Artificial intelligence-based data access control method and system

Abstract

The application relates to the technical field of machine learning, in particular to an artificial intelligence-based data access control method and system. The method comprises the following steps: S1, a preprocessing module acquires a plurality of historical access requests in advance, and for each historical access request, the preprocessing module generates historical representative data corresponding to the historical access request, and further generates new historical representative data based on the generated historical representative data; S2, an exercise module exercises generation of a plurality of control models based on all the historical representative data, and the control module sequentially stores the plurality of control models generated by the exercise module according to the generation order; S3, the control module receives a real-time access request from a user module, generates real-time representative data corresponding to the real-time access request, and controls and processes the real-time representative data by using the plurality of control models stored in sequence. The application can improve the intelligence of the access control method.

Description

Technical Field

[0001] This application relates to the field of machine learning technology, and in particular to data access control methods and systems based on artificial intelligence. Background Technology

[0002] With the acceleration of digital transformation, data has become a core asset for enterprises. However, traditional access control methods are difficult to adapt to complex access scenarios, and a new access control method is needed to better protect data security.

[0003] Chinese patent application CN105229662A discloses an access control device, method, and program. Based on the hierarchical order, it extracts hierarchical elements from information in an organizational information management department that are paired with the identified hierarchical elements, and then extracts hierarchical elements from the next higher level of the paired hierarchical elements. It then compares the identified hierarchical elements and the extracted hierarchical elements with hierarchical elements defined by a task allocation management department to determine whether access is permitted. Furthermore, Chinese patent application CN113505090A discloses an access control method and device. This method includes: in response to receiving a request from a first application to access a Universal Integrated Circuit Card (UICC), reading an access control condition file and an access control extension file from the UICC; wherein the access control extension file at least indicates whether an application authorized to access the UICC is allowed to provide access control conditions; determining a first access control condition based on the access control condition file and the access control extension file; and processing the first application's request to access the UICC based on the first access control condition. However, both access control methods in these patent applications lack intelligence. Summary of the Invention

[0004] This application includes a preprocessing module to generate historical representative data corresponding to historical access requests, and a new historical representative data to be generated based on the historical representative data. It also includes a training module to sequentially train and generate several control models based on all the historical representative data, and a control module to generate real-time representative data corresponding to real-time access requests. Finally, it uses the several control models to perform control processing on the real-time representative data. This application aims to improve the intelligence of access control methods.

[0005] This application provides a data access control method based on artificial intelligence, including the following steps:

[0006] S1. The preprocessing module obtains several historical access requests in advance, and for each historical access request, the preprocessing module generates historical representative data corresponding to the historical access request, and also continues to generate new historical representative data based on the generated historical representative data.

[0007] S2. The practice module generates several control models sequentially based on all historical representative data, and the control module stores the several control models generated by the practice module in the order of practice generation.

[0008] S3. The control module receives a real-time access request from the user module, generates real-time representative data corresponding to the real-time access request, and uses several control models stored in sequence to perform control processing on the real-time representative data.

[0009] As a preferred technical solution of this application, the training module sequentially trains and generates several control models based on all historical representative data, including the following steps:

[0010] S21. The practice module sets corresponding identifier data for each historical representative data, and uses each historical representative data and the corresponding identifier data to form each practice data group.

[0011] S22. The practice module uses all the practice data sets to practice and generate a control model. For each practice data set, the practice module uses the historical representative data in the practice data set as the input data of the control model generated in the practice to obtain the output data.

[0012] S23. The practice module counts the total number of output data that are the same as the identifier data in the corresponding practice data group, calculates the ratio of the total number to the total number of output data, and determines whether the ratio is greater than the preset ratio threshold. If yes, all steps end; otherwise, change processing is performed on all practice data groups, and the process jumps to S22.

[0013] As a preferred technical solution of this application, the practice module performs change processing on all practice data sets, including the following steps:

[0014] S231. The practice module determines a practice data group from all the practice data groups, and determines whether the output data corresponding to the determined practice data group is the same as the identifier data in the determined practice data group. If they are different, the output data corresponding to the determined practice data group is added to the historical representative data in the determined practice data group. If they are the same, the next step is continued.

[0015] S232. The practice module generates real-time data and determines whether the real-time data is greater than the preset reference data. If it is greater, the output data corresponding to the determined practice data group is added to the historical representative data in the determined practice data group. If it is not greater, the next step is continued.

[0016] S233. The practice module scrambles the output data corresponding to the determined practice data group to obtain scrambled output data, adds the scrambled output data to the historical representative data in the determined practice data group, and determines whether there is a practice data group that has not been determined. If yes, it jumps to S231; otherwise, it continues to the next step.

[0017] S234. The exercise module determines whether the termination condition is met. If not, it modifies the comparison data and jumps to S231. If the condition is met, it ends all steps.

[0018] As a preferred technical solution of this application, the practice module determines whether the termination condition is met by: the practice module counting the first number of practice data groups that have been changed due to the execution of S231, and the second number of practice data groups that have been changed due to the execution of S232, and determining whether the difference between the first number and the second number is less than a preset difference threshold. If yes, the termination condition is met; if no, the termination condition is not met.

[0019] As a preferred technical solution of this application, the practice module modifies the control data by: increasing the control data when the second quantity is greater than the first quantity, and decreasing the control data when the second quantity is less than the first quantity.

[0020] As a preferred technical solution of this application, the control module uses several sequentially stored control models to perform control processing on real-time representative data, including the following steps:

[0021] S31, The control module determines the first control model stored sequentially;

[0022] S32. The control module uses real-time representative data as input data for a defined control model to obtain output data, and adds the output data to the real-time representative data.

[0023] S33. The control module determines whether there is an undetermined control model. If it exists, it determines the next control model according to the storage order and jumps to S32. If it does not exist, it determines the final output data based on the output data of all control models and determines whether the real-time access request is allowed based on the final output data.

[0024] As a preferred technical solution of this application, the preprocessing module further generates new historical representative data based on the generated historical representative data, including the following steps:

[0025] S11. The preprocessing module performs PCA transformation on the generated historical representative data to obtain several feature values. For each feature value, the preprocessing module sets the weight value corresponding to the feature value and calculates the product of the feature value and the weight value corresponding to the feature value.

[0026] S12. The preprocessing module calculates the sum of all products to obtain the basic value, and the preprocessing module generates several random values ​​based on a Gaussian distribution. The preprocessing module also sets a ratio value.

[0027] S13. For each random value, the preprocessing module calculates the sum of the products of the base value and the random value and the proportion value to obtain intermediate data, and the preprocessing module performs PCA inverse transformation on the intermediate data to obtain new historical representative data.

[0028] This application also provides an artificial intelligence-based data access control system, including the following modules:

[0029] The preprocessing module is used to obtain several historical access requests in advance, and for each historical access request, generate historical representative data corresponding to the historical access request, and continue to generate new historical representative data based on the generated historical representative data;

[0030] The practice module is used to sequentially practice and generate several control models based on all historical representative data.

[0031] The user module is used to collect users' real-time access requests and send them to the control module.

[0032] The control module is used to sequentially store several control models generated by the exercise module in the order they were generated during the exercise. It is also used to receive real-time access requests from the user module, generate real-time representative data corresponding to the real-time access requests, and use the sequentially stored control models to perform control processing on the real-time representative data.

[0033] Compared with the prior art, the beneficial effects of this application are at least as follows:

[0034] In the technical solution provided in this application, firstly, the preprocessing module obtains several historical access requests in advance. For each historical access request, the preprocessing module generates historical representative data corresponding to the historical access request, and also continues to generate new historical representative data based on the generated historical representative data. Secondly, the practice module sequentially practices and generates several control models based on all the historical representative data, and the control module stores the control models generated by the practice module in the order they were generated during practice. Finally, the control module receives real-time access requests from the user module, generates real-time representative data corresponding to the real-time access requests, and uses the sequentially stored control models to perform control processing on the real-time representative data. This application improves the intelligence of the access control method, enabling it to adapt to complex access scenarios. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart of the data access control method based on artificial intelligence in the embodiments of this application;

[0037] Figure 2 This is a flowchart illustrating the generation of several control models in the embodiments of this application;

[0038] Figure 3 This is a flowchart illustrating the control processing of real-time representative data in an embodiment of this application;

[0039] Figure 4 This is a schematic diagram of an artificial intelligence-based data access control system in an embodiment of this application. Detailed Implementation

[0040] This application provides a data access control method and system based on artificial intelligence. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data used can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0041] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 The data access control method based on artificial intelligence in this application includes the following main steps:

[0042] S1. The preprocessing module obtains several historical access requests in advance, and for each historical access request, the preprocessing module generates historical representative data corresponding to the historical access request, and also continues to generate new historical representative data based on the generated historical representative data.

[0043] S2. The practice module generates several control models based on all historical representative data in sequence, and the control module stores the control models generated by the practice module in the order of their generation.

[0044] S3. The control module receives real-time access requests from the user module, generates real-time representative data corresponding to the real-time access requests, and uses several control models stored in sequence to perform control processing on the real-time representative data.

[0045] Specifically, to provide an intelligent access control method adaptable to complex access scenarios, in S1, the preprocessing module collects several historical access requests beforehand. These historical access requests may include information such as user permissions, the sensitivity of the accessed data, and access frequency. The various information included in the historical access requests varies depending on the access scenario. For each historical access request, the preprocessing module generates historical representative data corresponding to the historical access request. This historical representative data can be in vector form, with each value in the vector corresponding to a type of information in the historical access request. For each historical access request, the preprocessing module also continues to generate new historical representative data based on the generated historical representative data. This is done to ensure that the number of generated historical representative data is sufficient, enabling the training module to generate an accurate control model. In S2, the training module sequentially trains and generates several control models based on all the historical representative data and sends these generated control models to the control module. The control module stores the generated control models sequentially according to the order of training. In S3, the control module receives real-time access requests from the user module, generates real-time representative data corresponding to the real-time access requests, and the types of information included in the real-time access requests are the same as those included in the historical access requests. The method for generating real-time representative data is the same as the method for generating historical representative data. The control module uses several control models stored in sequence to perform control processing on the real-time representative data and finally decides whether to allow the real-time access request.

[0046] Furthermore, the practice module sequentially generates several control models based on all historical representative data, including the following steps:

[0047] S21. The practice module sets corresponding identifier data for each historical representative data, and uses each historical representative data and its corresponding identifier data to form each practice data group.

[0048] S22. The practice module uses all the practice data sets to practice and generate a control model. For each practice data set, the practice module uses the historical representative data in the practice data set as the input data of the control model generated in the practice to obtain the output data.

[0049] S23. The practice module counts the total number of output data that are the same as the identifier data in the corresponding practice data group, calculates the ratio of the total number to the total number of output data, and determines whether the ratio is greater than the preset ratio threshold. If yes, all steps end; otherwise, change processing is performed on all practice data groups, and the process jumps to S22.

[0050] Specifically, see, for example Figure 2As shown, the training module sequentially trains and generates several control models based on all historical representative data. In S21, the training module sets corresponding identifier data for each historical representative data set, and uses each historical representative data set and its corresponding identifier data to form a training data set. Each training data set consists of historical representative data and its corresponding identifier data. The identifier data represents the risk level of the historical access request corresponding to the historical representative data; the risk level is a positive integer, with a larger integer indicating a higher risk level. In S22, the training module uses all training data sets to train and generate a control model. The control model can be a support vector machine model as in existing technologies. After generating the control model, for each training data set, the training module uses the historical representative data in the training data set as input data for the generated control model and obtains the output data. In S23, the practice module counts the total number of output data that are identical to the identifier data in the corresponding practice data group. The practice data group corresponding to the output data refers to the practice data group that the control model generated by the input practice obtains the output data. The practice module calculates the ratio of the total number to the total number of output data and determines whether the ratio is greater than a preset ratio threshold. The ratio threshold is set according to the actual application scenario. If it is greater, no new control model is generated and all steps end. If it is not greater, all practice data groups are modified and the process jumps to S22 to continue execution and generate a new control model.

[0051] Furthermore, the practice module performs variation processing on all practice data sets, including the following steps:

[0052] S231. The practice module determines a practice data group from all the practice data groups, and determines whether the output data corresponding to the determined practice data group is the same as the identifier data in the determined practice data group. If they are different, the output data corresponding to the determined practice data group is added to the historical representative data in the determined practice data group. If they are the same, the next step is continued.

[0053] S232. The practice module generates real-time data and determines whether the real-time data is greater than the preset reference data. If it is greater, the output data corresponding to the determined practice data group is added to the historical representative data in the determined practice data group. If it is not greater, continue to the next step.

[0054] S233. The practice module scrambles the output data corresponding to the determined practice data group to obtain scrambled output data. The scrambled output data is added to the historical representative data in the determined practice data group. It is determined whether there is a practice data group that has not been determined. If yes, it jumps to S231. If no, it continues to the next step.

[0055] S234. The practice module determines whether the termination condition is met. If not, the comparison data is modified and the process jumps to S231. If the condition is met, all steps end.

[0056] Specifically, the process of the practice module performing change processing on all practice data sets is described. In S231, the practice module determines a practice data set from all practice data sets and checks whether the output data corresponding to the determined practice data set is the same as the identifier data in the determined practice data set. If they are not the same, the output data corresponding to the determined practice data set is added to the historical representative data in the determined practice data set. If they are the same, proceed to S232. In S232, the practice module generates real-time data, which is any value between zero and one. It checks whether the real-time data is greater than the preset control data, the initial value of which is also between zero and one. If it is greater, the output data corresponding to the determined practice data set is added to the historical representative data in the determined practice data set. If the historical representative data is in vector form, this means increasing the vector by one value. If it is not greater, proceed to S233. In S233, the practice module scrambles the output data corresponding to the determined practice data set to obtain scrambled output data. The scrambling process includes: generating an arbitrary value between negative and positive one; adding the generated arbitrary value to the output data corresponding to the determined practice data set to obtain the scrambled output data; adding the scrambled output data to the historical representative data in the determined practice data set; then determining whether there is an undetermined practice data set. If so, it jumps to S231 to determine an undetermined practice data set and execute subsequent steps; otherwise, it continues to S234. In S234, the practice module determines whether the termination condition is met. If not, it modifies the reference data and jumps to S231 to continue execution. It is important to note that during continued execution, all practice data sets are restored to their unmodified state. If this condition is met, all steps end.

[0057] By using the method described above, the training module uses training data sets with more features each time a new control model is generated, which can provide additional information for the new control model and help improve the accuracy of the new control model.

[0058] Furthermore, the practice module determines whether the termination condition is met by: the practice module counting the first number of practice data groups that have been modified due to the execution of S231, and the second number of practice data groups that have been modified due to the execution of S232, and determining whether the difference between the first number and the second number is less than a preset difference threshold. If yes, the termination condition is met; otherwise, the termination condition is not met.

[0059] Specifically, the process of determining whether the termination condition is met in the practice module is described. The practice module counts the first number of practice data sets that have been modified due to the execution of S231, and counts the second number of practice data sets that have been modified due to the execution of S232. It determines whether the difference between the first number and the second number is less than a preset difference threshold. The difference is the absolute value of the difference between the first number and the second number. If it is less than the threshold, the accuracy of the new control model generated by practicing with all the modified practice data sets will be better, and the termination condition is met. If it is not less than the threshold, the termination condition is not met.

[0060] Furthermore, the practice module modifies the control data by increasing the control data when the second quantity is greater than the first quantity, and decreasing the control data when the second quantity is less than the first quantity.

[0061] Specifically, the exercise module explains how to modify the control data. If the second statistical quantity is greater than the first statistical quantity, a method should be adopted that reduces the second statistical quantity in the next statistical analysis, i.e., the control data should be increased adaptively. If the second quantity is less than the first quantity, a method should be adopted that increases the second statistical quantity in the next statistical analysis, i.e., the control data should be decreased adaptively.

[0062] The practice module executes S234 above to find suitable control data. Alternatively, after each adaptive modification to the control data, it can execute S231 to S233 above and use all the practice data sets that have undergone the changes to practice the generated new control model. Then, the control data corresponding to the control model with the highest accuracy is used as the suitable control data.

[0063] Furthermore, the control module uses several sequentially stored control models to perform control processing on real-time representative data, including the following steps:

[0064] S31, The control module determines the first control model for sequential storage;

[0065] S32. The control module uses the real-time representative data as the input data of the defined control model to obtain the output data, and adds the output data to the real-time representative data.

[0066] S33. The control module determines whether there is an undetermined control model. If it exists, it determines the next control model according to the storage order and jumps to S32. If it does not exist, it determines the final output data based on the output data of all control models and determines whether the real-time access request is allowed based on the final output data.

[0067] Specifically, see, for example Figure 3 As shown, this describes the process by which the control module uses several sequentially stored control models to control and process real-time representative data. In S31, the control module determines the first control model in the sequential storage. In S32, the control module uses the real-time representative data as input data for the determined control model to obtain output data, which is then added to the real-time representative data. In S33, the control module determines whether there is an undetermined control model. If so, it determines the next control model according to the storage order and jumps to S32 to continue execution. If not, it determines the final output data based on the output data of all control models. The output data that appears most frequently among the output data of all control models can be used as the final output data. Then, based on the final output data, it determines whether the real-time access request is allowed. If the risk level represented by the final output data is high, the real-time access request can be rejected.

[0068] Furthermore, the preprocessing module continues to generate new historical representative data based on the generated historical representative data, including the following steps:

[0069] S11. The preprocessing module performs PCA transformation on the generated historical representative data to obtain several feature values. For each feature value, the preprocessing module sets the weight value corresponding to the feature value and calculates the product of the feature value and the weight value corresponding to the feature value.

[0070] S12. The preprocessing module calculates the sum of all products to obtain the basic value, and the preprocessing module generates several random values ​​based on a Gaussian distribution. The preprocessing module also sets a ratio value.

[0071] S13. For each random value, the preprocessing module calculates the sum of the products of the base value and the random value and the proportion value to obtain intermediate data, and performs PCA inverse transformation on the intermediate data to obtain new historical representative data.

[0072] Specifically, the preprocessing module further generates new historical representative data based on the generated historical representative data. In S11, the preprocessing module performs PCA transformation on the generated historical representative data to obtain several feature values. These feature values ​​represent the main characteristic directions of the historical representative data. For each feature value, the preprocessing module sets a weight value corresponding to the feature value and calculates the product of the feature value and its corresponding weight value. The same weight value can be set for each feature value, or different weight values ​​can be set for each feature value. In S12, the preprocessing module calculates the sum of all products to obtain the basic value. The preprocessing module generates several random values ​​based on a Gaussian distribution, with the number of random values ​​being the same as the number of feature values. Specifically, each random value is randomly generated from a Gaussian distribution with a mean of 0 and a standard deviation of 0.1. The preprocessing module also sets a ratio value, which can be 0.5. In S13, for each random value, the preprocessing module calculates the sum of the products of the base value and the random value multiplied by the proportional value to obtain intermediate data. This intermediate data is also in vector form. The preprocessing module further performs inverse PCA transformation on the intermediate data to ultimately obtain new historical representative data. Using these methods, new historical representative data that is quite similar to the historical representative data can be generated.

[0073] According to another aspect of the embodiments of this application, reference is made to... Figure 4 As shown, this application also provides an artificial intelligence-based data access control system, including a preprocessing module, a practice module, a user module, and a control module, to implement the artificial intelligence-based data access control method described above.

[0074] The functions of each module are as follows:

[0075] The preprocessing module is used to obtain several historical access requests in advance, and for each historical access request, generate historical representative data corresponding to the historical access request, and continue to generate new historical representative data based on the generated historical representative data;

[0076] The practice module is used to sequentially practice and generate several control models based on all historical representative data.

[0077] The user module is used to collect users' real-time access requests and send them to the control module.

[0078] The control module is used to sequentially store several control models generated by the exercise module in the order they were generated during the exercise. It is also used to receive real-time access requests from the user module, generate real-time representative data corresponding to the real-time access requests, and use the sequentially stored control models to perform control processing on the real-time representative data.

[0079] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0080] If the integrated unit is implemented as 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, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0081] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A data access control method based on artificial intelligence, characterized in that, include: S1. The preprocessing module obtains several historical access requests in advance. For each historical access request, the preprocessing module generates historical representative data corresponding to the historical access request, and also continues to generate new historical representative data based on the generated historical representative data. S2. The practice module generates several control models in sequence based on all the historical representative data, and the control module stores the control models generated by the practice module in the order they were generated in the practice. S3. The control module receives real-time access requests from the user module, generates real-time representative data corresponding to the real-time access requests, and uses the sequentially stored control models to perform control processing on the real-time representative data. The training module generates several control models sequentially based on all historical representative data, including: S21, the training module sets corresponding identifier data for each historical representative data, and uses each historical representative data and its corresponding identifier data to form a training data group; S22, the training module uses all training data groups to generate a control model, and for each training data group, the training module uses the historical representative data in the training data group as the input data for the generated control model to obtain output data; S23, the training module counts the total number of output data that are the same as the identifier data in the corresponding training data group, calculates the ratio of the total number to the total number of output data, and determines whether the ratio is greater than a preset ratio threshold. If yes, all steps end; otherwise, changes are processed for all training data groups, and the process jumps to S22. The process involves modifying all practice data sets, including: S231, where the practice module selects a practice data set from all practice data sets and determines whether the output data corresponding to the selected practice data set is the same as the identifier data in the selected practice data set. If they are different, the output data corresponding to the selected practice data set is added to the historical representative data in the selected practice data set. If they are the same, the next step is performed; S232, the practice module generates real-time data and determines whether the real-time data is greater than the preset reference data. If it is greater, the output data corresponding to the selected practice data set is added to the historical representative data in the selected practice data set. S233: The practice module scrambles the output data corresponding to the determined practice data group to obtain scrambled output data. The scrambled output data is added to the historical representative data in the determined practice data group. It is determined whether there is a practice data group that has not been determined. If yes, it jumps to S231. If no, it continues to the next step. S234: The practice module determines whether the termination condition is met. If not, it modifies the reference data and jumps to S231. If the condition is met, all steps end.

2. The method according to claim 1, characterized in that, The exercise module determines whether the termination condition is met by: counting the first number of exercise data groups that have been modified due to the execution of S231, and the second number of exercise data groups that have been modified due to the execution of S232; determining whether the difference between the first number and the second number is less than a preset difference threshold; if yes, the termination condition is met; otherwise, the termination condition is not met.

3. The method according to claim 2, characterized in that, The practice module modifies the control data as follows: when the second quantity is greater than the first quantity, the practice module increases the control data; when the second quantity is less than the first quantity, the practice module decreases the control data.

4. The method according to claim 3, characterized in that, The control module uses several sequentially stored control models to perform control processing on real-time representative data, including the following steps: S31, The control module determines the first control model for sequential storage; S32. The control module uses the real-time representative data as the input data of the defined control model to obtain the output data, and adds the output data to the real-time representative data. S33. The control module determines whether there is an undetermined control model. If it exists, it determines the next control model according to the storage order and jumps to S32. If it does not exist, it determines the final output data based on the output data of all control models and determines whether the real-time access request is allowed based on the final output data.

5. The method according to claim 1, characterized in that, The preprocessing module also continues to generate new historical representative data based on the generated historical representative data, including the following steps: S11. The preprocessing module performs PCA transformation on the generated historical representative data to obtain several feature values. For each feature value, the preprocessing module sets the weight value corresponding to the feature value and calculates the product of the feature value and the weight value corresponding to the feature value. S12. The preprocessing module calculates the sum of all products to obtain the basic value, and the preprocessing module generates several random values ​​based on a Gaussian distribution. The preprocessing module also sets a ratio value. S13. For each random value, the preprocessing module calculates the sum of the products of the base value and the random value and the proportion value to obtain intermediate data, and performs PCA inverse transformation on the intermediate data to obtain new historical representative data.

6. A data access control system based on artificial intelligence, used to implement the method as described in any one of claims 1 to 5, characterized in that, include: The preprocessing module is used to obtain several historical access requests in advance, and for each historical access request, generate historical representative data corresponding to the historical access request, and continue to generate new historical representative data based on the generated historical representative data; The practice module is used to sequentially practice and generate several control models based on all historical representative data. The user module is used to collect users' real-time access requests and send them to the control module. The control module is used to sequentially store several control models generated by the exercise module in the order they were generated during the exercise. It is also used to receive real-time access requests from the user module, generate real-time representative data corresponding to the real-time access requests, and use the sequentially stored control models to perform control processing on the real-time representative data.

Images