Cloud platform data security risk prediction method and system, and storage medium

Abstract

The invention discloses a cloud platform data security risk prediction method and system and a storage medium, and relates to the technical field of data security, and the method comprises the steps: obtaining at least one data storage node and at least one data storage path of a cloud platform; acquiring data importance levels of the data storage nodes; data of the cloud platform is backed up, and the backed-up data is stored in the block chain; obtaining at least one network attack category, and calculating the proportion of the network attack category; calculating to obtain an average influence factor of the network attack category on the cloud platform attack; calculating to obtain an overall influence factor of the at least one network attack on the cloud platform attack; and using the overall influence factor as a cloud platform data security risk prediction level. By arranging the security classification module, the exception acquisition module, the factor calculation module and the risk prediction module, different conditions of various network attacks and different influences on data are considered, and the obtained prediction result has high reference value.

Description

Technical Field

[0001] The present invention relates to the field of data security technology, and in particular to a cloud platform data security risk prediction method, system and storage medium. Background Art

[0002] With the rapid development of the digital economy and the advancement of the digital transformation of traditional businesses, data security has become the most pressing and fundamental security issue in the digital economy era. At this stage, a large number of complex data processing activities have emerged. How to systematically, comprehensively and effectively build and improve data security protection capabilities, and strike a balance between data economy, data value and data security, as well as perceive and monitor data theft, and predict possible data security risks in the future, so as to avoid data leakage incidents, are issues that the industry and enterprises are very concerned about.

[0003] Data security risk prediction involves complex network attacks and complex data security issues. The existing risk prediction methods do not comprehensively consider various situations, and the prediction results are not targeted enough and have low reference value. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, a cloud platform data security risk prediction method, system and storage medium are provided. This technical solution solves the problem that the data security risk prediction proposed in the above-mentioned background technology involves complex network attacks and complex data security issues, and the existing risk prediction methods do not comprehensively consider various situations, and the prediction results obtained are not targeted enough and have low reference value.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: A cloud platform data security risk prediction method, comprising: Acquire a data storage structure of the cloud platform, and acquire at least one data storage node and at least one data storage path of the cloud platform according to the data storage structure; Get the data importance level of the data storage node; Back up the data on the cloud platform, and store the backup data in the blockchain. The blockchain sets access verification, which includes face recognition and iris recognition. If both face recognition and iris recognition are passed, the authority to call the data in the blockchain is obtained. If both face recognition and iris recognition are not passed, the authority to call the data in the blockchain cannot be obtained. Obtain at least one network attack suffered by the cloud platform, classify the at least one network attack, obtain at least one network attack category, and calculate the proportion of the network attack category; Obtain the degree of data leakage after the cyber attack on the cloud platform in the cyber attack category; Obtain the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category; Obtain the proportion of false data after cyber attacks on cloud platforms in the cyber attack category; Calculate the average impact factor of network attack categories on cloud platform attacks; Calculate the overall impact factor of at least one network attack on the cloud platform attack; The overall impact factor is used as the cloud platform data security risk prediction level. The larger the overall impact factor, the greater the cloud platform data security risk.

[0006] Preferably, obtaining the data importance level of the data storage node comprises the following steps: Construct a neural network model, use the neural network model to identify keywords in the data of all data storage nodes, and divide the keywords into levels. The higher the importance of the keyword, the higher the keyword classification; According to the hierarchical division of keywords, the data of all data storage nodes are divided into levels to obtain the importance classification of each data; The importance level of each data of a single data storage node is weighted and accumulated to obtain the data importance level of the data storage node, wherein the weighted coefficient is the proportion of each data in the single data storage node.

[0007] Preferably, obtaining at least one network attack category and calculating the proportion of the network attack category comprises the following steps: building a neural network model, and using the neural network model to classify at least one network attack; Aggregate cyber attacks that fall into the same category into cyber attack categories; Count the total number of attacks of at least one network attack; Count the number of network attacks in the network attack category as the attack part number; The number of attack parts is divided by the total number of attacks to get the proportion of network attack categories.

[0008] Preferably, obtaining the degree of data leakage after the network attack on the cloud platform in the network attack category includes the following steps: After the cloud platform is attacked by a network attack in the network attack category, the amount of leaked data output by the data storage node to the outside of the cloud platform is obtained; The data importance level of the data storage node is used as a weight and multiplied by the amount of leaked data to obtain the weighted amount of leakage; The weighted amounts of leakage of all data storage nodes are accumulated as the degree of data leakage after the network attack on the cloud platform in the network attack category.

[0009] Preferably, obtaining the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category includes the following steps: After the cloud platform is attacked by the network attack in the network attack category, the data storage path is used for data interaction; If there is an abnormality in data interaction, the data storage path is regarded as the abnormal storage path. If not, no processing is performed; Counting the number of data storage paths that are abnormal storage paths to obtain the number of abnormalities; Counting the number of at least one data storage path to obtain a total number of paths; The value of dividing the number of anomalies by the total number of paths is used as the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category.

[0010] Preferably, obtaining the proportion of false data after the network attack on the cloud platform in the network attack category includes the following steps: After the cloud platform is attacked by a network attack in the network attack category, the post-attack data of the data storage node is obtained; Through the access verification set by the blockchain, the feature backup data corresponding to the data storage node in the blockchain is retrieved; Obtain data that is different from the post-attack data of the data storage node and the characteristic backup data as partial false data; Accumulate partial false data of all data storage nodes to obtain overall false data; Get the total data volume of all data storage nodes; The value of dividing the total amount of false data by the total amount of data is taken as the proportion of false data after the network attack on the cloud platform in the network attack category.

[0011] Preferably, the step of calculating the average impact factor of the network attack category on the cloud platform attack comprises the following steps: The average data leakage degree is obtained by adding up the data leakage degree of all network attacks on the cloud platform in the network attack category and averaging them. The average storage path abnormality degree is obtained by accumulating the abnormality degree of all network attacks on the cloud platform in the network attack category and averaging them. The average false data percentage is obtained by adding up the percentage of false data after all network attacks on the cloud platform in the network attack category and averaging them. The average impact factor is obtained by adding up the average data leakage degree, the average storage path abnormality degree, and the average false data ratio.

[0012] Preferably, the calculating of the overall impact factor of at least one network attack on the cloud platform attack comprises the following steps: Obtain at least one network attack category; Multiply the average impact factor in the network attack category by the proportion in the network attack category to obtain the average weighted impact factor of the network attack category; The average weighted impact factors of at least one network attack category are accumulated to obtain the overall impact factor of at least one network attack on the cloud platform attack.

[0013] A cloud platform data security risk prediction system, used to implement the above-mentioned cloud platform data security risk prediction method, comprising: A data acquisition module, wherein the data acquisition module acquires at least one data storage node and at least one data storage path of the cloud platform; A data classification module, wherein the data classification module obtains the data importance level of the data storage node; A data backup module, which backs up the data on the cloud platform, and the backup data is stored in the blockchain; A security classification module, wherein the security classification module obtains at least one network attack suffered by the cloud platform, classifies the at least one network attack, and obtains at least one network attack category; An abnormality acquisition module, wherein the abnormality acquisition module acquires the degree of data leakage after the network attack on the cloud platform in the network attack category, acquires the degree of abnormality of the storage path after the network attack on the cloud platform in the network attack category, and acquires the proportion of false data after the network attack on the cloud platform in the network attack category; A factor calculation module, wherein the factor calculation module calculates an average impact factor of a network attack category on a cloud platform attack, and calculates an overall impact factor of at least one network attack on a cloud platform attack; A risk prediction module uses an overall impact factor as a cloud platform data security risk prediction level.

[0014] A storage medium having a computer-readable program stored thereon, wherein the computer-readable program, when called, executes the above-mentioned cloud platform data security risk prediction method.

[0015] Compared with the prior art, the present invention has the following beneficial effects: By setting up data classification module, security classification module, anomaly acquisition module, factor calculation module and risk prediction module, the impact of existing network attacks on the cloud platform is used to infer the cloud platform's risk resistance. When predicting, the network attacks are classified and the cloud platform data is classified by importance. Then, according to the degree of data leakage, data change and path damage, the risk level of each network attack on the cloud platform is evaluated, and then the risk impact of all network attacks on the cloud platform is comprehensively obtained. In the prediction process, the different situations of various network attacks and the different impacts on the data are taken into account. The prediction results are highly matched with the cloud platform and have a high reference value. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the process of predicting the data security risk of a cloud platform of the present invention; Figure 2 A schematic diagram of a process for obtaining the data importance level of a data storage node according to the present invention; Figure 3 A schematic diagram of a flow chart of obtaining at least one network attack category and calculating the proportion of the network attack category according to the present invention; Figure 4 A schematic diagram of a flow chart of obtaining the degree of data leakage after a network attack on a cloud platform in a network attack category of the present invention; Figure 5 A schematic diagram of a flow chart of obtaining the abnormality degree of a storage path after a network attack on a cloud platform in a network attack category of the present invention; Figure 6 A schematic diagram of a process for obtaining the proportion of false data after a network attack on a cloud platform in a network attack category of the present invention; Figure 7 A schematic diagram of the process of calculating the average impact factor of network attack categories on cloud platform attacks in the present invention; Figure 8 A schematic diagram of the process of calculating the overall impact factor of at least one network attack on a cloud platform attack according to the present invention. DETAILED DESCRIPTION

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0018] Reference Figure 1 As shown, a cloud platform data security risk prediction method includes: Acquire a data storage structure of the cloud platform, and acquire at least one data storage node and at least one data storage path of the cloud platform according to the data storage structure; Get the data importance level of the data storage node; Back up the data on the cloud platform, and store the backup data in the blockchain. The blockchain sets access verification, which includes face recognition and iris recognition. If both face recognition and iris recognition are passed, the authority to call the data in the blockchain is obtained. If both face recognition and iris recognition are not passed, the authority to call the data in the blockchain cannot be obtained. Obtain at least one network attack suffered by the cloud platform, classify the at least one network attack, obtain at least one network attack category, and calculate the proportion of the network attack category; Obtain the degree of data leakage after the cyber attack on the cloud platform in the cyber attack category; Obtain the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category; Obtain the proportion of false data after cyber attacks on cloud platforms in the cyber attack category; Calculate the average impact factor of network attack categories on cloud platform attacks; Calculate the overall impact factor of at least one network attack on the cloud platform attack; The overall impact factor is used as the cloud platform data security risk prediction level. The larger the overall impact factor, the greater the cloud platform data security risk.

[0019] Reference Figure 2 As shown, obtaining the data importance level of the data storage node includes the following steps: Construct a neural network model, use the neural network model to identify keywords in the data of all data storage nodes, and divide the keywords into levels. The higher the importance of the keyword, the higher the keyword classification; According to the hierarchical division of keywords, the data of all data storage nodes are divided into levels to obtain the importance classification of each data; The importance level of each data of a single data storage node is weighted and accumulated to obtain the data importance level of the data storage node, wherein the weighted coefficient is the proportion of each data in the single data storage node; The purpose of obtaining the data importance level of the data storage node is to predict the data anomaly after a network attack. Under the same data anomaly situation, the more important the data is, the higher the risk will be. Therefore, it is necessary to grade the importance of the data. If the data is not differentiated, the accuracy of the prediction result will be compromised.

[0020] Reference Figure 3 As shown, obtaining at least one network attack category and calculating the proportion of the network attack category include the following steps: building a neural network model, and using the neural network model to classify at least one network attack; Aggregate cyber attacks that fall into the same category into cyber attack categories; Count the total number of attacks of at least one network attack; Count the number of network attacks in the network attack category as the attack part number; The number of attack parts is divided by the total number of attacks to get the proportion of network attack categories; There are different categories of network attacks. According to their attack effects, they can be classified and their codes can be matched with the categories. Thus, a rated neural network model is constructed, and then the neural network model is used to judge and identify the codes of network attacks, and the network attacks are assigned to the corresponding categories, thereby realizing the classification of network attacks. The purpose of calculating the proportion of network attack categories is: when obtaining the impact of network attack categories on cloud platform data, the impact is weighted according to the proportion of network attack categories, so as to synthesize the risk results of all network attack categories.

[0021] Reference Figure 4 As shown, obtaining the degree of data leakage after a network attack on a cloud platform in the network attack category includes the following steps: After the cloud platform is attacked by a network attack in the network attack category, the amount of leaked data output by the data storage node to the outside of the cloud platform is obtained; The data importance level of the data storage node is used as a weight and multiplied by the amount of leaked data to obtain the weighted amount of leakage; The weighted amount of leakage of all data storage nodes is accumulated as the degree of data leakage after the network attack on the cloud platform in the network attack category; When data is leaked, it must be output outside the cloud platform. Therefore, the amount of output data is taken as the amount of leaked data. The risk of data leakage is related to the importance of the data. The higher the importance, the higher the degree of leakage.

[0022] Reference Figure 5 As shown, obtaining the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category includes the following steps: After the cloud platform is attacked by the network attack in the network attack category, the data storage path is used for data interaction; If there is an abnormality in data interaction, the data storage path is regarded as the abnormal storage path. If not, no processing is performed; Counting the number of data storage paths that are abnormal storage paths to obtain the number of abnormalities; Counting the number of at least one data storage path to obtain a total number of paths; The value of dividing the number of anomalies by the total number of paths is taken as the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category; After a network attack, the data storage path may be damaged, resulting in the inability to transmit data, which will affect the normal use of the cloud platform. Therefore, it is necessary to evaluate the degree of abnormality of the storage path.

[0023] Reference Figure 6 As shown, obtaining the proportion of false data after a network attack on a cloud platform in a network attack category includes the following steps: After the cloud platform is attacked by a network attack in the network attack category, the post-attack data of the data storage node is obtained; Through the access verification set by the blockchain, the feature backup data corresponding to the data storage node in the blockchain is retrieved; Obtain data that is different from the post-attack data of the data storage node and the characteristic backup data as partial false data; Accumulate partial false data of all data storage nodes to obtain overall false data; Get the total data volume of all data storage nodes; The total amount of false data divided by the total amount of data is taken as the proportion of false data after the network attack on the cloud platform in the network attack category; During a cyber attack, not only does data leakage occur, but false data may also be injected into the cloud platform data, polluting the data in the cloud platform. Therefore, it is necessary to compare the amount of false data and then estimate the impact of each cyber attack on the cloud platform.

[0024] Reference Figure 7 As shown in Figure 2, calculating the average impact factor of network attack categories on cloud platform attacks includes the following steps: The average data leakage degree is obtained by adding up the data leakage degree of all network attacks on the cloud platform in the network attack category and averaging them. The average storage path abnormality degree is obtained by accumulating the abnormality degree of all network attacks on the cloud platform in the network attack category and averaging them. The average false data percentage is obtained by adding up the percentage of false data after all network attacks on the cloud platform in the network attack category and averaging them. The average impact factor is obtained by adding up the average data leakage degree, the average storage path abnormality degree and the average false data ratio. When calculating the average impact factor of network attack categories on cloud platform attacks, the degree of data leakage, the degree of storage path abnormality, and the proportion of false data are combined, and then the influence of multiple factors is considered, making the prediction more comprehensive and the results more accurate; Since the network environment is stable over a period of time and all attacks are roughly the same, the prediction results formed by this method can predict the risks of the cloud platform within a period of time. However, when the preset time is exceeded, the prediction results need to be updated using this method, and the updated results are used to predict the risks. When the predicted risk is within an acceptable range, the cloud platform will not be upgraded. When the predicted risk is not within an acceptable range, the cloud platform will be upgraded.

[0025] Reference Figure 8 As shown, calculating the overall impact factor of at least one network attack on the cloud platform attack includes the following steps: Obtain at least one network attack category; Multiply the average impact factor in the network attack category by the proportion in the network attack category to obtain the average weighted impact factor of the network attack category; The average weighted impact factors of at least one network attack category are accumulated to obtain the overall impact factor of at least one network attack on the cloud platform attack.

[0026] A cloud platform data security risk prediction system, used to implement the above-mentioned cloud platform data security risk prediction method, comprising: A data acquisition module, wherein the data acquisition module acquires at least one data storage node and at least one data storage path of the cloud platform; A data classification module, wherein the data classification module obtains the data importance level of the data storage node; A data backup module, which backs up the data on the cloud platform, and the backup data is stored in the blockchain; A security classification module, wherein the security classification module obtains at least one network attack suffered by the cloud platform, classifies the at least one network attack, and obtains at least one network attack category; An abnormality acquisition module, wherein the abnormality acquisition module acquires the degree of data leakage after the network attack on the cloud platform in the network attack category, acquires the degree of abnormality of the storage path after the network attack on the cloud platform in the network attack category, and acquires the proportion of false data after the network attack on the cloud platform in the network attack category; A factor calculation module, wherein the factor calculation module calculates an average impact factor of a network attack category on a cloud platform attack, and calculates an overall impact factor of at least one network attack on a cloud platform attack; A risk prediction module uses an overall impact factor as a cloud platform data security risk prediction level.

[0027] The working process of the above cloud platform data security risk prediction system is as follows; Step 1: The data acquisition module acquires the data storage structure of the cloud platform, and acquires at least one data storage node and at least one data storage path of the cloud platform according to the data storage structure; Step 2: The data classification module obtains the data importance level of the data storage node; Step 3: The data backup module backs up the data on the cloud platform, and the backup data is stored in the blockchain; Step 4: The security classification module obtains at least one network attack suffered by the cloud platform, classifies the at least one network attack, obtains at least one network attack category, and calculates the proportion of the network attack category; Step 5: The abnormal acquisition module obtains the degree of data leakage after the network attack on the cloud platform in the network attack category, obtains the abnormal degree of the storage path after the network attack on the cloud platform in the network attack category, and obtains the proportion of false data after the network attack on the cloud platform in the network attack category; Step 6: The factor calculation module calculates the average impact factor of the network attack category on the cloud platform attack, and calculates the overall impact factor of at least one network attack on the cloud platform attack; Step 7: The risk prediction module uses the overall impact factor as the cloud platform data security risk prediction level. The larger the overall impact factor, the greater the cloud platform data security risk.

[0028] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, the above-mentioned cloud platform data security risk prediction method is executed.

[0029] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0030] To sum up, the advantages of the present invention are: by setting up a data classification module, a security classification module, an anomaly acquisition module, a factor calculation module and a risk prediction module, the impact of existing network attacks on the cloud platform is used to infer the risk resistance of the cloud platform. When predicting, the network attacks are classified, and the data of the cloud platform is classified by importance. Then, according to the degree of data leakage, data change and path damage, the risk level of each network attack to the cloud platform is evaluated, and then the risk impact of all network attacks on the cloud platform is comprehensively obtained. In the prediction process, the different situations of various network attacks and the different impacts on the data are taken into account, and the obtained prediction results have a high degree of matching with the cloud platform and have a high reference value.

[0031] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A cloud platform data security risk prediction method, characterized in that: include: Acquire a data storage structure of the cloud platform, and acquire at least one data storage node and at least one data storage path of the cloud platform according to the data storage structure; Get the data importance level of the data storage node; Back up the data on the cloud platform, and store the backup data in the blockchain. The blockchain sets access verification, which includes face recognition and iris recognition. If both face recognition and iris recognition are passed, the authority to call the data in the blockchain is obtained. If both face recognition and iris recognition are not passed, the authority to call the data in the blockchain cannot be obtained. Obtain at least one network attack suffered by the cloud platform, classify the at least one network attack, obtain at least one network attack category, and calculate the proportion of the network attack category; Obtain the degree of data leakage after the cyber attack on the cloud platform in the cyber attack category; Obtain the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category; Obtain the proportion of false data after cyber attacks on cloud platforms in the cyber attack category; Calculate the average impact factor of network attack categories on cloud platform attacks; Calculate the overall impact factor of at least one network attack on the cloud platform attack; The overall impact factor is used as the cloud platform data security risk prediction level. The larger the overall impact factor, the greater the cloud platform data security risk.

2. A cloud platform data security risk prediction method according to claim 1, characterized in that: The step of obtaining the data importance level of the data storage node comprises the following steps: Construct a neural network model, use the neural network model to identify keywords in the data of all data storage nodes, and divide the keywords into levels. The higher the importance of the keyword, the higher the keyword classification; According to the hierarchical division of keywords, the data of all data storage nodes are divided into levels to obtain the importance classification of each data; The importance level of each data of a single data storage node is weighted and accumulated to obtain the data importance level of the data storage node, wherein the weighted coefficient is the proportion of each data in the single data storage node.

3. A cloud platform data security risk prediction method according to claim 2, characterized in that: Obtaining at least one network attack category and calculating the proportion of the network attack category comprises the following steps: building a neural network model, and using the neural network model to classify at least one network attack; Aggregate cyber attacks that fall into the same category into cyber attack categories; Count the total number of attacks of at least one network attack; Count the number of network attacks in the network attack category as the attack part number; The number of attack parts is divided by the total number of attacks to get the proportion of network attack categories.

4. A cloud platform data security risk prediction method according to claim 3, characterized in that: The step of obtaining the degree of data leakage after a network attack on a cloud platform in a network attack category comprises the following steps: After the cloud platform is attacked by a network attack in the network attack category, the amount of leaked data output by the data storage node to the outside of the cloud platform is obtained; The data importance level of the data storage node is used as a weight and multiplied by the amount of leaked data to obtain the weighted amount of leakage; The weighted amounts of leakage of all data storage nodes are accumulated as the degree of data leakage after the network attack on the cloud platform in the network attack category.

5. A cloud platform data security risk prediction method according to claim 4, characterized in that: The step of obtaining the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category includes the following steps: After the cloud platform is attacked by the network attack in the network attack category, the data storage path is used for data interaction; If there is an abnormality in data interaction, the data storage path is regarded as the abnormal storage path. If not, no processing is performed; Counting the number of data storage paths that are abnormal storage paths to obtain the number of abnormalities; Counting the number of at least one data storage path to obtain a total number of paths; The value of dividing the number of anomalies by the total number of paths is used as the abnormality degree of the storage path after the network attack on the cloud platform in the network attack category.

6. A cloud platform data security risk prediction method according to claim 5, characterized in that: The method of obtaining the proportion of false data after the network attack on the cloud platform in the network attack category includes the following steps: After the cloud platform is attacked by a network attack in the network attack category, the post-attack data of the data storage node is obtained; Through the access verification set by the blockchain, the feature backup data corresponding to the data storage node in the blockchain is retrieved; Obtain data that is different from the post-attack data of the data storage node and the characteristic backup data as partial false data; Accumulate partial false data of all data storage nodes to obtain overall false data; Get the total data volume of all data storage nodes; The value of dividing the total amount of false data by the total amount of data is taken as the proportion of false data after the network attack on the cloud platform in the network attack category.

7. A cloud platform data security risk prediction method according to claim 6, characterized in that: The calculation of the average impact factor of the network attack category on the cloud platform attack includes the following steps: The average data leakage degree is obtained by adding up the data leakage degree of all network attacks on the cloud platform in the network attack category and averaging them. The average storage path abnormality degree is obtained by accumulating the abnormality degree of all network attacks on the cloud platform in the network attack category and averaging them. The average false data percentage is obtained by adding up the percentage of false data after all network attacks on the cloud platform in the network attack category and averaging them. The average impact factor is obtained by adding up the average data leakage degree, the average storage path abnormality degree, and the average false data ratio.

8. A cloud platform data security risk prediction method according to claim 7, characterized in that: The calculating of the overall impact factor of at least one network attack on the cloud platform attack comprises the following steps: Obtain at least one network attack category; Multiply the average impact factor in the network attack category by the proportion in the network attack category to obtain the average weighted impact factor of the network attack category; The average weighted impact factors of at least one network attack category are accumulated to obtain the overall impact factor of at least one network attack on the cloud platform attack.

9. A cloud platform data security risk prediction system, used to implement the cloud platform data security risk prediction method according to any one of claims 1 to 8, characterized in that: include: A data acquisition module, wherein the data acquisition module acquires at least one data storage node and at least one data storage path of the cloud platform; A data classification module, wherein the data classification module obtains the data importance level of the data storage node; A data backup module, which backs up the data on the cloud platform, and the backup data is stored in the blockchain; A security classification module, wherein the security classification module obtains at least one network attack suffered by the cloud platform, classifies the at least one network attack, and obtains at least one network attack category; An abnormality acquisition module, wherein the abnormality acquisition module acquires the degree of data leakage after the network attack on the cloud platform in the network attack category, acquires the degree of storage path abnormality after the network attack on the cloud platform in the network attack category, and acquires the proportion of false data after the network attack on the cloud platform in the network attack category; A factor calculation module, wherein the factor calculation module calculates an average impact factor of a network attack category on a cloud platform attack, and calculates an overall impact factor of at least one network attack on a cloud platform attack; A risk prediction module uses an overall impact factor as a cloud platform data security risk prediction level.

10. A storage medium having a computer-readable program stored thereon, characterized in that: When the computer-readable program is called, it executes the cloud platform data security risk prediction method as described in any one of claims 1 to 8.

Images