A cloud resource management system and method based on education platform

Abstract

The present invention relates to the field of resource management technology, and specifically to a cloud resource management system and method based on an education platform, comprising: sequentially capturing the time interval and the ratio of views between any two adjacent time nodes; constructing a browsing change curve based on the time interval and the ratio of views, and analyzing whether an abnormality occurs in the browsing status of each resource data; obtaining the storage node of each abnormal resource in an abnormal resource set, and forming a node relationship diagram based on the direction and distance of information transmission between each abnormal resource and each resource data; constructing a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record; extracting the resource selectivity model value of the corresponding user, and matching the response time of each abnormal resource to the corresponding user according to the size of the model value, thereby improving the security performance of the platform and the resource usage performance.

Description

Technical Field

[0001] The present invention relates to the technical field of resource management, and in particular to a cloud resource management system and method based on an education platform. Background Art

[0002] As educational resource websites continue to emerge across the country, how to provide rich information to the majority of users, how to strengthen the construction of information resource libraries, how to expand the scope of shared information resources and how to reasonably use educational resource libraries have become not only the main difficulties faced by schools that have built networks, but also one of the important indicators to test the level of modern education in schools.

[0003] The education platform can uniformly manage various educational resources, including course resources, teacher resources, equipment resources, etc., thereby improving the utilization efficiency of educational resources. At the same time, the education platform can also realize the centralized management and sharing of various educational resources through information technology, thus avoiding the problem of resource dispersion and repeated waste.

[0004] There are a variety of cloud resource data in the education platform. In order to better manage cloud resources, different types of resource data are generally stored in different storage spaces. However, when a large number of users enter the same storage space to browse the same resources at the same time within a certain period of time, it is easy to cause the storage space to fail to operate, the number of resources to fail to display, and even cause the education platform to freeze and paralyze. Therefore, how to improve the platform's security performance and resource usage performance based on users' historical browsing habits of resources has become an urgent problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide a cloud resource management system and method based on an education platform to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a cloud resource management method based on an education platform, comprising the following steps:

[0007] Step S100: Collect all resource data in the education platform to form a cloud resource set; obtain the cloud storage space of each resource data in the cloud resource set respectively, and form different storage nodes respectively; collect the information of all users authorized to log in to the education platform and the historical browsing records of each resource data by the corresponding users to form a user browsing set; mark the time node when each resource data in the cloud resource set is browsed by any user, and form a node information set for each resource data respectively;

[0008] Step S200: sequentially capturing the time interval between any two adjacent time nodes and the pageview ratio of each corresponding resource data according to the node information set; constructing a pageview change curve according to the time interval and pageview ratio, and analyzing whether the pageview status of each resource data is abnormal according to the pageview change curve;

[0009] The process of constructing the browsing change curve based on the time interval and the pageview ratio in the above steps is as follows: weighting the time interval and the pageview ratio, and constructing the browsing change curve with the pageview count as the horizontal axis and the weighted state as the vertical axis;

[0010] Step S300: Extract all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; obtain the storage nodes of each abnormal resource in the abnormal resource set, and construct a node relationship graph based on the direction and distance of information transmission between each abnormal resource and each resource data; capture the abnormal time nodes of each abnormal resource in the abnormal resource set, obtain the user information of each abnormal data browsing at the abnormal time node and the corresponding user's historical browsing record; and construct a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record;

[0011] Step S400: Obtain all user information captured by each abnormal resource at the corresponding abnormal time node, extract the resource selectivity model value of the corresponding user respectively, and match the response time of each abnormal resource to the corresponding user according to the size of the model value.

[0012] Furthermore, step S100 includes:

[0013] Step S110: Collect all resource data in the education platform to form a cloud resource set; obtain cloud storage space for each resource data in the cloud resource set to form different storage nodes; collect information on all users authorized to log in to the education platform and the corresponding users' historical browsing records of each resource data to form a user browsing set;

[0014] In the above steps, each storage node stores a type of resource data, so the cloud storage space of each resource data is different.

[0015] When browsing resource data, the cloud storage space entered is different, which will not affect the memory of other spaces. The use of distributed storage space realizes the dynamic management of resource data and improves the user's experience of using resource data.

[0016] The historical browsing records in the user browsing set in the above steps represent the cloud resource browsing data of the corresponding user in time series;

[0017] Step S120: Mark the time nodes when each resource data in the cloud resource set is browsed by any user, and form a node information set A={t1, t2,…, tn} for each resource data, where t1, t2,…, tn respectively represent the time nodes when each resource data is browsed for the 1st, 2nd,…, nth time.

[0018] Furthermore, step S200 includes:

[0019] Step S210: Sequentially capture the number of views xi of each resource data at any time node ti according to the node information set A; obtain the time interval ti-t(i-1) between any two adjacent time nodes, where t0=0 when i=1, and the corresponding ratio of the number of views x(i-1) / xi between any two adjacent time nodes; obtain the browsing status formula at any time node ti according to the time interval and the ratio of the number of views between any two adjacent time nodes: Hi=α1*[ti-t(i-1)]+α2*[x(i-1) / xi], where α1 represents the weight value of the time interval, and α2 represents the weight value of the ratio of the number of views;

[0020] The process of analyzing the browsing state formula at any time node ti in the above steps includes:

[0021] For example, the number of views {x1, x2, …, xn} of a certain resource data at each time node in the node information set A={t1, t2, …, tn} is obtained, where x1, x2, …, xn represent the number of users who browsed a certain resource data at time nodes t1, t2, …, tn respectively; the time intervals of t1, t2, t3, … are calculated in sequence as t1, t2-t1, t3-t2, …; the ratios of the views of x1, x2, x3, … are calculated in sequence as 0, x1 / x2, x2 / x3, …; at this time, the browsing status formula at any time node ti is obtained: Hi=α1*[ti-t(i-1)]+α2*[x(i-1) / xi];

[0022] Step S220: Obtain the browsing status formula Hi at any time node ti, then construct a two-dimensional rectangular coordinate system with the number of views i as the horizontal coordinate and the browsing status value Hi as the vertical coordinate to form a browsing change curve. The number of views i in the above step is composed of regular numbers such as 1, 2, 3, etc., indicating that the time node when the i-th resource data was browsed is ti;

[0023] Step S230: sequentially traverse the slope values ​​between adjacent coordinate points in the browsing change curve, and calculate the absolute value of the difference between the currently traversed slope value and all previously obtained slope values, thereby forming a difference value set B of the currently traversed slope values; capture the number of slope differences in the difference value set B that are greater than a threshold value β, and when s / |B| is greater than a proportion threshold value γ, it indicates that a browsing state abnormality has occurred at the time node corresponding to the difference value set B; where s represents the number of slope differences greater than the threshold value β, and |B| represents the number of slope differences in the difference value set B;

[0024] The purpose of the above steps is to analyze whether the browsing status value Hi changes abnormally as the number of browsing times i increases in the browsing change curve; when the proportion of the number of slope differences greater than the threshold β exceeds the threshold, it means that the browsing status value corresponding to the coordinate point is very different from that of other coordinate points, further indicating that the browsing status of the resource data at the corresponding time node is abnormal;

[0025] By weighting the number of views and time intervals of each resource data, and confirming the browsing status values ​​at different time nodes, it is beneficial to analyze the status anomalies of each resource data at each time node, and facilitate subsequent analysis of the causes of anomalies when different users browse each resource data.

[0026] Furthermore, step S300 includes:

[0027] Step S310: Extract all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; set any abnormal resource data in the abnormal resource set as target abnormal data, and obtain the storage node of each resource data respectively. Construct a two-dimensional plane coordinate system with the storage node of the target abnormal data as the origin; simulate the direction and distance from the origin to the storage node of each resource data based on the direction and distance of information transmission between the target abnormal data and each resource data to form a node relationship graph; wherein the storage node of each resource data in the node relationship graph is assigned a position coordinate, and together with the storage node of the target abnormal data, it forms a node relationship graph;

[0028] Step S320: capturing the abnormal time node of the target abnormal data according to the abnormal resource set, further obtaining user information of the user who browsed the target abnormal data at the abnormal time node and the historical browsing records of the corresponding user, forming a browsing record set C={c1,c2,…,cm}, where c1,c2,…,cm represent the historical browsing records of the 1st, 2nd,…,mth users who browsed the target abnormal data at the abnormal time node; obtaining the time node and the corresponding browsed resource data of any historical browsing record in the browsing record set C, recording the time interval between two adjacent time nodes in sequence, and assigning the time interval to the resource data corresponding to each subsequent time node, respectively forming a time length value P of each resource data in any historical browsing record, wherein the time length value of the first time node is 0;

[0029] Step S330: Capture the location coordinates of each resource data in any historical browsing record according to the node relationship diagram, calculate the distance value of the resource data between two adjacent time nodes in turn, and assign the distance value to the resource data corresponding to the next time node, respectively forming a distance length value Q of each resource data in any historical browsing record. When the distance length value is larger, it means that the span of the user browsing resource data is larger and there is no regularity; construct the resource selectivity model Yj=ρ*[∑ (j-1) P*Q] / (j-1), where j represents the number of time nodes and j>1, and ρ represents the weight coefficient of each resource data in any historical browsing record;

[0030] By analyzing the simulated distance between target anomaly data and each resource data, a node relationship graph is constructed. The relationship between each resource in the historical browsing history is analyzed based on the node relationship graph to confirm the distance length value. This is conducive to analyzing the regularity of user browsing resource data and facilitating the subsequent construction of the user's resource selectivity model.

[0031] In the above steps, when the time length value is larger and the distance length value is longer, it means that the user has a longer time interval for entering the education platform to browse resources and the cloud storage space spanned is larger. At this time, the user has greater selectivity for resources in the education platform.

[0032] Furthermore, step S400 includes:

[0033] Step S410: Obtain all user information captured by the target anomaly data at the corresponding anomaly time point to form a user set; obtain the resource selectivity model value of each user based on the user information in the user set; and further sort the browsing order of each user in the user set in descending order based on the size of the resource selectivity model value;

[0034] Step S420: Match the response time of target abnormal data according to the browsing order of each user in descending order;

[0035] The response time allocation rules for different resource data in the above steps are stored in the database.

[0036] Cloud resource management system, the system includes: data acquisition module, database, anomaly analysis module, model building module and response selection module;

[0037] All resource data in the education platform are collected through the data collection module to form a cloud resource set; cloud storage space for each resource data in the cloud resource set is obtained respectively to form different storage nodes; information of all users authorized to log in to the education platform and historical browsing records of each resource data by the corresponding users are collected to form a user browsing set; time nodes when each resource data in the cloud resource set is browsed by any user are marked to form node information sets for each resource data;

[0038] Distributed storage of all collected data is performed through the database;

[0039] The abnormality analysis module sequentially captures the time interval between any two adjacent time nodes and the pageview ratio of the corresponding resource data according to the node information set; constructs a browsing change curve based on the time interval and the pageview ratio, and analyzes whether the browsing status of each resource data is abnormal based on the browsing change curve;

[0040] The model building module extracts all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; obtains the storage nodes of each abnormal resource in the abnormal resource set, and constructs a node relationship diagram based on the direction and distance of information transmission between each abnormal resource and each resource data; captures the abnormal time nodes of each abnormal resource in the abnormal resource set, obtains the user information of each abnormal data browsing at the abnormal time node and the corresponding user's historical browsing record; and constructs a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record;

[0041] The response selection module obtains all user information captured by each abnormal resource at the corresponding abnormal time node, extracts the resource selectivity model value of the corresponding user, and matches the response time of each abnormal resource to the corresponding user according to the size of the model value.

[0042] Furthermore, the data collection module includes a resource collection unit, a browsing collection unit, and a node collection unit;

[0043] The resource collection unit is used to collect all resource data in the education platform; the browsing collection unit is used to collect the user information of all authorized users to log in to the education platform and the corresponding users' historical browsing records of each resource data; the node collection unit is used to mark the time node when each resource data in the cloud resource collection is browsed by any user.

[0044] Furthermore, the anomaly analysis module includes an information capture unit and an anomaly analysis unit;

[0045] The information capture unit is used to capture the time interval between any two adjacent time nodes and the browsing volume ratio of the corresponding resource data in sequence according to the node information set; the abnormality analysis unit is used to construct a browsing change curve based on the time interval and the browsing volume ratio and analyze whether there is any abnormality in the browsing status of each resource data based on the browsing change curve.

[0046] Furthermore, the model building module includes an anomaly extraction unit, a node analysis unit, and a model building unit;

[0047] The anomaly extraction unit is used to extract all resource data with abnormal browsing status and the corresponding time nodes where the anomalies occurred; the node analysis unit is used to respectively obtain the storage nodes of each abnormal resource in the abnormal resource set, and form a node relationship diagram with the direction and distance of information transmission between each abnormal resource and each resource data; the model construction unit is used to capture the abnormal time nodes of each abnormal resource in the abnormal resource set, obtain the user information of browsing each abnormal data at the abnormal time node and the historical browsing records of the corresponding user; and then construct a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record.

[0048] Furthermore, the response selection module includes a user ranking unit and a resource response unit;

[0049] The user sorting unit is used to obtain all user information captured by each abnormal resource at the corresponding abnormal time node, and then extract the resource selectivity model value of the corresponding user respectively, and sort them according to the size of the model value; the resource response unit is used to match the response time of each abnormal resource to the corresponding user according to the size of the model value.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention realizes dynamic management of resource data and improves users' experience of using resource data by utilizing distributed storage space; by weighting the number of views and time intervals of each resource data, the browsing status values ​​of different time nodes are confirmed, which is conducive to status anomaly analysis of each resource data at each time node, and facilitates subsequent analysis of the causes of anomalies when different users browse each resource data; by analyzing the simulated distance between target anomaly data and each resource data to construct a node relationship graph, and analyzing the relationship between each resource in the historical browsing record based on the node relationship graph, confirming the distance length value, it is conducive to analyzing the regularity of users browsing resource data and facilitates the subsequent construction of the user's resource selectivity model. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 This is a structural diagram of a cloud resource management system based on an education platform of the present invention;

[0054] Figure 2 This is a flow chart of a cloud resource management method based on an education platform of the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] See also Figure 1 ,The present invention provides a technical solution: a cloud resource management system, the system includes: a data acquisition module, a database, an anomaly analysis module, a model building module, and a response selection module;

[0057] All resource data in the education platform are collected through the data collection module to form a cloud resource set; cloud storage space for each resource data in the cloud resource set is obtained respectively to form different storage nodes; information of all users authorized to log in to the education platform and historical browsing records of each resource data by the corresponding users are collected to form a user browsing set; time nodes when each resource data in the cloud resource set is browsed by any user are marked to form node information sets for each resource data;

[0058] The data collection module includes resource collection unit, browsing collection unit and node collection unit;

[0059] The resource collection unit is used to collect all resource data in the education platform; the browsing collection unit is used to collect the user information of all authorized users to log in to the education platform and the corresponding users' historical browsing records of each resource data; the node collection unit is used to mark the time node when each resource data in the cloud resource collection is browsed by any user.

[0060] Distributed storage of all collected data is performed through the database;

[0061] The abnormality analysis module sequentially captures the time interval between any two adjacent time nodes and the pageview ratio of the corresponding resource data according to the node information set; constructs a browsing change curve based on the time interval and the pageview ratio, and analyzes whether the browsing status of each resource data is abnormal based on the browsing change curve;

[0062] The abnormality analysis module includes an information capture unit and an abnormality analysis unit;

[0063] The information capture unit is used to capture the time interval between any two adjacent time nodes and the browsing volume ratio of the corresponding resource data in sequence according to the node information set; the abnormality analysis unit is used to construct a browsing change curve based on the time interval and the browsing volume ratio and analyze whether there is any abnormality in the browsing status of each resource data based on the browsing change curve.

[0064] The model building module extracts all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; obtains the storage nodes of each abnormal resource in the abnormal resource set, and constructs a node relationship diagram based on the direction and distance of information transmission between each abnormal resource and each resource data; captures the abnormal time nodes of each abnormal resource in the abnormal resource set, obtains the user information of each abnormal data browsing at the abnormal time node and the corresponding user's historical browsing record; and constructs a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record;

[0065] The model building module includes an anomaly extraction unit, a node analysis unit and a model building unit;

[0066] The anomaly extraction unit is used to extract all resource data with abnormal browsing status and the corresponding time nodes where the anomalies occurred; the node analysis unit is used to respectively obtain the storage nodes of each abnormal resource in the abnormal resource set, and form a node relationship diagram with the direction and distance of information transmission between each abnormal resource and each resource data; the model construction unit is used to capture the abnormal time nodes of each abnormal resource in the abnormal resource set, obtain the user information of browsing each abnormal data at the abnormal time node and the historical browsing records of the corresponding user; and then construct a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record.

[0067] The response selection module obtains all user information captured by each abnormal resource at the corresponding abnormal time node, extracts the resource selectivity model value of the corresponding user, and matches the response time of each abnormal resource to the corresponding user according to the size of the model value.

[0068] The response selection module includes a user ranking unit and a resource response unit;

[0069] The user sorting unit is used to obtain all user information captured by each abnormal resource at the corresponding abnormal time node, and then extract the resource selectivity model value of the corresponding user respectively, and sort them according to the size of the model value; the resource response unit is used to match the response time of each abnormal resource to the corresponding user according to the size of the model value.

[0070] See also Figure 2 The present invention provides a technical solution: a cloud resource management method based on an education platform, comprising the following steps:

[0071] Step S100: Collect all resource data in the education platform to form a cloud resource set; obtain the cloud storage space of each resource data in the cloud resource set respectively, and form different storage nodes respectively; collect the information of all users authorized to log in to the education platform and the historical browsing records of each resource data by the corresponding users to form a user browsing set; mark the time node when each resource data in the cloud resource set is browsed by any user, and form a node information set for each resource data respectively;

[0072] Step S100 includes:

[0073] Step S110: Collect all resource data in the education platform to form a cloud resource set; obtain cloud storage space for each resource data in the cloud resource set to form different storage nodes; collect information on all users authorized to log in to the education platform and the corresponding users' historical browsing records of each resource data to form a user browsing set;

[0074] In the above steps, each storage node stores a type of resource data. Therefore, the cloud storage space of each resource data is different. When browsing each resource data, the cloud storage space entered is different, which will not affect the memory of other spaces.

[0075] The historical browsing records in the user browsing set in the above steps represent the cloud resource browsing data of the corresponding user in time series;

[0076] Step S120: Mark the time nodes when each resource data in the cloud resource set is browsed by any user, and form a node information set A={t1, t2,…, tn} for each resource data, where t1, t2,…, tn respectively represent the time nodes when each resource data is browsed for the 1st, 2nd,…, nth time.

[0077] Step S200: sequentially capturing the time interval between any two adjacent time nodes and the pageview ratio of each corresponding resource data according to the node information set; constructing a pageview change curve according to the time interval and pageview ratio, and analyzing whether the pageview status of each resource data is abnormal according to the pageview change curve;

[0078] The process of constructing the browsing change curve based on the time interval and the pageview ratio in the above steps is as follows: weighting the time interval and the pageview ratio, and constructing the browsing change curve with the pageview count as the horizontal axis and the weighted state as the vertical axis;

[0079] Step S200 includes:

[0080] Step S210: Sequentially capture the number of views xi of each resource data at any time node ti according to the node information set A; obtain the time interval ti-t(i-1) between any two adjacent time nodes, where t0=0 when i=1, and the corresponding ratio of the number of views x(i-1) / xi between any two adjacent time nodes; obtain the browsing status formula at any time node ti according to the time interval and the ratio of the number of views between any two adjacent time nodes: Hi=α1*[ti-t(i-1)]+α2*[x(i-1) / xi], where α1 represents the weight value of the time interval, and α2 represents the weight value of the ratio of the number of views;

[0081] The process of analyzing the browsing state formula at any time node ti in the above steps includes:

[0082] For example, the number of views {x1, x2, x3, x4} of a certain resource data at each time node in the node information set A={t1, t2, t3, t4} is obtained, where x1, x2, x3, x4 represent the number of users who browsed a certain resource data at time nodes t1, t2, t3, t4 respectively; the time intervals of t1, t2, t3, t4 are calculated in sequence as t1=1h, t2-t1=30h, t3-t2=10h, t4-t3=100h respectively; the ratio of the views of x1, x2, x3, x4 is calculated in sequence as 0, x1 / x2=30, x2 / x3=10, x3 / x4=500; at this time, the browsing status formula at any time node ti is obtained: Hi=α1*[ti-t(i-1)]+α2*[x(i-1) / xi];

[0083] Step S220: Obtain the browsing status formula Hi at any time node ti, and construct a two-dimensional rectangular coordinate system with the number of views i as the horizontal coordinate and the browsing status value Hi as the vertical coordinate to form a browsing change curve;

[0084] Step S230: sequentially traverse the slope values ​​between adjacent coordinate points in the browsing change curve, and calculate the absolute value of the difference between the currently traversed slope value and all previously obtained slope values, thereby forming a difference value set B of the currently traversed slope values; capture the number of slope differences in the difference value set B that are greater than a threshold value β, and when s / |B| is greater than a proportion threshold value γ, it indicates that a browsing state abnormality has occurred at the time node corresponding to the difference value set B; where s represents the number of slope differences greater than the threshold value β, and |B| represents the number of slope differences in the difference value set B;

[0085] For example, if the coordinates in the browsing change curve are {(1, H1), (2, H2), (3, H3), (4, H4)}, the slope difference set captured when the number of views is 4 is {|H1|, |H2-H1|, |H3-H2|, |H4-H3|}. When the number of slope differences greater than 4 exceeds 3 / 4, it means that the browsing status of the resource data at the corresponding time node t4 is abnormal;

[0086] The purpose of the above steps is to analyze whether the browsing status value Hi changes abnormally as the number of browsing times i increases in the browsing change curve; when the proportion of the number of slope differences greater than the threshold β exceeds the threshold, it means that the browsing status value corresponding to the coordinate point is very different from that of other coordinate points, further indicating that the browsing status of the resource data at the corresponding time node is abnormal.

[0087] Step S300: Extract all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; obtain the storage nodes of each abnormal resource in the abnormal resource set, and construct a node relationship graph based on the direction and distance of information transmission between each abnormal resource and each resource data; capture the abnormal time nodes of each abnormal resource in the abnormal resource set, obtain the user information of each abnormal data browsing at the abnormal time node and the corresponding user's historical browsing record; and construct a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record;

[0088] Step S300 includes:

[0089] Step S310: Extract all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; set any abnormal resource data in the abnormal resource set as target abnormal data, and obtain the storage node of each resource data respectively. Construct a two-dimensional plane coordinate system with the storage node of the target abnormal data as the origin; simulate the direction and distance from the origin to the storage node of each resource data based on the direction and distance of information transmission between the target abnormal data and each resource data to form a node relationship graph; wherein the storage node of each resource data in the node relationship graph is assigned a position coordinate, and together with the storage node of the target abnormal data, it forms a node relationship graph;

[0090] Step S320: capturing the abnormal time node of the target abnormal data according to the abnormal resource set, further obtaining user information of the user who browsed the target abnormal data at the abnormal time node and the historical browsing record of the corresponding user, forming a browsing record set C={c1,c2,…,c500}, where c1,c2,…,c500 represent the historical browsing records of the 1st, 2nd,…,500th users who browsed the target abnormal data at the abnormal time node; obtaining the time node of any historical browsing record and the corresponding browsed resource data in the browsing record set C, recording the time interval between two adjacent time nodes in sequence, and assigning the time interval to the resource data corresponding to each subsequent time node, respectively forming a time length value P of each resource data in any historical browsing record, wherein the time length value of the first time node is 0;

[0091] Step S330: Capture the location coordinates of each resource data in any historical browsing record according to the node relationship diagram, calculate the distance value of the resource data between two adjacent time nodes in turn, and assign the distance value to the resource data corresponding to the next time node, respectively forming a distance length value Q of each resource data in any historical browsing record. When the distance length value is larger, it means that the span of the user browsing resource data is larger and there is no regularity; construct the resource selectivity model Yj=ρ*[∑ (j-1) P*Q] / (j-1), where j represents the number of time nodes and j>1, and ρ represents the weight coefficient of each resource data in any historical browsing record;

[0092] In the above steps, when the time length value is larger and the distance length value is longer, it means that the user has a longer time interval for entering the education platform to browse resources and the cloud storage space spanned is larger. At this time, the user has greater selectivity for resources in the education platform.

[0093] Step S400: Obtain all user information captured by each abnormal resource at the corresponding abnormal time node, extract the resource selectivity model value of the corresponding user respectively, and match the response time of each abnormal resource to the corresponding user according to the size of the model value.

[0094] Step S400 includes:

[0095] Step S410: Obtain all user information captured by the target anomaly data at the corresponding anomaly time point to form a user set; obtain the resource selectivity model value of each user based on the user information in the user set; and further sort the browsing order of each user in the user set in descending order based on the size of the resource selectivity model value;

[0096] Step S420: Match the response time of target abnormal data according to the browsing order of each user in descending order;

[0097] The response time allocation rules for different resource data in the above steps are stored in the database.

[0098] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A cloud resource management method based on an education platform, characterized by: The following steps are involved: Step S100: Collect all resource data in the education platform to form a cloud resource set; obtain the cloud storage space of each resource data in the cloud resource set respectively, and form different storage nodes respectively; collect the information of all users authorized to log in to the education platform and the historical browsing records of each resource data by the corresponding users to form a user browsing set; mark the time node when each resource data in the cloud resource set is browsed by any user, and form a node information set for each resource data respectively; Step S200: sequentially capturing the time interval between any two adjacent time nodes and the pageview ratio of each corresponding resource data according to the node information set; constructing a pageview change curve according to the time interval and pageview ratio, and analyzing whether the pageview status of each resource data is abnormal according to the pageview change curve; Step S300: Extract all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; obtain the storage nodes of each abnormal resource in the abnormal resource set, and construct a node relationship graph based on the direction and distance of information transmission between each abnormal resource and each resource data; capture the abnormal time nodes of each abnormal resource in the abnormal resource set, obtain the user information of each abnormal data browsing at the abnormal time node and the corresponding user's historical browsing record; and construct a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record; Step S400: Obtain all user information captured by each abnormal resource at the corresponding abnormal time node, extract the resource selectivity model value of the corresponding user respectively, and match the response time of each abnormal resource to the corresponding user according to the size of the model value.

2. The cloud resource management method based on an education platform according to claim 1, characterized in that: The step S100 includes: Step S110: Collect all resource data in the education platform to form a cloud resource set; obtain cloud storage space for each resource data in the cloud resource set to form different storage nodes; collect information on all users authorized to log in to the education platform and the corresponding users' historical browsing records of each resource data to form a user browsing set; Step S120: Mark the time nodes when each resource data in the cloud resource set is browsed by any user, and form a node information set A={t1, t2,…, tn} for each resource data, where t1, t2,…, tn respectively represent the time nodes when each resource data is browsed for the 1st, 2nd,…, nth time.

3. The cloud resource management method based on an education platform according to claim 2, characterized in that: The step S200 includes: Step S210: Sequentially capture the number of views xi of each resource data at any time node ti according to the node information set A; obtain the time interval ti-t(i-1) between any two adjacent time nodes, where t0=0 when i=1, and the corresponding ratio of the number of views x(i-1) / xi between any two adjacent time nodes; obtain the browsing status formula at any time node ti according to the time interval and the ratio of the number of views between any two adjacent time nodes: Hi=α1*[ti-t(i-1)]+α2*[x(i-1) / xi], where α1 represents the weight value of the time interval, and α2 represents the weight value of the ratio of the number of views; Step S220: Obtain the browsing status formula Hi at any time node ti, and construct a two-dimensional rectangular coordinate system with the number of views i as the horizontal coordinate and the browsing status value Hi as the vertical coordinate to form a browsing change curve; Step S230: sequentially traverse the slope values ​​between adjacent coordinate points in the browsing change curve, and calculate the absolute value of the difference between the currently traversed slope value and all the slope values ​​obtained previously, thereby forming a difference set B of the currently traversed slope values; capture the number of slope differences in the difference set B that are greater than the threshold β, and when s / |B| is greater than the proportion threshold γ, it indicates that the browsing status of the time node corresponding to the difference set B is abnormal; where s represents the number of slope differences greater than the threshold β, and |B| represents the number of slope differences in the difference set B.

4. The cloud resource management method based on an education platform according to claim 3, characterized in that: The step S300 includes: Step S310: Extract all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; set any abnormal resource data in the abnormal resource set as target abnormal data, and obtain the storage node of each resource data respectively. Construct a two-dimensional plane coordinate system with the storage node of the target abnormal data as the origin; simulate the direction and distance from the origin to the storage node of each resource data based on the direction and distance of information transmission between the target abnormal data and each resource data to form a node relationship graph; wherein the storage node of each resource data in the node relationship graph is assigned a position coordinate, and together with the storage node of the target abnormal data, it forms a node relationship graph; Step S320: capturing the abnormal time node of the target abnormal data according to the abnormal resource set, further obtaining user information of the user who browsed the target abnormal data at the abnormal time node and the historical browsing records of the corresponding user, forming a browsing record set C={c1,c2,…,cm}, where c1,c2,…,cm represent the historical browsing records of the 1st, 2nd,…,mth users who browsed the target abnormal data at the abnormal time node; obtaining the time node and the corresponding browsed resource data of any historical browsing record in the browsing record set C, recording the time interval between two adjacent time nodes in sequence, and assigning the time interval to the resource data corresponding to each subsequent time node, respectively forming a time length value P of each resource data in any historical browsing record; Step S330: Capture the location coordinates of each resource data in any historical browsing record according to the node relationship graph, calculate the distance value of the resource data between two adjacent time nodes in sequence, and assign the distance value to the resource data corresponding to the next time node, respectively forming the distance length value Q of each resource data in any historical browsing record; construct the resource selectivity model Yj=ρ*[∑ (j-1) P*Q] / (j-1), where j represents the number of time nodes and j>1, and ρ represents the weight coefficient of each resource data in any historical browsing record.

5. The cloud resource management method based on an education platform according to claim 4, characterized in that: The step S400 includes: Step S410: Obtain all user information captured by the target anomaly data at the corresponding anomaly time point to form a user set; obtain the resource selectivity model value of each user based on the user information in the user set; and further sort the browsing order of each user in the user set in descending order based on the size of the resource selectivity model value; Step S420: Match the response time of the target abnormal data according to the browsing order of each user in descending order.

6. A cloud resource management system for implementing the cloud resource management method based on an education platform according to any one of claims 1 to 5, characterized in that: The system includes: a data acquisition module, a database, an anomaly analysis module, a model building module and a response selection module; All resource data in the education platform are collected through the data collection module to form a cloud resource set; cloud storage space for each resource data in the cloud resource set is obtained respectively to form different storage nodes; information of all users authorized to log in to the education platform and historical browsing records of each resource data by the corresponding users are collected to form a user browsing set; time nodes when each resource data in the cloud resource set is browsed by any user are marked to form node information sets for each resource data; Distributed storage of all collected data is performed through the database; The abnormality analysis module sequentially captures the time interval between any two adjacent time nodes and the browsing volume ratio of the corresponding resource data according to the node information set; constructs a browsing change curve based on the time interval and the browsing volume ratio, and analyzes whether the browsing status of each resource data is abnormal based on the browsing change curve; The model building module extracts all resource data with abnormal browsing status and the corresponding time nodes of the abnormality to form abnormal resource sets; obtains the storage nodes of each abnormal resource in the abnormal resource set, and constructs a node relationship diagram based on the direction and distance of information transmission between each abnormal resource and each resource data; captures the abnormal time nodes of each abnormal resource in the abnormal resource set, obtains the user information of each abnormal data browsing at the abnormal time node and the corresponding user's historical browsing record; and constructs a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record; The response selection module obtains all user information captured by each abnormal resource at the corresponding abnormal time node, extracts the resource selectivity model value of the corresponding user, and matches the response time of each abnormal resource to the corresponding user according to the size of the model value.

7. The cloud resource management system according to claim 6, wherein: The data acquisition module includes a resource acquisition unit, a browsing acquisition unit and a node acquisition unit; The resource collection unit is used to collect all resource data in the education platform; the browsing collection unit is used to collect the user information of all authorized users to log in to the education platform and the corresponding users' historical browsing records of each resource data; the node collection unit is used to mark the time node when each resource data in the cloud resource collection is browsed by any user.

8. The cloud resource management system according to claim 6, wherein: The abnormality analysis module includes an information capture unit and an abnormality analysis unit; The information capture unit is used to capture the time interval between any two adjacent time nodes and the browsing volume ratio of the corresponding resource data in sequence according to the node information set; the abnormality analysis unit is used to construct a browsing change curve based on the time interval and the browsing volume ratio and analyze whether there is any abnormality in the browsing status of each resource data based on the browsing change curve.

9. The cloud resource management system according to claim 6, wherein: The model building module includes an anomaly extraction unit, a node analysis unit and a model building unit; The anomaly extraction unit is used to extract all resource data with abnormal browsing status and the corresponding time nodes where the anomalies occurred; the node analysis unit is used to respectively obtain the storage nodes of each abnormal resource in the abnormal resource set, and form a node relationship diagram with the direction and distance of information transmission between each abnormal resource and each resource data; the model construction unit is used to capture the abnormal time nodes of each abnormal resource in the abnormal resource set, obtain the user information of browsing each abnormal data at the abnormal time node and the historical browsing records of the corresponding user; and then construct a resource selectivity model based on the time length value and distance length value of the resource data corresponding to each time node in each historical browsing record.

10. The cloud resource management system according to claim 6, wherein: The response selection module includes a user sorting unit and a resource response unit; The user sorting unit is used to obtain all user information captured by each abnormal resource at the corresponding abnormal time node, and then extract the resource selectivity model value of the corresponding user respectively, and sort them according to the size of the model value; the resource response unit is used to match the response time of each abnormal resource to the corresponding user according to the size of the model value.

Images