A method and system for extracting and identifying spatial features of data

Abstract

The present invention discloses a method and system for extracting and identifying spatial features of data. The data identification method includes: obtaining current power data, and determining a current power data spatial feature library by using the data spatial feature extraction method; obtaining a historical data spatial feature library, and determining a sensitive data spatial feature library by using preset sensitive data features and the historical data spatial feature library; performing modular arithmetic on the current power data spatial feature library and the sensitive data spatial feature library to determine the identification result of the current power data. The present invention solves the problem of low identification accuracy of traditional sensitive data identification methods that do not consider the application scenarios of data. Based on the matching and identification of spatial feature vectors, it realizes the accurate identification of sensitive data in a large amount of power data, and further supports the automatic identification of power sensitive data, improves the identification efficiency, and further improves the data security protection level.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method and system for extracting and identifying spatial features of data. Background Art

[0002] In the digital age, due to its public service nature, the power industry has a vast amount of high-value sensitive data. If properly utilized, it can create huge economic value. However, if sensitive data is leaked, it will lead to serious economic consequences. Therefore, strengthening the security protection of power sensitive data has become an industry consensus. Accurate and efficient identification of power sensitive data is a prerequisite for security protection. However, the types of power sensitive data are complex, including both some production operation data and some customer sensitive information. The data content features vary greatly, and the determination of whether the same data is sensitive also differs in different business scenarios. Currently, the identification methods for data content or sensitive information features such as files and pictures are relatively mature, but they do not consider the business scenario, resulting in a high misjudgment rate for sensitive identification. For example, the same user information is sensitive in the user profile and should not be accessible to irrelevant people, but as a meeting notice contact, it is not sensitive information. If judged only from the data content features, misjudgment will occur. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and system for extracting and identifying spatial features of data, which solve the problem in the prior art that the identification of sensitive data does not consider different business scenarios and only discriminates from data content features, resulting in a high misjudgment rate.

[0004] In a first aspect, an embodiment of the present invention provides a method for extracting spatial features of data, including: obtaining the data characteristics of historical data, and constructing a data spatial feature model according to the data characteristics; performing spatial feature extraction on the historical data based on the data spatial feature model to determine the spatial features of the historical data, so as to form a historical data spatial feature library.

[0005] Optionally, the data characteristics include: data attributes, user attributes, operation attributes, and environmental attributes. The obtaining of the data characteristics of historical data includes: performing data analysis on the storage database of the historical data to determine the data attributes of the historical data; obtaining the preset relationship between user information and access rights and the access user information of the historical data, and determining the access rights to the historical data according to the user information and the preset relationship to determine the user attributes of the historical data; obtaining the operation information for operating the historical data to determine the operation attributes of the historical data; obtaining the gateway information of the user accessing the historical data to determine the environmental attributes of the historical data.

[0006] Second aspect, an embodiment of the present invention further provides a method for identifying data, including: obtaining current power data, and determining the current power data spatial feature library by using the data spatial feature extraction method described in the first aspect of this embodiment; obtaining a historical data spatial feature library, and determining a sensitive data spatial feature library by using preset sensitive data features and the historical data spatial feature library; performing a modulo operation on the current power data spatial feature library and the sensitive data spatial feature library to determine the identification result of the current power data.

[0007] Optionally, the obtaining a historical data spatial feature library, determining a sensitive data spatial feature library by using preset sensitive data features and the historical data spatial feature library includes: obtaining a preset rule for sensitive data; screening the historical data spatial feature library based on the preset rule to determine the sensitive data spatial feature library.

[0008] Optionally, the performing a modulo operation on the current power data spatial feature library and the sensitive data spatial feature library to determine the identification result of the current power data includes: performing a modulo operation on the current power data spatial feature library and the sensitive data spatial feature library to determine a first operation result; when the first operation result is zero, determining that the current power data is sensitive power data.

[0009] Optionally, the method for identifying data provided by the embodiment of the present invention further includes: when the first operation result is not zero, performing a modulo operation on the current power data spatial feature library and the historical data spatial feature library to determine a second operation result; when the second operation result is zero, determining that the current power data is conventional power data; when the second operation result is not zero, determining that the current power data is newly generated power data; adding the newly generated power data to the historical data spatial feature library.

[0010] Third aspect, an embodiment of the present invention further provides a data spatial feature extraction system, including: a model construction module, configured to obtain the data characteristics of historical data and construct a data spatial feature model according to the data characteristics; an extraction module, configured to perform spatial feature extraction on the historical data based on the data spatial feature model to determine the spatial features of the historical data, so as to form a historical data spatial feature library.

[0011] Fourth aspect, an embodiment of the present invention further provides a data recognition system, including: a first processing module, configured to obtain current power data and determine the current power data spatial feature library by using the data spatial feature extraction system as described in the third aspect of this embodiment; a second processing module, configured to obtain a historical data spatial feature library and determine a sensitive data spatial feature library by using preset sensitive data features and the historical data spatial feature library; a third processing module, configured to perform modulo operation on the current power data spatial feature library and the sensitive data spatial feature library to determine the recognition result of the current power data.

[0012] Fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions to execute the method provided in the first aspect or the second aspect of the embodiment of the present invention.

[0013] An embodiment of the present invention further provides an electronic device, including: a memory and a processor, which are communicatively connected to each other, where the memory stores computer instructions, and the processor is configured to execute the computer instructions to execute the method provided in the first aspect or the second aspect of the embodiment of the present invention.

[0014] The technical solution of the present invention has the following advantages:

[0015] 1. The data spatial feature extraction method provided by the present invention realizes the extraction of spatial features of historical data by constructing a data spatial feature model, determines the spatial features of historical data to form a historical data spatial feature library; fully considers sensitive attributes such as the application scenario and access object of the data, constructs multi-dimensional spatial features, and thus ensures the completeness of the sensitive data recognition process and the recognition rate of sensitive data.

[0016] 2. The data recognition method provided by the present invention determines the recognition result of the current power data by constructing a current power data spatial feature library and a sensitive data spatial feature library; solves the problem of low recognition accuracy of the traditional sensitive data recognition method that does not consider the application scenario of the data, realizes the accurate recognition of sensitive data in a large amount of power data based on the matching recognition of spatial feature vectors, and thus supports the automatic recognition of power sensitive data, improves the recognition efficiency, and further improves the data security protection level. Description of the Drawings

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of the method for extracting the spatial features of the data provided in the embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of the data characteristics provided in the embodiment of the present invention;

[0020] Figure 3 It is a flowchart of the method for identifying the data provided in the embodiment of the present invention;

[0021] Figure 4 It is a schematic diagram of the module composition of the system for extracting the spatial features of the data provided in the embodiment of the present invention;

[0022] Figure 5 It is a schematic diagram of the module composition of the system for identifying the data provided in the embodiment of the present invention;

[0023] Figure 6 It is a schematic diagram of the interaction process of the system for identifying the data provided in the embodiment of the present invention;

[0024] Figure 7 It is a composition diagram of a specific example of the computer device provided in the embodiment of the present invention. Specific Embodiments

[0025] The following will clearly and completely describe the technical solutions of the present invention with reference to the drawings. Obviously, the described embodiments are some embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0026] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0027] An embodiment of the present invention provides a method for extracting spatial features of data. This method fully considers sensitive attributes such as the application scenario and access object of the data, constructs multi-dimensional spatial features, and thus adapts to the situation where the determination of whether the same data is sensitive varies in different business scenarios. It solves the problem of low accuracy in identifying sensitive data by traditional methods (such as methods that only identify sensitive data through data content features) and static methods (without considering the application scenario and business environment of the data). By fully considering sensitive attributes such as the application scenario and access object of the data, multi-dimensional spatial features are constructed. For example, the same user information is sensitive information in the user profile and should not be accessible to irrelevant people, but as a meeting notice contact person, it is not sensitive information. If judged only from the data content features, misjudgment will occur.

[0028] Specifically, as Figure 1 shown, the method for extracting spatial features of the data specifically includes:

[0029] Step S01: Obtain the data characteristics of historical data, and construct a data spatial feature model according to the data characteristics.

[0030] In this embodiment, first, obtain the data characteristics of each historical data, and then construct a data spatial feature model as Figure 2 shown, where different dotted line types represent different data attributes, that is, first construct a power-sensitive data spatial feature model from four aspects: data characteristics, user attributes, data attributes, operation attributes, and environmental attributes. Then, when a visitor needs to use sensitive data, collect the attribute characteristics of these four dimensions in real time, and determine and identify sensitive data through spatial feature matching.

[0031] Step S02: Based on the data spatial feature model, perform spatial feature extraction on historical data to determine the spatial features of historical data, so as to form a historical data spatial feature library. In this embodiment, use the determined data spatial feature model to perform spatial feature extraction on historical data, determine the respective spatial features corresponding to the historical data, and then construct a historical data spatial feature library, V = {V1, V2, L, Vn}.

[0032] The method for extracting spatial features of data provided by the present invention realizes spatial feature extraction of historical data by constructing a data spatial feature model, determines the spatial features of historical data, and forms a historical data spatial feature library; fully considers sensitive attributes such as the application scenario and access object of the data, constructs multi-dimensional spatial features, and thus ensures the completeness of the sensitive data identification process and ensures the identification rate of sensitive data.

[0033] In a specific embodiment, the data characteristics include: data attributes, user attributes, operation attributes, and environmental attributes. The process of executing step S01 may specifically include the following steps:

[0034] Specifically, the collected data characteristics include information in four aspects: data attributes, user attributes, operation attributes, and environmental attributes, denoted as where represents data attributes, represents user attributes, represents operation attributes, represents environmental attributes. Among them, data attributes should include data type, data content characteristics, data security classification, data owner, data manager, data accessible time, data timeliness, etc. User attributes should include unique user identity ID, affiliated organizational unit, network location where the access is located, user temporary privilege pass, etc. Operation attributes should include possible operation types on the data, such as read operation, add operation, modify operation, delete operation, etc. Environmental attributes should include the specific access environment of the data in the actual scenario, such as possible access services, access geographical location, access usage time, etc.

[0035] Step S011: Perform data analysis on the storage database of historical data to determine the data attributes of the historical data. In the embodiment of the present invention, the data attributes are obtained by analyzing the storage database of power data (historical data) regularly or in advance. For example, customer email, address belong to different types of customer information, and each has its own content characteristic keywords. Information such as data security classification, data owner, data manager, data accessible time, data timeliness, etc. can be obtained through the attributes and descriptions of database tables. When accessing a certain field of a certain table in a certain database, data attributes can be collected simultaneously through the above methods.

[0036] Step S012: Obtain the preset relationship between user information and access permissions and the access user information of historical data, and determine the access permissions for historical data according to the user information and the preset relationship to determine the user attributes of the historical data.

[0037] In the embodiment of the present invention, user attributes can be obtained from the permission control system of the power information system. When a user needs to access a certain power data (business data), the user will first log in to the information system through a wired or wireless network. The information system will authenticate the user's account, password, IP address, etc. At this time, user attributes such as unique user identity ID, affiliated organizational unit, network location where the access is located can be collected; when a user needs to access data beyond the permissions, temporary permissions need to be obtained through the approval of each level of management department. At this time, information on the user's temporary privilege pass can be collected.

[0038] Step S013: Obtain the operation information of the operation history data to determine the operation attributes of the historical data. In practical applications, the operation attributes can be obtained by the power information system or the database server. When a user needs to access a certain business data, data reading operations, addition operations, modification operations, and deletion operations will be performed through the power information system. At this time, the operation attributes of the user can be obtained; the power information system will also send relevant operations to the background database server for execution. At this time, the operation attributes of the user can be obtained.

[0039] Step S14: Obtain the gateway information of the user accessing the historical data to determine the environmental attributes of the historical data. In the embodiments of the present invention, the environmental attributes can be collected and obtained from the user's access network. When a user needs to access a certain business data, they will first access the power information network boundary gateway through a wired or wireless network before they can log in and use the relevant system. At this time, information such as the geographical location, time, IP address, and terminal type where the user accesses the data can be collected, and it can also be obtained whether the user accesses the data through a private network, the Internet, a fixed network, or a mobile network.

[0040] The method for extracting the spatial features of data provided by the present invention realizes the extraction of the spatial features of historical data by constructing a data spatial feature model, determines the spatial features of the historical data, and forms a historical data spatial feature library; fully considering sensitive attributes such as the application scenarios and access objects of the data, a multi-dimensional spatial feature is constructed, thereby ensuring the completeness of the identification process of sensitive data and ensuring the recognition rate of sensitive data.

[0041] The embodiments of the present invention also provide a method for identifying data, as Figure 3 shown, specifically including the following steps:

[0042] Step S1: Obtain the current power data and determine the current power data spatial feature library. In this embodiment, when the power system receives an access request, it determines the current power data to be accessed corresponding to this access request, and then uses the above-mentioned method for extracting the spatial features of data to determine the current power data spatial feature library V'.

[0043] Step S2: Obtain the historical data spatial feature library, and use the preset sensitive data features and the historical data spatial feature library to determine the sensitive data spatial feature library. The obtained historical data spatial feature library is the historical data spatial feature library determined according to the above-mentioned method for extracting the spatial features of data.

[0044] Step S3: Perform a modulo operation on the current power data spatial feature library and the sensitive data spatial feature library to determine the identification result of the current power data.

[0045] The data recognition method provided by the present invention determines the recognition result of the current power data by constructing the current power data space feature library and the sensitive data space feature library; it solves the problem of low recognition accuracy of the traditional sensitive data recognition method that does not consider the application scenario of the data. Based on the matching recognition of the space feature vectors, it realizes the accurate recognition of sensitive data in the massive power data, and then can support the automatic recognition of power sensitive data, improve the recognition efficiency, and further improve the data security protection level.

[0046] In a specific embodiment, the execution of the above step S2 specifically includes the following steps:

[0047] Step S21: Obtain the preset rules of sensitive data. The preset rules of sensitive data can be sorted out and defined by security personnel and business personnel with reference to relevant sensitive data system specifications of the country, industry, and power enterprises for the characteristics of power sensitive data, and can be adjusted according to actual needs. The embodiments of the present invention are not limited thereto.

[0048] Step S22: Screen the historical data space feature library based on the preset rules to determine the sensitive data space feature library. In this embodiment, based on the preset rules, starting from the data attributes of the current power data, the characteristics of power sensitive data are sorted out and defined, and then the historical data space feature library is screened to complete the construction of the initial sensitive data space feature library. The sensitive data space feature library of power can be denoted as V s ={V s1 ,V s2 ,L,V sn}, where the sensitive data space feature library V s is a subset of the historical data space feature library V.

[0049] Specifically, the execution of the above step S3 specifically further includes the following steps:

[0050] Step S31: Perform a modulo operation on the current power data space feature library and the sensitive data space feature library to determine the first operation result.

[0051] Among them, the modulo operation is mostly used in program writing and has a wide range of applications in number theory and program design. From the discrimination of odd and even numbers to the discrimination of prime numbers, from modulo exponentiation to the method of finding the greatest common divisor, the modulo operation is everywhere. Specifically, perform a modulo operation on the current power data space feature library V' and the sensitive data space feature library V s to determine the first operation result, which can be expressed by the following formula:

[0052]

[0053] Step S32: When the first operation result is zero, determine that the current power data is sensitive power data. Specifically, if |V′ - V| = 0, it can be determined that the currently accessed power data is sensitive. s | = 0, it can be determined that the currently accessed power data is sensitive.

[0054] Step S33: When the first operation result is not zero, perform a modulo operation on the current power data spatial feature library and the historical data spatial feature library to determine the second operation result. Specifically, the modulo operation method is the same as the above formula (1) and will not be elaborated here.

[0055] Step S34: When the second operation result is zero, determine that the current power data is regular power data. If |V′ - V| ≠ 0, but |V′ - V| = 0, it can be determined that the currently accessed power data is not sensitive, that is, the current power data is regular power data. s | ≠ 0, but |V′ - V| = 0, it can be determined that the currently accessed power data is not sensitive, that is, the current power data is regular power data.

[0056] Step S35: When the second operation result is not zero, determine that the current power data is newly generated power data. If |V′ - V| ≠ 0 and |V′ - V| ≠ 0, it can be determined that the currently accessed power data is newly generated power data under new services. Furthermore, the historical data spatial feature library can be updated with the newly generated power data. Specifically, it can be updated in real time as it is generated, or it can be updated by storing it first and then periodically updating the database. This embodiment is not limited thereto. s | ≠ 0 and |V′ - V| ≠ 0, it can be determined that the currently accessed power data is newly generated power data under new services. Furthermore, the historical data spatial feature library can be updated with the newly generated power data. Specifically, it can be updated in real time as it is generated, or it can be updated by storing it first and then periodically updating the database. This embodiment is not limited thereto.

[0057] Step S36: Add the newly generated power data to the historical data spatial feature library. In this embodiment, the newly generated power data is incorporated into the historical data spatial feature V. Then, security personnel and business personnel refer to relevant sensitive data system specifications of the state, industry, and power enterprises to determine whether the data is sensitive. If it is sensitive, it is incorporated into the power sensitive data feature library V s .

[0058] The data identification method provided by the present invention determines the identification result of the current power data by constructing the current power data spatial feature library and the sensitive data spatial feature library; solves the problem of low identification accuracy of the traditional sensitive data identification method that does not consider the application scenario of the data, realizes the accurate identification of sensitive data in a large amount of power data based on the matching identification of spatial feature vectors, and further supports the automated identification of power sensitive data, improves the identification efficiency, and further improves the data security protection level.

[0059] The embodiment of the present invention also provides a data spatial feature extraction system, as Figure 4 shown, the system includes:

[0060] The model construction module 01 is used to obtain the data characteristics of historical data and construct a data space feature model according to the data characteristics. For detailed content, refer to the relevant description of step S01 in the above method embodiment, which will not be elaborated here.

[0061] The extraction module 02 is used to extract the spatial features of historical data based on the data space feature model, determine the spatial features of historical data, and form a historical data spatial feature library. For detailed content, refer to the relevant description of step S02 in the above method embodiment, which will not be elaborated here.

[0062] Through the collaborative cooperation of the above-mentioned various module components, the spatial feature extraction system of the data provided by the present invention realizes the extraction of the spatial features of historical data by constructing a data space feature model, determines the spatial features of historical data, and forms a historical data spatial feature library; fully considering sensitive attributes such as the application scenario and access object of the data, constructs multi-dimensional spatial features, thereby ensuring the completeness of the sensitive data recognition process and ensuring the recognition rate of sensitive data.

[0063] An embodiment of the present invention also provides a data recognition system, as Figure 5 shown. This system includes:

[0064] The first processing module 1 is used to obtain the current power data and determine the current power data spatial feature library by using the Figure 4 spatial feature extraction system of the data shown. For detailed content, refer to the relevant description of step S1 in the above method embodiment, which will not be elaborated here.

[0065] The second processing module 2 is used to obtain the historical data spatial feature library and determine the sensitive data spatial feature library by using the preset sensitive data features and the historical data spatial feature library. For detailed content, refer to the relevant description of step S2 in the above method embodiment, which will not be elaborated here.

[0066] The third processing module 3 is used to perform modular arithmetic on the current power data spatial feature library and the sensitive data spatial feature library to determine the recognition result of the current power data. For detailed content, refer to the relevant description of step S3 in the above method embodiment, which will not be elaborated here.

[0067] Specifically, the interaction process of the data recognition system provided in this embodiment is as Figure 6 shown. The data attributes, user attributes, operation attributes, and environment attributes are determined in the data server, unified permission system, power business system, and unified access gateway respectively. Then, after using each acquisition module to collect the corresponding attributes, a sensitive data spatial feature library is formed. Finally, the matching calculation of the sensitive data spatial features is performed to accurately identify and maintain the sensitive data in the power business system.

[0068] Through the collaborative cooperation of the above-mentioned various module components, the data recognition system provided by the present invention determines the recognition result of the current power data by constructing the current power data space feature library and the sensitive data space feature library; solves the problem of low recognition accuracy of the traditional sensitive data recognition method that does not consider the application scenario of data, realizes the accurate recognition of sensitive data in a large amount of power data based on the matching recognition of spatial feature vectors, and then supports the automatic recognition of power sensitive data, improves the recognition efficiency, and further improves the data security protection level.

[0069] An embodiment of the present invention provides a computer device, such as Figure 7 shown, including: at least one processor 401, such as a CPU (Central Processing Unit, central processor), at least one communication interface 403, a memory 404, and at least one communication bus 402. Among them, the communication bus 402 is used to realize the connection and communication between these components. Among them, the communication interface 403 may include a display screen (Display) and a keyboard (Keyboard). Optionally, the communication interface 403 may further include a standard wired interface and a wireless interface. The memory 404 may be a high-speed RAM memory (Random Access Memory, volatile random access memory), or a non-volatile memory, such as at least one disk memory. Optionally, the memory 404 may further be at least one storage device located far from the aforementioned processor 401. Among them, the processor 401 may execute the spatial feature extraction method of data or the recognition method of data. A set of program codes are stored in the memory 404, and the processor 401 calls the program codes stored in the memory 404 to execute the above-mentioned spatial feature extraction method of data or the recognition method of data.

[0070] Among them, the communication bus 402 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 402 may be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 7 only one line is shown in, but it does not mean that there is only one bus or one type of bus.

[0071] Among them, the memory 404 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 404 may further include a combination of the above types of memories.

[0072] Among them, the processor 401 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.

[0073] Among them, the processor 401 may further include a hardware chip. The above hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0074] Optionally, the memory 404 is further configured to store program instructions. The processor 401 may call the program instructions to implement the method for extracting spatial features of data or the method for identifying data as described in this application.

[0075] An embodiment of the present invention also provides a computer-readable storage medium, on which computer-executable instructions are stored, and the computer-executable instructions can execute a method for extracting spatial features of data or a method for identifying data. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (abbreviation: HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memories.

[0076] Obviously, the above embodiments are merely examples for clear illustration and not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. A method for extracting spatial features of data, characterized in that, Including: Obtain the data characteristics of historical power data, and construct a data space feature model according to the data characteristics; Based on the data space feature model, extract the space features of the historical power data, determine the space features of the historical power data, so as to form a historical power data space feature library; The data characteristics include: data attributes, user attributes, operation attributes and environmental attributes. The obtaining of the data characteristics of historical power data includes: Perform data analysis on the storage database of the historical power data to determine the data attributes of the historical power data; Obtain the preset relationship between user information and access rights and the access user information of the historical power data, and determine the access rights to the historical power data according to the user information and the preset relationship, so as to determine the user attributes of the historical power data; Obtain the operation information for operating the historical power data to determine the operation attributes of the historical power data; Obtain the gateway information of the user accessing the historical power data to determine the environmental attributes of the historical power data.

2. A method for identifying data, characterized in that, Including: Obtain current power data, and determine the current power data space feature library, including: Obtain the data characteristics of the current power data, and construct a data space feature model according to the data characteristics; Based on the data space feature model, extract the space features of the current power data, determine the space features of the current power data, so as to form a current power data space feature library; The data characteristics include: data attributes, user attributes, operation attributes and environmental attributes. The obtaining of the data characteristics of the current power data includes: Perform data analysis on the storage database of the current power data to determine the data attributes of the current power data; Obtain the preset relationship between user information and access rights and the access user information of the current power data, and determine the access rights to the current power data according to the user information and the preset relationship, so as to determine the user attributes of the current power data; Obtain the operation information for operating the current power data to determine the operation attributes of the current power data; Obtain the gateway information of the user accessing the current power data to determine the environmental attributes of the current power data; Obtain the historical power data space feature library as described in claim 1, and use the preset sensitive data features and the historical power data space feature library to determine the sensitive data space feature library; Perform modulo operation on the current power data space feature library and the sensitive data space feature library to determine the identification result of the current power data; The using the preset sensitive data features and the historical power data space feature library to determine the sensitive data space feature library includes: Obtain the preset rules of sensitive data; Based on the preset rules, screen the historical power data space feature library to determine the sensitive data space feature library.

3. The method for identifying data according to claim 2, characterized in that, The performing modulo operation on the current power data space feature library and the sensitive data space feature library to determine the identification result of the current power data includes: Perform modulo operation on the current power data space feature library and the sensitive data space feature library to determine the first operation result; When the first operation result is zero, it is determined that the current power data is sensitive power data.

4. The method for identifying data according to claim 3, characterized in that, It further includes: When the first operation result is not zero, perform a modulo operation on the current power data spatial feature library and the historical power data spatial feature library to determine a second operation result; When the second operation result is zero, it is determined that the current power data is conventional power data.

5. The method for identifying data according to claim 4, characterized in that, It further includes: When the second operation result is not zero, it is determined that the current power data is newly generated power data; Add the newly generated power data to the historical power data spatial feature library.

6. A system for extracting spatial features of data, characterized in that, It includes: A model construction module, configured to obtain the data characteristics of historical power data and construct a data spatial feature model according to the data characteristics; An extraction module, configured to perform spatial feature extraction on the historical power data based on the data spatial feature model, determine the spatial features of the historical power data, and form a historical power data spatial feature library; The data characteristics include: data attributes, user attributes, operation attributes, and environmental attributes. The obtaining of the data characteristics of the historical power data includes: Perform data analysis on the storage database of the historical power data to determine the data attributes of the historical power data; Obtain the preset relationship between user information and access rights and the access user information of the historical power data, and determine the access rights to the historical power data according to the user information and the preset relationship to determine the user attributes of the historical power data; Obtain the operation information for operating the historical power data to determine the operation attributes of the historical power data; Obtain the gateway information of the user accessing the historical power data to determine the environmental attributes of the historical power data.

7. A data recognition system, characterized in that, It includes: A first processing module, configured to obtain current power data and determine the current power data spatial feature library, including: Obtain the data characteristics of the current power data and construct a data spatial feature model according to the data characteristics; Perform spatial feature extraction on the current power data based on the data spatial feature model, determine the spatial features of the current power data, and form a current power data spatial feature library; The data characteristics include: data attributes, user attributes, operation attributes, and environmental attributes. The obtaining of the data characteristics of the current power data includes: Perform data analysis on the storage database of the current power data to determine the data attributes of the current power data; Obtain the preset relationship between user information and access rights and the access user information of the current power data, and determine the access rights to the current power data according to the user information and the preset relationship to determine the user attributes of the current power data; Obtain the operation information for operating the current power data to determine the operation attributes of the current power data; Obtain the gateway information of the user accessing the current power data to determine the environmental attributes of the current power data; A second processing module, configured to obtain the historical power data spatial feature library as described in claim 6, and use the preset sensitive data features and the historical power data spatial feature library to determine a sensitive data spatial feature library; A third processing module, configured to perform modular arithmetic on the current power data spatial feature library and the sensitive data spatial feature library to determine the recognition result of the current power data; The determination of the sensitive data spatial feature library by using the preset sensitive data features and the historical power data spatial feature library includes: Obtaining the preset rules of the sensitive data; Based on the preset rules, screening the historical power data spatial feature library to determine the sensitive data spatial feature library.

Images