Dynamic grading method, device and equipment for power business data

Abstract

The invention provides a dynamic grading method, device and equipment for power business data, and relates to the technical field of power data processing. The method comprises the following steps: acquiring a power grid event log of a target power grid, a data type of target power business data, a transmission path and a timestamp at a current moment; wherein the target power grid is a power grid where a node corresponding to the target power business data is located; obtaining a first grading result of the target power business data through a decision tree algorithm based on the data type and the transmission path; if the first grading result is a middle security grade, calculating the dynamic sensitivity of the target power business data based on a power grid event log, a data type and a timestamp; and determining a final security level of the target power business data based on the dynamic sensitivity. According to the invention, the real-time dynamic adjustment of the data security level can be realized, the error rate of power business data grading is reduced through a machine learning method, and the automation level is improved.

Description

Technical Field

[0001] This invention relates to the field of power data processing technology, and in particular to a dynamic classification method, apparatus, and equipment for power business data. Background Technology

[0002] In power systems, power business data exhibits high complexity and dynamism. Traditionally, the security level of power business data is generally based on a static data classification and grading mechanism with fixed labels, that is, the security level of power business data is divided by fixed labels.

[0003] However, when using power business data with different security levels, the traditional approach of classifying security levels based on fixed labels has revealed a series of problems, such as high-risk data not being upgraded with protection in a timely manner or low-risk data being over-encrypted. This problem arises because when a system experiences a sudden fault warning (such as abnormal temperature rise in critical equipment or a surge in overload on local lines), the same power business data may instantly transform into high-security-level core data. If it is still protected as low-security-level data, it may cause data leakage or damage, ultimately leading to a power system shutdown. Similarly, if the data is still protected according to the high-security-level mode after the fault has been resolved, it will result in a waste of resources.

[0004] Therefore, there is an urgent need for a solution that can dynamically adjust the security level of power business data, so as to achieve real-time dynamic adjustment of data security level and balance the security and efficiency of data use. Summary of the Invention

[0005] This invention provides a method, apparatus, and device for dynamic classification of power business data to achieve real-time dynamic adjustment of data security level, while reducing the error rate of power business data classification and improving the level of automation through machine learning.

[0006] In a first aspect, embodiments of the present invention provide a dynamic hierarchical method for power business data, including:

[0007] Obtain the power grid event logs of the target power grid, the data type, transmission path, and current timestamp of the target power business data; where the target power grid is the power grid where the node corresponding to the target power business data is located.

[0008] Based on the data type and transmission path, the first-level result of the target power business data is obtained through the decision tree algorithm.

[0009] If the first classification result is medium security level, then the dynamic sensitivity of the target power business data is calculated based on the power grid event log, data type, and timestamp.

[0010] Based on dynamic sensitivity, the final security level of the target power business data is determined.

[0011] In one possible implementation, the dynamic sensitivity of the target power business data is calculated based on the power grid event log, data type, and timestamp, including:

[0012] Obtain the sensitivity base value corresponding to the data type.

[0013] Based on power grid event logs and timestamps, a dynamic sensitivity decay coefficient is obtained.

[0014] The product of the sensitivity baseline and the sensitivity dynamic attenuation coefficient is used as the dynamic sensitivity of the target power business data.

[0015] In one possible implementation, the sensitivity dynamic attenuation coefficient is obtained based on the power grid event log and timestamps, including:

[0016] Retrieve the abnormal time corresponding to the abnormal event in the power grid event log.

[0017] Based on the abnormal time and the preset time threshold, multiple abnormal time regions are obtained; each abnormal time region corresponds to a different preset coefficient.

[0018] Identify the abnormal time region where the timestamp is located and record it as the target abnormal time region.

[0019] The preset coefficient corresponding to the abnormal time region of the target is used as the sensitivity dynamic decay coefficient.

[0020] In one possible implementation, the data types of the target power business data include: user-side data, equipment operation data, and statistical data. The sensitivity baseline value corresponding to user-side data is greater than the sensitivity baseline value corresponding to equipment operation data, and the sensitivity baseline value corresponding to equipment operation data is greater than the sensitivity baseline value corresponding to statistical data.

[0021] In one possible implementation, the final security level of the target power business data is determined based on dynamic sensitivity, including:

[0022] Obtain the frequency at which the target power grid is being attacked at the current moment.

[0023] Based on the frequency of attacks on the target power grid at the current moment, the dynamic sensitivity is corrected to obtain the corrected dynamic sensitivity.

[0024] If the corrected dynamic sensitivity is within the first preset range, the final security level is determined to be a high security level.

[0025] If the corrected dynamic sensitivity is within the second preset range, the final security level is determined to be medium security level.

[0026] If the corrected dynamic sensitivity is within the third preset range, the final security level is determined to be a low security level.

[0027] In one possible implementation, the method also includes:

[0028] If the final security level of the target power business data is high security level, then the target power business data will be encrypted with AES-128 and an access whitelist will be set for the target power business data.

[0029] If the final security level of the target power business data is medium security level, then the target power business data will be encrypted using AES-128.

[0030] If the final security level of the target power business data is low, then the target power business data will be anonymized.

[0031] In one possible implementation, the dynamic sensitivity is corrected based on the frequency of attacks on the target power grid at the current moment, resulting in a corrected dynamic sensitivity, including:

[0032] Obtain the frequency of attacks on the target power grid at multiple historical moments.

[0033] Based on the frequency of attacks on the target power grid at multiple historical moments, the average frequency of attacks on the target power grid is calculated and denoted as the first average.

[0034] Calculate the ratio of the frequency at which the target power grid is attacked at the current moment to the first mean, and denot it as the correction coefficient.

[0035] The product of dynamic sensitivity and correction coefficient is used as the corrected dynamic sensitivity.

[0036] In one possible implementation, after obtaining the first-level result of the target power business data based on data type and transmission path using a decision tree algorithm, the following is also included:

[0037] If the first classification result is a high security level or a low security level, then the first classification result will be used as the final security level of the target power business data.

[0038] Secondly, embodiments of the present invention provide a dynamic hierarchical device for power business data, comprising:

[0039] The first processing module is used to obtain the power grid event log of the target power grid, the data type, transmission path, and current time timestamp of the target power business data; wherein, the target power grid is the power grid where the node corresponding to the target power business data is located.

[0040] The second processing module is used to obtain the first-level result of the target power business data based on the data type and transmission path through a decision tree algorithm.

[0041] The third processing module is used to calculate the dynamic sensitivity of the target power business data based on the power grid event log, data type, and timestamp if the first classification result is medium security level.

[0042] The fourth processing module is used to determine the final security level of the target power business data based on dynamic sensitivity.

[0043] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.

[0044] In this embodiment of the invention, the target power business data is first initially classified according to its data type and transmission path using a decision tree algorithm. When the target power business data is classified as medium security level, the dynamic sensitivity of the target power business data is calculated using power grid event logs, data type, and timestamps. Based on the dynamic sensitivity, the security level of the target power business data is reassessed, thus determining the final security level of the target power business data. This scheme uses a decision tree algorithm to classify and determine the security level of power business data that is easy to classify. The machine learning approach can reduce the time required for classifying some power business data, improve efficiency, and achieve automation. For power business data that is susceptible to power grid events and external interference, dynamic sensitivity is set. The dynamic sensitivity can be adjusted in a timely manner based on real-time events occurring in the power grid, thereby dynamically determining the security level of the power business data at different times. This enables timely upgrading or downgrading of the protection level of power business data, dynamically balancing the security and efficiency of power business data usage. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating the implementation of the dynamic hierarchical method for power business data provided in this embodiment of the invention.

[0046] Figure 2 This is a schematic diagram of the structure of the dynamic classification device for power business data provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0048] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0049] See Figure 1 The document illustrates a flowchart of the implementation of the dynamic hierarchical method for power business data provided in an embodiment of the present invention, which is described in detail below:

[0050] Step 101: Obtain the power grid event log of the target power grid, the data type, transmission path, and current timestamp of the target power business data; wherein, the target power grid is the power grid where the node corresponding to the target power business data is located.

[0051] In one possible implementation, the data types of the target power business data include: user-side data, equipment operation data, and statistical data. The sensitivity baseline value corresponding to user-side data is greater than the sensitivity baseline value corresponding to equipment operation data, and the sensitivity baseline value corresponding to equipment operation data is greater than the sensitivity baseline value corresponding to statistical data.

[0052] For example, the sensitivity baseline for user-side data can be 7-9, the sensitivity baseline for device operation data can be 5 or 6, and the sensitivity baseline for statistical data can be 1-4. User-side data can be data directly related to personal identity, such as name, address, and precise location. Device operation data can be data that may infer user behavior, such as transformer temperature and current curves. Statistical data can be data that cannot pinpoint individual behavior, such as total regional electricity consumption.

[0053] For example, the power grid event log continuously records whether any equipment in the target power grid malfunctions, and whether the power grid enters emergency response mode (an emergency state entered by the power grid due to natural disasters such as typhoons and earthquakes). Target power business data can be transmitted via the public internet or a local area network. Power business data transmitted via the public internet carries a greater risk of data leakage.

[0054] Step 102: Based on the data type and transmission path, the first-level result of the target power business data is obtained through the decision tree algorithm.

[0055] For example, the first step is to make a first-level judgment based on the data type. Depending on the data type, the algorithm will proceed to the next branch of the decision tree. Then, the second step is to make a judgment based on the transmission path to obtain the first-level result.

[0056] For example, the first-level result for the combination of user-side data and local area network transmission is high security level; the first-level result for the combination of user-side data and public Internet transmission is also high security level.

[0057] The first-level result corresponding to the combination of equipment operation data and local area network transmission is high security level; the first-level result corresponding to the combination of equipment operation data and public Internet transmission is medium security level.

[0058] The first-level result for the combination of statistical data and local area network transmission is medium security level; the first-level result for the combination of statistical data and public Internet transmission is low security level.

[0059] Step 103: If the first classification result is medium security level, then calculate the dynamic sensitivity of the target power business data based on the power grid event log, data type and timestamp.

[0060] In one possible implementation, the dynamic sensitivity of the target power business data is calculated based on the power grid event log, data type, and timestamp, including:

[0061] Obtain the sensitivity base value corresponding to the data type.

[0062] Based on power grid event logs and timestamps, a dynamic sensitivity decay coefficient is obtained.

[0063] The product of the sensitivity baseline and the sensitivity dynamic attenuation coefficient is used as the dynamic sensitivity of the target power business data.

[0064] For example, the sensitivity attenuation coefficient can be dynamically adjusted using power grid event logs and timestamps. This allows for dynamic adjustment of sensitivity in real time, enabling real-time dynamic adjustment of data security levels, preventing data leakage or damage, and reducing resource waste.

[0065] In one possible implementation, the sensitivity dynamic attenuation coefficient is obtained based on the power grid event log and timestamps, including:

[0066] Retrieve the abnormal time corresponding to the abnormal event in the power grid event log.

[0067] Based on the abnormal time and the preset time threshold, multiple abnormal time regions are obtained; each abnormal time region corresponds to a different preset coefficient.

[0068] Identify the abnormal time region where the timestamp is located and record it as the target abnormal time region.

[0069] The preset coefficient corresponding to the abnormal time region of the target is used as the sensitivity dynamic decay coefficient.

[0070] For example, to facilitate understanding of the concept of abnormal time zones, assuming the abnormal time is 12:00:00, the time can be divided into three abnormal time zones based on preset time thresholds (5 minutes, 10 minutes, or 15 minutes, etc.): 12:00:01 to 12:05:00 (assuming a preset coefficient of 1.2 for this zone), 12:05:01 to 12:15:00 (assuming a preset coefficient of 1 for this zone), and the abnormal time zone after 12:15:01 (assuming a preset coefficient of 0.8 for this zone). Then, based on the timestamp, the dynamic sensitivity attenuation coefficient can be determined. This allows for second-level dynamic adjustment of the dynamic sensitivity, resulting in a faster response to power grid events.

[0071] For example, after step 102, the method further includes:

[0072] If the first classification result is a high security level or a low security level, then the first classification result will be used as the final security level of the target power business data.

[0073] Step 104: Determine the final security level of the target power business data based on dynamic sensitivity.

[0074] In one possible implementation, step 104 may include:

[0075] Obtain the frequency at which the target power grid is being attacked at the current moment.

[0076] Based on the frequency of attacks on the target power grid at the current moment, the dynamic sensitivity is corrected to obtain the corrected dynamic sensitivity.

[0077] If the corrected dynamic sensitivity is within the first preset range, the final security level is determined to be a high security level.

[0078] If the corrected dynamic sensitivity is within the second preset range, the final security level is determined to be medium security level.

[0079] If the corrected dynamic sensitivity falls within the third preset range, the final security level is determined to be a low security level.

[0080] For example, in order to ensure the accuracy of the final security level determination and to avoid false alarms, the dynamic sensitivity was additionally corrected based on the frequency of attacks on the target power grid at the current moment.

[0081] In one possible implementation, the dynamic sensitivity is corrected based on the frequency of attacks on the target power grid at the current moment, resulting in a corrected dynamic sensitivity, including:

[0082] Obtain the frequency of attacks on the target power grid at multiple historical moments.

[0083] Based on the frequency of attacks on the target power grid at multiple historical moments, the average frequency of attacks on the target power grid is calculated and denoted as the first average.

[0084] Calculate the ratio of the frequency at which the target power grid is attacked at the current moment to the first mean, and denot it as the correction coefficient.

[0085] The product of dynamic sensitivity and correction coefficient is used as the corrected dynamic sensitivity.

[0086] For example, in order to accurately determine the final security level, the dynamic sensitivity is corrected by using the frequency of attacks on the target power grid at multiple historical moments. Taking into account the impact of historical external factors on the determination of the security level, a more accurate security level can be obtained.

[0087] In one possible implementation, the method also includes:

[0088] If the final security level of the target power business data is high security level, then the target power business data will be encrypted with AES-128 and an access whitelist will be set for the target power business data.

[0089] If the final security level of the target power business data is medium security level, then the target power business data will be encrypted using AES-128.

[0090] If the final security level of the target power business data is low, then the target power business data will be anonymized.

[0091] For example, data anonymization typically involves: transforming the data, such as: numerical generalization (e.g., precise location "longitude 116.4 → area A"), character masking (user ID card "110XXX1990"), and data aggregation (single household electricity consumption → street average), etc.

[0092] For example, AES-128 encryption typically involves symmetric encryption of data using a 128-bit key, with an encryption speed of 10Gbps.

[0093] For example, setting an access whitelist for target power business data typically includes: an IP whitelist (allowing only the dispatch center's dedicated network IP to access and read data), binding to specific industrial control terminals, and setting access time windows (e.g., access is only available from 8:00 to 18:00 on weekdays).

[0094] The aforementioned dynamic classification method for power business data first performs an initial classification of the target power business data based on its data type and transmission path using a decision tree algorithm. When the target power business data is classified as medium security level, the dynamic sensitivity of the target power business data is calculated using grid event logs, data type, and timestamps. Based on the dynamic sensitivity, the classification level of the target power business data is reassessed, determining the final security level. This scheme uses a decision tree algorithm to classify and determine the security level of power business data that is easy to classify. The machine learning approach can reduce the classification time for some power business data, improve efficiency, and achieve automation. For power business data that is susceptible to grid events and external interference, dynamic sensitivity is set, which can be adjusted in a timely manner based on real-time grid events, thereby dynamically determining the security level of power business data at different times. This enables timely upgrading or downgrading of the protection level of power business data, dynamically balancing the security and efficiency of power business data usage.

[0095] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0096] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0097] Figure 2 A schematic diagram of the dynamic classification device for power business data provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0098] like Figure 2 As shown, the dynamic hierarchical device for power business data includes:

[0099] The first processing module 201 is used to obtain the power grid event log of the target power grid, the data type, transmission path, and current time timestamp of the target power business data; wherein, the target power grid is the power grid where the node corresponding to the target power business data is located.

[0100] The second processing module 202 is used to obtain the first-level result of the target power business data based on the data type and transmission path through a decision tree algorithm.

[0101] The third processing module 203 is used to calculate the dynamic sensitivity of the target power business data based on the power grid event log, data type and timestamp if the first classification result is medium security level.

[0102] The fourth processing module 204 is used to determine the final security level of the target power business data based on dynamic sensitivity.

[0103] In one possible implementation, the third processing module 203 can be used for:

[0104] Obtain the sensitivity base value corresponding to the data type.

[0105] Based on power grid event logs and timestamps, a dynamic sensitivity decay coefficient is obtained.

[0106] The product of the sensitivity baseline and the sensitivity dynamic attenuation coefficient is used as the dynamic sensitivity of the target power business data.

[0107] In one possible implementation, the third processing module 203 can be used for:

[0108] Retrieve the abnormal time corresponding to the abnormal event in the power grid event log.

[0109] Based on the abnormal time and the preset time threshold, multiple abnormal time regions are obtained; each abnormal time region corresponds to a different preset coefficient.

[0110] Identify the abnormal time region where the timestamp is located and record it as the target abnormal time region.

[0111] The preset coefficient corresponding to the abnormal time region of the target is used as the sensitivity dynamic decay coefficient.

[0112] In one possible implementation, the data types of the target power business data include: user-side data, equipment operation data, and statistical data. The sensitivity baseline value corresponding to the equipment operation data is greater than the sensitivity baseline value corresponding to the equipment operation data, and the sensitivity baseline value corresponding to the user-side data is greater than the sensitivity baseline value corresponding to the statistical data.

[0113] In one possible implementation, the fourth processing module 204 can be used for:

[0114] Obtain the frequency at which the target power grid is being attacked at the current moment.

[0115] Based on the frequency of attacks on the target power grid at the current moment, the dynamic sensitivity is corrected to obtain the corrected dynamic sensitivity.

[0116] If the corrected dynamic sensitivity is within the first preset range, the final security level is determined to be a high security level.

[0117] If the corrected dynamic sensitivity is within the second preset range, the final security level is determined to be medium security level.

[0118] If the corrected dynamic sensitivity is within the third preset range, the final security level is determined to be a low security level.

[0119] In one possible implementation, the dynamic classification device for power business data further includes a fifth processing module, which is used for:

[0120] If the final security level of the target power business data is high security level, then the target power business data will be encrypted with AES-128 and an access whitelist will be set for the target power business data.

[0121] If the final security level of the target power business data is medium security level, then the target power business data will be encrypted using AES-128.

[0122] If the final security level of the target power business data is low, then the target power business data will be anonymized.

[0123] In one possible implementation, the fourth processing module 204 can be used for:

[0124] Obtain the frequency of attacks on the target power grid at multiple historical moments.

[0125] Based on the frequency of attacks on the target power grid at multiple historical moments, the average frequency of attacks on the target power grid is calculated and denoted as the first average.

[0126] Calculate the ratio of the frequency at which the target power grid is attacked at the current moment to the first mean, and denot it as the correction coefficient.

[0127] The product of dynamic sensitivity and correction coefficient is used as the corrected dynamic sensitivity.

[0128] In one possible implementation, the third processing module 203 is further configured to:

[0129] If the first classification result is a high security level or a low security level, then the first classification result will be used as the final security level of the target power business data.

[0130] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 3 As shown, the electronic device 3 of this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above.

[0131] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.

[0132] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.

[0133] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0134] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0135] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A dynamic hierarchical method for power business data, characterized in that, include: Obtain the power grid event log of the target power grid, the data type, transmission path, and current timestamp of the target power business data; wherein, the target power grid is the power grid where the node corresponding to the target power business data is located; Based on the data type and the transmission path, the first hierarchical result of the target power business data is obtained through the decision tree algorithm; If the first classification result is medium security level, then the dynamic sensitivity of the target power business data is calculated based on the power grid event log, the data type, and the timestamp. Based on the dynamic sensitivity, the final security level of the target power business data is determined.

2. The dynamic hierarchical method for power business data according to claim 1, characterized in that, The calculation of the dynamic sensitivity of the target power business data based on the power grid event log, the data type, and the timestamp includes: Obtain the sensitivity base value corresponding to the data type; Based on the power grid event log and the timestamp, the sensitivity dynamic attenuation coefficient is obtained; The product of the sensitivity base value and the sensitivity dynamic attenuation coefficient is taken as the dynamic sensitivity of the target power business data.

3. The dynamic hierarchical method for power business data according to claim 2, characterized in that, The process of obtaining the sensitivity dynamic attenuation coefficient based on the power grid event log and the timestamp includes: Obtain the abnormal time corresponding to the abnormal event in the power grid event log; Based on the abnormal time and the preset time threshold, multiple abnormal time regions are obtained; wherein, each abnormal time region corresponds to a different preset coefficient; Determine the abnormal time region where the timestamp is located and record it as the target abnormal time region; The preset coefficient corresponding to the target abnormal time region is used as the sensitivity dynamic decay coefficient.

4. The dynamic hierarchical method for power business data according to claim 2, characterized in that, The target power business data includes the following data types: user-side data, equipment operation data, and statistical data. The sensitivity baseline value corresponding to user-side data is greater than that corresponding to equipment operation data, and the sensitivity baseline value corresponding to equipment operation data is greater than that corresponding to statistical data.

5. The dynamic hierarchical method for power business data according to claim 1, characterized in that, The determination of the final security level of the target power business data based on the dynamic sensitivity includes: Obtain the frequency at which the target power grid is currently under attack; Based on the frequency of attacks on the target power grid at the current moment, the dynamic sensitivity is corrected to obtain the corrected dynamic sensitivity. If the corrected dynamic sensitivity is within the first preset range, then the final security level is determined to be a high security level; If the corrected dynamic sensitivity is within the second preset range, then the final security level is determined to be a medium security level. If the corrected dynamic sensitivity is within the third preset range, then the final security level is determined to be a low security level.

6. The dynamic hierarchical method for power business data according to claim 5, characterized in that, The method further includes: If the final security level of the target power business data is high security level, then the target power business data is encrypted with AES-128 and an access whitelist is set for the target power business data. If the final security level of the target power service data is medium security level, then the target power service data is encrypted using AES-128. If the final security level of the target power business data is low, then the target power business data will be de-identified.

7. The dynamic hierarchical method for power business data according to claim 6, characterized in that, The step of correcting the dynamic sensitivity based on the frequency of attacks on the target power grid at the current moment to obtain the corrected dynamic sensitivity includes: Obtain the attack frequency of the target power grid at multiple historical moments; Based on the frequency of attacks on the target power grid at multiple historical moments, the average frequency of attacks on the target power grid is calculated and denoted as the first average. Calculate the ratio of the frequency at which the target power grid is attacked at the current moment to the first average value, and record it as the correction coefficient; The product of the dynamic sensitivity and the correction coefficient is used as the corrected dynamic sensitivity.

8. The dynamic hierarchical method for power business data according to claim 1, characterized in that, After the step of obtaining the first hierarchical result of the target power service data based on the data type and the transmission path using a decision tree algorithm, the method further includes: If the first classification result is a high security level or a low security level, then the first classification result shall be taken as the final security level of the target power business data.

9. A dynamic hierarchical device for power business data, characterized in that, include: The first processing module is used to obtain the power grid event log of the target power grid, the data type, transmission path, and current time timestamp of the target power business data; wherein, the target power grid is the power grid where the node corresponding to the target power business data is located; The second processing module is used to obtain the first hierarchical result of the target power business data based on the data type and the transmission path through a decision tree algorithm; The third processing module is used to calculate the dynamic sensitivity of the target power business data based on the power grid event log, the data type, and the timestamp if the first classification result is a medium security level. The fourth processing module is used to determine the final security level of the target power business data based on the dynamic sensitivity.

10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 8.

Images