Tower foundation state monitoring method and device, computer equipment, storage medium and computer program product

Abstract

The application relates to a tower foundation state monitoring method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring sensor data corresponding to a tower foundation to be analyzed transmitted by a Beidou short message communication terminal; the sensor data at least comprises weather data, inclination data, catchment data and position data of the tower foundation to be analyzed; performing feature extraction processing on the sensor data to obtain a feature vector corresponding to the sensor data; performing fusion processing on the feature vector corresponding to the sensor data to obtain a target feature vector; inputting the target feature vector into a tower foundation state monitoring model which has been trained to obtain a target tower foundation state monitoring result corresponding to the tower foundation to be analyzed. The method can improve the monitoring accuracy of the tower foundation state.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a tower base condition monitoring method, device, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] In the power grid sector, monitoring the condition of tower foundations and promptly identifying potential hazards is crucial for ensuring the safety of personnel and equipment.

[0003] In traditional technology, the monitoring of the tower base condition is generally carried out by manual inspection; however, this manual inspection method is subject to subjective factors and is prone to errors, resulting in a low accuracy rate in monitoring the tower base condition. Summary of the Invention

[0004] Therefore, it is necessary to provide a tower base condition monitoring method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the monitoring accuracy of tower base condition in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for monitoring the condition of a tower base, including:

[0006] The sensor data corresponding to the tower base to be analyzed is obtained from the Beidou short message communication terminal; the sensor data includes at least the meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed;

[0007] The sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the sensor data;

[0008] The feature vectors corresponding to the sensor data are fused to obtain the target feature vector;

[0009] The target feature vector is input into the trained tower base status monitoring model to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

[0010] In one embodiment, the step of performing feature extraction processing on the sensor data to obtain a feature vector corresponding to the sensor data includes:

[0011] Identify the data type of the sensor data;

[0012] Based on the correspondence between data types and feature extraction models, determine the feature extraction model corresponding to the data type of the sensor data;

[0013] The sensor data is input into the feature extraction model corresponding to the sensor data for feature extraction processing to obtain the feature vector corresponding to the sensor data.

[0014] In one embodiment, the step of fusing the feature vectors corresponding to the sensor data to obtain the target feature vector includes:

[0015] Determine the associated sensor data corresponding to the sensor data;

[0016] The associated sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the associated sensor data;

[0017] The feature vector corresponding to the sensor data is used as the main feature vector, and the feature vector corresponding to the associated sensor data is used as the auxiliary feature vector. These are input into the attention mechanism model for attention mechanism processing to obtain the attention weights corresponding to the sensor data.

[0018] Based on the attention weights corresponding to the sensor data, the feature vectors corresponding to the sensor data are fused to obtain the target feature vector.

[0019] In one embodiment, the step of inputting the target feature vector into the trained tower base status monitoring model to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed includes:

[0020] Obtain the historical tower base status monitoring model corresponding to the trained tower base status monitoring model;

[0021] The target feature vector is input into the trained tower base status monitoring model to obtain the first tower base status monitoring result corresponding to the tower base to be analyzed;

[0022] The target feature vector is input into the historical tower base status monitoring model to obtain the second tower base status monitoring result corresponding to the tower base to be analyzed.

[0023] Based on the first tower base status monitoring results and the second tower base status monitoring results, the target tower base status monitoring results corresponding to the tower base to be analyzed are determined.

[0024] In one embodiment, determining the target tower base status monitoring result corresponding to the tower base to be analyzed based on the first tower base status monitoring result and the second tower base status monitoring result includes:

[0025] Obtain the first model weights of the trained tower base state monitoring model and the second model weights of the historical tower base state monitoring model;

[0026] Based on the first model weight and the second model weight, the first tower base status monitoring results and the second tower base status monitoring results are fused to obtain the target tower base status monitoring results corresponding to the tower base to be analyzed.

[0027] In one embodiment, the trained tower base status monitoring model is obtained by training in the following manner:

[0028] The sample sensor data corresponding to the sample tower base transmitted by the sample Beidou short message communication terminal is obtained; the sample sensor data includes at least the meteorological data, tilt data, water runoff data and location data of the sample tower base;

[0029] The sample sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the sample sensor data;

[0030] The feature vectors corresponding to the sample sensor data are fused to obtain the sample target feature vector;

[0031] The sample target feature vector is input into the tower base state monitoring model to be trained to obtain the predicted tower base state monitoring result corresponding to the sample tower base;

[0032] Based on the difference between the predicted tower base status monitoring results and the actual tower base status monitoring results corresponding to the sample tower base, the tower base status monitoring model to be trained is iteratively trained to obtain the trained tower base status monitoring model.

[0033] Secondly, this application also provides a tower base condition monitoring device, comprising:

[0034] The data acquisition module is used to acquire sensor data corresponding to the tower base to be analyzed transmitted by the Beidou short message communication terminal; the sensor data includes at least meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed;

[0035] The feature extraction module is used to perform feature extraction processing on the sensor data to obtain the feature vector corresponding to the sensor data;

[0036] The vector fusion module is used to fuse the feature vectors corresponding to the sensor data to obtain the target feature vector;

[0037] The result determination module is used to input the target feature vector into the trained tower base status monitoring model to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

[0038] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0039] The sensor data corresponding to the tower base to be analyzed is obtained from the Beidou short message communication terminal; the sensor data includes at least the meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed;

[0040] The sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the sensor data;

[0041] The feature vectors corresponding to the sensor data are fused to obtain the target feature vector;

[0042] The target feature vector is input into the trained tower base status monitoring model to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0044] The sensor data corresponding to the tower base to be analyzed is obtained from the Beidou short message communication terminal; the sensor data includes at least the meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed;

[0045] The sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the sensor data;

[0046] The feature vectors corresponding to the sensor data are fused to obtain the target feature vector;

[0047] The target feature vector is input into the trained tower base status monitoring model to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0049] The sensor data corresponding to the tower base to be analyzed is obtained from the Beidou short message communication terminal; the sensor data includes at least the meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed;

[0050] The sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the sensor data;

[0051] The feature vectors corresponding to the sensor data are fused to obtain the target feature vector;

[0052] The target feature vector is input into the trained tower base status monitoring model to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

[0053] The aforementioned tower foundation condition monitoring method, device, computer equipment, storage medium, and computer program product first acquire meteorological data, tilt data, runoff data, and location data of the tower foundation to be analyzed, transmitted by a Beidou short message communication terminal, as sensor data corresponding to the tower foundation to be analyzed. Then, feature extraction processing is performed on the sensor data to obtain the corresponding feature vectors. Next, the feature vectors are fused to obtain the target feature vector. Finally, the target feature vector is input into the trained tower foundation condition monitoring model to obtain the target tower foundation condition monitoring result. In this way, by acquiring multiple sensor data for the tower foundation to be analyzed, a comprehensive understanding of the tower foundation's condition and status can be obtained when monitoring its condition. Through feature extraction and fusion processing, key information can be extracted more accurately, making the tower foundation condition monitoring results more consistent with the actual situation, thus improving the accuracy and reliability of tower foundation condition monitoring. Moreover, this method does not require manual intervention, avoiding the subjective factors and errors inherent in manual inspections, which can lead to low accuracy in tower foundation condition monitoring, thereby improving the accuracy of tower foundation condition monitoring. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart illustrating a tower base condition monitoring method in one embodiment;

[0056] Figure 2 This is a flowchart illustrating the steps for obtaining the status monitoring results of the target tower base corresponding to the tower base to be analyzed in one embodiment;

[0057] Figure 3 This is a flowchart illustrating the tower base condition monitoring method in another embodiment;

[0058] Figure 4 This is a schematic diagram of the tower base monitoring equipment connection in one embodiment;

[0059] Figure 5 This is a schematic diagram of data transmission in one embodiment;

[0060] Figure 6 This is a structural block diagram of a tower base condition monitoring device in one embodiment;

[0061] Figure 7This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0064] In one exemplary embodiment, such as Figure 1 As shown, a tower base status monitoring method is provided. This embodiment illustrates the application of this method to a server. It is understood that this method can also be applied to terminals, and further to systems including terminals and servers, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; the server can be a standalone server or a server cluster consisting of multiple servers, such as a web server. In this embodiment, the method includes the following steps:

[0065] Step S101: Obtain sensor data corresponding to the tower base to be analyzed transmitted by the Beidou short message communication terminal; the sensor data includes at least meteorological data, tilt angle data, water runoff data and location data of the tower base to be analyzed.

[0066] Among them, the BeiDou short message communication terminal refers to a communication device based on the BeiDou satellite navigation system. In practical scenarios, the BeiDou short message communication terminal refers to the BeiDou-3 regional short message communication module.

[0067] Among them, the tower base to be analyzed refers to the tower base that needs to be monitored for its condition.

[0068] Among them, tower base refers to the foundation of transmission line towers.

[0069] Sensor data refers to data collected by sensors targeting the tower base to be analyzed. It should be noted that sensors include meteorological sensors (such as miniature weather instruments), tilt sensors, water catchment sensors (such as water catchment meters), and GNSS (Global Navigation Satellite System) monitoring sensors, etc.

[0070] The parameters corresponding to the sensor are shown in Table 1 below:

[0071] Table 1 Sensor Performance Parameters

[0072]

[0073] Meteorological data refers to meteorological data related to the tower base to be analyzed, including data such as temperature, humidity, air pressure, wind speed, wind direction, rainfall, and solar radiation, which are collected by meteorological sensors.

[0074] The tilt angle data refers to the tilt angle of the tower base to be analyzed, which is used to characterize the tilt change of the tower base to be analyzed, and is collected by the tilt angle sensor.

[0075] Among them, the water catchment data is used to characterize the water catchment situation of the tower base to be analyzed, including data such as water flow rate, flow velocity, and water level, which are collected by water catchment sensors.

[0076] Among them, the location data refers to the three-dimensional coordinate data of the tower base, which is used to characterize the tower base displacement, settlement and other deformation, and is collected by GNSS monitoring sensors.

[0077] For example, in response to a status monitoring command for the tower base to be analyzed, the server acquires data transmitted by the BeiDou short message communication terminal; then, based on the tower base identifier (such as the tower base name), the server filters out the meteorological data, tilt data, runoff data, and location data of the tower base to be analyzed from the data transmitted by the BeiDou short message communication terminal; then, the server uses the meteorological data, tilt data, runoff data, and location data of the tower base to be analyzed as the sensor data corresponding to the tower base to be analyzed transmitted by the BeiDou short message communication terminal.

[0078] Step S102: Perform feature extraction processing on the sensor data to obtain the feature vector corresponding to the sensor data.

[0079] Feature extraction processing refers to the process of determining the feature vectors corresponding to sensor data.

[0080] Here, the feature vector refers to the representation vector corresponding to the sensor data.

[0081] For example, the server inputs the sensor data into the feature extraction model corresponding to the data type of the sensor data according to the data type of the sensor data, and performs feature extraction processing on the sensor data through the feature extraction model to obtain the feature vector corresponding to the sensor data.

[0082] Step S103: The feature vectors corresponding to the sensor data are fused to obtain the target feature vector.

[0083] Among them, fusion processing can refer to weighted summation processing.

[0084] The target feature vector refers to the feature vector obtained by fusing the feature vectors corresponding to the sensor data.

[0085] For example, the server inputs the feature vector corresponding to the sensor data into the attention mechanism model, and predicts the feature vector corresponding to the sensor data through the attention mechanism model to obtain the attention weight corresponding to the sensor data. Then, the server performs fusion processing on the feature vector corresponding to the sensor data according to the attention weight corresponding to the sensor data to obtain the target feature vector. For example, the server performs weighted summation processing on the feature vector corresponding to the sensor data according to the attention weight corresponding to the sensor data to obtain the target feature vector.

[0086] Step S104: Input the target feature vector into the trained tower base status monitoring model to obtain the target tower base status monitoring results corresponding to the tower base to be analyzed.

[0087] Among them, the tower base condition monitoring model refers to the network model that can use the target feature vector to obtain the target tower base condition monitoring results corresponding to the tower base to be analyzed.

[0088] Among them, the target tower foundation status monitoring results are used to characterize the health status of the tower foundation to be analyzed, such as stable status, crack status, uneven settlement status, high-risk status, etc.

[0089] For example, the server inputs the target feature vector into the trained tower base state monitoring model, and performs classification processing on the target feature vector through the trained tower base state monitoring model to obtain the prediction probability corresponding to each preset tower base state monitoring result; then, the server selects the preset tower base state monitoring result with the highest prediction probability from each preset tower base state monitoring result as the target tower base state monitoring result corresponding to the tower base to be analyzed.

[0090] In the aforementioned tower foundation condition monitoring method, meteorological data, tilt data, runoff data, and location data of the tower foundation to be analyzed, transmitted by the BeiDou short message communication terminal, are first acquired as sensor data corresponding to the tower foundation to be analyzed. Then, feature extraction processing is performed on the sensor data to obtain the corresponding feature vectors. Next, the feature vectors are fused to obtain the target feature vector. Finally, the target feature vector is input into the trained tower foundation condition monitoring model to obtain the target tower foundation condition monitoring result. In this way, by acquiring multiple sensor data for the tower foundation to be analyzed, a comprehensive understanding of the tower foundation's condition and status can be obtained when monitoring its condition. Through feature extraction and fusion processing, key information can be extracted more accurately, making the tower foundation condition monitoring results more consistent with the actual situation, thus improving the accuracy and reliability of tower foundation condition monitoring. Moreover, this method does not require manual intervention, avoiding the subjective factors and errors inherent in manual inspections, which can lead to low accuracy in tower foundation condition monitoring, thereby improving the accuracy of tower foundation condition monitoring.

[0091] In an exemplary embodiment, step S102, which involves performing feature extraction processing on the sensor data to obtain a feature vector corresponding to the sensor data, further includes: identifying the data type of the sensor data; determining the feature extraction model corresponding to the data type of the sensor data based on the correspondence between the data type and the feature extraction model; and inputting the sensor data into the feature extraction model corresponding to the sensor data for feature extraction processing to obtain a feature vector corresponding to the sensor data.

[0092] Here, data type refers to the type of sensor data, such as numerical type, character type, etc.

[0093] Feature extraction models refer to network models that can perform feature extraction processing on data, such as convolutional neural networks and recurrent neural networks.

[0094] The correspondence between data types and feature extraction models is used to characterize the association between them. For example, data type A corresponds to feature extraction model a, data type B corresponds to feature extraction model b, and data type C corresponds to feature extraction model c.

[0095] For example, the server identifies the data type of the sensor data; then, the server obtains the correspondence between the data type and the feature extraction model, and determines the feature extraction model corresponding to the data type of the sensor data based on the correspondence between the data type and the feature extraction model; then, the server inputs the sensor data into the feature extraction model corresponding to the sensor data, and performs feature extraction processing on the sensor data through the feature extraction model to obtain the feature vector corresponding to the sensor data.

[0096] In this embodiment, the feature extraction model corresponding to the data type of sensor data is determined according to the correspondence between data type and feature extraction model. This enables the matching of specialized feature extraction models according to different data types, improving the accuracy and adaptability of feature extraction and enhancing the accuracy of determining the feature vector corresponding to the sensor data.

[0097] In an exemplary embodiment, step S103 above, which involves fusing the feature vectors corresponding to the sensor data to obtain the target feature vector, further includes: determining the associated sensor data corresponding to the sensor data; performing feature extraction processing on the associated sensor data to obtain the feature vectors corresponding to the associated sensor data; inputting the feature vectors corresponding to the sensor data as the main feature vectors and the feature vectors corresponding to the associated sensor data as auxiliary feature vectors into an attention mechanism model for attention mechanism processing to obtain the attention weights corresponding to the sensor data; and fusing the feature vectors corresponding to the sensor data according to the attention weights to obtain the target feature vector.

[0098] Among these, correlated sensor data refers to sensor data other than the sensor data itself. For example, if the sensor data is meteorological data, then the correlated sensor data would be tilt angle data, runoff data, and location data.

[0099] Among them, the main feature vector refers to the feature vector with a larger corresponding weight.

[0100] In this context, the auxiliary feature vector refers to the feature vector with a smaller corresponding weight.

[0101] Among them, the attention mechanism model refers to the network model that can determine the attention weights corresponding to the data.

[0102] Among them, attention mechanism processing refers to the processing procedure that determines the attention weights corresponding to the data.

[0103] Among them, attention weights are used to characterize the importance of the sensor data.

[0104] For example, the server determines the associated sensor data corresponding to the sensor data; then, according to the data type of the associated sensor data, the server inputs the associated sensor data into the feature extraction model corresponding to the data type of the associated sensor data, and performs feature extraction processing on the associated sensor data through the feature extraction model to obtain the feature vector corresponding to the associated sensor data; then, the server uses the feature vector corresponding to the sensor data as the main feature vector and the feature vector corresponding to the associated sensor data as the auxiliary feature vector, and inputs it into the attention mechanism model for attention mechanism processing to obtain the attention weight corresponding to the sensor data; finally, the server performs fusion processing on the feature vector corresponding to the sensor data according to the attention weight corresponding to the sensor data to obtain the fused feature vector as the target feature vector; for example, the server performs weighted summation processing on the feature vector corresponding to the sensor data according to the attention weight corresponding to the sensor data to obtain the fused feature vector as the target feature vector.

[0105] In this embodiment, during the fusion process, both key indicator data and related key indicator data are considered simultaneously, which is equivalent to considering two different types of data at the same time. This makes the feature vector obtained by the fusion process more comprehensive and helps to improve the accuracy of the target feature vector determination.

[0106] In an exemplary embodiment, step S104 above, which involves inputting the target feature vector into the trained tower base status monitoring model to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed, specifically includes the following steps:

[0107] Step S201: Obtain the historical tower base status monitoring model corresponding to the trained tower base status monitoring model.

[0108] Step S202: Input the target feature vector into the trained tower base state monitoring model to obtain the first tower base state monitoring result corresponding to the tower base to be analyzed.

[0109] Step S203: Input the target feature vector into the historical tower base status monitoring model to obtain the second tower base status monitoring result corresponding to the tower base to be analyzed.

[0110] Step S204: Based on the first tower base status monitoring results and the second tower base status monitoring results, determine the target tower base status monitoring results corresponding to the tower base to be analyzed.

[0111] Among them, the historical tower base status monitoring model refers to the tower base status monitoring model corresponding to the target feature vector in the past time period, such as the tower base status monitoring model corresponding to the target feature vector in the past week, the tower base status monitoring model corresponding to the target feature vector in the past month, etc.

[0112] Among them, the first tower base status monitoring result refers to the tower base status monitoring result corresponding to the tower base to be analyzed, output by the trained tower base status monitoring model.

[0113] Among them, the second tower base condition monitoring result refers to the tower base condition monitoring result corresponding to the tower base to be analyzed, output by the historical tower base condition monitoring model.

[0114] For example, the server obtains the historical tower base status monitoring model corresponding to the trained tower base status monitoring model; then, the server inputs the target feature vector into the trained tower base status monitoring model, and predicts the target feature vector using the trained tower base status monitoring model to obtain the first tower base status monitoring result corresponding to the tower base to be analyzed; then, the server inputs the target feature vector into the historical tower base status monitoring model, and predicts the target feature vector using the historical tower base status monitoring model to obtain the second tower base status monitoring result corresponding to the tower base to be analyzed; finally, the server determines the target tower base status monitoring result corresponding to the tower base to be analyzed based on the first tower base status monitoring result and the second tower base status monitoring result.

[0115] In this embodiment, by utilizing the trained tower base condition monitoring model and the historical tower base condition monitoring model, it is equivalent to using two different models to predict the tower base condition monitoring results corresponding to the tower base to be analyzed. This allows for a more comprehensive tower base condition monitoring result, which is beneficial to improving the accuracy of determining the tower base condition monitoring results corresponding to the tower base to be analyzed.

[0116] In an exemplary embodiment, step S204 above, which determines the target tower base status monitoring result corresponding to the tower base to be analyzed based on the first tower base status monitoring result and the second tower base status monitoring result, further includes: obtaining the first model weight of the trained tower base status monitoring model and the second model weight of the historical tower base status monitoring model; and performing fusion processing on the first tower base status monitoring result and the second tower base status monitoring result based on the first model weight and the second model weight to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

[0117] Among them, the weight of the first model represents the importance of the base state monitoring model after training.

[0118] The weight of the second model represents the importance of the historical tower base status monitoring model.

[0119] For example, the server determines the first model weight of the trained tower base condition monitoring model and the second model weight of the historical tower base condition monitoring model based on the prediction accuracy of the trained tower base condition monitoring model for the target feature vector and the prediction accuracy of the historical tower base condition monitoring model for the target feature vector. Then, the server fuses the first tower base condition monitoring result and the second tower base condition monitoring result based on the first model weight and the second model weight to obtain the fused tower base condition monitoring result, which is used as the target tower base condition monitoring result corresponding to the tower base to be analyzed. For example, if the first tower base condition monitoring result is a cracked state and the second tower base condition monitoring result is a stable state, with the first model weight being 0.8 and the second model weight being 0.2, the obtained target tower base condition monitoring result corresponding to the tower base to be analyzed is a cracked state.

[0120] In this embodiment, by using the model weights of the trained tower base condition monitoring model and the historical tower base condition monitoring model, the importance of different models is considered, and the tower base condition monitoring results corresponding to the tower base to be analyzed are determined comprehensively, which helps to improve the accuracy of determining the tower base condition monitoring results corresponding to the tower base to be analyzed.

[0121] In an exemplary embodiment, the tower base condition monitoring method provided in this application further includes a training step for the trained tower base condition monitoring model, which further includes: acquiring sample sensor data corresponding to the sample tower base transmitted by the sample Beidou short message communication terminal; the sample sensor data includes at least meteorological data, tilt data, runoff data, and location data of the sample tower base; performing feature extraction processing on the sample sensor data to obtain the feature vector corresponding to the sample sensor data; performing fusion processing on the feature vector corresponding to the sample sensor data to obtain the sample target feature vector; inputting the sample target feature vector into the tower base condition monitoring model to be trained to obtain the predicted tower base condition monitoring result corresponding to the sample tower base; and iteratively training the tower base condition monitoring model to be trained based on the difference between the predicted tower base condition monitoring result corresponding to the sample tower base and the actual tower base condition monitoring result to obtain the trained tower base condition monitoring model.

[0122] Among them, the sample Beidou short message communication terminal refers to the Beidou short message communication terminal used to train the tower base status monitoring model.

[0123] Among them, the sample tower base refers to the tower base used to train the tower base state monitoring model.

[0124] Among them, sample sensor data refers to the sensor data corresponding to the sample tower base.

[0125] Among them, the sample target feature vector refers to the feature vector obtained by fusing the feature vectors corresponding to the sample sensor data.

[0126] Among them, the predicted tower base condition monitoring result refers to the predicted value corresponding to the tower base condition monitoring result of the sample tower base.

[0127] The actual tower base condition monitoring result refers to the actual value corresponding to the tower base condition monitoring result of the sample tower base.

[0128] For example, in response to a model training instruction for a tower base condition monitoring model to be trained, the server acquires meteorological data, tilt data, runoff data, and location data corresponding to the sample tower base transmitted by the sample BeiDou short message communication terminal, all of which are used as sample sensor data corresponding to the sample tower base transmitted by the sample BeiDou short message communication terminal. Next, the server inputs the sample sensor data into a feature extraction model corresponding to the data type of the sample sensor data, and performs feature extraction processing on the sample sensor data through the feature extraction model to obtain the feature vector corresponding to the sample sensor data. Then, the server inputs the feature vector corresponding to the sample sensor data into an attention mechanism model, and predicts the feature vector corresponding to the sample sensor data through the attention mechanism model to obtain the attention weight corresponding to the sample sensor data. Then, the server performs fusion processing on the feature vector corresponding to the sample sensor data based on the attention weight corresponding to the sample sensor data to obtain the sample target feature vector. For example, the server performs fusion processing on the sample sensor data based on the attention weight corresponding to the sample sensor data. The corresponding feature vectors are weighted and summed to obtain the sample target feature vector. Then, the server inputs the sample target feature vector into the tower base state monitoring model to be trained. The tower base state monitoring model classifies the sample target feature vector to obtain the prediction probability corresponding to each preset tower base state monitoring result. Next, the server selects the preset tower base state monitoring result with the highest prediction probability from the preset tower base state monitoring results as the predicted tower base state monitoring result corresponding to the sample tower base. Then, the server obtains the actual tower base state monitoring result corresponding to the sample tower base and obtains the loss value based on the difference between the predicted tower base state monitoring result and the actual tower base state monitoring result. Next, the server adjusts the model parameters of the tower base state monitoring model to be trained based on the loss value. Then, the server retrains the tower base state monitoring model with adjusted model parameters until the loss value obtained by the trained tower base state monitoring model is less than the loss value threshold. At this point, training stops, and the trained tower base state monitoring model is taken as the completed tower base state monitoring model.

[0129] In this embodiment, by pre-training the tower base status monitoring model, it is convenient to predict the tower base status monitoring results corresponding to the tower base to be analyzed after obtaining the sensor data corresponding to the tower base to be analyzed transmitted by the Beidou short message communication terminal in practical applications. Moreover, the tower base status monitoring model receives new data in each iteration, and performs internal model improvement and optimization, which makes it easier to make predictions more effectively and improves the prediction accuracy of the tower base status monitoring model.

[0130] In one exemplary embodiment, such as Figure 3 As shown, another method for monitoring the status of the tower base is provided. Taking the application of this method to a server as an example, it includes the following steps:

[0131] Step S301: Obtain sensor data corresponding to the tower base to be analyzed transmitted by the Beidou short message communication terminal; the sensor data includes at least meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed.

[0132] Step S302: Identify the data type of the sensor data; determine the feature extraction model corresponding to the data type of the sensor data based on the correspondence between the data type and the feature extraction model; input the sensor data into the feature extraction model corresponding to the sensor data for feature extraction processing to obtain the feature vector corresponding to the sensor data.

[0133] Step S303: Determine the associated sensor data corresponding to the sensor data; perform feature extraction processing on the associated sensor data to obtain the feature vector corresponding to the associated sensor data.

[0134] Step S304: The feature vector corresponding to the sensor data is used as the main feature vector, and the feature vector corresponding to the associated sensor data is used as the auxiliary feature vector. These are input into the attention mechanism model for attention mechanism processing to obtain the attention weights corresponding to the sensor data.

[0135] Step S305: Based on the attention weights corresponding to the sensor data, perform fusion processing on the feature vectors corresponding to the sensor data to obtain the target feature vector.

[0136] Step S306: Obtain the historical tower base status monitoring model corresponding to the trained tower base status monitoring model; input the target feature vector into the trained tower base status monitoring model to obtain the first tower base status monitoring result corresponding to the tower base to be analyzed; input the target feature vector into the historical tower base status monitoring model to obtain the second tower base status monitoring result corresponding to the tower base to be analyzed.

[0137] Step S307: Obtain the first model weight of the trained tower base condition monitoring model and the second model weight of the historical tower base condition monitoring model; based on the first model weight and the second model weight, perform fusion processing on the first tower base condition monitoring result and the second tower base condition monitoring result to obtain the target tower base condition monitoring result corresponding to the tower base to be analyzed.

[0138] In the aforementioned tower foundation condition monitoring method, when monitoring the tower foundation condition, data from multiple sensors targeting the tower foundation to be analyzed are acquired to comprehensively understand the tower foundation's condition and status. Through feature extraction and fusion processing, key information can be extracted more accurately, making the tower foundation condition monitoring results more consistent with the actual situation, which is beneficial to improving the accuracy and reliability of tower foundation condition monitoring. Moreover, this method does not require manual intervention, avoiding the subjective factors and errors inherent in manual inspection, which lead to low accuracy in tower foundation condition monitoring, thereby improving the accuracy of tower foundation condition monitoring.

[0139] In an exemplary embodiment, to more clearly illustrate the tower foundation status monitoring method provided in this application, the following specific embodiment will be used to describe the tower foundation status monitoring method in detail. In one embodiment, this application also provides a tower foundation monitoring data transmission model based on BeiDou short message technology. When monitoring the tower foundation status, meteorological data, tilt angle data, water catchment data, and location data of the tower foundation to be analyzed, transmitted by the BeiDou short message communication terminal, are first acquired as sensor data corresponding to the tower foundation to be analyzed. Then, feature extraction processing is performed on the sensor data to obtain the feature vector corresponding to the sensor data. Then, the feature vector corresponding to the sensor data is fused to obtain the target feature vector. Finally, the target feature vector is input into the trained tower foundation status monitoring model to obtain the target tower foundation status monitoring result corresponding to the tower foundation to be analyzed. Specifically, it includes the following:

[0140] A data transmission model for tower-based monitoring based on BeiDou short message technology, such as Figure 4 As shown, it includes: a data acquisition module for acquiring sensor data and image data within the area; a BeiDou short message communication terminal for receiving sensor data and image data from the data acquisition module; a power supply module connected to both the BeiDou short message communication terminal and the data acquisition module; and a client for receiving sensor data transmitted from the BeiDou short message communication terminal.

[0141] The data acquisition module includes a meteorological sensor, an inclination sensor, a water catchment sensor, and a GNSS monitoring sensor, all of which are electrically connected to the BeiDou short message communication terminal.

[0142] The solar charging device is a solar panel.

[0143] Among them, the energy storage battery is a gel battery.

[0144] The power supply module also includes a solar controller, which is electrically connected to the energy storage battery and the solar charging device.

[0145] The network server is connected to the Beidou short message communication terminal and the client respectively, and is used to relay sensor data and image data.

[0146] The solar panel in this application is a monocrystalline silicon panel with the following parameters: power specification of 60W, rated voltage of 22.4V, nominal power of 60W, peak voltage of 22.4V, and peak current of 2.29A.

[0147] The solar panels are controlled by a solar controller with the following parameters: maximum charging current of 10A, maximum load current of 10A, maximum voltage of no more than 50V, battery voltage of 12V / 24V, no-load power consumption of 6MA~25MA, and operating temperature of -35℃~+60℃.

[0148] The gel battery has a capacity of 20Ah, a voltage of 9-12.6V, a continuous current of 3A, and an overcurrent protection value of 6A.

[0149] Specifically, the BeiDou short message communication terminal is the BeiDou-3 regional short message communication module.

[0150] The parameters of the BeiDou-3 regional short message communication module are as follows: power supply parameters are +4.5V to +5.5V, transmission current is no more than 3.5A, maximum length of a single message is 1000 characters (14000 bits), and operating temperature range is -30 to +75℃.

[0151] The data acquisition module specifically includes meteorological sensors, tilt sensors, water flow sensors, and GNSS monitoring sensors.

[0152] This application provides a data transmission model for tower-based monitoring based on BeiDou short message technology, including the following steps: Figure 5 As shown: sensor data within the area is acquired; after transmission via BeiDou short message service, the sensor data and image data are packetized; the packetized data is then transmitted over the network and stored on the network side; the client receives the sensor data.

[0153] Specifically, data collection commands are sent to meteorological sensors, tilt sensors, water catchment sensors, and GNSS monitoring sensors via the BeiDou short message communication terminal. The data returned by the four types of sensors are processed and sequentially packetized and transmitted to the network server for storage. Users can view the monitoring data collected and reported by the terminal through client software.

[0154] Data transmission via conventional networks presents numerous challenges in terms of installation and coverage. Network cables cannot cover all practical installation environments, and laying them at tower base monitoring sites is costly, with some areas presenting significant construction difficulties. Furthermore, signal coverage is poor in sparsely populated plains, mountains, pastoral areas, and remote mountainous regions, compromising stable data transmission. Therefore, a data transmission terminal utilizing BeiDou technology, integrating a BeiDou-3 regional short message communication module, effectively addresses the challenges of weak mobile network signals and lack of coverage, making equipment installation in such areas essential for tower base monitoring equipment.

[0155] The above embodiments, when monitoring the tower base status, acquire data from multiple sensors targeting the tower base to be analyzed, thereby gaining a comprehensive understanding of the tower base's status and condition. Through feature extraction and fusion processing, key information can be extracted more accurately, making the tower base status monitoring results more consistent with the actual situation, thus improving the accuracy and reliability of tower base status monitoring. Moreover, this method requires no manual intervention, avoiding the subjective factors and errors inherent in manual inspections, which can lead to low accuracy in tower base status monitoring, thereby improving the accuracy of tower base status monitoring. Simultaneously, this application overcomes the shortcomings of traditional tower base monitoring networks, such as limited coverage and instability, ensuring the real-time and stable transmission of data during tower base monitoring equipment operation. Tower base monitoring is a technology that uses high-precision sensors to monitor the health status of tower structures, playing a crucial role in ensuring the safety of communication towers, power towers, and other tall structures. In addressing communication blind spots, tower bases far from cities may be outside the coverage of traditional radio or cellular networks; BeiDou short message service can provide stable communication services globally, especially suitable for remote areas or marine applications. Regarding the need for low power consumption and long-distance transmission, traditional wireless communication consumes a lot of energy during long-distance transmission, while BeiDou short message technology can achieve long-distance communication while maintaining low power consumption. Regarding the need for small data volume transmission, sensors monitoring the health status of tower bases typically generate small amounts of data; therefore, BeiDou short message technology becomes an efficient transmission method, capable of efficiently sending critical monitoring data within limited data volumes. Regarding the need for real-time monitoring, the safe operation of tower bases requires real-time or near-real-time monitoring and reporting of any potential structural problems. The BeiDou system can ensure timely data transmission to the monitoring center, even under extreme weather conditions.

[0156] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0157] Based on the same inventive concept, this application also provides a tower base condition monitoring device for implementing the tower base condition monitoring method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the tower base condition monitoring device provided below can be found in the limitations of the tower base condition monitoring method described above, and will not be repeated here.

[0158] In one exemplary embodiment, such as Figure 6 As shown, a tower base condition monitoring device is provided, comprising: a data acquisition module 601, a feature extraction module 602, a vector fusion module 603, and a result determination module 604, wherein:

[0159] The data acquisition module 601 is used to acquire sensor data corresponding to the tower base to be analyzed transmitted by the Beidou short message communication terminal; the sensor data includes at least meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed.

[0160] The feature extraction module 602 is used to perform feature extraction processing on the sensor data to obtain the feature vector corresponding to the sensor data.

[0161] The vector fusion module 603 is used to fuse the feature vectors corresponding to the sensor data to obtain the target feature vector.

[0162] The result determination module 604 is used to input the target feature vector into the trained tower base state monitoring model to obtain the target tower base state monitoring result corresponding to the tower base to be analyzed.

[0163] In an exemplary embodiment, the feature extraction module 602 is further configured to identify the data type of the sensor data; determine the feature extraction model corresponding to the data type of the sensor data according to the correspondence between the data type and the feature extraction model; input the sensor data into the feature extraction model corresponding to the sensor data for feature extraction processing to obtain the feature vector corresponding to the sensor data.

[0164] In an exemplary embodiment, the vector fusion module 603 is further configured to: determine associated sensor data corresponding to the sensor data; perform feature extraction processing on the associated sensor data to obtain feature vectors corresponding to the associated sensor data; input the feature vectors corresponding to the sensor data as the main feature vectors and the feature vectors corresponding to the associated sensor data as auxiliary feature vectors into the attention mechanism model for attention mechanism processing to obtain attention weights corresponding to the sensor data; and perform fusion processing on the feature vectors corresponding to the sensor data according to the attention weights corresponding to the sensor data to obtain the target feature vector.

[0165] In an exemplary embodiment, the result determination module 604 is further configured to: acquire the historical tower base status monitoring model corresponding to the trained tower base status monitoring model; input the target feature vector into the trained tower base status monitoring model to obtain the first tower base status monitoring result corresponding to the tower base to be analyzed; input the target feature vector into the historical tower base status monitoring model to obtain the second tower base status monitoring result corresponding to the tower base to be analyzed; and determine the target tower base status monitoring result corresponding to the tower base to be analyzed based on the first tower base status monitoring result and the second tower base status monitoring result.

[0166] In an exemplary embodiment, the result determination module 604 is further configured to obtain the first model weight of the trained tower base status monitoring model and the second model weight of the historical tower base status monitoring model; and to perform fusion processing on the first tower base status monitoring result and the second tower base status monitoring result according to the first model weight and the second model weight to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

[0167] In an exemplary embodiment, the tower base condition monitoring device further includes a model training module for acquiring sample sensor data corresponding to the sample tower base transmitted by the sample Beidou short message communication terminal; the sample sensor data includes at least meteorological data, tilt data, runoff data, and location data of the sample tower base; performing feature extraction processing on the sample sensor data to obtain the feature vector corresponding to the sample sensor data; performing fusion processing on the feature vector corresponding to the sample sensor data to obtain the sample target feature vector; inputting the sample target feature vector into the tower base condition monitoring model to be trained to obtain the predicted tower base condition monitoring result corresponding to the sample tower base; and iteratively training the tower base condition monitoring model to be trained based on the difference between the predicted tower base condition monitoring result corresponding to the sample tower base and the actual tower base condition monitoring result to obtain the trained tower base condition monitoring model.

[0168] Each module in the aforementioned tower base condition monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0169] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores meteorological data, tilt data, runoff data, and location data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a tower base condition monitoring method.

[0170] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0171] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0172] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0173] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0174] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0175] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0176] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring the condition of a tower base, characterized in that, The method includes: The sensor data corresponding to the tower base to be analyzed is obtained from the Beidou short message communication terminal; the sensor data includes at least the meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed; The sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the sensor data; The process involves: identifying associated sensor data corresponding to the sensor data; inputting the associated sensor data into a feature extraction model corresponding to the data type of the associated sensor data to obtain a feature vector corresponding to the associated sensor data; using the feature vector corresponding to the sensor data as the primary feature vector and the feature vector corresponding to the associated sensor data as the auxiliary feature vector, inputting them into an attention mechanism model for attention mechanism processing to obtain the attention weights corresponding to the sensor data; and performing a weighted summation of the feature vectors corresponding to the sensor data based on the attention weights to obtain the target feature vector. Obtain the historical tower base status monitoring model corresponding to the trained tower base status monitoring model; input the target feature vector into the trained tower base status monitoring model to obtain the first tower base status monitoring result corresponding to the tower base to be analyzed; input the target feature vector into the historical tower base status monitoring model to obtain the second tower base status monitoring result corresponding to the tower base to be analyzed; determine the target tower base status monitoring result corresponding to the tower base to be analyzed based on the first tower base status monitoring result and the second tower base status monitoring result.

2. The method according to claim 1, characterized in that, The step of performing feature extraction processing on the sensor data to obtain the feature vector corresponding to the sensor data includes: Identify the data type of the sensor data; Based on the correspondence between data types and feature extraction models, determine the feature extraction model corresponding to the data type of the sensor data; The sensor data is input into the feature extraction model corresponding to the sensor data for feature extraction processing to obtain the feature vector corresponding to the sensor data.

3. The method according to claim 1, characterized in that, The step of determining the target tower base status monitoring result corresponding to the tower base to be analyzed based on the first tower base status monitoring result and the second tower base status monitoring result includes: Obtain the first model weights of the trained tower base state monitoring model and the second model weights of the historical tower base state monitoring model; Based on the first model weight and the second model weight, the first tower base status monitoring results and the second tower base status monitoring results are fused to obtain the target tower base status monitoring results corresponding to the tower base to be analyzed.

4. The method according to any one of claims 1 to 3, characterized in that, The trained tower base condition monitoring model was obtained through the following method: The sample sensor data corresponding to the sample tower base transmitted by the sample Beidou short message communication terminal is obtained; the sample sensor data includes at least the meteorological data, tilt data, water runoff data and location data of the sample tower base; The sample sensor data is subjected to feature extraction processing to obtain the feature vector corresponding to the sample sensor data; The feature vectors corresponding to the sample sensor data are fused to obtain the sample target feature vector; The sample target feature vector is input into the tower base state monitoring model to be trained to obtain the predicted tower base state monitoring result corresponding to the sample tower base; Based on the difference between the predicted tower base status monitoring results and the actual tower base status monitoring results corresponding to the sample tower base, the tower base status monitoring model to be trained is iteratively trained to obtain the trained tower base status monitoring model.

5. A tower base condition monitoring device, characterized in that, The device includes: The data acquisition module is used to acquire sensor data corresponding to the tower base to be analyzed transmitted by the Beidou short message communication terminal; the sensor data includes at least meteorological data, tilt data, water runoff data and location data of the tower base to be analyzed; The feature extraction module is used to perform feature extraction processing on the sensor data to obtain the feature vector corresponding to the sensor data; A vector fusion module is used to determine the associated sensor data corresponding to the sensor data; input the associated sensor data into a feature extraction model corresponding to the data type of the associated sensor data to obtain the feature vector corresponding to the associated sensor data; input the feature vector corresponding to the sensor data as the primary feature vector and the feature vector corresponding to the associated sensor data as the auxiliary feature vector into an attention mechanism model for attention mechanism processing to obtain the attention weight corresponding to the sensor data; and perform weighted summation on the feature vector corresponding to the sensor data according to the attention weight to obtain the target feature vector. The result determination module is used to obtain the historical tower base status monitoring model corresponding to the trained tower base status monitoring model; input the target feature vector into the trained tower base status monitoring model to obtain the first tower base status monitoring result corresponding to the tower base to be analyzed; input the target feature vector into the historical tower base status monitoring model to obtain the second tower base status monitoring result corresponding to the tower base to be analyzed; and determine the target tower base status monitoring result corresponding to the tower base to be analyzed based on the first tower base status monitoring result and the second tower base status monitoring result.

6. The apparatus according to claim 5, characterized in that, The feature extraction module is further configured to identify the data type of the sensor data; determine the feature extraction model corresponding to the data type of the sensor data based on the correspondence between the data type and the feature extraction model; input the sensor data into the feature extraction model corresponding to the sensor data for feature extraction processing to obtain the feature vector corresponding to the sensor data.

7. The apparatus according to claim 5, characterized in that, The result determination module is further configured to obtain the first model weight of the trained tower base status monitoring model and the second model weight of the historical tower base status monitoring model; and to perform fusion processing on the first tower base status monitoring result and the second tower base status monitoring result according to the first model weight and the second model weight to obtain the target tower base status monitoring result corresponding to the tower base to be analyzed.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images