CN111831886B - Network courseware pushing method based on big data - Google Patents
Network courseware pushing method based on big data Download PDFInfo
- Publication number
- CN111831886B CN111831886B CN202010694953.8A CN202010694953A CN111831886B CN 111831886 B CN111831886 B CN 111831886B CN 202010694953 A CN202010694953 A CN 202010694953A CN 111831886 B CN111831886 B CN 111831886B
- Authority
- CN
- China
- Prior art keywords
- courseware
- test
- concentration
- user
- sub
- 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
- G06F16/90—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
- G06F16/9532—Query formulation
-
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
- G09B5/12—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations different stations being capable of presenting different information simultaneously
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to the field of online education and big data, and discloses a network courseware pushing method based on big data, which comprises the following steps: each piece of subcontract has a corresponding concentration index, the user terminal acquires eye movement data of a user, the attention analysis server processes the eye movement data to obtain a first test concentration, and compares the first test concentration with the standard eye movement index to judge whether to perform a second test; when a second test is carried out, the attention analysis server acquires test reply data of the user, and a second test concentration is obtained after the test reply data is processed; the attention analysis server analyzes the learning concentration of the user according to the first test concentration and the second test concentration and sends the learning concentration to the courseware pushing server; the courseware pushing server generates a courseware pushing instruction according to the user learning concentration, the concentration index of the sub-courseware and the user learning record analysis, and the courseware content server sends the corresponding sub-courseware to the user terminal according to the courseware pushing instruction.
Description
Technical Field
The invention relates to the field of online education and big data, in particular to a network courseware pushing method based on big data.
Background
With the rapid development of information technology, network education performed by means of the internet has unprecedented development worldwide, and the appearance of online education has great influence on the teaching mode, the education quality, the teaching concept of higher education and even the direction of higher education development.
China is a large population country, the problem of unfair education is difficult to solve only by means of traditional education forms, the goal of education popularization is difficult to realize, and the ever-increasing cultural demands of people are difficult to meet, so that online education is vigorously developed, and the development and sharing of network course resources to a greater extent are also the trends of education development of China. Compared with the traditional education, the online education has the advantages that the online education meets the demands of a plurality of social working people without diploma on diploma, the online education is not limited by space, the time cost on the space is reduced, and the online education can lead people to be in contact with a great variety of knowledge and lead people to learn more suitable things.
Currently, online education generally adopts a sequence that a user autonomously selects learning contents, that is, the user selects contents and a sequence to be learned according to own interests and needs or learns according to a preset learning sequence of a current learning course. However, if the content selected by the user or the preset learning content is not suitable for the current attention, the learning effect is not good, and the currently learned knowledge point cannot be grasped.
Therefore, in the process of performing the network learning, how to adaptively adjust the learning content according to the attention index of the user during the learning, so as to improve the learning effect of the user, and the problem to be solved is urgent.
Disclosure of Invention
The existing online education technical scheme has the following defects: 1. since online education completely depends on the user to learn autonomously, the requirement on the self-control ability of the user is high, the situation that the user cannot master difficult knowledge points due to inattention can occur, and the learning task cannot be completed autonomously and efficiently. 2. The user cannot scientifically select the most suitable content for the current learning according to the current learning state.
Aiming at the defects of the prior art, the invention provides a network courseware pushing method based on big data, which comprises the following steps:
s1) the courseware preprocessing server divides the courseware into sub-courseware according to the knowledge points, sets corresponding concentration index for each sub-courseware and then stores the concentration index into a sub-courseware database;
s2) the attention analysis server tests the attention of the user to obtain the learning concentration of the user, which includes:
s2.1) the user terminal acquires eye movement data of a user and sends the eye movement data to the attention analysis server;
s2.2) the attention analysis server analyzes and processes the eye movement data to obtain a first test concentration ratio, and compares the first test concentration ratio with a standard eye movement index to judge whether to perform a second test;
s2.3) carrying out a second test when the first test concentration is smaller than the standard eye movement index, sending test conversation data to the user terminal by the attention analysis server, receiving test reply data sent by the user and processing the test reply data to obtain a second test concentration;
s2.4) the attention analysis server analyzes according to the first test concentration and the second test concentration to obtain a user learning concentration, and sends the user learning concentration to a courseware pushing server;
s3) the courseware pushing server analyzes according to the user learning concentration, the concentration index of the sub-courseware and the user learning record to obtain a courseware pushing instruction and sends the courseware pushing instruction to the courseware content server;
s4) the courseware content server responds to the received courseware pushing instruction to push the corresponding sub-courseware to the user terminal.
According to a preferred embodiment, in step S2.2:
when the first test concentration ratio is greater than the standard eye movement index, the user is shown to be concentrated, the second test is not carried out, and the user continues to learn the first sub-courseware; the first sub-courseware is the sub-courseware being learned by the user.
According to a preferred embodiment, step S2.3 comprises:
the attention analysis server sends test conversation data to the user terminal;
the user sends corresponding test reply data to the attention analysis server according to the received test dialogue data;
the attention analysis server acquires test reply data and historical test reply data of a user learning theme;
the attention analysis server calculates a second test concentration based on the test reply data and the historical test reply data.
According to a preferred embodiment, step S2.3 comprises:
the attention analysis server creates a history concentration degree vector for each history test reply data, extracts a word vector of each history test reply data, and analyzes the word vector to obtain a word frequency vector;
the attention analysis server calculates the similarity between the word frequency vector and the standard word frequency vector to obtain a test feedback value of each historical concentration vector;
the attention analysis server creates an instant concentration vector for the test reply data, and calculates the test interval between each historical concentration vector and the instant concentration vector through a test interval function;
the attention analysis server carries out ascending sequencing on the historical concentration vectors according to the test intervals, and then selects n historical concentration vectors with the minimum test intervals;
the attention analysis server calculates an average of the test feedback values of the n historical concentration vectors with the smallest test interval to obtain a second test concentration of the user.
According to a preferred embodiment, in step S2.4, the formula for calculating the learning concentration is:
where m represents the first test concentration,
representing the standard eye movement index, n representing the second test concentration,
representing the average of the historical second test concentrations, the coefficients alpha, beta being enhancement indices of the first test concentration and the second test concentration respectively,
according to a preferred embodiment, step S3 includes:
s3.1, the courseware pushing server analyzes the learning subjects of the users according to the learning records of the users and receives a sub-courseware list corresponding to the learning subjects of the users;
s3.2, the courseware pushing server selects the sub-courseware with the concentration index smaller than the learning concentration of the user in the sub-courseware list to generate a courseware pushing instruction;
and S3.3, the courseware content server responds to the received courseware pushing instruction to push the corresponding sub-courseware to the user terminal.
According to a preferred embodiment, at the time of the second test, timestamp data of the first sub-courseware is recorded and stored in the user database; the timestamp data is used to mark the learning progress of the sub-courseware.
According to a preferred embodiment, after completing the learning of the second sub-courseware, the user continues to learn the first sub-courseware according to the timestamp data; and the second sub-courseware recommends the learning sub-courseware for the courseware pushing server.
According to a preferred embodiment, the user terminal comprises a notebook computer, a tablet computer and a desktop computer with a camera.
According to a preferred embodiment, the concentration index is used for indicating the learning difficulty and learning duration of the knowledge points of the sub-courseware.
The invention has the following beneficial effects:
the method and the device can effectively analyze the current attention of the user so as to judge the current learning state of the user, and recommend the most suitable learning content for the user according to the current attention and the learning state of the user, so that the user can quickly master the currently learned knowledge points and efficiently finish the learning task.
In addition, the invention takes the influence of the degree of attention deviation on the learning concentration into consideration and enhances the learning concentration to a certain extent when the learning concentration is calculated, so that the influence on the calculation of the learning concentration value is larger and the result is more accurate as the attention of the user deviates from the standard.
Drawings
Fig. 1 schematically shows a flow chart of the network courseware pushing method of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1, the big data-based network courseware pushing method of the present invention includes the following steps:
s1) the courseware preprocessing server divides the courseware into sub-courseware according to the knowledge points, sets corresponding concentration index for each sub-courseware and then stores the concentration index to the courseware content server;
specifically, the courseware content server divides courseware into sub-courseware according to the knowledge point data set. The courseware content server comprises a content identification module, a courseware segmentation module, an original courseware database and a sub-courseware database, wherein the content identification module identifies a knowledge point data set of courseware by using a text identification technology and an image identification technology, the courseware segmentation module segments the courseware into sub-courseware according to the knowledge points, and time stamp data of each sub-courseware is recorded.
Preferably, the concentration index for a sub-course is the lowest user learning concentration at which the user is eligible to learn the sub-course.
Preferably, the background manager establishes a concentration index for each courseware, and the concentration index of the courseware is related to the learning difficulty and the learning duration of the courseware.
Preferably, the sub-courseware and the tag information of the sub-courseware are stored in a sub-courseware database of the courseware content server. The sub-courseware tag information comprises concentration index of the sub-courseware, learning subject, knowledge point data set, learning duration and learning difficulty.
S2) the attention analysis server tests the attention of the user to obtain the learning concentration of the user, which includes:
s2.1) the user terminal obtains eye movement data of the user and sends the eye movement data to the attention analysis server.
Specifically, the user terminal comprises intelligent equipment with a communication function and a camera, and the intelligent equipment comprises a notebook computer, a tablet personal computer and a desktop all-in-one machine with the camera.
The user terminal periodically collects eye movement data of the user and sends the eye movement data to the analysis server.
Preferably, the user terminal obtains the current eye movement data of the user through the camera, and the eye movement data completely records the gazing track of the user.
S2.2) the attention analysis server analyzes and processes the eye movement data to obtain a first test concentration ratio, and compares the first test concentration ratio with the standard eye movement index to judge whether to perform a second test.
Specifically, the attention analysis server performs feature extraction on the eye movement data to obtain eye movement feature parameters, and the eye movement feature parameters include: the total number of gazing screens, the dwell time of each gazing screen, the sequential trajectory of the gazing points, and the dwell time of the average gazing screen. And analyzing and processing the eye movement characteristic parameters to obtain a first test concentration ratio.
Preferably, the attention analysis server periodically receives the eye movement data collected by the user terminal, and compares the first test concentration obtained after the eye movement data is processed with the standard eye movement index. When the first test concentration is less than the standard eye movement index, indicating that the user's attention is below the standard value, the user needs to perform a second test. When the first test concentration ratio is greater than or equal to the standard eye movement index, the attention of the user is shown to be concentrated, the user does not need to perform the second test, and the user can continue to learn the current sub-courseware.
And S2.3) carrying out a second test when the first test concentration is smaller than the standard eye movement index, sending test conversation data to the user terminal by the attention analysis server, receiving test reply data sent by the user and processing the test reply data to obtain a second test concentration.
Specifically, the second test is that the attention analysis server sends test session data to the user terminal, the user replies according to session information in the test session data to generate test reply data of the user, and the user terminal sends the test reply data to the attention analysis server. The test reply data may be a question or a common sense question relating to the content of the sub-courseware the user is learning at that time.
Specifically, step S2.3 comprises:
the attention analysis server sends the test dialogue data to the user terminal, and the user sends corresponding test reply data to the attention analysis server according to the received test dialogue data.
The attention analysis server obtains the test reply data and the historical test reply data of the user learning theme, and calculates a second test concentration ratio according to the test reply data and the historical test reply data.
Specifically, the calculation, by the attention analysis server, of the second test concentration from the test reply data and the historical test reply data includes:
the attention analysis server creates a history concentration degree vector for each history test reply data, extracts a word vector of each history test reply data, and then carries out word frequency statistics on the word vector to obtain a word frequency vector.
And the attention analysis server calculates the similarity between the word frequency vector and the standard word frequency vector to obtain a test feedback value of each historical concentration vector, and stores the historical concentration vectors and the corresponding test feedback values in a database.
Specifically, the calculation formula of the similarity between the word frequency vector and the standard word frequency vector is as follows:
wherein A is the word frequency vector of the test reply data, B is the standard word frequency vector, and alpha is the similarity.
The attention analysis server creates an instant concentration vector according to the test reply data, and calculates a test interval of each history concentration vector and the instant concentration vector through a test interval function.
Specifically, the test interval function is:
d＝||M-N||2
wherein the concentration vector space is an s-dimensional real number vector space RsM is the instant concentration vector and N is the historical concentration vector.
And the attention analysis server carries out ascending sequencing on the historical concentration vectors according to the test intervals, and then selects n historical concentration vectors with the minimum test intervals.
The attention analysis server calculates an average of the test feedback values of the n historical concentration vectors with the smallest test interval to obtain a second test concentration of the user.
Preferably, the attention analysis server averages the test feedback values of the n history concentration vectors with the minimum test interval to obtain a second test concentration of the current user test reply data, and stores the instant concentration vector of the current test reply data and the corresponding second test concentration in the database.
When n is selected to be different values, different results can be generated, and if the value of n is too small, the prediction precision can be reduced; if the value of n is too large, noise may be increased, and prediction accuracy may be degraded. Thus, n is generally lower than the square root of the number of historical concentration vectors.
Preferably, a standard answer is preset for each test dialogue data, and a word frequency vector in the standard answer is extracted from a word vector space to obtain a standard word frequency vector of each dialogue information
Preferably, the second test concentration of the new concentration vector can be calculated by averaging the test feedback values of several recent historical concentration vectors only after the concentration vector space has assigned a test feedback value for a given instant concentration vector.
In another embodiment, the attention analysis server sends the historical test reply data to an administrator who assigns a test feedback data value to the historical concentration vector corresponding to each historical test reply data based on an analysis of the test reply data.
And S2.4) analyzing by the attention analysis server according to the first test concentration and the second test concentration to obtain the learning concentration of the user, and sending the learning concentration to the courseware pushing server.
Specifically, in step S2.4, the calculation formula of the user learning concentration ratio is:
m represents the first concentration of the test,
representing the standard eye movement index, n representing the second test concentration,
represents the average of the historical second test concentrations,
learning concentration ratio calculation formula index part
For a first test attention deviation index, the coefficient α is a first enhancement index, i.e., an enhancement index of the first test concentration;
for the second test attention deviation scatter index, the coefficient β is the second enhancement index, i.e., the enhancement index for the second test concentration.
A first test attention deviation index for measuring a degree to which a user's current attention deviates from a standard in a first test; a second test attention deviation index for measuring the degree to which the user's current attention deviates from the average level in the second test;
the first augmentation index α is used to control the degree of augmentation of the deviation of attention for its first test, and the second augmentation index β is used to control the degree of augmentation of the deviation of attention for the second test. The influence of the degree of attention deviation on the learning concentration is considered in the learning concentration calculation, and is enhanced to a certain extent, so that the influence on the calculation of the learning concentration value is larger and the result is more accurate as the attention of the user deviates from the standard.
Applying a piecewise function f (x, y) in the learning concentration calculation marks positive and negative values for the first and second learning concentrations. When the first test concentration is greater than the standard eye movement index, the mark is positive, namely, in the first test, the attention of the user is in a concentrated state, and when the first test concentration is less than the standard eye movement index, the mark is negative, namely, in the first test, the attention of the user is in a dispersed state; when the second test concentration is greater than the second test concentration average, marking as a positive value, namely, in the second test, the user attention is in a concentrated state, and when the second test concentration is less than the second test concentration average, marking as a negative value, namely, in the second test, the user attention is in a dispersed state;
preferably, a rest threshold is preset, and when the learning concentration of the user is lower than the preset rest threshold, the user stops learning and takes a rest.
Preferably, a learning threshold is preset, and when the learning concentration of the user is higher than the preset learning threshold, the sub-courseware is not switched, and the current sub-courseware continues to be learned.
S3), the courseware pushing server analyzes and obtains a courseware pushing instruction according to the learning concentration, the concentration index of the sub-courseware and the user learning record, and the courseware content server sends the corresponding sub-courseware to the user terminal according to the courseware pushing instruction.
In one embodiment, step S3 includes:
s3.1, the courseware pushing server analyzes the learning subjects of the users according to the learning records of the users and receives a sub-courseware list corresponding to the learning subjects of the users;
and S3.2, the courseware pushing server selects the sub-courseware with the concentration index smaller than the learning concentration of the user in the sub-courseware list to generate a courseware pushing instruction.
Optionally, the concentration index of the sub-courseware is the lowest learning concentration of the user required for learning the sub-courseware, and when the concentration index of the sub-courseware is smaller than the learning concentration of the user, the user is suitable for learning the corresponding sub-courseware.
And S3.3, the courseware content server responds to the received courseware pushing instruction to push the corresponding sub-courseware to the user terminal.
In the embodiment, when the user performs the second test, the timestamp data of the currently-learned sub-courseware is recorded and stored in the user database; after the user completes the learning of the second sub-courseware, based on the timestamp data, the user continues to complete the learning of the first sub-courseware from the place where the learning of the sub-courseware was interrupted.
The first sub-courseware is the sub-courseware learned by the user before executing the second test, namely the sub-courseware currently learned by the user, and the second sub-courseware is the sub-courseware recommended by the courseware pushing server.
Preferably, the timestamp data is used to mark the progress of the study of the sub-courseware; the user database is used for storing user login information, identity information and user learning records.
S4) the courseware content server responds to the received courseware pushing instruction to push the corresponding sub-courseware to the user terminal.
The method and the device effectively analyze the current attention of the user so as to judge the current learning state of the user, and recommend the currently most suitable learning content to the user according to the current attention and the learning state of the user, so that the user can quickly master the currently learned knowledge points and efficiently finish the learning task. In addition, the invention takes the influence of the degree of attention deviation on the learning concentration into consideration and enhances the learning concentration to a certain extent when the learning concentration is calculated, so that the influence on the calculation of the learning concentration value is larger and the result is more accurate as the attention of the user deviates from the standard.
In one embodiment, the educational courseware pushing system comprises a plurality of user terminals and an online courseware cloud platform, and the online courseware cloud platform is respectively in communication connection with the plurality of user terminals.
The network courseware cloud platform includes: the system comprises a courseware preprocessing server, an attention analysis server, a courseware pushing server, a courseware content server and a database, wherein the servers and the database in the network courseware cloud platform are in communication connection.
The courseware preprocessing server is used for dividing courseware into sub-courseware according to the knowledge points, setting corresponding concentration index for each sub-courseware and then storing the concentration index to the courseware content server.
The attention analysis server is used for carrying out attention test on the user to obtain the learning concentration of the user.
The courseware pushing server is used for analyzing according to the user learning concentration, the concentration index of the sub-courseware and the user learning record to obtain a courseware pushing instruction, and sending the courseware pushing instruction to the courseware content server.
And the courseware content server is used for pushing the corresponding sub-courseware to the user terminal according to the received courseware pushing instruction.
Optionally, the database includes: a sub courseware database, a user database and an original courseware database. The courseware database may be used to store courseware and the concentration index corresponding to the courseware. The original courseware database may be used to store original courseware before segmentation. The user database may be used to store user login information, identity information, and user learning records.
Optionally, in another embodiment, step S3 includes:
s3.1, the courseware pushing server analyzes the learning subjects of the users based on the learning records of the users and receives a sub-courseware list corresponding to the learning subjects of the users;
s3.2, screening out a sub-courseware list suitable for the current attention learning of the user by the courseware pushing server based on the learning concentration of the user and the concentration index of the sub-courseware, sending the sub-courseware list to a display interface of the user terminal, and selecting the next sub-courseware to be learned by the user according to the self condition;
s3.3, the user terminal sends the user selection data to a courseware pushing server, and the courseware pushing server generates courseware pushing instructions according to the user selection data;
and S3.4, the courseware content server responds to the courseware pushing instruction and sends the corresponding sub-courseware to the user terminal.
In this embodiment, when the user performs the second test, the timestamp data of the current learning sub-courseware is recorded, the courseware content server determines to complete the first sub-courseware based on the timestamp data, that is, the time required for learning the current sub-courseware, the courseware content server responds to the courseware pushing instruction based on the time delay, and after the learning of the current sub-courseware is completed, the courseware content server responds to the courseware pushing instruction to send the corresponding sub-courseware to the user terminal.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. A big data-based network courseware pushing method is characterized by comprising the following steps:
s1) the courseware preprocessing server divides the courseware into sub-courseware according to the knowledge points, sets corresponding concentration index for each sub-courseware and then stores the concentration index into a sub-courseware database;
s2) the attention analysis server tests the attention of the user to obtain the learning concentration of the user, which includes:
s2.1) the user terminal acquires eye movement data of a user and sends the eye movement data to the attention analysis server;
s2.2) the attention analysis server analyzes and processes the eye movement data to obtain a first test concentration ratio, and compares the first test concentration ratio with a standard eye movement index to judge whether to perform a second test;
s2.3) carrying out a second test when the first test concentration is smaller than the standard eye movement index, sending test conversation data to the user terminal by the attention analysis server, receiving test reply data sent by the user and processing the test reply data to obtain a second test concentration;
s2.4) the attention analysis server analyzes according to the first test concentration and the second test concentration to obtain a user learning concentration, and sends the user learning concentration to a courseware pushing server;
the formula for calculating the learning concentration ratio is as follows:
where m represents the first test concentration,
representing the standard eye movement index, n representing the second test concentration,
representing the average of the historical second test concentrations, the coefficients alpha, beta being enhancement indices of the first test concentration and the second test concentration respectively,
s3) the courseware pushing server analyzes according to the user learning concentration, the concentration index of the sub-courseware and the user learning record to obtain a courseware pushing instruction and sends the courseware pushing instruction to the courseware content server;
s4) the courseware content server responds to the received courseware pushing instruction to push the corresponding sub-courseware to the user terminal.
2. Method according to claim 1, characterized in that in step S2.2:
when the first test concentration ratio is larger than the standard eye movement index, the second test is not carried out, and the user continues to learn the first sub-courseware; the first sub-courseware is the sub-courseware being learned by the user.
3. Method according to claim 2, characterized in that step S2.3 comprises:
the attention analysis server sends test conversation data to the user terminal;
the user sends corresponding test reply data to the attention analysis server according to the received test dialogue data;
the attention analysis server acquires test reply data and historical test reply data of a user learning theme;
the attention analysis server calculates a second test concentration based on the test reply data and the historical test reply data.
4. A method according to claim 3, characterised in that step S2.3 further comprises:
the attention analysis server creates a history concentration degree vector for each history test reply data, extracts a word vector of each history test reply data, and analyzes the word vector to obtain a word frequency vector;
the attention analysis server calculates the similarity between the word frequency vector and the standard word frequency vector to obtain a test feedback value of each historical concentration vector;
the attention analysis server creates an instant concentration vector for the test reply data, and calculates the test interval between each historical concentration vector and the instant concentration vector through a test interval function;
the attention analysis server carries out ascending sequencing on the historical concentration vectors according to the test intervals, and then k historical concentration vectors with the minimum test intervals are selected;
the attention analysis server calculates an average of the test feedback values of the k historical concentration vectors with the smallest test interval to obtain a second test concentration of the user.
5. The method according to claim 4, wherein step S3 includes:
s3.1, the courseware pushing server analyzes the learning subjects of the users according to the learning records of the users and receives a sub-courseware list corresponding to the learning subjects of the users;
s3.2, the courseware pushing server selects the sub-courseware with the concentration index smaller than the learning concentration of the user in the sub-courseware list to generate a courseware pushing instruction;
and S3.3, the courseware content server responds to the received courseware pushing instruction to push the corresponding sub-courseware to the user terminal.
6. The method of claim 5, wherein timestamp data for the first sub-courseware is recorded and stored in the user database at the time of the second test; the timestamp data is used to mark the learning progress of the sub-courseware.
7. The method of claim 6, wherein the user, after completing the learning of the second sub-courseware, proceeds to learn the first sub-courseware according to the timestamp data; and the second sub-courseware recommends the learning sub-courseware for the courseware pushing server.
8. The method of claim 7, wherein the user terminal comprises a laptop computer, a tablet computer, and a desktop computer with a camera.
9. The method of claim 8, wherein the concentration index is used to indicate difficulty and duration of learning of points of knowledge of a sub-courseware.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110033629.6A CN112784144B (en) | 2020-07-18 | 2020-07-18 | Online education courseware pushing method based on big data |
| CN202010694953.8A CN111831886B (en) | 2020-07-18 | 2020-07-18 | Network courseware pushing method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010694953.8A CN111831886B (en) | 2020-07-18 | 2020-07-18 | Network courseware pushing method based on big data |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110033629.6A Division CN112784144B (en) | 2020-07-18 | 2020-07-18 | Online education courseware pushing method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111831886A CN111831886A (en) | 2020-10-27 |
| CN111831886B true CN111831886B (en) | 2021-05-25 |
Family
ID=72922858
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010694953.8A Active CN111831886B (en) | 2020-07-18 | 2020-07-18 | Network courseware pushing method based on big data |
| CN202110033629.6A Active CN112784144B (en) | 2020-07-18 | 2020-07-18 | Online education courseware pushing method based on big data |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110033629.6A Active CN112784144B (en) | 2020-07-18 | 2020-07-18 | Online education courseware pushing method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111831886B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792248B (en) * | 2021-11-16 | 2022-02-22 | 深圳华埔之星科技有限公司 | Online education course sharing and distributing system based on Internet and mobile terminal |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833877A (en) * | 2010-03-24 | 2010-09-15 | 杭州全动科技有限公司 | Enlightening education method for preschool child |
| CN106601054A (en) * | 2016-12-20 | 2017-04-26 | 成都远策数码科技有限公司 | Teaching material pushing system and method applied to internet education platform |
| CN109859821A (en) * | 2018-12-21 | 2019-06-07 | 睿远空间教育科技(深圳)有限公司 | Concentration training method, device, system and storage medium based on E.E.G acquisition |
| CN109885727A (en) * | 2019-02-21 | 2019-06-14 | 广州视源电子科技股份有限公司 | Data method for pushing, device, electronic equipment and system |
| CN111325109A (en) * | 2020-01-22 | 2020-06-23 | 福建中医药大学 | Attention training method |
| CN111400592A (en) * | 2020-03-12 | 2020-07-10 | 山东师范大学 | Personalized course recommendation method and system based on eye movement technology and deep learning |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100248828A1 (en) * | 2009-03-24 | 2010-09-30 | Ty Huynh Kaing | Educational toy |
| CN108665734A (en) * | 2017-03-28 | 2018-10-16 | 深圳市掌网科技股份有限公司 | A kind of teaching method and system based on virtual reality |
| US20200273358A1 (en) * | 2017-09-27 | 2020-08-27 | Sarit Gvili | Educational Device |
| CN107929007B (en) * | 2017-11-23 | 2020-01-21 | 北京萤视科技有限公司 | Attention and visual ability training system and method using eye tracking and intelligent evaluation technology |
| CN108281052B (en) * | 2018-02-09 | 2019-11-01 | 郑州市第十一中学 | A kind of on-line teaching system and online teaching method |
| CN108682189A (en) * | 2018-04-20 | 2018-10-19 | 南京脑桥智能科技有限公司 | A kind of learning state confirmation system and method |
| CN108615420B (en) * | 2018-04-28 | 2020-08-28 | 北京比特智学科技有限公司 | Courseware generation method and device |
| CN109009171B (en) * | 2018-08-01 | 2020-11-13 | 深圳市心流科技有限公司 | Attention assessment method, attention assessment system and computer-readable storage medium |
| CN111339801B (en) * | 2018-12-19 | 2023-10-17 | 杭州海康威视系统技术有限公司 | Personnel attention detection method, device, equipment and system |
| CN109977903B (en) * | 2019-04-03 | 2020-03-17 | 珠海读书郎网络教育有限公司 | Method and device for intelligent classroom student management and computer storage medium |
| CN110136464B (en) * | 2019-04-18 | 2021-05-11 | 深圳市宏电技术股份有限公司 | Driving assisting method, device and equipment |
| CN110378812A (en) * | 2019-05-20 | 2019-10-25 | 北京师范大学 | A kind of adaptive on-line education system and method |
| CN111292850A (en) * | 2020-01-22 | 2020-06-16 | 福建中医药大学 | ADHD children attention intelligent rehabilitation system |
-
2020
- 2020-07-18 CN CN202010694953.8A patent/CN111831886B/en active Active
- 2020-07-18 CN CN202110033629.6A patent/CN112784144B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833877A (en) * | 2010-03-24 | 2010-09-15 | 杭州全动科技有限公司 | Enlightening education method for preschool child |
| CN106601054A (en) * | 2016-12-20 | 2017-04-26 | 成都远策数码科技有限公司 | Teaching material pushing system and method applied to internet education platform |
| CN109859821A (en) * | 2018-12-21 | 2019-06-07 | 睿远空间教育科技(深圳)有限公司 | Concentration training method, device, system and storage medium based on E.E.G acquisition |
| CN109885727A (en) * | 2019-02-21 | 2019-06-14 | 广州视源电子科技股份有限公司 | Data method for pushing, device, electronic equipment and system |
| CN111325109A (en) * | 2020-01-22 | 2020-06-23 | 福建中医药大学 | Attention training method |
| CN111400592A (en) * | 2020-03-12 | 2020-07-10 | 山东师范大学 | Personalized course recommendation method and system based on eye movement technology and deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 大学生移动学习注意力差异研究;赵鑫硕;《中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑》;20171015(第10期);H127-23 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112784144B (en) | 2022-11-29 |
| CN112784144A (en) | 2021-05-11 |
| CN111831886A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832952B (en) | Education courseware pushing system | |
| KR102106462B1 (en) | Method for filtering similar problem based on weight | |
| CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN107680019B (en) | Examination scheme implementation method, device, equipment and storage medium | |
| CN109241268B (en) | Similar information recommendation method, device, equipment and storage medium | |
| CN109800663A (en) | Teachers ' teaching appraisal procedure and equipment based on voice and video feature | |
| CN108898115B (en) | Data processing method, storage medium and electronic device | |
| CN110659311B (en) | Topic pushing method and device, electronic equipment and storage medium | |
| CN115205764B (en) | Online learning concentration monitoring method, system and medium based on machine vision | |
| CN109740567A (en) | Key point location model training method, localization method, device and equipment | |
| CN111831886B (en) | Network courseware pushing method based on big data | |
| KR102327011B1 (en) | Method and apparatus for enhancing consultation service quality | |
| CN112861809A (en) | Classroom new line detection system based on multi-target video analysis and working method thereof | |
| CN113257060A (en) | Question answering solving method, device, equipment and storage medium | |
| US11868440B1 (en) | Statistical model training systems | |
| CN114971425B (en) | Database information monitoring method, device, equipment and storage medium | |
| CN111415283A (en) | Factor analysis method and device for effective online teaching | |
| CN112990105B (en) | Method and device for evaluating user, electronic equipment and storage medium | |
| CN114627085A (en) | Target image identification method and device, storage medium and electronic equipment | |
| CN113822589A (en) | Intelligent interviewing method, device, equipment and storage medium | |
| CN112446360A (en) | Target behavior detection method and device and electronic equipment | |
| CN110807179A (en) | User identification method, device, server and storage medium | |
| CN111597997A (en) | Computer control teaching equipment | |
| US11900327B2 (en) | Evaluation adjustment factoring for bias | |
| US11893152B1 (en) | Sentiment-based adaptations of user representations in virtual environments |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210430 Address after: 518000 Room 301, north, 3rd floor, gymnasium, Bao'an District, Yu'an West Road, 84 District, Xin'an street, Bao'an District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Lanqing Education Technology Group Co.,Ltd. Address before: 628000 Xuefeng Qiao Road 338, Lizhou District, Guangyuan, Sichuan Applicant before: GUANGYUAN LIANGZHIHUI TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |