Practical teaching resource sharing method and system based on artificial intelligence

Abstract

The invention relates to the technical field of data storage, and particularly discloses a training teaching resource sharing method and system based on artificial intelligence. The method comprises the following steps: arranging a plurality of storage servers, and setting a login management table in each storage server; when a user uploads teaching resources, selecting one storage server as a first server according to the login management table; selecting a second server in the storage server, and synchronizing the teaching resources to the second server; the second server predicts access pressure in a plurality of future time periods based on teaching resources stored in the second server; if a plurality of future time periods in which the access pressure is greater than the first threshold exist, selecting a third server, and synchronizing part of stored teaching resources to the third server; the second server and the third server distribute the access key for the sharing target, the sharing target obtains the teaching resources based on the access key, intelligent distribution and optimization of the teaching resources are achieved, and the user access experience is greatly improved.

Description

Technical Field

[0001] This application relates to the technical field of data storage, and particularly to a method and system for sharing training teaching resources based on artificial intelligence. Background Art

[0002] Traditional methods for sharing training teaching resources have many limitations, such as uneven resource allocation, low access efficiency, inability to effectively predict and cope with peak access periods, etc. These problems limit the maximum utilization of educational resources. To solve these problems, people have begun to explore the use of artificial intelligence technology to optimize the sharing of training teaching resources. Through artificial intelligence technology, the access patterns of teaching resources can be analyzed to predict future access pressure, thereby realizing intelligent resource allocation and optimization.

[0003] For example, the Chinese patent document with the publication number CN118862120A discloses a data access method and system applied to a teaching platform. This method uses a Hadoop cluster and a streaming processing tool. The configuration of the Hadoop cluster and real-time monitoring of data access operation parameters can ensure the stability and scalability of the teaching platform, and adapt to different scales of users and data volumes. The application of the streaming processing tool and data access optimization enables the teaching platform to respond to users' data access requests in real time. Another example is the Chinese patent document with the publication number CN116028501A, which discloses an artificial intelligence data sharing method and system based on blockchain. This method obtains a shared value by analyzing the sharing parameters (co-temporal value, co-secondary value, and time-sharing value) of the shared data, and then divides the data into common data and infrequently used data, and stores them in different blocks respectively. The system can also intelligently display the shared data according to the shared value or display coefficient, improving the user experience.

[0004] However, although the above methods have improved the efficiency of teaching resource sharing and the user experience to a certain extent, they still have some drawbacks. For example, Patent Document 1 may not be flexible and accurate enough in resource allocation and access prediction, resulting in ineffective response during peak access periods and possible low efficiency in resource allocation. Although Patent Document 2 improves data security, there may be performance bottlenecks in processing large-scale data and real-time performance. Summary of the Invention

[0005] To solve the problems raised in the above background art, this application provides a method and system for sharing training teaching resources based on artificial intelligence.

[0006] To achieve the above invention purpose, the present invention proposes a method for sharing training teaching resources based on artificial intelligence, including: Deploy multiple storage servers, and set up a login management table in each of the storage servers. The login management table records the historical login information of each user; When a user uploads teaching resources, select one of the storage servers as the first server according to the login management table; Based on the sharing target of the teaching resources and the login management table, the first server selects a second server from the storage servers and synchronizes the teaching resources to the second server; Based on the teaching resources already stored in itself and the login management table, the second server combines a prediction model to predict the access pressure for multiple future time periods; If there are multiple future time periods in which the access pressure is greater than a first threshold, select a third server from the storage servers and synchronize some of the already stored teaching resources to the third server; The second server and the third server distribute access keys for the sharing target, and the sharing target obtains the teaching resources based on the access keys.

[0007] Further, predicting the access pressure for the future time period includes the following steps: Extract from the login management table the access volume of each user for each type of teaching resource per hour, generate an access sequence for each day based on the access volume, cluster the access sequences on an annual basis to obtain multiple clustering results, divide multiple access patterns for each type of teaching resource based on the clustering results, and use the center of the clustering results as the representative sequence of the access pattern; Obtain the teaching resources already stored in the second server as the resources to be analyzed, obtain the access pattern of each type of the resources to be analyzed based on the date of the future time period, and obtain the representative sequence in the access pattern as the first prediction sequence; Obtain the monthly user change amount, correct the first prediction sequence based on the monthly user change amount to obtain a second prediction sequence, merge the second prediction sequences of different resources to be analyzed to obtain a third prediction sequence, and use the access volume per hour in the third prediction sequence as the access pressure for the future time period.

[0008] Further, clustering the access sequences includes the following steps: Traverse and combine different access sequences to obtain multiple combined sequences. Each combined sequence includes two access sequences, which are respectively defined as the first sequence and the second sequence. Calculate a difference sequence based on the first sequence and the second sequence. The difference sequence is the absolute value of the difference in access volume between the corresponding time periods of the first sequence and the second sequence. Obtain a first feature after processing the difference sequence using the sliding window method; Respectively screen the top N of the largest values of the access volume and the corresponding first time period and second time period that appear in the first sequence and the second sequence, extract a third sequence corresponding to the first time period and a fourth sequence corresponding to the second time period from the difference sequence, and calculate the average values of the third sequence and the fourth sequence respectively as the second feature and the third feature; Cluster the access sequences of each month based on the first feature, the second feature, and the third feature.

[0009] Further, the steps of selecting the third server from the storage servers include the following: Define the future time period when the access pressure in the second server is greater than the first threshold as the migration time period, take the sum of the access pressures of the storage server during the migration time period as the first pressure value, calculate the second pressure value of each storage server throughout the day during the migration time period. The login management table includes the access speed of the user. Perform a weighted sum of the access speed, the first pressure value, and the second pressure value to obtain the evaluation value of the storage server, and select the storage server with the smallest evaluation value as the third server.

[0010] Further, the steps for the shared target to obtain the teaching resources based on the access key include the following: The second server and the third server generate a shared key and a one-dimensional initial matrix, generate a key sequence based on the shared key and the one-dimensional initial matrix, divide the key sequence into multiple subsequences, generate storage addresses based on each subsequence, select one of the storage addresses as the target address. The second server and the third server generate a random key, encrypt the teaching resources based on the random key to obtain encrypted data, and store the encrypted data and the random key in different storage addresses respectively, which are defined as the first address and the second address; Select a target server from the second server and the third server based on the access time of the shared target. The shared target decrypts the encrypted data at the first address based on the random key at the second address in the target server to obtain the teaching resources.

[0011] Further, after the shared target obtains the teaching resources, the target server regenerates the random key, uses the random key to re-encrypt the teaching resources and stores them in the first address, selects a third address from the storage addresses, and stores the regenerated random key in the third address.

[0012] Further, generating the storage address based on the subsequence includes the following steps: Convert the numerical values included in the subsequence into ASCII characters, then convert the ASCII characters into basic characters according to the corresponding multi-national character names, generate a character sequence of the subsequence based on the basic characters, and establish a conversion rule table, where the conversion rule table includes the corresponding relationship between each such character sequence and the storage address.

[0013] Further, if the teaching resource does not exist in the third server, request to re-obtain the teaching resource from the second server. Further, use the K-means or DBSCAN algorithm to cluster the access sequence.

[0014] The present invention also provides an artificial intelligence-based training teaching resource sharing system for the method described above. The system includes: A storage module, including multiple storage servers, where a login management table is set in each storage server, and the login management table records the historical login information of each user; An upload module. When a user uploads a teaching resource, the upload module selects one of the storage servers as the first server according to the login management table. The first server selects a second server from the storage servers based on the sharing target of the teaching resource and the login management table, and synchronizes the teaching resource to the second server; An optimization module. The second server predicts the access pressure for multiple future time periods based on the teaching resources already stored in itself and the login management table, in combination with a prediction model; if there are multiple future time periods in which the access pressure is greater than a first threshold, the optimization module selects a third server from the storage servers and synchronizes some of the already stored teaching resources to the third server; An encryption module. The second server and the third server distribute access keys for the sharing target based on the encryption module, and the sharing target obtains the teaching resource based on the access key. Beneficial effects

[0015] By deploying multiple storage servers and setting up a login management table in each server, the present invention can record in detail the login time and login address of each user. When a user uploads teaching resources, the system can select the most suitable storage server as the first server according to the user's login history and sharing target. The first server intelligently selects a second server based on the sharing target of the teaching resources and the login management table and synchronizes the resources to it, thereby optimizing the distribution of resources. By predicting the access pressure in the future time period through a prediction model, it is possible to more accurately predict and cope with the access peak, thus avoiding the inefficiency of resource allocation and the system pressure during the access peak. The dynamic resource allocation mechanism of the present invention based on user behavior and resource requirements can more flexibly cope with the resource requirements of different users and different time periods, thereby improving the utilization efficiency of resources and the access experience of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flowchart of the steps of a method for sharing training teaching resources based on artificial intelligence according to the present application; Figure 2 is a schematic diagram of the principle of generating a difference sequence according to the present application; Figure 3 is a schematic diagram of the principle of generating a first feature according to the present application; Figure 4 is a schematic diagram of the structure of a system for sharing training teaching resources based on artificial intelligence according to the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of the present application, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0019] As Figure 1 shown, a method for sharing training teaching resources based on artificial intelligence includes: S1: Deploy multiple storage servers, and set up a login management table in each storage server, and the login management table records the historical login information of each user.

[0020] S2: When a user uploads teaching resources, select a storage server as the first server according to the login management table.

[0021] In this embodiment, 3 storage servers are arranged, namely storage servers A, B, and C. Each storage server is provided with a login management table, which records the user login time and login address. The login time is accurate to the minute, and the login address is the IP address and the actual place of origin. Each time a user logs in, storage servers A, B, and C will record the login information in the login management table and synchronize it to other storage servers, so that the login management tables of storage servers A, B, and C keep the content consistent.

[0022] When user A uploads teaching resources, first determine the sharing target of the teaching resources. The sharing target is other users who can access and download the teaching resources. For example, user A designates the sharing target as 3,000 employees in company B. Then, according to the login management table, determine which storage server user A is often assigned to for data communication. For example, through the login management table, it is determined that in the past month, user A has been assigned to conduct data communication with storage server A each time. Therefore, storage server A is used as the first server. The teaching resources uploaded by user A are first stored in the first server.

[0023] S3: Based on the sharing target of the teaching resources and the login management table, the first server selects a second server from the storage servers and synchronizes the teaching resources to the second server.

[0024] The first server can determine which storage server each sharing target often logs in through the login management table. For example, it is determined that all sharing targets often log in to storage server B. Storage server B is used as the second server, and the teaching resources are copied to the second server. By this method, there is no need to copy the teaching resources to each storage server, thus reducing the resource occupancy of the storage servers. In particular, the first server itself can also be used as the second server, and multiple second servers can be selected.

[0025] S4: Based on the teaching resources already stored in itself and the login management table, the second server combines a prediction model to predict the access pressure for multiple future time periods.

[0026] S5: If there are multiple future time periods with access pressure greater than the first threshold, select a third server from the storage servers and synchronize some of the already stored teaching resources to the third server.

[0027] The login management table also includes the time points when each user accesses each type of teaching resource. The second server can predict the access pressure in a future time period based on the teaching resources it has stored and the login management table. By setting a first threshold, it can determine which time periods have high access pressure and which have low access pressure. For example, if the access pressure between 19:00 and 21:00 tomorrow is obtained through prediction and is greater than the first threshold, it indicates that there will be high access pressure between 19:00 and 21:00 tomorrow. Then, a server with lower access pressure is selected from the storage servers as the third server. The second server sends some teaching resources to the third server and diverts users to access the third server to download teaching resources, thereby reducing its own access pressure. The specific method for predicting access pressure will be introduced later.

[0028] S6: The second server and the third server share an access key for the target distribution. The shared target obtains the teaching resources based on the access key.

[0029] The second server and the third server also send the access key to the account of the shared target. The shared target can decrypt and access the teaching resources only when holding the access key, thus ensuring that unauthorized users cannot access the teaching resources.

[0030] Specifically, if the teaching resources do not exist in the third server, a request is sent to re-obtain the teaching resources from the second server.

[0031] If the third server loses the teaching resources due to abnormal reasons, the lost teaching resources can be re-obtained from the second server.

[0032] In the present invention, by arranging multiple storage servers and setting a login management table in each server, the login time and login address of each user can be recorded in detail. When a user uploads teaching resources, the system can select the most suitable storage server as the first server according to the user's login history and the shared target. The first server intelligently selects the second server based on the shared target of the teaching resources and the login management table and synchronizes the resources to it, thereby optimizing the distribution of resources. By predicting the access pressure in a future time period through a prediction model, it is possible to more accurately predict and respond to access peaks, thus avoiding inefficient resource allocation and system pressure during access peaks. The dynamic resource allocation mechanism based on user behavior and resource requirements in the present invention can more flexibly respond to the resource requirements of different users and different time periods, thereby improving the utilization efficiency of resources and the access experience of users.

[0033] Through the collaborative work of multiple storage servers and the application of a prediction model, this solution effectively improves the ability to process large-scale data and real-time performance, and avoids the problem of performance bottlenecks. In addition, this solution also ensures the security of teaching resources and the accuracy of access control by distributing access keys to shared targets, further enhancing the security of the system and the user experience.

[0034] It should be particularly noted that through the present invention, the intelligent allocation and optimization of teaching resources are achieved, and the ability to process large-scale data and real-time performance is improved, greatly enhancing the user access experience.

[0035] The prediction of the access pressure in the future time period in this embodiment includes the following steps: Extract the hourly access volume of each teaching resource by users from the login management table, generate a daily access sequence based on the access volume, cluster the access sequences on an annual basis to obtain multiple clustering results, divide multiple access patterns for each teaching resource based on the clustering results, and use the center of the clustering results as the representative sequence of the access pattern.

[0036] Among them, the K-means or DBSCAN algorithm is used to cluster the access sequences.

[0037] The login management table records the access records of users to each teaching resource. By counting the access records, the hourly access volume of each teaching resource can be obtained. For example, the access volume of teaching resource A between 19:00 and 20:00 is 200. After obtaining the access volume, generate the access sequence of each teaching resource on a daily basis, and each access sequence includes 24 access volumes. Then cluster the access sequences of the past year, so that multiple access patterns of teaching resources can be obtained according to the clustering results. For example, if the clustering results include 5 clusters, it means that all teaching resources have 5 access patterns. Then use the center of the clustering results as the representative sequence of each access pattern. In particular, this embodiment uses the DBSCAN algorithm for clustering, thus omitting the step of determining the number of clusters.

[0038] Obtain the teaching resources stored in the second server as the resources to be analyzed, obtain the access pattern of each resource to be analyzed based on the date of the future time period, and obtain the representative sequence in the access pattern as the first prediction sequence.

[0039] In this embodiment, when calculating, first obtain the teaching resources already stored in the second server. For the convenience of distinction, define them as resources to be analyzed. This embodiment determines the access mode of each teaching resource based on the following steps. First, obtain the date of the future time period to be predicted. Then, obtain the dates with the same attributes in the past year. The same attributes mean that both dates are in the same month and are both working day or rest day attributes, and their sorting regarding working days or rest days in the month is the same. For example, for March 1, 2020, and determine that this day is the first rest day in March, then obtain the date of the first rest day in March 2019, which is March 2. Then, obtain the access mode of each resource to be analyzed on the 5 rest days before March 1, 2020. Here, it is defined as the access mode sequence of the current time period, and the access mode of the 5 rest days before March 2, 2019. Here, it is defined as the access mode sequence of the past time period.

[0040] By comparing the access model sequences of the current time period and the past time period, determine the number of times the same pattern appears. For example, through comparison, it is determined that there are three same access modes of the resource A to be analyzed in the current time period and the past time period, which is greater than or equal to the second threshold. The second threshold is set to 3. Then, set the access mode of the teaching resource A on March 2, 2019 as the access mode on March 1, 2020, and use the representative sequence as the first prediction sequence for March 1.

[0041] If the number of same access modes is less than the second threshold, it indicates that the access situation of the resource A to be analyzed has changed, perhaps the exam month has been changed. At this time, obtain the access volume of the resource A to be analyzed per hour per day within the 5 rest days before March 1, 2020, add up the access volumes in the same time period and take the average, and multiply by the preset coefficient as the access volume on March 1. For example, from February 25 to February 29, the access volumes at 18:00 - 19:00 are 15, 25, 30, 40, 26 respectively. Then, the access volume at 18:00 - 19:00 on March 1, 2020 is (18 + 15 + 30 + 40 + 26) / 5 * 0.8 = 20.64.

[0042] Obtain the monthly user change amount, correct the first prediction sequence based on the monthly user change amount to obtain the second prediction sequence, merge the second prediction sequences of different resources to be analyzed to obtain the third prediction sequence, and use the access volume per hour in the third prediction sequence as the access pressure in the future time period.

[0043] The monthly user change is obtained based on the number of people registered in the system. For example, on February 29, the number of registered people in the system was 3,000, and on March 1, the number of registered people was 3,015. The ratio is 3,015 / 3,000 = 1.005, and the number of visits in each time period in the first prediction sequence is increased by 1.005 times to obtain the second prediction sequence. If there are teaching resources A, B, and C in the second server, the second prediction sequences of the three teaching resources are added together (the number of visits in the same time period is added together) to obtain the third prediction sequence. The third prediction sequence can be used to obtain the number of visits to the second server per hour on March 1, and then the hourly access pressure can be obtained.

[0044] In this embodiment, clustering access sequences includes the following steps: Different access sequences are traversed and combined to obtain multiple combination sequences. Each combination sequence includes two access sequences, which are defined as the first sequence and the second sequence respectively. The difference sequence is calculated based on the first sequence and the second sequence. The difference sequence is the absolute value of the difference in the number of visits between the first sequence and the second sequence in the corresponding time period. The first feature is obtained after processing the difference sequence based on the sliding window method.

[0045] For example, if there are access sequences 1, 2, and 3, then after traversing the combinations, combination sequences 1, 2, and 3 are obtained. Combination sequence 1 includes access sequences 1 and 2, combination sequence 2 includes access sequences 2 and 3, and combination sequence 3 includes access sequences 1 and 3. Here, one of the combination sequences is selected for explanation, and access sequences 1 and 2 are defined as the first sequence and the second sequence respectively. For the sake of convenience, only a simple example is given here. Figure 2 As shown, assuming that the first sequence is [10, 50, 30, 20, 60] and the second sequence is [20, 40,70, 55, 25], the difference sequence is [10, 10, 40, 35, 35]. Here, the window size is 3 and the sliding step size is 1, as shown in Figure 3 As shown, the first feature obtained according to the difference sequence is [20, 28.3, 36.7]. The closer the value in the first feature is to 0, the more similar the first sequence and the second sequence are.

[0046] Filter the top N visits with the largest values ​​in the first sequence and the second sequence and the corresponding first and second time periods, extract the third sequence corresponding to the first time period and the fourth sequence corresponding to the second time period from the difference sequence, and calculate the average values ​​of the third and fourth sequences as the second and third features, respectively.

[0047] If N is set to 2, then the first sequence is 60 and 50, and the corresponding first time period includes 5 and 2. The second sequence is 70 and 55, and the corresponding second time period is 3 and 4. The third sequence is [10, 35], and its mean is 22.5. The fourth sequence is [40, 35], and its mean is 37.5. Then 22.5 and 37.5 are taken as the second and third features respectively. The smaller the second and third features are, the more similar the first and second sequences are.

[0048] The access sequences of each month are clustered based on the first feature, the second feature, and the third feature.

[0049] By extracting the first feature, the second feature, and the third feature as input features of the clustering algorithm, the clustering speed can be significantly improved when the amount of data is large.

[0050] In this embodiment, selecting a third server from the storage server includes the following steps: Define the future time period in which the access pressure of the second server is greater than the first threshold as the migration time period, take the sum of the access pressure of the storage server in the migration time period as the first pressure value, calculate the second pressure value of each storage server throughout the migration time period, the login management table includes the user's access speed, and perform weighted summation on the access speed, the first pressure value and the second pressure value to obtain the evaluation value of the storage server, and select the storage server with the smallest evaluation value as the third server.

[0051] Through prediction, it is determined that the access pressure of the second server from 18:00 to 20:00 tomorrow exceeds the first threshold, so the migration time period is defined as 18:00-20:00 tomorrow. Then, the access pressure of the remaining storage servers between 18:00-20:00 tomorrow is obtained, and the sum of the access pressures of 18:00-19:00 and 19:00-20:00 is taken as the first pressure value. The smaller the first pressure value, the smaller the access pressure of the storage server during the migration time period.

[0052] Then, the second pressure value of each storage server throughout the day tomorrow is calculated. The second pressure value of this embodiment is calculated by the following method: first, the third prediction sequence of each storage server tomorrow is obtained, and the third prediction sequence is fitted based on the least squares method to obtain the function of access pressure with respect to time change: , then find the function The inverse of the integral over the entire day, i.e. , thereby obtaining the second pressure value. In the above formula, P is the second pressure value, For tomorrow's starting time, The end time of tomorrow. The larger the second pressure value, the greater the access pressure value of the storage server throughout the day, and the smaller its reciprocal.

[0053] The smaller the access speed value, the faster the access speed is, and the faster the user can access resources. If the access speed weight is set to 0.3, the first pressure value weight is set to 0.5, and the second pressure value weight is set to 0.2, the evaluation value is , where S is the evaluation value, A, B, and C are the access speed, the first pressure value, and the second pressure value, respectively. The smaller the evaluation value, the smaller the overall access pressure of the storage server.

[0054] In this embodiment, the shared target obtains the teaching resource based on the access key, including the following steps: The second server and the third server generate a shared key and a one-dimensional initial matrix, generate a key sequence based on the shared key and the one-dimensional initial matrix, divide the key sequence into multiple subsequences, generate a storage address based on each subsequence, select one storage address as the target address, the second server and the third server generate a random key, encrypt the teaching resources based on the random key to obtain encrypted data, and store the encrypted data and the random key in different storage addresses, which are defined as the first address and the second address respectively.

[0055] Generating a storage address based on a subsequence includes the following steps: The numerical values ​​included in the subsequence are converted into ASCII characters, and then the ASCII characters are converted into basic characters according to the corresponding multinational character names, and the character sequence of the subsequence is generated based on the basic characters, and a conversion rule table is established, which includes the corresponding relationship between each character sequence and the storage address.

[0056] In this embodiment, for the convenience of introduction, the shared key is set to , the one-dimensional initial matrix is , then the key sequence is , then split according to fixed length, for example, with 2 elements as a subsequence, we can get subsequence 1 as [8, 8], subsequence 2 as [24, 0], if the last digit is insufficient, add 0, convert the elements of the subsequence into ASCII characters, then 8 is converted to BS, which is the backspace character, and Ctrl / H, then replace it with H, that is, 8 is converted to H, similarly, 24 is converted to X, 0 is converted to @, then the two subsequences are converted to HH and X@ respectively. Then set the address conversion rule table, which includes the correspondence between each character and the storage address, for example, HH corresponds to storage address 1, and X@ corresponds to storage address 2.

[0057] The random key generated by the second server and the third server is a random number. The encrypted data is obtained by XORing the random number with the teaching resource. In other embodiments, the encryption can also be performed using logical algorithms such as AND and OR. After the encryption is completed, the encrypted data is stored in the storage address 1, and the random number is stored in the storage address 2.

[0058] A target server is selected from the second server and the third server based on the access time of the shared target, and the shared target obtains the teaching resource after decrypting the encrypted data of the first address based on the random key of the second address in the target server.

[0059] When the shared target needs to access the teaching resources, it first accesses the second server. If the second server determines that the current access pressure is small, it uses itself as the target server. If the access pressure of the second server is large, it uses the third server as the target server. The shared user uses the previous method to generate subsequence 1 and subsequence 2 to determine the storage address where the teaching resources and random keys may be stored. Then, the encrypted data and random keys are taken out from the storage address, and the encrypted data is decrypted using the random key to obtain the teaching resources. If there are at least three storage addresses, after obtaining the encrypted data from one of the storage addresses, the keys are taken out from the remaining two storage addresses in turn to try to decrypt until the correct random key is obtained.

[0060] In this embodiment, after the shared target obtains the teaching resources, the target server regenerates the random key, uses the random key to re-encrypt the teaching resources and stores them in the first address, selects the third address from the storage address, and stores the regenerated random key in the third address.

[0061] Through this step, whenever a shared target accesses the teaching resources in the target server, the target server regenerates the random key, uses the newly generated random key to re-encrypt the teaching resources, obtains new encrypted data, stores the encrypted data in the original first address, selects a third address from the storage address, and stores the random key in the third address. If there are only two storage addresses, the random key is still stored in the second address.

[0062] like Figure 4 As shown, the present invention also provides an artificial intelligence-based practical teaching resource sharing system for the above method, the system comprising: The storage module includes a plurality of storage servers. A login management table is set in each storage server. The login management table records the historical login information of each user.

[0063] Upload module, when the user uploads teaching resources, the upload module selects a storage server as the first server according to the login management table. The first server selects the second server in the storage server based on the sharing target of the teaching resources and the login management table, and synchronizes the teaching resources to the second server.

[0064] The optimization module predicts the access pressure of multiple future time periods based on the second server's stored teaching resources and login management table combined with the prediction model; if there are multiple future time periods with access pressure greater than the first threshold, the optimization module selects a third server from the storage server and synchronizes part of the stored teaching resources to the third server.

[0065] The encryption module, the second server and the third server distribute access keys to the shared target based on the encryption module, and the shared target obtains the teaching resources based on the access keys.

[0066] It should be understood that the various technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for sharing practical teaching resources based on artificial intelligence, characterized in that: Arrange multiple storage servers, and set a login management table in each storage server, wherein the login management table records the historical login information of each user; When a user uploads teaching resources, one of the storage servers is selected as the first server according to the login management table; The first server selects a second server from the storage server based on the sharing target of the teaching resource and the login management table, and synchronizes the teaching resource to the second server; The second server predicts access pressures in multiple future time periods based on the teaching resources and the login management table stored in the second server and in combination with a prediction model; If there are multiple future time periods in which the access pressure is greater than the first threshold, selecting a third server from the storage servers, and synchronizing the stored part of the teaching resources to the third server; The second server and the third server distribute access keys to the shared target, and the shared target obtains the teaching resource based on the access keys.

2. The method according to claim 1, characterized in that Predicting the access pressure in the future time period comprises the following steps: Extracting the number of user visits to each teaching resource per hour from the login management table, generating a daily access sequence based on the number of visits, clustering the access sequence in units of years to obtain multiple clustering results, dividing each teaching resource into multiple access modes based on the clustering results, and taking the center of the clustering results as a representative sequence of the access mode; Acquire the teaching resources stored in the second server as resources to be analyzed, acquire the access pattern of each resource to be analyzed based on the date of the future time period, and acquire the representative sequence in the access pattern as a first prediction sequence; Obtain monthly user change, modify the first prediction sequence based on the monthly user change to obtain a second prediction sequence, merge the second prediction sequences of different resources to be analyzed to obtain a third prediction sequence, and use the number of visits per hour in the third prediction sequence as the access pressure in the future time period.

3. The method according to claim 2, characterized in that Clustering the access sequences comprises the following steps: Traversing and combining different access sequences to obtain multiple combination sequences, each combination sequence includes two access sequences, which are defined as a first sequence and a second sequence respectively, calculating a difference sequence based on the first sequence and the second sequence, the difference sequence being the absolute value of the difference in the access volume between the first sequence and the second sequence in the corresponding time period, and obtaining a first feature after processing the difference sequence based on a sliding window method; Respectively select the first N visits with the largest values ​​in the first sequence and the second sequence and the corresponding first time period and second time period, extract the third sequence corresponding to the first time period and the fourth sequence corresponding to the second time period from the difference sequence, calculate the average values ​​of the third sequence and the fourth sequence, and use them as the second feature and the third feature respectively; The access sequences of each month are clustered based on the first feature, the second feature, and the third feature.

4. The method according to claim 1, characterized in that: Selecting the third server from the storage servers comprises the following steps: Define the future time period in which the access pressure of the second server is greater than the first threshold as the migration time period, take the sum of the access pressures of the storage servers in the migration time period as the first pressure value, calculate the second pressure value of each storage server in the migration time period for the whole day, the login management table includes the user's access speed, and perform weighted summation of the access speed, the first pressure value and the second pressure value to obtain the evaluation value of the storage server, and select the storage server with the smallest evaluation value as the third server.

5. The method according to claim 1, characterized in that The shared target obtains the teaching resource based on the access key, comprising the following steps: The second server and the third server generate a shared key and a one-dimensional initial matrix, generate a key sequence based on the shared key and the one-dimensional initial matrix, divide the key sequence into multiple subsequences, generate a storage address based on each subsequence, select one storage address as a target address, the second server and the third server generate a random key, encrypt the teaching resource based on the random key to obtain encrypted data, and store the encrypted data and the random key in different storage addresses, which are defined as a first address and a second address respectively; A target server is selected from the second server and the third server based on the access time of the shared target, and the shared target obtains the teaching resource after decrypting the encrypted data of the first address based on the random key of the second address in the target server.

6. The method according to claim 5, characterized in that After the shared target obtains the teaching resource, the target server regenerates the random key, uses the random key to re-encrypt the teaching resource and stores it in the first address, selects a third address from the storage address, and stores the regenerated random key in the third address.

7. The method according to claim 5, characterized in that Generating the storage address based on the subsequence comprises the following steps: The numerical values ​​included in the subsequence are converted into ASCII characters, and then the ASCII characters are converted into basic characters according to the corresponding multinational character names, and the character sequence of the subsequence is generated based on the basic characters, and a conversion rule table is established, wherein the conversion rule table includes the corresponding relationship between each character sequence and the storage address.

8. The method according to claim 1, characterized in that If the teaching resource does not exist in the third server, a request is made to re-acquire the teaching resource from the second server.

9. The method according to claim 2, characterized in that: The access sequences are clustered using K-means or DBSCAN algorithm.

10. A practical teaching resource sharing system based on artificial intelligence, used to implement the method according to any one of claims 1 to 9, characterized in that: The storage module includes a plurality of storage servers, and a login management table is set in each of the storage servers, wherein the login management table records the historical login information of each user; An upload module, when a user uploads teaching resources, the upload module selects one of the storage servers as the first server according to the login management table, the first server selects a second server from the storage server based on the sharing target of the teaching resources and the login management table, and synchronizes the teaching resources to the second server; The optimization module, the second server predicts the access pressure of multiple future time periods based on the teaching resources and the login management table stored in the second server and the prediction model; if there are multiple future time periods in which the access pressure is greater than the first threshold, the optimization module selects a third server from the storage server and synchronizes part of the stored teaching resources to the third server; An encryption module, the second server and the third server distribute access keys to the shared target based on the encryption module, and the shared target obtains the teaching resource based on the access key.

Images