A reservoir area landslide creep deformation analysis method, device and electronic equipment

Abstract

The embodiments of this specification disclose a method, device and electronic device for analyzing creep deformation of landslides in a reservoir area. The method includes first determining each target deformation identification thread unit in each deformation identification thread unit, and then determining each knowledge segment vector corresponding to the landslide creep deformation data according to each target deformation identification thread unit. Next, the correlation coefficient between each preset category label and the knowledge segment vector set is determined, and further, the target category label corresponding to the landslide creep deformation data is determined based on each correlation coefficient, and finally the landslide creep deformation analysis result is determined. By introducing the knowledge segment vector through the deformation identification thread unit and determining the category label corresponding to the landslide creep deformation data according to the correlation coefficient between each preset category label and the knowledge segment vector set, the purpose of automatically analyzing the creep deformation data of the landslide in the reservoir area is achieved, and the accuracy of the analysis results is improved, meeting the requirements of timely prediction of landslide risks.

Description

Technical Field

[0001] One or more embodiments of this specification relate to the field of intelligent measurement and control technology, and in particular, to a method, device, and electronic equipment for analyzing creep deformation of landslides in reservoir areas. Background Art

[0002] Landslides are common geological hazards. Due to various factors, the strength of reservoir slope rock and soil gradually decreases, or the shear stress within the slope continues to increase, compromising the slope's stability. The weaker upper rock mass within the slope first deforms because its shear strength is less than the shear stress. Creep deformation in the reservoir area can lead to landslides. Therefore, creep deformation is a key indicator for determining the likelihood of a landslide. However, manual identification methods are often used in actual analysis. Because creep deformation of reservoir landslides is a slow process, manual identification often results in inaccurate analysis and judgment due to visual fatigue, making it impossible to predict landslide risks in a timely manner. Summary of the Invention

[0003] The embodiments of this specification provide a method, device, and electronic device for analyzing creep deformation of landslides in a reservoir area. The technical solutions are as follows:

[0004] In a first aspect, an embodiment of this specification provides a method for analyzing creep deformation of landslides in a reservoir area, the method comprising:

[0005] determining at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction;

[0006] Determine the knowledge segment vectors corresponding to the landslide creep deformation data according to each target deformation identification thread unit;

[0007] Determine, based on a mean algorithm, the correlation coefficient between each preset category label and a knowledge segment vector set, wherein the preset category labels include a risk-free label, a low-risk label, a medium-risk label, and a high-risk label, and the knowledge segment vector set is composed of each of the knowledge segment vectors;

[0008] The target category labels corresponding to the landslide creep deformation data are determined based on the correlation coefficients, and the landslide creep deformation analysis results are determined according to the target category labels. The landslide creep deformation analysis results include no risk, low risk, medium risk and high risk.

[0009] In a second aspect, a device for analyzing creep deformation of landslides in a reservoir area is provided, the device comprising:

[0010] a determination module, configured to determine at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction;

[0011] A vector module, configured to determine the knowledge segment vectors corresponding to the landslide creep deformation data according to the target deformation identification thread units;

[0012] an association module, configured to determine, based on a mean algorithm, an association coefficient between each preset category label and a knowledge segment vector set, wherein the preset category labels include a risk-free label, a low-risk label, a medium-risk label, and a high-risk label, and the knowledge segment vector set is composed of each of the knowledge segment vectors;

[0013] An analysis module is used to determine a target category label corresponding to the landslide creep deformation data based on each of the correlation coefficients, and determine a landslide creep deformation analysis result according to the target category label, wherein the landslide creep deformation analysis result includes no risk, low risk, medium risk and high risk.

[0014] In a third aspect, an electronic device is provided, including a device processor and a memory;

[0015] The device processor is connected to the memory;

[0016] The memory is used to store executable program code;

[0017] The device processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0018] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions. When the instructions are executed on a computer or device processor, the computer or device processor executes the method provided in the first aspect or any possible implementation of the first aspect.

[0019] The beneficial effects brought about by the technical solutions provided in some embodiments of this specification include at least the following: first, each target deformation recognition thread unit in each deformation recognition thread unit is determined based on the analysis instruction, and then each knowledge segment vector corresponding to the landslide creep deformation data is determined according to each target deformation recognition thread unit. Then, the correlation coefficient between each preset category label and the knowledge segment vector set is determined based on the mean algorithm, and further, the target category label corresponding to the landslide creep deformation data is determined based on each correlation coefficient, and finally the landslide creep deformation analysis result is determined according to the target category label. By introducing the knowledge segment vector through the deformation recognition thread unit and determining the category label corresponding to the landslide creep deformation data according to the correlation coefficient between each preset category label and the knowledge segment vector set, the purpose of automatically analyzing the landslide creep deformation data in the reservoir area is achieved, and the accuracy of the analysis result is improved, meeting the requirement of timely prediction of landslide risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flowchart of a reservoir landslide creep deformation analysis method provided in the embodiment of this specification;

[0022] Figure 2 A schematic diagram of the structure of a reservoir area landslide creep deformation analysis device provided in an embodiment of this specification;

[0023] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0025] Throughout this specification, the claims, and the accompanying drawings, the terms "first," "second," "third," and the like are used to distinguish between different items, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may include other steps or elements inherent to the process, method, product, or apparatus.

[0026] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of this specification. Various examples may appropriately omit, replace, or add various processes or components. For example, the described methods may be performed in an order different from the order described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined in other examples.

[0027] See also Figure 1 , Figure 1 The figure shows an overall flow chart of a reservoir area landslide creep deformation analysis method provided in an embodiment of this specification.

[0028] like Figure 1As shown, the reservoir area landslide creep deformation analysis method may include at least the following steps:

[0029] Step 101: Determine at least one target deformation recognition thread unit among the deformation recognition thread units based on an analysis instruction.

[0030] In the embodiment of the present specification, the server may receive an analysis instruction sent from a target terminal, and continuously receive collected landslide creep deformation data to analyze the landslide creep deformation in the reservoir area.

[0031] Landslide creep deformation is caused by various factors, including a gradual decrease in slope rock and soil strength or an increase in internal shear stress, which destabilizes the slope. The weaker upper rock mass within the slope first deforms because its shear strength is less than its shear stress. When this deformation reaches the slope surface, intermittent tensile cracks form. These cracks intensify the infiltration of surface water, further expanding the deformation. The trailing cracks widen, and small dislocations appear. Shear cracks also develop on either side of the sliding mass, squeezing the rock and soil near the toe of the slope. At this point, the sliding surface is essentially formed, but not yet fully penetrated. This slow deformation is often overlooked, but once a landslide occurs, it poses a significant risk. Therefore, long-term monitoring of landslide creep deformation is necessary to obtain data.

[0032] After receiving the landslide creep deformation data and analysis instructions collected by the sensor, the server needs to determine each target deformation recognition thread unit in each deformation recognition thread unit according to the analysis instruction.

[0033] The deformation recognition thread unit is essentially a data recognition thread. Simply inputting data into it generates the desired output features. Each deformation recognition thread unit can be configured by professionals in this field, or it can self-learn based on the set data recognition standards. To reduce the computational complexity of the data recognition process while ensuring sufficient feature output, it is necessary to extract each deformation recognition thread unit to obtain each target deformation recognition thread unit. Subsequently, only these target deformation recognition thread units are used to analyze the landslide creep deformation data.

[0034] Optionally, when extracting the target deformation recognition thread unit, a random extraction method or a regular extraction method may be selected, which depends on the analysis instruction received by the server.

[0035] In one embodiment, the determining at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction includes:

[0036] receiving an analysis instruction and determining an extraction rule corresponding to the analysis instruction;

[0037] Extraction is performed in each of the deformation recognition thread units based on the extraction rule to obtain at least one target deformation recognition thread unit.

[0038] In the embodiments of this specification, when extracting target deformation recognition thread units using rule-based extraction, the server first receives an analysis instruction from the target terminal and then determines the extraction rules included in the analysis instruction. Next, extraction is performed across all deformation recognition thread units based on the determined extraction rules to obtain all target deformation recognition thread units. This fixed extraction rule ensures that the extracted target deformation recognition thread units are spaced regularly, strengthening the connections between the knowledge fragment vectors subsequently output by each target deformation recognition thread unit.

[0039] As an example, when there are 24 deformation recognition thread units, the extraction rule corresponding to the analysis instruction is to select a target deformation recognition thread unit every 5 deformation recognition thread units. If the second deformation recognition thread unit is determined as the target deformation recognition thread unit, then the 8th deformation recognition thread unit, the 14th deformation recognition thread unit and the 20th deformation recognition thread unit are correspondingly determined as the target deformation recognition thread units.

[0040] Optionally, when there are 24 deformation recognition thread units, the extraction rule corresponding to the analysis instruction is to select a target deformation recognition thread unit every 7 deformation recognition thread units. If the 8th deformation recognition thread unit is determined as the target deformation recognition thread unit, then the 16th deformation recognition thread unit and the 24th deformation recognition thread unit are correspondingly determined as the target deformation recognition thread units.

[0041] In one possible implementation, before determining the knowledge segment vectors corresponding to the landslide creep deformation data according to the target deformation identification thread units, the method further includes:

[0042] Determining a target training termination evaluation index value of each target deformation recognition thread unit based on a sample training set, wherein the sample training set includes sample deformation data and a sample knowledge fragment vector corresponding to the sample deformation data;

[0043] Training each of the target deformation recognition thread units according to the target training termination evaluation index value to obtain a trained target deformation recognition thread unit;

[0044] The target deformation identification thread units respectively determine the knowledge segment vectors corresponding to the landslide creep deformation data:

[0045] The knowledge segment vectors corresponding to the landslide creep deformation data are determined respectively according to the trained target deformation recognition thread units.

[0046] In an embodiment of the present specification, before using the target deformation recognition thread unit to determine the knowledge segment vector corresponding to the landslide creep deformation data, if each deformation recognition thread unit has not been pre-set by a person skilled in the art, each target deformation recognition thread unit needs to be trained. A sample training set can be first obtained through historical analysis records, wherein the sample training set may include each sample deformation data and its corresponding sample knowledge segment vector. Then, the target training termination evaluation index value is determined based on the sample output and recognition output in the sample training set. Further, each target deformation recognition thread unit is trained based on the target training termination evaluation index value to obtain a trained target deformation recognition thread unit. When each knowledge segment vector corresponding to the landslide creep deformation data is subsequently determined based on each target deformation recognition thread unit, it can be directly obtained through each trained target deformation recognition thread unit.

[0047] In one possible implementation, determining the target training termination evaluation index value of each target deformation recognition thread unit based on the example training set includes:

[0048] For any target deformation recognition thread unit, input each example deformation data in the example training set into the target deformation recognition thread unit to obtain each recognition knowledge fragment vector;

[0049] Determining each recognition evaluation index value based on each recognition knowledge segment vector and the example knowledge segment vector corresponding to each of the example deformation data;

[0050] The recognition evaluation index values ​​are integrated based on the weight fusion method to obtain the target training termination evaluation index value of the target deformation recognition thread unit.

[0051] In an embodiment of the present specification, when determining the target training termination evaluation index value of each target deformation recognition thread unit based on the example training set, for any target deformation recognition thread unit, each example deformation data in the example training set can be first input into the target deformation recognition thread unit to obtain each recognition knowledge segment vector that has not been trained. Then, a ratio calculation is performed between each recognition knowledge segment vector and the example knowledge segment vector corresponding to each example deformation data, and each recognition evaluation index value is determined based on the ratio calculation result. Furthermore, the weight corresponding to each recognition evaluation index value is first determined based on a preset weight rule, and then each recognition evaluation index value is integrated based on a weight fusion method, that is, each recognition evaluation index value is multiplied by the weight and then added to obtain the target training termination evaluation index value of the target deformation recognition thread unit.

[0052] Step 102: Determine each knowledge segment vector corresponding to the landslide creep deformation data according to each target deformation identification thread unit.

[0053] In the embodiments of this specification, since each target deformation recognition thread unit is essentially a data recognition thread, inputting data into it can generate the desired output features. Each deformation recognition thread unit can be configured by those skilled in the art, or it can self-learn based on the configured data recognition standards. Therefore, landslide creep deformation data can be used as input and transmitted to each target deformation recognition thread unit, resulting in the generation of knowledge fragment vectors as output. Each knowledge fragment vector can be represented as a feature vector, including the landslide influencing factor and creep deformation description.

[0054] Step 103: Determine the correlation coefficient between each preset category label and the knowledge segment vector set based on the mean algorithm.

[0055] The preset category labels include a no-risk label, a low-risk label, a medium-risk label, and a high-risk label, and the knowledge segment vector set is composed of the knowledge segment vectors.

[0056] In the embodiment of this specification, after determining the knowledge segment vectors corresponding to the landslide creep deformation data, the correlation coefficient between each pre-set category label and the knowledge segment vector set composed of all knowledge segment vectors can be determined. Subsequently, the category label corresponding to the knowledge segment vector set can be determined by analyzing the correlation coefficient, thereby determining the landslide creep deformation analysis results.

[0057] The preset category labels include no risk, low risk, medium risk, and high risk. Therefore, it is necessary to determine the correlation coefficient between each preset category label and each knowledge segment vector in the knowledge segment vector set. This is defined as the correlation coefficient. A larger correlation coefficient indicates a higher degree of correlation between the landslide creep deformation data to be analyzed and that category label. Next, the correlation coefficients are averaged to obtain the correlation coefficient between each preset category label and the knowledge segment vector set.

[0058] In one possible implementation, the determining of the correlation coefficient between each preset category label and the knowledge segment vector set based on the mean algorithm includes:

[0059] For any preset category label, determining a preset knowledge segment vector corresponding to the preset category label;

[0060] respectively determining the ratio of each of the knowledge fragment vectors in the knowledge fragment vector set to the preset knowledge fragment vector to obtain respective ratio results;

[0061] The mean of each ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

[0062] In the embodiments of this specification, when determining the correlation coefficient between each preset category label and the knowledge segment vector set based on the mean algorithm, for any preset category label, the preset knowledge segment vector corresponding to the preset category label is first determined. Next, a ratio calculation is performed between each knowledge segment vector in the knowledge segment vector set and the preset knowledge segment vector, resulting in a respective ratio result. Furthermore, a mean calculation is performed on all the obtained ratio results, and the mean result is used as the correlation coefficient between the category label and the knowledge segment vector set.

[0063] In one possible implementation, after respectively determining the ratio of each of the knowledge fragment vectors in the knowledge fragment vector set to the preset knowledge fragment vector and obtaining each ratio result, the method further includes:

[0064] Calculating the standard deviation of each ratio result to obtain a standard deviation result;

[0065] Screening the ratio results based on the standard deviation result and the standard deviation threshold to obtain target ratio results;

[0066] The mean of the ratio results is calculated to obtain the correlation coefficient between the category label and the knowledge segment vector set:

[0067] The mean of each target ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

[0068] In the embodiments of this specification, in order to improve the accuracy of subsequent analysis results, after obtaining each ratio result, the large deviation data caused by accidental errors or other factors can be eliminated. First, the standard deviation of all ratio results can be calculated to obtain the standard deviation result. Then, the calculated standard deviation result is compared with the preset standard deviation threshold. If the standard deviation result exceeds the standard deviation threshold, the ratio result with the largest difference from the average value in each ratio result is filtered out until the standard deviation result meets the standard deviation threshold requirement, and the target ratio results after screening are obtained. When performing mean calculation on each ratio result later, it is only necessary to perform mean calculation on each target ratio result after screening.

[0069] Step 104: determining target category labels corresponding to the landslide creep deformation data based on the correlation coefficients, and determining landslide creep deformation analysis results according to the target category labels.

[0070] The landslide creep deformation analysis results include no risk, low risk, medium risk and high risk.

[0071] In the embodiment of this specification, after obtaining the correlation coefficients, the maximum correlation coefficient can be determined, and the target type label corresponding to the landslide creep deformation data can be further queried based on the maximum correlation coefficient, and finally the landslide creep deformation analysis result can be determined based on the target type label.

[0072] As an example, the preset category labels include no-risk label, low-risk label, medium-risk label and high-risk label. If the target category label is determined to be a medium-risk label, the corresponding landslide creep deformation analysis result determines that there is a moderate landslide risk in the reservoir area.

[0073] Optionally, the low risk can be divided into 1-20 levels, the medium risk into 21-40 levels, and the high risk into 41-60 levels. The higher the level, the greater the probability of landslide.

[0074] In one embodiment, determining the target category label corresponding to the landslide creep deformation data based on each correlation coefficient includes:

[0075] Construct a probability distribution queue based on each correlation coefficient;

[0076] The category label corresponding to the maximum correlation coefficient in the possibility distribution queue is determined according to the maximum value method, and the target category label corresponding to the landslide creep deformation data is obtained.

[0077] In the embodiments of this specification, when determining the target category label corresponding to landslide creep deformation data using various correlation coefficients, a probability distribution queue can be first constructed based on the correlation coefficients. This probability distribution queue clearly indicates the degree of correlation between the landslide creep deformation data to be processed and each preset category label, making the subsequent determination of the target category label more convenient and rapid. Next, the maximum correlation coefficient in this probability distribution queue is determined using the maximum value method, and the category label corresponding to this maximum correlation coefficient is further searched to obtain the target category label corresponding to the landslide creep deformation data.

[0078] As an example, the possibility distribution queue is (0.02, 0.45, 0.9, 0.12), where 0.02, 0.45, 0.9, and 0.12 are the correlation coefficients corresponding to the no-risk label, low-risk label, medium-risk label, and high-risk label, respectively. It can be determined that 0.9 is the maximum correlation coefficient, and its corresponding type label is the medium-risk label, which means that there is a moderate landslide risk in the reservoir area.

[0079] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] See next Figure 2 , Figure 2 The schematic diagram of the structure of a reservoir landslide creep deformation analysis device provided in the embodiment of this specification is shown. Figure 2 The reservoir area landslide creep deformation analysis device shown is used to perform this application Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0081] like Figure 2 As shown, the reservoir area landslide creep deformation analysis device may at least include:

[0082] A determination module 201 is configured to determine at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction;

[0083] A vector module 202 is configured to determine the knowledge segment vectors corresponding to the landslide creep deformation data according to the target deformation identification thread units;

[0084] An association module 203 is configured to determine, based on a mean value algorithm, an association coefficient between each preset category label and a knowledge segment vector set, wherein the preset category labels include a risk-free label, a low-risk label, a medium-risk label, and a high-risk label, and the knowledge segment vector set is composed of each of the knowledge segment vectors;

[0085] The analysis module 204 is configured to determine target category labels corresponding to the landslide creep deformation data based on the correlation coefficients, and determine landslide creep deformation analysis results according to the target category labels, wherein the landslide creep deformation analysis results include no risk, low risk, medium risk, and high risk.

[0086] In one embodiment, the determining module 201 is specifically configured to:

[0087] receiving an analysis instruction and determining an extraction rule corresponding to the analysis instruction;

[0088] Extraction is performed in each of the deformation recognition thread units based on the extraction rule to obtain at least one target deformation recognition thread unit.

[0089] In one embodiment, the determining module 201 is further configured to:

[0090] Determining a target training termination evaluation index value of each target deformation recognition thread unit based on a sample training set, wherein the sample training set includes sample deformation data and a sample knowledge fragment vector corresponding to the sample deformation data;

[0091] Training each of the target deformation recognition thread units according to the target training termination evaluation index value to obtain a trained target deformation recognition thread unit;

[0092] The target deformation identification thread units respectively determine the knowledge segment vectors corresponding to the landslide creep deformation data:

[0093] The knowledge segment vectors corresponding to the landslide creep deformation data are determined respectively according to the trained target deformation recognition thread units.

[0094] In one embodiment, the determining module 201 is further configured to:

[0095] For any target deformation recognition thread unit, input each example deformation data in the example training set into the target deformation recognition thread unit to obtain each recognition knowledge fragment vector;

[0096] Determining each recognition evaluation index value based on each recognition knowledge segment vector and the example knowledge segment vector corresponding to each of the example deformation data;

[0097] The recognition evaluation index values ​​are integrated based on the weight fusion method to obtain the target training termination evaluation index value of the target deformation recognition thread unit.

[0098] In one embodiment, the association module 203 is specifically configured to:

[0099] For any preset category label, determining a preset knowledge segment vector corresponding to the preset category label;

[0100] respectively determining the ratio of each of the knowledge fragment vectors in the knowledge fragment vector set to the preset knowledge fragment vector to obtain respective ratio results;

[0101] The mean of each ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

[0102] In one embodiment, the association module 203 is further configured to:

[0103] Calculating the standard deviation of each ratio result to obtain a standard deviation result;

[0104] Screening the ratio results based on the standard deviation result and the standard deviation threshold to obtain target ratio results;

[0105] The mean of the ratio results is calculated to obtain the correlation coefficient between the category label and the knowledge segment vector set:

[0106] The mean of each target ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

[0107] In one embodiment, the analysis module 204 is specifically configured to:

[0108] Construct a probability distribution queue based on each correlation coefficient;

[0109] The category label corresponding to the maximum correlation coefficient in the possibility distribution queue is determined according to the maximum value method, and the target category label corresponding to the landslide creep deformation data is obtained.

[0110] Those skilled in the art will clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently perform or cooperate with other components to perform specific functions, where the hardware can be, for example, a field-programmable gate array (FPGA) or an integrated circuit (IC).

[0111] Each processing unit and / or module in the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0112] See next Figure 3 , Figure 3 A schematic structural diagram of an electronic device provided in an embodiment of this specification is shown.

[0113] like Figure 3 As shown, the electronic device 300 may include: at least one device processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 and at least one communication bus 302 .

[0114] The communication bus 302 may be used to implement the connection and communication between the above components.

[0115] The user interface 303 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0116] The network interface 304 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, and the like.

[0117] Among them, the device processor 301 may include one or more processing cores. The device processor 301 uses various interfaces and lines to connect the various parts of the entire electronic device 300, and executes various functions of the electronic device 300 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the device processor 301 can be implemented in at least one hardware form of DSP, FPGA, PLA. The device processor 301 can integrate one or a combination of CPU, GPU and modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to handle wireless communications. It is understandable that the above-mentioned modem may not be integrated into the device processor 301, but may be implemented separately through a chip.

[0118] Among them, the memory 305 may include RAM and ROM. Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned device processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0119] Specifically, the device processor 301 may be used to call the reservoir area landslide creep deformation analysis application stored in the memory 305 and specifically perform the following operations:

[0120] determining at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction;

[0121] Determine the knowledge segment vectors corresponding to the landslide creep deformation data according to each target deformation identification thread unit;

[0122] Determine, based on a mean algorithm, the correlation coefficient between each preset category label and a knowledge segment vector set, wherein the preset category labels include a risk-free label, a low-risk label, a medium-risk label, and a high-risk label, and the knowledge segment vector set is composed of each of the knowledge segment vectors;

[0123] The target category labels corresponding to the landslide creep deformation data are determined based on the correlation coefficients, and the landslide creep deformation analysis results are determined according to the target category labels. The landslide creep deformation analysis results include no risk, low risk, medium risk and high risk.

[0124] As an optional embodiment of this specification, the determining at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction includes:

[0125] receiving an analysis instruction and determining an extraction rule corresponding to the analysis instruction;

[0126] Extraction is performed in each of the deformation recognition thread units based on the extraction rule to obtain at least one target deformation recognition thread unit.

[0127] As an optional embodiment of this specification, before determining the knowledge segment vectors corresponding to the landslide creep deformation data according to the target deformation identification thread units, the method further includes:

[0128] Determining a target training termination evaluation index value of each target deformation recognition thread unit based on a sample training set, wherein the sample training set includes sample deformation data and a sample knowledge fragment vector corresponding to the sample deformation data;

[0129] Training each of the target deformation recognition thread units according to the target training termination evaluation index value to obtain a trained target deformation recognition thread unit;

[0130] The target deformation identification thread units respectively determine the knowledge segment vectors corresponding to the landslide creep deformation data:

[0131] The knowledge segment vectors corresponding to the landslide creep deformation data are determined respectively according to the trained target deformation recognition thread units.

[0132] As an optional embodiment of this specification, the determining of the target training termination evaluation index value of each target deformation recognition thread unit based on the example training set includes:

[0133] For any target deformation recognition thread unit, input each example deformation data in the example training set into the target deformation recognition thread unit to obtain each recognition knowledge fragment vector;

[0134] Determining each recognition evaluation index value based on each recognition knowledge segment vector and the example knowledge segment vector corresponding to each of the example deformation data;

[0135] The recognition evaluation index values ​​are integrated based on the weight fusion method to obtain the target training termination evaluation index value of the target deformation recognition thread unit.

[0136] As an optional embodiment of this specification, the determination of the correlation coefficient between each preset category label and the knowledge segment vector set based on the mean algorithm includes:

[0137] For any preset category label, determining a preset knowledge segment vector corresponding to the preset category label;

[0138] respectively determining the ratio of each of the knowledge fragment vectors in the knowledge fragment vector set to the preset knowledge fragment vector to obtain respective ratio results;

[0139] The mean of each ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

[0140] As an optional embodiment of this specification, after determining the ratio of each knowledge segment vector in the knowledge segment vector set to the preset knowledge segment vector and obtaining each ratio result, the method further includes:

[0141] Calculating the standard deviation of each ratio result to obtain a standard deviation result;

[0142] Screening the ratio results based on the standard deviation result and the standard deviation threshold to obtain target ratio results;

[0143] The mean of the ratio results is calculated to obtain the correlation coefficient between the category label and the knowledge segment vector set:

[0144] The mean of each target ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

[0145] As an optional embodiment of this specification, the determining of the target category label corresponding to the landslide creep deformation data based on each of the correlation coefficients includes:

[0146] Construct a probability distribution queue based on each correlation coefficient;

[0147] The category label corresponding to the maximum correlation coefficient in the possibility distribution queue is determined according to the maximum value method, and the target category label corresponding to the landslide creep deformation data is obtained.

[0148] The embodiments of this specification also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic or optical card, a nanosystem (including a molecular memory IC), or any other type of medium or device suitable for storing instructions and / or data.

[0149] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0150] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0151] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0152] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0153] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or 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 software functional units.

[0154] 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 memory. 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. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

[0155] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0156] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A reservoir area landslide creep deformation analysis method, characterized in that: The method comprises: determining at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction; Determine the knowledge segment vectors corresponding to the landslide creep deformation data according to each target deformation identification thread unit; Determine, based on a mean algorithm, the correlation coefficient between each preset category label and a knowledge segment vector set, wherein the preset category labels include a risk-free label, a low-risk label, a medium-risk label, and a high-risk label, and the knowledge segment vector set is composed of each of the knowledge segment vectors; Determining target category labels corresponding to the landslide creep deformation data based on the correlation coefficients, and determining landslide creep deformation analysis results according to the target category labels, wherein the landslide creep deformation analysis results include no risk, low risk, medium risk, and high risk; The determination of the correlation coefficient between each preset category label and the knowledge fragment vector set based on the mean algorithm includes: For any preset category label, determining a preset knowledge segment vector corresponding to the preset category label; respectively determining the ratio of each of the knowledge fragment vectors in the knowledge fragment vector set to the preset knowledge fragment vector to obtain respective ratio results; Calculating the standard deviation of each ratio result to obtain a standard deviation result; Screening the ratio results based on the standard deviation result and the standard deviation threshold to obtain target ratio results; The mean of each target ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

2. The method according to claim 1, characterized in that The determining, based on the analysis instruction, at least one target deformation recognition thread unit among the deformation recognition thread units comprises: receiving an analysis instruction and determining an extraction rule corresponding to the analysis instruction; Extraction is performed in each of the deformation recognition thread units based on the extraction rule to obtain at least one target deformation recognition thread unit.

3. The method according to claim 1, characterized in that Before respectively determining the knowledge segment vectors corresponding to the landslide creep deformation data according to the target deformation identification thread units, the method further includes: Determining a target training termination evaluation index value of each target deformation recognition thread unit based on a sample training set, wherein the sample training set includes sample deformation data and a sample knowledge fragment vector corresponding to the sample deformation data; Training each target deformation recognition thread unit according to each target training termination evaluation index value to obtain a trained target deformation recognition thread unit; The target deformation identification thread units respectively determine the knowledge segment vectors corresponding to the landslide creep deformation data: The knowledge segment vectors corresponding to the landslide creep deformation data are determined respectively according to the trained target deformation recognition thread units.

4. The method according to claim 3, characterized in that The determining of the target training termination evaluation index value of each target deformation recognition thread unit based on the example training set includes: For any target deformation recognition thread unit, input each example deformation data in the example training set into the target deformation recognition thread unit to obtain each recognition knowledge fragment vector; Determining each recognition evaluation index value based on each recognition knowledge segment vector and the example knowledge segment vector corresponding to each of the example deformation data; The recognition evaluation index values ​​are integrated based on the weight fusion method to obtain the target training termination evaluation index value of the target deformation recognition thread unit.

5. The method according to claim 1, wherein The determining of the target category label corresponding to the landslide creep deformation data based on each of the correlation coefficients includes: Construct a probability distribution queue based on each correlation coefficient; The category label corresponding to the maximum correlation coefficient in the possibility distribution queue is determined according to the maximum value method, and the target category label corresponding to the landslide creep deformation data is obtained.

6. A reservoir area landslide creep deformation analysis device, characterized in that: The device comprises: a determination module, configured to determine at least one target deformation recognition thread unit among the deformation recognition thread units based on the analysis instruction; A vector module, configured to determine the knowledge segment vectors corresponding to the landslide creep deformation data according to the target deformation identification thread units; an association module, configured to determine, based on a mean algorithm, an association coefficient between each preset category label and a knowledge segment vector set, wherein the preset category labels include a risk-free label, a low-risk label, a medium-risk label, and a high-risk label, and the knowledge segment vector set is composed of each of the knowledge segment vectors; An analysis module for determining a target category label corresponding to the landslide creep deformation data based on each of the correlation coefficients, and determining a landslide creep deformation analysis result according to the target category label, wherein the landslide creep deformation analysis result includes no risk, low risk, medium risk, and high risk; The association module is specifically used for: For any preset category label, determining a preset knowledge segment vector corresponding to the preset category label; respectively determining the ratio of each of the knowledge fragment vectors in the knowledge fragment vector set to the preset knowledge fragment vector to obtain respective ratio results; Calculating the standard deviation of each ratio result to obtain a standard deviation result; Screening the ratio results based on the standard deviation result and the standard deviation threshold to obtain target ratio results; The mean of each target ratio result is calculated to obtain the correlation coefficient between the category label and the knowledge fragment vector set.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or processor to execute the steps of the method according to any one of claims 1 to 5.

Images