Cloud data security protection system driven by artificial intelligence

Abstract

The invention discloses a cloud data security protection system driven by artificial intelligence. The system comprises a preprocessing module. According to the method, the cloud data are disordered through the random algorithm, the disordered data are encrypted through the asymmetric encryption mode, and the random operator is encrypted through the symmetric encryption mode, so that triple encryption of the cloud data is realized, and due to the fact that the readable data obtained after conversion of the cloud data are subjected to region division and the random algorithm is adopted, the encryption efficiency is greatly improved. The encryption of disordered data is enhanced, the security in the data processing and transmission process is ensured while the efficient operation of the system is ensured, the situation that the security is sacrificed due to pursuit of a single performance index is avoided, and the symmetric encryption mode and the asymmetric encryption mode do not need complex hardware support or a special software environment, so that the security is improved. And the generated key is compatible with the existing encryption standard and protocol, so that the method can be seamlessly integrated with other encryption systems, and the overall efficiency and effect of data protection are improved.

Description

Technical Field

[0001] The present invention relates to the field of cloud data encryption technology, and in particular to an artificial intelligence driven cloud data security protection system. Background Art

[0002] A cloud server is a computing service with elastically scalable processing power. Among them, private cloud servers are cloud servers that only allow certain users to access, and public cloud servers are cloud servers that are accessible to all users, but sometimes certain conditions must be met before they can be accessed. With the development of cloud services, users have higher and higher requirements for network security protection.

[0003] The commonly used method for protecting cloud data is to encrypt it. However, while pursuing encryption performance, existing technologies often require more computing resources and storage space, and the encryption form is relatively simple. The protection of cloud data is still too simple, vulnerable to security threats, and difficult to meet the needs of staff. Summary of the invention

[0004] In order to solve the above technical problems, an artificial intelligence-driven cloud data security protection system is provided, which solves the problem that the above-mentioned existing technologies, while pursuing encryption performance, often require more computing resources and storage space, and the encryption form is relatively single, and the protection of cloud data is still too simple and vulnerable to security threats.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] In a first aspect of the present invention, an artificial intelligence-driven cloud data security protection method is provided, comprising:

[0007] Acquire cloud data, scan the cloud data, and perform preprocessing, wherein the preprocessing is to interpolate abnormal data;

[0008] Obtain the database, convert the preprocessed cloud data, and obtain readable data;

[0009] Scan the readable data, scramble the readable data using a random algorithm, and obtain messy data;

[0010] Obtain the encrypted public key and encrypted private key based on the messy data;

[0011] Encrypt the messy data based on the encryption public key and the encryption private key;

[0012] Extract the random operator of the random algorithm and encrypt the random operator using the AES algorithm.

[0013] Preferably, scanning and processing the cloud data includes the following steps:

[0014] Scan cloud data, obtain abnormal data in the cloud data and mark it;

[0015] Obtaining the processing records of historical data, and extracting multiple analysis data with the same conditions as the abnormal data from the processing records of the historical data;

[0016] Get the mean of multiple analysis data and interpolate abnormal data;

[0017] The mean calculation formula is:

[0018]

[0019] In the formula, is the mean, and E is the analytical data.

[0020] Preferably, the obtaining of the processing records of the historical data and extracting a plurality of analysis data having the same condition as the abnormal data from the processing records of the historical data comprises the following steps:

[0021] Obtain historical records and scan historical records to obtain deviation data in historical records;

[0022] Extract multiple filling data with the same conditions as the deviation data in the historical records;

[0023] Constructing a rectangular coordinate system based on multiple filling data;

[0024] Use point-by-point comparison to obtain the data to be filled that is closest to the deviation data;

[0025] The data to be filled fills the deviation data.

[0026] Preferably, the step of acquiring a database, converting the preprocessed cloud data, and acquiring readable data specifically comprises the following steps:

[0027] Get the database;

[0028] Extract the comparison table from the database;

[0029] Compare the cloud data with the reference table to obtain readable data.

[0030] Preferably, scanning the readable data, scrambling the readable data using a random algorithm, and obtaining the scrambled data comprises the following steps:

[0031] Scanning readable data;

[0032] Divide the readable data evenly into multiple data intervals;

[0033] Assign values ​​to bits in the data interval according to the order of the data interval;

[0034] Generate a random operator with the same number of bits as the data interval using a random algorithm;

[0035] The bits in the data interval are sorted according to the size of the random algorithm to obtain messy data.

[0036] Preferably, obtaining the encryption public key and the encryption private key based on the messy data includes the following steps:

[0037] Extract multiple messy data;

[0038] Convert multiple messy data into decimal quantitative data respectively;

[0039] Construct two prime numbers randomly;

[0040] Obtain the modulus of the corresponding quantized data according to the two prime numbers;

[0041] According to the Euler function, combine two prime numbers to obtain the value of the Euler function;

[0042] According to the value of Euler function, obtain the public key exponent;

[0043] Obtain the private key exponent based on the public key exponent and the Euler function value;

[0044] Obtain the encrypted public key and the encrypted private key according to the public key exponent, the private key exponent and the modulus;

[0045] Among them, the calculation formula of the Euler function value is:

[0046] (q-1)(p-1)=T;

[0047] The calculation formula of modulus is:

[0048] N = pq;

[0049] Among them, the specific composition of the encrypted public key and the encrypted private key is:

[0050] Encrypted public key: (E, N);

[0051] Encrypted private key: (D, N);

[0052] Where q and p are two selected prime numbers, T is the value of the Euler function, E is the public key exponent, D is the private key exponent, and N is the modulus.

[0053] Preferably, encrypting the messy data according to the encryption public key and the encryption private key comprises the following steps:

[0054] Extract multiple quantitative data separately;

[0055] The quantized data is exponentiated according to the public key exponent to obtain the power exponent;

[0056] According to the power exponent, combined with the modulus, obtain the corresponding remainder;

[0057] The quantized data is replaced according to the remainder, thereby completing the encryption of the messy data.

[0058] Preferably, the step of extracting a random operator of a random algorithm and encrypting the random operator using an AES algorithm comprises the following steps:

[0059] Extract random operators from random algorithms;

[0060] Convert the random operator into 128-bit byte data;

[0061] Based on the byte data, the byte data is XORed in combination with CTR to encrypt the random operator.

[0062] In a second aspect of the present invention, there is also provided an artificial intelligence driven cloud data security protection system, comprising:

[0063] A preprocessing module, the preprocessing module is used to obtain cloud data, scan the cloud data, and perform preprocessing, wherein the preprocessing is to interpolate abnormal data;

[0064] Conversion module: The conversion module is used to obtain a database, convert the pre-processed cloud data, and obtain readable data;

[0065] A scrambling module, the scrambling module is used to scan the readable data and scramble the readable data using a random algorithm to obtain messy data;

[0066] An acquisition module, the acquisition module is used to acquire an encrypted public key and an encrypted private key according to the messy data;

[0067] A first encryption module, wherein the first encryption module is used to encrypt the messy data according to the encryption public key and the encryption private key;

[0068] The second encryption module is used to extract the random operator of the random algorithm and encrypt the random operator using the AES algorithm.

[0069] In a third aspect of the present invention, an electronic device is further provided. The electronic device comprises at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method of the first aspect of the present invention.

[0070] Compared with the prior art, the advantages of the present invention are: the present invention scrambles the cloud data through a random algorithm, encrypts the messy data through an asymmetric encryption method, and encrypts the random operator through a symmetric encryption method, thereby realizing triple encryption of the cloud data. Since the readable data after the cloud data conversion is divided into regions, and the encryption of the messy data is enhanced due to the use of a random algorithm, while ensuring the efficient operation of the system, the security of the data processing and transmission process is ensured, and the situation of sacrificing security for the pursuit of a single performance indicator is avoided. Moreover, both the symmetric encryption method and the asymmetric encryption method do not require complex hardware support or special software environment, and the generated key is compatible with existing encryption standards and protocols, so that the method can be seamlessly integrated with other encryption systems, improving the overall efficiency and effect of data protection, thereby ensuring the overall data processing capability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a schematic diagram of the cloud data security protection method driven by artificial intelligence in the present invention;

[0072] Figure 2 A schematic diagram of a method for scanning and processing cloud data in the present invention;

[0073] Figure 3 A schematic diagram of a method for obtaining a processing record of historical data and extracting a plurality of analysis data having the same condition as the abnormal data from the processing record of historical data in the present invention;

[0074] Figure 4 A schematic diagram of a method for acquiring a database in the present invention, converting pre-processed cloud data, and acquiring readable data;

[0075] Figure 5 A schematic diagram of a method for scanning readable data and scrambling the readable data using a random algorithm to obtain messy data in the present invention;

[0076] Figure 6 A schematic diagram of a method for obtaining an encrypted public key and an encrypted private key based on messy data in the present invention;

[0077] Figure 7 It is a schematic diagram of a method for encrypting messy data according to an encryption public key and an encryption private key in the present invention;

[0078] Figure 8 A schematic diagram of a method for extracting a random operator from a random algorithm and encrypting the random operator using an AES algorithm in the present invention;

[0079] Fig. 9 A block diagram of an exemplary electronic device capable of implementing embodiments of the present invention is shown;

[0080] Among them, 900 is an electronic device, 901 is a computing unit, 902 is a ROM, 903 is a RAM, 904 is a bus, 905 is an I / O interface, 906 is an input unit, 907 is an output unit, 908 is a storage unit, and 909 is a communication unit. DETAILED DESCRIPTION

[0081] 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.

[0082] Please refer to Figure 1 As shown, in a first aspect of the present invention, an artificial intelligence-driven cloud data security protection method is provided, comprising:

[0083] S101, acquiring cloud data, scanning the cloud data, and performing preprocessing, wherein the preprocessing is interpolating abnormal data;

[0084] S102, obtaining a database, converting the preprocessed cloud data, and obtaining readable data;

[0085] S103, scanning the readable data, and scrambling the readable data using a random algorithm to obtain messy data;

[0086] S104, obtaining an encrypted public key and an encrypted private key based on the messy data;

[0087] S105, encrypting the messy data according to the encryption public key and the encryption private key;

[0088] S106, extracting a random operator of the random algorithm, and encrypting the random operator using the AES algorithm;

[0089] It can be understood by those skilled in the art that the accuracy of cloud data is ensured by processing cloud data, cloud data is converted into readable data that can be recognized by computers, readable data is scanned and evenly divided, and data intervals are disrupted by random operators, which is the first encryption. By disrupting the data, the computing power required for brute force cracking of the data is increased. The messy data is encrypted by the encryption public key and the encryption private key, which is double encryption. The basic process of encrypting the transmitted information by the asymmetric encryption algorithm is: Party A first generates a pair of keys and uses one of them as a public key; Party B, who obtains the public key, uses the key to encrypt the information to be encrypted and then sends it to Party A; Party A then uses another corresponding private key to decrypt the encrypted information, thus realizing confidential data transmission. The encryption public key can be publicly distributed, and the encryption private key is saved by the user. There is no need to exchange keys before communication, which reduces the risk of being attacked during the transmission process and ensures the confidentiality of data transmission. By using symmetric encryption for the random operator, since the mathematical operation of symmetric encryption is relatively simple and the efficiency of processing large amounts of data is high, it is the preferred encryption method of the random operator. Through the triple encryption method, cloud data is securely protected.

[0090] Please refer to Figure 2 As shown, scanning and processing cloud data includes the following steps:

[0091] S201, scanning the cloud data, obtaining abnormal data in the cloud data and marking it;

[0092] S202, obtaining a processing record of historical data, and extracting a plurality of analysis data having the same condition as the abnormal data from the processing record of historical data;

[0093] S203, obtaining the mean of multiple analysis data, and interpolating abnormal data;

[0094] The mean calculation formula is:

[0095]

[0096] In the formula, is the mean, E is the analysis data;

[0097] It is understood by those skilled in the art that historical records contain past data and events, and this information is crucial for understanding and processing anomalies in current data. By acquiring historical records and processing them, useful information can be extracted. In the processed historical records, analytical data with the same conditions as the current abnormal data are extracted. These data have similar characteristics or patterns as the abnormal data. By calculating the mean of multiple analytical data, a relatively stable and reliable reference value can be obtained. The reference value can be used to interpolate the abnormal part of the current data, thereby correcting errors or omissions in the data. The interpolated data is more complete and accurate.

[0098] Please refer to Figure 3 As shown, obtaining the processing records of historical data and extracting multiple analysis data with the same conditions as the abnormal data in the processing records of historical data include the following steps:

[0099] S301, obtaining historical records and scanning the historical records to obtain deviation data in the historical records;

[0100] S302, extracting multiple filling data with the same conditions as the deviation data in the historical records;

[0101] S303, constructing a rectangular coordinate system according to a plurality of filling data;

[0102] S304, using point-by-point comparison to obtain data to be filled that is closer to the deviation data;

[0103] S305, filling the deviation data with the data to be filled;

[0104] Those skilled in the art will appreciate that a comprehensive scan of historical records is intended to identify deviations or anomalies in historical data. These deviation data may be caused by equipment failure, measurement errors, or special events. These fill-in data have similar features or conditions to the deviation data and can therefore be used as candidate data to fill in the deviation data. A rectangular coordinate system is constructed to more intuitively compare and analyze the similarity between the fill-in data and the deviation data. In this coordinate system, a scatter plot or line graph of the fill-in data and the deviation data can be drawn. In the rectangular coordinate system, the fill-in data and the deviation data are compared point by point to find the fill-in data points that are most similar to the deviation data. These similar fill-in data points can be used as data to be filled in to replace or correct the deviation data. By replacing or correcting the deviation data, the filled data can be more in line with the actual situation.

[0105] Please refer to Figure 4 As shown, obtaining a database, converting the preprocessed cloud data, and obtaining readable data specifically include the following steps:

[0106] S401, obtaining a database;

[0107] S402, extracting a comparison table from a database;

[0108] S403, comparing the cloud data with the comparison table to obtain readable data;

[0109] Those skilled in the art can understand that the specific Python code is as follows:

[0110] import sqlite3

[0111] import pandas as pd

[0112] #Get database connection

[0113] def get_database_connection(db_path):

[0114] conn=sqlite3.connect(db_path)

[0115] return conn

[0116] #Extract the comparison table from the database

[0117] def extract_mapping_table(conn, table_name):

[0118] query=f′SELECT*FROM{table_name}″

[0119] df_mapping=pd.read_sql_query(query,conn)

[0120] return df_mapping

[0121] #Compare cloud data with the reference table to obtain readable data

[0122] def transform_data(raw_data, mapping_table):

[0123] #Assume that raw_data is a DataFrame containing raw cloud data

[0124] #Assume mapping_table is a DataFrame containing a comparison table

[0125] #This is a simplified mapping conversion, the actual situation may be more complicated

[0126] #For example, suppose raw_data has a column 'code', which needs to be mapped to 'readable_name' in mapping_table

[0127] merged_data=pd.merge(raw_data, mapping_table, left_on='code', right_on='code_in_mapping')

[0128] #Select the required columns and generate readable data

[0129] readable_data=merged_data[[′original_column1′,′original_column2′,′readable_name′]]

[0130] # You can rename the columns to more clearly represent the readable data

[0131] readable_data.columns=['Column1', 'Column2', 'ReadableName']

[0132] return readable_date

[0133] #Example usage

[0134] if_name_==″_main_″:

[0135] db_path="path / to / your / database.db"

[0136] table_name="mapping_table"

[0137] #Get database connection

[0138] conn=get_database_connection(db_path)

[0139] #Extract comparison table

[0140] mapping_table=extract_mapping_table(conn, table_name)

[0141] #Assume that raw_data is the original cloud data obtained from somewhere else (such as a CSV file)

[0142] #Here we use a simple DataFrame to simulate

[0143] raw_data=pd.DataFrame({'code': [1, 2, 3], 'original_column1': ['data1', 'data2', 'data3'], 'original_column2': [100, 200, 300]})

[0144] #Convert the data into a readable format

[0145] readable_data=transform_data(raw_data, mapping_table)

[0146] print(readable_data)

[0147] The database usually contains a large amount of standard data, rules or mapping tables. By comparing the reference tables in the database with the cloud data, the cloud data can be converted into readable data that can be read by computers, making subsequent data analysis and processing more convenient and accurate.

[0148] Please refer to Figure 5 As shown, scanning the readable data, scrambling the readable data using a random algorithm, and obtaining the scrambled data includes the following steps:

[0149] S501, scanning readable data;

[0150] S502, evenly divide the readable data into multiple data intervals;

[0151] S503, assigning values ​​to bits in the data interval according to the data interval sorting;

[0152] S504, using a random algorithm to generate a random operator with the same number of bits as the number in the data interval;

[0153] S505, sorting the bits in the data interval according to the size of the random algorithm to obtain messy data;

[0154] It will be understood by those skilled in the art that, since the readable data is binary, the data is divided into multiple data intervals, and each interval is processed and analyzed independently, and values ​​are assigned by different 0 / 1 positions in the data interval. The data in the data interval is reordered according to these operators, which can significantly increase the randomness and unpredictability of the data. Through sorting and assignment, a false ordered structure can be established for the data in the data interval to meet different data encryption or obfuscation requirements. This method is applicable to various types of data and scenarios. Whether it is text data, numerical data or image data, similar methods can be used to perform operations such as division, sorting, assignment and encryption.

[0155] Please refer to Figure 6 As shown, according to the messy data, obtaining the encrypted public key and the encrypted private key includes the following steps:

[0156] S601, extracting multiple messy data;

[0157] S602, converting the plurality of disorderly data into decimal quantized data respectively;

[0158] S603, randomly construct two prime numbers;

[0159] S604, respectively obtaining moduli of corresponding quantized data according to two prime numbers;

[0160] S605, according to the Euler function, combining two prime numbers, obtaining the Euler function value;

[0161] S606. Obtain a public key exponent according to the Euler function value;

[0162] S607, obtaining a private key index according to the public key index and the Euler function value;

[0163] S608, obtaining an encrypted public key and an encrypted private key according to the public key exponent, the private key exponent and the modulus;

[0164] Among them, the calculation formula of the Euler function value is:

[0165] (q-1)(p-1)=T;

[0166] The calculation formula of modulus is:

[0167] N = pq;

[0168] Among them, the specific composition of the encrypted public key and the encrypted private key is:

[0169] Encrypted public key: (E, N);

[0170] Encrypted private key: (D, N);

[0171] Where q and p are two selected prime numbers, T is the value of the Euler function, E is the public key exponent, D is the private key exponent, and N is the modulus;

[0172] It can be understood by those skilled in the art that by converting messy data into decimal quantized data, the data can be used for subsequent mathematical operations in a standardized form. Prime numbers play an important role in encryption algorithms because their mathematical properties make them ideal for generating secure keys. The modulus of the corresponding quantized data is calculated using the two selected prime numbers. The modulus is a key parameter in the encryption algorithm, which determines the range of the encrypted data and affects the strength and security of the encryption. According to the definition of the Euler function, the Euler function value is calculated in combination with the two selected prime numbers. The Euler function value is used to determine the public key exponent and the private key exponent in the encryption algorithm. , according to the value of Euler function, select a suitable public key exponent, the public key exponent is a part of the encrypted public key, use the public key exponent and Euler function value to calculate the private key exponent, combine the public key exponent, private key exponent and modulus, generate the encrypted public key and encrypted private key, these two pairs of keys are the core of the encryption and decryption process, ensuring the confidentiality and integrity of the data, each step of the method is based on mathematical operations and algorithms, does not require complex hardware support or special software environment, and the generated encrypted public key and private key can be compatible with existing encryption standards and protocols, so that the method can be seamlessly integrated with other encryption systems to improve the overall efficiency and effectiveness of data protection.

[0173] Please refer to Figure 7 As shown, according to the encryption public key and the encryption private key, encrypting the messy data includes the following steps:

[0174] S701, extracting multiple quantitative data respectively;

[0175] S702, exponentiate the quantized data according to the public key exponent to obtain a power exponent;

[0176] S703, obtaining a corresponding remainder according to the power exponent and the modulus;

[0177] S704, replacing the quantized data according to the remainder, thereby completing encryption of the messy data;

[0178] Those skilled in the art will understand that exponentiation is an important step in the encryption algorithm, which generates an intermediate result by performing mathematical operations on data and the public key exponent, and this intermediate result will be used in the subsequent encryption process. In the encryption algorithm, the remainder operation is a common operation, which is used to limit the range of the encryption result, making the encryption result more difficult to predict and crack. The replacement operation is the last step of the encryption process, which converts the original plaintext data into ciphertext data, making it difficult for unauthorized personnel to easily read and understand the content of the data. Although the encryption and decryption processes involve complex mathematical operations, modern computers and algorithm optimization make these operations relatively efficient in practical applications, and public key encryption algorithms have a clear mathematical basis and implementation steps, making them easy to be programmed and integrated into various applications.

[0179] Please refer to Figure 8 As shown, extracting the random operator of the random algorithm and encrypting the random operator using the AES algorithm includes the following steps:

[0180] S801, extracting a random operator in a random algorithm;

[0181] S802, converting the random operator into 128-bit byte data;

[0182] S803, performing an XOR operation on the byte data in combination with CTR, thereby encrypting the random operator;

[0183] It can be understood by those skilled in the art that the random operator is identified and extracted from the random algorithm, which is the starting point of the encryption process. The extracted random operator is converted into 128-bit byte data of a fixed length. This step ensures the length consistency of the encrypted data and facilitates subsequent encryption operations and processing. The counter mode, namely CTR, is used to perform an XOR operation on the converted 128-bit byte data to achieve encryption. The CTR mode is a stream cipher mode. A pseudo-random byte stream is generated by combining the counter value with the key, and then an XOR operation is performed with the plaintext to obtain the ciphertext. The CTR mode provides a high degree of security in combination with the encryption method of the random operator. Due to the randomness and unpredictability of the random operator and the pseudo-random byte stream generation mechanism of the CTR mode, the encrypted data is difficult to crack. The XOR operation is a very fast encryption method. Combined with the stream cipher characteristics of the CTR mode, the encryption process can be carried out efficiently and is suitable for fast encryption of large amounts of data. The CTR mode and the XOR operation are relatively simple encryption methods, which are easy to implement in hardware and software, reducing the threshold of encryption technology.

[0184] In a second aspect of the present invention, there is also provided an artificial intelligence driven cloud data security protection system, comprising:

[0185] A preprocessing module, the preprocessing module is used to obtain cloud data, scan the cloud data, and perform preprocessing, wherein the preprocessing is to interpolate abnormal data;

[0186] Conversion module: The conversion module is used to obtain a database, convert the pre-processed cloud data, and obtain readable data;

[0187] A scrambling module, the scrambling module is used to scan the readable data and scramble the readable data using a random algorithm to obtain messy data;

[0188] An acquisition module, the acquisition module is used to acquire an encrypted public key and an encrypted private key according to the messy data;

[0189] A first encryption module, wherein the first encryption module is used to encrypt the messy data according to the encryption public key and the encryption private key;

[0190] The second encryption module is used to extract the random operator of the random algorithm and encrypt the random operator using the AES algorithm.

[0191] According to an embodiment of the present invention, the present invention further provides an electronic device.

[0192] Fig. 9 A schematic block diagram of an electronic device 900 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0193] The electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0194] Multiple components in the electronic device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the electronic device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0195] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as methods S101 to S106. For example, in some embodiments, methods S101 to S106 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the methods S101 to S106 described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to execute methods S101 to S106 in any other appropriate manner (eg, by means of firmware).

[0196] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0197] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0198] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0199] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0200] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0201] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0202] In summary, the advantages of the present invention are: cloud data is scrambled by a random algorithm, and the messy data is encrypted by an asymmetric encryption method, and the random operator is encrypted by a symmetric encryption method, thereby achieving triple encryption of cloud data. Since the readable data after the cloud data conversion is divided into regions, the encryption of the messy data is enhanced due to the use of a random algorithm. While ensuring the efficient operation of the system, the security of data processing and transmission is ensured, avoiding the situation where security is sacrificed for the pursuit of a single performance indicator. Moreover, both the symmetric encryption method and the asymmetric encryption method do not require complex hardware support or special software environment, and the generated key is compatible with existing encryption standards and protocols, so that the method can be seamlessly integrated with other encryption systems to improve the overall efficiency and effect of data protection, thereby ensuring the overall data processing capability of the system.

[0203] 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. An artificial intelligence-driven cloud data security protection system, characterized in that: include: A preprocessing module, the preprocessing module is used to obtain cloud data, scan the cloud data, and perform preprocessing, wherein the preprocessing is to interpolate abnormal data; Conversion module: The conversion module is used to obtain a database, convert the pre-processed cloud data, and obtain readable data; A scrambling module, the scrambling module is used to scan the readable data and scramble the readable data using a random algorithm to obtain messy data; An acquisition module, the acquisition module is used to acquire an encrypted public key and an encrypted private key according to the messy data; A first encryption module, wherein the first encryption module is used to encrypt the messy data according to the encryption public key and the encryption private key; The second encryption module is used to extract the random operator of the random algorithm and encrypt the random operator using the AES algorithm.

2. An artificial intelligence-driven cloud data security protection method, characterized in that: include: Acquire cloud data, scan the cloud data, and perform preprocessing, wherein the preprocessing is to interpolate abnormal data; Obtain the database, convert the preprocessed cloud data, and obtain readable data; Scan the readable data, scramble the readable data using a random algorithm, and obtain messy data; Obtain the encrypted public key and encrypted private key based on the messy data; Encrypt the messy data based on the encryption public key and the encryption private key; Extract the random operator of the random algorithm and encrypt the random operator using the AES algorithm.

3. The artificial intelligence-driven cloud data security protection method according to claim 2, characterized in that: Scan cloud data, obtain abnormal data in the cloud data and mark it; Obtaining the processing records of historical data, and extracting multiple analysis data with the same conditions as the abnormal data from the processing records of the historical data; Get the mean of multiple analysis data and interpolate abnormal data; The mean calculation formula is: In the formula, is the mean, and E is the analytical data.

4. The artificial intelligence-driven cloud data security protection method according to claim 3 is characterized in that: The obtaining of the processing records of the historical data and the extraction of a plurality of analysis data having the same condition as the abnormal data in the processing records of the historical data comprises the following steps: Obtain historical records and scan historical records to obtain deviation data in historical records; Extract multiple filling data with the same conditions as the deviation data in the historical records; Constructing a rectangular coordinate system based on multiple filling data; Use point-by-point comparison to obtain the data to be filled that is closest to the deviation data; The data to be filled fills the deviation data.

5. The artificial intelligence-driven cloud data security protection method according to claim 4 is characterized in that: The step of acquiring a database, converting the preprocessed cloud data, and acquiring readable data specifically includes the following steps: Get the database; Extract the comparison table from the database; Compare the cloud data with the reference table to obtain readable data.

6. The artificial intelligence-driven cloud data security protection method according to claim 5, characterized in that: The scanning of the readable data and the use of a random algorithm to shuffle the readable data to obtain the shuffled data include the following steps: Scanning readable data; Divide the readable data evenly into multiple data intervals; Assign values ​​to bits in the data interval according to the order of the data interval; Generate a random operator with the same number of bits as the data interval using a random algorithm; The bits in the data interval are sorted according to the size of the random algorithm to obtain messy data.

7. The artificial intelligence-driven cloud data security protection method according to claim 6, characterized in that: The method of obtaining the encrypted public key and the encrypted private key based on the messy data includes the following steps: Extract multiple messy data; Convert multiple messy data into decimal quantitative data respectively; Construct two prime numbers randomly; Obtain the modulus of the corresponding quantized data according to the two prime numbers; According to the Euler function, combine two prime numbers to obtain the value of the Euler function; According to the value of Euler function, obtain the public key exponent; Obtain the private key exponent based on the public key exponent and the Euler function value; Obtain the encrypted public key and the encrypted private key according to the public key exponent, the private key exponent and the modulus; Among them, the calculation formula of the Euler function value is: (q-1)(p-1)=T; The calculation formula of modulus is: N = pq; Among them, the specific composition of the encrypted public key and the encrypted private key is: Encrypted public key: (E, N); Encrypted private key: (D, N); Where q and p are two selected prime numbers, T is the value of the Euler function, E is the public key exponent, D is the private key exponent, and N is the modulus.

8. The artificial intelligence-driven cloud data security protection method according to claim 7, characterized in that: The method of encrypting the messy data according to the encryption public key and the encryption private key comprises the following steps: Extract multiple quantitative data separately; The quantized data is exponentiated according to the public key exponent to obtain the power exponent; According to the power exponent, combined with the modulus, obtain the corresponding remainder; The quantized data is replaced according to the remainder, thereby completing the encryption of the messy data.

9. The artificial intelligence-driven cloud data security protection method according to claim 8, characterized in that: The step of extracting a random operator of a random algorithm and encrypting the random operator using an AES algorithm comprises the following steps: Extract random operators from random algorithms; Convert the random operator into 128-bit byte data; Based on the byte data, the byte data is XORed in combination with CTR to encrypt the random operator.

10. An electronic device comprising at least one processor; and a memory connected in communication with the at least one processor; characterized in that: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 2 to 9.

Images