is used to perform quantization encoding operations and information extraction operations on the displacement information to obtain a feature sequence set, and then the feature sequence set is sent to decoders containing different extrapolation activation functions through thread-dividing operations, and finally the prediction timing results corresponding to each type of extrapolation algorithm are obtained.

[0062] S2. Obtain a set of true measurement values of the target slope after the preset time period, calculate the error sequence and standard error between the predicted value set of each extrapolation algorithm and the true measurement value set, and calculate the error convergence of each extrapolation algorithm based on the error sequence.

[0063] In the embodiment of the present invention, according to the embodiment scenario in the above step S1, the set of real measurement values is the real geotechnical position information of the target slope from August to November this year.

[0064] In the embodiment of the present invention, the formula for the standard error S is:

[0065]

[0066] Wherein, t in the formula is the time corresponding to all prediction points and monitoring points from August to November, n is the total number of prediction points, is the predicted value at time t, the y t is the actual measured value at time t, is the error value at time t, and is the element value of the error sequence.

[0067] In the embodiment of the present invention, the convergence of the error sequence can be determined by checking whether the mean square error of the error sequence at each time point gradually decreases.

[0068] S3. According to a preset balanced screening strategy, the extrapolation algorithm with a smaller standard error and a higher error convergence is extracted as the optimal extrapolation algorithm, and the predicted value set corresponding to the optimal extrapolation algorithm is output and displayed.

[0069] In the embodiment of the present invention, the balanced screening strategy is to extract the optimal strategy from N extrapolation algorithms from the perspective of standard error and convergence.

[0070] For more details, please refer to Figure 3 As shown, in the embodiment of the present invention, the extrapolation algorithm with smaller standard error and higher convergence is extracted as the optimal extrapolation algorithm according to the preset balanced screening strategy, including:

[0071] S301, extracting the extrapolation algorithm whose standard error is less than a preset qualified threshold as a candidate extrapolation algorithm;

[0072] S302. Obtain the error convergence corresponding to each candidate extrapolation algorithm, perform a normalization operation on the error convergence to obtain a convergence score, calculate the ratio of the standard error to the convergence score, and extract the effective extrapolation algorithm with the smallest ratio as the optimal extrapolation algorithm.

[0073] In the embodiment of the present invention, by checking the standard error, it can be checked whether the current various algorithms can accurately predict, and by querying the error convergence, it can be determined whether the various algorithms are adapted to the geographical environment and change pattern of the target slope.

[0074] In an embodiment of the present invention, the error convergence corresponding to each candidate extrapolation algorithm is normalized, and the standard error is used as the numerator and the convergence score is used as the denominator to perform a ratio. The higher the ratio, the less suitable the algorithm is, and vice versa. Therefore, the effective extrapolation algorithm with the smallest ratio is extracted as the optimal extrapolation algorithm.

[0075] For further reference, Figure 4As shown, in the embodiment of the present invention, extracting the extrapolation algorithm with smaller standard error and higher convergence as the optimal extrapolation algorithm according to the preset balanced screening strategy may further include:

[0076] S311, calculating the similarity of the fitting curves between each of the predicted value sets and the true measurement value set to obtain a similarity score set;

[0077] S312, performing a goodness of fit analysis on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and screening a set of effective extrapolation algorithms based on the goodness of fit analysis results;

[0078] S313, extracting an effective extrapolation algorithm whose standard error is less than a preset qualification threshold from the effective extrapolation algorithm set as a candidate extrapolation algorithm;

[0079] S314. If there are multiple valid extrapolation algorithms whose standard errors are smaller than the qualified threshold, compare the error convergences of the candidate extrapolation algorithms, and extract the candidate extrapolation algorithm with the highest error convergence as the optimal extrapolation algorithm.

[0080] In an embodiment of the present invention, to prevent accidental factors from causing the algorithm's predicted values to be very close to the actual measured values, the similarity of the fitting curves between the predicted value set and the actual measured value set can be used to determine whether each extrapolation algorithm meets the target slope's computational environment. Specifically, in an embodiment of the present invention, the similarity of the fitting curves between each of the predicted value sets and the actual measured value set can be calculated using a dynamic time warping (DTW) algorithm. The DTW algorithm is an algorithm that measures the optimal alignment between two sequences and is commonly used in gesture recognition, data mining, and information retrieval, and will not be further described here.

[0081] Furthermore, in an embodiment of the present invention, the goodness of fit analysis is performed on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and a set of effective extrapolation algorithms is screened based on the goodness of fit analysis results, including:

[0082] Extracting the extrapolation algorithm with a similarity score greater than a preset first effective threshold as a primary effective extrapolation algorithm;

[0083] Performing an evaluation operation based on algorithm fit and significance on the primary effective extrapolation algorithm to obtain a goodness of fit evaluation index and a significance test index respectively;

[0084] The absolute value of the difference between the goodness of fit evaluation index and the preset target value is calculated, and the primary effective extrapolation algorithm whose absolute value is less than the preset second effective threshold and whose significance is greater than the preset third effective threshold is extracted as the effective extrapolation algorithm to obtain a set of effective extrapolation algorithms.

[0085] In accordance with the principle of selecting the best from the best, the embodiment of the present invention not only controls the similarity score, but also performs an evaluation operation based on the algorithm fit and significance, and obtains the goodness of fit evaluation index R 2 , and the significance F value.

[0086] In the embodiment of the present invention, the algorithm evaluation rule is to evaluate the algorithm from two aspects: algorithm fit and significance. In addition, the preset target value is 1.

[0087] Furthermore, the goodness of fit score R 2 The R 2 The closer it is to 1, the better the fitting effect; and the significance score F value is an indicator to verify the overall significance level of the algorithm to compare the pros and cons of the algorithm. The larger the significance F value, the higher the overall significance level of the algorithm.

[0088] The embodiment of the present invention needs to calculate the regression sum of squares SSR and the residual sum of squares SSE corresponding to the predicted value set corresponding to each extrapolation algorithm, and sum the regression squares and the residual sum of squares to obtain the overall sum of squares SST, wherein the calculation formulas of the regression sum of squares SSR and the residual sum of squares SSE are as follows:

[0089]

[0090] Wherein, t is a time point, at time t, is the predicted value at time t, the y t is the actual measurement value at time t; is the actual average value for each month;

[0091] Then we get:

[0092] SST=SSE+SSR

[0093] Then, the goodness of fit score R is obtained through the formula 2 :

[0094]

[0095] And the significance score F can be obtained:

[0096]

[0097] Wherein, α1 and α2 are two degree of freedom parameters.

[0098] Thus, after obtaining the goodness-of-fit evaluation index and significance test index according to the above process, the preset second effective threshold and the preset third effective threshold are used to control and obtain an effective extrapolation algorithm set. The first effective threshold, the second effective threshold, and the third effective threshold can be adjusted according to specific circumstances.

[0099] Finally, the embodiment of the present invention can output and display the prediction curve corresponding to the optimal extrapolation algorithm, for example, visually display it in a curve chart of displacement changing with time on the front-end application interface.

[0100] The embodiment of the present invention uses multiple algorithms in parallel to simultaneously predict the historical displacement information of the target slope using multiple types of extrapolation algorithms to obtain various sets of predicted values. The error sequence and standard error between the predicted value sets of each type of extrapolation algorithm and the true measurement value set are then calculated. Based on the error sequence, the error convergence of each type of extrapolation algorithm is calculated, and the extrapolation algorithm with the smaller standard error and higher error convergence is extracted as the optimal extrapolation algorithm. A smaller standard error indicates that the prediction accuracy of the current algorithm is feasible, while a higher error convergence can always ensure that the adaptability of the algorithm to the geographical environment during geotechnical engineering detection is matched. Therefore, the embodiment of the present invention provides a comprehensive prediction method for geotechnical engineering monitoring, which can improve the accuracy of prediction results during geotechnical engineering monitoring.

[0101] like Figure 5 , which is a functional module diagram of a geotechnical engineering monitoring and comprehensive prediction device provided by an embodiment of the present invention.

[0102] The geotechnical engineering monitoring and prediction device 100 described in the present invention can be installed in an electronic device. Depending on the functionality to be implemented, the geotechnical engineering monitoring and prediction device 100 can include a multi-algorithm identification module 101, an error calculation module 102, and an optimal algorithm extraction module 103. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and is stored in the electronic device's memory.

[0103] In this embodiment, the functions of each module / unit are as follows:

[0104] The multi-algorithm identification module 101 is used to obtain historical displacement information of the target slope within a preset time period, and use a pre-built extrapolation integrated model to perform multi-algorithm parallel prediction on the historical displacement information to obtain a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model;

[0105] The error calculation module 102 is configured to obtain a set of true measurement values of the target slope after the preset time period, calculate an error sequence and a standard error between a set of predicted values of various extrapolation algorithms and the set of true measurement values, and calculate error convergence of various extrapolation algorithms based on the error sequence;

[0106] The optimal algorithm extraction module 103 is used to extract the extrapolation algorithm with smaller standard error and higher error convergence as the optimal extrapolation algorithm according to the preset balanced screening strategy, and output and display the prediction value set corresponding to the optimal extrapolation algorithm.

[0107] In detail, each module described in the geotechnical engineering monitoring comprehensive prediction device 100 described in the embodiment of the present application adopts the same Figures 1 to 4 The technical means are the same as the comprehensive prediction method for geotechnical engineering monitoring described in , and can produce the same technical effects, so they will not be repeated here.

[0108] like Figure 6 FIG. 1 is a schematic structural diagram of an electronic device 1 for implementing a comprehensive prediction method for geotechnical engineering monitoring provided by an embodiment of the present invention.

[0109] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a geotechnical engineering monitoring comprehensive prediction program.

[0110] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device 1, and utilizes various interfaces and lines to connect the various components of the entire electronic device. It executes or executes programs or modules stored in the memory 11 (for example, executing a geotechnical engineering monitoring and comprehensive prediction program, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device and process data.

[0111] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 can also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the memory 11 can also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of a comprehensive prediction program for geotechnical engineering monitoring, etc., but can also be used to temporarily store data that has been output or is to be output.

[0112] The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0113] The communication interface 13 is used for communication between the above-mentioned electronic device 1 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, for displaying information processed in the electronic device and for displaying a visual user interface.

[0114] Figure 6 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 6The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0115] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering the various components. Preferably, the power source may be logically connected to the at least one processor 10 via a power management device, thereby implementing functions such as charging management, discharging management, and power consumption management through the power management device. The power source may further include any components such as one or more DC or AC power sources, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0116] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0117] The geotechnical engineering monitoring comprehensive prediction program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following:

[0118] Obtaining historical displacement information of the target slope within a preset time period, performing multi-algorithm parallel prediction on the historical displacement information using a pre-built extrapolation integrated model, and obtaining a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model;

[0119] Obtaining a set of true measurement values of the target slope after the preset time period, calculating error sequences and standard errors between predicted value sets of various extrapolation algorithms and the true measurement value sets, and calculating error convergence of various extrapolation algorithms based on the error sequences;

[0120] According to the preset balanced screening strategy, the extrapolation algorithm with less standard error and higher error convergence is extracted as the optimal extrapolation algorithm, and the prediction value set corresponding to the optimal extrapolation algorithm is output and displayed.

[0121] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0122] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0123] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0124] Obtaining historical displacement information of the target slope within a preset time period, performing multi-algorithm parallel prediction on the historical displacement information using a pre-built extrapolation integrated model, and obtaining a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model;

[0125] Obtaining a set of true measurement values of the target slope after the preset time period, calculating error sequences and standard errors between predicted value sets of various extrapolation algorithms and the true measurement value sets, and calculating error convergence of various extrapolation algorithms based on the error sequences;

[0126] According to the preset balanced screening strategy, the extrapolation algorithm with less standard error and higher error convergence is extracted as the optimal extrapolation algorithm, and the prediction value set corresponding to the optimal extrapolation algorithm is output and displayed.

[0127] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0128] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0129] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0130] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0131] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0132] Blockchain, as used in this article, refers to a novel application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each block contains information about a batch of online transactions, used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0133] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0134] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A comprehensive prediction method for geotechnical engineering monitoring, characterized in that: The method comprises: Obtaining historical displacement information of the target slope within a preset time period, performing multi-algorithm parallel prediction on the historical displacement information using a pre-built extrapolation integrated model, and obtaining a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model; Obtaining a set of true measurement values of the target slope after the preset time period, calculating error sequences and standard errors between predicted value sets of various extrapolation algorithms and the true measurement value sets, and calculating error convergence of various extrapolation algorithms based on the error sequences; According to a preset balanced screening strategy, extracting the extrapolation algorithm with a smaller standard error and a higher error convergence as the optimal extrapolation algorithm, and outputting and displaying a set of predicted values corresponding to the optimal extrapolation algorithm, wherein, according to the preset balanced screening strategy, extracting the extrapolation algorithm with a smaller standard error and a higher convergence as the optimal extrapolation algorithm includes: Calculating the similarity of the fitting curves between each of the predicted value sets and the true measurement value set to obtain a similarity score set; Performing a goodness of fit analysis on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and screening a set of effective extrapolation algorithms based on the goodness of fit analysis results; Extracting an effective extrapolation algorithm whose standard error is less than a preset qualification threshold from the effective extrapolation algorithm set as a candidate extrapolation algorithm; If there are multiple valid extrapolation algorithms whose standard error is less than the qualified threshold, the error convergences of the candidate extrapolation algorithms are compared, and the candidate extrapolation algorithm with the highest error convergence is extracted as the optimal extrapolation algorithm.

2. The geotechnical engineering monitoring comprehensive prediction method according to claim 1, characterized in that: The step of extracting the extrapolation algorithm with the smaller standard error and higher convergence as the optimal extrapolation algorithm according to the preset balanced screening strategy includes: Extracting the extrapolation algorithm whose standard error is less than a preset qualified threshold as a candidate extrapolation algorithm; Obtain the error convergence corresponding to each of the candidate extrapolation algorithms, perform a normalization operation on the error convergence to obtain a convergence score, calculate the ratio of the standard error to the convergence score, and extract the effective extrapolation algorithm with the smallest ratio as the optimal extrapolation algorithm.

3. The geotechnical engineering monitoring comprehensive prediction method according to claim 2, characterized in that: The goodness of fit analysis is performed on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and a set of effective extrapolation algorithms is screened based on the goodness of fit analysis results, including: Extracting the extrapolation algorithm with a similarity score greater than a preset first effective threshold as a primary effective extrapolation algorithm; Performing an evaluation operation based on algorithm fit and significance on the primary effective extrapolation algorithm to obtain a goodness of fit evaluation index and a significance test index respectively; The absolute value of the difference between the goodness of fit evaluation index and the preset target value is calculated, and the primary effective extrapolation algorithm whose absolute value is less than the preset second effective threshold and whose significance is greater than the preset third effective threshold is extracted as the effective extrapolation algorithm to obtain a set of effective extrapolation algorithms.

4. The geotechnical engineering monitoring comprehensive prediction method according to claim 1, characterized in that: The method of using the pre-built extrapolation integrated model to perform multi-algorithm parallel prediction on the historical displacement information to obtain a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model includes: quantifying the historical displacement information using a pre-built extrapolation integration model to obtain a displacement information vector; Performing feature extraction on the displacement information vector to obtain a feature sequence set; Utilizing activation functions based on various types of extrapolation algorithms, thread-by-thread asynchronous prediction is performed on the feature sequence set to obtain a set of prediction values corresponding to various types of extrapolation algorithms.

5. A geotechnical engineering monitoring and comprehensive prediction device, characterized in that: The device comprises: A multi-algorithm identification module is used to obtain historical displacement information of the target slope within a preset time period, and use a pre-built extrapolation integrated model to perform multi-algorithm parallel prediction on the historical displacement information to obtain a set of prediction values corresponding to each type of extrapolation algorithm in the extrapolation integrated model; an error calculation module, configured to obtain a set of true measurement values of the target slope after the preset time period, calculate an error sequence and a standard error between a set of predicted values of various extrapolation algorithms and the set of true measurement values, and calculate error convergence of various extrapolation algorithms based on the error sequence; The optimal algorithm extraction module is used to extract the extrapolation algorithm with a smaller standard error and a higher error convergence as the optimal extrapolation algorithm according to a preset balanced screening strategy, and output and display the predicted value set corresponding to the optimal extrapolation algorithm, wherein the extraction of the extrapolation algorithm with a smaller standard error and a higher convergence as the optimal extrapolation algorithm according to the preset balanced screening strategy includes: Calculating the similarity of the fitting curves between each of the predicted value sets and the true measurement value set to obtain a similarity score set; Performing a goodness of fit analysis on the extrapolation algorithms whose similarity scores are greater than a preset effective threshold, and screening a set of effective extrapolation algorithms based on the goodness of fit analysis results; Extracting an effective extrapolation algorithm whose standard error is less than a preset qualification threshold from the effective extrapolation algorithm set as a candidate extrapolation algorithm; If there are multiple valid extrapolation algorithms whose standard error is less than the qualified threshold, the error convergences of the candidate extrapolation algorithms are compared, and the candidate extrapolation algorithm with the highest error convergence is extracted as the optimal extrapolation algorithm.

6. The geotechnical engineering monitoring and comprehensive prediction device according to claim 5, characterized in that: The step of extracting the extrapolation algorithm with the smaller standard error and higher convergence as the optimal extrapolation algorithm according to the preset balanced screening strategy includes: Extracting the extrapolation algorithm whose standard error is less than a preset qualified threshold as a candidate extrapolation algorithm; Obtain the error convergence corresponding to each of the candidate extrapolation algorithms, perform a normalization operation on the error convergence to obtain a convergence score, calculate the ratio of the standard error to the convergence score, and extract the effective extrapolation algorithm with the smallest ratio as the optimal extrapolation algorithm.

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the comprehensive prediction method for geotechnical engineering monitoring as described in any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the comprehensive prediction method for geotechnical engineering monitoring according to any one of claims 1 to 4 is implemented.

Images