A method and related equipment for protecting municipal engineering construction data

Abstract

The present application provides a method and related equipment for the security protection of municipal engineering construction data, which belongs to the field of data security protection technology. By acquiring multiple engineering features, the engineering feature sample data at different construction points are determined; multiple central sample data are extracted from all engineering feature sample data to determine the offset decision amount of each engineering feature; multiple feature offset sample data are divided from all engineering feature sample data by each offset decision amount, and the offset correction coefficient of each feature offset sample data is determined according to each feature offset sample data; multiple fusion correction values ​​are determined according to all offset correction coefficients, and the security detection standard is determined according to all fusion correction values; and the security of the engineering construction data is judged by the security detection standard. The scheme of the present application can avoid the influence of the complex linear relationship between the engineering feature sample data on the data offset correction, thereby improving the accuracy of the security detection of municipal engineering construction data.

Description

Technical Field

[0001] The present application relates to the technical field of data security protection, and in particular, to a method and related equipment for protecting the security of municipal engineering construction data. Background Art

[0002] Data security protection is a series of technical means used to ensure the integrity, confidentiality and availability of data throughout its life cycle. These technologies cover the security protection of data in various links such as storage, transmission, and processing. They mainly include data encryption, access control, data backup and recovery, data desensitization, security detection and defense, data integrity protection, data leakage prevention, data auditing, data masking and data destruction. They can promptly detect and respond to potential security threats in data, thereby reducing the risk of data leakage and damage.

[0003] The security protection of municipal engineering construction data is an important safeguard to ensure data security during the construction and operation of urban infrastructure. Engineering construction data covers multiple fields such as urban planning, architectural design, traffic management, and water conservancy projects. By comprehensively using encryption, access control, security detection, auditing, desensitization, and leakage prevention, the security of engineering construction data can be effectively protected to ensure the stable operation of urban infrastructure. In the security detection of engineering construction data, due to differences in construction conditions, construction methods, construction environment, and external interference at different construction sites, the collected engineering construction data has data offset (that is, the distribution and regularity of the data are different), which reduces the accuracy of security detection of engineering construction data. However, in the existing technology, conventional data fusion methods are often used to reduce the impact of data offset on the accuracy of security detection of engineering construction data. However, this method only performs a simple linear combination of different engineering features in the engineering construction data, ignoring the possible complex linear relationship between engineering feature sample data at different construction sites, and thus cannot completely solve the data offset phenomenon. Therefore, how to avoid the impact of the complex linear relationship between engineering feature sample data on data offset correction and improve the accuracy of security detection of engineering construction data has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a method and related equipment for the security protection of municipal engineering construction data, which can avoid the influence of the complex linear relationship between engineering feature sample data on data offset correction, thereby improving the accuracy of engineering construction data security detection.

[0005] In a first aspect, the present application provides a method for protecting the security of municipal engineering construction data, comprising the following steps:

[0006] Acquire multiple engineering features from the target municipal engineering construction data, and then determine engineering feature sample data at different construction points through all the engineering features;

[0007] Extracting a plurality of central sample data from all engineering feature sample data, and determining the offset decision amount of each engineering feature based on the discrete features between each engineering feature sample data and each central sample data;

[0008] Dividing a plurality of feature offset sample data from all the engineering feature sample data by the offset decision amount of each engineering feature, and determining an offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data;

[0009] Perform feature fusion on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, then perform offset correction on each offset feature fusion value according to all offset correction coefficients to obtain multiple fusion correction values, and determine the safety detection standard of municipal engineering construction data based on all fusion correction values;

[0010] The safety detection standard is used to determine whether the target municipal engineering construction data is safe, and then data security protection is completed based on the judgment result.

[0011] In some embodiments, extracting a plurality of central sample data from all engineering feature sample data specifically includes:

[0012] Select an engineering feature as the selected engineering feature;

[0013] Obtain all engineering feature values ​​corresponding to the selected engineering feature from all engineering feature sample data;

[0014] Determine multiple central characteristic values ​​of the selected engineering characteristic based on all engineering characteristic values;

[0015] Continue to determine multiple central eigenvalues ​​of the remaining engineering features;

[0016] A plurality of central sample data are determined according to the central characteristic values ​​corresponding to the respective engineering characteristics.

[0017] In some embodiments, determining the offset decision amount of each engineering feature based on the discrete features between each engineering feature sample data and each center sample data specifically includes:

[0018] Determine the sample data discrete amount between each engineering feature sample data and each center sample data, and use all sample data discrete amounts as discrete features between each engineering feature sample data and each center sample data;

[0019] Select an engineering feature as the selected engineering feature;

[0020] Determine all feature offsets of the selected engineering feature according to the engineering feature value of the selected engineering feature in all engineering feature sample data and the corresponding engineering feature value in each center sample data;

[0021] Determine the offset decision amount of the selected engineering feature according to all sample data discrete amounts and all feature offset amounts of the selected engineering feature;

[0022] Continue to determine the offset decision amounts for the remaining engineering features.

[0023] In some embodiments, dividing a plurality of feature offset sample data from all engineering feature sample data by using the offset decision amount of each engineering feature specifically includes:

[0024] Determine the offset threshold of the corresponding engineering feature according to the engineering feature value of each engineering feature in all engineering feature sample data;

[0025] All engineering feature sample data are divided into a plurality of feature offset sample data according to the offset threshold of each engineering feature and the offset decision amount of each engineering feature.

[0026] In some embodiments, determining the offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data specifically includes:

[0027] Selecting a feature offset sample data as selected feature offset sample data;

[0028] Determine a feature distribution moment of the selected feature offset sample data according to all engineering feature values ​​in the selected feature offset sample data, wherein the feature distribution moment is distribution attribute information of the corresponding engineering feature in the selected feature offset sample data;

[0029] Determine an offset correction coefficient for the selected feature offset sample data according to the feature distribution moment and all engineering feature values ​​in the selected feature offset sample data;

[0030] Continue to determine the offset correction coefficients for the remaining feature offset sample data.

[0031] In some embodiments, performing feature fusion on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values ​​specifically includes:

[0032] Selecting a feature offset sample data as selected feature offset sample data;

[0033] Obtaining the maximum engineering characteristic value and the minimum engineering characteristic value in the selected characteristic offset sample data;

[0034] According to the maximum engineering feature value and the minimum engineering feature value, all engineering feature values ​​in the selected feature offset sample data are fused into an offset feature fusion value of the selected feature offset sample data;

[0035] Continue to determine the offset feature fusion values ​​of the remaining feature offset sample data, thereby obtaining multiple offset feature fusion values.

[0036] In some embodiments, determining the safety detection standard of municipal engineering construction data based on all fused correction values ​​specifically includes:

[0037] Determine the security feature aggregation amount during security detection based on all fused correction values;

[0038] The safety detection standard of municipal engineering construction data is determined by the safety feature aggregation amount.

[0039] In a second aspect, the present application provides a security protection system for municipal engineering construction data, which includes a data security protection unit, and the data security protection unit includes:

[0040] An acquisition module is used to acquire multiple engineering features from the target municipal engineering construction data, and then determine the engineering feature sample data at different construction points through all the engineering features;

[0041] A processing module, used to extract multiple central sample data from all engineering feature sample data, and determine the offset decision amount of each engineering feature based on the discrete features between each engineering feature sample data and each central sample data;

[0042] The processing module is further used to divide a plurality of feature offset sample data from all engineering feature sample data according to the offset decision amount of each engineering feature, and determine the offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data;

[0043] The processing module is also used to perform feature fusion on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, and then perform offset correction on each offset feature fusion value according to all offset correction coefficients to obtain multiple fusion correction values, and determine the safety detection standard of municipal engineering construction data according to all fusion correction values;

[0044] The execution module is used to determine whether the target municipal engineering construction data is safe through the security detection standard, and then complete the data security protection according to the judgment result.

[0045] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned method for security protection of municipal engineering construction data.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for securely protecting municipal engineering construction data.

[0047] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0048] In the security protection method and related equipment for municipal engineering construction data provided by the present application, after obtaining multiple engineering features in the target municipal engineering construction data, the engineering feature sample data at different construction points are determined through all the engineering features; multiple central sample data are extracted from all the engineering feature sample data, and the offset decision amount of each engineering feature is determined based on the discrete features between each engineering feature sample data and each central sample data; multiple feature offset sample data are divided from all the engineering feature sample data through the offset decision amount of each engineering feature, and the offset correction coefficient of each feature offset sample data is determined according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data; feature fusion is performed on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, and then offset correction is performed on each offset feature fusion value according to all the offset correction coefficients to obtain multiple fusion correction values, and the security detection standard of the engineering construction data is determined according to all the fusion correction values; the target municipal engineering construction data is judged whether it is safe according to the security detection standard, and the data security protection is completed according to the judgment result.

[0049] It can be seen that in this application, after obtaining multiple engineering features in the target municipal engineering construction data, first, the engineering feature sample data at different construction points are determined through all the engineering features, and then multiple center sample data are extracted from all the engineering feature sample data, so as to determine the degree of offset of the corresponding engineering feature in all the sample data according to the discrete features between each engineering feature sample data and each center sample data, that is, the offset decision amount, and then after selecting the engineering features with a higher degree of offset, the sample data composed of the engineering features with a higher degree of offset in all the engineering feature sample data are used as the feature offset sample data in this application, so as to obtain multiple feature offset sample data, and secondly, the offset correction coefficient of each feature offset sample data is determined according to the distribution attribute information of the corresponding engineering features in each feature offset sample data, and the present application uses the offset correction coefficient to characterize the overall offset degree of the corresponding feature offset sample data, and then, the engineering feature values ​​in each feature offset sample data are feature fused to obtain multiple offset feature fusion values. Afterwards, all offset correction coefficients are used to perform offset correction on each offset feature fusion value to obtain multiple fusion correction values, and then the safety detection standard of the engineering construction data is determined based on all the fusion correction values, and the safety of the target municipal engineering construction data is judged by the safety detection standard, thereby achieving the safety protection of the engineering construction data. The present application uses the offset correction coefficient to correct the result obtained by data fusion (i.e., offset feature fusion value), that is, when the overall offset degree of the corresponding feature offset sample data is high, the corresponding offset correction coefficient is small, so that the high overall offset degree is corrected by a smaller offset correction coefficient, so that on the basis of conventional data fusion, constraints are imposed on the engineering features by the offset correction coefficient, so as to avoid excessive reliance on certain engineering features for the safety detection of engineering construction data, thereby reducing the influence of complex linear relationships on safety detection; in summary, the scheme of the present application can avoid the influence of complex linear relationships between engineering feature sample data on data offset correction, thereby improving the accuracy of safety detection of engineering construction data. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flowchart of a method for protecting the security of municipal engineering construction data according to some embodiments of the present application;

[0051] Figure 2 is a schematic diagram of a process for determining an offset correction coefficient according to some embodiments of the present application;

[0052] Figure 3 is a schematic diagram of a process for determining an offset feature fusion value according to some embodiments of the present application;

[0053] Figure 4 is a structural block diagram of a data security protection unit according to some embodiments of the present application;

[0054] Figure 5 It is a diagram of the internal structure of a computer device for implementing a method for securely protecting municipal engineering construction data as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0055] The core of this application is to obtain multiple engineering features in the target municipal engineering construction data, and then determine the engineering feature sample data at different construction points through all the engineering features; extract multiple central sample data from all the engineering feature sample data, and determine the offset decision amount of each engineering feature based on the discrete features between each engineering feature sample data and each central sample data; divide multiple feature offset sample data from all the engineering feature sample data through the offset decision amount of each engineering feature, and determine the offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data; perform feature fusion on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, and then perform offset correction on each offset feature fusion value according to all the offset correction coefficients to obtain multiple fusion correction values, and determine the safety detection standard of the engineering construction data according to all the fusion correction values; judge whether the target municipal engineering construction data is safe through the safety detection standard, and then complete data security protection according to the judgment result; the influence of the complex linear relationship between the engineering feature sample data on the data offset correction can be avoided, thereby improving the accuracy of the safety detection of the engineering construction data.

[0056] 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. Figure 1 , which is a flow chart of a method for protecting the security of municipal engineering construction data according to some embodiments of the present application. The method 100 for protecting the security of municipal engineering construction data mainly includes the following steps:

[0057] In step 101, a plurality of engineering features are obtained from the target municipal engineering construction data, and then engineering feature sample data at different construction points are determined through all the engineering features.

[0058] In specific implementation, the construction time, construction progress, construction type and air quality index in the target municipal engineering construction data can be used as multiple engineering features, and then the construction time, construction progress, construction type and air quality index at different construction points can be determined, and the set of construction time, construction progress, construction type and air quality index at each construction point can be used as the engineering feature sample data at the corresponding construction point.

[0059] It should be noted that the engineering feature sample data described in the present application contains multiple engineering feature values, one engineering feature value corresponds to one engineering feature, and the engineering features are divided into numerical type and text type. Among them, the numerical engineering features can directly use the corresponding numerical values ​​as the engineering features in the present application, and the text-type engineering features can adopt the unique hot encoding technology in the prior art, and convert the text in the text-type engineering features into BCD (Binary-Coded Decimal) code and then use it as the engineering features in the present application.

[0060] In step 102, a plurality of central sample data are extracted from all engineering feature sample data, and the offset decision amount of each engineering feature is determined based on the discrete features between each engineering feature sample data and each central sample data.

[0061] In some embodiments, extracting a plurality of central sample data from all engineering feature sample data may be achieved by using the following steps:

[0062] Select an engineering feature as the selected engineering feature;

[0063] Obtain all engineering feature values ​​corresponding to the selected engineering feature from all engineering feature sample data;

[0064] Determine multiple central characteristic values ​​of the selected engineering characteristic based on all engineering characteristic values;

[0065] Continue to determine multiple central eigenvalues ​​of the remaining engineering features;

[0066] A plurality of central sample data are determined according to the central characteristic values ​​corresponding to the respective engineering characteristics.

[0067] In specific implementation, the following method can be used to determine multiple central feature values ​​of the selected engineering feature based on all engineering feature values, namely: first, determine the square root of the square difference between every two engineering feature values, and use all the obtained results as the similarity index of the K-means clustering algorithm in the prior art. After obtaining multiple cluster centers through the K-means clustering algorithm, each cluster center is used as the central feature value in this application, thereby obtaining multiple central feature values ​​of the selected engineering feature. In other embodiments, it can also be determined by other methods, which will not be repeated here.

[0068] It should be noted that, in the present application, when the K-means clustering algorithm in the prior art is used for the engineering feature values ​​corresponding to each engineering feature, the number of cluster centers selected is the same, that is, the total number of central feature values ​​corresponding to each engineering feature is the same. In addition, the central feature value corresponding to each engineering feature has a unique ranking number, and the ranking number is determined according to the size of the central feature value corresponding to the engineering feature. For example, when the central feature values ​​corresponding to the engineering features are ranked as 2.1, 3.5, 3.7, 5.5 and 6.1, the ranking number corresponding to the central feature value 2.1 is 1, and the ranking number corresponding to the central feature value 3.5 is 2 (obviously, when the central feature values ​​are 3.7, 5.5 and 6.1, the corresponding ranking numbers are 3, 4 and 5, respectively); as a preferred embodiment, determining multiple central sample data according to the central feature values ​​corresponding to each engineering feature can be implemented in the following manner, that is, taking a set of central feature values ​​with the same ranking number in each engineering feature as central sample data, thereby obtaining multiple central sample data. In other embodiments, it can also be determined by other methods, which are not limited here.

[0069] It should be noted that the central sample data is used to classify each engineering feature sample data. The present application adopts the Euclidean distance in the prior art as the similarity index between each engineering feature sample data and all the central sample data, so as to classify each engineering feature sample data into the corresponding cluster of the central sample data. Therefore, in some embodiments, the offset decision amount of each engineering feature is determined based on the discrete features between each engineering feature sample data and each central sample data, which can be implemented by the following steps:

[0070] Determine the sample data discrete amount between each engineering feature sample data and each center sample data, and use all sample data discrete amounts as discrete features between each engineering feature sample data and each center sample data;

[0071] Select an engineering feature as the selected engineering feature;

[0072] Determine all feature offsets of the selected engineering feature according to the engineering feature value of the selected engineering feature in all engineering feature sample data and the corresponding engineering feature value in each center sample data;

[0073] Determine the offset decision amount of the selected engineering feature according to all sample data discrete amounts and all feature offset amounts of the selected engineering feature;

[0074] Continue to determine the offset decision amounts for the remaining engineering features.

[0075] In specific implementation, the sample data discrete amount between each engineering feature sample data and each center sample data can be determined in the following manner, namely: first, select an engineering feature sample data; secondly, use the Euclidean distance algorithm in the prior art to determine the Euclidean distance between the engineering feature sample data and each center sample data; then use the Euclidean distance between the engineering feature sample data and each center sample data as the sample data discrete amount; repeat the above steps to determine the sample data discrete amount between the remaining engineering feature sample data and each center sample data; in other embodiments, it can also be determined by other methods, which are not limited here.

[0076] It should be noted that the sample data discrete amount represents the degree of discreteness between the engineering feature sample data and the central sample data. The larger the sample data discrete amount, the higher the degree of discreteness between the engineering feature sample data and the central sample data. The smaller the sample data discrete amount, the lower the degree of discreteness between the engineering feature sample data and the central sample data.

[0077] In specific implementation, determining all feature offsets of the selected engineering feature based on the engineering feature value of the selected engineering feature in all engineering feature sample data and the corresponding engineering feature value in each center sample data can be achieved in the following manner, namely: first, selecting the engineering feature value of the selected engineering feature in one engineering feature sample data, determining the absolute value of the difference between the engineering feature value and the engineering feature value corresponding to the selected engineering feature in each center sample data, repeating the above steps to determine the absolute value of the difference between the engineering feature value of the selected engineering feature in the remaining engineering feature sample data and the corresponding engineering feature value in each center sample data, and finally, using all the obtained results as all feature offsets of the selected engineering feature. In other embodiments, it can also be determined by other methods, which will not be repeated here.

[0078] It should be noted that the feature offset is used to quantify the change of the engineering feature value in the sample data, reflecting the offset of the corresponding engineering feature value between different sample data. The feature offset characterizes the degree of offset of the corresponding engineering feature between the selected engineering feature sample data and the central sample data. The larger the feature offset, the higher the degree of offset of the corresponding engineering feature between the selected engineering feature sample data and the central sample data. The smaller the feature offset, the lower the degree of offset of the corresponding engineering feature between the selected engineering feature sample data and the central sample data.

[0079] It should be noted that each feature offset has a unique corresponding engineering feature sample data and central sample data. Therefore, in the specific implementation, the offset decision amount of the selected engineering feature can be determined according to the discrete amounts of all sample data and all feature offsets of the selected engineering feature. The following method can be used, namely: first, select a feature offset, obtain the sample data discrete amount between the engineering feature sample data and the central sample data corresponding to the feature offset, determine the result of the product of the feature offset and the corresponding sample data discrete amount, repeat the above steps, determine the results corresponding to the remaining feature offsets, and secondly, add the results corresponding to all feature offsets and divide them by the sum of all sample data discrete amounts. Finally, the result obtained is used as the offset decision amount of the engineering feature.

[0080] It should be noted that the offset decision amount characterizes the degree of offset of the corresponding engineering feature in all sample data. The larger the offset decision amount, the higher the degree of offset of the corresponding engineering feature in all sample data. The smaller the offset decision amount, the lower the degree of offset of the corresponding engineering feature in all sample data. The offset decision amount is used to reflect the stability and consistency of the corresponding engineering feature.

[0081] In step 103, multiple feature offset sample data are divided from all engineering feature sample data according to the offset decision amount of each engineering feature, and the offset correction coefficient of each feature offset sample data is determined according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data.

[0082] In some embodiments, dividing a plurality of feature offset sample data from all engineering feature sample data by the offset decision amount of each engineering feature can be implemented by the following steps:

[0083] Determine the offset threshold of the corresponding engineering feature according to the engineering feature value of each engineering feature in all engineering feature sample data;

[0084] All engineering feature sample data are divided into a plurality of feature offset sample data according to the offset threshold of each engineering feature and the offset decision amount of each engineering feature.

[0085] In specific implementation, determining the offset threshold of the corresponding engineering feature according to the engineering feature value of each engineering feature in all engineering feature sample data can be achieved in the following manner, namely: first, selecting an engineering feature, obtaining the engineering feature value of the engineering feature in all engineering feature sample data, then determining the standard deviation and mean of all engineering feature values ​​of the engineering feature, and finally, multiplying the mean by 2 and adding the standard deviation to obtain the result as the offset threshold of the engineering feature. In other embodiments, it can also be determined by other methods, which will not be repeated here.

[0086] In some embodiments, dividing all engineering feature sample data into a plurality of feature offset sample data by using the offset threshold of each engineering feature and the offset decision amount of each engineering feature can be implemented by the following steps:

[0087] The offset of all engineering features is judged by using the offset threshold and offset decision amount of each engineering feature to obtain multiple engineering offset features;

[0088] All engineering feature sample data are divided into a plurality of feature offset sample data through all engineering offset features.

[0089] In specific implementation, all engineering features are subjected to offset judgment through the offset threshold and offset decision amount of each engineering feature, and multiple engineering offset features can be obtained in the following manner, namely: first, an engineering feature is selected, and then, when the offset decision amount of the engineering feature is greater than or equal to the offset threshold, the engineering feature is judged as an engineering offset feature; when the offset decision amount of the engineering feature is less than the offset threshold, no processing is performed, and the above steps are repeated to perform offset judgment on the remaining engineering features, thereby obtaining multiple engineering offset features.

[0090] In specific implementation, dividing all engineering feature sample data into multiple feature offset sample data through all engineering offset features can be achieved in the following manner, namely: first, selecting an engineering feature sample data, then obtaining the engineering feature values ​​corresponding to each engineering feature judged as an engineering offset feature in the engineering feature sample data, and then taking a set consisting of the engineering feature values ​​corresponding to all engineering features judged as engineering offset features as a feature offset sample data, repeating the above steps to determine the feature offset sample data corresponding to the remaining engineering feature sample data, thereby obtaining multiple feature offset sample data, which can also be determined by other methods in other embodiments, which will not be repeated here.

[0091] In some embodiments, reference Figure 2 As shown, this figure is a schematic diagram of a flow chart of determining an offset correction coefficient shown in some embodiments of the present application. Determining the offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data can be implemented by the following steps:

[0092] First, in step 1031, a feature offset sample data is selected as selected feature offset sample data;

[0093] Then, in step 1032, the feature distribution moment of the selected feature offset sample data is determined according to all engineering feature values ​​in the selected feature offset sample data, wherein the feature distribution moment is the distribution attribute information of the corresponding engineering feature in the selected feature offset sample data;

[0094] Next, in step 1033, the offset correction coefficient of the selected feature offset sample data is determined according to the feature distribution moment and all engineering feature values ​​in the selected feature offset sample data;

[0095] Finally, in step 1034, the offset correction coefficients of the remaining feature offset sample data continue to be determined.

[0096] It should be noted that the characteristic distribution moment described in the present application characterizes the degree of fluctuation in the distribution of all engineering feature values ​​in the corresponding feature offset sample data. The larger the characteristic distribution moment, the greater the degree of fluctuation in the distribution of each engineering feature value in the corresponding feature offset sample data. The smaller the characteristic distribution moment, the smaller the degree of fluctuation in the distribution of each engineering feature value in the corresponding feature offset sample data. As a preferred embodiment, determining the characteristic distribution moment of the selected feature offset sample data based on all engineering feature values ​​in the selected feature offset sample data can be achieved in the following manner, namely: taking the variance of all engineering feature values ​​in the selected feature offset sample data as the characteristic distribution moment. In other embodiments, it can also be determined by other methods, which will not be repeated here.

[0097] In specific implementation, determining the offset correction coefficient of the selected feature offset sample data based on the feature distribution moment and all engineering feature values ​​in the selected feature offset sample data can be achieved in the following manner, namely: first, determining the average value of all engineering feature values ​​in the selected feature offset sample data; second, determining the square of the difference between each engineering feature value in the selected feature offset sample data and the average value; then, determining the square of the difference between each engineering feature value in the selected feature offset sample data and the feature distribution moment; finally, adding the squares of the differences between each engineering feature value and the average value and dividing the sum by the sum of the squares of the differences between each engineering feature value and the feature distribution moment to obtain the offset correction coefficient of the selected feature offset sample data.

[0098] It should be noted that the offset correction coefficient described in the present application is used to characterize the overall offset degree of the corresponding feature offset sample data. The larger the offset correction coefficient, the lower the overall offset degree of the corresponding feature offset sample data. The smaller the offset correction coefficient, the higher the overall offset degree of the corresponding feature offset sample data. That is, when the overall offset degree of the corresponding feature offset sample data is high, the corresponding offset correction coefficient is small, so that the high overall offset degree is corrected by a smaller offset correction coefficient, thereby realizing the correction of data offset phenomenon at different construction points.

[0099] In step 104, feature fusion is performed on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, and then offset correction is performed on each offset feature fusion value according to all offset correction coefficients to obtain multiple fusion correction values, and the safety detection standard of the engineering construction data is determined based on all fusion correction values.

[0100] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of determining the offset feature fusion value shown in some embodiments of the present application. The engineering feature values ​​in each feature offset sample data are subjected to feature fusion to obtain multiple offset feature fusion values, which can be achieved by using the following steps:

[0101] First, in step 1041, a feature offset sample data is selected as selected feature offset sample data;

[0102] Then, in step 1042, the maximum engineering feature value and the minimum engineering feature value in the selected feature offset sample data are obtained;

[0103] Next, in step 1043, all engineering feature values ​​in the selected feature offset sample data are fused into offset feature fusion values ​​of the selected feature offset sample data according to the maximum engineering feature value and the minimum engineering feature value;

[0104] Finally, in step 1044, the offset feature fusion values ​​of the remaining feature offset sample data are continued to be determined, thereby obtaining multiple offset feature fusion values.

[0105] In specific implementation, all engineering feature values ​​in the selected feature offset sample data are fused into the offset feature fusion value of the selected feature offset sample data according to the maximum engineering feature value and the minimum engineering feature value. This can be achieved in the following manner, namely: first, an engineering feature value in the selected feature offset sample data is selected, and the result after subtracting the minimum engineering feature value from the engineering feature value is compared with the difference between the maximum engineering feature value and the minimum engineering feature value, and the obtained result is used as the transition engineering feature value of the engineering feature value, and the above steps are repeated to determine the transition engineering feature values ​​of the remaining engineering feature values ​​in the selected feature offset sample data. Finally, the average value of all transition engineering feature values ​​is used as the offset feature fusion value of the selected feature offset sample data. In other embodiments, it can also be determined by other methods, which will not be repeated here.

[0106] In some embodiments, performing offset correction on each offset feature fusion value according to all offset correction coefficients to obtain multiple fusion correction values ​​can be implemented by the following steps:

[0107] Selecting a feature offset sample data as selected feature offset sample data;

[0108] Obtaining an offset correction coefficient corresponding to the selected feature offset sample data;

[0109] Correcting the offset feature fusion value corresponding to the selected feature offset sample data according to the offset correction coefficient to obtain a fusion correction value corresponding to the selected feature offset sample data;

[0110] Continue to determine the fusion correction values ​​corresponding to the remaining feature offset sample data, thereby obtaining multiple fusion correction values.

[0111] In specific implementation, the offset feature fusion value corresponding to the selected feature offset sample data is corrected according to the offset correction coefficient. The process of obtaining the fusion correction value corresponding to the selected feature offset sample data can be implemented in the following manner, namely: the product of the offset correction coefficient and the offset feature fusion value corresponding to the selected feature offset sample data is used as the fusion correction value corresponding to the selected feature offset sample data. In other embodiments, it can also be determined by other methods, which will not be repeated here.

[0112] It should be noted that the feature fusion described in the present application refers to the process of fusing all engineering feature values ​​into offset feature fusion values ​​of corresponding feature offset sample data based on the distribution information of all engineering feature values ​​in the feature offset sample data, and the overall fluctuation degree of the corresponding feature offset sample data can be reflected by the fusion result (i.e., the offset feature fusion value). In addition, the offset correction described in the present application refers to reducing the overall fluctuation degree of feature offset sample data with a larger overall offset degree through the offset correction coefficient, which can avoid the situation where the overall fluctuation degree of the corresponding feature offset sample data increases due to the offset of the engineering construction data, thereby reducing the impact of the offset of the engineering construction data on the safety detection of the engineering construction data.

[0113] In some embodiments, determining the safety detection standard of engineering construction data based on all fused correction values ​​can be implemented by the following steps:

[0114] Determine the security feature aggregation amount during security detection based on all fused correction values;

[0115] The safety detection standard of the engineering construction data is determined by the safety feature aggregation amount.

[0116] It should be noted that the security feature aggregation amount described in the present application is used to characterize the degree of discreteness between all fused correction values. The larger the security feature aggregation amount, the higher the degree of discreteness between all fused correction values, and the smaller the security feature aggregation amount, the lower the degree of discreteness between all fused correction values. As a preferred embodiment, determining the security feature aggregation amount during security detection based on all fused correction values ​​can be implemented in the following manner, namely: first, using Python in the existing programming language, and selecting the NumPy library, sorting each fused correction value from large to small, and then obtaining the fused correction values ​​corresponding to the top 25% of the distribution endpoints and the fused correction values ​​corresponding to the top 75% of the distribution endpoints from the sorted results. Finally, after subtracting the fused correction value corresponding to the top 25% of the distribution endpoints from the fused correction value corresponding to the top 75% of the distribution endpoints, the obtained result is used as the security feature aggregation amount during security detection. In other embodiments, it can also be determined by other methods, which are not limited here.

[0117] In specific implementation, the safety detection standard for engineering construction data determined by the security feature aggregation amount can be achieved in the following manner, namely: first, the aggregation adjustment coefficient and the discrete adjustment coefficient are obtained, and then the variance of the engineering feature fusion data is determined. Finally, the security feature aggregation amount is multiplied by the aggregation adjustment coefficient plus the variance of the engineering feature fusion data and the discrete adjustment coefficient as the safety detection standard for engineering construction data. In other embodiments, it can also be determined by other methods, which will not be repeated here.

[0118] It should be noted that the security detection in the present application can, for example, be to monitor whether the engineering construction data has been invaded, and determine whether the engineering construction data is safe through security detection standards. The higher the security detection standard, the stricter the standard for determining whether the engineering construction data has been invaded, and the lower the security detection standard, the looser the standard for determining whether the engineering construction data has been invaded. In addition, the aggregation adjustment coefficient in the present application is used to control the sensitivity of the security detection standard to the deviation of the engineering construction data distribution center. The larger the aggregation adjustment coefficient, the higher the sensitivity of the security detection standard to the deviation of the engineering construction data distribution center. The smaller the aggregation adjustment coefficient, the lower the sensitivity of the security detection standard to the deviation of the engineering construction data distribution center. When a larger aggregation adjustment coefficient is set, more data intrusions will be detected. The discrete adjustment coefficient is used to control the sensitivity of the security detection standard to the overall discreteness of the engineering construction data. The larger the discrete adjustment coefficient, the The higher the sensitivity of the security detection standard to the overall discreteness of the engineering construction data, the smaller the discrete adjustment coefficient, and the lower the sensitivity of the security detection standard to the overall discreteness of the engineering construction data. When the security detection standard is too large, some engineering feature sample data that have actually been invaded may be identified as not being invaded. When the security detection standard is too small, some engineering feature sample data that have not been invaded may be misjudged as being invaded, thereby reducing the accuracy of the security detection of the engineering construction data. Therefore, as a preferred embodiment, after setting different aggregation adjustment coefficients and discrete adjustment coefficients, the influence of different aggregation adjustment coefficients and discrete adjustment coefficients on the security detection accuracy may be determined by experimental methods, so that the aggregation adjustment coefficient and discrete adjustment coefficient corresponding to the experimental control group with the highest security detection accuracy are used as the aggregation adjustment coefficient and discrete adjustment coefficient of the present application. In other embodiments, they may also be determined by other methods, which are not limited here.

[0119] In step 105, the security detection standard is used to determine whether the target municipal engineering construction data is safe, and then data security protection is completed based on the determination result.

[0120] It should be noted that each fusion correction value in the engineering feature fusion data corresponds to a feature offset sample data. Therefore, in some embodiments, the safety detection standard is used to determine whether the target municipal engineering construction data is safe, and then the data security protection is completed according to the judgment result. The following steps can be used to achieve this:

[0121] Selecting a fusion correction value as a selected fusion correction value;

[0122] Obtaining feature offset sample data corresponding to the selected fusion correction value;

[0123] Performing safety judgment on the feature offset sample data according to the safety detection standard and the selected fusion correction value;

[0124] Continue to make safety judgments on the feature offset sample data corresponding to the remaining fusion correction values;

[0125] Thus, data security protection is completed based on the judgment results.

[0126] In specific implementation, the security judgment of the feature offset sample data based on the security detection standard and the selected fusion correction value can be achieved in the following manner, namely: first, when the selected fusion correction value is greater than or equal to the security detection standard, it is judged that an intrusion has occurred in the feature offset sample data corresponding to the selected fusion correction value; then, when the selected fusion correction value is less than the security detection standard, it is judged that no intrusion has occurred in the feature offset sample data corresponding to the selected fusion correction value.

[0127] In specific implementation, data security protection can be achieved according to the results of the judgment in the following manner, namely: first, when the feature offset sample data corresponding to the fusion correction value is judged to be an intrusion, an alarm is sent to the designated municipal unit, and the construction point corresponding to the feature offset sample data is recorded; when the feature offset sample data corresponding to the fusion correction value is judged to be no intrusion, no processing is performed; the present application completes the data security protection of the target municipal engineering construction data by performing intrusion judgment on each feature offset sample data.

[0128] In addition, in another aspect of the present application, in some embodiments, the present application provides a security protection system for municipal engineering construction data, the system includes a data security protection unit, reference Figure 4 , which is a structural block diagram of a data security protection unit according to some embodiments of the present application, the data security protection unit 200 includes: an acquisition module 201, a processing module 202 and an execution module 203, which are described as follows:

[0129] Acquisition module 201, in this application, acquisition module 201 is mainly used to acquire multiple engineering features in the target municipal engineering construction data, and then determine the engineering feature sample data at different construction points through all the engineering features;

[0130] Processing module 202, in this application, processing module 202 is mainly used to extract multiple central sample data from all engineering feature sample data, and determine the offset decision amount of each engineering feature based on the discrete features between each engineering feature sample data and each central sample data;

[0131] In specific implementation, the processing module 202 in the present application is also used to divide a plurality of feature offset sample data from all engineering feature sample data according to the offset decision amount of each engineering feature, and determine the offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data;

[0132] In addition, the processing module 202 in the present application is also used to perform feature fusion on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, and then perform offset correction on each offset feature fusion value according to all offset correction coefficients to obtain multiple fusion correction values, and determine the safety detection standard of the engineering construction data according to all fusion correction values;

[0133] Execution module 203, in this application, execution module 203 is mainly used to determine whether the target municipal engineering construction data is safe through the security detection standard, and then complete data security protection according to the judgment result.

[0134] In addition, in some embodiments, the present application also provides a computer device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned method for security protection of municipal engineering construction data.

[0135] In some embodiments, reference Figure 5 , which is an internal structure diagram of a computer device for implementing a method for protecting the security of municipal engineering construction data according to some embodiments of the present application. The method for protecting the security of municipal engineering construction data in the above embodiments can be Figure 5 The computer device 300 shown in the figure is implemented, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303 and at least one communication interface 304.

[0136] Processor 301 may be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC) or one or more components for controlling the execution of the method for protecting the municipal engineering construction data in the present application.

[0137] The communication bus 302 is used to transmit information between the above components.

[0138] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0139] The memory 303 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The security protection method for municipal engineering construction data in the above embodiment can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0140] The communication interface 304 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0141] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0142] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0143] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for protecting the security of municipal engineering construction data.

[0144] In summary, the embodiments of the present application disclose a method and related equipment for protecting the security of municipal engineering construction data. After obtaining multiple engineering features from the target municipal engineering construction data, the engineering feature sample data at different construction points are determined through all the engineering features; multiple central sample data are extracted from all the engineering feature sample data, and the offset decision amount of each engineering feature is determined based on the discrete features between each engineering feature sample data and each central sample data; multiple feature offset sample data are divided from all the engineering feature sample data through the offset decision amount of each engineering feature, and the offset correction coefficient of each feature offset sample data is determined according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data; feature fusion is performed on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, and then offset correction is performed on each offset feature fusion value according to all the offset correction coefficients to obtain multiple fusion correction values, and the security detection standard of the engineering construction data is determined according to all the fusion correction values; whether the target municipal engineering construction data is safe is judged by the security detection standard, and then the data security protection is completed according to the judgment result; the influence of the complex linear relationship between the engineering feature sample data on the data offset correction can be avoided, thereby improving the accuracy of the security detection of the engineering construction data.

[0145] Although the preferred embodiments of the present application 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 falling within the scope of the present application.

[0146] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for protecting the security of municipal engineering construction data, characterized in that: The steps include: Acquire multiple engineering features from the target municipal engineering construction data, and then determine engineering feature sample data at different construction points through all the engineering features; Extracting a plurality of central sample data from all engineering feature sample data, and determining the offset decision amount of each engineering feature based on the discrete features between each engineering feature sample data and each central sample data; Dividing a plurality of feature offset sample data from all the engineering feature sample data by the offset decision amount of each engineering feature, and determining an offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data; Perform feature fusion on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, then perform offset correction on each offset feature fusion value according to all offset correction coefficients to obtain multiple fusion correction values, and determine the safety detection standard of municipal engineering construction data based on all fusion correction values; Determine whether the target municipal engineering construction data is safe by using the security detection standard, and then complete data security protection according to the judgment result; The offset decision amount of each engineering feature is determined based on the discrete features between each engineering feature sample data and each central sample data, specifically including: Determine the sample data discrete amount between each engineering feature sample data and each center sample data, and use all sample data discrete amounts as discrete features between each engineering feature sample data and each center sample data; Select an engineering feature as the selected engineering feature; Determine all feature offsets of the selected engineering feature according to the engineering feature value of the selected engineering feature in all engineering feature sample data and the corresponding engineering feature value in each center sample data; Determine the offset decision amount of the selected engineering feature according to all sample data discrete amounts and all feature offset amounts of the selected engineering feature; Continue to determine the offset decision amounts for the remaining engineering features.

2. The method according to claim 1, characterized in that Extracting multiple central sample data from all engineering feature sample data specifically includes: Select an engineering feature as the selected engineering feature; Obtain all engineering feature values ​​corresponding to the selected engineering feature from all engineering feature sample data; Determine multiple central characteristic values ​​of the selected engineering characteristic based on all engineering characteristic values; Continue to determine multiple central eigenvalues ​​of the remaining engineering features; A plurality of central sample data are determined according to the central characteristic values ​​corresponding to the respective engineering characteristics.

3. The method according to claim 1, characterized in that The offset decision amount of each engineering feature is used to divide multiple feature offset sample data from all engineering feature sample data, including: Determine the offset threshold of the corresponding engineering feature according to the engineering feature value of each engineering feature in all engineering feature sample data; All engineering feature sample data are divided into a plurality of feature offset sample data according to the offset threshold of each engineering feature and the offset decision amount of each engineering feature.

4. The method according to claim 1, characterized in that Determining the offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data specifically includes: Selecting a feature offset sample data as selected feature offset sample data; Determine a feature distribution moment of the selected feature offset sample data according to all engineering feature values ​​in the selected feature offset sample data, wherein the feature distribution moment is distribution attribute information of the corresponding engineering feature in the selected feature offset sample data; Determine an offset correction coefficient for the selected feature offset sample data according to the feature distribution moment and all engineering feature values ​​in the selected feature offset sample data; Continue to determine the offset correction coefficients for the remaining feature offset sample data.

5. The method according to claim 1, characterized in that The engineering feature values ​​in each feature offset sample data are subjected to feature fusion to obtain multiple offset feature fusion values, including: Selecting a feature offset sample data as selected feature offset sample data; Obtaining the maximum engineering characteristic value and the minimum engineering characteristic value in the selected characteristic offset sample data; According to the maximum engineering feature value and the minimum engineering feature value, all engineering feature values ​​in the selected feature offset sample data are fused into an offset feature fusion value of the selected feature offset sample data; Continue to determine the offset feature fusion values ​​of the remaining feature offset sample data, thereby obtaining multiple offset feature fusion values.

6. The method according to claim 1, characterized in that The safety inspection standards for municipal engineering construction data are determined based on all fused correction values, including: Determine the security feature aggregation amount during security detection based on all fused correction values; The safety detection standard of municipal engineering construction data is determined by the safety feature aggregation amount.

7. A security protection device for municipal engineering construction data, which uses the method described in any one of claims 1 to 6 to perform security protection on municipal engineering construction data, characterized in that: The security protection device for the municipal engineering construction data includes a data security protection unit, which includes: An acquisition module is used to acquire multiple engineering features from the target municipal engineering construction data, and then determine the engineering feature sample data at different construction points through all the engineering features; A processing module, used to extract multiple central sample data from all engineering feature sample data, and determine the offset decision amount of each engineering feature based on the discrete features between each engineering feature sample data and each central sample data; The processing module is further used to divide a plurality of feature offset sample data from all engineering feature sample data according to the offset decision amount of each engineering feature, and determine the offset correction coefficient of each feature offset sample data according to the distribution attribute information of the corresponding engineering feature in each feature offset sample data; The processing module is further used to perform feature fusion on the engineering feature values ​​in each feature offset sample data to obtain multiple offset feature fusion values, and then perform offset correction on each offset feature fusion value according to all offset correction coefficients to obtain multiple fusion correction values, and determine the safety detection standard of the engineering construction data according to all fusion correction values; The execution module is used to determine whether the target municipal engineering construction data is safe through the security detection standard, and then complete the data security protection according to the judgment result.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store computer programs, and the processor is used to call and run the computer program from the memory, so that the computer device executes the security protection method for municipal engineering construction data described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for securely protecting municipal engineering construction data according to any one of claims 1 to 6 are implemented.

Images