A high-altitude cold risk assessment method and system based on big data

Abstract

The present invention discloses a high-cold risk assessment method and system based on big data, and relates to the technical field of electronic digital data processing. The high-cold risk assessment method based on big data includes the following steps: obtaining first device data by performing data source comparison and verification on device data, transmitting the first device data to a constructed first device database for storage, monitoring the data transmission status in real time at a preset real-time monitoring window during the data transmission process, preprocessing and feature extraction of the first device data according to a feature extraction module to obtain first feature data, and comparing and verifying the first feature data with preset second feature data to obtain a high-cold risk assessment index. The present invention collects device data in the high-cold area range through sensors and performs data source comparison and verification and preprocessing, thereby improving the data quality in the high-cold risk assessment and solving the problem of low data quality in the high-cold risk assessment in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a high-altitude cold risk assessment method and system based on big data. Background Art

[0002] Alpine regions such as the Qinghai-Tibet Plateau and northern Heilongjiang Province often face a variety of natural disaster risks due to extreme weather conditions and environmental characteristics, including the phenomenon of alpine freezing. Alpine freezing refers to the fact that due to high altitude and long-term low temperatures, permafrost does not melt all year round, resulting in sparse vegetation and increased soil erosion, which in turn affects the stability and sustainability of the local ecosystem. With the advent of the big data era, technical support is provided for analyzing and evaluating the trend of alpine freezing in alpine regions through data.

[0003] The existing system classifies alpine climate change into a certain level by combining data such as topography, vegetation coverage and soil type in alpine areas. It then conducts equivalent classification and analysis based on key features and combined with preset level indicators to achieve an assessment of alpine climate change risks.

[0004] For example, a patent application with publication number: CN112363061A discloses a thermal runaway risk assessment method based on big data, including: extracting multiple data from multiple devices equipped with power batteries in normal operation and charging status; calculating the average temperature value of each temperature sampling value in each data; obtaining the maximum value of the temperature rise rate value in each data; cleaning the data; establishing a function model between various state parameter values, the average temperature value and the maximum value of the temperature rise value, and training the function model; using the trained function model to obtain the current temperature rise rate prediction value, and obtain the current actual temperature rise rate value; comparing the current temperature rise rate prediction value with the current actual temperature rise rate value, and determining the thermal runaway risk based on the comparison result.

[0005] For example, the invention patent with announcement number: CN112445701 B announces an application software adaptation evaluation and early warning method and system based on big data, including: obtaining the running information of the application software; obtaining the running status information of the device to be installed and sending the status information to the data center; the data center receives the status information, and calculates the adaptation index of the device to be installed according to the status information; before distributing the application software to the device to be installed, judging whether the application software is suitable for installation according to the running information of the application software and the adaptation index of the device to be installed.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the existing technology, the harsh environment in high-altitude cold regions leads to inaccurate recognition of collected data, and there is a problem of low data quality in high-altitude cold risk assessment. Summary of the invention

[0008] The embodiments of the present application solve the problem of low data quality in high-altitude cold risk assessment in the prior art by providing a high-altitude cold risk assessment method and system based on big data, thereby improving the data quality in high-altitude cold risk assessment.

[0009] The embodiment of the present application provides a high-cold risk assessment method based on big data, including the following steps: S1 collects equipment data in a high-cold area through a sensor and performs data source comparison and verification to obtain first equipment data, and transmits the collected first equipment data to a constructed first equipment database for storage, wherein the equipment data includes climate data and terrain image data, and the climate data includes ambient temperature, surface temperature and soil temperature; S2 preprocesses and extracts features of the first equipment data to obtain first feature data, and obtains a land freeze-thaw index according to the soil temperature in the first feature data, wherein the first feature data includes climate temperature and vegetation coverage area, and the land freeze-thaw index is used to quantify the degree of influence of land freeze-thaw cycles in high-cold areas on soil and surface characteristics; S3 compares and verifies the first feature data with the preset second feature data to obtain a high-cold risk assessment index, and the high-cold risk assessment index is used to assess the high-cold risk level in high-cold areas.

[0010] Furthermore, the specific steps of the data source comparison and verification are as follows: configure a data source identifier for the collected device data, the data source identifier is used to distinguish the source of the device data, and the device data is grouped according to the data identification field to obtain a data source identification data group, and the data source identification data group is statistically analyzed according to the data source identifier to obtain a verification range, and the device data in the data source identification data group is compared and verified with the verification range to obtain the first device data, and the verification range represents a verification interval determined according to the mean and standard deviation of the data source identification data group.

[0011] Furthermore, the specific steps of the preprocessing are as follows: obtaining a hash value corresponding to the first device data through a hash algorithm, judging whether there is duplicate data in the first device data based on the obtained hash value, removing the duplicate data if so, and recording the deduplicated data as the second device data; performing distance analysis on the second device data through an agglomerative hierarchical clustering method to obtain a distance matrix, and obtaining a clustering hierarchy diagram based on the distance matrix, judging whether there is abnormal data in the second device data based on the clustering hierarchy diagram, removing the abnormal data if so, and recording the second device data after removing the abnormal data as the third device data.

[0012] Furthermore, the climate temperature in the third device data is classified according to the data type to obtain a temperature data group, and the temperature mean within a preset time interval is counted to obtain a temperature sequence, wherein the temperature data group includes the ambient temperature, surface temperature and soil temperature, and the preset time interval is the total duration of the monitoring time points in the high-cold area; the grayscale value of each pixel in the terrain image data in the third device data is compared and verified with the grayscale threshold to obtain the vegetation coverage area, and the grayscale threshold is used to distinguish whether the image is a vegetation coverage area.

[0013] Furthermore, the specific steps of transmitting the collected first device data to the constructed first device database for storage are as follows: encoding the first device data through arithmetic coding to obtain compressed data, and transmitting the compressed data to the first device database; after receiving the compressed data, the first device database decompresses the compressed data according to the encoding value of the compressed data to obtain the first device data and stores it in the first device database.

[0014] Furthermore, the transmitting of the collected first device data to the constructed first device database for storage also includes real-time monitoring of the data transmission process. The specific method of real-time monitoring of the data transmission process is as follows: during the first device data transmission process, determine whether the data transmission rate and delay obtained at a preset real-time monitoring window exceed a preset threshold value. If so, stop transmission and issue an alarm; otherwise, continue monitoring. The preset real-time monitoring window is used to detect the data transmission rate and delay within a preset time period. The preset threshold value includes a preset maximum transmission rate and a preset maximum delay time.

[0015] Furthermore, the specific steps for obtaining the land freeze-thaw index are as follows: classify the climate temperature in the third device data according to the data type to obtain the soil temperature, and analyze the soil temperature within a preset time interval to obtain the soil temperature average, and at the same time compare and verify the soil temperature average and the standard soil temperature value to obtain the land freeze-thaw index; classify the land freeze-thaw cycle in the high-cold area according to the obtained land freeze-thaw index, and the classification is used to determine the degree of influence of the land freeze-thaw cycle in the high-cold area on the soil and surface characteristics.

[0016] Furthermore, the land freeze-thaw index is calculated using the following formula:

[0017]

[0018] Among them, e is a natural constant, R is the land freeze-thaw index, T is the soil temperature in the high-cold area, i is the number of the monitoring time point in the high-cold area, i = 1, 2, 3..., q, q is the total duration of the monitoring time point in the high-cold area, T i is the mean soil temperature at the i-th monitoring time point in the high-cold region, is the standard soil temperature value.

[0019] Furthermore, the high-altitude cold risk assessment index is calculated using the following formula:

[0020]

[0021] Among them, S is the high-cold risk assessment index, i is the monitoring time point in the high-cold area, i = 1, 2, ..., q, q is the total duration of the monitoring time points in the high-cold area, j is the data number of the temperature series, j = 1, 2, 3 ... N, N is the total number of data numbers of the temperature series, is the jth data in the temperature series at the ith monitoring time point in the high-cold region, x j is the j data of the temperature sequence in the second characteristic data, is the mean temperature of the first characteristic data in the high-cold region, Y i is the vegetation coverage area in the alpine region at the i-th monitoring time point, y is the vegetation coverage area in the second characteristic data, is the mean of the vegetation coverage area at the monitoring time point in the first characteristic data of the alpine region, ρ1 is the temperature weight, and ρ2 is the vegetation coverage area weight.

[0022] An embodiment of the present application provides a high-cold risk assessment system based on big data, including a data acquisition module, a feature extraction module and a data comparison and verification module; wherein the data acquisition module is used to collect equipment data in a high-cold area through a sensor and perform data source comparison and verification to obtain first equipment data, and transmit the collected first equipment data to a constructed first equipment database for storage, wherein the equipment data includes climate data and terrain image data, and the climate data includes ambient temperature, surface temperature and soil temperature; the feature extraction module is used to preprocess and extract features from the first equipment data to obtain first feature data, and obtain a land freeze-thaw index according to the soil temperature in the first feature data, wherein the first feature data includes climate temperature and vegetation coverage area, and the land freeze-thaw index is used to quantify the degree of influence of land freeze-thaw cycles in high-cold areas on soil and surface characteristics; the data comparison and verification module is used to compare and verify the first feature data with preset second feature data to obtain a high-cold risk assessment index, and the high-cold risk assessment index is used to assess the high-cold risk level in high-cold areas.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] 1. By collecting equipment data in high-altitude cold areas through sensors and performing data source comparison, verification and preprocessing, the accuracy and consistency of the data are improved, thereby improving the data quality in high-altitude cold risk assessment, and effectively solving the problem of low data quality in high-altitude cold risk assessment in existing technologies.

[0025] 2. Encode the first device data through arithmetic coding to obtain compressed data, thereby reducing the time and bandwidth of data transmission, thereby improving the efficiency of data transmission and data processing.

[0026] 3. By real-time monitoring of the data transmission process, abnormal situations that occur during data transmission can be monitored and resolved in real time, thereby improving the security and reliability of data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A flow chart of a high-cold risk assessment method based on big data provided in an embodiment of the present application;

[0028] Figure 2 A high-cold risk assessment index diagram provided in an embodiment of the present application;

[0029] Figure 3 A schematic diagram of the structure of a high-cold risk assessment system based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The embodiment of the present application solves the problem of low data quality in high-altitude cold risk assessment in the prior art by providing a high-altitude cold risk assessment method and system based on big data. The data acquisition module is used to collect equipment data in high-altitude cold areas through sensors and compare and verify the data sources to obtain first equipment data. The first equipment data is then transmitted to a constructed first equipment database for storage. During the data transmission process, the data transmission status is monitored in real time at a preset real-time monitoring window. Finally, a feature extraction module is used to preprocess and extract features from the first equipment data to obtain first feature data. The first feature data and the preset second feature data are compared and verified to obtain a high-altitude cold risk assessment index, thereby improving the data quality in high-altitude cold risk assessment.

[0031] The technical solution in the embodiment of the present application is to solve the problem of low data quality in the above-mentioned high-altitude cold risk assessment, and the overall idea is as follows:

[0032] The first device data is obtained by comparing and verifying the data source of the device data, and then the data transmission status is monitored in real time at a preset real-time monitoring window during the data transmission process. Finally, the first device data is preprocessed and feature extracted to obtain the first feature data and compared and verified with the second feature data to obtain the high-altitude cold risk assessment index, thereby achieving the effect of improving the data quality in the high-altitude cold risk assessment.

[0033] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0034] like Figure 1 As shown, it is a flow chart of a high-cold risk assessment method based on big data provided by an embodiment of the present application, the method comprising the following steps: S1 collects equipment data in a high-cold area through a sensor and performs data source comparison and verification to obtain first equipment data, and transmits the collected first equipment data to a constructed first equipment database for storage, the equipment data includes climate data and terrain image data, and the climate data includes ambient temperature, surface temperature and soil temperature; S2 preprocesses and extracts features of the first equipment data to obtain first feature data, and obtains a land freeze-thaw index according to the soil temperature in the first feature data, the first feature data includes climate temperature and vegetation coverage area, and the land freeze-thaw index is used to quantify the degree of influence of land freeze-thaw cycles in high-cold areas on soil and surface characteristics; S3 compares and verifies the first feature data and the preset second feature data to obtain a high-cold risk assessment index, and the high-cold risk assessment index is used to assess the high-cold risk level in high-cold areas.

[0035] In this embodiment, the sensors include temperature sensors and radar sensors, which are used to collect climate data and terrain image data. During the sensor data collection process, fields are added to the collected device data to mark the source and type of the data, which helps to accurately identify the source and data type of the data during subsequent data processing and analysis, and facilitates data classification, thereby improving the data quality in high-altitude cold risk assessment.

[0036] Furthermore, the specific steps of data source comparison and verification are as follows: configure a data source identifier for the collected device data, the data source identifier is used to distinguish the source of the device data, and the device data is grouped according to the data identification field to obtain a data source identification data group, and the data source identification data group is statistically analyzed according to the data source identifier to obtain a verification range, and the device data in the data source identification data group is compared and verified with the verification range to obtain the first device data, and the verification range represents the verification interval determined according to the mean and standard deviation of the data source identification data group.

[0037] In this embodiment, when the sensor device collects data, the geographic coordinates corresponding to the device data are automatically recorded as the data identification source, so as to realize the comparison and verification of the data through the data identification source, group the device data according to the data identification field to obtain the data source identification data group, perform statistical analysis on the data source identification data group to obtain the mean and standard deviation, determine the verification range according to the sum and difference between the mean and the standard deviation, and accurately understand the distribution and characteristics of the data in the data identification data group; compare and verify the data in the data identification data group with the verification range, and remove the data if it is not within the verification range, thereby improving the accuracy of the data, and finally obtaining the first device data; the geographic coordinates represent the data source of the corresponding device data, the data source identification data group is a data group obtained by classification according to the data identification field, and the statistical analysis is used to obtain the mean and standard deviation of the data source identification data group, and the quality of the first device data is improved through data source comparison and verification.

[0038] Furthermore, the specific steps of preprocessing are as follows: obtain the hash value corresponding to the first device data through a hash algorithm, determine whether there is duplicate data in the first device data based on the obtained hash value, remove the duplicate data if so, and record the deduplicated data as the second device data; perform distance analysis on the second device data through an agglomerative hierarchical clustering method to obtain a distance matrix, and obtain a clustering hierarchy diagram based on the distance matrix, determine whether there is abnormal data in the second device data based on the clustering hierarchy diagram, remove the abnormal data if so, and record the second device data after removing the abnormal data as the third device data.

[0039] In this embodiment, the hash value corresponding to the first device data is obtained by using the SHA-256 hash algorithm in the built-in hash lib library in Python, and the generated hash value is compared with the existing hash value. If there are duplicate hash values, the data corresponding to these hash values ​​are removed from the first device data, and the data remaining after the deduplication is processed is recorded as the second device data; the square root of the sum of the squares of the differences between the data in the second device data is obtained by using the Euclidean distance through the agglomerative hierarchical clustering method, and the distance between all the data in the second device data is obtained to obtain a distance matrix, and agglomerative hierarchical clustering is performed according to the distance matrix. Starting from each data in the second device data, the closest data is gradually merged to form a clustering hierarchy to obtain a clustering hierarchy diagram. According to whether there is data that cannot be merged in the clustering hierarchy diagram, if there is data, it is abnormal data of the second device data, and the abnormal data is removed, and the second device data after the abnormal data is removed is recorded as the third device data, and the clustering hierarchy diagram is used to visualize the relationship between the data; through the hash algorithm comparison, the duplicate data is effectively removed to ensure the uniqueness and accuracy of the second device data. Through cluster analysis, the abnormal data in the second device data can be identified and removed, thereby improving the quality and reliability of the third device data.

[0040] Furthermore, the specific steps of feature extraction are as follows: classify the climate temperature in the third device data according to the data type to obtain a temperature data group, and count the temperature mean within a preset time interval to obtain a temperature sequence, the temperature data group includes ambient temperature, surface temperature and soil temperature, and the preset time interval is the total duration of the monitoring time points in the high-cold area; compare and verify the grayscale value of each pixel in the terrain image data in the third device data with the grayscale threshold to obtain the vegetation coverage area, and the grayscale threshold is used to distinguish whether the image is a vegetation coverage area.

[0041] In this embodiment, pixels of the image are obtained according to the terrain image data in the third device data, and the pixel grayscale value is obtained through gray_image in the OpenCV library of Python. The obtained pixel grayscale value is compared and checked with the grayscale threshold. If the grayscale value of the pixel is higher than the grayscale threshold, it is considered that the pixel represents a vegetation coverage area. The number of pixels higher than the grayscale threshold is counted to obtain the vegetation coverage area. The grayscale threshold is the lowest grayscale value of the vegetation coverage area obtained according to historical data. The vegetation coverage area is obtained by counting the number of all pixels determined to be vegetation coverage areas to obtain the proportion of vegetation coverage area in the terrain image. The accurate vegetation coverage area is provided by comparing and checking with the grayscale threshold, thereby improving the accuracy of subsequent calculation of the high-altitude cold risk assessment index.

[0042] Furthermore, the specific steps of transmitting the collected first device data to the constructed first device database for storage are as follows: encoding the first device data through arithmetic coding to obtain compressed data, and transmitting the compressed data to the first device database; after receiving the compressed data, the first device database decompresses the compressed data according to the encoding value of the compressed data to obtain the first device data and stores it in the first device database.

[0043] In this embodiment, the frequency of occurrence of the first device data is counted, and the interval (0, 1) is continuously divided into multiple coding intervals according to the frequency of occurrence of the data. Each coding interval represents a data in the first device data, and the interval size is proportional to the probability of occurrence of the data. The first device data is continuously input and the coding interval is updated. When all the data are completed, the binary representation of the final coding interval is output as compressed data; data decoding uses the same frequency and coding interval as in the compression process as the initial decoder, determines the corresponding first device data in the compressed data according to the coding interval and frequency of the decoder, repeats the operation until the end code is read to stop the operation, and the decoding is completed. The data is compressed and transmitted through algorithm encoding, which improves the reliability of the data during transmission, the compression rate of the data, and the accuracy of decoding.

[0044] Furthermore, the collected first device data is transmitted to the constructed first device database for storage, and real-time monitoring of the data transmission process is also included. The specific method of real-time monitoring of the data transmission process is as follows: during the first device data transmission process, determine whether the data transmission rate and delay obtained at the preset real-time monitoring window exceed the preset threshold value. If so, stop transmission and issue an alarm, otherwise continue monitoring. The preset real-time monitoring window is used to detect the data transmission rate and delay within a preset time period. The preset threshold includes a preset maximum transmission rate and a preset maximum delay time.

[0045] In this embodiment, a preset real-time monitoring window is used to monitor the data transmission rate and delay. In each real-time monitoring window, the data transmission rate of each real-time monitoring window is obtained by recording the amount of data transmitted in each real-time monitoring window and dividing it by the preset time period of each real-time monitoring window; in each real-time monitoring window, the time interval for the first device data to pass through each real-time monitoring window is recorded, and the time interval is the delay time of the data transmission of each real-time monitoring window. The data transmission rate and delay time obtained in each real-time monitoring window are compared with the preset maximum transmission rate and maximum delay time. If it is detected that the data transmission rate exceeds the preset threshold or the delay exceeds the preset threshold, the current data transmission process is stopped, and an alarm is issued to notify relevant personnel or systems for further investigation and processing, otherwise the monitoring of the next real-time monitoring window is continued. The preset real-time monitoring window represents a preset time period, and the preset threshold is the fastest transmission rate and maximum delay time in normal data transmission obtained based on historical data, which improves the efficiency and stability of system operation, and can also respond and adjust quickly when an abnormality occurs, ensuring the smoothness and reliability of the data transmission process.

[0046] Furthermore, the specific steps for obtaining the land freeze-thaw index are as follows: classify the climate temperature in the third device data according to the data type to obtain the soil temperature, and analyze the soil temperature within a preset time interval to obtain the average soil temperature, and at the same time compare and verify the average soil temperature with the standard soil temperature value to obtain the land freeze-thaw index; classify the land freeze-thaw cycle in the high-cold area according to the obtained land freeze-thaw index, and the classification is used to determine the degree of influence of the land freeze-thaw cycle in the high-cold area on the soil and surface characteristics.

[0047] In this embodiment, when the temperature sensor collects data, the source of the temperature data is identified, the acquired temperature type is recorded, and the climate temperature is classified according to the identifier to obtain the soil temperature; the data is divided according to the preset time interval, and the data in each time interval is averaged to obtain the average soil temperature within the preset time; the land freeze-thaw index level is divided according to the soil temperature according to the historical data, and the land freeze-thaw index level includes slight impact, moderate impact, significant impact and severe impact. The land freeze-thaw index level classification table is shown in Table 1:

[0048] Table 1 Land freeze-thaw index classification table

[0049]

[0050]

[0051] Furthermore, the land freeze-thaw index is calculated using the following formula:

[0052]

[0053] Among them, e is a natural constant, R is the land freeze-thaw index, T is the soil temperature in the high-cold area, i is the number of the monitoring time point in the high-cold area, i = 1, 2, 3..., q, q is the total duration of the monitoring time point in the high-cold area, T i is the mean soil temperature at the i-th monitoring time point in the high-cold region, is the standard soil temperature value.

[0054] In this embodiment, the land freeze-thaw index R reflects the independent variable T i and The relative change degree between them, assuming q = 1, the statistical table of land freeze-thaw index is shown in Table 2:

[0055] Table 2 Statistics of data compression effect evaluation values

[0056]

[0057] It can be seen from Table 2 that the fifth group of data has the lowest land freeze-thaw index, and the corresponding land freeze-thaw index level is the lowest. The second group of data has the highest land freeze-thaw index, and the corresponding land freeze-thaw index level is the highest, reaching a serious impact, with severe freezing and thawing of the soil. It can be seen from the table that the smaller the difference between the mean soil temperature and the standard soil temperature value at the monitoring time point in the alpine region, the lower the land freeze-thaw index. It should be understood that the land freeze-thaw index R is the result of calculating the difference between the mean soil temperature and the standard soil temperature value at different monitoring time points in the alpine region, which can capture the overall changes in soil temperature within the monitoring time point in the entire alpine region, which is helpful for data accuracy in data processing. Comprehensive analysis can accurately obtain the land freeze-thaw index, thereby reflecting the degree of influence of the land freeze-thaw cycle in the alpine region on soil and surface properties.

[0058] Furthermore, the high-altitude cold risk assessment index is calculated using the following formula:

[0059]

[0060] Among them, S is the high-cold risk assessment index, i is the monitoring time point in the high-cold area, i = 1, 2, ..., q, q is the total duration of the monitoring time points in the high-cold area, j is the data number of the temperature series, j = 1, 2, 3 ... N, N is the total number of data numbers of the temperature series, is the jth data in the temperature series at the ith monitoring time point in the high-cold region, x j is the j data of the temperature sequence in the second characteristic data, is the mean temperature of the first characteristic data in the high-cold region, Y i is the vegetation coverage area in the alpine region at the i-th monitoring time point, y is the vegetation coverage area in the second characteristic data, is the mean of the vegetation coverage area at the monitoring time point in the first characteristic data of the alpine region, ρ1 is the temperature weight, and ρ2 is the vegetation coverage area weight.

[0061] It is important to understand that the independent variable i in this formula affects and Y i , these are the temperature series and plant coverage area in the first characteristic series of i different alpine regions at the monitoring time point, S is obtained by comparing the real-time characteristic data and Y i With the benchmark data x j and y, as Figure 2 As shown in the figure, it is a schematic diagram of the change of the high-cold risk assessment index provided in the embodiment of the present application. It is assumed that the total duration of the monitoring time points in the high-cold area is 20, the total number of data numbers of the temperature sequence is 30, the temperature weight parameter is 0.6, and the vegetation coverage area weight parameter is 0.4. Figure 2It can be seen that the temperature series difference is positively correlated with the vegetation coverage area difference, and the alpine risk index is positively correlated with the temperature series difference and the vegetation coverage area difference. The vegetation coverage area will decrease with the increase of the temperature series difference, resulting in the continuous increase of the vegetation coverage area difference. With the continuous increase of the temperature series difference and the continuous increase of the vegetation coverage area difference, the alpine risk assessment index continues to rise. The larger the value of the alpine risk assessment index, the higher the probability of alpine risk in the alpine area, and vice versa, the lower the probability of alpine risk in the alpine area, which achieves a more intuitive description of the probability of alpine risk in the alpine area.

[0062] In this embodiment, is the mean value of the temperature in the first characteristic data of the high-cold region. According to the mean values ​​of the ambient temperature, surface temperature and soil temperature in the first characteristic data, the calculation of S consists of two parts. The first part is The second part is based on the calculation of the temperature series. Based on the calculation of vegetation coverage area, two weight parameters are used to better evaluate the effect of changes in the risk of alpine climate change. Comprehensive analysis can accurately obtain the results of the alpine climate change risk assessment index.

[0063] like Figure 3 As shown, it is a structural schematic diagram of a high-cold risk assessment system based on big data provided in an embodiment of the present application. The high-cold risk assessment system based on big data provided in an embodiment of the present application includes: a data acquisition module, a feature extraction module and a data comparison and verification module; wherein the data acquisition module is used to collect equipment data in the high-cold area through a sensor and perform data source comparison and verification to obtain first equipment data, and transmit the collected first equipment data to a constructed first equipment database for storage, the equipment data includes climate data and terrain image data, and the climate data includes ambient temperature, surface temperature and soil temperature; the feature extraction module is used to preprocess and feature extract the first equipment data to obtain first feature data, and obtain a land freeze-thaw index according to the soil temperature in the first feature data, the first feature data includes climate temperature and vegetation coverage area, and the land freeze-thaw index is used to quantify the degree of influence of land freeze-thaw cycles in high-cold areas on soil and surface characteristics; the data comparison and verification module is used to compare and verify the first feature data with the preset second feature data to obtain a high-cold risk assessment index, and the high-cold risk assessment index is used to assess the high-cold risk level in high-cold areas.

[0064] In this embodiment, the sensors include temperature sensors and radar sensors, which are used to obtain climate temperature data and terrain image data in high-altitude cold areas; data source comparison and verification are used to ensure the consistency and accuracy of the collected equipment data; the second characteristic data represents preset indicator characteristic data obtained based on historical data, including climate temperature and vegetation coverage area, which is used to compare and verify the first characteristic data to obtain the high-altitude cold risk index.

[0065] To sum up, the embodiments of the present application collect equipment data in high-altitude cold areas through sensors and perform data source comparison, verification and preprocessing, thereby improving the accuracy and consistency of the data, and further improving the data quality in high-altitude cold risk assessment, effectively solving the problem of low data quality in high-altitude cold risk assessment in the prior art.

[0066] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0068] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0070] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0071] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A high-altitude cold risk assessment method based on big data, characterized in that: The following steps are involved: S1, collecting device data in a high-cold area through a sensor and performing data source comparison and verification to obtain first device data, and transmitting the collected first device data to a constructed first device database for storage, wherein the device data includes climate data and terrain image data, and the climate data includes ambient temperature, surface temperature and soil temperature; S2, preprocessing and feature extraction of the first device data to obtain first feature data, and obtaining a land freeze-thaw index according to the soil temperature in the first feature data, wherein the first feature data includes climate temperature and vegetation coverage area, and the land freeze-thaw index is used to quantify the influence of the land freeze-thaw cycle in the alpine region on the soil and surface characteristics; S3, comparing and verifying the first characteristic data with the preset second characteristic data to obtain a high-cold risk assessment index, wherein the high-cold risk assessment index is used to assess the high-cold risk level in the high-cold area; The specific steps of the pretreatment are as follows: Obtain a hash value corresponding to the first device data by using a hash algorithm, determine whether the first device data contains duplicate data according to the obtained hash value, and if so, remove the duplicate data, and record the deduplicated data as the second device data; Performing distance analysis on the second device data by using an agglomerative hierarchical clustering method to obtain a distance matrix, and obtaining a clustering hierarchy diagram according to the distance matrix, judging whether the second device data has abnormal data according to the clustering hierarchy diagram, and removing the abnormal data if any, and recording the second device data after removing the abnormal data as the third device data; The specific steps of feature extraction are as follows: The climate temperature in the third device data is classified according to the data type to obtain a temperature data group, and the temperature mean value within a preset time interval is counted to obtain a temperature sequence, wherein the temperature data group includes the ambient temperature, the surface temperature and the soil temperature, and the preset time interval is the total duration of the monitoring time points in the high-cold area; Comparing and verifying the grayscale value of each pixel in the terrain image data in the third device data with the grayscale threshold to obtain the vegetation coverage area, wherein the grayscale threshold is used to distinguish whether the image is a vegetation coverage area; The specific steps for obtaining the land freeze-thaw index are as follows: The climate temperature in the data of the third device is classified according to the data type to obtain the soil temperature, and the soil temperature within a preset time interval is analyzed to obtain the soil temperature average value, and the soil temperature average value is compared and verified with the standard soil temperature value to obtain the land freeze-thaw index; The land freeze-thaw cycle in the alpine region is classified into different levels according to the obtained land freeze-thaw index, and the classification is used to judge the influence of the land freeze-thaw cycle in the alpine region on the soil and surface characteristics; The land freeze-thaw index is calculated using the following formula: Among them, e is a natural constant, R is the land freeze-thaw index, T is the soil temperature in the high-cold area, i is the number of the monitoring time point in the high-cold area, i = 1, 2, 3..., q, q is the total duration of the monitoring time point in the high-cold area, T i is the mean soil temperature at the i-th monitoring time point in the high-cold region, is the standard soil temperature value.

2. The high-altitude cold risk assessment method based on big data as claimed in claim 1, characterized in that: The specific steps of the data source comparison and verification are as follows: Configuring a data source identifier for the collected device data, wherein the data source identifier is used to distinguish the source of the device data, and grouping the device data according to the data identifier field to obtain a data source identifier data group; A verification range is obtained by performing statistical analysis on the data source identification data group according to the data source identification, and the device data in the data source identification data group is compared and verified with the verification range to obtain the first device data, wherein the verification range represents a verification interval determined according to the mean and standard deviation of the data source identification data group.

3. The high-altitude cold risk assessment method based on big data as claimed in claim 1, characterized in that: The specific steps of transferring the collected first device data to the constructed first device database for storage are as follows: Encoding the first device data by arithmetic coding to obtain compressed data, and transmitting the compressed data to the first device database; After receiving the compressed data, the first device database decompresses the compressed data according to the encoding value of the compressed data to obtain the first device data and stores the first device data in the first device database.

4. The high-altitude cold risk assessment method based on big data as claimed in claim 1, characterized in that: The step of transmitting the collected first device data to the constructed first device database for storage also includes real-time monitoring of the data transmission process. The specific method of real-time monitoring of the data transmission process is as follows: During data transmission of the first device, determine whether the data transmission rate and delay obtained at the preset real-time monitoring window exceed the preset threshold value. If so, stop transmission and issue an alarm; otherwise, continue monitoring. The preset real-time monitoring window is used to detect the data transmission rate and delay within a preset time period. The preset threshold value includes a preset maximum transmission rate and a preset maximum delay time.

5. The high-altitude cold risk assessment method based on big data as claimed in claim 1, characterized in that: The high-altitude cold risk assessment index is calculated using the following formula: Among them, S is the high-cold risk assessment index, i is the monitoring time point in the high-cold area, i = 1, 2, ..., q, q is the total duration of the monitoring time points in the high-cold area, j is the data number of the temperature series, j = 1, 2, 3 ... N, N is the total number of data numbers of the temperature series, is the jth data in the temperature series at the ith monitoring time point in the high-cold region, x j is the j data of the temperature sequence in the second characteristic data, is the mean temperature of the first characteristic data in the high-cold region, Y i is the vegetation coverage area in the alpine region at the i-th monitoring time point, y is the vegetation coverage area in the second characteristic data, is the mean of the vegetation coverage area at the monitoring time point in the first characteristic data of the alpine region, ρ1 is the temperature weight, and ρ2 is the vegetation coverage area weight.

6. A high-altitude cold risk assessment system based on big data, used to execute the method described in any one of claims 1 to 5, characterized in that: It includes a data acquisition module, a feature extraction module and a data comparison and verification module; The data acquisition module is used to collect equipment data in the high-cold area through sensors and perform data source comparison and verification to obtain first equipment data, and transmit the collected first equipment data to the constructed first equipment database for storage, wherein the equipment data includes climate data and terrain image data, and the climate data includes ambient temperature, surface temperature and soil temperature; The feature extraction module is used to preprocess and extract features from the first device data to obtain first feature data, and obtain a land freeze-thaw index according to the soil temperature in the first feature data, wherein the first feature data includes climate temperature and vegetation coverage area, and the land freeze-thaw index is used to quantify the influence of the land freeze-thaw cycle in the alpine region on the soil and surface characteristics; The data comparison and verification module is used to compare and verify the first characteristic data with the preset second characteristic data to obtain a high-cold risk assessment index, and the high-cold risk assessment index is used to assess the high-cold risk level in high-cold areas.

Images