Landslide state determination method based on clustering algorithm and related device

Abstract

The embodiment of the application provides a landslide state determination method based on a clustering algorithm and related devices, the method comprises the following steps: obtaining displacement amounts of K monitoring points in a vertical monitoring hole of a slope within a preset time interval to obtain K time-history displacement amounts; performing clustering processing on the K monitoring points according to the K time-history displacement amounts to obtain a clustering processing result; determining M category mutation monitoring points according to the clustering processing result, wherein M is an integer less than or equal to K; and determining a landslide state of the slope according to a credibility of the M category mutation monitoring points and a number of the category mutation monitoring points. The application can determine the landslide state of the slope based on the time-history displacement amounts of the monitoring points in the vertical monitoring hole of the slope, thereby improving the efficiency of determining the landslide state of the slope.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a landslide state determination method based on a clustering algorithm and related devices. BACKGROUND

[0002] Among many geological disasters, landslides have always been an important content of engineering geology research due to their large number, strong destructive nature, and large potential economic losses. Since the early and mid-20th century, the world population has been growing, human activities have gradually expanded the space range, and engineering activities supported by technical and economic conditions have continuously disturbed the geological environment. Global climate change has formed extreme abnormal rainfall, which has made the frequency of landslide disasters, especially large-scale landslide disasters, higher and higher, and the economic losses and casualties caused by them have also been increasing.

[0003] The existing landslide state determination is usually performed by professional personnel analyzing and judging the monitoring data, which results in low efficiency of landslide state determination of the slope. SUMMARY

[0004] The embodiments of the present application provide a landslide state determination method based on a clustering algorithm and related devices, which can determine the landslide state of the slope based on the displacement of the monitoring points of the slope, thereby improving the efficiency of landslide state determination of the slope.

[0005] The first aspect of the embodiments of the present application provides a landslide state determination method based on a clustering algorithm, which comprises:

[0006] Obtaining the displacement of K monitoring points in a preset time interval in a vertical monitoring hole of a slope to obtain K time-history displacements;

[0007] Performing clustering processing on the K monitoring points according to the K time-history displacements to obtain a clustering processing result;

[0008] According to the clustering processing result, determining M category mutation monitoring points, M being an integer less than or equal to K;

[0009] According to the reliability of the M category mutation monitoring points and the number of the category mutation monitoring points, determining the landslide state of the slope.

[0010] In combination with the first aspect, in one possible implementation manner, the performing clustering processing on the K monitoring points according to the K time-history displacements to obtain a clustering processing result comprises:

[0011] Determining an initial first clustering center and an initial second clustering center, the initial first clustering center and the initial second clustering center being time-history displacements randomly selected from the K time-history displacements;

[0012] obtaining a first distance set and a second distance set, the first distance set being a distance between each of the K time-history displacement amounts and the initial first cluster center, and the second distance set being a distance between each of the K time-history displacement amounts and the initial second cluster center;

[0013] determining a first type of monitoring point set and a second type of monitoring point set according to the first distance set and the second distance set, a monitoring point in the first type of monitoring point set having a distance to the initial first cluster center smaller than a distance to the initial second cluster center, and a monitoring point in the second type of monitoring point set having a distance to the initial second cluster center smaller than a distance to the initial first cluster center;

[0014] determining a new first cluster center according to a mean value of time-history displacements corresponding to monitoring points in the first type of monitoring point set, and determining a new second cluster center according to time-history displacements corresponding to monitoring points in the second type of monitoring point set;

[0015] repeating the steps of obtaining the new first cluster center and the new second cluster center until final first and second cluster centers are determined, the final first cluster center corresponding to a monitoring point set having a mean value of time-history displacements of a constant value, and the final second cluster center corresponding to a monitoring point set having a mean value of time-history displacements of a constant value;

[0016] the monitoring point set corresponding to the final first cluster center is determined as the first type of monitoring point, and the monitoring point set corresponding to the final second cluster center is determined as the second type of monitoring point, to obtain a clustering processing result.

[0017] In combination with the first aspect, in a possible implementation manner, a distance between a time-history displacement amount and the initial first cluster center or the initial second cluster center is determined by a method shown in the following formula:

[0018]

[0019] wherein u it is the time-history displacement amount of the ith monitoring point at the tth time; u ct is the initial first cluster center or u ct is the initial second cluster center, and u is the displacement amount of the tth time.

[0020] In combination with the first aspect, in a possible implementation manner, the new first cluster center and the new second cluster center are determined by a method shown in the following formula:

[0021]

[0022]

[0023] wherein, u c1 is a new first cluster center, u c2 is a new second cluster center, S1 is a time history displacement corresponding to a monitoring point in the first set of monitoring points, S2 is a time history displacement corresponding to a monitoring point in the second set of monitoring points, N1 is a number of monitoring points in the first set of monitoring points, and N2 is a number of monitoring points in the second set of monitoring points.

[0024] With reference to the first aspect, in a possible implementation manner, the method further includes:

[0025] obtaining a mutation displacement amount of the category mutation monitoring point at an ending moment of a preset time interval, and obtaining a mutation displacement amount threshold value;

[0026] determining a credibility of the category mutation monitoring point according to the mutation displacement amount and the mutation displacement amount threshold value;

[0027] determining a credibility of the category mutation monitoring point according to the mutation displacement amount and the mutation displacement amount threshold value, including:

[0028] determining the credibility of the category mutation monitoring point by a method shown in the following formula:

[0029]

[0030] wherein, Δu cr is the mutation displacement amount, Δu th is the mutation displacement amount threshold value, and R is the credibility of the category mutation monitoring point.

[0031] With reference to the first aspect, in a possible implementation manner, the obtaining of the mutation displacement amount threshold value includes:

[0032] obtaining a length of a monitoring unit at the category mutation monitoring point, and obtaining a maximum shear strain of a plastic stage of a soil material at the category mutation monitoring point;

[0033] determining the mutation displacement amount threshold value according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material;

[0034] determining the mutation displacement amount threshold value according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material, including:

[0035] determining the mutation displacement threshold value by a method shown in the following formula:

[0036] Δu th = l e γ a

[0037] wherein, l e is the length of the monitoring unit, γ a is the maximum shear strain of the plastic stage of the soil material, Δu th is the threshold value of the sudden displacement amount.

[0038] In combination with the first aspect, in a possible implementation, the determining of the landslide state of the slope according to the credibility of the M category sudden change monitoring points and the number of the category sudden change monitoring points comprises:

[0039] if M is greater than a preset number threshold, determining that the landslide state of the slope is a first landslide state;

[0040] if M is less than or equal to the preset number threshold and the credibility is less than 100%, determining that the landslide state of the slope is a second landslide state;

[0041] if M is less than or equal to the preset number threshold and the credibility is greater than or equal to 100%, determining that the landslide state of the slope is a third landslide state.

[0042] The second aspect of the embodiment of the present application provides a landslide state determination device based on a clustering algorithm, the device comprising:

[0043] an acquisition unit configured to acquire displacement amounts of K monitoring points in a vertical monitoring hole of a slope within a preset time interval to obtain K time-history displacement amounts;

[0044] a processing unit configured to perform clustering processing on the K monitoring points according to the K time-history displacement amounts to obtain a clustering processing result;

[0045] a first determination unit configured to determine the M category sudden change monitoring points according to the clustering processing result, M being an integer less than or equal to K;

[0046] a second determination unit configured to determine the landslide state of the slope according to the credibility of the M category sudden change monitoring points and the number of the category sudden change monitoring points.

[0047] In combination with the second aspect, in a possible implementation, the processing unit is configured to:

[0048] determine an initial first clustering center and an initial second clustering center, the initial first clustering center and the initial second clustering center being time-history displacement amounts randomly selected from the K time-history displacement amounts;

[0049] obtaining a first distance set and a second distance set, the first distance set being a distance between each of the K time-history displacement amounts and the initial first clustering center, and the second distance set being a distance between each of the K time-history displacement amounts and the initial second clustering center;

[0050] determining a first type of monitoring point set and a second type of monitoring point set according to the first distance set and the second distance set, a monitoring point in the first type of monitoring point set having a distance to the initial first clustering center smaller than a distance to the initial second clustering center, and a monitoring point in the second type of monitoring point set having a distance to the initial second clustering center smaller than a distance to the initial first clustering center;

[0051] determining a new first clustering center according to a mean value of time-history displacements corresponding to monitoring points in the first type of monitoring point set, and determining a new second clustering center according to time-history displacements corresponding to monitoring points in the second type of monitoring point set;

[0052] repeating the steps of obtaining the new first clustering center and the new second clustering center until a final first clustering center and a final second clustering center are determined, the final first clustering center corresponding to a monitoring point set in which monitoring points have a mean value of time-history displacements as a constant value, and the final second clustering center corresponding to a monitoring point set in which monitoring points have a mean value of time-history displacements as a constant value;

[0053] the monitoring point set corresponding to the final first clustering center is determined as a first type of monitoring point, and the monitoring point set corresponding to the final second clustering center is determined as a second type of monitoring point, to obtain a clustering processing result.

[0054] In combination with the second aspect, in a possible implementation manner, the apparatus is further configured to:

[0055] determine the distance between the time-history displacement amount and the initial first clustering center and the initial second clustering center by a method shown in the following formula:

[0056]

[0057] wherein, u it is the time-history displacement amount of the i th monitoring point at the t th time; u ct is the initial first clustering center or u ct is the initial second clustering center, and is the displacement amount of the i th monitoring point at the t th time.

[0058] In combination with the second aspect, in a possible implementation manner, the apparatus is further configured to:

[0059] determine the new first clustering center and the new second clustering center by a method shown in the following formula:

[0060]

[0061]

[0062] wherein u c1 is the new first cluster center, u c2 is the new second cluster center, S1 is the time history displacement of the monitoring point in the first type monitoring point set, S2 is the time history displacement of the monitoring point in the second type monitoring point set, N1 is the number of monitoring points in the first type monitoring point set, and N2 is the number of monitoring points in the second type monitoring point set.

[0063] With reference to the second aspect, in a possible implementation manner, the apparatus is further configured to:

[0064] obtain a mutation displacement amount of the category mutation monitoring point at an ending moment of a preset time interval, and obtain a mutation displacement amount threshold value;

[0065] determine a credibility of the category mutation monitoring point according to the mutation displacement amount and the mutation displacement amount threshold value;

[0066] In the aspect of determining the credibility of the category mutation monitoring point according to the mutation displacement amount and the mutation displacement amount threshold value, the apparatus is further configured to:

[0067] determine the credibility of the category mutation monitoring point by a method shown in the following formula:

[0068]

[0069] wherein Δu cr is the mutation displacement amount, Δu th is the mutation displacement amount threshold value, and R is the credibility of the category mutation monitoring point.

[0070] With reference to the second aspect, in a possible implementation manner, in the aspect of obtaining the mutation displacement amount threshold value, the apparatus is further configured to:

[0071] obtain a length of a monitoring unit at the category mutation monitoring point, and obtain a maximum shear strain of a plastic stage of a soil material at the category mutation monitoring point;

[0072] determine the mutation displacement amount threshold value according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material;

[0073] In the aspect of determining the mutation displacement amount threshold value according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material, the apparatus is configured to:

[0074] The mutation displacement threshold is determined by a method shown in the following formula:

[0075] Δu th =l e γ a

[0076] wherein, l e is the length of the monitoring unit, γ a is the maximum shear strain of the plastic stage of the soil material, Δu th is the mutation displacement threshold.

[0077] In combination with the second aspect, in a possible implementation manner, the second determining unit is configured to:

[0078] if M is greater than the preset quantity threshold, determining that the landslide state of the slope is a first landslide state;

[0079] if M is less than or equal to the preset quantity threshold, and the credibility is less than 100%, determining that the landslide state of the slope is a second landslide state;

[0080] if M is less than or equal to the preset quantity threshold, and the credibility is greater than or equal to 100%, determining that the landslide state of the slope is a third landslide state.

[0081] The third aspect of the embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected with each other, wherein the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0082] The fourth aspect of the embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0083] The fifth aspect of the embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application. The computer program product can be a software installation package.

[0084] The embodiment of the present application has at least the following beneficial effects:

[0085] The displacement of K monitoring points in a vertical monitoring hole of a slope at a preset time interval is obtained to obtain K time-history displacement amounts, the K monitoring points are clustered according to the K time-history displacement amounts to obtain a clustering result, the M category mutation monitoring points are determined according to the clustering result, M is an integer less than or equal to K, and the landslide state of the slope is determined according to the reliability of the M category mutation monitoring points and the number of the category mutation monitoring points, so that the landslide state of the slope can be determined based on the displacement of the monitoring points of the slope, thereby improving the efficiency of determining the landslide state of the slope. BRIEF DESCRIPTION OF DRAWINGS

[0086] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0087] Figure 1A A flowchart of a landslide state determination method based on a clustering algorithm is provided for the embodiments of the present application;

[0088] Figure 1B A schematic diagram of an array MEMS deep displacement monitoring device is provided for the embodiments of the present application;

[0089] Figure 1C A clustering algorithm based on time-history displacement amounts of slope monitoring points is provided for the embodiments of the present application;

[0090] Figure 1D A setting diagram of a monitoring position is provided for the embodiments of the present application;

[0091] Figure 1E Monitoring data curve diagrams of each stage of monitoring position 1 are provided for the embodiments of the present application;

[0092] Figure 1F Monitoring data curve diagrams of each stage of monitoring position 2 are provided for the embodiments of the present application;

[0093] Figure 2 A structure diagram of a terminal is provided for the embodiments of the present application;

[0094] Figure 3 A structure diagram of a landslide state determination device based on a clustering algorithm is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0095] With reference to the drawings and embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0096] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device including a series of steps or units is not limited to the listed steps or units, but can optionally further include steps or units not listed, or can optionally further include other steps or units inherent to the process, method, product, or device.

[0097] In the present application, the phrase "embodiment" means that the specific features, structures, or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present application can be combined with other embodiments.

[0098] Please refer to Figure 1A , Figure 1A A flowchart of a landslide state determination method based on a clustering algorithm is provided for the embodiments of the present application. As shown in Figure 1A , the method comprises:

[0099] 101, obtaining displacement amounts of K monitoring points in a slope vertical monitoring hole within a preset time interval to obtain K time-history displacement amounts.

[0100] The time-history displacement amounts can be obtained by the whole array MEMS deep displacement monitoring device. As shown in Figure 1B , Figure 1B A schematic diagram of an array MEMS deep displacement monitoring device is shown. The array MEMS deep displacement monitoring device comprises a plurality of monitoring units, which are connected in series from the bottom of the hole to the hole opening. Each monitoring unit has a MEMS displacement sensor built-in, and the monitoring units are flexibly connected.

[0101] A monitoring hole is drilled vertically in the slope body, in particular, the monitoring hole must be drilled below the bedrock. The MEMS deep displacement monitoring device is placed in the vertical monitoring hole, so that the displacement data at each depth in the monitoring hole can be monitored and obtained. The displacement data can be time-history displacement amounts.

[0102] The preset time interval is set by experience or historical data. For example, the preset time interval is 8 days, etc.

[0103] 102. Cluster the K monitoring points according to the K time-history displacement amounts to obtain a clustering result.

[0104] The K monitoring points can be clustered by a clustering center, which is initially randomly selected and gradually optimized, and finally a usable clustering center is obtained, and the time-history displacement mean of the monitoring points in the monitoring point set corresponding to the final clustering center is a constant value.

[0105] 103. Determine M category mutation monitoring points according to the clustering result, where M is an integer less than or equal to K.

[0106] Whether the category of a monitoring point mutates or not can be determined according to the clustering result, and if the category of the monitoring point changes, the monitoring point is determined as a category mutation monitoring point.

[0107] 104. Determine the landslide state of the slope according to the reliability of the M category mutation monitoring points and the number of the category mutation monitoring points.

[0108] The reliability can be determined according to the mutation displacement amount of the category mutation monitoring point and a preset mutation displacement amount threshold.

[0109] The landslide state of the slope can be determined according to whether the number of the mutation monitoring points exceeds a preset number threshold and whether the reliability is greater than a preset reliability threshold.

[0110] In this example, the K time-history displacement amounts of the K monitoring points of the slope within a preset time interval are obtained, the K monitoring points are clustered according to the K time-history displacement amounts to obtain a clustering result, M category mutation monitoring points are determined according to the clustering result, where M is an integer less than or equal to K, and the landslide state of the slope is determined according to the reliability of the M category mutation monitoring points and the number of the category mutation monitoring points. The landslide state of the slope can be determined based on the displacement amounts of the monitoring points of the vertical monitoring hole of the slope, thereby improving the efficiency of determining the landslide state of the slope.

[0111] In one possible implementation, a possible method of clustering the K monitoring points according to the K time-history displacement amounts to obtain a clustering result includes:

[0112] A1, determining an initial first clustering center and an initial second clustering center, the initial first clustering center and the initial second clustering center being time history displacement amounts randomly selected from the K time history displacement amounts;

[0113] A2, obtaining a first distance set and a second distance set, the first distance set being a distance between each time history displacement amount in the K time history displacement amounts and the initial first clustering center, the second distance set being a distance between each time history displacement amount in the K time history displacement amounts and the initial second clustering center;

[0114] A3, determining a first type of monitoring point set and a second type of monitoring point set according to the first distance set and the second distance set, a monitoring point in the first type of monitoring point set having a distance to the initial first clustering center smaller than a distance to the initial second clustering center, a monitoring point in the second type of monitoring point set having a distance to the initial second clustering center smaller than a distance to the initial first clustering center;

[0115] A4, determining a new first clustering center according to a mean value of time history displacement of a monitoring point in the first type of monitoring point set, and determining a new second clustering center according to time history displacement of a monitoring point in the second type of monitoring point set;

[0116] A5, repeatedly performing the steps of obtaining the new first clustering center and the new second clustering center until a final first clustering center and a final second clustering center are determined, the final first clustering center corresponding to a monitoring point set in which a mean value of time history displacement of the monitoring points is a constant value, and the final second clustering center corresponding to a monitoring point set in which a mean value of time history displacement of the monitoring points is a constant value;

[0117] A6, the monitoring point set corresponding to the final first clustering center being determined as the first type of monitoring point, and the monitoring point set corresponding to the final second clustering center being determined as the second type of monitoring point, to obtain a clustering processing result.

[0118] Wherein, a mean value of time history displacement of a monitoring point in the first type of monitoring point set can be determined as a new first clustering center, and a mean value of time history displacement of a monitoring point in the second type of monitoring point set can be determined as a new second clustering center.

[0119] The final clustering center is determined through iteration, and the first type of monitoring point and the second type of monitoring point are obtained according to the final clustering center, so as to obtain a clustering result, thereby improving the accuracy of clustering.

[0120] In one possible implementation, the distance between the time history displacement amount and the initial first clustering center and the initial second clustering center is determined by a method shown in the following formula:

[0121]

[0122] wherein u it is the time-history displacement of the i-th monitoring point at the t-th time; u ct is the initial first cluster center or u ct is the initial second cluster center, and u

[0123] The method for determining the distance between the time-history displacement and the initial second cluster center is the same as the method for determining the distance between the time-history displacement and the initial first cluster center.

[0124] In one possible implementation, the new first cluster center and the new second cluster center are determined by the following formula:

[0125]

[0126]

[0127] wherein u c1 is the new first cluster center, u c2 is the new second cluster center, S1 is the time-history displacement corresponding to the monitoring points in the first set of monitoring points, S2 is the time-history displacement corresponding to the monitoring points in the second set of monitoring points, N1 is the number of monitoring points in the first set of monitoring points, and N2 is the number of monitoring points in the second set of monitoring points.

[0128] In one possible implementation, the reliability of the category mutation point can also be determined, and the details are as follows:

[0129] B1, acquiring a mutation displacement of the category mutation monitoring point at the end of a preset time interval, and acquiring a mutation displacement threshold;

[0130] B2, determining the reliability of the category mutation monitoring point according to the mutation displacement and the mutation displacement threshold.

[0131] The preset time interval can be a time interval of a monitoring period, etc.

[0132] In one possible implementation, the reliability of the category mutation monitoring point is determined by the following formula:

[0133]

[0134] wherein Δu cr is the mutation displacement, Δu th is the mutation displacement threshold, and R is the reliability of the category mutation monitoring point.

[0135] In one possible implementation, a possible method for obtaining a mutation displacement threshold value includes:

[0136] C1, obtaining a length of a monitoring unit at a category mutation monitoring point, and obtaining a maximum shear strain of a plastic stage of a soil material at the category mutation monitoring point;

[0137] C2, determining the mutation displacement threshold value according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material.

[0138] In one possible implementation, the mutation displacement threshold value is determined by a method shown in the following formula:

[0139] Δu th =l e γ a

[0140] wherein, l e is the length of the monitoring unit, γ a is the maximum shear strain of the plastic stage of the soil material, and Δu th is the mutation displacement threshold value.

[0141] In one possible implementation, a possible method for determining a landslide state of the slope according to a reliability of the M category mutation monitoring points and a number of the category mutation points includes:

[0142] D1, if M is greater than or equal to a preset number threshold value, determining that the landslide state of the slope is a first landslide state;

[0143] D2, if M is less than the preset number threshold value and the reliability is less than 100%, determining that the landslide state of the slope is a second landslide state;

[0144] D3, if M is less than the preset number threshold value and the reliability is greater than or equal to 100%, determining that the landslide state of the slope is a third landslide state.

[0145] wherein, the preset number threshold value is set by an empirical value or historical data. For example, the preset number threshold value can be 1.

[0146] wherein, the first landslide state can be a disordered deformation state, which can be understood as a non-sliding surface; the second landslide state can be an ordered continuous deformation state, which can be understood as an existing potential sliding surface; and the third landslide state can be an ordered discontinuous deformation state, which can be understood as an existing determined sliding surface.

[0147] After determining the landslide state of the slope, the position of the landslide can also be determined, which can be specifically: if the slope is in the second landslide state, the position of the abrupt change point is determined as the position of the potential sliding surface; if the slope is in the third landslide state, the position of the abrupt change point is determined as the position of the deterministic sliding surface.

[0148] In one specific implementation, Figure 1C An algorithm schematic diagram of clustering based on time-history displacement of slope monitoring points is provided for the embodiments of the application.

[0149] Step 1, randomly selecting an initial clustering center u c1 and u c2 ;

[0150] wherein the initial clustering center u c1 and u c2 are time-history displacements randomly selected from K time-history displacements. At this time, the count i = 1, indicating that the time-history displacement of the first monitoring point is about to be judged in terms of category.

[0151] Step 2, calculating the first distance d1 and the second distance d2, and judging whether the first distance d1 is less than the second distance d2. The first distance is the distance between the time-history displacement and the initial clustering center u c1 , and the second distance is the distance between the time-history displacement and the initial clustering center u c2 .

[0152] Step 3, judging whether the first distance d1 is less than the second distance d2, if yes, the category of the monitoring point corresponding to the time-history displacement is determined as category 0, if not, the category of the monitoring point corresponding to the time-history displacement is determined as category 1.

[0153] After the category is judged, the size of the count i and the number K of monitoring points is compared, if i is less than K, the count i = i + 1, indicating that the time-history displacement of the next monitoring point is about to be judged in terms of category, if i is not less than K, it indicates that the category judgment of the time-history displacement of all monitoring points is completed.

[0154] Step 4, updating u c1 and u c2 ;

[0155] The mean of the time-history displacement of the monitoring point corresponding to category 0 is determined as the new clustering center u c1 , and the mean of the time-history displacement of the monitoring point corresponding to category 1 is determined as the new clustering center u c2 .

[0156] Step 5, repeating the above steps 1-4 until u c1 and u c2 are unchanged.

[0157] The value of u no longer changes c1 and u c2 The cluster center has been determined as the final cluster center, and clustering has been completed.

[0158] In one specific implementation, the method is illustrated using two monitoring locations arranged on a slope as an example. The schematic diagram of the monitoring point arrangement is shown below. Figure 1D As shown.

[0159] In both embodiments, the threshold for the abrupt shift is Δu. cr =100mm. Specific Implementation Example 1

[0161] The monitoring data curves at each stage of monitoring location 1 are as follows: Figure 1E As shown, the total depth of the monitoring hole and the total length of the MEMS monitoring device are both 65m, and the length of each MEMS monitoring unit is l. e =1000mm, with an accuracy of 0.1mm. Monitoring at this point began on November 23, 2020, and continued until September 7, 2021, acquiring one deep displacement monitoring data point every 8 days, for a total of 37 data points. These 37 data points are divided into four monitoring phases: (a) represents the deep displacement monitoring results up to day 73, (b) represents up to day 145, (c) represents up to day 217, and (d) represents up to day 289. The data curves for each phase are shown below. Figure 1E As shown.

[0162] Clustering calculations were performed on the time-history displacement curve clusters at each depth during the four monitoring phases to obtain the category of time-history displacement at each depth during each monitoring phase. The category is labeled as 0 or 1. The specific clustering results are as follows: Figure 1E As shown.

[0163] As shown by the category broken line in the first monitoring stage, there are a total of 3 abrupt change points from the bottom to the top of the monitoring hole, where the category changes abruptly and the deep displacement increases, as shown in positions 1, 2, and 3 in the figure. The number of abrupt change points is 3 in both the second and third monitoring stages. Therefore, at the end of the first, second, and third monitoring stages, the sliding surface identification result is that the landslide is in a state of disordered deformation. The number of abrupt change points in the fourth monitoring stage is 1, the depth of the abrupt change point is -28m, and the abrupt displacement on the 289th day is 3.58mm, with a confidence level of 3.58%, which is less than 100%. Therefore, at the end of the fourth monitoring stage, the sliding surface identification result is that the landslide is in a state of ordered discontinuous deformation, and the sliding surface has not yet appeared.

[0164] According to the sliding surface identification method of the present invention, in this embodiment, at the end of the first, second and third monitoring stages, the sliding surface identification result of monitoring location 1 is that the landslide is in a state of disordered deformation and the sliding surface has not yet appeared. At the end of the fourth monitoring stage, that is, on September 7, 2021, the sliding surface identification result of monitoring location 1 is that the sliding surface has not yet appeared. Specific Implementation Example 2

[0166] The monitoring data curves at each stage of monitoring location 2 are as follows: Figure 1F As shown, the total depth of the monitoring hole and the total length of the MEMS monitoring equipment are both 29m, and the length of each MEMS monitoring unit is l. e =1000mm, with an accuracy of 0.1mm. Monitoring at this point began on August 18, 2020, and continued until August 13, 2021, acquiring one deep displacement monitoring data point every 10 days, for a total of 37 data points. These 37 data points are divided into four monitoring phases, representing (a) up to day 61, (b) up to day 161, (c) up to day 261, and (d) up to day 361, respectively. The data curves for each phase are shown below. Figure 1F As shown.

[0167] Clustering calculations were performed on the time-history displacement curve clusters at each depth during the four monitoring phases to obtain the category of time-history displacement at each depth during each monitoring phase. The category is labeled as 0 or 1. The specific clustering results are as follows: Figure 1F As shown.

[0168] As shown by the category broken line, for each monitoring stage, there is one abrupt change in category and a gradual increase in deep displacement from the bottom to the top of the monitoring borehole. The depths of these abrupt change points are -19m, -21m, -21m, and -21m, respectively. At the end of each monitoring stage, the abrupt displacements at these points are 2.70mm, 23.52mm, 24.08mm, and 717.88mm, respectively, with confidence levels of 2.7000%, 23.52%, 24.08%, and 717.88%. Therefore, at the end of the first, second, and third monitoring stages, the sliding surface identification result indicates that the landslide is in an ordered continuous deformation state, and the sliding surface has not yet appeared. At the end of the fourth monitoring stage, the sliding surface identification result indicates that the landslide is in an ordered discontinuous deformation state, and the sliding surface is located at a depth of -21m.

[0169] According to the sliding surface location identification method of the present invention, in this embodiment, at the end of the first, second and third monitoring stages, the sliding surface identification result is that the landslide is in an orderly continuous deformation state and the sliding surface has not yet appeared; at the end of the fourth monitoring stage, that is, on August 13, 2021, the sliding surface identification result is that the landslide is in an orderly discontinuous deformation state and the sliding surface is located at a depth of -21m.

[0170] Consistent with the above embodiment, please refer to Figure 2 , Figure 2 A terminal structure schematic diagram provided by the embodiment of the application is shown in the figure, including a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected with each other, wherein the memory is used for storing a computer program, the computer program includes program instructions, the processor is configured to invoke the program instructions, the above program includes instructions for executing the following steps;

[0171] Obtaining displacement amounts of K monitoring points in a slope vertical monitoring hole within a preset time interval to obtain K time-history displacement amounts;

[0172] Performing clustering processing on the K monitoring points according to the K time-history displacement amounts to obtain a clustering processing result;

[0173] According to the clustering processing result, determining to obtain M category mutation monitoring points, M is an integer less than or equal to K;

[0174] According to the reliability of the M category mutation monitoring points and the number of the category mutation monitoring points, determining the landslide state of the slope.

[0175] The above mainly introduces the scheme of the embodiment of the application from the perspective of the method execution process. It can be understood that the terminal contains hardware structure and / or software modules corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should easily realize that the units and algorithm steps of each example described in the embodiments provided in the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0176] The embodiment of the application can divide the functional units of the terminal according to the above method examples, for example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be realized in the form of hardware or software functional unit. It should be noted that the division of units in the embodiment of the application is illustrative, and is only a logical function division. Actual implementation can have another division method.

[0177] Consistent with the above, please refer to Figure 3 , Figure 3 A structure schematic diagram of a landslide state determination device based on a clustering algorithm provided by the embodiment of the application is shown in the figure, including a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected with each other, wherein the memory is used for storing a computer program, the computer program includes program instructions, the processor is configured to invoke the program instructions, the above program includes instructions for executing the following steps;Figure 3 The device comprises:

[0178] The acquisition unit 301 is configured to acquire displacement amounts of K monitoring points in a slope vertical monitoring hole within a preset time interval to obtain K time-history displacement amounts.

[0179] The processing unit 302 is configured to perform clustering processing on the K landslide monitoring points according to the K time-history displacement amounts to obtain a clustering processing result.

[0180] The first determination unit 303 is configured to determine the M category mutation monitoring points according to the clustering processing result, where M is an integer less than or equal to K.

[0181] The second determination unit 304 is configured to determine a landslide state of the slope according to a reliability of the K category mutation monitoring points and a number of the category mutation monitoring points.

[0182] In one possible implementation, the processing unit 302 is configured to:

[0183] determine an initial first clustering center and an initial second clustering center, where the initial first clustering center and the initial second clustering center are time-history displacement amounts randomly selected from the K time-history displacement amounts;

[0184] acquire a first distance set and a second distance set, where the first distance set is a distance between each time-history displacement amount in the K time-history displacement amounts and the initial first clustering center, and the second distance set is a distance between each time-history displacement amount in the K time-history displacement amounts and the initial second clustering center;

[0185] determine a first type monitoring point set and a second type monitoring point set according to the first distance set and the second distance set, where a distance between a monitoring point in the first type monitoring point set and the initial first clustering center is less than a distance between the initial first clustering center and the initial second clustering center, and a distance between a monitoring point in the second type monitoring point set and the initial second clustering center is less than a distance between the initial second clustering center and the initial first clustering center;

[0186] determine a new first clustering center according to a mean value of time-history displacement corresponding to the monitoring points in the first type monitoring point set, and determine a new second clustering center according to time-history displacement corresponding to the monitoring points in the second type monitoring point set;

[0187] The step of obtaining the new first clustering center and the new second clustering center is repeatedly performed until a final first clustering center and a final second clustering center are determined, the time-history displacement mean value of the monitoring points in the monitoring point set corresponding to the final first clustering center is a constant value, and the time-history displacement mean value of the monitoring points in the monitoring point set corresponding to the final second clustering center is a constant value;

[0188] The monitoring point set corresponding to the final first clustering center is determined as the first type of monitoring points, and the monitoring point set corresponding to the final second clustering center is determined as the second type of monitoring points, to obtain a clustering processing result.

[0189] In a possible implementation, the apparatus is further configured to:

[0190] The distance between the time-history displacement and the initial first clustering center and the initial second clustering center is determined by a method shown in the following formula:

[0191]

[0192] wherein u it is the time-history displacement of the ith monitoring point at the t time; ct is the initial first clustering center or u ct is the initial second clustering center, and u c1 is the time-history displacement of the ith monitoring point at the t time.

[0193] In a possible implementation, the apparatus is further configured to:

[0194] The new first clustering center and the new second clustering center are determined by a method shown in the following formula:

[0195]

[0196]

[0197] wherein u c1 is the new first clustering center, u c2 is the new second clustering center, S1 is the time-history displacement corresponding to the monitoring points in the first type of monitoring point set, S2 is the time-history displacement corresponding to the monitoring points in the second type of monitoring point set, N1 is the number of monitoring points in the first type of monitoring point set, and N2 is the number of monitoring points in the second type of monitoring point set.

[0198] In a possible implementation, the first determining unit 303 is configured to:

[0199] Obtain a mutation displacement of the category mutation monitoring point at an ending moment of a preset time interval, and obtain a mutation displacement threshold;

[0200] determine the credibility of the category mutation monitoring point according to the mutation displacement and the mutation displacement threshold value;

[0201] In the aspect of determining the credibility of the category mutation monitoring point according to the mutation displacement and the mutation displacement threshold value, the apparatus is further configured to:

[0202] determine the credibility of the category mutation monitoring point by a method shown in the following formula:

[0203]

[0204] wherein, Δu cr is the mutation displacement, Δu th is the mutation displacement threshold value, and R is the credibility of the category mutation monitoring point.

[0205] In a possible implementation, in the aspect of obtaining the mutation displacement threshold value, the apparatus is further configured to:

[0206] obtain the length of a monitoring unit at the category mutation monitoring point, and obtain the maximum shear strain of a plastic stage of a soil material at the category mutation monitoring point;

[0207] determine the mutation displacement threshold value according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material;

[0208] In the aspect of determining the mutation displacement threshold value according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material, the apparatus is configured to:

[0209] determine the mutation displacement threshold value by a method shown in the following formula:

[0210] Δu th = l e γ a

[0211] wherein, l e is the length of the monitoring unit, γ a is the maximum shear strain of the plastic stage of the soil material, and Δu th is the mutation displacement threshold value.

[0212] In a possible implementation, the second determining unit 304 is configured to:

[0213] if M is greater than a preset quantity threshold value, determine that the landslide state of the slope is a first landslide state;

[0214] if M is less than or equal to the preset quantity threshold value and the credibility is less than 100%, determine that the landslide state of the slope is a second landslide state;

[0215] If the M is less than or equal to the preset quantity threshold, and the credibility is greater than or equal to 100%, it is determined that the landslide state of the slope is a third landslide state.

[0216] The embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all steps of any one of the landslide state determination methods based on the clustering algorithm as described in the method embodiment.

[0217] The embodiment of the present application further provides a computer program product, which comprises a non-transitory computer-readable storage medium storing a computer program, and the computer program causes a computer to execute part or all steps of any one of the landslide state determination methods based on the clustering algorithm as described in the method embodiment.

[0218] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0219] In the above embodiments, the description of each embodiment is focused on, and the part not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0220] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical or other forms.

[0221] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0222] In addition, each functional unit in the embodiments of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software program module.

[0223] When the integrated unit is realized in the form of a software program module and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the application. The foregoing storage medium includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0224] A person of ordinary skill in the art can understand that all or part of the steps of the various methods in the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer readable storage medium, which can include a flash disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0225] The embodiments of the application are described in detail above, and the principles and implementation manners of the application are described by applying specific examples. The above description of the embodiments is only used to help understand the method of the application and its core idea; meanwhile, for a person of ordinary skill in the art, according to the idea of the application, the specific implementation manner and application range can be changed, and the above description of the embodiments should not be understood as a limitation of the application.

Claims

1. A landslide state determination method based on a clustering algorithm, characterized by, The method comprises: obtaining displacement amounts of K monitoring points in a slope vertical monitoring hole within a preset time interval to obtain K time-history displacement amounts; performing clustering processing on the K monitoring points according to the K time-history displacement amounts to obtain a clustering processing result; determining M category mutation monitoring points according to the clustering processing result, M being an integer less than or equal to K; determining whether a monitoring point is a category mutation monitoring point according to whether the category of the monitoring point in the clustering processing result mutates; determining a landslide state of the slope according to a confidence level of the M category mutation monitoring points and a number of the category mutation monitoring points; the determining of the landslide state of the slope according to the confidence level of the M category mutation monitoring points and the number of the category mutation monitoring points comprises: if M is greater than a preset number threshold, determining that the landslide state of the slope is a first landslide state; if M is less than or equal to the preset number threshold and the confidence level is less than 100%, determining that the landslide state of the slope is a second landslide state; if M is less than or equal to the preset number threshold and the confidence level is greater than or equal to 100%, determining that the landslide state of the slope is a third landslide state; the first landslide state is a disordered deformation state; the second landslide state is an ordered continuous deformation state; and the third landslide state is an ordered discontinuous deformation state; the method further comprises: obtaining a mutation displacement amount of a category mutation monitoring point at an end time of a preset time interval, and obtaining a mutation displacement amount threshold; determining a confidence level of the category mutation monitoring point according to the mutation displacement amount and the mutation displacement amount threshold; the determining of the confidence level of the category mutation monitoring point according to the mutation displacement amount and the mutation displacement amount threshold comprises: determining the confidence level of the category mutation monitoring point by a method shown in the following formula: ； wherein, is the mutation displacement amount, is the mutation displacement amount threshold value, and R is the reliability of the category mutation monitoring point. the obtaining of the mutation displacement amount threshold comprises: obtaining a length of a monitoring unit at the category mutation monitoring point, and obtaining a maximum shear strain of a plastic stage of a soil material at the category mutation monitoring point; determining the mutation displacement amount threshold according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material; the determining of the mutation displacement amount threshold according to the length of the monitoring unit and the maximum shear strain of the plastic stage of the soil material comprises: determining the mutation displacement threshold by a method shown in the following formula: ； wherein, is the length of the monitoring unit, is the maximum shear strain of the plastic stage of the soil material, is the threshold of the abrupt displacement amount.

2. The method of claim 1, wherein, the clustering processing of the K monitoring points according to the K time-history displacement amounts to obtain the clustering processing result comprises: determining an initial first clustering center and an initial second clustering center, the initial first clustering center and the initial second clustering center being time-history displacement amounts randomly selected from the K time-history displacement amounts; obtaining a first distance set and a second distance set, the first distance set being distances between each time-history displacement amount in the K time-history displacement amounts and the initial first clustering center, and the second distance set being distances between each time-history displacement amount in the K time-history displacement amounts and the initial second clustering center; According to the first distance set and the second distance set, a first type of monitoring point set and a second type of monitoring point set are determined, monitoring points in the first type of monitoring point set have a distance to the initial first cluster center smaller than a distance to the initial second cluster center, and monitoring points in the second type of monitoring point set have a distance to the initial second cluster center smaller than a distance to the initial first cluster center; According to a mean value of time-history displacement corresponding to a monitoring point in the first type of monitoring point set, a new first cluster center is determined, and according to time-history displacement of a monitoring point in the second type of monitoring point set, a new second cluster center is determined; The steps of obtaining the new first cluster center and the new second cluster center are repeatedly performed until a final first cluster center and a final second cluster center are determined, the mean value of time-history displacement of monitoring points in a monitoring point set corresponding to the final first cluster center is a constant value, and the mean value of time-history displacement of monitoring points in a monitoring point set corresponding to the final second cluster center is a constant value; The monitoring point set corresponding to the final first cluster center is determined as the first type of monitoring point, and the monitoring point set corresponding to the final second cluster center is determined as the second type of monitoring point, to obtain a clustering processing result.

3. The method of claim 2, wherein, The distance between the time-history displacement amount and the initial first cluster center and the initial second cluster center is determined by a method shown in the following formula: ； wherein, is the displacement amount of the i-th monitoring point at the t-th time; is the displacement amount of the initial first cluster center or the initial second cluster center at the t-th time.

4. The method of claim 2, wherein, The new first cluster center and the new second cluster center are determined by a method shown in the following formula: ； ； wherein u c1 is the new first cluster center, u c2 is the new second cluster center, S1 is the time history displacement corresponding to the monitoring point in the first type monitoring point set, S2 is the time history displacement corresponding to the monitoring point in the second type monitoring point set, N1 is the number of monitoring points in the first type monitoring point set, and N2 is the number of monitoring points in the second type monitoring point set.

5. A landslide state determination apparatus based on a clustering algorithm, characterized by, The device comprises: An acquisition unit is configured to acquire displacement amounts of K monitoring points in a vertical monitoring hole of a slope within a preset time interval to obtain K time-history displacement amounts. A processing unit is configured to perform clustering processing on the K monitoring points according to the K time-history displacement amounts to obtain a clustering processing result. A first determination unit is configured to determine M category mutation monitoring points according to the clustering processing result, M being an integer less than or equal to K; and determine whether a monitoring point is a category mutation monitoring point according to whether the category of the monitoring point in the clustering processing result has mutated. A second determination unit is configured to determine a landslide state of the slope according to a confidence level of the M category mutation monitoring points and a number of the category mutation monitoring points. The determination of the landslide state of the slope according to the confidence level of the M category mutation monitoring points and the number of the category mutation monitoring points comprises: If M is greater than a preset number threshold, the landslide state of the slope is determined as a first landslide state; If M is less than or equal to the preset number threshold and the confidence level is less than 100%, the landslide state of the slope is determined as a second landslide state; If M is less than or equal to the preset number threshold and the confidence level is greater than or equal to 100%, the landslide state of the slope is determined as a third landslide state; The first landslide state is a disordered deformation state, the second landslide state is an ordered continuous deformation state, and the third landslide state is an ordered discontinuous deformation state. The device is further configured to: Acquire a mutation displacement amount of the category mutation monitoring point at an end time point of the preset time interval, and acquire a mutation displacement amount threshold. According to the mutation displacement and the mutation displacement threshold, a credibility of the category mutation monitoring point is determined; According to the mutation displacement and the mutation displacement threshold, a credibility of the category mutation monitoring point is determined, including: The credibility of the category mutation monitoring point is determined by a method shown in the following formula: ； wherein, is the mutation displacement amount, is the mutation displacement amount threshold value, and R is the reliability of the category mutation monitoring point. The mutation displacement threshold is determined according to the length of the monitoring unit at the category mutation monitoring point and the maximum shear strain of the soil material in the plastic stage at the category mutation monitoring point. The mutation displacement threshold is determined according to the length of the monitoring unit at the category mutation monitoring point and the maximum shear strain of the soil material in the plastic stage at the category mutation monitoring point, including: The mutation displacement threshold is determined by a method shown in the following formula: The processing unit is used to: Determine an initial first clustering center and an initial second clustering center, the initial first clustering center and the initial second clustering center being time-history displacement quantities randomly selected from the K time-history displacement quantities; ； wherein, is the length of the monitoring unit, is the maximum shear strain of the plastic stage of the soil material, is the threshold of the abrupt displacement amount.

6. The apparatus of claim 5, wherein, Obtain a first distance set and a second distance set, the first distance set being a distance between each time-history displacement quantity in the K time-history displacement quantities and the initial first clustering center, and the second distance set being a distance between each time-history displacement quantity in the K time-history displacement quantities and the initial second clustering center; According to the first distance set and the second distance set, determine a first type monitoring point set and a second type monitoring point set, a monitoring point in the first type monitoring point set having a distance to the initial first clustering center smaller than a distance to the initial second clustering center, and a monitoring point in the second type monitoring point set having a distance to the initial second clustering center smaller than a distance to the initial first clustering center; Determine a mean value of time-history displacement of the monitoring point in the first type monitoring point set as a new first clustering center, and determine a mean value of time-history displacement of the monitoring point in the second type monitoring point set as a new second clustering center; Repeat the steps of obtaining the new first clustering center and the new second clustering center until a final first clustering center and a final second clustering center are determined, the final first clustering center corresponding to a monitoring point set in which a mean value of time-history displacement of the monitoring points is a constant value, and the final second clustering center corresponding to a monitoring point set in which a mean value of time-history displacement of the monitoring points is a constant value; The monitoring point set corresponding to the final first clustering center is determined as a first type monitoring point, and the monitoring point set corresponding to the final second clustering center is determined as a second type monitoring point, to obtain a clustering processing result. A device includes a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute a method according to any one of claims 1-4. ​ 7. A terminal, characterized by comprising: ​ 8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1-4.

Images