A high-reliability learning resource security sharing method and device based on big data

By adopting big data technology on the online learning resource sharing platform, setting encryption levels based on the sensitivity of learning resources, monitoring data tampering and evaluating credibility, the credibility and security issues in online learning resource sharing are solved, and the problem of credibility and security is achieved High-quality and secure resource sharing.

CN118568754BActive Publication Date: 2024-11-26ZHEJIANG UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411038288.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-26
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

In the existing online learning resource sharing platform, the credibility problem of learning resources is becoming increasingly prominent, and due to the complex sources and uneven quality, it is difficult to ensure the security and quality of resources.

Method used

Using a big data-based method, by acquiring and classifying learning resource data, setting encryption levels according to sensitivity, and storing and monitoring data tampering in distributed storage nodes, dynamically adjusting encryption levels, and credibility assessment is carried out in combination with user feedback evaluation. , ensure the secure sharing of resources.

Benefits of technology

It realizes strong protection of highly sensitive data, improves the credibility and sharing security of learning resources, ensures that users obtain high-quality learning resources, and improves the accuracy of recommendations through user similarity recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118568754B_ABST
    Figure CN118568754B_ABST
Patent Text Reader

Abstract

The present invention relates to a high-credibility learning resource security sharing method and device based on big data, including: obtaining learning resource data, setting an encryption level and encrypting it according to the sensitivity of the learning resource data, storing it in distributed storage nodes, and monitoring the tampering of the learning resource data; obtaining feedback evaluation information data of different users on the learning resource data, evaluating the credibility of the learning resource data, and dynamically adjusting the encryption level of the learning resource data; decrypting and sharing the learning resource data requested to be shared according to the type of user requesting sharing and its authority, wherein the user obtains the learning resource data requested to be shared through active search or passive recommendation, and recommends learning resource data to users based on the similarity between users to the same type of learning resource data. Through the above-mentioned method, the credibility of learning materials is improved, ensuring that users can obtain high-quality learning resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of computer resource sharing, and in particular, relates to a high-reliability learning resource security sharing method and device based on big data. Background Art

[0002] When studying, you need to refer to a lot of materials. In the era of digital education, online sharing of learning resources has become increasingly common. In the existing data sharing platform, a cloud service center can be used and communicated with the cloud service center, so that users can share learning resources online.

[0003] However, due to the complex sources and uneven quality of online shared learning resources, the credibility of learning resources has become increasingly prominent; therefore, it is necessary to propose a highly reliable learning resource secure sharing method and system. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a high-reliability learning resource security sharing method and device based on big data to address the problems existing in the prior art.

[0005] According to a first aspect of an embodiment of the present application, a method for securely sharing high-reliability learning resources based on big data is provided, comprising:

[0006] Acquire learning resource data, set encryption levels according to the classification of the learning resource data, and encrypt the learning resource data, wherein the learning resource data is classified according to sensitivity;

[0007] Store the encrypted learning resource data in distributed storage nodes and monitor the tampering of the learning resource data;

[0008] Obtain feedback and evaluation information data from different users on learning resource data, and evaluate the credibility of the learning resource data;

[0009] Dynamically adjust the encryption level of learning resource data based on tampering conditions and credibility assessment results;

[0010] The learning resource data requested to be shared is decrypted and shared according to the type of user requesting sharing and their permissions. The user obtains the learning resource data requested to be shared through active search or passive recommendation, and learning resource data is recommended to the user based on the similarity between users for the same type of learning resource data.

[0011] Further, learning resource data is obtained, encryption strength is set according to the classification of the learning resource data, and encryption processing is performed on the learning resource data, including:

[0012] The learning resource data is classified using an information recognition and extraction model, and labels are assigned to the learning resource data according to the classification results, wherein the labels include high sensitivity, medium sensitivity, and low sensitivity;

[0013] When the label of the learning resource data is high sensitivity, the encryption level is determined to be level one, and the level one encryption algorithm is executed; when the label of the learning resource data is medium sensitivity, the encryption level is determined to be level two, and the level two encryption algorithm is executed; when the label of the learning resource data is low sensitivity, the encryption level is determined to be level three, and the level three encryption algorithm is executed; wherein the encryption strength of the level one encryption algorithm, the level two encryption algorithm, and the level three encryption algorithm decreases gradually.

[0014] Furthermore, the encrypted learning resource data is stored in distributed storage nodes, and the tampering of the learning resource data is monitored, including:

[0015] Based on whether the learning resource data has been tampered with as input, the encrypted learning resource data is hashed to generate a hash value;

[0016] Divide the distributed storage nodes into first-level encrypted storage nodes, second-level encrypted storage nodes and third-level encrypted storage nodes, and store the hashed learning resource data and its hash value in the corresponding storage nodes according to the encryption level of the learning resource data;

[0017] Compare the hash values ​​of different storage nodes to monitor tampering.

[0018] Furthermore, feedback evaluation information data of different users on the learning resource data is obtained to evaluate the credibility of the learning resource data, including:

[0019] Obtaining feedback evaluation information data of different users on learning resource data, performing word segmentation, removing stop words, and extracting stems, thereby dividing the feedback evaluation information data into positive evaluation and negative evaluation;

[0020] Comparing the number of positive evaluations and the number of negative evaluations to determine whether the learning resource data has primary credibility, wherein if the number of positive evaluations is greater than the number of negative evaluations, then determining that the learning resource data has primary credibility;

[0021] If the learning resource data has primary credibility, the ratio of the number of positive evaluations to the number of negative evaluations is calculated, and the credibility level of the learning resource data is determined based on the ratio.

[0022] Furthermore, according to the type of user requesting sharing and their permissions, the learning resource data is decrypted and shared, including:

[0023] Obtaining a sharing request from a user, and determining whether the sharing request satisfies the user's permissions and operation restrictions;

[0024] If the user permissions and operation restrictions are met, the learning resource data requested by the user to be shared will be decrypted and shared.

[0025] Furthermore, the similarity between user u and user v for the same type of learning resource data is used to make recommendations for the user. The similarity is calculated as follows:

[0026] J(u_A,v_A) ;

[0027] Among them, u_A is the set of A-type learning resource data clicked by user u, and v_A is the set of A-type learning resource data clicked by user v.

[0028] According to a second aspect of an embodiment of the present application, a high-reliability learning resource security sharing device based on big data is provided, comprising:

[0029] An encryption module, used to obtain learning resource data, set encryption levels according to the classification of the learning resource data, and encrypt the learning resource data, wherein the learning resource data is classified according to sensitivity;

[0030] A tampering monitoring module is used to store the encrypted learning resource data in distributed storage nodes and monitor the tampering of the learning resource data;

[0031] A credibility evaluation module is used to obtain feedback and evaluation information data of different users on the learning resource data and evaluate the credibility of the learning resource data;

[0032] A dynamic adjustment module is used to dynamically adjust the encryption level of learning resource data according to the tampering situation and credibility evaluation results;

[0033] The sharing module is used to decrypt and share the learning resource data requested for sharing according to the type of user requesting sharing and their permissions. The user obtains the learning resource data requested for sharing through active search or passive recommendation, and the learning resource data is recommended to the user based on the similarity between users for the same type of learning resource data.

[0034] According to a third aspect of an embodiment of the present application, a computer program product is provided, comprising a computer program / instruction, which implements the method described in the first aspect when executed by a processor.

[0035] According to a fourth aspect of an embodiment of the present application, there is provided an electronic device, including:

[0036] one or more processors;

[0037] A memory for storing one or more programs;

[0038] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect.

[0039] According to a fifth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0040] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0041] It can be seen from the above embodiments that the present application classifies the learning resource data according to its sensitivity and sets the encryption strength in a graded manner, thereby achieving stronger protection for highly sensitive data with personal identity information; adopts a distributed storage method, sets multiple storage nodes to store learning resource data, and monitors data tampering; obtains feedback evaluation information data, and performs quantitative assessment of the credibility of the learning resource data, thereby dynamically adjusting the encryption strength, further improving the credibility of the learning resources and the security of sharing, and ensuring that users can obtain high-quality learning resources; recommends learning resource data to users based on the similarity between users of the same type of learning resource data, thereby improving the accuracy of the recommendation, thereby making it more likely that users will obtain the required learning resources.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] Figure 1 It is a flow chart of the high-credibility learning resource security sharing method based on big data of the present invention.

[0045] Figure 2 This is a flow chart of S100 of the present invention.

[0046] Figure 3 This is a flow chart of S200 of the present invention.

[0047] Figure 4 This is a flow chart of S300 of the present invention.

[0048] Figure 5 It is a block diagram of the high-credibility learning resource security sharing device based on big data of the present invention.

[0049] Figure 6 is a schematic diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0050] Here, exemplary embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application.

[0051] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0052] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0053] like Figure 1 As shown, the present application provides a flowchart of a method for secure sharing of high-credibility learning resources based on big data, which method may include the following steps:

[0054] S100: Acquire learning resource data, set encryption levels according to the classification of the learning resource data, and encrypt the learning resource data, wherein the learning resource data is classified according to sensitivity;

[0055] In this embodiment, learning resource data is obtained, encryption strength is set according to the classification of the learning resource data, and the learning resources are encrypted, thereby effectively protecting the security of the learning resources and preventing unauthorized access and data leakage. The classification of learning resource data includes highly sensitive data resources, medium sensitive data resources, and low sensitive data resources.

[0056] Specifically, Figure 2 As shown, this step can be divided into the following sub-steps:

[0057] S101: Classify the learning resource data using an information recognition and extraction model, and assign labels to the learning resource data according to the classification results, wherein the labels include high sensitivity, medium sensitivity, and low sensitivity;

[0058] Specifically, information recognition and extraction models are used, such as recurrent neural networks, long short-term memory networks, and convolutional neural networks based on deep learning, to classify and identify learning resource data, and assign labels to the learning resource data. The labels include high sensitivity, medium sensitivity, and low sensitivity. High-sensitivity resources contain user personal identity information, medium-sensitive resources may be non-public learning resources uploaded by users and do not contain personal identity information, and low-sensitivity resources are public resources on the Internet.

[0059] S102: When the label of the learning resource data is high sensitivity, the encryption level is determined to be level one, and the level one encryption algorithm is executed; when the label of the learning resource data is medium sensitivity, the encryption level is determined to be level two, and the level two encryption algorithm is executed; when the label of the learning resource data is low sensitivity, the encryption level is determined to be level three, and the level three encryption algorithm is executed; wherein the encryption strength of the level one encryption algorithm, the level two encryption algorithm, and the level three encryption algorithm decreases step by step.

[0060] Specifically, the learning resource data is classified according to the sensitivity, the encryption level is determined according to the classification result, and the corresponding encryption operation is performed; when the classified information is a highly sensitive data resource, the encryption level is determined to be level one, and the level one encryption algorithm is executed; when the classified information is a medium sensitive data resource, the encryption level is determined to be level two, and the level two encryption algorithm is executed; when the classified information is a low sensitive data resource, the encryption level is determined to be level three, and the level three encryption algorithm is executed, and the encryption strength of the level one encryption algorithm, the level two encryption algorithm, and the level three encryption algorithm decreases step by step. For example, highly sensitive data resources include personal identity information, such as private lesson preparation materials, etc., which can be encrypted by AES, RSA, and ECC; medium sensitive data resources include public lesson preparation materials, etc., which can be encrypted by 3DES and IDEA; low sensitive data resources include announcements, network materials, etc., which can be encrypted by DES, RC2, and RC4.

[0061] It should be noted that the above encryption level is the initial encryption level of learning resource data. In specific implementation, the encryption level of learning resource data will also be adjusted according to real-time tampering conditions, access frequency, feedback evaluation, etc. For example: when it is found that the access frequency of a certain type of resource has increased significantly or new resources are added, the sensitivity of this type of resource will be temporarily increased, and low-sensitivity data resources will be increased to medium-sensitive data resources, and medium-sensitive data resources will be increased to high-sensitivity data resources, thereby increasing the encryption strength to prevent potential threats; when it is found that a certain type of resource has been downgraded to old resources, the sensitivity of this type of resource will be reduced, and medium-sensitive data resources will be reduced to low-sensitive data resources, and high-sensitive data resources will be reduced to medium-sensitive data resources.

[0062] S200: storing the encrypted learning resource data in distributed storage nodes, and monitoring the tampering of the learning resource data;

[0063] In this embodiment, a distributed storage method is adopted, multiple storage nodes are set to store learning resource data, and data tampering is monitored to verify the integrity of the learning resources and prevent the resources from being tampered with during transmission. Figure 3 As shown in the figure, the specific process of monitoring data tampering is as follows:

[0064] S201: Based on whether the learning resource data has been tampered with as input, hash processing is performed on the encrypted learning resource data to generate a hash value;

[0065] Specifically, the encrypted learning resource data is hashed, and hash functions such as SHA-256 and Keccak-256 are used to take whether the data has been changed as the input value, where the input value is that the data has not been changed, to generate a hash value; this hash value is a unique hash value, which is unidirectional, collision-resistant and deterministic.

[0066] S202: Divide the distributed storage nodes into first-level encryption storage nodes, second-level encryption storage nodes, and third-level encryption storage nodes, and store the hashed learning resource data and its hash value in the corresponding storage nodes according to the encryption level of the learning resource data;

[0067] Then, multiple first-level encryption storage nodes, second-level encryption storage nodes, and third-level encryption storage nodes are set up. According to the encryption level of the learning resource data, the encrypted and hashed learning resource data with the encryption level of the first level and its hash value are stored in multiple first-level encryption storage nodes; the encrypted and hashed learning resource data with the encryption level of the second level and its hash value are stored in multiple second-level encryption storage nodes; the encrypted and hashed learning resource data with the encryption level of the third level and its hash value are stored in multiple third-level encryption storage nodes. In this step, the data of corresponding sensitivity is stored in different levels to restrict other users' operations; for example, when the shared data is in the first-level encryption storage node, the data stored in the node is a highly sensitive data resource, such as personal identity information, private lesson preparation materials, etc., and such data may require a password to be entered before it can be viewed or can only be viewed but not downloaded according to the requirements of the uploading user; for example, when the shared data is in the second-level encryption storage node, the data stored in the node is a medium-sensitive data resource, such as public lesson preparation materials, etc., and such data may require users of related majors to view it according to the requirements of the uploading user; for example, when the shared data is in the third-level encryption storage node, it can be viewed directly without setting operation permissions. At the same time, if the user's role is guest, he can only query the data of the third-level encrypted storage node, which improves the security performance of the entire resource sharing.

[0068] S203: Compare hash values ​​of different storage nodes and monitor tampering.

[0069] By comparing the hash values ​​of different storage nodes, tampering is monitored. When the hash values ​​of each storage node are consistent, it means that the input value during hash processing is: the data has not been changed, and it is determined that no tampering has occurred; when the hash values ​​of a single or multiple storage nodes are inconsistent with those of other storage nodes, it means that the input value during hash processing is: the data has been changed, and it is determined that tampering has occurred. Each storage node has a complete copy of the blockchain, so the integrity of the learning resource data can be verified by comparing the data on different storage nodes; if the data on one or more nodes is tampered with, its hash value will be inconsistent with the hash value on other nodes, so that data tampering can be detected.

[0070] S300: Obtaining feedback evaluation information data of different users on learning resource data, and evaluating the credibility of the learning resource data;

[0071] In this embodiment, role feedback evaluation information data is obtained to evaluate the credibility of learning resource data, thereby improving the credibility of learning resource data and ensuring that users can obtain high-quality learning materials. Figure 4 As shown in the figure, the specific process of the evaluation is:

[0072] S301: Obtaining feedback evaluation information data of different users on learning resource data, performing word segmentation, removing stop words, and extracting stems, thereby dividing the feedback evaluation information data into positive evaluation and negative evaluation;

[0073] Specifically, feedback evaluation information from multiple users is collected, and word segmentation, stop word removal, and stem extraction are performed to obtain positive or negative features of the feedback evaluation information, such as positive features: correct, good, relatively good, etc., and negative features: inaccurate, incorrect, poor, useless, etc. According to the positive features and negative features, the feedback evaluation information can be divided into positive evaluation and negative evaluation.

[0074] S302: comparing the number of positive evaluations and the number of negative evaluations to determine whether the learning resource data has primary credibility, wherein if the number of positive evaluations is greater than the number of negative evaluations, then determining that the learning resource data has primary credibility;

[0075] Count the number of positive and negative reviews respectively. If the number of positive reviews is greater than the number of negative reviews, the learning resource data is judged to have primary credibility. Assuming that the number of positive reviews is 100 and the number of negative reviews is 10, the learning resource is judged to have primary credibility; assuming that the number of positive reviews is 100 and the number of negative reviews is 120, the learning resource is judged to have no primary credibility; assuming that the number of positive reviews is 100 and the number of negative reviews is 100, the learning resource is judged to have no primary credibility.

[0076] S303: If the learning resource data has primary credibility, then calculate the ratio of the number of positive evaluations to the number of negative evaluations, and determine the credibility level of the learning resource data according to the ratio;

[0077] Specifically, under the premise that the learning resource has primary credibility, a first percentage threshold interval, a second percentage threshold interval, and a third percentage threshold interval are preset to calculate the ratio of the number of negative reviews to the number of positive reviews. Assume that the first percentage threshold interval is 0-20%, the second percentage threshold interval is 21-50%, and the third percentage threshold interval is 51-99%.

[0078] By comparing the ratio, the first percentage threshold interval, the second percentage threshold interval, and the third percentage threshold interval, the credibility level of the learning resource data is output; when the ratio is in the first percentage threshold interval, the credibility level of the output learning resource data is a high credibility level; when the ratio is in the second percentage threshold interval, the credibility level of the output learning resource data is a medium credibility level; when the ratio is in the third percentage threshold interval, the credibility level of the output learning resource data is a low credibility level. In the above manner, users can query the credibility of learning resource data to ensure that users can obtain high-quality learning materials.

[0079] For example, suppose case 1: the number of positive reviews is 100 and the number of negative reviews is 10, then the proportion is 10%, and the credibility level of the output learning resource is high credibility level; case 2: the number of positive reviews is 70 and the number of negative reviews is 10, then the proportion is 40%, and the credibility level of the output learning resource is medium credibility level; case 3: the number of positive reviews is 15 and the number of negative reviews is 10, then the proportion is 66.66%, and the credibility level of the output learning resource is low credibility level.

[0080] S400: dynamically adjusting the encryption level of the learning resource data according to the tampering situation and the credibility evaluation result;

[0081] Specifically, if the data is tampered with, or the credibility level of the data is reduced, it is determined that the resource has been downgraded and the encryption level needs to be adjusted downward.

[0082] S500: decrypting and sharing the learning resource data requested for sharing according to the type of user requesting sharing and the authority thereof;

[0083] In this implementation, access roles and their permissions are set up to share learning resources and implement fine-grained access control to ensure the rational use of resources. The process of sharing learning resources is as follows:

[0084] S501: Obtaining a sharing request from a user, and determining whether the sharing request satisfies the user's authority and operation restrictions;

[0085] Specifically, define access roles for user types, and assign unique identifiers to each role; user types include administrators, ordinary users, and visitors; then, according to the responsibilities and scope of permissions of the roles, permissions are divided into first-level permissions, second-level permissions, and third-level permissions; first-level permissions include read permissions, write permissions, and execute permissions, second-level permissions include read permissions and write permissions, and third-level permissions include read permissions; for example, administrators have read permissions, write permissions, and execute permissions; ordinary users have read permissions and write permissions; and visitors have read permissions. Then set operation restrictions, including operation time, operation location, and operation conditions. For example, administrator operations must be performed during working hours and must be authenticated by the administrator to use the school network to implement permissions; ordinary user operations must be authenticated to implement permissions; and visitors can only implement permissions on weekends.

[0086] S502: If the user authority and operation restrictions are met, the learning resource data requested to be shared by the user is decrypted and shared;

[0087] In the process of sharing learning resource data, the data needs to be decrypted; for example, shared highly sensitive data resources include personal identity information, private lesson preparation materials, etc., which are encrypted using AES, RSA, and ECC; shared medium-sensitive data resources include public lesson preparation materials, etc., which are encrypted using 3DES and IDEA; shared low-sensitivity data resources include announcements, network materials, etc., which are encrypted using DES, RC2, and RC4; during the decryption process, confirm the encryption method, find the key or private key, and in the decryption tool, enter and select the decryption key or private key to start the decryption operation. After the encrypted data is decrypted, learning resource data sharing can be realized.

[0088] In the specific implementation, it is necessary to set up an audit log to review the historical access and operations of the role, and adjust the role permissions and operation restrictions. If the administrator exercises permissions outside working hours or outside the school network, the implementation status must be confirmed in a timely manner.

[0089] In a specific implementation, the user obtains the learning resource data requested to be shared through active search or passive recommendation, and the learning resource data is recommended to the user based on the similarity between users for the same type of learning resource data.

[0090] Collect interaction data between roles and learning resource data, calculate the similarity between multiple roles, and recommend learning resource data to users.

[0091] Collect the interaction data between roles and learning resource data, and calculate the similarity of multiple roles to the same type of learning resource data. The calculation process uses the Jaccard similarity coefficient:

[0092] J(u_A,v_A) ;

[0093] Among them, u_A is the set of A-type learning resource data clicked by user u, and v_A is the set of A-type learning resource data clicked by user v.

[0094] The value obtained through the above calculation is used to describe the dissimilarity between sets. The larger the value, the lower the similarity.

[0095] The similarity obtained according to the above formula is between 0 and 1, with 0.5 as the dividing point. When it is between 0.5 and 1, it is considered that the difference between the two users is large, and the other values ​​are considered that the difference between the two users is small. After calculating the similarity between multiple roles, learning resource data is recommended to two users with small differences. For example, if user u and user v click on category a of category A learning materials (such as multiple teaching materials related to network communication in the communication category), and user u also clicks on category b of category A learning materials (such as multiple teaching materials related to mobile communication in the communication category), and user v also clicks on category c of category A learning materials (such as multiple teaching materials related to communication circuits in the communication category), then category c of category A learning materials is recommended to user u, and category b of category A learning materials is recommended to user v.

[0096] It can be seen from the above embodiments that the present application classifies the learning resource data according to its sensitivity and sets the encryption strength in a graded manner, thereby achieving stronger protection for highly sensitive data with personal identity information; adopts a distributed storage method, sets multiple storage nodes to store learning resource data, and monitors data tampering; obtains feedback evaluation information data, and performs quantitative assessment of the credibility of the learning resource data, thereby dynamically adjusting the encryption strength, further improving the credibility of the learning resources and the security of sharing, and ensuring that users can obtain high-quality learning resources; recommends learning resource data to users based on the similarity between users of the same type of learning resource data, thereby improving the accuracy of the recommendation, thereby making it more likely that users will obtain the required learning resources.

[0097] Corresponding to the aforementioned embodiment of the high-credibility learning resource secure sharing method based on big data, the present application also provides an embodiment of a high-credibility learning resource secure sharing system based on big data.

[0098] Figure 5 is a block diagram of a high-reliability learning resource security sharing device based on big data according to an exemplary embodiment. Figure 5 , the device may include:

[0099] The encryption module 100 is used to obtain the learning resource data, set the encryption level according to the classification of the learning resource data, and encrypt the learning resource data, wherein the learning resource data is classified according to the sensitivity;

[0100] The tampering monitoring module 200 is used to store the encrypted learning resource data in the distributed storage nodes and monitor the tampering of the learning resource data;

[0101] Credibility evaluation module 300, used to obtain feedback evaluation information data of different users on learning resource data, and evaluate the credibility of the learning resource data;

[0102] A dynamic adjustment module 400, used to dynamically adjust the encryption level of the learning resource data according to the tampering situation and the credibility evaluation result;

[0103] The sharing module 500 is used to decrypt and share the learning resource data requested to be shared according to the type of user requesting sharing and their permissions, wherein the user obtains the learning resource data requested to be shared through active search or passive recommendation, and the learning resource data is recommended to the user based on the similarity between users to the same type of learning resource data.

[0104] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0105] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0106] Accordingly, the present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned high-trustworthiness learning resource security sharing method based on big data.

[0107] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned high-reliability learning resource security sharing method based on big data. Figure 6 As shown, a hardware structure diagram of a high-reliability learning resource security sharing system based on big data provided by an embodiment of the present invention is provided for any device with data processing capabilities, except Figure 6In addition to the processor, memory and network interface shown, any device with data processing capability in which the apparatus in the embodiment is located may also include other hardware, generally based on the actual functions of the device with data processing capability, which will not be described in detail.

[0108] Correspondingly, the present application also provides a computer-readable storage medium on which computer instructions are stored, and when the instructions are executed by the processor, the high-confidence learning resource security sharing method based on big data as described above is implemented. The computer-readable storage medium can be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or a memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an SD card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium can also include both an internal storage unit of any device with data processing capabilities and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and can also be used to temporarily store data that has been output or is to be output.

[0109] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the contents disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0110] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A high-reliability learning resource security sharing method based on big data, characterized in that: include: Acquire learning resource data, set encryption levels according to the classification of the learning resource data, and encrypt the learning resource data, wherein the learning resource data is classified according to sensitivity; Store the encrypted learning resource data in distributed storage nodes and monitor the tampering of the learning resource data; Obtain feedback and evaluation information data from different users on learning resource data, and evaluate the credibility of the learning resource data; Dynamically adjust the encryption level of learning resource data based on tampering conditions and credibility assessment results; Decrypt and share the learning resource data requested for sharing according to the type of user requesting sharing and their permissions, wherein the user obtains the learning resource data requested for sharing through active search or passive recommendation, and recommends learning resource data to the user based on the similarity between users for the same type of learning resource data; The process of obtaining feedback and evaluation information data of different users on the learning resource data and evaluating the credibility of the learning resource data includes: Obtaining feedback evaluation information data of different users on learning resource data, performing word segmentation, removing stop words, and extracting stems, thereby dividing the feedback evaluation information data into positive evaluation and negative evaluation; Comparing the number of positive evaluations and the number of negative evaluations to determine whether the learning resource data has primary credibility, wherein if the number of positive evaluations is greater than the number of negative evaluations, then determining that the learning resource data has primary credibility; If the learning resource data has primary credibility, then the ratio of the number of positive evaluations to the number of negative evaluations is calculated, and the credibility level of the learning resource data is determined according to the ratio; Among them, the recommendation is made to the user based on the similarity between user u and user v for the same type of learning resource data. The similarity is calculated as follows: J(u_A,v_A) ; Among them, u_A is the set of A-type learning resource data clicked by user u, and v_A is the set of A-type learning resource data clicked by user v.

2. The method according to claim 1, characterized in that Acquire learning resource data, set encryption strength according to the classification of learning resource data, and encrypt the learning resource data, including: The learning resource data is classified using an information recognition and extraction model, and labels are assigned to the learning resource data according to the classification results, wherein the labels include high sensitivity, medium sensitivity, and low sensitivity; When the label of the learning resource data is high sensitivity, the encryption level is determined to be level one, and the level one encryption algorithm is executed; when the label of the learning resource data is medium sensitivity, the encryption level is determined to be level two, and the level two encryption algorithm is executed; when the label of the learning resource data is low sensitivity, the encryption level is determined to be level three, and the level three encryption algorithm is executed; wherein the encryption strength of the level one encryption algorithm, the level two encryption algorithm, and the level three encryption algorithm decreases gradually.

3. The method according to claim 1, characterized in that The encrypted learning resource data is stored in distributed storage nodes, and the tampering of the learning resource data is monitored, including: Based on whether the learning resource data has been tampered with as input, the encrypted learning resource data is hashed to generate a hash value; Divide the distributed storage nodes into first-level encrypted storage nodes, second-level encrypted storage nodes and third-level encrypted storage nodes, and store the hashed learning resource data and its hash value in the corresponding storage nodes according to the encryption level of the learning resource data; Compare the hash values ​​of different storage nodes to monitor tampering.

4. The method according to claim 1, characterized in that Decrypt and share learning resource data based on the type of user requesting sharing and their permissions, including: Obtaining a sharing request from a user, and determining whether the sharing request satisfies the user's permissions and operation restrictions; If the user permissions and operation restrictions are met, the learning resource data requested by the user to be shared will be decrypted and shared.

5. A high-reliability learning resource security sharing device based on big data, characterized in that: include: An encryption module, used to obtain learning resource data, set encryption levels according to the classification of the learning resource data, and encrypt the learning resource data, wherein the learning resource data is classified according to sensitivity; A tampering monitoring module is used to store the encrypted learning resource data in distributed storage nodes and monitor the tampering of the learning resource data; A credibility evaluation module is used to obtain feedback and evaluation information data of different users on the learning resource data and evaluate the credibility of the learning resource data; A dynamic adjustment module is used to dynamically adjust the encryption level of learning resource data according to the tampering situation and credibility evaluation results; A sharing module is used to decrypt and share the learning resource data requested for sharing according to the type of user requesting sharing and their permissions, wherein the user obtains the learning resource data requested for sharing through active search or passive recommendation, and recommends learning resource data to the user based on the similarity between users for the same type of learning resource data; The process of obtaining feedback and evaluation information data of different users on the learning resource data and evaluating the credibility of the learning resource data includes: Obtaining feedback evaluation information data of different users on learning resource data, performing word segmentation, removing stop words, and extracting stems, thereby dividing the feedback evaluation information data into positive evaluation and negative evaluation; Comparing the number of positive evaluations and the number of negative evaluations to determine whether the learning resource data has primary credibility, wherein if the number of positive evaluations is greater than the number of negative evaluations, then determining that the learning resource data has primary credibility; If the learning resource data has primary credibility, then the ratio of the number of positive evaluations to the number of negative evaluations is calculated, and the credibility level of the learning resource data is determined according to the ratio; Among them, the recommendation is made to the user based on the similarity between user u and user v for the same type of learning resource data. The similarity is calculated as follows: J(u_A,v_A) ; Among them, u_A is the set of A-type learning resource data clicked by user u, and v_A is the set of A-type learning resource data clicked by user v.

6. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 4 is implemented.

7. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.

8. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.