CN111597442A - Classroom learning method based on big data - Google Patents
Classroom learning method based on big data Download PDFInfo
- Publication number
- CN111597442A CN111597442A CN202010396216.XA CN202010396216A CN111597442A CN 111597442 A CN111597442 A CN 111597442A CN 202010396216 A CN202010396216 A CN 202010396216A CN 111597442 A CN111597442 A CN 111597442A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- learning
- learning data
- information
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012795 verification Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 40
- 238000007418 data mining Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 239000002131 composite material Substances 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012552 review Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 8
- 238000002360 preparation method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Networks & Wireless Communication (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a classroom learning method based on big data, which comprises the following steps: connecting a terminal where a user is located with a big data server; after the connection is successful, verifying the identity information of the user; after the verification is finished, acquiring a network request sent by a terminal, identifying a network identifier of the network request and analyzing flow information of the network request, wherein the flow information comprises request content and a flow schedule; acquiring current learning data from a big data server according to the network identification and the flow information; and transmitting the current learning data to the terminal for the user to learn. The accurate current learning data is obtained by utilizing the network identification and the flow information identified by the network request sent by the user terminal, compared with the prior art that a large amount of useless learning data is fed back according to the user request so that the user needs to screen the target content, the time is greatly saved, the learning efficiency is improved, and the experience of the user is improved.
Description
Technical Field
The invention relates to the technical field of IT big data, in particular to a classroom learning method based on big data.
Background
At present, online education is more popular with parents and teachers, so that students and teachers can teach and receive knowledge at home without teaching environment limitation and departing from a face-to-face education mode, but the prior online education method is that the teachers prepare ppt and content to be spoken in advance on first terminals of the teachers and then carry out video connection with second terminals of the students and give lessons, but if the teachers do not have the time to prepare the ppt and the content of the lessons, the quality of a classroom is low due to insufficient preparation, so that the learning efficiency of the students is seriously influenced, scientists propose a method for autonomous learning by using big data knowledge, the flow of the method is that a big data end is connected with a user to obtain required knowledge content from the big data end for autonomous learning, but the method has the following problems that a great amount of big data can feed back a great amount of learning content according to the needs of the user after the user sends out a learning application, however, most of the learning contents are not needed by the user, so the user is required to manually screen the learning contents needed by the user, which wastes time and has low efficiency, and the user experience is poor.
Disclosure of Invention
Aiming at the displayed problems, the method is based on the fact that a user terminal connected with a big data server end is verified, network identification and flow information are obtained after a network request sent by a user end is identified and analyzed, and then accurate learning data are obtained according to the network identification and the flow information and are pushed to the terminal where the user is located.
A classroom learning method based on big data comprises the following steps:
connecting a terminal where a user is located with a big data server; after the connection is successful, verifying the identity information of the user;
after the verification is finished, acquiring a network request sent by the terminal, identifying a network identifier of the network request and analyzing flow information of the network request, wherein the flow information comprises request content and a flow schedule;
acquiring current learning data from the big data server according to the network identification and the process information;
and transmitting the current learning data to the terminal for the user to learn.
Preferably, the connection between the terminal where the user is located and the big data server is connected; after the connection is successful, verifying the identity information of the user, including:
sending the identification information and the connection request of the terminal to the big data server so that the big data server checks the identification information and the connection request, and generating feedback information to the terminal after the check is finished;
if the feedback information is connectable, connecting the terminal with the big data server;
if the feedback result is that the connection cannot be performed, displaying a message of 'unable connection to the server' on the terminal;
after the connection is successful, acquiring current scene information of the user and analyzing the current scene information to analyze whether the current scene information is common preset scene information or not;
if the current scene information is the common preset scene information, sending a prompt for acquiring a user name and a password registered by a user to the terminal;
if the current scene information is not the common preset scene information, sending a prompt for acquiring a user name and a password registered by the user and face identification to the terminal;
after the user name and the password input by the user and the current face image are obtained, whether the user name and the password are correct or not and whether the current face image is a preset face image or not are confirmed;
if so, sending an identity confirmation prompt to the terminal;
otherwise, sending out the prompt that the identity is invalid to the terminal.
Preferably, after displaying a message of "unable to connect to the server" on the terminal if the feedback result is that the connection is impossible, the method further includes:
analyzing the reason why the terminal cannot be connected with the big data server end to generate an analysis report;
and displaying the analysis report on the terminal so that the user can process the analysis report.
Preferably, after the verification is completed, acquiring a network request sent by the terminal, identifying a network identifier of the network request, and analyzing flow information of the network request, where the flow information includes request content and a flow schedule, and includes:
acquiring a network parameter corresponding to the network request;
allocating a unique identifier for the network parameter, and confirming the unique identifier as the network identifier;
parsing the network request to obtain requested content, the requested content comprising: one or more of subject knowledge, papers, periodicals;
and after the request content is analyzed, generating the flow schedule.
Preferably, the obtaining current learning data from the big data server according to the network identifier and the flow information includes:
acquiring a knowledge recommendation set from a big database in a big data server according to the request content;
pushing the knowledge recommendation set to the terminal to obtain the interest degree of the user for each learning data in the knowledge recommendation set, and obtaining n interest degrees;
constructing a user interest matrix based on the n interest degrees;
selecting a target interest degree with the maximum interest degree from the user interest matrix, and acquiring target learning data corresponding to the target interest degree;
confirming the target learning data as the current learning data.
Preferably, the method further comprises:
acquiring user interest matrixes of different users, calculating the similarity of each user interest matrix by using a similarity algorithm, and constructing a user similarity matrix;
acquiring learning data contained in each user interest matrix in the user interest matrixes of different users, calculating the similarity of the learning data by using a similarity algorithm, and constructing a learning data similarity matrix;
constructing a user recommendation matrix and a learning data recommendation matrix according to the user similarity matrix and the learning data similarity matrix;
and after the construction is finished, scheduling a pre-established network model, and inputting the plurality of user information in the user recommendation matrix and the plurality of learning data in the learning data recommendation matrix into the network model for training until the network model converges.
Preferably, the method further comprises:
preprocessing the current learning data;
confirming the function type and data characteristics of the preprocessed current learning data;
searching in a big database according to the function type of the current learning data, and counting out first associated information content;
carrying out secondary retrieval in the big database according to the data characteristics of the current learning data, and counting out second associated information content;
storing and determining the first associated information content and the second associated information content as data mining information;
interpreting and evaluating the data mining information to generate a data mining report;
and displaying the data mining information and the data mining report on the terminal.
Preferably, the method further comprises:
counting m first learning data acquired by the user at m moments;
determining a first data type of each of the m first learning data;
acquiring second learning data corresponding to a preset number of kth moments, and acquiring a second data type of the second learning data, wherein the kth moment is any one moment in m moments;
judging whether the probability that a preset number of second data types are the same as the first data types is greater than or equal to a preset probability or not;
if so, training a network model by using the m moments and the m first data types to obtain a trained network model;
when the user sends a learning request, counting the current time corresponding to the learning request, and recommending the learning data similar to the first data type corresponding to the current time for the user by using the trained network model.
Preferably, the method further comprises:
acquiring the learning progress of the user on the current learning data in real time;
updating a flow schedule according to the learning progress;
when the process schedule is displayed, storing the current learning data and the identity information of the user into a pre-established learning record folder;
after the storage is finished, generating a compressed file according to the learning record folder, and sending the compressed file to the terminal so that the user can check and review the compressed file at any time;
and updating the learning record folder in real time according to the learning frequency of the user.
Preferably, the acquiring a knowledge recommendation set from a big database in a big data server according to the request content includes;
step B1, obtaining a composite word in the request content, wherein the composite word can be one or more of a word, a single character and a idiom;
step B1, setting the synthesized word as a word sequence X (X)1,X2,X3,....Xn)；
Step B2, calculating the similarity between the learning data in the big database and the word sequence X by using the following formula:
wherein Sim (X, Y) represents the similarity between the learning data in the big database and the word sequence X, n represents the total number of synthesized words in the word sequence X, q represents the q-th synthesized word, mqA synthetic sequence value expressed as the q-th synthetic word, g is the total number of the learning data, h is the h-th learning data, bhA learning sequence value expressed as the h-th learning data;
step B3, calculating the information gain of each synthesized word in the word sequence X;
wherein, P (C)q) Is represented as CqProbability value of class document in g learning data, PqThe g learning data are expressed to contain the proportion of the synthesized word q, and W is expressed as the information gain of each synthesized word;
step B4, obtaining a prediction value according to the information gain and the similarity;
repeating the steps B3-B4 to obtain a plurality of inferred values;
and acquiring final learning data corresponding to the plurality of inference values to generate the knowledge inference set.
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.
Fig. 1 is a flowchart illustrating a big data-based classroom learning method according to the present invention;
FIG. 2 is another flowchart of the big data-based classroom learning method provided by the present invention;
fig. 3 is another work flow chart of the big data-based classroom learning method provided by the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
At present, online education is more popular with parents and teachers, so that students and teachers can teach and receive knowledge at home without teaching environment limitation and departing from a face-to-face education mode, but the prior online education method is that the teachers prepare ppt and content to be spoken in advance on first terminals of the teachers and then carry out video connection with second terminals of the students and give lessons, but if the teachers do not have the time to prepare the ppt and the content of the lessons, the quality of a classroom is low due to insufficient preparation, so that the learning efficiency of the students is seriously influenced, scientists propose a method for autonomous learning by using big data knowledge, the flow of the method is that a big data end is connected with a user to obtain required knowledge content from the big data end for autonomous learning, but the method has the following problems that a great amount of big data can feed back a great amount of learning content according to the needs of the user after the user sends out a learning application, however, most of the learning contents are not needed by the user, so the user is required to manually screen the learning contents needed by the user, which wastes time and has low efficiency, and the user experience is poor. In order to solve the above problem, this embodiment discloses a method for obtaining network identification and flow information after identifying and analyzing a network request sent by a user side based on a user terminal connected to a big data server side, and then obtaining accurate learning data according to the network identification and the flow information and pushing the learning data to a terminal where a user is located.
A big data-based classroom learning method, as shown in fig. 1, includes the following steps:
s101, connecting a terminal where a user is located with a big data server; after the connection is successful, verifying the identity information of the user;
step S102, after the verification is finished, acquiring a network request sent by a terminal, identifying a network identifier of the network request and analyzing flow information of the network request, wherein the flow information comprises request content and a flow schedule;
step S103, acquiring current learning data from a big data server according to the network identification and the process information;
step S104, transmitting the current learning data to a terminal for a user to learn;
in this embodiment, the connection between the terminal where the user is located and the big data server is firstly connected through the network, the connection may be in a manner that the network accesses the big data server, and after the connection is successful, the identity information of the user is verified to determine whether the user is a legal user for utilizing the big data. And when the verification is successful, acquiring a network request sent by a user at a terminal, identifying a network identifier of the network request, wherein the network identifier is a unique identifier of each user terminal, analyzing the flow information of the network request, wherein the flow information comprises request content and a flow schedule, the request content is learning data required by the user, acquiring accurate current learning data from a big data server according to the network identifier and the flow information, and finally transmitting the accurate current learning data to the terminal where the user is located for the user to learn and look up.
The working principle of the technical scheme is as follows: connecting a terminal where a user is located with a big data server; after the connection is successful, verifying the identity information of the user; after the verification is finished, acquiring a network request sent by a terminal, identifying a network identifier of the network request and analyzing flow information of the network request, wherein the flow information comprises request content and a flow schedule; acquiring current learning data from a big data server according to the network identification and the flow information; and transmitting the current learning data to the terminal for the user to learn.
The beneficial effects of the above technical scheme are: the accurate current learning data is obtained by utilizing the network identification and the flow information identified by the network request sent by the user terminal, compared with the prior art that a large amount of useless learning data is fed back according to the user request so that the user needs to screen the target content, the time is greatly saved, the learning efficiency is improved, and the experience of the user is improved.
In one embodiment, the connection between the terminal where the user is located and the big data server is connected; after the connection is successful, verifying the identity information of the user, including:
sending the identification information and the connection request of the terminal to a big data server so that the big data server checks the identification information and the connection request, and generating feedback information to the terminal after the checking is finished;
if the feedback information is connectable, connecting the terminal with the big data server;
if the feedback result is that the connection cannot be carried out, displaying a message of 'unable connection to the server side' on the terminal;
after the connection is successful, acquiring current scene information of a user, analyzing the current scene information, and analyzing whether the current scene information is common preset scene information;
if the current scene information is common preset scene information, sending a prompt for acquiring a user name and a password registered by a user to a terminal;
if the current scene information is not the common preset scene information, sending a prompt for acquiring a user name and a password registered by the user and face identification to the terminal;
after a user name and a password input by a user and a current face image are obtained, whether the user name and the password are correct or not and whether the current face image is a preset face image or not are confirmed;
if so, sending an identity confirmation prompt to the terminal;
otherwise, sending an invalid identity prompt to the terminal.
The beneficial effects of the above technical scheme are: the security of big data is ensured, and the security of the identity information of the user is ensured by double verification of the identity information of the user. The use safety of big data is further improved.
In one embodiment, after displaying a message of "no connection to the server" on the terminal if the feedback result is that no connection is possible, the method further includes:
analyzing the reason that the terminal cannot be connected with the big data server end to generate an analysis report;
displaying the analysis report on a terminal so that a user can process the analysis report;
in this embodiment, the specific process of analyzing the reason why the terminal cannot connect to the big data server is to detect whether the network connection of the user terminal is normal or not, input "abnormal network connection" into the analysis report if the network connection of the user terminal is abnormal, check whether the server state of the big data server is normal or not if the network connection of the user terminal is normal, input "abnormal server state" into the analysis report if the server state is abnormal, detect whether the network environment of the user terminal is abnormal if the server state is normal, and input "abnormal network environment" into the analysis report if the network environment of the user is abnormal. After the analysis report is generated, the analysis report is displayed on a terminal where the user is located so that the user can repair the problem in the analysis report, and particularly, when the analysis report is abnormal in server state, a prompt that the user waits for the server to be maintained is sent to the user.
The beneficial effects of the above technical scheme are: the user can accurately know the reason why the big data server end cannot be connected and process according to the reason so as to conveniently connect the big data server end for learning.
In an embodiment, as shown in fig. 2, after the verification is completed, acquiring a network request sent by a terminal, identifying a network identifier of the network request, and parsing flow information of the network request, where the flow information includes request content and a flow schedule, and the method includes:
step S201, obtaining a network parameter corresponding to the network request;
step S202, allocating a unique identifier for the network parameter, and determining the unique identifier as the network identifier;
step S203, parsing the network request to obtain a request content, where the request content includes: one or more of subject knowledge, papers, periodicals;
step S204, after the request content is analyzed, a flow schedule is generated;
in this embodiment, the network parameter may be an ip address of a terminal where the user is located, a unique identifier is allocated to the ip address of the user, the identifier is determined as a network identifier, the network request is analyzed to obtain request content, the analysis mode may be a mode of analyzing a keyword in the network request sent by the user, after the request content of the user is analyzed, a flow schedule is generated, and the flow schedule is used to record a learning progress of the user on learning data so as to know the learning condition and the learning progress of the user in real time.
The technical scheme has the advantages that the request content can be accurately analyzed according to the network request sent by the user, the target learning data can be rapidly acquired according to the request content, the retrieval time is saved, and the efficiency is improved.
In one embodiment, the obtaining of the current learning data from the big data server according to the network identifier and the flow information includes:
acquiring a knowledge recommendation set from a big database in a big data server side according to the request content;
pushing the knowledge recommendation set to a terminal to obtain the interest degree of each learning data in the knowledge recommendation set by a user, and obtaining n interest degrees;
constructing a user interest matrix based on the n interest degrees;
selecting a target interest degree with the maximum interest degree from the user interest matrix, and acquiring target learning data corresponding to the target interest degree;
confirming the target learning data as current learning data;
in this embodiment, n is a positive integer greater than or equal to 2, the search can be quickly performed in the large database according to the keyword of the user to generate an indication recommendation set related to the keyword, the indication recommendation set includes a plurality of learning data, then, the interest level of the user in each learning data in the plurality of learning data is obtained, n interest levels are obtained, a user interest matrix is constructed by using the n interest levels, and the target learning data with the maximum user interest level is selected from the matrix and is pushed to the terminal of the user as the current learning data for the user to learn and refer to.
The beneficial effects of the above technical scheme are: the target learning data with the maximum user interest degree is selected to be pushed to the terminal of the client, so that the requirements of the user are met, the interest of the user is considered, and the experience of the user is further improved.
In one embodiment, as shown in fig. 3, the method further comprises:
s301, obtaining user interest matrixes of different users, calculating the similarity of each user interest matrix by using a similarity algorithm, and constructing a user similarity matrix;
step S302, learning data contained in each user interest matrix in the user interest matrixes of different users are obtained, the similarity of the learning data is calculated by using a similarity algorithm, and a learning data similarity matrix is constructed;
step S303, constructing a user recommendation matrix and a learning data recommendation matrix according to the user similarity matrix and the learning data similarity matrix;
step S304, after the construction is finished, a pre-established network model is scheduled, and a plurality of pieces of user information in the user recommendation matrix and a plurality of pieces of learning data in the learning data recommendation matrix are input into the network model for training until the network model converges.
The beneficial effects of the above technical scheme are: the user recommendation matrix and the learning data recommendation matrix can be used for pushing a person with the same interest degree in a certain learning data simultaneously or pushing the learning data of another user with the same interest degree in a certain user, so that each user can know more learning data and learn more knowledge, and the learning efficiency is further improved.
In one embodiment, the method further comprises:
preprocessing the current learning data;
confirming the function type and data characteristics of the preprocessed current learning data;
searching in a big database according to the function type of the current learning data, and counting out first associated information content;
carrying out secondary retrieval in the big database according to the data characteristics of the current learning data, and counting out second associated information content;
storing and determining the first associated information content and the second associated information content as data mining information;
interpreting and evaluating the data mining information to generate a data mining report;
displaying data mining information and data mining reports on the terminal;
in this embodiment, the pretreatment is: checking the integrity and consistency of each datum in the current learning data; denoising, filling up missing fields and deleting invalid data are carried out on each piece of current learning data, then the function type and the data characteristics of the current learning data are confirmed, wherein the function type can be calculation, statistics, thinking, research, practice and the like, and the data characteristics can be the composition of the learning data, the arrangement of the learning data and the like. And then acquiring first associated information and second associated information from a big database according to the function type and the data characteristics of the learning data, storing the first associated information and the second associated information together and determining the first associated information and the second associated information as data mining information, then explaining and evaluating the data mining information, wherein the explained content can be the source and the reason of the data, the evaluated content can be the similarity of the data mining information and the current data and the grade of the content, and finally displaying the data mining information and a data mining report on a terminal where a user is located, and the user can choose to browse or skip the data mining information and the data mining report.
The beneficial effects of the above technical scheme are: the data mining information is provided for the user, so that the user can browse and learn more learning data, the user does not need to manually search other learning data in a complicated way, the time is saved, the user is prevented from missing important learning data, and the experience of the user is further improved.
In one embodiment, the method further comprises:
counting m first learning data acquired by a user at m moments;
determining a first data type of each of the m first learning data;
acquiring second learning data corresponding to a preset number of kth moments, and acquiring a second data type of the second learning data, wherein the kth moment is any one moment in m moments;
judging whether the probability that the preset number of second data types are the same as the first data types is greater than or equal to the preset probability or not;
if so, training the network model by using m moments and m first data types to obtain a trained network model;
when a user sends a learning request, counting the current time corresponding to the sent learning request, and recommending the learning data with the type similar to the first data type corresponding to the current time for the user by using the trained network model;
in this embodiment, the m is a positive integer greater than or equal to 5, first 8 learning data of the user at different 8 moments and 8 learning data corresponding to the 8 moments are counted, where the 8 moments may be specific integer moments or integer moments plus zero moments, for example, three quarters in the afternoon or eight quarters in the morning, and then a first data type of the 8 learning data is determined. After the determination, respectively corresponding 8 first data types and 8 learning data, taking the fifth noon as an example, obtaining first learning data of the fifth noon and determining first data types of the first learning data to store, then discontinuously obtaining a plurality of second learning data of the fifth noon, determining second data types of the plurality of second learning data, determining similarity between the plurality of second data types and the first data types, wherein the similarity is the same number ratio of the plurality of second data types as the first data types, when the similarity is greater than or equal to a preset probability, determining that the preference data type of the user is the learning data of the first data type at the fifth noon, wherein the preset probability can be 70%, then training the network model by using the time of the fifth noon and the corresponding first data types until the model converges, and when the user sends a network request every fifth noon, the learning data of the first data type is pushed for the user, the user does not need to search and retrieve, and fast learning is achieved.
The beneficial effects of the above technical scheme are: learning data of different data types are regularly pushed according to the learning habits of the user, the situation that the user actively searches the learning data related to the first data type every time is avoided, and the learning efficiency and the learning accuracy are effectively improved.
In one embodiment, the method further comprises:
acquiring the learning progress of a user on current learning data in real time;
updating a flow schedule according to the learning progress;
when the process schedule is displayed, storing the current learning data and the identity information of the user into a pre-established learning record folder;
after the storage is finished, generating a compressed file according to the learning record folder, and sending the compressed file to the terminal so that a user can check and review the compressed file at any time;
and updating the learning record folder in real time according to the learning frequency of the user.
The beneficial effects of the above technical scheme are: the user can browse the learned data at any time for reviewing without beginning to learn, and time is saved.
In one embodiment, a knowledge recommendation set is obtained from a big database in a big data server according to the request content, including;
step B1, obtaining the synthesized words in the request content, wherein the synthesized words can be one or more of words, single characters and idioms;
step B1, setting the synthesized word as a word sequence X (X)1,X2,X3,....Xn)；
Step B2, calculating the similarity between the learning data in the big database and the word sequence X by using the following formula:
wherein Sim (X, Y) represents the similarity between the learning data in the large database and the word sequence X, n represents the total number of synthetic words in the word sequence X, q represents the q-th synthetic word, m representsqA synthetic sequence value expressed as the q-th synthetic word, g is the total number of the learning data, h is the h-th learning data, bhA learning sequence value expressed as the h-th learning data;
step B3, calculating the information gain of each synthesized word in the word sequence X;
wherein, P (C)q) Is represented as CqProbability value of class document in g learning data, PqThe g learning data are expressed to contain the proportion of the synthesized word q, and W is expressed as the information gain of each synthesized word;
step B4, obtaining a prediction value according to the information gain and the similarity;
repeating the steps B3-B4 to obtain a plurality of inferred values;
and acquiring final learning data corresponding to the plurality of inference values to generate the knowledge inference set.
The beneficial effects of the above technical scheme are: the similarity and difference in semantic aspect between words can be accurately reflected, the learning data of the user psychology instrument can be more accurately acquired from the large database, the information gain can be calculated to reflect the information amount which can be provided by the synthesized word for the whole learning data, the importance of the synthesized word can be accurately judged, the main work of searching the learning data by partial synthesized words can be omitted as appropriate, the main work is distributed to the relatively important synthesized word for searching, the searching accuracy is improved, and the working time is reduced.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A classroom learning method based on big data is characterized by comprising the following steps:
connecting a terminal where a user is located with a big data server; after the connection is successful, verifying the identity information of the user;
after the verification is finished, acquiring a network request sent by the terminal, identifying a network identifier of the network request and analyzing flow information of the network request, wherein the flow information comprises request content and a flow schedule;
acquiring current learning data from the big data server according to the network identification and the process information;
and transmitting the current learning data to the terminal for the user to learn.
2. The big-data-based classroom learning method according to claim 1, wherein the connection between the terminal where the user is located and the big data server is established; after the connection is successful, verifying the identity information of the user, including:
sending the identification information and the connection request of the terminal to the big data server so that the big data server checks the identification information and the connection request, and generating feedback information to the terminal after the check is finished;
if the feedback information is connectable, connecting the terminal with the big data server;
if the feedback result is that the connection cannot be performed, displaying a message of 'unable connection to the server' on the terminal;
after the connection is successful, acquiring current scene information of the user and analyzing the current scene information to analyze whether the current scene information is common preset scene information or not;
if the current scene information is the common preset scene information, sending a prompt for acquiring a user name and a password registered by a user to the terminal;
if the current scene information is not the common preset scene information, sending a prompt for acquiring a user name and a password registered by the user and face identification to the terminal;
after the user name and the password input by the user and the current face image are obtained, whether the user name and the password are correct or not and whether the current face image is a preset face image or not are confirmed;
if so, sending an identity confirmation prompt to the terminal;
otherwise, sending out the prompt that the identity is invalid to the terminal.
3. The big-data based classroom learning method of claim 1, wherein after displaying a "no connection to server" message on the terminal if the feedback result is that no connection is possible, the method further comprises:
analyzing the reason why the terminal cannot be connected with the big data server end to generate an analysis report;
and displaying the analysis report on the terminal so that the user can process the analysis report.
4. The big-data-based classroom learning method according to claim 1, wherein after the verification is completed, the method obtains a network request sent by the terminal, identifies a network identifier of the network request, and parses flow information of the network request, wherein the flow information includes request content and a flow schedule, and comprises:
acquiring a network parameter corresponding to the network request;
allocating a unique identifier for the network parameter, and confirming the unique identifier as the network identifier;
parsing the network request to obtain requested content, the requested content comprising: one or more of subject knowledge, papers, periodicals;
and after the request content is analyzed, generating the flow schedule.
5. The big data based classroom learning method of claim 1, wherein said obtaining current learning data from said big data server based on said network identification and flow information comprises:
acquiring a knowledge recommendation set from a big database in a big data server according to the request content;
pushing the knowledge recommendation set to the terminal to obtain the interest degree of the user for each learning data in the knowledge recommendation set, and obtaining n interest degrees;
constructing a user interest matrix based on the n interest degrees;
selecting a target interest degree with the maximum interest degree from the user interest matrix, and acquiring target learning data corresponding to the target interest degree;
confirming the target learning data as the current learning data.
6. The big-data based classroom learning method of claim 5, wherein said method further comprises:
acquiring user interest matrixes of different users, calculating the similarity of each user interest matrix by using a similarity algorithm, and constructing a user similarity matrix;
acquiring learning data contained in each user interest matrix in the user interest matrixes of different users, calculating the similarity of the learning data by using a similarity algorithm, and constructing a learning data similarity matrix;
constructing a user recommendation matrix and a learning data recommendation matrix according to the user similarity matrix and the learning data similarity matrix;
and after the construction is finished, scheduling a pre-established network model, and inputting the plurality of user information in the user recommendation matrix and the plurality of learning data in the learning data recommendation matrix into the network model for training until the network model converges.
7. The big-data based classroom learning method of claim 1, wherein said method further comprises:
preprocessing the current learning data;
confirming the function type and data characteristics of the preprocessed current learning data;
searching in a big database according to the function type of the current learning data, and counting out first associated information content;
carrying out secondary retrieval in the big database according to the data characteristics of the current learning data, and counting out second associated information content;
storing and determining the first associated information content and the second associated information content as data mining information;
interpreting and evaluating the data mining information to generate a data mining report;
and displaying the data mining information and the data mining report on the terminal.
8. The big-data based classroom learning method of claim 1, wherein said method further comprises:
counting m first learning data acquired by the user at m moments;
determining a first data type of each of the m first learning data;
acquiring second learning data corresponding to a preset number of kth moments, and acquiring a second data type of the second learning data, wherein the kth moment is any one moment in m moments;
judging whether the probability that a preset number of second data types are the same as the first data types is greater than or equal to a preset probability or not;
if so, training a network model by using the m moments and the m first data types to obtain a trained network model;
when the user sends a learning request, counting the current time corresponding to the learning request, and recommending the learning data similar to the first data type corresponding to the current time for the user by using the trained network model.
9. The big-data based classroom learning method of claim 1, wherein said method further comprises:
acquiring the learning progress of the user on the current learning data in real time;
updating a flow schedule according to the learning progress;
when the process schedule is displayed, storing the current learning data and the identity information of the user into a pre-established learning record folder;
after the storage is finished, generating a compressed file according to the learning record folder, and sending the compressed file to the terminal so that the user can check and review the compressed file at any time;
and updating the learning record folder in real time according to the learning frequency of the user.
10. The big-data based classroom learning method of claim 5, wherein said obtaining a knowledge recommendation set from a big database in a big data server according to said requested content comprises;
step B1, obtaining a composite word in the request content, wherein the composite word can be one or more of a word, a single character and a idiom;
step B1, setting the synthesized word as a word sequence X (X)1,X2,X3,....Xn)；
Step B2, calculating the similarity between the learning data in the big database and the word sequence X by using the following formula:
wherein Sim (X, Y) represents the similarity between the learning data in the big database and the word sequence X, n represents the total number of synthesized words in the word sequence X, q represents the q-th synthesized word, mqA synthetic sequence value expressed as the q-th synthetic word, g is the total number of the learning data, h is the h-th learning data, bhA learning sequence value expressed as the h-th learning data;
step B3, calculating the information gain of each synthesized word in the word sequence X;
wherein, P (C)q) Is represented as CqProbability value of class document in g learning data, PqThe g learning data are expressed to contain the proportion of the synthesized word q, and W is expressed as the information gain of each synthesized word;
step B4, obtaining a prediction value according to the information gain and the similarity;
repeating the steps B3-B4 to obtain a plurality of inferred values;
and acquiring final learning data corresponding to the plurality of inference values to generate the knowledge inference set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010396216.XA CN111597442A (en) | 2020-05-12 | 2020-05-12 | Classroom learning method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010396216.XA CN111597442A (en) | 2020-05-12 | 2020-05-12 | Classroom learning method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111597442A true CN111597442A (en) | 2020-08-28 |
Family
ID=72183647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010396216.XA Withdrawn CN111597442A (en) | 2020-05-12 | 2020-05-12 | Classroom learning method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111597442A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681317A (en) * | 2023-03-22 | 2023-09-01 | 北京游娱网络科技有限公司 | Method for generating evaluation report based on learning data and electronic equipment |
-
2020
- 2020-05-12 CN CN202010396216.XA patent/CN111597442A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681317A (en) * | 2023-03-22 | 2023-09-01 | 北京游娱网络科技有限公司 | Method for generating evaluation report based on learning data and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tang et al. | Smart recommendation for an evolving e-learning system: Architecture and experiment | |
| CN109118402B (en) | Army cadre online learning, examination and evaluation system and method | |
| CN109637238B (en) | Method, device, equipment and storage medium for generating exercise questions | |
| US11226991B2 (en) | Interest tag determining method, computer device, and storage medium | |
| CN109214965B (en) | Data sorting method, system and device | |
| CN106251261B (en) | Training scheme generation method and device | |
| Zakharov | Feedback micro-engineering in EER-Tutor | |
| CN110473435A (en) | A kind of the word assistant learning system and method for the quantification with learning cycle | |
| Brandes et al. | Using action research to distill research-based segments of pedagogical content knowledge of K-12 computer science teachers | |
| CN111597442A (en) | Classroom learning method based on big data | |
| KR100772183B1 (en) | On-line learning system and methode | |
| CN112950038A (en) | Personalized operation arrangement method based on learning situation data | |
| CN112269921A (en) | Learning method for big data | |
| CN112926934A (en) | Teaching evaluation method, system and computer readable storage medium | |
| CN117237153A (en) | Teaching affair management system based on vocational training platform | |
| CN114090526B (en) | Cloud education resource management system | |
| CN110569297A (en) | Student learning state statistics and evaluation system | |
| CN110008356B (en) | Error correction book generation system and method | |
| CN115018676A (en) | Interactive equipment is used in online education based on VR technique | |
| Shrestha et al. | Determining learning style preferences of learners | |
| US20020032690A1 (en) | Method for processing data and generating test report of test system | |
| CN113590961A (en) | Personalized exercise recommendation method and device based on cognition and state evaluation and intelligent terminal | |
| CN108255833B (en) | Knowledge information interaction method and system | |
| CN112287115A (en) | Personalized teaching method, system and device based on knowledge mastery degree graph | |
| CN111161113A (en) | Method and system for quickly assisting in entering score information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200828 |