CN111475716A - Online course recommendation method, system, equipment and storage medium - Google Patents
Online course recommendation method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN111475716A CN111475716A CN202010223699.3A CN202010223699A CN111475716A CN 111475716 A CN111475716 A CN 111475716A CN 202010223699 A CN202010223699 A CN 202010223699A CN 111475716 A CN111475716 A CN 111475716A
- Authority
- CN
- China
- Prior art keywords
- course
- user
- historical
- category
- recommended
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 239000013598 vector Substances 0.000 claims abstract description 67
- 238000012549 training Methods 0.000 claims description 18
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000007474 system interaction Effects 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an online course recommendation method, a system, equipment and a storage medium, wherein the method comprises the following steps: requesting to acquire identity associated information of a user from an account management system, requesting to acquire historical course data of the user from a course management system, and combining to obtain a characteristic vector of the user; inputting the characteristic vector of the user into a trained new class acceptance prediction model to obtain a predicted new class acceptance value of the user; if the new class acceptance value of the user is larger than a first threshold value, determining the class of the interested course of the user according to the historical browsing data of the user; selecting recommended courses of the user from a course database according to the interested categories of the user; and responding to a course recommendation request sent by the user terminal, and pushing the selected recommended course to the user terminal. By adopting the scheme of the invention, the personalized course recommendation for different users is realized, and the course recommendation and selection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of online education, in particular to an online course recommendation method, system, equipment and storage medium.
Background
With the rapid development of online education technology, more and more people choose to participate in various curriculum learning related knowledge online. Firstly, a user needs to order lessons on line, the user selects required courses according to own requirements and idle time during lesson ordering, and then the course management platform can arrange lessons according to the course selection of the user. When a user orders a course, the course suitable for the user needs to be screened from a large number of courses. In the course recommendation method in the prior art, generally, historical course data of a user is simply captured, similar courses are recommended to the user according to the courses participated by the user, however, for different users, the requirements may be various, the recommendation method is too simple, and if a uniform recommendation rule is adopted, a personalized recommendation method for the user is difficult to realize. In addition, if the course recommendation is performed only according to the courses participated by the user, the user is not utilized to select more diversified course categories, which is not beneficial to the popularization of newly developed courses. After long-term use, the use experience of the user can be reduced, and the user can not select the required course from the recommended courses, and can automatically search the massive data to greatly reduce the course selection efficiency.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide an online course recommendation method, system, device and storage medium, so that personalized course recommendation for different users is realized, and course recommendation and selection efficiency is improved.
The embodiment of the invention provides an online course recommendation method, which comprises the following steps:
requesting to acquire identity associated information of a user from an account management system, requesting to acquire historical course data of the user from a course management system, and combining to obtain a characteristic vector of the user, wherein the historical course data comprises historical browsing data and historical participation course data;
inputting the characteristic vector of the user into a trained new class acceptance prediction model to obtain a predicted new class acceptance value of the user;
if the new class acceptance value of the user is larger than a first threshold value, determining the class of the interesting course of the user according to the historical browsing data of the user;
selecting recommended courses of the user from a course database according to the interested categories of the user;
and responding to a course recommendation request sent by the user terminal, and pushing the selected recommended course to the user terminal.
Optionally, the new class acceptance prediction model is a new class acceptance prediction model constructed based on machine learning, and the method further includes training the new class acceptance prediction model by using the following steps:
requesting to the account management system for inquiring users of which the registration duration is greater than a second threshold and the number of the historical participation courses is greater than a third threshold as sample users;
requesting to an account management system to acquire the identity associated information of the sample users, requesting to a course management system to acquire historical course data, and respectively combining to obtain the characteristic vector of each sample user;
after the new class acceptance value marking is carried out on the feature vector of each sample user, a training sample is added;
and iteratively training the new class acceptance prediction model by adopting the training samples.
Optionally, the tagging of the new class acceptance value for the feature vector of each sample user includes the following steps:
sending an electronic questionnaire to a user terminal of the sample user, the electronic questionnaire including a level option of accepting a new course willingness;
and extracting the degree grade of the willingness of the sample user to accept the new course from the feedback of the user terminal, determining the new course acceptance value of the sample user according to the corresponding relation between the degree grade of the willingness of accepting the new course and the new course acceptance value, and marking the sample user.
Optionally, the historical browsing data includes historical browsing courses, browsing times of each historical browsing course, and browsing duration of each historical browsing course, and the historical participation course data includes historical participation course, participation times of each historical participation course, and participation duration of each historical participation course.
Optionally, the combining to obtain the feature vector of the user includes the following steps:
respectively mapping attribute values of all attributes of the identity correlation information, the historical browsing data and the historical participation data to obtain a first characteristic vector, a second characteristic vector and a third characteristic vector;
counting the number a1 of the course categories with the browsing times of the user being greater than a fourth threshold or the browsing duration of the user being greater than a fifth threshold;
counting the number a2 of the class with the user participation times larger than the fourth threshold or the user participation time larger than the fifth threshold;
calculating the similarity a3 of the historical browsing course category and the historical participation course category;
searching for the overlapping category of the historical browsing course category and the historical participation course category, calculating the ratio a4 of the browsing times and the participation times of the overlapping category, and calculating the ratio a5 of the browsing duration and the participation duration of the overlapping category;
combining the quantity a1, the quantity a2, the similarity a3, the ratio a4 and the ratio a5 to obtain a fourth feature vector;
and combining the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain the feature vector of the user.
Optionally, if the new class acceptance value of the user is greater than a first threshold, the determining the class of the user's interest class according to the historical browsing data of the user includes:
counting the number a6 of the course categories with the browsing times of the user being greater than the fourth threshold and the browsing duration of the user being greater than the fifth threshold;
and if the number a6 is greater than a sixth threshold, the class with the browsing times greater than the fourth threshold and the browsing time greater than a fifth threshold is taken as the interested class, and if the number a6 is less than or equal to the sixth threshold, the class with the browsing times greater than the fourth threshold or the browsing time greater than the fifth threshold is taken as the interested class.
Optionally, if the new class acceptance value of the user is greater than the first threshold, after the recommended course of the user is selected from the course database according to the category of interest of the user, the method further includes the following steps:
calculating the similarity between the recommended course category and the historical participation course category, and sequencing the recommended courses from low to high according to the similarity;
and pushing the selected recommended course information to the user terminal, wherein pushing the selected recommended course information to the user terminal according to the sequence.
Optionally, if the new class acceptance value of the user is greater than the first threshold, after the recommended course of the user is selected from the course database according to the category of interest of the user, the method further includes the following steps:
inquiring the number of course openers and the number of people booked for each recommended course from the course management system;
calculating the ratio m of the number of the booked lessons to the number of the opened lessons of each recommended lesson;
and sorting the recommended courses in the same category according to the ratio m from low to high.
Optionally, after obtaining the predicted new class acceptance value of the user, the method further includes the following steps:
if the new course acceptance value of the user is smaller than or equal to a first threshold value, selecting the course corresponding to the historical participation course category as a recommended course;
and responding to a course recommendation request sent by the user terminal, and pushing the selected recommended course to the user terminal.
Optionally, if the new class acceptance value of the user is less than or equal to the first threshold, after selecting the class corresponding to the historical participation class as the recommended class, the method further includes the following steps:
acquiring a teacher preference tag, a collection teacher tag, a horizontal grade tag and a occupation type tag of a user;
acquiring a teacher attribute label, a teacher identity label, a level grade label and a course category label of each recommended course;
for each recommended course, calculating the matching degree of a teacher attribute label and a teacher preference label of the user, the matching degree of a collected teacher label and a teacher identity label, the matching degree of a horizontal grade label and a horizontal grade label of the user and the matching degree of a course category label and an occupation type label of the user, and weighting and summing the matching degrees to obtain the matching degree of each recommended course and the user;
sorting the recommended courses according to the matching degree from high to low;
and pushing the selected recommended course information to the user terminal, wherein pushing the selected recommended course information to the user terminal according to the sequence.
Optionally, before pushing the selected recommended course information to the user terminal, the method further includes the following steps:
inquiring course progress and course assessment data of each historical participation category of the user from the course management system;
determining the level grade of the user corresponding to the historical participation course category according to the course progress and the course assessment data of the user;
screening out courses of the recommended courses that correspond to the historical participation course category and are less than or equal to the user's level rating.
The embodiment of the invention also provides an online course recommendation system, which is applied to the online course recommendation method, and the system comprises:
the data acquisition module is used for requesting the account management system to acquire the identity associated information of the user, requesting the course management system to acquire historical course data of the user, and combining the historical course data to obtain a characteristic vector of the user, wherein the historical course data comprises historical browsing data and historical participation course data;
the acceptance prediction module is used for inputting the characteristic vector of the user into a trained new class acceptance prediction model to obtain a predicted new class acceptance value of the user;
the course selection module is used for determining the interested course category of the user according to the historical browsing data of the user and selecting the recommended course of the user in the course database according to the interested category of the user if the new course acceptance value of the user is greater than a first threshold value;
and the user interaction module is used for responding to the course recommendation request sent by the user terminal and pushing the selected recommended course to the user terminal.
An embodiment of the present invention further provides an online course recommendation apparatus, including:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the online course recommendation method via execution of the executable instructions.
The embodiment of the present invention further provides a computer-readable storage medium for storing a program, where the program implements the steps of the online course recommendation method when executed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
The online course recommendation method, the system, the equipment and the storage medium provided by the invention have the following advantages:
the method solves the problems in the prior art, a new course acceptance value model for accurately predicting the willingness degree of accepting a new course is established based on big data analysis, the new course acceptance value is predicted for the user based on the basic information and historical course data of the user, and the course which is more in line with the requirements of different users is recommended for the user in a personalized way when a course recommendation request sent by a user terminal is received according to the difference of the new course acceptance values, so that the course recommendation efficiency is improved, the necessity of carrying out course retrieval in mass data by the user is reduced, and the course selection efficiency is improved; the whole method does not adopt an excessively complex algorithm, and for each user, the new course acceptance value can be predicted once within a period of time, so that the operation burden and the operation speed of the course recommendation system can be reduced.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.
FIG. 1 is a flowchart of an online course recommendation method according to a first embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a course pushing system according to a first embodiment of the present invention;
FIG. 3 is an interaction diagram of the course pushing system according to the first embodiment of the present invention;
FIG. 4 is a flowchart of the training of the class acceptability prediction model according to the first embodiment of the present invention;
FIG. 5 is a schematic diagram of system interaction in training a class acceptance prediction model according to a first embodiment of the present invention;
FIG. 6 is a flowchart of combining feature vectors of users according to the first embodiment of the present invention;
FIG. 7 is a flowchart of a multi-dimensional matching lesson and ordering lessons in accordance with a first embodiment of the present invention;
FIG. 8 is a flowchart of the second embodiment of the present invention for ordering lessons after determining lessons in a category of interest;
FIG. 9 is a flow chart of the third embodiment of the present invention for screening out low level lessons;
FIG. 10 is a schematic diagram of an online course recommendation device in accordance with one embodiment of the present invention;
fig. 11 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
In order to solve the technical problem in the prior art, and in consideration of different requirements of different users for recommending courses, a first embodiment of the present invention provides an online course recommendation method, which first predicts a new course acceptance value of a user, and determines a category of interest of the user according to historical browsing data of the user under the condition that the new course acceptance value of the user is high, so as to recommend a course to the user, without being limited to the category of the course in which the user participates.
As shown in fig. 1, in a first embodiment, the online course recommendation method includes the following steps:
s100: requesting to acquire identity associated information of a user from an account management system, requesting to acquire historical course data of the user from a course management system, and combining to obtain a characteristic vector of the user, wherein the historical course data comprises historical browsing data and historical participation course data;
for each user, combining the identity associated information of the user with historical course data to obtain a feature vector of the user;
s200: inputting the characteristic vector of the user into a trained new class acceptance prediction model to obtain a predicted new class acceptance value of the user;
the new class acceptance value represents the dispersion degree of the browsing and participating courses of the user, the higher the new class acceptance value is, the higher the dispersion degree of the browsing and participating courses of the user is, which indicates that the acceptance degree of the user to the new class is higher, and the new class acceptance value is more suitable for the user not limited to the course-participating recommendation mode;
s300: if the new class acceptance value of the user is larger than a first threshold value, the acceptance of the user to the new class is high, and the interested class of the user is determined according to the historical browsing data of the user;
s400: selecting recommended courses of the user from the course database according to the interested categories of the user, so that the recommended courses are not limited to the categories of the courses participated by the user, but more various courses are recommended to the user according to the interest points of the user;
s500: and responding to a course recommendation request sent by the user terminal, and pushing the selected recommended course to the user terminal. Specifically, when a course recommendation request sent by a user terminal is received, first, user identification information (for example, a user ID, a user mobile phone number, and the like) for sending the course recommendation request is determined, then, a recommended course corresponding to a user is queried according to the user identification information, the queried recommended course is pushed to the user terminal, and the user can directly browse courses meeting the needs of the user on the user terminal.
Here, the course recommendation request may be issued when the user clicks a "recommend course for me" button on a course selection page of the user terminal, or when a client home page of the online learning platform is opened on the user terminal, the course recommendation request is issued to display recommended courses in a specific block in the home page.
According to the online course recommending method, a new course acceptance value model for accurately predicting the willingness degree of accepting a new course is obtained based on big data analysis and training, basic information and historical course data of a user are collected through the step S100, the new course acceptance value is predicted through the step S200, and according to the difference of the new course acceptance values, courses which meet the requirements of different users better are recommended for the user in a personalized manner when a course recommending request sent by a user terminal is received, so that the course recommending efficiency is improved, the necessity of carrying out course retrieval from the user to mass data is reduced, and the course selecting efficiency is improved.
In the online course recommendation method, the steps S100 to S400 may be a process executed for each registered user of the online learning platform at intervals, that is, a recommended course corresponding to each registered user is updated at intervals, and when a course recommendation request of the user terminal is received in the step S500, information of the recommended course that has been determined before is directly queried and pushed to the user terminal. For the user side, the time from sending the course recommending request to receiving the recommended course information is shorter, and the experience is better. In addition, the whole method for determining the recommended course does not adopt an excessively complex algorithm, and for each user, the acceptance value of a new course within a period of time is predicted once, so that the operation load and the operation speed of the course recommending system can be reduced.
In this embodiment, the class of lessons is a class of lessons, for example, classes of english quasixfold exam, english blessing exam, business english, middle school mathematics, middle school language, etc., each class of lessons corresponding to a wide variety of rich lessons.
As shown in fig. 2 and fig. 3, the first embodiment further provides an online course recommendation system M100, which is applied to the online course recommendation method, and the system includes:
the data acquisition module M110 is configured to request the account management system M200 to acquire identity-related information of a user, request the course management system M300 to acquire historical course data of the user, and combine the historical course data to obtain a feature vector of the user;
an acceptance prediction module M120, configured to input the feature vector of the user to a trained new class acceptance prediction model to obtain a predicted new class acceptance value of the user;
a course selecting module M130, configured to determine, according to historical browsing data of the user, a category of a course of interest of the user if the new course acceptance value of the user is greater than a first threshold, and select, according to the category of interest of the user, a recommended course of the user in the course database M400;
the user interaction module M140 is configured to respond to the course recommendation request sent by the user terminal M500, and push the selected recommended course to the user terminal.
In the online course recommendation system, the data acquisition module M110 interacts with the account management system M200 and the course management system M300 to acquire basic information and historical course data of a user, the acceptance prediction module M120 is adopted to predict the acceptance value of a new course, the course selection module M130 carries out personalized recommendation on courses which meet the requirements of different users when receiving a course recommendation request sent by a user terminal according to the difference of the acceptance values of the new course, and the user interaction module M140 interacts with the user terminal to realize the pushing of recommended courses, so that the course recommendation efficiency is improved, the requirement of course retrieval from a user to mass data is reduced, and the course selection efficiency is improved.
The account management system M200 is configured to manage account information of all users of the online learning platform, and when the data acquisition module M110 of the online course recommendation system M100 sends an information query request including a user ID to the account management system M200, the account management system M200 returns identity association information associated with the user ID. In this embodiment, the identity association information includes a series of attribute values of the user's age range, occupation type, residence, academic calendar, etc. which may affect the user's willingness to accept new courses.
The course management system M300 is configured to manage the course behavior data of all users of the online learning platform, including browsing course data and participating course data, where participating in a course refers to a student registering and participating in the learning of a course. When the data collection module M110 of the online course recommending system M100 sends a historical course data query request including the user ID to the course management system M300, the course management system M300 queries the historical course data according to the user ID. In this embodiment, the historical lesson data includes historical browsing data and historical participation lesson data, the historical browsing data includes a historical browsing lesson category, a browsing number of times of each historical browsing lesson category, and a browsing duration of each historical browsing lesson category, and the historical participation lesson data includes a historical participation lesson category, an participation number of each historical participation lesson category, and an participation duration of each historical participation lesson category. Here, the browsing number and the browsing duration refer to a sum of a total browsing number and a browsing duration of the same class, and the participation number and the participation duration refer to a sum of a total participation number and a participation duration of the same class.
The course database M400 is configured to store course information of all online courses of the online learning platform, where the course information includes information such as course category, course content, course teacher information, course time, and number of opened course persons. The course selection module M130 of the online course recommendation system M100 sends a course query request including a course category to the course database M400, if the new course acceptance value of the user is greater than the first threshold, the course category in the course query request is the interested category of the user, and after receiving the course query request, the course database M400 queries a matched course according to the course category and returns the matched course to the online course recommendation system M100.
When the user terminal M500 sends a request for recommending courses to the online course recommending system M100, the user interaction module M140 of the online course recommending system M100 analyzes the user ID in the request for recommending courses, determines the recommended course information corresponding to the user according to the user ID, and pushes the recommended course information to the user terminal M500, and the user terminal M500 displays the recommended course information on the corresponding course display page when receiving the recommended course information.
As shown in fig. 4 and 5, in this embodiment, the new class acceptance prediction model is a new class acceptance prediction model constructed based on machine learning, and the online course recommendation method further includes training the new class acceptance prediction model by using the following steps:
s610: the online course recommendation system M100 firstly sends a sample user requirement to the account management system M200, wherein the sample user requirement is a user with the registration duration being greater than a second threshold and the number of the historical participating courses being greater than a third threshold, the account management system M200 inquires a user ID meeting the sample user requirement, and returns the user ID to the online course recommendation system M100 as a sample user;
s620: the online course recommending system M100 requests the account management system M200 to acquire the identity associated information of the sample user, requests the course management system M300 to acquire historical course data, and combines the historical course data to obtain a feature vector of each sample user;
s630: after the new class acceptance value marking is carried out on the feature vector of each sample user, a training sample is added;
s640: and iteratively training the new class acceptance prediction model by adopting the training samples until the new class acceptance prediction model converges to obtain the trained new class acceptance prediction model.
The new class acceptance prediction model can be a neural network constructed based on deep learning, such as a convolutional neural network, and comprises a convolutional layer and a pooling layer for extracting features, a softmax classification layer for predicting the new class acceptance, a full-connection layer for connecting the pooling layer and the softmax classification layer, and the like, and when a loss function from the iterative training model to the model is smaller than a preset threshold value, the new class acceptance prediction model is considered to be converged. In other alternative embodiments, the new class acceptance prediction model may be other types of models, such as a support vector machine, a classification tree model, and the like.
In this embodiment, the step S630: the method for marking the new class acceptance value of the feature vector of each sample user comprises the following steps:
s631: sending an electronic questionnaire to the user terminal M500 of the sample user, the electronic questionnaire including a level option of accepting a new course willingness;
s632: and extracting the degree grade of the new course accepting intention of the sample user from the feedback of the user terminal M500, determining the new course acceptance value of the sample user according to the corresponding relation between the degree grade of the new course accepting intention and the new course acceptance value, and marking the sample user.
Therefore, in the embodiment, through online electronic automatic investigation of the willingness of the user to accept the new course, staff do not need to manually mark the new course acceptance value of the feature vector of the sample user, on one hand, the preparation efficiency of sample data is improved, on the other hand, compared with staff marking, the online investigation result is more real and accurate, and the prediction result of the trained model is more accurate.
As shown in fig. 6, in this embodiment, the step S100 of combining the feature vectors of the users includes the following steps:
s110: respectively mapping attribute values of all attributes of the identity correlation information, the historical browsing data and the historical participation data to obtain a first characteristic vector, a second characteristic vector and a third characteristic vector;
s120: counting the number a1 of the course categories with the browsing times of the user being greater than a fourth threshold or the browsing duration of the user being greater than a fifth threshold;
s130: counting the number a2 of the class with the user participation times larger than the fourth threshold or the user participation time larger than the fifth threshold;
s140: calculating the similarity a3 of the historical browsing course category and the historical participation course category; the similarity calculation here can employ the following steps:
counting the number x of the overlapped classes of the history browsing course classes and the history participation course classes, counting the number y of the overlapped classes of the history browsing course classes, which are not overlapped with the course classes in the history participation course classes, but are overlapped with the similar classes of the history participation course classes, wherein the similar classes of the course classes are preset, for example, the preset course class A and the preset course class B are mutually similar courses, the history browsing course classes have a course class A, and when the history participation course classes have no course class A but have a course class B, the course class A in the history browsing course classes is determined to be overlapped with the similar classes of the course class B in the history participation course classes, and the similarity is calculated as follows: (x + k x y)/total number of historical participation class, where k is a predetermined coefficient, 0< k < 1;
s150: searching for the overlapping category of the historical browsing course category and the historical participation course category, calculating the ratio a4 of the browsing times and the participation times of the overlapping category, and calculating the ratio a5 of the browsing duration and the participation duration of the overlapping category;
setting values of a ratio a4 and a ratio a5 as default values if there is no overlapping category between the history browsing course category and the history participation course category;
s160: combining the quantity a1, the quantity a2, the similarity a3, the ratio a4 and the ratio a5 to obtain a fourth feature vector;
s170: and combining the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain the feature vector of the user.
Similarly, when the feature vectors of the respective sample users are obtained by combining in step S620 during the training of the new class acceptance prediction model, the first feature vector, the second feature vector, and the third feature vector are formed by the method in step S110, the fourth feature vector is formed by the methods in steps S120 to S160, and then the feature vectors of the respective sample users are obtained by combining in step S170.
By means of calculation and combination of the feature vectors of the user in the embodiment, the feature vectors with higher association degree with the new class acceptance value of the user can be obtained, on one hand, the validity of the feature vectors in the adopted sample data can be guaranteed during model training, the trained new class acceptance prediction model is a model which truly and effectively reflects the receiving willingness degree of the new class of the user, on the other hand, when the new class acceptance of the user is predicted, the adopted input data are some attribute values which most possibly influence the receiving degree of the new class of the user, and prediction is more accurate.
In this embodiment, if the new class acceptance value of the user is greater than the first threshold, in step S300, determining the class of interest of the user according to the historical browsing data of the user includes:
s310: counting the number a6 of the course categories with the browsing times of the user being greater than the fourth threshold and the browsing duration of the user being greater than the fifth threshold;
s320: if the number a6 is greater than the sixth threshold, preferentially taking the class with the browsing times greater than the fourth threshold and the browsing time greater than the fifth threshold as the class of interest;
s330: if a6 is less than or equal to the sixth threshold, in order to ensure the richness of the course recommendation, the course categories with the browsing times of the user being greater than the fourth threshold or the browsing duration of the user being greater than the fifth threshold are all taken as the categories of interest.
Therefore, in the embodiment, the interested classes of the user are comprehensively judged by combining the browsing behavior of the user, and the classes of the classes which are more in line with the interested requirements of the user can be recommended for the user, so that the possibility that the user can not obtain effective class recommendation and needs to query in mass classes by himself is reduced.
In this embodiment, in order to consider the course recommendation requirements of different users, the step S200: after obtaining the predicted new class acceptance value of the user, the method further comprises the following steps:
s700: if the new course acceptance value of the user is less than or equal to the first threshold, it indicates that the user has a low acceptance intention for the new course, and tends to select the course related to the course category in which the user has currently participated in the course, therefore, the course corresponding to the historical participation course category is selected as the recommended course, that is, the course matched with the historical participation course category is selected in the course database as the recommended course of the user, and then the step S500 is continued.
Therefore, the online course recommendation method can realize personalized intelligent course recommendation according to different requirements of different users. Furthermore, for a user with a low class acceptance value, in order to improve the use experience of course recommendation, under the condition that the number of recommended courses is large, in order to help the user to quickly find the course which is most matched with the user, and recommend and display the course which is more in line with the requirement of the user, in the embodiment, multi-dimensional matching of the courses and the user is further added, the courses are sorted according to the matching result, the courses with the top sorting order are preferentially recommended, the time of the user for inquiring the courses is shortened, and the course recommendation efficiency and the course recommendation conversion rate are improved.
As shown in fig. 7, in this embodiment, in step S700, if the new class acceptance value of the user is less than or equal to the first threshold value, S710: after the course corresponding to the historical participation course category is selected as a recommended course, the method further comprises the following steps:
s720: acquiring a teacher preference tag, a collection teacher tag, a horizontal grade tag and a occupation type tag of a user;
s730: acquiring a teacher attribute label, a teacher identity label, a level grade label and a course category label of each recommended course;
s740: for each recommended course, calculating the matching degree of the teacher attribute label and the teacher preference label of the user, the matching degree of the collection teacher label and the teacher identity label, the matching degree of the horizontal grade label of the course and the horizontal grade label of the user and the matching degree of the course category label and the occupation type label of the user;
for the calculation of the matching degree of the teacher attribute label of the course and the teacher preference label of the user, the number of overlapped labels can be counted and divided by the total number of the teacher preference labels to obtain the matching degree, and the similarity between the feature vector of the teacher attribute label and the feature vector of the teacher preference label can also be calculated as the matching degree, wherein the teacher attribute label can comprise the age zone, the gender, the nationality, the personality type and the like of the teacher, and the teacher preference label can comprise the teacher age zone, the gender, the nationality of the teacher, the personality type of the teacher and the like preferred by the user;
calculating the matching degree of the collected teacher label and the teacher identity label, wherein the teacher identity label is the ID of the teacher, the collected teacher labels are the IDs of the collected teachers, if the teacher ID of the course is the ID of the teacher collected by the user, the matching degree is 1, otherwise, the matching degree is 0;
the horizontal level label of the user may be different for each class, and therefore, when the horizontal level label of the class and the horizontal level label of the user are calculated, the matching degree of the horizontal level label of the class and the horizontal level label of the user and the same class of the class is calculated;
calculating the matching degree of the course category labels and the occupation type labels of the user, and searching according to the preset matching degree mapping relation between each occupation type and each course category to obtain the matching degree of the course category labels and the occupation type labels of the user;
s750: weighting and summing the matching degrees of the labels obtained by calculation to obtain the matching degree of each recommended course and the user; the matching degree weights corresponding to the teacher attribute label, the teacher identity label, the horizontal level label and the course category label can be set according to the importance degree, and can be set by a user through a user terminal in advance, so that course recommendation more meeting the requirements of the user can be obtained;
s760: and sorting the recommended courses according to the matching degree from high to low.
In step S500, if the new class acceptance value of the user is less than or equal to the first threshold, when the selected recommended course information is pushed to the user terminal, the selected recommended course information is pushed to the user terminal according to the ranking. Therefore, the recommended course which is firstly seen by the user on the user terminal is the recommended course with the highest matching degree with the course requirement, and higher conversion rate of course recommendation to course subscription participation can be realized.
The invention also provides an online course recommendation method and system of the second embodiment. This embodiment differs from the first embodiment in that: the online course recommending system further comprises a course sequencing module, if the new course acceptance value of the user is greater than a first threshold value, after the recommended course is selected for the user, the course sequencing module further sequences the recommended course, and the recommending efficiency and the recommended course conversion rate are improved.
As shown in fig. 8, in this embodiment, if the new class acceptance value of the user is greater than the first threshold, the step S400: after selecting recommended courses of the user in the course database according to the interested categories of the user, the course sequencing module is further used for sequencing the recommended courses by adopting the following steps:
s410: calculating the similarity between the category of the recommended course and the category of the historical participation course;
when calculating, firstly judging whether the category of the recommended course exists in the historical participation course categories, if so, setting the similarity to 1;
if the recommended course category does not exist in the historical participation course category, judging whether the recommended course category is a similar category of the historical participation course category, if so, setting the similarity as k, wherein k is a preset coefficient, 0< k <1, and if not, setting the similarity as 0;
in another alternative embodiment, if the category of the recommended course exists in the historical participation course categories, the historical participation times corresponding to the category of the recommended course may be further searched, and the similarity of the category of the recommended course is searched according to the mapping relationship between the historical participation times and the similarity of the same category;
in another alternative embodiment, if the category of the recommended course does not exist in the historical participation course categories and is a similar category of the historical participation course categories, further searching the historical participation times of the corresponding similar category, and searching the similarity of the category of the recommended course according to the mapping relationship between the historical participation times and the similarity of the similar category;
s420: and sequencing the recommended courses according to the similarity from low to high.
In step S500, the selected recommended course information is pushed to the user terminal, including pushing the selected recommended course information to the user terminal according to the ranking.
Therefore, when the courses are recommended to the user with high class acceptance, the courses of the categories which are browsed but not participated in are preferentially recommended, richer types of courses can be provided for the user, the diversity of the categories of the participated courses of the user is improved, and the course arrangement is balanced.
Steps S410 to S420 are sorting of the respective categories of the recommended course. Further, in this embodiment, the classes in each category may be sorted according to their number of attendance, and the classes with more remaining denominations are recommended to the user in preference, so that the number of attendance of each class can be balanced, and situations where some classes are full and some classes have few attendance can be avoided.
In this embodiment, if the new class acceptance value of the user is greater than the first threshold, the step S400: after selecting recommended courses of the user in the course database according to the interested categories of the user, the course sequencing module is further used for sequencing the recommended courses by adopting the following steps:
s430: inquiring the number of course openers and the number of people booked for each recommended course from the course management system; the number of the opened curriculum is the number of the planned recruits for the curriculum, and the number of the appointed curriculum is the number of the people who have been registered to participate in the curriculum;
s440: calculating the ratio m of the number of the booked lessons to the number of the opened lessons of each recommended lesson;
s450: and for the recommended courses in the same category, sorting the recommended courses according to the ratio m from low to high, namely, the recommended courses with more vacant registration denominations are ranked more ahead.
Both the sorting manners of the courses in the steps S410 to S420 and the sorting manners of the courses in each course category in the steps S430 to S450 may be adopted, or only one of them may be adopted, that is, only the steps S410 to S420 are executed, and then the step S500 is executed, or only the steps S430 to S450 are executed, and then the step S500 is executed, or after the steps S410 to S420 are executed, the steps S430 to S450 are executed, and then the step S500 is executed.
The invention also provides an online course recommendation method and system of the third embodiment. This embodiment differs from the first embodiment in that: the online course recommending system further comprises a level evaluating module and a course screening module, after the recommended course needing to be pushed to the user terminal is determined, the level evaluating module evaluates the level grade of the user according to historical course data of the user, and the course screening module screens out courses lower than the level grade of the user to avoid repeated recommendation.
As shown in fig. 9, in this embodiment, the step S500: before pushing the selected recommended course information to the user terminal, the method further comprises the following steps:
s810: the level evaluation module inquires course progress and course assessment data of each historical participation category of the user from the course management system;
s820: the level assessment module determines the level grade of the user corresponding to the historical participation course category according to the course progress and the course assessment data of the user, and after the level grade corresponding to the user is determined, the level assessment module can be added as a level grade label of the user corresponding to the course category;
the level assessment module determines a level grade of the user corresponding to the historical participation course category according to the course progress and the course assessment data of the user, specifically, the level assessment module determines the course progress that the latest course assessment data of the user reaches a preset assessment standard, and determines the level grade according to the course progress, for example, the user's progress in the four-six English level course category indicates that the user has completed the four-level English learning, and the course assessment is qualified, the level grade is in accordance with the four-level English level, and if the course assessment is unqualified, the level grade is not in accordance with the four-level English level;
s830: the course filtering module filters out courses corresponding to the historical participation course category and lower than or equal to the user' S level among the recommended courses, and then proceeds to step S500. For example, if the horizontal level of the user in the class of class four and six in english is in conformity with class four in english, then the class entering class four in english or english is removed from the recommended class.
Here, steps S810 to S830 may be performed between step S400 and step S500, or may be performed between step S760 and step S500, that is, after determining that a user has a high or low class acceptance value and recommends a class, it is necessary to filter the classes according to their level levels, remove unnecessary low-level classes, and then recommend the filtered classes for the user.
The embodiment of the invention also provides an online course recommending device, which comprises a processor; a memory having stored therein executable instructions of the processor; wherein the processor is configured to perform the steps of the online course recommendation method via execution of the executable instructions.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.
An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 10. The electronic device 600 shown in fig. 10 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 10, the electronic device 600 is embodied in the form of a general purpose computing device. The combination of the electronic device 600 may include, but is not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting different platform combinations (including memory unit 620 and processing unit 610), a display unit 640, etc.
Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the above-mentioned online course recommendation method section of the present specification. For example, the processing unit 610 may perform the steps as shown in fig. 1. Specifically, when the processing unit 610 executes each step in fig. 1, a specific step execution manner may adopt a specific implementation manner of each step of the online course recommendation method, which is not described again.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The embodiment of the present invention further provides a computer-readable storage medium for storing a program, where the program implements the steps of the online course recommendation method when executed. In some possible embodiments, aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned online course recommendation method section of this specification, when the program product is run on the terminal device.
Referring to fig. 11, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, C + +, or the like, as well as conventional procedural programming languages, such as the "C" language or similar programming languages.
In summary, compared with the prior art, the online course recommendation method, system, device and storage medium provided by the present invention have the following advantages:
the method comprises the steps of establishing a new course acceptance value model for accurately predicting the willingness degree of accepting a new course based on big data analysis, predicting the new course acceptance value for a user based on basic information and historical course data of the user, and recommending courses meeting requirements of different users for the user in a personalized manner according to different new course acceptance values when a course recommendation request sent by a user terminal is received, so that the course recommendation efficiency is improved, the requirement of the user for course retrieval in mass data is reduced, and the course selection efficiency is improved; the whole method does not adopt an excessively complex algorithm, and for each user, the new course acceptance value can be predicted once within a period of time, so that the operation burden and the operation speed of the course recommendation system can be reduced.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (14)
1. An online course recommendation method is characterized by comprising the following steps:
requesting to acquire identity associated information of a user from an account management system, requesting to acquire historical course data of the user from a course management system, and combining to obtain a characteristic vector of the user, wherein the historical course data comprises historical browsing data and historical participation course data;
inputting the characteristic vector of the user into a trained new class acceptance prediction model to obtain a predicted new class acceptance value of the user;
if the new class acceptance value of the user is larger than a first threshold value, determining the class of the interesting course of the user according to the historical browsing data of the user;
selecting recommended courses of the user from a course database according to the interested categories of the user;
and responding to a course recommendation request sent by the user terminal, and pushing the selected recommended course to the user terminal.
2. The online course recommendation method according to claim 1, wherein said new course acceptance prediction model is a new course acceptance prediction model constructed based on machine learning, said method further comprising training said new course acceptance prediction model by using the steps of:
requesting to the account management system for inquiring users of which the registration duration is greater than a second threshold and the number of the historical participation courses is greater than a third threshold as sample users;
requesting to an account management system to acquire the identity associated information of the sample users, requesting to a course management system to acquire historical course data, and respectively combining to obtain the characteristic vector of each sample user;
after the new class acceptance value marking is carried out on the feature vector of each sample user, a training sample is added;
and iteratively training the new class acceptance prediction model by adopting the training samples.
3. The online course recommendation method according to claim 2, wherein said marking the feature vector of each sample user with a new course acceptance value comprises the following steps:
sending an electronic questionnaire to a user terminal of the sample user, the electronic questionnaire including a level option of accepting a new course willingness;
and extracting the degree grade of the willingness of the sample user to accept the new course from the feedback of the user terminal, determining the new course acceptance value of the sample user according to the corresponding relation between the degree grade of the willingness of accepting the new course and the new course acceptance value, and marking the sample user.
4. The online course recommendation method of claim 1, wherein said historical browsing data comprises historical browsing course categories, browsing times of each historical browsing course category and browsing duration of each historical browsing course category, and said historical participation course data comprises historical participation course categories, participation times of each historical participation course category and participation duration of each historical participation course category.
5. The online course recommendation method of claim 4, wherein said combining to obtain the feature vector of the user comprises the steps of:
respectively mapping attribute values of all attributes of the identity correlation information, the historical browsing data and the historical participation data to obtain a first characteristic vector, a second characteristic vector and a third characteristic vector;
counting the number a1 of the course categories with the browsing times of the user being greater than a fourth threshold or the browsing duration of the user being greater than a fifth threshold;
counting the number a2 of the class with the user participation times larger than the fourth threshold or the user participation time larger than the fifth threshold;
calculating the similarity a3 of the historical browsing course category and the historical participation course category;
searching for the overlapping category of the historical browsing course category and the historical participation course category, calculating the ratio a4 of the browsing times and the participation times of the overlapping category, and calculating the ratio a5 of the browsing duration and the participation duration of the overlapping category;
combining the quantity a1, the quantity a2, the similarity a3, the ratio a4 and the ratio a5 to obtain a fourth feature vector;
and combining the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain the feature vector of the user.
6. The online course recommendation method as claimed in claim 4, wherein if the new course acceptance value of the user is greater than a first threshold, said determining the category of the course of interest of the user according to the historical browsing data of the user comprises:
counting the number a6 of the course categories with the browsing times of the user being greater than the fourth threshold and the browsing duration of the user being greater than the fifth threshold;
and if the number a6 is greater than a sixth threshold, the class with the browsing times greater than the fourth threshold and the browsing time greater than a fifth threshold is taken as the interested class, and if the number a6 is less than or equal to the sixth threshold, the class with the browsing times greater than the fourth threshold or the browsing time greater than the fifth threshold is taken as the interested class.
7. The online course recommendation method of claim 6, wherein if the new course acceptance value of the user is greater than the first threshold, after selecting the recommended course of the user from the course database according to the interest category of the user, further comprising the steps of:
calculating the similarity between the recommended course category and the historical participation course category, and sequencing the recommended courses from low to high according to the similarity;
and pushing the selected recommended course information to the user terminal, wherein pushing the selected recommended course information to the user terminal according to the sequence.
8. The online course recommendation method according to any one of claims 1 to 7, wherein, if the new course acceptance value of the user is greater than the first threshold, after selecting the recommended course of the user from the course database according to the interest category of the user, further comprising the steps of:
inquiring the number of course openers and the number of people booked for each recommended course from the course management system;
calculating the ratio m of the number of the booked lessons to the number of the opened lessons of each recommended lesson;
and sorting the recommended courses in the same category according to the ratio m from low to high.
9. The online course recommendation method according to any one of claims 1 to 7, further comprising the following steps after obtaining the predicted new course acceptance value of the user:
if the new course acceptance value of the user is smaller than or equal to a first threshold value, selecting the course corresponding to the historical participation course category as a recommended course;
and responding to a course recommendation request sent by the user terminal, and pushing the selected recommended course to the user terminal.
10. The online course recommendation method of claim 9, wherein if the new course acceptance value of the user is less than or equal to the first threshold, after selecting the course corresponding to the historical participation course category as the recommended course, further comprising the steps of:
acquiring a teacher preference tag, a collection teacher tag, a horizontal grade tag and a occupation type tag of a user;
acquiring a teacher attribute label, a teacher identity label, a level grade label and a course category label of each recommended course;
for each recommended course, calculating the matching degree of a teacher attribute label and a teacher preference label of the user, the matching degree of a collected teacher label and a teacher identity label, the matching degree of a horizontal grade label and a horizontal grade label of the user and the matching degree of a course category label and an occupation type label of the user, and weighting and summing the matching degrees to obtain the matching degree of each recommended course and the user;
sorting the recommended courses according to the matching degree from high to low;
and pushing the selected recommended course information to the user terminal, wherein pushing the selected recommended course information to the user terminal according to the sequence.
11. The online course recommendation method according to any one of claims 1 to 7, wherein before pushing the selected recommended course information to the user terminal, further comprising the steps of:
inquiring course progress and course assessment data of each historical participation category of the user from the course management system;
determining the level grade of the user corresponding to the historical participation course category according to the course progress and the course assessment data of the user;
screening out courses of the recommended courses that correspond to the historical participation course category and are less than or equal to the user's level rating.
12. An online course recommendation system applied to the online course recommendation method according to any one of claims 1 to 11, the system comprising:
the data acquisition module is used for requesting the account management system to acquire the identity associated information of the user, requesting the course management system to acquire historical course data of the user, and combining the historical course data to obtain a characteristic vector of the user, wherein the historical course data comprises historical browsing data and historical participation course data;
the acceptance prediction module is used for inputting the characteristic vector of the user into a trained new class acceptance prediction model to obtain a predicted new class acceptance value of the user;
the course selection module is used for determining the interested course category of the user according to the historical browsing data of the user and selecting the recommended course of the user in the course database according to the interested category of the user if the new course acceptance value of the user is greater than a first threshold value;
and the user interaction module is used for responding to the course recommendation request sent by the user terminal and pushing the selected recommended course to the user terminal.
13. An online course recommending apparatus, comprising:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the online course recommendation method of any of claims 1-11 via execution of the executable instructions.
14. A computer-readable storage medium storing a program, wherein the program when executed implements the steps of the online course recommendation method of any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010223699.3A CN111475716A (en) | 2020-03-26 | 2020-03-26 | Online course recommendation method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010223699.3A CN111475716A (en) | 2020-03-26 | 2020-03-26 | Online course recommendation method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111475716A true CN111475716A (en) | 2020-07-31 |
Family
ID=71747797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010223699.3A Pending CN111475716A (en) | 2020-03-26 | 2020-03-26 | Online course recommendation method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111475716A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417302A (en) * | 2020-12-08 | 2021-02-26 | 六晟信息科技(杭州)有限公司 | Big data-based information content intelligent analysis recommendation processing system |
| CN112561750A (en) * | 2020-12-14 | 2021-03-26 | 软通动力信息技术(集团)股份有限公司 | Course recommendation method and device, electronic equipment and storage medium |
| CN112632385A (en) * | 2020-12-29 | 2021-04-09 | 中国平安人寿保险股份有限公司 | Course recommendation method and device, computer equipment and medium |
| CN112733026A (en) * | 2021-01-07 | 2021-04-30 | 任杰 | Online course pushing method based on big data |
| CN112749340A (en) * | 2021-01-19 | 2021-05-04 | 敖客星云(北京)科技发展有限公司 | Course recommendation method and system based on big data, mobile terminal and storage medium |
| CN112784044A (en) * | 2021-01-18 | 2021-05-11 | 辽宁向日葵教育科技有限公司 | Knowledge base recommendation system based on content tags |
| CN112785378A (en) * | 2021-01-22 | 2021-05-11 | 平安养老保险股份有限公司 | Course recommendation method and device, computer equipment and storage medium |
| CN112884505A (en) * | 2021-02-03 | 2021-06-01 | 北京百家科技集团有限公司 | User behavior prediction method and device, computer equipment and storage medium |
| CN113065060A (en) * | 2021-02-18 | 2021-07-02 | 山东师范大学 | Deep learning-based education platform course recommendation method and system |
| CN113392135A (en) * | 2021-06-04 | 2021-09-14 | 南京海容互连电子科技有限公司 | Intelligent online education interaction method, device, equipment and storage medium |
| CN113672722A (en) * | 2021-08-20 | 2021-11-19 | 中国平安财产保险股份有限公司 | Online course intelligent recommendation method and device, electronic equipment and storage medium |
| CN113762801A (en) * | 2021-09-17 | 2021-12-07 | 北京量子之歌科技有限公司 | Network course management method, device, equipment and storage medium |
| CN113781086A (en) * | 2021-01-21 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Article recommendation method, device, medium and electronic equipment |
| CN114357411A (en) * | 2022-01-19 | 2022-04-15 | 英才(广州)在线教育科技有限公司 | Online education system based on block chain |
| CN114661949A (en) * | 2022-03-31 | 2022-06-24 | 南京硕茂电子科技有限公司 | Client data analysis system and method under big data situation |
| CN114757431A (en) * | 2022-04-27 | 2022-07-15 | 上海妙克信息科技有限公司 | User information processing method and device, electronic equipment and computer readable medium |
| CN114896498A (en) * | 2022-05-16 | 2022-08-12 | 咪咕文化科技有限公司 | Course recommendation method, system, terminal and storage medium |
| CN116257694A (en) * | 2023-05-16 | 2023-06-13 | 安徽教育网络出版有限公司 | Intelligent search recommendation method and system based on online learning courses |
| CN116992142A (en) * | 2023-08-08 | 2023-11-03 | 广东蕾特恩科技发展有限公司 | Intelligent course recommendation system and method based on user big data |
| CN117390277A (en) * | 2023-10-27 | 2024-01-12 | 深圳华云科技研发有限公司 | Course resource and service management method and system |
| CN117555937A (en) * | 2024-01-12 | 2024-02-13 | 山东街景智能制造科技股份有限公司 | Data acquisition method and system for product recommendation |
-
2020
- 2020-03-26 CN CN202010223699.3A patent/CN111475716A/en active Pending
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417302B (en) * | 2020-12-08 | 2021-06-04 | 六晟信息科技(杭州)有限公司 | Big data-based information content intelligent analysis recommendation processing system |
| CN112417302A (en) * | 2020-12-08 | 2021-02-26 | 六晟信息科技(杭州)有限公司 | Big data-based information content intelligent analysis recommendation processing system |
| CN112561750A (en) * | 2020-12-14 | 2021-03-26 | 软通动力信息技术(集团)股份有限公司 | Course recommendation method and device, electronic equipment and storage medium |
| CN112632385A (en) * | 2020-12-29 | 2021-04-09 | 中国平安人寿保险股份有限公司 | Course recommendation method and device, computer equipment and medium |
| CN112632385B (en) * | 2020-12-29 | 2023-09-22 | 中国平安人寿保险股份有限公司 | Course recommendation method, course recommendation device, computer equipment and medium |
| CN112733026A (en) * | 2021-01-07 | 2021-04-30 | 任杰 | Online course pushing method based on big data |
| CN112784044A (en) * | 2021-01-18 | 2021-05-11 | 辽宁向日葵教育科技有限公司 | Knowledge base recommendation system based on content tags |
| CN112749340A (en) * | 2021-01-19 | 2021-05-04 | 敖客星云(北京)科技发展有限公司 | Course recommendation method and system based on big data, mobile terminal and storage medium |
| CN113781086A (en) * | 2021-01-21 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Article recommendation method, device, medium and electronic equipment |
| CN112785378A (en) * | 2021-01-22 | 2021-05-11 | 平安养老保险股份有限公司 | Course recommendation method and device, computer equipment and storage medium |
| CN112884505A (en) * | 2021-02-03 | 2021-06-01 | 北京百家科技集团有限公司 | User behavior prediction method and device, computer equipment and storage medium |
| CN113065060A (en) * | 2021-02-18 | 2021-07-02 | 山东师范大学 | Deep learning-based education platform course recommendation method and system |
| CN113065060B (en) * | 2021-02-18 | 2022-11-29 | 山东师范大学 | Deep learning-based education platform course recommendation method and system |
| CN113392135A (en) * | 2021-06-04 | 2021-09-14 | 南京海容互连电子科技有限公司 | Intelligent online education interaction method, device, equipment and storage medium |
| CN113672722A (en) * | 2021-08-20 | 2021-11-19 | 中国平安财产保险股份有限公司 | Online course intelligent recommendation method and device, electronic equipment and storage medium |
| CN113672722B (en) * | 2021-08-20 | 2023-08-22 | 中国平安财产保险股份有限公司 | Online course intelligent recommendation method and device, electronic equipment and storage medium |
| CN113762801A (en) * | 2021-09-17 | 2021-12-07 | 北京量子之歌科技有限公司 | Network course management method, device, equipment and storage medium |
| CN113762801B (en) * | 2021-09-17 | 2024-03-26 | 北京量子之歌科技有限公司 | Network course management method, device, equipment and storage medium |
| CN114357411A (en) * | 2022-01-19 | 2022-04-15 | 英才(广州)在线教育科技有限公司 | Online education system based on block chain |
| CN114357411B (en) * | 2022-01-19 | 2022-09-02 | 英才(广州)在线教育科技有限公司 | Online education system based on block chain |
| CN114661949B (en) * | 2022-03-31 | 2023-11-24 | 布谷鸟数字科技(中山)股份有限公司 | Client data analysis system and method under big data situation |
| CN114661949A (en) * | 2022-03-31 | 2022-06-24 | 南京硕茂电子科技有限公司 | Client data analysis system and method under big data situation |
| CN114757431A (en) * | 2022-04-27 | 2022-07-15 | 上海妙克信息科技有限公司 | User information processing method and device, electronic equipment and computer readable medium |
| CN114896498A (en) * | 2022-05-16 | 2022-08-12 | 咪咕文化科技有限公司 | Course recommendation method, system, terminal and storage medium |
| CN116257694A (en) * | 2023-05-16 | 2023-06-13 | 安徽教育网络出版有限公司 | Intelligent search recommendation method and system based on online learning courses |
| CN116257694B (en) * | 2023-05-16 | 2023-08-22 | 安徽教育网络出版有限公司 | Intelligent search recommendation method and system based on online learning courses |
| CN116992142A (en) * | 2023-08-08 | 2023-11-03 | 广东蕾特恩科技发展有限公司 | Intelligent course recommendation system and method based on user big data |
| CN116992142B (en) * | 2023-08-08 | 2024-02-09 | 广东蕾特恩科技发展有限公司 | Intelligent course recommendation system and method based on user big data |
| CN117390277A (en) * | 2023-10-27 | 2024-01-12 | 深圳华云科技研发有限公司 | Course resource and service management method and system |
| CN117555937A (en) * | 2024-01-12 | 2024-02-13 | 山东街景智能制造科技股份有限公司 | Data acquisition method and system for product recommendation |
| CN117555937B (en) * | 2024-01-12 | 2024-04-19 | 山东街景智能制造科技股份有限公司 | Data acquisition method and system for product recommendation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111475716A (en) | Online course recommendation method, system, equipment and storage medium | |
| CN112214670B (en) | Online course recommendation method and device, electronic equipment and storage medium | |
| CN106021363B (en) | course recommendation method and device | |
| KR20190118477A (en) | Entity recommendation method and apparatus | |
| CN104680453B (en) | Course based on student's attribute recommends method and system | |
| CN111831905B (en) | Recommendation method and device based on team scientific research influence and sustainability modeling | |
| CN110825956A (en) | Information flow recommendation method and device, computer equipment and storage medium | |
| CN111209474A (en) | Online course recommendation method and device, computer equipment and storage medium | |
| Bydžovská | Course Enrolment Recommender System | |
| US11238124B2 (en) | Search optimization based on relevant-parameter selection | |
| CN116257694B (en) | Intelligent search recommendation method and system based on online learning courses | |
| US20140019389A1 (en) | Method, Software, and System for Making a Decision | |
| CN111859147B (en) | Object recommendation method, object recommendation device and electronic equipment | |
| CN115577185A (en) | Muting course recommendation method and device based on mixed reasoning and mesopic group decision | |
| CN116204714A (en) | Recommendation method, recommendation device, electronic equipment and storage medium | |
| CN114707068A (en) | Method, device, equipment and medium for recommending intelligence base knowledge | |
| CN110929169A (en) | Position recommendation method based on improved Canopy clustering collaborative filtering algorithm | |
| Mishra et al. | Dynamic identification of learning styles in MOOC environment using ontology based browser extension | |
| CN117194716B (en) | Educational robot course personalized recommendation system based on big data | |
| KR20200133976A (en) | Contents Curation Method and Apparatus thereof | |
| CN112330387B (en) | Virtual broker applied to house watching software | |
| CN116362426B (en) | Learning behavior prediction management system and method based on artificial intelligence and deep learning | |
| CN113626638A (en) | Short video recommendation processing method and device, intelligent terminal and storage medium | |
| CN117851563A (en) | Automatic question answering method and device, electronic equipment and readable storage medium | |
| CN112765374A (en) | Education resource screening system and method for information push |
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 |
Effective date of registration: 20210104 Address after: 200030 unit 01, room 801, 166 Kaibin Road, Xuhui District, Shanghai Applicant after: Shanghai Ping An Education Technology Co.,Ltd. Address before: 152, 86 Tianshui Road, Hongkou District, Shanghai Applicant before: TUTORABC NETWORK TECHNOLOGY (SHANGHAI) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200731 |
|
| WD01 | Invention patent application deemed withdrawn after publication |