Data security protection system and method based on artificial intelligence

Abstract

The invention relates to the technical field of data security protection, in particular to a data security protection system and method based on artificial intelligence, and the method comprises the steps: obtaining historical transmission data, analyzing the historical transmission data, determining transmission duration, generating a jitter signal, determining a transmission path performance value based on the jitter signal, and determining a transmission path performance value based on the transmission path performance value. The method comprises the steps of determining a transmission path performance value, determining a transmission path sequence table, determining a transmission path weight based on the transmission path performance value and the transmission path sequence table, determining an SVM model for classification based on the transmission path weight according to historical transmission data, and classifying actual transmission data in an actual transmission data set based on the SVM model for classification. According to the method, the SVM model is constructed to classify the actual transmission data, the sensitive data and the non-sensitive data are distinguished, the transmission data groups are distributed according to the stability of the transmission paths and the sensitive degree of the data, and more sensitive data are distributed to the transmission paths with high stability.

Description

Technical Field

[0001] The present invention relates to the technical field of data security protection, and particularly to an artificial intelligence-based data security protection system and method thereof. Background Art

[0002] With the rapid development of information technology, data has become an important asset of enterprises and organizations. However, during the process of data transmission, storage, and processing, many security threats are faced.

[0003] Existing artificial intelligence-based data security protection systems have many deficiencies in data classification and transmission path allocation. In the data classification link, the classification accuracy is poor, lacking in-depth mining and comprehensive analysis of data features, making it difficult to accurately distinguish sensitive data and non-sensitive data. In the transmission path allocation link, the transmission stability is not fully considered, and the data sensitivity level is ignored, resulting in poor data transmission security.

[0004] Therefore, an artificial intelligence-based data security protection system and method thereof are proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide an artificial intelligence-based data security protection system and method thereof to solve at least one of the above-mentioned problems in the prior art.

[0006] In a first aspect, the present invention provides an artificial intelligence-based data security protection method, including:

[0007] Analyze historical transmission data, where the historical transmission data includes data transmission duration. If the transmission duration is not equal to the standard value of the transmission duration, a jitter signal is generated;

[0008] Based on the jitter signal, analyze the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path to determine the transmission path performance value. Based on the transmission path performance value, determine the transmission path sequence table. Based on the transmission path performance value and the transmission path sequence table, determine the transmission path weight;

[0009] Based on the transmission path weight, determine the SVM model for classification according to the historical transmission data. Based on the SVM model for classification, classify the actual transmission data in the actual transmission data group. The classification results include non-sensitive data and sensitive data;

[0010] Based on the classification results of the actual transmission data in the transmission data group, determine the sensitive sorting table. Based on the sensitive sorting table and the transmission path weight, determine the transmission data group allocation value of the transmission path. Based on the transmission data group allocation value of the transmission path, allocate the transmission data group to the transmission path with high stability according to the transmission data group allocation value.

[0011] Second aspect, the present invention provides an artificial intelligence-based data security protection system, including:

[0012] Data analysis module: Analyze historical transmission data, where the historical transmission data includes data transmission duration. If the transmission duration is not equal to the transmission duration standard value, a jitter signal is generated.

[0013] Transmission path stability evaluation module: Based on the jitter signal, analyze the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path to determine the transmission path performance value. Based on the transmission path performance value, determine the transmission path sequence table. Based on the transmission path performance value and the transmission path sequence table, determine the transmission path weight.

[0014] SVM model training and classification module: Based on the transmission path weight, determine the SVM model for classification according to the historical transmission data. Based on the SVM model for classification, classify the actual transmission data in the actual transmission data group. The classification results include non-sensitive data and sensitive data.

[0015] Sensitive data transmission path allocation module: Based on the classification results of the actual transmission data in the transmission data group, determine the sensitive sorting table. Based on the sensitive sorting table and the transmission path weight, determine the transmission data group allocation value of the transmission path. Based on the transmission data group allocation value of the transmission path, allocate the transmission data group to the transmission path with high stability according to the transmission data group allocation value.

[0016] Advantages of the present invention:

[0017] 1. Analyze historical transmission data, where the historical transmission data includes data transmission duration. If the transmission duration is not equal to the transmission duration standard value, a jitter signal is generated. Based on the jitter signal, analyze the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path to determine the transmission path performance value. Based on the transmission path performance value, determine the transmission path sequence table. Based on the transmission path performance value and the transmission path sequence table, determine the transmission path weight. Through the analysis of historical transmission data, the present invention can accurately identify the jitter signal during the transmission process, and then evaluate the stability of the transmission path. According to the transmission path performance value and the transmission path weight, data can be allocated more reasonably, and a higher transmission path weight can be assigned to the transmission path with higher stability, which is beneficial to improving the stability of network data transmission and providing reliable support for subsequent data allocation on the transmission path.

[0018] 2. Based on the transmission path weights, determine the SVM model for classification according to historical transmission data. Based on the SVM model for classification, classify the actual transmission data in the actual transmission data group. The classification results include non-sensitive data and sensitive data. Based on the classification results of the actual transmission data in the transmission data group, determine the sensitive sorting table. Based on the sensitive sorting table and the transmission path weights, determine the transmission data group allocation value of the transmission path. Based on the transmission data group allocation value of the transmission path, allocate the transmission data group to the transmission path with high stability according to the transmission data group allocation value. By constructing an SVM model to classify the actual transmission data, the present invention can accurately distinguish sensitive data and non-sensitive data, providing a prerequisite for subsequent data security processing and management. The transmission data group is allocated according to the stability of the transmission path and the sensitivity degree of the data, and more sensitive data is allocated to the transmission path with high stability, reducing the risk of leakage or tampering of sensitive data during transmission and enhancing the security of data during transmission. Combining the transmission path weights and the transmission data group allocation value to arrange the data transmission path avoids waste and unreasonable allocation of resources and improves the overall data transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 is a flowchart of a data security protection method based on artificial intelligence according to an embodiment of the present invention;

[0021] Figure 2 is a system block diagram of a data security protection system based on artificial intelligence according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of the device structure of a data security protection device based on artificial intelligence according to an embodiment of the present invention;

[0023] Reference numerals in the drawings: 3. Computer device; 301. Processor; 302. Memory; 303. Computer program. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] Embodiment 1

[0026] Figure 1 The following is a flowchart of a data security protection method based on artificial intelligence provided by Embodiment 1 of the present invention. A data security protection method based on artificial intelligence can be executed by a data security protection system based on artificial intelligence. A data security protection system based on artificial intelligence can be implemented by software and / or hardware. A data security protection system based on artificial intelligence can be configured in a data security protection device based on artificial intelligence. Optionally, a data security protection device based on artificial intelligence can be an electronic device, and the electronic device can be a notebook, a desktop computer, a smart tablet, etc. The embodiments of the present invention do not limit this.

[0027] As Figure 1 shown, a data security protection method based on artificial intelligence provided by the embodiments of the present invention specifically includes:

[0028] Step 1: Analyze historical transmission data. Among them, the historical transmission data includes the data transmission duration. If the transmission duration is not equal to the transmission duration standard value, a jitter signal is generated;

[0029] Obtain the historical transmission duration from the log file, and compare the transmission duration with the transmission duration standard value:

[0030] If the transmission duration is not equal to the transmission duration standard value, a jitter signal is generated;

[0031] If the transmission duration is equal to the transmission duration standard value, a normal signal is generated;

[0032] It should be noted that the transmission duration standard value is set by those skilled in the art according to past experience;

[0033] Step 2: Based on the jitter signal, analyze the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path to determine the transmission path performance value. Based on the transmission path performance value, determine the transmission path sequence table. Based on the transmission path performance value and the transmission path sequence table, determine the transmission path weight;

[0034] Subtract the transmission duration corresponding to the generation of the jitter signal from the standard value of the transmission duration, take the absolute value of the difference to obtain the transmission duration deviation value corresponding to the jitter signal, sum up and average all the transmission duration deviation values corresponding to the jitter signals to obtain the average transmission duration deviation, and perform a ratio process on the average transmission duration deviation and the standard value of the transmission duration to obtain the ratio of the duration deviation degree;

[0035] Count the number of times the jitter signal is generated in the transmission path within the historical monitoring period and mark it as the number of jitter times. Perform a ratio process on the number of jitter times and the total number of data stored corresponding to the transmission path in the historical period to obtain the ratio of the number of jitter times;

[0036] Multiply the ratio of the duration deviation degree and the ratio of the number of jitter times to obtain the performance value of the transmission path;

[0037] It should be noted that the performance value of the transmission path reflects the fluctuation of each historical transmission path. The larger the performance value of the transmission path, the more unstable the corresponding transmission path is, and the smaller the performance value of the transmission path, the more stable the corresponding transmission path is;

[0038] Sort the performance values of the transmission paths for the historical transmission paths from large to small to obtain the transmission path sequence list;

[0039] Based on the performance value of the transmission path and the transmission path sequence list, through the formula: Calculate to obtain the transmission path weight W i , where d max represents the performance value of the first sorted transmission path in the transmission path sequence list, d i represents the performance value of the i-th transmission path, and A is a boundary value set by those skilled in the art according to actual needs to limit the transmission path weight;

[0040] It should be noted that in network routing, without the constraint of the boundary value A, it may occur that the performance value of a certain transmission path is extremely small (i.e., d i is much smaller than the performance values of other transmission paths), resulting in the transmission path weight W i corresponding to this transmission path being too large. When allocating data to the transmission path for transmission later, too much allocated data will cause congestion on this transmission path. By setting an appropriate value of A, this situation can be effectively avoided, providing reliable support for subsequent data allocation on the transmission path;

[0041] The technical solution of this embodiment is as follows: Analyze historical transmission data, where the historical transmission data includes the data transmission duration. If the transmission duration is not equal to the transmission duration standard value, a jitter signal is generated. Based on the jitter signal, analyze the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path to determine the transmission path performance value. Based on the transmission path performance value, determine the transmission path sequence list. Based on the transmission path performance value and the transmission path sequence list, determine the transmission path weight. Through the analysis of historical transmission data, the present invention can accurately identify the jitter signal during the transmission process, and then evaluate the stability of the transmission path. According to the transmission path performance value and the transmission path weight, data can be more reasonably allocated, and a higher transmission path weight is assigned to the path with a more stable transmission path, which is beneficial to improving the stability of network data transmission and providing reliable support for subsequent data allocation on the transmission path.

[0042] Embodiment 2

[0043] As Figure 1 shown, a data security protection method based on artificial intelligence provided by an embodiment of the present invention specifically includes:

[0044] Step 3: Based on the transmission path weight, determine the SVM model for classification according to historical transmission data. Based on the SVM model for classification, classify the actual transmission data in the actual transmission data group, and the classification results include non-sensitive data and sensitive data;

[0045] According to historical transmission data, integrate all historical transmission data within the historical monitoring period into a historical transmission data set, use the historical transmission data set as the training data set, count the number of data samples in the training data set, and mark it as the total number of training data n;

[0046] Select an appropriate kernel function K(x i , x j ) and an appropriate penalty parameter C, and construct the objective function as:

[0047]

[0048] Among them, α i and α j are both Lagrange multipliers, x i represents the i-th data sample, x j represents the j-th data sample, γ i and γ j represent the class labels corresponding to the data samples;

[0049] It should be noted that the role of the kernel function is to map the data in the original space to a higher-dimensional feature space, making the data linearly separable in this high-dimensional space;

[0050] Obtain the optimal solution according to the objective function Construct a decision function to obtain an SVM model for classification;

[0051] Based on the SVM model for classification, obtain the actual transmission data, integrate all the actual transmission data into an actual transmission data group, and divide the actual transmission data group into multiple transmission data groups with the same number of actual transmission data;

[0052] Based on any one group of transmission data groups;

[0053] Input the features of the actual transmission data in the transmission data group into the trained SVM model, and the SVM model outputs the category label corresponding to the actual transmission data, that is, sensitive data or non-sensitive data;

[0054] Step 4: Based on the classification results of the actual transmission data in the transmission data group, determine a sensitivity ranking table. Based on the sensitivity ranking table and the transmission path weight, determine the transmission data group allocation value of the transmission path. Based on the transmission data group allocation value of the transmission path, allocate the transmission data group to the transmission path with high stability according to the transmission data group allocation value;

[0055] Count the number of sensitive data in the transmission data group and mark it as the number of sensitive data. Perform a ratio process on the number of sensitive data and the total number of actual transmission data in the transmission data group to obtain the sensitive data quantity ratio;

[0056] Obtain the data bytes of all the actual transmission data in the transmission data group, sum up the data bytes of all the actual transmission data to obtain the total data byte sum, extract the data bytes of all the sensitive data in the transmission data group, sum up the data bytes of all the sensitive data to obtain the sensitive data byte sum, and perform a ratio process on the sensitive data byte sum and the total data byte sum to obtain the sensitive data degree ratio;

[0057] Perform a product process on the sensitive data quantity ratio and the sensitive data degree ratio to obtain a sensitive performance value;

[0058] Sort the sensitive performance values corresponding to multiple groups of transmission data groups from large to small to obtain a sensitive performance value ranking table corresponding to the transmission data groups;

[0059] Count the number of transmission data groups in the actual transmission data group and mark it as the number of transmission data groups;

[0060] Sum up the transmission path weights corresponding to all the transmission paths to obtain the total transmission path weight. Perform a ratio process on the transmission path weight and the total transmission path weight to obtain the transmission path weight ratio;

[0061] Multiply the transmission path weight ratio by the number of transmission data groups to obtain the transmission data group allocation value of the transmission path. Based on the transmission data group allocation value of the transmission path, divide the sensitive performance value sorting table, and then allocate the transmission data groups to the transmission paths with high stability according to the transmission data group allocation value, thereby strengthening the protection of data security;

[0062] The technical solution of this embodiment is as follows: Based on the transmission path weight, determine the SVM model for classification according to the historical transmission data. Based on the SVM model for classification, classify the actual transmission data in the actual transmission data group. The classification results include non-sensitive data and sensitive data. Based on the classification results of the actual transmission data in the transmission data group, determine the sensitive sorting table. Based on the sensitive sorting table and the transmission path weight, determine the transmission data group allocation value of the transmission path. Based on the transmission data group allocation value of the transmission path, allocate the transmission data groups to the transmission paths with high stability according to the transmission data group allocation value. By constructing an SVM model to classify the actual transmission data, the present invention can accurately distinguish sensitive data and non-sensitive data, providing a prerequisite for subsequent data security processing and management. Allocate the transmission data groups according to the stability of the transmission path and the sensitivity of the data, allocate more sensitive data to the transmission paths with high stability, reduce the risk of leakage or tampering of sensitive data during transmission, and enhance the security of data during transmission. Combine the transmission path weight and the transmission data group allocation value to arrange the data transmission path, avoid waste and unreasonable allocation of resources, and improve the overall data transmission efficiency.

[0063] Embodiment III

[0064] As Figure 2 shown, a data security protection system based on artificial intelligence provided by an embodiment of the present invention specifically includes:

[0065] Data analysis module: Analyze the historical transmission data. Among them, the historical transmission data includes the data transmission duration. If the transmission duration is not equal to the transmission duration standard value, a jitter signal is generated;

[0066] Transmission path stability evaluation module: Based on the jitter signal, analyze the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path to determine the transmission path performance value. Based on the transmission path performance value, determine the transmission path sequence table. Based on the transmission path performance value and the transmission path sequence table, determine the transmission path weight;

[0067] SVM model training and classification module: Based on the transmission path weight, determine the SVM model for classification according to the historical transmission data. Based on the SVM model for classification, classify the actual transmission data in the actual transmission data group. The classification results include non-sensitive data and sensitive data;

[0068] Sensitive data transmission path allocation module: Based on the classification result of the actual transmitted data in the transmitted data group, determine the sensitive sorting table. Based on the sensitive sorting table and the transmission path weight value, determine the transmitted data group allocation value of the transmission path. Based on the transmitted data group allocation value of the transmission path, allocate the transmitted data group to the transmission path with high stability according to the transmitted data group allocation value.

[0069] Embodiment 4

[0070] Refer to Figure 3 Moreover, an embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements a data security protection method based on artificial intelligence as described in any one of the above methods.

[0071] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that Figure 3 merely an example of the computer device 3, which does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0072] The so-called processor 301 may be a central processing unit (CPU). The processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0073] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In some other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk equipped on the computer device 3, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a Boot Loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or will be output.

[0074] Embodiment 5

[0075] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements a data security protection method based on artificial intelligence as described in any one of the above methods.

[0076] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0077] In the above embodiments, the descriptions of the various embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] Those of ordinary skill in the art will realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0079] In the embodiments disclosed in this application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0080] Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by technicians in the art according to the actual situation.

[0083] The above has described a detailed description of an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A data security protection method based on artificial intelligence, characterized in that: include: Analyze historical transmission data, wherein the historical transmission data includes data transmission duration, and if the transmission duration is not equal to a standard value of the transmission duration, generate a jitter signal; Based on the jitter signal, the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path are analyzed to determine a transmission path sequence table, and the transmission path weight is determined in combination with the transmission path performance value; Determine an SVM model for classification according to the historical transmission data, and divide the actual transmission data in the actual transmission data group into non-sensitive data and sensitive data by using the SVM model; The sensitive sorting table is determined by the divided sensitive data, and the transmission data group allocation value of the transmission path is determined in combination with the transmission path weight. For transmission paths with high stability, the transmission data group is allocated according to the transmission data group allocation value.

2. According to the data security protection method based on artificial intelligence in claim 1, it is characterized in that: The transmission path sequence table is obtained in the following manner: Based on the jitter signal, the duration deviation ratio and the jitter frequency ratio are analyzed and the transmission path performance value is obtained by multiplying them. The transmission path performance values ​​are sorted from large to small for the historical transmission paths to obtain a transmission path sequence table.

3. According to claim 2, a data security protection method based on artificial intelligence is characterized in that: The duration deviation ratio and the jitter frequency ratio are obtained as follows: The transmission time corresponding to the jitter signal generation is subtracted from the standard value of the transmission time, and then the absolute value is taken, and the average is taken to obtain the mean value of the transmission time deviation, and the mean value of the transmission time deviation is processed by ratio processing with the standard value of the transmission time to obtain the time deviation degree ratio; The number of times the jitter signal is generated in the transmission path in the historical monitoring period is counted, and the ratio is processed with the total number of data storage corresponding to the transmission path in the historical period to obtain the jitter number ratio.

4. According to the data security protection method based on artificial intelligence in claim 1, it is characterized in that: The transmission path weight is obtained in the following way: Based on the transmission path performance value and the transmission path sequence table, the formula: W i = Calculate the transmission path weight W i , where d max Indicates the performance value of the transmission path ranked first in the transmission path sequence list, d i represents the transmission path performance value of the ith transmission path, and A is a boundary value set by those skilled in the art according to actual needs to limit the transmission path weight.

5. According to the data security protection method based on artificial intelligence in claim 1, it is characterized in that: The determination process of the SVM model for classification is: According to the historical transmission data, all the historical transmission data in the historical monitoring period are integrated into a historical transmission data set, and the historical transmission data set is used as a training data set; Select an appropriate kernel function K(x i , x j ) and appropriate penalty parameter C, the objective function is constructed as: Among them, α i and α j are all Lagrange multipliers, x i represents the i-th data sample, x j represents the jth data sample, γ i and γ j Represents the category label corresponding to the data sample, and n is the number of data samples in the training data set; Find the optimal solution based on the objective function Construct a decision function and obtain the SVM model for classification.

6. The data security protection method based on artificial intelligence according to claim 1 is characterized in that: The process of determining the classification result of the actual transmission data in the transmission data group is as follows: Based on the SVM model for classification, actual transmission data is obtained, all actual transmission data are integrated into an actual transmission data group, and the actual transmission data group is divided into a plurality of transmission data groups with the same number of actual transmission data; The features of the actual transmitted data in the transmission data group are input into the trained SVM model, and the SVM model outputs the category label corresponding to the actual transmitted data, that is, sensitive data or non-sensitive data.

7. The data security protection method based on artificial intelligence according to claim 6 is characterized in that: The sensitivity ranking table is obtained in the following manner: By analyzing the sensitive data, we can obtain the sensitive data quantity ratio and the sensitive data degree ratio, and perform product processing to obtain the sensitive performance value; The sensitive performance values ​​corresponding to the multiple transmission data groups are sorted from large to small to obtain a sensitive performance value sorting table corresponding to the transmission data groups.

8. The data security protection method based on artificial intelligence according to claim 7 is characterized in that: The sensitive data quantity ratio and the sensitive data degree ratio are obtained in the following manner: Counting the amount of sensitive data in the transmission data group and performing ratio processing with the total amount of actual transmission data in the transmission data group to obtain a sensitive data amount ratio; The data bytes of all actually transmitted data in the transmission data group are extracted and summed to obtain the total data bytes. The data bytes of all sensitive data in the transmission data group are extracted and summed to obtain the sum of sensitive data bytes. The sum of sensitive data bytes is ratioed with the sum of data bytes to obtain a sensitive data degree ratio.

9. The data security protection method based on artificial intelligence according to claim 6 is characterized in that: The process of obtaining the transmission data group allocation value of the transmission path is as follows: The transmission path weights corresponding to all transmission paths are summed to obtain a total transmission path weight, and the transmission path weights are ratioed with the total transmission path weights to obtain a transmission path weight ratio; The transmission path weight ratio is multiplied by the number of transmission data groups to obtain the transmission data group allocation value of the transmission path.

10. A data security protection system based on artificial intelligence, characterized in that: include: Data analysis module: analyzes historical transmission data, wherein the historical transmission data includes data transmission duration. If the transmission duration is not equal to the standard value of the transmission duration, a jitter signal is generated; Transmission path stability evaluation module: Based on the jitter signal, the transmission duration corresponding to the generation of the jitter signal and the number of times the jitter signal is generated in the transmission path are analyzed to determine the transmission path sequence table, and the transmission path weight is determined in combination with the transmission path performance value; SVM model training and classification module: Determine the SVM model used for classification based on historical transmission data, and divide the actual transmission data in the actual transmission data group into non-sensitive data and sensitive data through the SVM model; Sensitive data transmission path allocation module: Determine the sensitive sorting table through the divided sensitive data, and determine the transmission data group allocation value of the transmission path in combination with the transmission path weight, and allocate the transmission data group according to the transmission data group allocation value for the transmission path with high stability.

Images