Education cloud platform management method

Abstract

The invention discloses an education cloud platform management method, and belongs to the technical field of data processing, and the method comprises the following steps: S1, obtaining stored user education information from a cloud platform; s2, performing iterative processing on the user education information to obtain a plurality of latest features, and generating a threshold value; s3, determining a key key of the user education information according to the threshold value; and S4, in the cloud platform, completing encryption operation based on the key key of the user education information. According to the method, the storage performance and the key key generated by the data information are combined, so that the safety of the user education information can be more effectively guaranteed, the storage efficiency is considered, and the data redundancy and the fault-tolerant capability are also considered.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to an education cloud platform management method. Background Art

[0002] With the rapid development of information technology, the field of education is gradually moving towards digitalization and intelligence. As an important carrier of this trend, education cloud platforms have been widely used in various educational institutions and learning scenarios. These platforms not only provide rich learning resources and convenient learning tools, but also provide users with personalized learning paths and recommendations by storing and analyzing users' educational information. However, with the rapid growth of user educational information, how to ensure its security and privacy has become an important challenge facing education cloud platforms.

[0003] Traditionally, the management of educational information mainly relies on simple data storage and retrieval functions, lacks effective protection of user educational information, is difficult to ensure the security of user information, and is vulnerable to various network attacks and data leakage threats. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes an education cloud platform management method.

[0005] The technical solution of the present invention is: a method for managing an education cloud platform comprises the following steps:

[0006] S1, obtain the stored user education information from the cloud platform;

[0007] S2, iteratively process the user education information to obtain several latest features and generate a threshold value;

[0008] S3. Determine the key of the user's education information according to the threshold value;

[0009] S4. In the cloud platform, encryption operations are completed based on the key key of the user's education information.

[0010] Furthermore, S2 includes the following sub-steps:

[0011] S21, determining the number of iterations of user education information based on the virtual machine of the cloud platform;

[0012] S22, iteratively processing the user education information within the iteration number to obtain a number of latest features;

[0013] S23. Obtain a threshold value of the user education information based on several latest features of the user education information.

[0014] The beneficial effects of the above further scheme are: In the present invention, the cloud platform provides abundant virtual machine resources, and the number of iterations can be flexibly adjusted according to the complexity and scale of the user education information. Through iterative processing, deeper features can be extracted from the user education information, which are essential for understanding the user's encryption needs. By setting a threshold value, the protection of sensitive user education information can be strengthened.

[0015] Furthermore, in S21, the calculation formula for the number of iterations N of the user education information is:

[0016] ; Where K represents the time synchronization interval, f represents the scheduler execution frequency of the virtual machine, ln(·) represents the logarithmic function, and round(·) represents the rounding function.

[0017] Further, S22 includes the following sub-steps:

[0018] S221, extracting features of the user education information using an initial convolution kernel to obtain initial features of the user education information;

[0019] S222, expanding the initial convolution kernel to obtain the latest convolution kernel, and using the latest convolution kernel to extract features of the user education information to obtain the latest features of the user education information;

[0020] S223. Repeat S222 until the number of iterations is reached to obtain several latest features of the user's education information.

[0021] The beneficial effect of the above further scheme is: in the present invention, in S222, each time the convolution kernel size is expanded, the size of the convolution kernel can be doubled, and the corresponding matrix will also change. The initial convolution kernel, as the starting point of feature extraction, can capture the basic, low-level features in the user's education information, laying the foundation for subsequent feature extraction and iterative processing. By expanding the initial convolution kernel, the latest convolution kernel is obtained, which can extract deeper and more complex features, so that the feature extraction process can better adapt to changes in user education information and improve the accuracy and robustness of the processing.

[0022] Furthermore, in S221, the initial feature Z of the user education information start The calculation formula is:

[0023] ; In the formula, e represents the exponent, w start represents the two-dimensional matrix corresponding to the initial convolution kernel, b start represents the bias of the initial convolution kernel, L n represents the nth text in the user's education information, L n+1represents the n+1th text in the user's education information, N represents the number of texts in the user's education information, and dis(·) represents the text similarity function.

[0024] The convolution kernel is a two-dimensional matrix.

[0025] Furthermore, in S222, the latest feature Z of the user education information at the i-th iteration i_new The calculation formula is:

[0026] ; In the formula, e represents the index, Z start represents the initial features of user education information, w i represents the two-dimensional matrix of the latest convolution kernel at the i-th iteration, b i represents the bias of the latest convolution kernel at the i-th iteration, Z i-1_new represents the latest features of the user's education information at the i-1th iteration, f(·) represents the activation function, and c represents a constant.

[0027] Furthermore, in S23, the calculation formula of the threshold value T of the user education information is:

[0028] ; In the formula, Z1 represents the first latest feature, Z M represents the Mth latest feature, MAX(·) represents the maximum value, MIN(·) represents the minimum value, and rand(0,1) represents a random number between 0 and 1.

[0029] Furthermore, S3 includes the following sub-steps:

[0030] S31, generating performance parameters according to the storage volume where the user education information is located;

[0031] S32, generating image storage parameters according to the threshold value of the user interaction information;

[0032] S33. Generate a key for user education information based on performance parameters and image storage parameters.

[0033] The beneficial effect of the above further solution is that in the present invention, by considering the storage volume where the user education information is located, parameters that meet the performance characteristics of the storage environment can be generated. As the performance of the storage volume changes, the performance parameters can be updated accordingly to ensure that the storage strategy always matches the actual situation. The key key generated by combining storage performance and data protection requirements can more effectively ensure the security of user education information.

[0034] Furthermore, in S31, the calculation formula of the performance parameter O is: ; In the formula, C represents the capacity of the storage volume and B represents the bytes of user education information.

[0035] Furthermore, in S32, the calculation formula of the mirror storage parameter P is: ; Where T represents the threshold value of user education information, Indicates rounding up.

[0036] The beneficial effects of the present invention are: by iteratively processing user education information, the present invention can extract more valuable features from the user education information, understand the user information more deeply, and make the generated threshold values ​​correspond to different data protection requirements; the present invention combines storage performance and key keys generated by data information to more effectively ensure the security of user education information, not only considering storage efficiency, but also taking into account data redundancy and fault tolerance. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The flowchart of the education cloud platform management method. DETAILED DESCRIPTION

[0038] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0039] like Figure 1 As shown, the present invention provides an education cloud platform management method, comprising the following steps:

[0040] S1, obtain the stored user education information from the cloud platform;

[0041] S2, iteratively process the user education information to obtain several latest features and generate a threshold value;

[0042] S3. Determine the key of the user's education information according to the threshold value;

[0043] S4. In the cloud platform, encryption operations are completed based on the key key of the user's education information.

[0044] In this embodiment of the present invention, S2 includes the following sub-steps:

[0045] S21, determining the number of iterations of user education information based on the virtual machine of the cloud platform;

[0046] S22, iteratively processing the user education information within the iteration number to obtain a number of latest features;

[0047] S23. Obtain a threshold value of the user education information based on several latest features of the user education information.

[0048] In the present invention, the cloud platform provides abundant virtual machine resources, and the number of iterations can be flexibly adjusted according to the complexity and scale of user education information. Through iterative processing, deeper features can be extracted from user education information, which are essential for understanding the user's encryption needs. By setting a threshold value, the protection of sensitive user education information can be strengthened.

[0049] In the embodiment of the present invention, in S21, the calculation formula for the iteration number N of the user education information is:

[0050] ; Where K represents the time synchronization interval, f represents the scheduler execution frequency of the virtual machine, ln(·) represents the logarithmic function, and round(·) represents the rounding function.

[0051] In this embodiment of the present invention, S22 includes the following sub-steps:

[0052] S221, extracting features of the user education information using an initial convolution kernel to obtain initial features of the user education information;

[0053] S222, expanding the initial convolution kernel to obtain the latest convolution kernel, and using the latest convolution kernel to extract features of the user education information to obtain the latest features of the user education information;

[0054] S223. Repeat S222 until the number of iterations is reached to obtain several latest features of the user's education information.

[0055] In the present invention, in S222, each time the convolution kernel size is expanded, the size of the convolution kernel can be doubled, and the corresponding matrix will also change. As the starting point of feature extraction, the initial convolution kernel can capture the basic and low-level features in the user's education information, laying the foundation for subsequent feature extraction and iterative processing. By expanding the initial convolution kernel, the latest convolution kernel is obtained, which can extract deeper and more complex features, so that the feature extraction process can better adapt to the changes in the user's education information and improve the accuracy and robustness of the processing.

[0056] In the embodiment of the present invention, in S221, the initial feature Z of the user education information start The calculation formula is:

[0057] ; In the formula, e represents the exponent, w start represents the two-dimensional matrix corresponding to the initial convolution kernel, b start represents the bias of the initial convolution kernel, L n represents the nth text in the user's education information, L n+1 represents the n+1th text in the user's education information, N represents the number of texts in the user's education information, and dis(·) represents the text similarity function.

[0058] The convolution kernel is a two-dimensional matrix.

[0059] In the embodiment of the present invention, in S222, the latest feature Z of the user education information at the i-th iteration i_new The calculation formula is:

[0060] ; In the formula, e represents the index, Z start represents the initial features of user education information, w i represents the two-dimensional matrix of the latest convolution kernel at the i-th iteration, b i represents the bias of the latest convolution kernel at the i-th iteration, Z i-1_new represents the latest features of the user's education information at the i-1th iteration, f(·) represents the activation function, and c represents a constant.

[0061] In the embodiment of the present invention, in S23, the calculation formula of the threshold value T of the user education information is:

[0062] ; In the formula, Z1 represents the first latest feature, Z M represents the Mth latest feature, MAX(·) represents the maximum value, MIN(·) represents the minimum value, and rand(0,1) represents a random number between 0 and 1.

[0063] In this embodiment of the present invention, S3 includes the following sub-steps:

[0064] S31, generating performance parameters according to the storage volume where the user education information is located;

[0065] S32, generating image storage parameters according to the threshold value of the user interaction information;

[0066] S33. Generate a key for user education information based on performance parameters and image storage parameters.

[0067] In the present invention, by considering the storage volume where the user education information is located, parameters that meet the performance characteristics of the storage environment can be generated. As the performance of the storage volume changes, the performance parameters can be updated accordingly to ensure that the storage strategy always matches the actual situation. The key key (O, P) generated by combining storage performance and data protection requirements can more effectively protect the security of user education information.

[0068] In the embodiment of the present invention, in S31, the calculation formula of the performance parameter O is: ; In the formula, C represents the capacity of the storage volume and B represents the bytes of user education information.

[0069] In the embodiment of the present invention, in S32, the calculation formula of the mirror storage parameter P is: ; Where T represents the threshold value of user education information, Indicates rounding up.

[0070] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A method for managing an education cloud platform, characterized in that: The following steps are involved: S1, obtain the stored user education information from the cloud platform; S2, iteratively process the user education information to obtain several latest features and generate a threshold value; S3. Determine the key of the user's education information according to the threshold value; S4. In the cloud platform, encryption operations are completed based on the key of the user's education information.

2. The educational cloud platform management method according to claim 1, characterized in that: The S2 comprises the following sub-steps: S21, determining the number of iterations of user education information based on the virtual machine of the cloud platform; S22, iteratively processing the user education information within the iteration number to obtain a number of latest features; S23. Obtain a threshold value of the user education information based on several latest features of the user education information.

3. The educational cloud platform management method according to claim 2, characterized in that: In S21, the calculation formula for the iteration number N of the user education information is: ; Where K represents the time synchronization interval, f represents the scheduler execution frequency of the virtual machine, ln(·) represents the logarithmic function, and round(·) represents the rounding function.

4. The educational cloud platform management method according to claim 2, characterized in that: The S22 comprises the following sub-steps: S221, extracting features of the user education information using an initial convolution kernel to obtain initial features of the user education information; S222, expanding the initial convolution kernel to obtain the latest convolution kernel, and using the latest convolution kernel to extract features of the user education information to obtain the latest features of the user education information; S223. Repeat S222 until the number of iterations is reached to obtain several latest features of the user's education information.

5. The educational cloud platform management method according to claim 4, characterized in that: In S221, the initial feature Z of the user education information start The calculation formula is: ; In the formula, e represents the exponent, w start represents the two-dimensional matrix corresponding to the initial convolution kernel, b start represents the bias of the initial convolution kernel, L n represents the nth text in the user's education information, L n+1 represents the n+1th text in the user's education information, N represents the number of texts in the user's education information, and dis(·) represents the text similarity function.

6. The educational cloud platform management method according to claim 4, characterized in that: In S222, the latest feature Z of the user education information at the i-th iteration i_new The calculation formula is: ; In the formula, e represents the index, Z start represents the initial features of user education information, w i represents the two-dimensional matrix of the latest convolution kernel at the i-th iteration, b i represents the bias of the latest convolution kernel at the i-th iteration, Z i-1_new represents the latest features of the user's education information at the i-1th iteration, f(·) represents the activation function, and c represents a constant.

7. The educational cloud platform management method according to claim 2, characterized in that: In S23, the calculation formula of the threshold value T of the user education information is: ; In the formula, Z1 represents the first latest feature, Z M represents the Mth latest feature, MAX(·) represents the maximum value, MIN(·) represents the minimum value, and rand(0,1) represents a random number between 0 and 1.

8. The educational cloud platform management method according to claim 1, characterized in that: The S3 comprises the following sub-steps: S31, generating performance parameters according to the storage volume where the user education information is located; S32, generating image storage parameters according to the threshold value of the user interaction information; S33. Generate a key for user education information based on performance parameters and image storage parameters.

9. The educational cloud platform management method according to claim 8, characterized in that: In S31, the calculation formula of the performance parameter O is: ; In the formula, C represents the capacity of the storage volume and B represents the bytes of user education information.

10. The educational cloud platform management method according to claim 8, characterized in that: In S32, the calculation formula of the mirror storage parameter P is: ; Where T represents the threshold value of user education information, Indicates rounding up.

Images