CN114491650A - A desensitization encryption method and system for geospatial information - Google Patents

Abstract

The invention provides a method and system for desensitizing and encrypting geospatial information. The method includes: performing statistical classification on geospatial information data according to space-time attributes, ownership attributes and land type attributes; The vertical ownership feature exchange and reorganization method desensitizes and encrypts the ownership attribute data and the land category attribute data based on the normalization processing method of land category features; performs data reorganization on the desensitized and encrypted geospatial data to form geographic statistical data; Data verification is performed on the geostatistical data and the geospatial information data. The present invention desensitizes and encrypts the spatiotemporal attribute data, weight attribute data and land type attribute data through the space-time coordinate conversion method, the vertical ownership feature exchange and reorganization method and the land type feature normalization processing method, thereby improving the data desensitization and encryption efficiency. speed and reliability for data encryption.

Description

A desensitization encryption method and system for geospatial information

technical field

The invention relates to the field of data security, and more particularly, to a method and system for desensitizing and encrypting geospatial information.

Background technique

With the rapid development of the upstream and downstream industrial chains of the geographic information industry, data governance technology has been derived from the traditional big data industries such as finance, medical care, party and government, and education to the geographic information industry. At the same time, it also has an impact on the privacy and security of geographic information big data. Effective desensitization and encryption of geospatial information will play a vital role in the development of the geographic information industry. Traditional industry data types are mostly text, image, and voice data. The data feature information is relatively simple, and the data structure is relatively regular. At present, hardware isolation is mainly used for data encryption at the hardware level, but it also blocks the flow of data; software; At the level, technologies such as distributed learning, federated learning, and database dynamic update are mainly used for privacy desensitization encryption. Geospatial information data mainly includes sensitive information such as spatiotemporal location information, ownership information, and land type feature information. The spatial level of data is more complex, and traditional data governance methods are obviously difficult to meet the needs.

The land and space information data contains a large amount of personal privacy information and national strategic deployment information. Traditional data cleaning, statistics, and analysis methods will retain the sensitive attributes of the data, which cannot realize the open circulation of data, and it is difficult to meet the multi-departmental cross-cooperative management. The desensitization and encryption method of geospatial information based on multi-element separation interprets, encrypts, cleans, counts, and checks the data in sequence to ensure the validity and migration of the encrypted data, and promote the development of the data industry chain in the geographic information industry. At the same time, it also creates an opportunity for the combination of remote sensing mapping technology and geographic information privacy and security computing.

SUMMARY OF THE INVENTION

Aiming at the technical problems existing in the prior art, the present invention provides a method and system for desensitizing and encrypting geospatial information, which can improve the speed of data desensitization and encryption and ensure the reliability of data encryption.

According to a first aspect of the present invention, a desensitization encryption method for geospatial information is provided, comprising:

Step 1: Perform spatial constraint mask processing on the geospatial information data, and perform statistical classification on the geospatial information data according to space-time attributes, ownership attributes and land type attributes, and obtain spatio-temporal attribute data, ownership attribute data and land type attribute data ;

Step 2: Detach the spatiotemporal attribute data based on the spatiotemporal coordinate transformation method, the property attribute data based on the vertical property feature exchange and reorganization method, and the land type attribute data based on the land type feature normalization processing method. sensitive encryption;

Step 3, performing data reorganization on the desensitized and encrypted geospatial data to form geographic statistical data;

Step 4: Perform data verification on the geographic statistical data and the geographic spatial information data.

On the basis of the above technical solutions, the present invention can also make the following improvements.

Optionally, performing desensitization and encryption on the spatiotemporal attribute data based on the spatiotemporal coordinate transformation method in the step 2, including:

slicing the spatiotemporal attribute data twice;

Based on the size and coordinates of each slice data after two slices, calculate the rotation angle of each slice data and the size after coordinate conversion;

Based on the rotation angle of each slice data and the size after coordinate conversion, desensitization and encryption processing is performed on each slice data after two slices.

Optionally, the slicing of the spatiotemporal attribute data twice includes:

Slice the spatiotemporal attribute data for the first time according to the M*N size;

Perform a second slice of each sliced data after the first slice according to the X*Y size;

Correspondingly, based on the size and coordinates of each sliced data after two slices, the rotation angle of each sliced data and the converted size of the projection coordinates are calculated, including:

Assuming that the coordinates of the sliced data after two slices are (x, y), the rotation angle θ of the sliced data is:

；

;

的取值范围为（0，90）； where k ₁ , k ₂ and k ₃ are coordinate offset constants,

The value range is (0, 90);

The dimension of the slice data after projection coordinate transformation is:

；

;

Among them, X _t , Y _t represent the slice data size after projection coordinate conversion;

Based on the rotation angle of each slice data and the size of the converted projection coordinates, each slice data after the second slice is subjected to projection coordinate conversion to obtain desensitized and encrypted spatiotemporal attribute data.

Optionally, performing desensitization and encryption on the ownership attribute data based on the vertical ownership feature exchange and reorganization method, including:

Suppose that data A contains data feature P, and data B contains data feature Q and label feature M. When data A and data B are used as sample data to construct an algorithm model together with label M, some features in feature P and feature Q are used to construct an algorithm model. Swap to form new tenure features _Pt and _Qt .

Optionally, the part of features in feature P and feature Q are exchanged to form new property features P _t and Q _t , including:

，数据B的初始特征图集

，i和j为特征数据的下标； Let the initial feature atlas of data A be

, the initial feature atlas of data B

, i and j are the subscripts of the feature data;

，采用初始特征图集Q的最 后一列

代替，并在初始特征图集P中添加一列

， 得到新权属特征P_t； For the last column of the initial feature atlas P

, using the last column of the initial feature atlas Q

instead, and add a column to the initial feature atlas P

, obtain the new ownership feature P _t ;

，采用初始特征图集P的 最后一列

代替，得到新权属特征Q_t。For the last column of the initial feature atlas Q

, using the last column of the initial feature atlas P

Instead, a new ownership feature _Qt is obtained.

Optionally, performing desensitization and encryption on the land type attribute data based on the land type feature normalization processing method, including:

For the land type attribute data, the land type attributes are unified based on the five land types of agricultural land, construction land, forest land, water area and unused land, and the land type attribute data are grouped into five major land type attribute data.

According to a second aspect of the present invention, a desensitization and encryption system for geospatial information is provided, comprising:

The statistical classification module is used to perform spatial constraint mask processing on geospatial information data, and perform statistical classification of geospatial information data according to space-time attributes, ownership attributes and land type attributes, and obtain spatio-temporal attribute data, ownership attribute data and land type attributes. class attribute data;

The desensitization and encryption module is used for respectively processing the space-time attribute data based on the space-time coordinate transformation method, the ownership attribute data based on the vertical ownership feature exchange and reorganization method, and the land type feature normalization processing method. Attribute data is desensitized and encrypted;

The data reorganization module is used to reorganize the desensitized and encrypted geospatial data to form geographic statistical data;

A data verification module, configured to perform data verification on the geographic statistical data and the geographic spatial information data.

According to a third aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the processor is configured to implement the steps of a method for desensitizing and encrypting geospatial information when executing a computer management program stored in the memory.

According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer management program is stored, and when the computer management program is executed by a processor, the steps of the method for desensitizing and encrypting geospatial information are implemented.

In the method and system for desensitizing and encrypting geospatial information provided by the present invention, firstly, the data attributes of geospatial information are interpreted and analyzed, and the data attributes are classified and sorted according to space-time attributes, ownership attributes and land type attributes to obtain a primary data source. ; Then use spatiotemporal coordinate transformation, vertical ownership feature exchange and reorganization, and land type feature normalization to encrypt spatiotemporal attributes, ownership attributes, and land type attributes, and desensitize and encrypt the data for statistical classification into geographic statistical data; In order to ensure the consistency of the reorganized geographic statistical data and the key information of the geospatial information data source, the two sets of data are finally compared and verified to prevent the loss of important information during the desensitization process, improve the speed of data desensitization and encryption, and meet the requirements of data encryption. reliability.

Description of drawings

1 is a flowchart of a method for desensitizing and encrypting geospatial information provided by the present invention;

2 is a schematic diagram of the overall processing process of the desensitization encryption method for geospatial information;

FIG. 3 is a schematic diagram of performing projection coordinate transformation on spatiotemporal attribute data based on a spatiotemporal coordinate transformation method;

Fig. 4 is the schematic diagram of feature P and feature Q recombination;

FIG. 5 is a schematic diagram of normalizing the land type attribute data;

6 is a schematic structural diagram of a geospatial information desensitization encryption system provided by the present invention;

7 is a schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

FIG. 8 is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention.

Detailed ways

The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. The following examples are intended to illustrate the present invention, but not to limit the scope of the present invention.

The invention provides a method and system for desensitizing and encrypting geospatial information based on the separation of multiple elements. The geospatial information data mainly includes land survey data, agricultural economic rights data, national land spatial planning data, land use status data, etc. The spatial information data attributes are interpreted and analyzed, and the data attributes are classified and sorted according to space-time attributes, ownership attributes, and land type attributes to obtain primary data sources. Then, spatiotemporal coordinate transformation, vertical ownership feature exchange and reorganization, and land type feature normalization are used to encrypt the time and space attributes, ownership attributes, and land type attributes, and the desensitized and encrypted data are statistically classified into geographic statistical data. In order to ensure the consistency of the reorganized geographic statistical data and the key information of the geospatial information data source, the two sets of data are finally compared and verified to prevent the loss of important information during the desensitization process.

Example 1

A desensitization encryption method for geospatial information, as shown in Figure 1 and Figure 2, the desensitization encryption method comprises the following steps:

Step 1: Perform spatial constraint mask processing on the geospatial information data, and perform statistical classification on the geospatial information data according to space-time attributes, ownership attributes and land type attributes, and obtain spatio-temporal attribute data, ownership attribute data and land type attribute data .

It can be understood that the geospatial information data mainly includes land survey data, agricultural economic rights data, national land spatial planning data, land use status data, etc. First, the geospatial information data is subjected to spatial constraint masking to ensure the unified registration of geographic coordinates. Then, the features of geospatial information data are statistically classified according to space-time attributes, ownership attributes, and land type attributes, and the integrity and validity of the data features after classification and statistics are verified by sampling inspection.

Step 2: Detach the spatiotemporal attribute data based on the spatiotemporal coordinate transformation method, the property attribute data based on the vertical property feature exchange and reorganization method, and the land type attribute data based on the land type feature normalization processing method. Sensitive encryption.

Specifically, as shown in Figure 3, the projection coordinate transformation is performed on the spatiotemporal attribute data. First, the data after the spatial constraint mask is sliced according to the size of M*N, and then each slice is sliced twice according to the size of X*Y and number, and then perform coordinate transformation on the spatiotemporal attributes of each sliced data after two slices. Among them, the projection coordinate transformation of spatiotemporal attribute data is divided into multiple operation steps, including two slices and coordinate transformation operations. On the one hand, it can meet the requirements of computer parallel computing, that is, multiple operation steps can be performed simultaneously, which improves the data encryption efficiency. On the other hand, the reliability of data encryption is guaranteed, and the data is difficult to decrypt easily. Let the coordinates of the first slice data in the upper left corner after the second slice be (1, 1), followed by (2, 1)... (1, 2)... That is, each slice data will have a coordinate (x , y), the calculation formula of the rotation angle θ of each slice data is as follows:

；

;

Among them, k ₁ , k ₂ and k ₃ are coordinate offset constants, and the values of k ₁ , k ₂ and k ₃ can be set according to the data volume of the geospatial information data to ensure that the data volume after projection coordinate transformation does not Increase too much, the value range of θ is (0, 90).

Among them, the rotation angle of the coordinate transformation is calculated according to the coordinates of each slice data, and the rotation angle of each slice data is different, which can improve the security of data desensitization encryption.

The size of each slice data converted from projected coordinates is calculated as follows:

;

;

;

;

;

;

Among them, X _t and Y _t represent the size of the secondary slice data after coordinate conversion, and L represents the radius of the rotation azimuth circle. The coordinate-transformed size is calculated according to the coordinates of each slice data, and the coordinate-transformed size corresponding to each slice data is different, which improves the reliability of data encryption.

According to the rotation angle and size of each slice data calculated above, rotate each slice data after the secondary cutting blade, and change the size to (X _t , Y _t ).

As an embodiment, the desensitization and encryption of the ownership attribute data based on the vertical ownership feature exchange and reorganization method includes: assuming that data A includes data feature P, data B includes data feature Q and label feature M, and when When data A and data B are used as sample data to construct an algorithm model together with label M, some features in feature P and feature Q are exchanged to form new attribute features P _t and Q _t .

，数据B的初始特征图集

，i和j为特征数据的下标； Wherein, exchanging some features in feature P and feature Q to form new attribute features P _t and Q _t includes: Assuming the initial feature atlas of data A

, the initial feature atlas of data B

, i and j are the subscripts of the feature data;

，采用初始特征图集Q的最 后一列

代替，并在初始特征图集P中添加一列

， 得到新权属特征P_t；对于初始特征图集Q的最后一列

，采用初始特征 图集P的最后一列

代替，得到新权属特征Q_t。 For the last column of the initial feature atlas P

, using the last column of the initial feature atlas Q

instead, and add a column to the initial feature atlas P

, get the new attribute feature P _t ; for the last column of the initial feature atlas Q

, using the last column of the initial feature atlas P

Instead, a new ownership feature _Qt is obtained.

与特征组

进行交换构成新的权 属特征P_t和Q_t。算法流程如下： Specifically, vertical ownership feature exchange and reorganization is performed on the ownership attribute data, as shown in Figure 4, assuming that data A contains data feature P, data B contains data feature Q and label feature M, when data A and data B When the algorithm model is constructed together as sample data and label M, the model training will not constitute an image if the features in data A and data B are partially exchanged and the weights are shared during training, so the feature group

with feature groups

The swaps form new tenure features P _t and Q _t . The algorithm flow is as follows:

和初始特征图集

，特征图集P和特征图集Q均为多维矩阵，可 参见图4。Enter the initial feature atlas separately

and the initial feature atlas

, the feature atlas P and the feature atlas Q are multi-dimensional matrices, as shown in Figure 4.

，且每次P和Q均只替换相同位具体算法如 下：

, and each time P and Q only replace the same bits. The specific algorithm is as follows:

；

;

；

;

；

;

As an embodiment, performing desensitization and encryption on the land type attribute data based on the land type feature normalization processing method includes: for the land type attribute data, based on agricultural land, building land, forest land, water area and unused land The five land types are used to unify the land type attributes, and the land type attribute data are grouped into five land type attribute data.

Specifically, the land type attribute data in various geospatial information data are normalized. As shown in Figure 5, the current land use data includes wetlands, cultivated land, forest land, commercial service land, industrial and mining land, residential land, and water area. , grassland, other land use, etc. Land spatial planning data includes architectural planning land, agricultural planning land, mountains, waters, woodlands, lakes, grasslands, etc. Because the data is sensitive information, the data circulation is poor, and each geospatial data land type The attribute naming methods are inconsistent. The present invention proposes five categories of agricultural land, construction land, forest land, water area, and unused land to unify the land type attributes, and classify the secondary land categories in the geospatial data into five categories, and then Categorize statistics.

Step 3, performing data reorganization on the desensitized and encrypted geospatial data to form geographic statistical data.

It is understandable that the desensitized and encrypted space-time attributes, ownership attributes, and land type attributes are reorganized into geographic statistical data to ensure that sensitive information has been desensitized and encrypted, and can support attribute retrieval queries.

Step 4, performing data verification on the geographic statistical data and the geographic spatial information data.

It is understandable that, after desensitizing and encrypting the geospatial information data, and reorganizing the data, the geostatistical data is obtained. In this step 4, data verification is performed on the geographical statistical data and the geospatial information data. First, statistical verification is carried out to verify the integrity of the features, then the reliability of the data is sampled using the field inspection data, and finally the data compression and decompression, data transmission, and sharing test are carried out. The liquidity of data.

In order to verify the performance of the method of the present invention, the present invention selects the local land use data in Jingzhou to do experimental verification, and the experimental parameters are set as shown in Table 1 below:

Table 1 Experimental parameters

Statistical verification was carried out on the local land use status data in Jingzhou City and the land types in the desensitized and encrypted geographic statistical data, and the compression, decompression, transmission, and sharing functions of the desensitized and encrypted geographic statistical data were tested. Data format size conversion. The experimental results are shown in Table 2 below:

Table 2 Experimental results

The experimental results show that the total area of land types does not change after data desensitization and encryption, and the data can be compressed, transmitted, and decompressed after desensitization and encryption, and the data size increases within a reliable range.

Embodiment 2

A desensitization encryption system for geospatial information, see FIG. 6 , the desensitization encryption system includes a statistical classification module 61, a desensitization encryption module 62, a data reorganization module 63 and a data verification module 64, wherein:

The statistical classification module 61 is used to perform spatial constraint mask processing on the geospatial information data, and perform statistical classification on the geospatial information data according to the spatiotemporal attributes, ownership attributes and land type attributes, and obtain spatiotemporal attribute data, ownership attribute data and Land type attribute data.

The desensitization and encryption module 62 is used to respectively perform the spatial-temporal attribute data based on the spatiotemporal coordinate transformation method, the title attribute data based on the vertical title feature exchange and recombination method, and the ground type feature normalization processing method. Class attribute data is desensitized and encrypted.

The data reorganization module 63 is used to reorganize the desensitized and encrypted geospatial data to form geographic statistical data.

The data verification module 64 is configured to perform data verification on the geographic statistical data and the geographic spatial information data.

It can be understood that a desensitization and encryption system for geospatial information provided by the present invention corresponds to the desensitization and encryption methods for geospatial information provided in the foregoing embodiments, and the relevant technical features of the desensitization and encryption system for geospatial information may refer to Geospatial Information. The relevant technical features of the information desensitization encryption method will not be repeated here.

Embodiment 3

Please refer to FIG. 7 , which is a schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. As shown in FIG. 7 , an embodiment of the present invention provides an electronic device 700, including a memory 710, a processor 720, and a computer program 711 stored in the memory 710 and running on the processor 720, and the processor 720 executes the computer program At 711, the desensitization and encryption method for geospatial information of the first embodiment is implemented.

Embodiment 4

Please refer to FIG. 8, which is a schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. As shown in FIG. 8 , this embodiment provides a computer-readable storage medium 800 on which a computer program 811 is stored. When the computer program 811 is executed by a processor, the method for desensitizing and encrypting geospatial information in Embodiment 1 is implemented.

A method and system for desensitizing and encrypting geospatial information provided by the embodiments of the present invention have the following advantages:

(1) The present invention proposes a method for transforming the spatiotemporal attributes of geospatial information data, which refines the data hierarchy by transforming projected coordinates after secondary data slicing. It provides a new idea for geospatial data governance and cleaning; on the other hand, the proposed rotation angle calculation method not only satisfies the reliability of data encryption, but also greatly reduces the encrypted data space and ensures the timeliness of data storage and operation.

(2) The present invention proposes a vertical exchange and reorganization method of geospatial information data ownership features, which uses the idea of federated learning to reorganize geospatial data. The reorganized ownership features ensure the privacy of the data from the perspective of single data. From the perspective of the algorithm model, the reliability of the model is not lost. The vertical ownership feature exchange enriches the feature complexity to a certain extent, and avoids the poor model generalization effect caused by subsequent data modeling.

(3) The present invention proposes a variety of methods for normalizing land type attributes in geospatial information data, formulating five major categories of agricultural land, construction land, forest land, water area, and unused land to unify land type attributes. The attribute angle opens up the circulation between data, and at the same time desensitizes and encrypts the land type attributes. It sets the ground class standard for the follow-up privacy and security calculation with satellite remote sensing data, and proposes a new idea for the privacy and security calculation of geospatial information data.

It should be noted that, in the foregoing embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded computer or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means implementing the functions specified in one or more of the flowcharts and/or one or more blocks of the block diagrams.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of the present invention.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention. Thus, provided that 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 such modifications and variations.

Claims (9)

1. A method for desensitizing encryption of geospatial information, comprising:

step 1, carrying out space constraint mask processing on geographic space information data, and carrying out statistical classification on the geographic space information data according to a space-time attribute, an ownership attribute and a land attribute to obtain space-time attribute data, ownership attribute data and land attribute data;

step 2, desensitizing and encrypting the space-time attribute data based on a space-time coordinate transformation method, the ownership attribute data based on a longitudinal ownership feature exchange recombination method and the territorial attribute data based on a territorial feature normalization processing method;

step 3, performing data recombination on the desensitized encrypted geospatial data to form geographic statistical data;

and 4, performing data verification on the geographic statistical data and the geospatial information data.

2. The desensitization encryption method according to claim 1, wherein said desensitization encryption of said spatiotemporal attribute data based on spatiotemporal coordinate transformation method in step 2 comprises:

slicing the spatio-temporal attribute data twice;

calculating the rotation angle and the size after coordinate conversion of each piece of slice data based on the size and the coordinate of each piece of slice data after twice slicing;

and performing desensitization encryption processing on each piece of slice data after twice slicing based on the rotation angle and the size of the size after coordinate conversion of each piece of slice data.

3. The desensitized encryption method of claim 2, wherein said twice slicing the spatiotemporal attribute data comprises:

performing first slicing on the spatio-temporal attribute data according to the size of M x N;

performing second slicing on each slice data after the first slicing according to the X-Y size;

correspondingly, the calculating the rotation angle and the projection coordinate converted size of each slice data based on the size and the coordinate of each slice data after twice slicing includes:

assuming that the coordinates of the slice data after the two slicing are (x, y), the rotation angle θ of the slice data is:

；

wherein k is₁、k₂And k₃In order to be a coordinate-shift constant,

the value range of (1) is (0, 90);

the size of the converted projection coordinates of the slice data is as follows:

；

wherein, X_t、Y_tRepresenting the size of the slice data after the projection coordinate conversion;

and performing projection coordinate conversion on each piece of slice data subjected to secondary slicing based on the rotation angle of each piece of slice data and the size of the projection coordinate converted to obtain desensitized and encrypted space-time attribute data.

4. The desensitization encryption method of claim 1, wherein said desensitization encryption of said ownership attribute data based on longitudinal ownership feature exchange reassembly comprises:

the data A comprises data characteristics P, the data B comprises data characteristics Q and label characteristics M, and when the data A and the data B are used as sample data and the label M are used together to construct an algorithm model, the characteristics P and partial characteristics in the characteristics Q are exchanged to form new attribute characteristics P_tAnd Q_t。

5. Desensitization encryption method according to claim 4, characterized in that said exchange of part of the characteristics P and Q constitutes a new attribute characteristic P_tAnd Q_tThe method comprises the following steps:

let initial feature set of data A

Initial feature atlas of data B

I and j are subscripts of the feature data;

for the last column of the initial feature set P

Using the last column of the initial feature set Q

Instead of, and adding a column to the initial feature set P

Obtaining a new ownership feature P_t；

Last column for initial feature set Q

Using the last column of the initial feature set P

Instead, a new ownership feature Q is obtained_t。

6. The desensitization encryption method according to claim 1, wherein said desensitization encryption of said locale attribute data based on a locale feature normalization processing method comprises:

and for the land attribute data, unifying the land attributes based on five land types of agricultural land, construction land, forest land, water area and unused land, and integrating the land attribute data into five land attribute data.

7. A geospatial information desensitization encryption system, comprising:

the statistical classification module is used for carrying out spatial constraint mask processing on the geographic spatial information data and carrying out statistical classification on the geographic spatial information data according to the time-space attribute, the ownership attribute and the land attribute to obtain time-space attribute data, ownership attribute data and land attribute data;

the desensitization encryption module is used for desensitizing and encrypting the space-time attribute data based on a space-time coordinate transformation method, the ownership attribute data based on a longitudinal ownership feature exchange recombination method and the land-type attribute data based on a land-type feature normalization processing method;

the data recombination module is used for carrying out data recombination on the desensitized encrypted geospatial data to form geographic statistical data;

and the data verification module is used for performing data verification on the geographic statistical data and the geographic spatial information data.

8. An electronic device comprising a memory, a processor for implementing the steps of the geospatial information desensitization encryption method according to any of claims 1-6 when executing a computer management class program stored in the memory.

9. A computer-readable storage medium, having stored thereon a computer management like program, which when executed by a processor, carries out the steps of the method of desensitizing encryption of geospatial information according to any of claims 1-6.

Images