CN111897859B - Big data intelligent report platform for enterprise online education - Google Patents
Big data intelligent report platform for enterprise online education Download PDFInfo
- Publication number
- CN111897859B CN111897859B CN202011054974.XA CN202011054974A CN111897859B CN 111897859 B CN111897859 B CN 111897859B CN 202011054974 A CN202011054974 A CN 202011054974A CN 111897859 B CN111897859 B CN 111897859B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- learning
- information
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2453—Query optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a big data intelligent report platform for enterprise online education, which comprises: counting registered target users based on an online education system, and simultaneously acquiring user information of the target users and education service logs of the target users based on the online education system; performing first analysis processing on the education service log of each target user based on the analysis database; performing second analysis processing on the user information of the target user based on the user database; summarizing corresponding education service logs into a recording area of a data table according to different target dimensions according to the first analysis processing result, the second analysis processing result and service attributes in a service database; and calling related information to be summarized from the recording area for displaying according to the input preset dimension. The service logs are analyzed through analyzing the database, and are summarized according to different dimensions, so that the total number of inquires is greatly reduced, and the aims of accurate data and no timeout inquiry are fulfilled.
Description
Technical Field
The invention relates to the technical field of online education, in particular to a big data intelligent report platform for enterprise online education.
Background
At present, a report system is common in various companies, and total data in a certain period of time can be conveniently inquired. But most of the data is the original data of the query, and the data is not problematic in the case of small amount of companies and small amount of data, but is not applicable to enterprises with large amount of data.
In order to better improve the learning desire of employees, some enterprises generally inquire the learning duration, login times, learning times, hot courses and the like of online learning of employees in departments. At present, various data of enterprises are huge, learning data in a period of time cannot be counted through an original database, overtime may occur, and in addition, in order to store and analyze a large amount of data and ensure normal operation of the data, in order to achieve the purposes of data accuracy and rapid query, and in order to enable a user to quickly and accurately obtain various statistical data of a company, an existing reporting system needs good hardware support, so that the cost is relatively high.
Therefore, the invention provides a big data intelligent report platform for enterprise online education.
Disclosure of Invention
The invention provides a big data intelligent report platform for enterprise online education, which is used for analyzing business logs by analyzing a database, summarizing according to different dimensions, and greatly reducing the total number of inquires, so that the aims of accurate data and no timeout of inquiry are fulfilled.
The invention provides a big data intelligent report platform for enterprise online education, which comprises:
counting registered target users based on an online education system, and simultaneously acquiring user information of the target users and education service logs of the target users based on the online education system;
performing first analysis processing on the education service log of each target user based on the analysis database;
performing second analysis processing on the user information of the target user based on a user database;
summarizing corresponding education service logs into a recording area of a data table according to different target dimensions according to the first analysis processing result, the second analysis processing result and service attributes in a service database;
and calling information to be summarized related to the preset dimension from the recording area for displaying according to the input preset dimension.
In one possible implementation, the step of aggregating the corresponding education service logs into the recording area of the data table according to different target dimensions includes:
acquiring a first target project and a second target project related to the education service log;
reading each piece of data in an original business database based on a report system, acquiring a change record of each piece of data, and constructing a record change set;
reading the change records of the first target item based on the record change set, performing data backup, and simultaneously sending a target instruction to a middle message piece;
the second target project part performs service summary calculation of different target dimensions through the intermediate message part according to the target instruction, and reserves a calculation result;
determining a project data volume for the first and second target projects;
when the project data volume is larger than or equal to a preset data volume, using two channels corresponding to a first database, and determining incremental synchronization data of the two channels;
summarizing the reserved calculation results into a recording area of a data table according to different target dimensions according to the incremental synchronous data;
when the project data volume is smaller than the preset data volume, using a single channel corresponding to a second database, and determining incremental asynchronous data of the single channel through two adjacent time intervals;
and summarizing the retained calculation results into a recording area of the data table according to different target dimensions according to the incremental asynchronous data.
In one possible implementation manner, the obtaining of the user information of the target user and the education service log of the target user based on the online education system further includes:
determining the department where the target user is located according to the user information of the target user, and acquiring department tasks of the department where the target user is located from a report platform, wherein the department tasks comprise: the online learning duration, the online learning course and the online learning task are communicated;
judging whether the target user is qualified for online learning by the current time according to the department task;
if the target users are qualified, keeping the learning records of the target users, making learning reports of the target users, and meanwhile, determining the learning reports of the departments and displaying the learning reports based on each target user;
otherwise, sending an alarm instruction to the terminal of the target user for alarm reminding.
In one possible implementation manner, the step of determining whether the target user online learning is qualified by the current time includes:
when the target user logs in the online education system, capturing user watching information of the target user based on a learning interface and playing video information of the learning interface, and acquiring first frame content in the user watching information and second frame content in the playing video information at the same time point according to a timestamp;
performing pre-analysis on the first frame content, determining the current viewing state of the target user, and acquiring a feature vector of the first frame content;
meanwhile, acquiring morphological motion information of the target user based on the previous frame content and the next frame content of the first frame content, and correcting the current viewing state based on the morphological motion information to obtain a real-time viewing state;
preprocessing the second frame content, determining the current playing state of the learning interface, and acquiring a feature vector of the second frame content;
meanwhile, based on the picture display information of the last frame content and the next frame content of the second frame content, the current playing state is corrected, and a real-time playing state is obtained;
determining a distribution distance between the feature vector of the first frame content and the feature vector of the second frame content;
establishing a one-to-one corresponding relation of each time point according to the real-time watching state and the real-time playing state, and correcting the one-to-one corresponding relation according to the distribution distance;
extracting time points with inconsistent real-time watching states and real-time playing states according to the corrected corresponding relations and a preset relation library, calibrating the inconsistent time points, and meanwhile calculating the time ratio of the inconsistent time points to the whole timestamp ending the current time;
when the time ratio is larger than or equal to a preset ratio, judging that the target user is unqualified in online learning, and recording and feeding back inconsistent time points;
otherwise, judging that the target user is qualified for online learning.
In a possible implementation manner, before counting the registered target users based on the online education system, the method further includes:
acquiring a historical search record and a historical browsing interface related to the historical search record in the online learning process of the target user based on an online education system, and coding the historical search record and the historical browsing interface;
extracting all action events in the coding processing result, classifying the action events, preprocessing each type of event, and normalizing to obtain a feature vector of each type of event;
capturing system operation information of the target user for performing historical search operations in online learning based on an online education system, wherein the system operation information comprises: the running time, running power and heating parameters of each historical search;
establishing a system operation model of the online education system according to the system operation information, and matching first feedback information related to the system operation model from a model database;
inputting the characteristic vector into the system operation model to obtain second feedback information;
acquiring a first influence factor of the second feedback information aiming at the first feedback information, and acquiring a second influence factor of the first feedback information aiming at the second feedback information;
acquiring an optimization set from an optimization database according to the first feedback information and the second feedback information;
carrying out quantitative adjustment on optimization indexes in the optimization set according to the first influence factor and the second influence factor, and selecting a comprehensive optimization mode from a mode database according to the optimization set subjected to quantitative adjustment;
and performing optimization upgrading on the online education system according to the comprehensive optimization mode, and counting registered target users based on the online education system after optimization upgrading.
In a possible implementation manner, after determining, according to the user information of the target user, a department where the target user is located, and acquiring a department task of the department from a reporting platform, the method further includes:
acquiring historical learning data of all users in the same department of a target enterprise, and establishing a learning cycle model of the same department according to the historical learning data, wherein the historical learning data comprises: the learning progress, learning mastery degree and learning performance of the online education system in the learning process of different users in the same department;
acquiring the time point when each user of the same department reaches each historical prediction learning, and simultaneously estimating the learning capacity of each user at each historical prediction learning time point based on the learning cycle model;
sequentially establishing the difference degree of each user between adjacent learning abilities, and establishing a difference degree set;
correspondingly correcting each layer of the network in the learning period model according to the difference degree set, and estimating a final report form of the same department according to the corrected learning period model;
recording and acquiring real-time learning report forms of online learning of different users in the same department in the online education system;
and performing row-to-column correspondence comparison on the real-time learning report and the final report, extracting row and column information with the contrast ratio greater than a preset degree, and transmitting the row and column information to a corresponding user terminal for display.
In a possible implementation manner, during the first parsing process performed on the educational service log of each target user, the method further includes:
acquiring the data length of the user information of the target user, and dividing the user information according to a data division rule to obtain a plurality of sections of user subdata;
simultaneously, carrying out binary coding on all the user subdata according to a dividing sequence, and respectively establishing coding units corresponding to one another;
extracting irregular data in the coding unit, and meanwhile, calculating a polymerization degree value of the irregular data and the corresponding user subdata;
if the polymerization degree value exceeds a preset value, carrying out error correction processing on the corresponding coding unit, wherein the error correction processing step comprises the following steps:
dividing the coded data of the coding unit to obtain N information data blocks;
adding a cyclic redundancy check sequence into the N information data blocks, and simultaneously carrying out coding error correction on the N information data blocks added with the cyclic redundancy check sequence so as to obtain N error correction coding blocks;
according to the data of the N error correction coding blocks, carrying out coding processing on the N information data blocks, and acquiring M check packets of the N error correction coding blocks, wherein M is greater than N;
carrying out error correction processing on the coding units corresponding to the N error correction coding blocks and the M check packets, and simultaneously transmitting the error correction processing result to the coding units;
screening data to be replaced in the irregular data in the corresponding coding unit, updating and replacing the data to be replaced based on the data to be updated corresponding to the error correction processing result, and reserving a new coding unit;
if the polymerization degree value does not exceed a preset value, the corresponding coding unit is reserved;
acquiring a characteristic vector set of the education service log, and constructing a characteristic model by using a convolutional neural network through the characteristic vector set;
classifying the education service log by dividing the feature model based on the unit data of the reserved coding units;
and calling an analysis mode from the analysis database according to the classification result, and performing first analysis processing on the education service log according to the analysis mode.
In a possible implementation manner, before summarizing the corresponding education service logs into the recording area of the data table according to the first parsing processing result, the second parsing processing result and the service attribute in the service database according to different target dimensions, the method further includes:
determining a comprehensive attribute value of the target dimension, and determining whether the corresponding education service logs can be summarized to a recording area of the data table according to the target dimension according to the comprehensive attribute value, wherein the method comprises the following steps:
acquiring a dimension data set X of the target dimension, and extracting individual sample data in the dimension data set X, wherein,
，
representing the nth sample data;
clustering the sample data, and acquiring the attribute of each type of the clustered sample data
Wherein the first attribute
Has a value range of
Wherein the number of classes of the sample is, and
；
represents the ith attribute value range in the category, and
；i=1,2,3,…,n1；
determining a comprehensive attribute value of the target dimension according to the attribute of the clustered sample data;
wherein the content of the first and second substances,
a composite attribute value representing the target dimension,
j =1,2,3, …, n, representing the jth sample data, wherein the total number of sample data is represented,
representing a clustering probability that a first sample data is classified into a first class;
represents the jth sample data
The degree of difference from the standard sample data,
represents the integrated data density of all of the sample data,
represents a composite weight value of all the sample data,
representing the average clustering accuracy of all the sample data in the clustering process,
represents an average data loss rate of all the sample data,
a standard data density representing the standard sample data,
represents the average weight of all the sample data, and
；
based on a dimension database, calling a target function matched with the comprehensive attribute value, and judging whether the target function meets a preset constraint condition;
if yes, summarizing the corresponding education service logs into the recording area of the data table according to the target dimension.
In one possible implementation, after determining that the objective function does not satisfy the preset constraint condition,
determining the information entropy of the target dimension according to the comprehensive attribute value;
wherein the content of the first and second substances,
an entropy of information representing the target dimension,
represents a measurement indicator within the target dimension, and
and represents the total number of the measurement indexes,
expressed in the measurement index of
The proportion of the amount of the information to be processed,
a weight coefficient representing the value of the composite attribute,
a composite attribute value representing the target dimension,
a value representing a comprehensive dimension attribute of the target dimension, [2 ]]Representing rounding;
determining whether the information entropy of the target dimension is within a preset information entropy range;
if the information entropy of the target dimension is within the preset information entropy range, summarizing the corresponding education service logs into a recording area of the data table according to the target dimension;
otherwise, screening data to be optimized from the sample data of the target dimension, simultaneously calling dimension optimization parameters from the dimension database according to the information entropy, optimizing the data to be optimized according to the dimension optimization parameters, and optimizing the target dimension according to an optimization processing result.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart of a big data intelligent reporting platform for enterprise online education according to an embodiment of the present invention;
FIG. 2 is a flowchart of a system report summary according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides a big data intelligent report platform facing enterprise online education, as shown in figure 1, comprising:
step 1: counting registered target users based on an online education system, and simultaneously acquiring user information of the target users and education service logs of the target users based on the online education system;
step 2: performing first analysis processing on the education service log of each target user based on the analysis database;
and step 3: performing second analysis processing on the user information of the target user based on a user database;
and 4, step 4: summarizing corresponding education service logs into a recording area of a data table according to different target dimensions according to the first analysis processing result, the second analysis processing result and service attributes in a service database;
and 5: and calling information to be summarized related to the preset dimension from the recording area for displaying according to the input preset dimension.
In this embodiment, the user information includes the user name, the course of learning, the department to which the user belongs, the learning ability of the user, and the like;
in this embodiment, the first parsing process is performed on the education service log, for example, key information in the education service log is extracted, and a course learning condition of the user is determined;
the second analysis processing is performed on the user information, for example, to determine the learning ability, the department to which the user belongs, and the like.
In this embodiment, the predetermined dimension is, for example, related to a learning course, a department to which the learning course belongs, and the like.
The summary information is, for example, a summary table related thereto.
The beneficial effects of the above technical scheme are: the service logs are analyzed through analyzing the database, and are summarized according to different dimensions, so that the total number of inquires is greatly reduced, and the aims of accurate data and no timeout inquiry are fulfilled.
The invention provides a big data intelligent report platform for enterprise online education, which summarizes corresponding education service logs into a recording area of a data table according to different target dimensions and comprises the following steps:
acquiring a first target project and a second target project related to the education service log;
reading each piece of data in an original business database based on a report system, acquiring a change record of each piece of data, and constructing a record change set;
reading the change records of the first target item based on the record change set, performing data backup, and simultaneously sending a target instruction to a middle message piece;
the second target project part performs service summary calculation of different target dimensions through the intermediate message part according to the target instruction, and reserves a calculation result;
determining a project data volume for the first and second target projects;
when the project data volume is larger than or equal to a preset data volume, using two channels corresponding to a first database, and determining incremental synchronization data of the two channels;
summarizing the reserved calculation results into a recording area of a data table according to different target dimensions according to the incremental synchronous data;
when the project data volume is smaller than the preset data volume, using a single channel corresponding to a second database, and determining incremental asynchronous data of the single channel through two adjacent time intervals;
and summarizing the retained calculation results into a recording area of the data table according to different target dimensions according to the incremental asynchronous data.
The above steps further include the following embodiments, as shown in fig. 2, including:
MySQL used by a company service original database, and a report system reads bin-log of the service database by using canal so as to obtain a change record of each piece of data of the service database.
The report-collector project reads the service library change record in the canal, then saves a backup of the original data, and then sends a message to the MQ.
And the report-computer project performs service summary calculation of different dimensions through the consumption MQ and then stores the calculation result.
If the project data size is large, a Greenplus database is used, and if the Greenplus is used, the data of a report database of a report needs to be subjected to incremental synchronization through canal and dts-mysql2 pg.
The full synchronization middleware rds _ dbsync is a tool to synchronize all data full of report MySQL to Greenplus when the Greenplus database is used for the first time.
And the user inquires, summarizes and calculates data stored in the report MySQL or Greenplus after the user inquires and calculates the data through a report-web-server project in a management background.
In the technical scheme related to fig. 2, bin-log data of the business database is read by canal, and statistics is performed according to different business dimensions, so that the query data volume is greatly reduced, and the effects of achieving data accuracy and query rapidness are achieved, for example, the data of the login persons of a certain department for one month is counted before, only the login log of a user can be queried before, and 1 million pieces of data may be needed to be queried in 1 million login logs. In the existing scheme, when a log is newly added to a service library, a report library adds 1 to the number of logins in one record of a database according to the dimensionality of departments and months, and only 1 required data needs to be found out from thousands of data when the number of logins is inquired, so that the data volume is greatly reduced.
Aiming at the technical scheme related to the graph 2, the canal synchronous service library data is used, real-time synchronization and no loss of the data are guaranteed, data summarization is carried out according to different dimensions, the data volume of query is greatly reduced, the query speed is improved, and compared with MySQL, the Greenplus database is used, the data support volume of Greenplus is larger, and the query speed is higher.
In this embodiment, both the first target item and the second target item may be related to a report-computer item.
In this embodiment, the target dimension is, for example, related to different time periods, different departments, a total point of department learning, a total duration of department learning, a number of user learning courses, a total score obtained by a user, and the like, and further, a multi-dimensional table is obtained according to a plurality of parameters.
In the embodiment, by comparing and judging the size of the project data volume, the transmission channel can be effectively selected, and reasonable and effective transmission of data is ensured.
Wherein the first database may be related to a greenplus database and the second database may be related to a MySQL database.
The corresponding incremental synchronous data may be related to the relevant parameters of the database itself and the transmission parameters in the transmission process of the two-channel transmission, and the corresponding incremental asynchronous data may be related to the relevant parameters of the database itself and the transmission parameters in the transmission process of the single channel at different time periods.
The beneficial effects of the above technical scheme are: through carrying out the data summarization of different dimensions, be convenient for reduce the inquiry work load, improve the query speed, through selecting different passageways, and then obtain the asynchronous data of increment synchronous data of binary channels or single channel, be convenient for effectively revise the calculated result to effectively summarize to the table that corresponds, improve the high efficiency that the data was summarized.
The invention provides a big data intelligent report platform facing enterprise online education, which further comprises the following steps in the process of acquiring the user information of a target user and the education service log of the target user based on the online education system:
determining the department where the target user is located according to the user information of the target user, and acquiring department tasks of the department where the target user is located from a report platform, wherein the department tasks comprise: the online learning duration, the online learning course and the online learning task are communicated;
judging whether the target user is qualified for online learning by the current time according to the department task;
if the target users are qualified, keeping the learning records of the target users, making learning reports of the target users, and meanwhile, determining the learning reports of the departments and displaying the learning reports based on each target user;
otherwise, sending an alarm instruction to the terminal of the target user for alarm reminding.
The beneficial effects of the above technical scheme are: by making the learning report form of the user, on one hand, the multi-dimensional effective statistics is conveniently carried out on the learning progress of the user, and on the other hand, the learning report form is used for reminding the user to improve the learning efficiency.
The invention provides a big data intelligent report platform for enterprise online education, which judges whether the target user is qualified by the current time through online learning by the steps of:
when the target user logs in the online education system, capturing user watching information of the target user based on a learning interface and playing video information of the learning interface, and acquiring first frame content in the user watching information and second frame content in the playing video information at the same time point according to a timestamp;
performing pre-analysis on the first frame content, determining the current viewing state of the target user, and acquiring a feature vector of the first frame content;
meanwhile, acquiring morphological motion information of the target user based on the previous frame content and the next frame content of the first frame content, and correcting the current viewing state based on the morphological motion information until a real-time viewing state is obtained;
preprocessing the second frame content, determining the current playing state of the learning interface, and acquiring a feature vector of the second frame content;
meanwhile, based on the picture display information of the last frame content and the next frame content of the second frame content, the current playing state is corrected, and a real-time playing state is obtained;
determining a distribution distance between the feature vector of the first frame content and the feature vector of the second frame content;
establishing a one-to-one corresponding relation of each time point according to the real-time watching state and the real-time playing state, and correcting the one-to-one corresponding relation according to the distribution distance;
extracting time points with inconsistent real-time watching states and real-time playing states according to the corrected corresponding relations and a preset relation library, calibrating the inconsistent time points, and meanwhile calculating the time ratio of the inconsistent time points to the whole timestamp ending the current time;
when the time ratio is larger than or equal to a preset ratio, judging that the target user is unqualified in online learning, and recording and feeding back inconsistent time points;
otherwise, judging that the target user is qualified for online learning.
In this embodiment, the information that the user watches refers to the current learning situation of the user when the user watches the learning course, and the video information that the user plays is the video of the learning course played by the user.
In this embodiment, the first frame content and the second frame content are acquired synchronously, and are acquired based on the same time point capture, and the corresponding morphological and motion information includes, for example, the concentration degree of pupil rotation of the user, facial micro-expression, note-taking information, and the like.
In this embodiment, the first frame content is modified according to the previous frame content and the next frame content, so as to obtain a more accurate real-time viewing state;
in this embodiment, the feature vector is obtained to obtain the distribution distance, which may be obtained by vector subtraction.
In this embodiment, the corresponding relationship may be the same time point, the watching state of the user, and a certain picture of the video playing.
For example, at time a, a video is in a playing state, but the user does not watch the video, and this time is set as an inconsistent time.
The beneficial effects of the above technical scheme are: the method has the advantages that frame section comparison at the same time point is carried out on two parts of contents of watching information and playing video information from a user, a judgment basis is provided for effectively judging whether target user online learning is qualified or not, the distribution distance between the same frames is convenient to determine by obtaining the characteristic vectors at the same time point, correction processing is carried out on the corresponding relation, and whether the user online learning is qualified or not is further convenient to further determine by comparing the time ratio with the preset ratio, so that effective supervision is carried out in the process of counting the learning progress of the user, the learning enthusiasm of the user is further ensured, and the learning efficiency of the user is improved.
The invention provides a big data intelligent report platform for enterprise online education, which is based on an online education system and comprises the following components in advance of counting registered target users:
acquiring a historical search record and a historical browsing interface related to the historical search record in the online learning process of the target user based on an online education system, and coding the historical search record and the historical browsing interface;
extracting all action events in the coding processing result, classifying the action events, preprocessing each type of event, and normalizing to obtain a feature vector of each type of event;
capturing system operation information of the target user for performing historical search operations in online learning based on an online education system, wherein the system operation information comprises: the running time, running power and heating parameters of each historical search;
establishing a system operation model of the online education system according to the system operation information, and matching first feedback information related to the system operation model from a model database;
inputting the characteristic vector into the system operation model to obtain second feedback information;
acquiring a first influence factor of the second feedback information aiming at the first feedback information, and acquiring a second influence factor of the first feedback information aiming at the second feedback information;
acquiring an optimization set from an optimization database according to the first feedback information and the second feedback information;
carrying out quantitative adjustment on optimization indexes in the optimization set according to the first influence factor and the second influence factor, and selecting a comprehensive optimization mode from a mode database according to the optimization set subjected to quantitative adjustment;
and performing optimization upgrading on the online education system according to the comprehensive optimization mode, and counting registered target users based on the online education system after optimization upgrading.
In this embodiment, the action events in the encoding processing result are extracted, and classification processing and normalization processing are performed to obtain feature vectors of events of the same kind, and to obtain system operation parameters to enable a system operation model to be constructed.
In this embodiment, the first feedback information may be a parameter related to operation, the action event corresponding to the feature vector may be related to an event such as operation, and the second feedback information is convenient to obtain by inputting the feature vector into the system operation model, and is also a parameter related to operation.
In this embodiment, the obtained optimization set may be for performing an optimizable index and a parameter on the operation process, and performing quantization adjustment, and is for performing effective adjustment on the optimization index to improve the optimization performance of the optimization index, and the online education system is optimized and upgraded by selecting an optimization mode, so that the operation efficiency of the system is improved, and the efficiency of form summarization is improved.
In this embodiment, by obtaining the influence factors that affect each other, such as the operation influence factors, for example, the value range of the first influence factor is [1, 3], and the value range of the second influence factor is [2, 5 ].
In this embodiment, the comprehensive optimization mode is, for example, to optimize a certain block of the system, or to optimize the entire system.
The beneficial effects of the above technical scheme are: the optimization indexes can be conveniently obtained by obtaining the first feedback information and the second feedback information, the optimization performance of the optimization indexes can be improved by being conveniently adjusted in a quantification mode, the online education system can be optimized and upgraded by selecting the optimization mode, the operation efficiency of the system can be conveniently improved, and the table summarizing efficiency can be improved.
The invention provides a big data intelligent report platform facing enterprise online education, which determines the department of a target user according to the user information of the target user, and also comprises the following steps after acquiring the department task of the department from the report platform:
acquiring historical learning data of all users in the same department of a target enterprise, and establishing a learning cycle model of the same department according to the historical learning data, wherein the historical learning data comprises: the learning progress, learning mastery degree and learning performance of the online education system in the learning process of different users in the same department;
acquiring the time point when each user of the same department reaches each historical prediction learning, and simultaneously estimating the learning capacity of each user at each historical prediction learning time point based on the learning cycle model;
sequentially establishing the difference degree of each user between adjacent learning abilities, and establishing a difference degree set;
correspondingly correcting each layer of the network in the learning period model according to the difference degree set, and estimating a final report form of the same department according to the corrected learning period model;
recording and acquiring real-time learning report forms of online learning of different users in the same department in the online education system;
and performing row-to-column correspondence comparison on the real-time learning report and the final report, extracting row and column information with the contrast ratio greater than a preset degree, and transmitting the row and column information to a corresponding user terminal for display.
In this embodiment, the one-to-one correspondence between rows and columns is because the table includes rows and columns, and the data in each cell is compared correspondingly, so as to prompt the user.
The beneficial effects of the above technical scheme are: by estimating the learning ability of the users and constructing the difference degree of the learning ability between adjacent users in the same department, the total summary report of the same department is convenient to optimize, and the learning efficiency is improved.
The invention provides a big data intelligent report platform facing enterprise online education, which further comprises the following steps in the first analysis processing process of the education service log of each target user:
acquiring the data length of the user information of the target user, and dividing the user information according to a data division rule to obtain a plurality of sections of user subdata;
simultaneously, carrying out binary coding on all the user subdata according to a dividing sequence, and respectively establishing coding units corresponding to one another;
extracting irregular data in the coding unit, and meanwhile, calculating a polymerization degree value of the irregular data and the corresponding user subdata;
if the polymerization degree value exceeds a preset value, carrying out error correction processing on the corresponding coding unit, wherein the error correction processing step comprises the following steps:
dividing the coded data of the coding unit to obtain N information data blocks;
adding a cyclic redundancy check sequence into the N information data blocks, and simultaneously carrying out coding error correction on the N information data blocks added with the cyclic redundancy check sequence so as to obtain N error correction coding blocks;
according to the data of the N error correction coding blocks, carrying out coding processing on the N information data blocks, and acquiring M check packets of the N error correction coding blocks, wherein M is greater than N;
carrying out error correction processing on the coding units corresponding to the N error correction coding blocks and the M check packets, and simultaneously transmitting the error correction processing result to the coding units;
screening data to be replaced in the irregular data in the corresponding coding unit, updating and replacing the data to be replaced based on the data to be updated corresponding to the error correction processing result, and reserving a new coding unit;
if the polymerization degree value does not exceed a preset value, the corresponding coding unit is reserved;
acquiring a characteristic vector set of the education industry log, and constructing a characteristic model by using a convolutional neural network through the characteristic vector set;
classifying the education service log by dividing the feature model based on the unit data of the reserved coding units;
and calling an analysis mode from the analysis database according to the classification result, and performing first analysis processing on the education service log according to the analysis mode.
In this embodiment, the irregular data may be data that is not similar to the original data in the coding unit.
In this embodiment, the polymerization degree value may be a degree of similarity between data.
In this embodiment, the parsing manner may be DOM parsing or SAX parsing.
The beneficial effects of the above technical scheme are: the user information can be effectively divided by obtaining the data length of the user information of a target user, binary coding is carried out on the divided user subdata according to the dividing sequence, a corresponding coding unit can be accurately determined, so that irregular data in the coding unit can be quickly obtained, when the polymerization degree value of the irregular data and the corresponding user subdata exceeds a preset value, the error correction processing on the coding unit can be quickly completed, N information data blocks are effectively obtained by dividing the coding unit, the coding error correction on the N information data blocks can be efficiently completed by adding a cyclic redundancy check sequence in the information data blocks, further N error correction coding blocks are obtained, the error correction processing on the corresponding coding unit can be accurately completed by extracting M check packets in the error correction coding blocks, and the error correction processing result is transmitted into the coding unit, the method is beneficial to screening the replacement data with the irregular data in the corresponding coding unit, updating and replacing are carried out through the replacement data, the data accuracy of the coding unit is guaranteed, the irregular data with the polymerization degree value not exceeding the preset value is reserved, the characteristic model can be accurately and efficiently constructed by acquiring the characteristic vector set of the education service log, the education service log can be accurately classified according to the characteristic model, and a foundation is provided for the first analysis.
The invention provides a big data intelligent report platform for enterprise online education, which is used for summarizing corresponding education service logs into a recording area of a data table according to different target dimensions according to a first analysis processing result, a second analysis processing result and service attributes in a service database, and also comprises the following steps:
determining a comprehensive attribute value of the target dimension, and determining whether the corresponding education service logs can be summarized to a recording area of the data table according to the target dimension according to the comprehensive attribute value, wherein the method comprises the following steps:
acquiring a dimension data set X of the target dimension, and extracting individual sample data in the dimension data set X, wherein,
，
representing the nth sample data;
clustering the sample data, and acquiring the attribute of each type of the clustered sample data
Wherein the first attribute
Has a value range of
Wherein the number of classes of the sample is, and
；
represents the ith attribute value range in the category, and
；i=1,2,3,…,n1；
determining a comprehensive attribute value of the target dimension according to the attribute of the clustered sample data;
wherein the content of the first and second substances,
a composite attribute value representing the target dimension,
j =1,2,3, …, n, representing the jth sample data, wherein the total number of sample data is represented,
representing a clustering probability that a first sample data is classified into a first class;
represents the jth sample data
The degree of difference from the standard sample data,
represents the integrated data density of all of the sample data,
represents a composite weight value of all the sample data,
representing the average clustering accuracy of all the sample data in the clustering process,
represents an average data loss rate of all the sample data,
a standard data density representing the standard sample data,
represents the average weight of all the sample data, and
；
based on a dimension database, calling a target function matched with the comprehensive attribute value, and judging whether the target function meets a preset constraint condition;
if yes, summarizing the corresponding education service logs into the recording area of the data table according to the target dimension.
The beneficial effects of the above technical scheme are: the method has the advantages that the sample data in the target dimension data set is acquired, the attribute of the sample data is convenient to acquire, the comprehensive attribute value of the target dimension is convenient to acquire accurately through the attribute of the sample data, the difference between the sample data and the standard sample data and the average weight of the sample data, the target function matched with the comprehensive attribute value is favorably called through the dimension database, and the corresponding education service logs are gathered in the recording area of the data table for the target dimension meeting the constraint condition, so that the accuracy of the data of the recording area is indirectly improved.
The invention provides a big data intelligent report platform for enterprise online education, which is characterized in that after the objective function is judged not to meet the preset constraint condition,
determining the information entropy of the target dimension according to the comprehensive attribute value;
wherein the content of the first and second substances,
an entropy of information representing the target dimension,
represents a measurement indicator within the target dimension, and
and represents the total number of the measurement indexes,
expressed in the measurement index of
The proportion of the amount of the information to be processed,
a weight coefficient representing the value of the composite attribute,
a composite attribute value representing the target dimension,
a value representing a comprehensive dimension attribute of the target dimension, [2 ]]Representing rounding;
determining whether the information entropy of the target dimension is within a preset information entropy range;
if the information entropy of the target dimension is within the preset information entropy range, summarizing the corresponding education service logs into a recording area of the data table according to the target dimension;
otherwise, screening data to be optimized from the sample data of the target dimension, simultaneously calling dimension optimization parameters from the dimension database according to the information entropy, optimizing the data to be optimized according to the dimension optimization parameters, and optimizing the target dimension according to an optimization processing result.
The beneficial effects of the above technical scheme are: when the target dimension does not meet the preset constraint condition, the information entropy of the target dimension is accurately determined through the comprehensive attribute value and the measurement index in the target dimension, the information entropy of the target dimension is within the preset information entropy range, the corresponding education service logs are gathered into the recording area of the data table through the target dimension, the target dimension which is not within the preset information entropy range is optimized through calling the dimension parameters, accurate optimization processing is carried out, the target dimension is accurately optimized through the processing result, and therefore the rationality of data utilization is greatly improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. The utility model provides a big data intelligence statement platform towards online education of enterprise which characterized in that includes:
counting registered target users based on an online education system, and simultaneously acquiring user information of the target users and education service logs of the target users based on the online education system;
performing first analysis processing on the education service log of each target user based on the analysis database;
performing second analysis processing on the user information of the target user based on a user database;
summarizing corresponding education service logs into a recording area of a data table according to different target dimensions according to the first analysis processing result, the second analysis processing result and service attributes in a service database;
calling information to be summarized related to a preset dimension from the recording area to display according to the input preset dimension;
the step of summarizing the corresponding education service logs into the recording area of the data table according to different target dimensions comprises the following steps:
acquiring a first target project and a second target project related to the education service log;
reading each piece of data in an original business database based on a report system, acquiring a change record of each piece of data, and constructing a record change set;
reading the change records of the first target item based on the record change set, performing data backup, and simultaneously sending a target instruction to a middle message piece;
the second target project part performs service summary calculation of different target dimensions through the intermediate message part according to the target instruction, and reserves a calculation result;
determining a project data volume for the first and second target projects;
when the project data volume is larger than or equal to a preset data volume, using two channels corresponding to a first database, and determining incremental synchronization data of the two channels;
summarizing the reserved calculation results into a recording area of a data table according to different target dimensions according to the incremental synchronous data;
when the project data volume is smaller than the preset data volume, using a single channel corresponding to a second database, and determining incremental asynchronous data of the single channel through two adjacent time intervals;
and summarizing the retained calculation results into a recording area of the data table according to different target dimensions according to the incremental asynchronous data.
2. The big data intelligent reporting platform for enterprise online education as claimed in claim 1, wherein in the process of obtaining the user information of the target user and the education service log of the target user based on the online education system, further comprising:
determining the department where the target user is located according to the user information of the target user, and acquiring department tasks of the department where the target user is located from a report platform, wherein the department tasks comprise: the online learning duration, the online learning course and the online learning task are communicated;
judging whether the target user is qualified for online learning by the current time according to the department task;
if the target users are qualified, keeping the learning records of the target users, making learning reports of the target users, and meanwhile, determining the learning reports of the departments and displaying the learning reports based on each target user;
otherwise, sending an alarm instruction to the terminal of the target user for alarm reminding.
3. The big data intelligent reporting platform for enterprise online education as claimed in claim 2, wherein the step of determining whether the target user is qualified for online learning by the current time comprises:
when the target user logs in the online education system, capturing user watching information of the target user based on a learning interface and playing video information of the learning interface, and acquiring first frame content in the user watching information and second frame content in the playing video information at the same time point according to a timestamp;
performing pre-analysis on the first frame content, determining the current viewing state of the target user, and acquiring a feature vector of the first frame content;
meanwhile, acquiring morphological motion information of the target user based on the previous frame content and the next frame content of the first frame content, and correcting the current viewing state based on the morphological motion information to obtain a real-time viewing state;
preprocessing the second frame content, determining the current playing state of the learning interface, and acquiring a feature vector of the second frame content;
meanwhile, based on the picture display information of the last frame content and the next frame content of the second frame content, the current playing state is corrected, and a real-time playing state is obtained;
determining a distribution distance between the feature vector of the first frame content and the feature vector of the second frame content;
establishing a one-to-one corresponding relation of each time point according to the real-time watching state and the real-time playing state, and correcting the one-to-one corresponding relation according to the distribution distance;
extracting time points with inconsistent real-time watching states and real-time playing states according to the corrected corresponding relations and a preset relation library, calibrating the inconsistent time points, and meanwhile calculating the time ratio of the inconsistent time points to the whole timestamp ending the current time;
when the time ratio is larger than or equal to a preset ratio, judging that the target user is unqualified in online learning, and recording and feeding back inconsistent time points;
otherwise, judging that the target user is qualified for online learning.
4. The big data intelligent reporting platform for enterprise online education as claimed in claim 1, wherein before counting the registered target users based on the online education system, further comprising:
acquiring a historical search record and a historical browsing interface related to the historical search record in the online learning process of the target user based on an online education system, and coding the historical search record and the historical browsing interface;
extracting all action events in the coding processing result, classifying the action events, preprocessing each type of event, and normalizing to obtain a feature vector of each type of event;
capturing system operation information of the target user for performing historical search operations in online learning based on an online education system, wherein the system operation information comprises: the running time, running power and heating parameters of each historical search;
establishing a system operation model of the online education system according to the system operation information, and matching first feedback information related to the system operation model from a model database;
inputting the characteristic vector into the system operation model to obtain second feedback information;
acquiring a first influence factor of the second feedback information aiming at the first feedback information, and acquiring a second influence factor of the first feedback information aiming at the second feedback information;
acquiring an optimization set from an optimization database according to the first feedback information and the second feedback information;
carrying out quantitative adjustment on optimization indexes in the optimization set according to the first influence factor and the second influence factor, and selecting a comprehensive optimization mode from a mode database according to the optimization set subjected to quantitative adjustment;
and performing optimization upgrading on the online education system according to the comprehensive optimization mode, and counting registered target users based on the online education system after optimization upgrading.
5. The big data intelligent reporting platform for enterprise online education as claimed in claim 2, wherein after determining the department of the target user according to the user information of the target user and obtaining the department task of the department from the reporting platform, further comprising:
acquiring historical learning data of all users in the same department of a target enterprise, and establishing a learning cycle model of the same department according to the historical learning data, wherein the historical learning data comprises: the learning progress, learning mastery degree and learning performance of the online education system in the learning process of different users in the same department;
acquiring the time point when each user of the same department reaches each historical prediction learning, and simultaneously estimating the learning capacity of each user at each historical prediction learning time point based on the learning cycle model;
sequentially establishing the difference degree of each user between adjacent learning abilities, and establishing a difference degree set;
correspondingly correcting each layer of the network in the learning period model according to the difference degree set, and estimating a final report form of the same department according to the corrected learning period model;
recording and acquiring real-time learning report forms of online learning of different users in the same department in the online education system;
and performing row-to-column correspondence comparison on the real-time learning report and the final report, extracting row and column information with the contrast ratio greater than a preset degree, and transmitting the row and column information to a corresponding user terminal for display.
6. The big data intelligent reporting platform for enterprise online education as claimed in claim 1, wherein in the first parsing process of the education service log of each target user, further comprising:
acquiring the data length of the user information of the target user, and dividing the user information according to a data division rule to obtain a plurality of sections of user subdata;
simultaneously, carrying out binary coding on all the user subdata according to a dividing sequence, and respectively establishing coding units corresponding to one another;
extracting irregular data in the coding unit, and meanwhile, calculating a polymerization degree value of the irregular data and the corresponding user subdata;
if the polymerization degree value exceeds a preset value, carrying out error correction processing on the corresponding coding unit, wherein the error correction processing step comprises the following steps:
dividing the coded data of the coding unit to obtain N information data blocks;
adding a cyclic redundancy check sequence into the N information data blocks, and simultaneously carrying out coding error correction on the N information data blocks added with the cyclic redundancy check sequence so as to obtain N error correction coding blocks;
according to the data of the N error correction coding blocks, carrying out coding processing on the N information data blocks, and acquiring M check packets of the N error correction coding blocks, wherein M is greater than N;
carrying out error correction processing on the coding units corresponding to the N error correction coding blocks and the M check packets, and simultaneously transmitting the error correction processing result to the coding units;
screening data to be replaced in the irregular data in the corresponding coding unit, updating and replacing the data to be replaced based on the data to be updated corresponding to the error correction processing result, and reserving a new coding unit;
if the polymerization degree value does not exceed a preset value, the corresponding coding unit is reserved;
acquiring a characteristic vector set of the education service log, and constructing a characteristic model by using a convolutional neural network through the characteristic vector set;
classifying the education service log by dividing the feature model based on the unit data of the reserved coding units;
and calling an analysis mode from the analysis database according to the classification result, and performing first analysis processing on the education service log according to the analysis mode.
7. The big data intelligent reporting platform for enterprise online education as claimed in claim 1, wherein according to the first parsing result, the second parsing result and the business attributes in the business database, before summarizing the corresponding education business logs into the recording area of the data table according to different target dimensions, further comprising:
determining a comprehensive attribute value of the target dimension, and determining whether the corresponding education service logs can be summarized to a recording area of the data table according to the target dimension according to the comprehensive attribute value, wherein the method comprises the following steps:
acquiring a dimension data set X of the target dimension, and extracting individual sample data in the dimension data set X, wherein,
，
representing the nth sample data; representing the 1 st sample data; representing the 2 nd sample data;
clustering the sample data, and acquiring the attribute of each type of the clustered sample data
determining a comprehensive attribute value of the target dimension according to the attribute of the clustered sample data;
wherein a composite attribute value representing the target dimension,
j =1,2,3, …, n, representing the jth sample data, wherein the total number of sample data is represented,
representing a clustering probability that a first sample data is classified into a first class;
representing the degree of difference between the jth sample data and standard sample data,
represents the integrated data density of all of the sample data,
represents a composite weight value of all the sample data,
representing the average clustering accuracy of all the sample data in the clustering process,
represents an average data loss rate of all the sample data,
a standard data density representing the standard sample data,
represents the average weight of all the sample data, and
；
based on a dimension database, calling a target function matched with the comprehensive attribute value, and judging whether the target function meets a preset constraint condition;
if yes, summarizing the corresponding education service logs into the recording area of the data table according to the target dimension.
8. The big data intelligent reporting platform for enterprise online education as claimed in claim 7, wherein after the objective function is judged not to satisfy the preset constraint condition,
determining the information entropy of the target dimension according to the comprehensive attribute value;
wherein the content of the first and second substances,
an entropy of information representing the target dimension,
represents a measurement indicator within the target dimension, and
and is and
the total number of the measurement indexes is expressed,
expressed in the measurement index of
The proportion of the amount of the information to be processed,
a weight coefficient representing the value of the composite attribute,
a composite attribute value representing the target dimension,
a value representing a comprehensive dimension attribute of the target dimension, [2 ]]Representing rounding;
determining whether the information entropy of the target dimension is within a preset information entropy range;
if the information entropy of the target dimension is within the preset information entropy range, summarizing the corresponding education service logs into a recording area of the data table according to the target dimension;
otherwise, screening data to be optimized from the sample data of the target dimension, simultaneously calling dimension optimization parameters from the dimension database according to the information entropy, optimizing the data to be optimized according to the dimension optimization parameters, and optimizing the target dimension according to an optimization processing result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011054974.XA CN111897859B (en) | 2020-09-30 | 2020-09-30 | Big data intelligent report platform for enterprise online education |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011054974.XA CN111897859B (en) | 2020-09-30 | 2020-09-30 | Big data intelligent report platform for enterprise online education |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111897859A CN111897859A (en) | 2020-11-06 |
| CN111897859B true CN111897859B (en) | 2021-01-05 |
Family
ID=73224081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011054974.XA Active CN111897859B (en) | 2020-09-30 | 2020-09-30 | Big data intelligent report platform for enterprise online education |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111897859B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114780622B (en) * | 2022-06-27 | 2022-09-02 | 天津能源物联网科技股份有限公司 | Intelligent heat supply data analysis method and system based on big data platform |
| CN116048985B (en) * | 2023-01-10 | 2023-10-20 | 睿智合创(北京)科技有限公司 | Decision data measurement and viewing result report method |
| CN117648383A (en) * | 2024-01-30 | 2024-03-05 | 中国人民解放军国防科技大学 | Heterogeneous database real-time data synchronization method, device, equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010277202A (en) * | 2009-05-26 | 2010-12-09 | Nippon Telegr & Teleph Corp <Ntt> | Educational social networking service provision device, method and program, and computer-readable recording medium |
| JP2018032276A (en) * | 2016-08-25 | 2018-03-01 | 株式会社内田洋行 | Educational learning activity support system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107577805B (en) * | 2017-09-26 | 2020-08-18 | 华南理工大学 | Business service system for log big data analysis |
| CN109766417B (en) * | 2018-11-30 | 2020-11-24 | 浙江大学 | Knowledge graph-based literature dating history question-answering system construction method |
| CN110457259A (en) * | 2019-08-06 | 2019-11-15 | 合肥泓泉档案信息科技有限公司 | A kind of archival digitalization management and analysis |
-
2020
- 2020-09-30 CN CN202011054974.XA patent/CN111897859B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010277202A (en) * | 2009-05-26 | 2010-12-09 | Nippon Telegr & Teleph Corp <Ntt> | Educational social networking service provision device, method and program, and computer-readable recording medium |
| JP2018032276A (en) * | 2016-08-25 | 2018-03-01 | 株式会社内田洋行 | Educational learning activity support system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111897859A (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111897859B (en) | Big data intelligent report platform for enterprise online education | |
| US9921936B2 (en) | Method and system for IT resources performance analysis | |
| CN111127105A (en) | User hierarchical model construction method and system, and operation analysis method and system | |
| CN111737646B (en) | Advertisement promotion effect evaluation data processing method, system and storage medium | |
| CN112131203A (en) | Method and system for building data warehouse | |
| CN102497435A (en) | Data distributing method and device of data service | |
| CN114266492A (en) | Enterprise financing fund matching method based on data mining | |
| CN113220756A (en) | Logistics data real-time processing method, device, equipment and storage medium | |
| CN115719283A (en) | Intelligent accounting management system | |
| CN116468536A (en) | Automatic risk control rule generation method | |
| CN115617743A (en) | Science and technology project archive management system based on data acquisition | |
| CN113628024A (en) | Financial data intelligent auditing system and method based on big data platform system | |
| CN112001539B (en) | High-precision passenger transport prediction method and passenger transport prediction system | |
| CN111031363B (en) | User audience situation prediction method and system based on quantitative big data | |
| CN117290364A (en) | Intelligent market investigation data storage method | |
| CN112990569A (en) | Fruit price prediction method | |
| CN114625901B (en) | Multi-algorithm integration method and device | |
| CN116127194A (en) | Enterprise recommendation method | |
| CN116185797A (en) | Method, device and storage medium for predicting server resource saturation | |
| CN111882289B (en) | Device and method for measuring and calculating project data auditing index interval | |
| US20240004375A1 (en) | Data processing method, and electronic device and storage medium | |
| CN111143688A (en) | Evaluation method and system based on mobile news client | |
| CN117151948B (en) | College student outgoing check-in comprehensive management method and system | |
| CN117094743B (en) | Automatic cigarette retail market data statistical analysis system and method | |
| CN115034659A (en) | Data source evaluation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No.637, 6 / F, 101 West Fourth Ring Road South, Fengtai District, Beijing Patentee after: Zhixueyun (Beijing) Technology Co.,Ltd. Address before: No.637, 6 / F, 101 West Fourth Ring Road South, Fengtai District, Beijing Patentee before: Zhixueyun (Beijing) Technology Co.,Ltd. |