A data management system and method for a digital education platform

Abstract

The present invention discloses a data management system and method for a digital education platform, which relates to the technical field of education platform data management, and comprises the following steps: collecting relevant access data of online courses of the education platform and performing data cleaning processing; then calculating a first indicator of the online courses and establishing an academic year course access prediction model; using the academic year course access prediction model to predict the access indicator of the online courses in each academic year to obtain first access indicator data, and performing first indicator processing to obtain course data to be compressed; then dynamically decompressing the online courses; the present invention is used to solve the problem that the existing education platform data management technology cannot, when storing online courses of the education platform, accurately and dynamically decompress the online courses according to the access situation of the online courses in the historical academic year without affecting the normal use of the online courses, so as to save storage space of the education platform database.

Description

Technical Field

[0001] The present invention relates to the technical field of education platform data management, and in particular to a data management system and method for a digital education platform. Background Art

[0002] Education platform data management technology refers to a series of technical means and methods used to collect, store, organize, process, analyze and protect education-related data in the education platform environment. Among them, data storage of the education platform refers to the use of various technical means and equipment to efficiently, safely and reliably store and manage the massive data generated by the education platform.

[0003] Existing education platform data management technologies mostly use a relatively fixed storage method when storing online courses on the education platform, that is, course resources are stored in the original format after uploading, and are not dynamically adjusted according to the actual usage of the course; this results in some unpopular courses or low-activity courses occupying a large amount of storage space for a long time, and these spaces are not fully utilized most of the time; for example, some highly professional niche courses may only be visited by a few users in a specific period, but they occupy the same storage resources as popular courses, resulting in idle waste of storage resources; for example, the patent application with publication number CN118760686A discloses a data storage method and system for a smart education platform. Although this solution can save storage space by removing redundant learning materials, it is not suitable for those who occupy a large amount of storage space for a long time. Storage space is saved, but non-redundant but unpopular courses cannot be processed; and in order to save storage space, some education platforms may over-compress courses; although this reduces storage costs to a certain extent, it will have a negative impact on user experience; over-compressed course videos may have problems such as image quality degradation and audio distortion, and when users access them, the decompression process may be more complicated, resulting in a long course loading time; for example, some high-definition experimental demonstration courses, if over-compressed, may prevent students from clearly observing the experimental details, affecting learning outcomes; therefore, when storing online courses on the education platform, the existing education platform data management technology cannot accurately and dynamically decompress online courses based on the access situation of the online courses in the previous academic year without affecting the normal use of the online courses, so as to save storage space for the education platform database. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the prior art to a certain extent, by collecting relevant access data of online courses on an education platform and performing data cleaning processing; then calculating the first indicator of the online courses and establishing an academic year course access prediction model; using the academic year course access prediction model to predict the access indicator of the online courses for each academic year, and performing first indicator processing to obtain course data to be compressed; then dynamically decompressing the online courses; so as to solve the problem that the existing education platform data management technology cannot, when storing online courses on the education platform, accurately and dynamically decompress the online courses based on the access situation of the online courses in the historical academic year without affecting the normal use of the online courses, so as to save storage space of the education platform database.

[0005] To achieve the above objectives, in a first aspect, the present application provides a data management system for a digital education platform, comprising a data acquisition module, a model building module, a prediction processing module, and a compression management module;

[0006] The data acquisition module includes a data acquisition unit and a data cleaning unit. The data acquisition unit is used to collect relevant access data of the online courses of the education platform, which is marked as first access data. The data cleaning unit is used to perform cleaning and screening processing to obtain second access data.

[0007] The model building module calculates a first indicator of the online course based on the second access data and establishes a course access prediction model for the academic year;

[0008] The prediction processing module includes an indicator prediction unit and an indicator processing unit. The indicator prediction unit uses the academic year course access prediction model to predict the access index of the online course in each academic year to obtain first access index data. The indicator processing unit is used to perform first index processing to obtain the course data to be compressed.

[0009] The compression management module dynamically decompresses the online course based on the course data to be compressed and the first access data.

[0010] Furthermore, the data collection unit is configured with a data collection strategy, which includes:

[0011] Obtain the total number of visits and total visit duration of all online courses on the education platform each day, and calculate the average visit duration of all online courses each day, which is recorded as the first average duration;

[0012] For any online course on the education platform, obtain the corresponding online course's daily access data, including: the total number of people who visit the corresponding online course each day, the total number of visits to the corresponding online course each day, the average duration of each visit, and the amount of storage space occupied by the corresponding online course each day;

[0013] Repeatedly obtain the daily relevant access data and the first average duration of all online courses on the education platform, record the acquisition date, classify and store them according to the corresponding online courses, and mark them as the first access data.

[0014] Furthermore, the data cleaning unit is configured with a data cleaning strategy, which includes:

[0015] Based on the first access data, the first average duration in the first access data is sorted according to the acquisition date and recorded as a first duration sequence, and the total number of people who visited the online course, the total number of times the online course was visited, the average duration of each visit, and the size of the storage space occupied in the access data related to any online course in the first access data are sorted according to the acquisition date and recorded in order as a number sequence, a number sequence, a second duration sequence, and a course size sequence;

[0016] The first duration sequence, number of people sequence, number of times sequence, second duration sequence and course size sequence are cleaned and processed respectively, and the second access data is obtained after completion;

[0017] Data cleaning processing includes: sorting the corresponding data according to the acquisition date as a time data sequence, and recording any data in the time data sequence as A i , where i represents the sequence number in the time data series, if A i+n Exists; then based on the time data series, extract A i to A i+n , recorded as the first sequence, and extract A i to A i-n , recorded as the second sequence, calculate the mean and standard deviation of the first sequence, record them as B0 and B1 respectively, and calculate the mean and standard deviation of the second sequence, record them as C0 and C1 respectively, judge A i Does it satisfy |A at the same time? i -B0|>3*B1 and |A i -C0|>3*C1, if both are satisfied, mark A i It is abnormal data and is replaced, otherwise it is marked as A i is normal data; if A i+n If it does not exist, mark A i For normal data; repeatedly mark all data in the time data series;

[0018] The replacement process includes: for abnormal data A i , in the corresponding time data series, obtain two distances A i The most recent normal data are recorded as RA i and LAi ; Calculate A by the first substitution formula i The replacement value TA i , the first replacement formula is as follows: TA i =q1*RA i +q2*LA i , where q1 and q2 are weight coefficients, q1+q2=1, and the value range of q1 and q2 is [0, 1]; and using TA i Replace A i .

[0019] Furthermore, the model building module is configured with a model building strategy, which includes:

[0020] For any online course, a first indicator of the corresponding online course is calculated daily based on the second access data, where the first indicator includes a course activity indicator and a course consumption ratio indicator;

[0021] Calculating the course activity index includes: calculating the course activity index of the online course on the day using the course activity formula. The course activity formula is as follows: Where DC represents the course activity index of the online course on that day, E represents the total number of visits to the online course on that day, T represents the average visit duration of each visit to the online course on that day, V represents the average first visit duration of the day, and F represents the total number of people who visited the online course on that day;

[0022] Calculating the course consumption ratio indicator includes: calculating the course consumption ratio indicator of the online course on that day through the resource consumption calculation formula. The course consumption ratio indicator formula is as follows: REC represents the course consumption ratio of the online course on that day, and H represents the amount of storage space occupied by the online course on that day;

[0023] Repeat the calculation of the first indicator for all online courses every day and mark it as the third access data.

[0024] Furthermore, the model building strategy also includes:

[0025] Normalizing the third access data according to data type, scaling all data sizes in the third access data to [0, 1], and obtaining fourth access data upon completion;

[0026] An initial access prediction model is constructed based on a long short-term memory network. The initial access prediction model includes an input layer, an LSTM processing layer, a dropout layer, and a fully connected layer. The LSTM processing layer includes x1 LSTM layers.

[0027] Set the learning rate of model training to x2, the batch size to x3, and the number of training rounds to x4; use the fourth visit data to train the initial visit prediction model, and after completion, obtain the academic year course visit prediction model.

[0028] Furthermore, the indicator prediction unit is configured with an indicator prediction strategy, which includes:

[0029] For any online course on the education platform, obtain the daily course activity index and course consumption ratio index of the corresponding online course for k1 academic years; record them as the first sample data, normalize the first sample data, and input them into the academic year course access prediction model to obtain the daily course activity index and course consumption ratio index of the corresponding online course in the next academic year, which are recorded as the first predicted data of the academic year.

[0030] Furthermore, the indicator processing unit is configured with an indicator processing strategy, which includes:

[0031] For the first forecast data of the academic year for any online course on the education platform, obtain the daily course activity index and course consumption ratio index in the corresponding first forecast data of the academic year, and calculate the daily decompression index using the decompression index formula. The decompression index formula is as follows: DR = q3*DC + q4*RC, where DR is the decompression index, q3 and q4 are weight coefficients, q3+q4=1, and the value range of q3 and q4 is [0, 1]. Repeat the calculation of the daily decompression index in the corresponding first forecast data of the academic year to obtain the second forecast data.

[0032] Set the decompression threshold to DR0, and judge the daily decompression index in the second predicted data. If the decompression index of the day is less than or equal to DR0, mark the day as a compression day, otherwise mark the day as a decompression day. After completion, obtain the third predicted data;

[0033] Repeatedly obtain the third prediction data of all online courses and mark them as course data to be compressed.

[0034] Furthermore, the compression management module is configured with a compression management strategy, which includes:

[0035] Based on the course data to be compressed, the third predicted data of any online course is divided according to the month time, and any month is judged and marked, including: if the number of compressed days in the month is greater than or equal to k2, then the month is marked as a compressed month; if the number of compressed days in the month is less than or equal to k3, then the month is marked as a decompression month; if the number of compressed days in the month is less than k2 and greater than k3, then the month is marked as a fluctuating month. After completion, the compression management data of the corresponding online course is obtained.

[0036] Furthermore, the compression management strategy also includes:

[0037] For any online course on the education platform, decompression management is performed according to the corresponding compression management data, including:

[0038] If the online course is in a compressed month, the online course will be compressed;

[0039] If the online course is in the decompression month, the online course will be decompressed;

[0040] If the online course is in a fluctuating month, if the decompression index of the online course for 4 consecutive days is less than or equal to the decompression threshold, the online course will be compressed; if the average value of the decompression index of the online course for 4 consecutive days is greater than or equal to the decompression threshold, the online course will be decompressed.

[0041] In a second aspect, the present application provides a data management method for a digital education platform, comprising the following steps:

[0042] Collect relevant access data of online courses on the education platform, mark it as first access data, and perform data cleaning to obtain second access data;

[0043] Calculating the first index of the online course based on the second access data and establishing a course access prediction model for the academic year;

[0044] Using the academic year course access prediction model to predict the access index of the online course in each academic year, obtaining first access index data, and performing first index processing to obtain the course data to be compressed;

[0045] Dynamic decompression management is performed on the online course based on the course data to be compressed and the first access data.

[0046] The beneficial effects of the present invention are as follows: the present invention collects relevant access data of online courses on an education platform, marks it as first access data, and performs data cleaning processing to obtain second access data; calculates a first index of the online course based on the second access data, and establishes a school year course access prediction model; uses the school year course access prediction model to predict the access index of the online course for each school year to obtain first access index data, and performs first index processing to obtain course data to be compressed; dynamically decompresses the online course based on the course data to be compressed and the first access data; and can accurately perform dynamic decompression on the online course without affecting the normal use of the online course, thereby saving storage space of the education platform database;

[0047] The present invention dynamically decompresses the online courses of the education platform, which has the advantage that it can compress the semesters and holidays when the online courses are not in use, thereby releasing a large amount of storage space and reducing the storage cost of the education platform; by calculating the course activity index and course consumption ratio index of the online courses, it can provide the education platform with accurate quantitative information on the course usage and resource utilization of the online courses, thereby improving the accuracy of decompression management of the online courses; the academic year course access prediction model predicts the access index of the online courses, which has the advantage that it can understand the usage and resource demand of the online courses in advance, so that the education platform can plan in advance and achieve more accurate data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a principle block diagram of the system of the present invention;

[0049] Figure 2 is a flow chart of the steps of the method of the present invention;

[0050] Figure 3 This is a flow chart of the indicator processing strategy of the present invention;

[0051] Figure 4 This is a decompression management flow chart of the present invention;

[0052] Figure 5 Schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0053] 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.

[0054] Example 1, please refer to Figure 1 As shown, the present application provides a data management system for a digital education platform, including a data acquisition module, a model building module, a prediction processing module, and a compression management module;

[0055] The data acquisition module includes a data acquisition unit and a data cleaning unit. The data acquisition unit is used to collect relevant access data of the online courses of the education platform, which is marked as first access data. The data cleaning unit is used to perform cleaning and screening processing to obtain second access data.

[0056] The data collection unit is configured with a data collection strategy, which includes: obtaining the total number of visits and total visit duration of all online courses on the education platform every day, and calculating the average visit duration of all online courses every day, that is, the total visit duration per day / the total number of visits per day, recorded as the first average duration;

[0057] For any online course on the education platform, obtain the corresponding online course's daily access data, including: the total number of people who visit the corresponding online course each day, the total number of visits to the corresponding online course each day, and the average duration of each visit, as well as the amount of storage space occupied by the corresponding online course each day. The amount of storage space occupied by the online course will change with changes in course content and the accumulation of user interaction data;

[0058] Repeatedly obtain the daily access data and first average duration of all online courses on the education platform, record the acquisition date, classify and store them according to the corresponding online courses, and mark them as first access data;

[0059] The data cleaning unit is configured with a data cleaning strategy, which includes: based on the first access data, sorting the first average duration in the first access data according to the acquisition date, recording it as a first duration sequence, and sorting the total number of people who visited the online course, the total number of times the online course was visited, the average duration of each visit, and the size of the storage space occupied in the access data related to any online course in the first access data according to the acquisition date, and recording them in order as a number sequence, a number sequence, a second duration sequence, and a course size sequence;

[0060] The first duration sequence, number of people sequence, number of times sequence, second duration sequence and course size sequence are cleaned and processed respectively, and the second access data is obtained after completion;

[0061] Data cleaning processing includes: sorting the corresponding data according to the acquisition date, including the first duration sequence, the number of people sequence, the number of times sequence, the second duration sequence and the course size sequence; recording as a time data sequence, for any data in the time data sequence, recording as A i , where i represents the sequence number in the time data series, if A i+n Exists; then based on the time data series, extract A i to A i+n , recorded as the first sequence, and extract A i to A i-n , recorded as the second series, calculate the mean and standard deviation of the first series, record them as B0 and B1 respectively, and calculate the mean and standard deviation of the second series, record them as C0 and C1 respectively;

[0062] Judgment Ai Does it satisfy |A i -B0|>3*B1 and |A i -C0|>3*C1, if both are satisfied, mark A i It is abnormal data and is replaced, otherwise it is marked as A i is normal data; if A i+n If it does not exist, mark A i is normal data; repeat marking all the data in the time data series; in this embodiment, n=6, that is, obtain A i The sequence of the first 7 days and the sequence of the last 7 days are judged separately; the reason why they both meet |A i -B0|>3*B1 and |A i -C0|>3*C1 is considered abnormal data. This is because online course data is affected by factors such as holidays, course start times, and exams, which can cause sudden changes in the data. For example, if a holiday starts on a certain day, the number of visitors suddenly decreases. If the data of that day and the previous six days are used as a sequence for judgment, the data on the day the holiday starts will be considered abnormal. By comparing the degree of deviation of the data point from the mean and standard deviation of the previous and next series, abnormal data in the time data series can be accurately identified, and normal data that has suddenly changed due to factors such as holidays, course start times, and exams will not be mistaken as abnormal data.

[0063] The replacement process includes: for abnormal data A i , in the corresponding time data series, obtain two distances A i The most recent normal data are recorded as RA i and LA i ; Calculate A by the first substitution formula i The replacement value TA i , the first replacement formula is as follows: TA i =q1*RA i +q2*LA i , where q1 and q2 are weight coefficients, q1+q2=1, and the value range of q1 and q2 is [0, 1]; and using TA i Replace A i RA i and LA i Preferably located in A i Data on both sides, if RA i and LA i Distance A i Similarly, q1 and q2 can be set to 0.5 at the same time. If they are different, the weight coefficient of the data with a longer distance can be appropriately reduced, and the weight coefficient of the data with a closer distance can be increased;

[0064] In the specific implementation process, most existing education platforms use a relatively fixed storage method, that is, course resources are stored in the original format after uploading. This results in some unpopular or low-activity courses occupying a large amount of storage space for a long time, and this space is not fully utilized most of the time; for example, some highly professional niche courses may only be visited by a few users in a specific period, but occupy the same storage resources as popular courses, resulting in a waste of storage resources on the education platform.

[0065] The model building module calculates the first indicator of the online course based on the second access data and establishes a course access prediction model for the academic year;

[0066] The model building module is configured with a model building strategy, which includes: for any online course, calculating the first indicator of the corresponding online course every day based on the second access data, the first indicator including the course activity indicator and the course consumption ratio indicator;

[0067] Calculating the course activity index includes: calculating the course activity index of the online course on the day using the course activity formula. The course activity formula is as follows: Among them, DC represents the course activity index of the online course on that day, E represents the total number of visits to the online course on that day, T represents the average visit duration of each visit to the online course on that day, V represents the average first visit duration of the day, and F represents the total number of people who visited the online course on that day; the course activity index is used to measure the activity level of various interactive behaviors of the online course in one day. E*T reflects the total interaction level of all users on the online course on that day, taking into account the visit frequency and visit duration of each person. Dividing by V is to eliminate the impact of the difference in visit time caused by the different content nature of different online courses, so that the activity of different online courses is comparable. Multiplying by A is because the number of visitors is the key factor in measuring the activity of online courses. Courses with more visitors are usually more active. Comparing the online course activity indicators of different courses can intuitively understand which courses are more active on that day. Online courses with high activity are not suitable for compression.

[0068] Calculating the course consumption ratio indicator includes: calculating the course consumption ratio indicator of the online course on that day through the resource consumption calculation formula. The course consumption ratio indicator formula is as follows: REC represents the daily course consumption ratio of the online course, and H represents the amount of storage space occupied by the online course on that day. The course consumption ratio reflects the relationship between daily course resource usage and actual usage. A higher course consumption ratio means that the course achieves higher utilization efficiency with relatively less storage resource investment, that is, the course resources are fully utilized. A lower course consumption ratio indicates that the course occupies more storage resources but the actual usage is relatively low, which may indicate storage resource waste.

[0069] Repeat the calculation of the first indicator for each day of all online courses and mark it as the third access data;

[0070] Normalizing the third access data according to data type, that is, normalizing the course activity index and course consumption ratio index in the third access data, scaling all data sizes in the third access data to [0, 1], and obtaining the fourth access data after completion;

[0071] An initial access prediction model is constructed based on a long short-term memory network. The initial access prediction model includes an input layer, an LSTM processing layer, a dropout layer, and a fully connected layer. The LSTM processing layer includes x1 LSTM layers. In this embodiment, x1 = 2, i.e., 2 LSTM layers. x1 can be set according to the actual application scenario, generally 1-3 layers, but not too many. Too many LSTM layers will increase the computational cost and risk overfitting. The dropout layer is used to prevent overfitting. During training, it randomly sets the output of some neurons to 0, which can force the model to learn features on different subsets of neurons and increase the generalization ability of the model. The dropout rate is usually set between 0.1 and 0.5. For example, a setting of 0.3 means that 30% of the neuron outputs are randomly discarded in each training iteration.

[0072] Set the learning rate of model training to x2, the batch size to x3, and the number of training rounds to x4. In this embodiment, x2 = 0.001, x3 = 256, and x4 = 200. Use the fourth access data to train the initial access prediction model. After completion, obtain the academic year course access prediction model.

[0073] During the specific implementation process, by calculating the course activity index and course consumption ratio index of online courses, the education platform can be provided with accurate quantitative information about the course usage and resource utilization of online courses. It can clearly understand the activity level of each course and the consumption of storage resources, which facilitates the subsequent accurate decompression and management based on these data.

[0074] The prediction processing module includes an indicator prediction unit and an indicator processing unit. The indicator prediction unit uses the academic year course access prediction model to predict the access index of the online course in each academic year to obtain first access index data. The indicator processing unit is used to perform first index processing to obtain the course data to be compressed.

[0075] The indicator prediction unit is configured with an indicator prediction strategy, which includes: for any online course on the education platform, obtaining the daily course activity index and course consumption ratio index of the corresponding online course for k1 academic years; recording this as first sample data, normalizing the first sample data, and inputting it into the academic year course access prediction model to obtain the daily course activity index and course consumption ratio index of the corresponding online course for the next academic year, which are recorded as the first predicted data for the academic year; in this embodiment, k1=3, that is, using data from three academic years to predict data for the next academic year;

[0076] The indicator processing unit is configured with an indicator processing strategy, which includes: Figure 4 As shown, for the first forecast data of the academic year of any online course of the education platform, the daily course activity index and course consumption ratio index in the corresponding first forecast data of the academic year are obtained, and the daily decompression index is calculated by the decompression index formula, which is as follows: DR=q3*DC+q4*RC, where DR is the decompression index, q3 and q4 are weight coefficients, q3+q4=1, and the value range of q3 and q4 is [0, 1]; the daily decompression index in the corresponding first forecast data of the academic year is repeatedly calculated to obtain the second forecast data; in this embodiment, q3=q4=0.5, q3 and q4 can be adjusted according to the actual application scenario, and the weighted average decompression index can be regarded as a quantification of the comprehensive importance of the course; the decompression index obtained by combining these two indicators can more comprehensively evaluate the status of the course in platform resource management and user services, and provide a more accurate basis for course decompression decisions;

[0077] Set the decompression threshold to DR0, and judge the daily decompression index in the second predicted data. If the decompression index of the day is less than or equal to DR0, mark the day as a compression day, otherwise mark the day as a decompression day. After completion, obtain the third predicted data;

[0078] During the specific implementation process, the decompression threshold can be set based on the balance between storage cost and experience. If the platform hopes to significantly reduce storage costs by compressing courses, the decompression threshold DR0 can be set relatively high. For example, through analysis, it is found that when 30% of course resources are deeply compressed, the storage cost can be reduced by 20%. Then DR0 can be determined based on this goal so that a sufficient number of courses can be in a compressed state most of the time to achieve the purpose of cost control; however, in order to ensure the students' learning experience, the possibility of compression of popular courses should also be minimized. For example, for courses that are in the final exam review stage, they should be set to no compression or less compression to ensure that students can review smoothly.

[0079] The compression management module dynamically decompresses and manages the online course based on the course data to be compressed and the first access data;

[0080] The compression management module is configured with a compression management strategy, which includes: based on the course data to be compressed, dividing the third predicted data of any online course according to the month, that is, from January to December; and judging and marking any month, including: if the number of compressed days in the month is greater than or equal to k2, then marking the month as a compressed month; if the number of compressed days in the month is less than or equal to k3, then marking the month as a decompression month; if the number of compressed days in the month is less than k2 and greater than k3, then marking the month as a fluctuating month, and after completion, the compression management data of the corresponding online course is obtained; in this embodiment, k2=27, k3=15; dividing by month allows the education platform to plan resources from a macro perspective; the usage of courses in different months may vary due to factors such as semester arrangements and holidays; for example, during the school's winter and summer vacations, the activity of most regular courses may decrease, and resource demand will also decrease accordingly; by dividing by month, the platform can predict and arrange large-scale resource compression in these months in advance to avoid frequent compression and decompression of the same online course;

[0081] See also Figure 5 As shown, for any online course on the education platform, decompression management is performed according to the corresponding compression management data, including:

[0082] If the online course is in a compressed month, the online course will be compressed;

[0083] If the online course is in the decompression month, the online course will be decompressed;

[0084] In a fluctuating month, if the decompression index of an online course is less than or equal to the decompression threshold for k4 consecutive days, the online course will be compressed to avoid the situation where an online course that is still in use is accidentally compressed, resulting in a degraded learning experience. If the average value of the decompression index of an online course for k4 consecutive days is greater than or equal to the decompression threshold, the online course will be decompressed. Decompression can be performed in a timely manner when the online course starts. In this embodiment, k4 is 5 days.

[0085] During the specific implementation process, when compressing or decompressing online courses, if the corresponding online courses have been compressed or decompressed, there is no need to perform secondary compression or decompression. For example, if an online course has been compressed, when it is in the compression month, there is no need for secondary compression. After compressing the online course, it does not mean that the online course cannot be watched and studied. It just means that when students watch and study the online course, the education platform needs to decompress it first, which requires a longer loading time.

[0086] Example 2, please refer to Figure 2 As shown, the present application provides a data management method for a digital education platform, comprising the following steps:

[0087] Step S1: collect access data related to online courses on the education platform, mark it as first access data, and perform data cleaning to obtain second access data. Step S1 includes the following sub-steps:

[0088] Step S101, obtaining the total number of visits and total visit duration of all online courses on the education platform each day, and calculating the average visit duration of all online courses each day, which is recorded as the first average duration;

[0089] Step S102: For any online course on the education platform, obtain the daily access data of the corresponding online course, including: obtaining the total number of people who visit the corresponding online course each day, the total number of visits to the corresponding online course each day, and the average duration of each visit, and obtaining the amount of storage space occupied by the corresponding online course each day;

[0090] Step S103, repeatedly obtaining daily access data and first average duration of all online courses on the education platform, recording the acquisition date, classifying and storing them according to the corresponding online courses, and marking them as first access data;

[0091] Step S104: Based on the first access data, the first average duration in the first access data is sorted by the acquisition date and recorded as a first duration sequence. Furthermore, the total number of people who visited the online course, the total number of times the online course was visited, the average duration of each visit, and the size of the storage space occupied in the access data related to any online course in the first access data are sorted by the acquisition date and recorded in order as a number sequence, a number sequence, a second duration sequence, and a course size sequence.

[0092] Step S105, performing data cleaning processing on the first duration sequence, the number of people sequence, the number of times sequence, the second duration sequence, and the course size sequence, and obtaining the second access data after completion;

[0093] Step S106: data cleaning process. Step S106 includes the following sub-steps:

[0094] Step S1061: record the corresponding data sorted by acquisition date as a time data sequence, and any data in the time data sequence as A i , where i represents the sequence number in the time data series, if A i+n Exists; then based on the time data series, extract A i to A i+n , recorded as the first sequence, and extract Ai to A i-n , recorded as the second sequence;

[0095] Step S1062, calculating the mean and standard deviation of the first sequence, which are denoted as B0 and B1 in sequence, and calculating the mean and standard deviation of the second sequence, which are denoted as C0 and C1 in sequence;

[0096] Step S1063, determine A i Does it satisfy |A i -B0|>3*B1 and |A i -C0|>3*C1, if both are satisfied, mark A i It is abnormal data and is replaced, otherwise it is marked as A i is normal data; if A i+n If it does not exist, mark A i For normal data; repeatedly mark all data in the time data series;

[0097] Step S1064: Replacement processing includes: for abnormal data A i , in the corresponding time data series, obtain two distances A i The most recent normal data are recorded as RA i and LA i ; Calculate A by the first substitution formula i The replacement value TA i , the first replacement formula is as follows: TA i =q1*RA i +q2*LA i , where q1 and q2 are weight coefficients, q1+q2=1, and the value range of q1 and q2 is [0, 1]; and using TA i Replace A i .

[0098] Step S2, calculating the first indicator of the online course based on the second access data, and establishing a course access prediction model for the academic year; Step S2 includes the following sub-steps:

[0099] Step S201: For any online course, calculate the first daily indicator of the corresponding online course based on the second access data, where the first indicator includes a course activity indicator and a course consumption ratio indicator;

[0100] Step S202, calculating the course activity index includes: calculating the course activity index of the online course on the day using the course activity formula, the course activity formula is as follows: Where DC represents the course activity index of the online course on that day, E represents the total number of visits to the online course on that day, T represents the average visit duration of each visit to the online course on that day, V represents the average first visit duration of the day, and F represents the total number of people who visited the online course on that day;

[0101] Step S203, calculating the course consumption ratio index includes: calculating the course consumption ratio index of the online course on that day using a resource consumption calculation formula. The course consumption ratio index formula is as follows: REC represents the course consumption ratio of the online course on that day, and H represents the amount of storage space occupied by the online course on that day;

[0102] Step S204, repeatedly calculating the first indicator of all online courses every day, marking it as the third access data;

[0103] Step S205 , normalizing the third access data according to the data type, scaling all data sizes in the third access data to [0, 1], and obtaining fourth access data.

[0104] Step S206: constructing an initial access prediction model based on a long short-term memory network. The initial access prediction model includes an input layer, an LSTM processing layer, a Dropout layer, and a fully connected layer. The LSTM processing layer includes x1 LSTM layers.

[0105] Step S207, set the learning rate of model training to x2, the batch size to x3, and the number of training rounds to x4; use the fourth access data to train the initial access prediction model, and after completion, obtain the academic year course access prediction model.

[0106] Step S3, using the academic year course access prediction model to predict the access index of the online course for each academic year, obtaining first access index data, and performing first index processing to obtain the course data to be compressed; Step S3 includes the following sub-steps:

[0107] Step S301: For any online course on the education platform, obtain the daily course activity index and course consumption ratio index of the corresponding online course for k1 academic years; record them as first sample data;

[0108] Step S302: normalize the first sample data and input it into the academic year course access prediction model to obtain the daily course activity index and course consumption ratio index of the corresponding online course for the next academic year, which are recorded as the first predicted data for the academic year;

[0109] Step S303: For the first forecast data of the academic year for any online course on the education platform, obtain the daily course activity index and course consumption ratio index in the corresponding first forecast data of the academic year, and calculate the daily decompression index using the decompression index formula. The decompression index formula is as follows: DR = q3*DC + q4*RC, where DR is the decompression index, q3 and q4 are weight coefficients, q3+q4=1, and the value range of q3 and q4 is [0, 1];

[0110] Step S304, repeatedly calculating the daily decompression index in the first forecast data of the corresponding academic year to obtain the second forecast data;

[0111] Step S305: Set the decompression threshold to DR0, and judge the daily decompression index in the second prediction data. If the decompression index of the day is less than or equal to DR0, mark the day as a compression day; otherwise, mark the day as a decompression day. After completion, obtain the third prediction data.

[0112] Step S306: repeatedly obtain the third prediction data of all online courses and mark them as course data to be compressed.

[0113] Step S4, dynamically decompressing and managing the online course based on the course data to be compressed and the first access data; Step S4 includes the following sub-steps:

[0114] Step S401: Based on the course data to be compressed, the third predicted data of any online course is divided according to the month time, and any month is judged and marked, including: if the number of compressed days in the month is greater than or equal to k2, then the month is marked as a compressed month; if the number of compressed days in the month is less than or equal to k3, then the month is marked as a decompression month; if the number of compressed days in the month is less than k2 and greater than k3, then the month is marked as a fluctuating month. After completion, the compressed management data of the course is obtained;

[0115] Step S402: The corresponding network performs decompression management on any online course on the education platform according to the corresponding compressed management data. Step S402 includes the following sub-steps:

[0116] Step S4021: If the online course is in a compressed month, the online course is compressed;

[0117] Step S4022: If the online course is in the decompression period, the online course is decompressed;

[0118] Step S4023: If the online course is in a fluctuating month, and the decompression index of the online course for k4 consecutive days is less than or equal to the decompression threshold, the online course is compressed; if the average value of the decompression index of the online course for k4 consecutive days is greater than or equal to the decompression threshold, the online course is decompressed.

[0119] Example 3, please refer to Figure 5 As shown, Figure 5 A schematic diagram of the structure of an electronic device is provided, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps of a data management method for a digital education platform are executed to implement the following functions: collecting access data related to online courses on the education platform, marking it as first access data, and performing data cleaning processing to obtain second access data; calculating a first indicator of the online course based on the second access data, and establishing a school year course access prediction model; using the school year course access prediction model to predict the access indicator of the online course for each school year to obtain first access indicator data, and performing first indicator processing to obtain course data to be compressed; and dynamically decompressing and managing the online course based on the course data to be compressed and the first access data.

[0120] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0121] Example 4. The present application also provides a computer-readable storage medium. The present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the data management method of a digital education platform are executed to achieve the following functions: collecting relevant access data of online courses of the education platform, marking it as first access data, and performing data cleaning processing to obtain second access data; calculating the first indicator of the online course based on the second access data, and establishing an academic year course access prediction model; using the academic year course access prediction model to predict the access indicator of the online course for each academic year, obtaining first access indicator data, and performing first indicator processing to obtain course data to be compressed; dynamically decompressing and managing the online course based on the course data to be compressed and the first access data.

[0122] Through the description of the above embodiments, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on this understanding, the above technical solutions, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiment.

[0123] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data management system for a digital education platform, characterized in that: It includes data acquisition module, model building module, prediction processing module and compression management module; The data acquisition module includes a data acquisition unit and a data cleaning unit. The data acquisition unit is used to collect relevant access data of the online courses of the education platform, which is marked as first access data. The data cleaning unit is used to perform cleaning and screening processing to obtain second access data. The model building module calculates a first indicator of the online course based on the second access data and establishes a course access prediction model for the academic year; The prediction processing module includes an indicator prediction unit and an indicator processing unit. The indicator prediction unit uses the academic year course access prediction model to predict the access index of the online course in each academic year to obtain first access index data. The indicator processing unit is used to perform first index processing to obtain the course data to be compressed. The compression management module dynamically decompresses and manages the online course based on the course data to be compressed and the first access data; The model building module is configured with a model building strategy, which includes: For any online course, a first indicator of the corresponding online course is calculated daily based on the second access data, where the first indicator includes a course activity indicator and a course consumption ratio indicator; Calculating the course activity index includes: calculating the course activity index of the online course on the day using the course activity formula. The course activity formula is as follows: , where DC represents the course activity index of the online course on that day, E represents the total number of visits to the online course on that day, T represents the average visit duration of each visit to the online course on that day, V represents the average duration of the first visit on that day, and F represents the total number of people who visit the online course on that day; Calculating the course consumption ratio indicator includes: calculating the course consumption ratio indicator of the online course on that day through the resource consumption calculation formula. The course consumption ratio indicator formula is as follows: , where RC represents the course consumption ratio of the online course on that day, and H represents the size of the storage space occupied by the online course on that day; Repeat the calculation of the first indicator for each day of all online courses and mark it as the third access data; Model building strategies also include: Normalizing the third access data according to their data types, scaling all data sizes in the third access data to [0, 1], and obtaining fourth access data upon completion; An initial access prediction model is constructed based on a long short-term memory network. The initial access prediction model includes an input layer, an LSTM processing layer, a dropout layer, and a fully connected layer. The LSTM processing layer includes x1 LSTM layers. Set the learning rate of model training to x2, the batch size to x3, and the number of training rounds to x4; use the fourth visit data to train the initial visit prediction model, and after completion, obtain the academic year course visit prediction model.

2. The data management system of a digital education platform according to claim 1, characterized in that: The data acquisition unit is configured with a data acquisition strategy, which includes: Obtain the total number of visits and total visit duration of all online courses on the education platform each day, and calculate the average visit duration of all online courses each day, which is recorded as the first average duration; For any online course on the education platform, obtain the corresponding online course's daily access data, including: the total number of people who visit the corresponding online course each day, the total number of visits to the corresponding online course each day, the average duration of each visit, and the amount of storage space occupied by the corresponding online course each day; Repeatedly obtain the daily relevant access data and the first average duration of all online courses on the education platform, record the acquisition date, classify and store them according to the corresponding online courses, and mark them as the first access data.

3. The data management system of a digital education platform according to claim 2, characterized in that: The data cleaning unit is configured with a data cleaning strategy, which includes: Based on the first access data, the first average duration in the first access data is sorted according to the acquisition date and recorded as a first duration sequence, and the total number of people who visited the online course, the total number of times the online course was visited, the average duration of each visit, and the size of the storage space occupied in the access data related to any online course in the first access data are sorted according to the acquisition date and recorded in order as a number sequence, a number sequence, a second duration sequence, and a course size sequence; The first duration sequence, number of people sequence, number of times sequence, second duration sequence and course size sequence are cleaned and processed respectively, and the second access data is obtained after completion; Data cleaning processing includes: sorting the corresponding data according to the acquisition date as a time data sequence, and recording any data in the time data sequence as A i , where i represents the sequence number in the time data series, if A i+n Exists; then based on the time data series, extract A i to A i+n , recorded as the first sequence, and extract A i to A i-n , recorded as the second sequence, calculate the mean and standard deviation of the first sequence, record them as B0 and B1 respectively, and calculate the mean and standard deviation of the second sequence, record them as C0 and C1 respectively, judge A i Does it satisfy |A i -B0|>3*B1 and |A i -C0|>3*C1, if both are satisfied, mark A i It is abnormal data and is replaced, otherwise it is marked as A i is normal data; if A i+n If it does not exist, mark A i For normal data; repeatedly mark all data in the time data series; The replacement process includes: for abnormal data A i , in the corresponding time data series, obtain two distances A i The most recent normal data are recorded as RA i and LA i ; Calculate A by the first substitution formula i The replacement value TA i , the first replacement formula is as follows: , where q1 and q2 are weight coefficients, q1+q2=1, and the value range of q1 and q2 is [0, 1]; and using TA i Replace A i .

4. The data management system of a digital education platform according to claim 3, characterized in that: The indicator prediction unit is configured with an indicator prediction strategy, which includes: For any online course on the education platform, obtain the daily course activity index and course consumption ratio index of the corresponding online course for k1 academic years; record them as the first sample data, normalize the first sample data, and input them into the academic year course access prediction model to obtain the daily course activity index and course consumption ratio index of the corresponding online course in the next academic year, which are recorded as the first predicted data of the academic year.

5. The data management system of a digital education platform according to claim 4, characterized in that: The indicator processing unit is configured with an indicator processing strategy, which includes: For the first academic year forecast data of any online course on the education platform, obtain the daily course activity index and course consumption ratio index in the corresponding first academic year forecast data, and calculate the daily decompression index using the decompression index formula. The decompression index formula is as follows: , where DR is the decompression index, q3 and q4 are weight coefficients, q3+q4=1, and the value range of q3 and q4 is [0, 1]; repeatedly calculate the decompression index of each day in the first forecast data of the corresponding academic year to obtain the second forecast data; Set the decompression threshold to DR0, and judge the daily decompression index in the second predicted data. If the decompression index of the day is less than or equal to DR0, mark the day as a compression day, otherwise mark the day as a decompression day. After completion, obtain the third predicted data; Repeatedly obtain the third prediction data of all online courses and mark them as course data to be compressed.

6. The data management system of a digital education platform according to claim 5, characterized in that: The compression management module is configured with compression management policies, which include: Based on the course data to be compressed, the third predicted data of any online course is divided according to the month time, and any month is judged and marked, including: if the number of compressed days in the month is greater than or equal to k2, then the month is marked as a compressed month; if the number of compressed days in the month is less than or equal to k3, then the month is marked as a decompression month; if the number of compressed days in the month is less than k2 and greater than k3, then the month is marked as a fluctuating month. After completion, the compression management data of the corresponding online course is obtained.

7. The data management system of a digital education platform according to claim 6, characterized in that: Compression management strategies also include: For any online course on the education platform, decompression management is performed according to the corresponding compression management data, including: If the online course is in a compressed month, the online course will be compressed; If the online course is in the decompression month, the online course will be decompressed; If the online course is in a fluctuating month, if the decompression index of the online course for 4 consecutive days is less than or equal to the decompression threshold, the online course will be compressed; if the average value of the decompression index of the online course for 4 consecutive days is greater than or equal to the decompression threshold, the online course will be decompressed.

8. A data management method for a digital education platform, used to implement the data management system of any one of claims 1 to 7, characterized in that: The steps include: Collect relevant access data of online courses on the education platform, mark it as first access data, and perform data cleaning to obtain second access data; Calculating the first index of the online course based on the second access data and establishing a course access prediction model for the academic year; Using the academic year course access prediction model to predict the access index of the online course in each academic year, obtaining first access index data, and performing first index processing to obtain the course data to be compressed; Dynamic decompression management is performed on the online course based on the course data to be compressed and the first access data.

Images