CN110990691A - Online course recommendation method and device and computer storage medium - Google Patents
Online course recommendation method and device and computer storage medium Download PDFInfo
- Publication number
- CN110990691A CN110990691A CN201911115500.9A CN201911115500A CN110990691A CN 110990691 A CN110990691 A CN 110990691A CN 201911115500 A CN201911115500 A CN 201911115500A CN 110990691 A CN110990691 A CN 110990691A
- Authority
- CN
- China
- Prior art keywords
- recommended
- course
- courses
- learning
- historical
- 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 32
- 238000010586 diagram Methods 0.000 description 17
- 238000012360 testing method Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Health & Medical Sciences (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)
Abstract
The invention provides an online course recommending method, device and computer storage medium, which are used for recommending learning courses suitable for a user when the user selects courses, wherein the method comprises the steps of forming a plurality of reference object sets by history objects with the similarity larger than a set threshold value with the similarity of the objects to be recommended and each history object participating in learning according to the similarity of the objects to be recommended and each history object, selecting a course matched with the current learning state information of the objects to be recommended from the learning path of each history object in the reference object sets aiming at any one reference object set, taking the course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set, determining a target course needing to be recommended to the objects to be recommended from the alternative courses corresponding to each reference object set, and recommending the determined target course to the objects to be recommended, so that the learning courses suitable for the user can be recommended to the user.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an online course recommendation method, an online course recommendation apparatus, and a computer storage medium.
Background
With the rapid development of internet technology, the digitalized online learning mode is more and more accepted by the public, the user scale of the online education platform increases in a geometric manner, in order to meet the learning requirements of different users, the contents of various online education platforms are continuously rich, the coverage is continuously enlarged, and more course selection and learning space is provided for registered users.
However, when facing a large amount of courses, users often have the inevitable appearance of blindness and difficulty in selection, and it is difficult to select a learning course suitable for themselves from the large amount of courses. At present, no recommendation method for online education courses exists.
Disclosure of Invention
The invention provides an online course recommending method, an online course recommending device and a computer storage medium, which are used for recommending a learning course suitable for a user to the user when the user selects the course.
Based on the foregoing problems, in a first aspect, an embodiment of the present invention provides an online course recommendation method, including:
determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning;
according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
aiming at any one reference object set, selecting a course matched with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence, and taking the course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set;
and determining target courses needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set, and recommending the determined target courses to the object to be recommended.
In a possible implementation manner, the current learning state information of the object to be recommended is first participating in online learning;
the selecting a course matching with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence comprises the following steps:
and aiming at any one history object in the reference object set, taking the firstly learned course in the learning path of the history object as the course matched with the current learning state information of the object to be recommended.
In a possible implementation manner, the current learning state information of the object to be recommended is that online learning is already participated in;
the selecting a course matching with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence comprises the following steps:
acquiring a course which is learned by the object to be recommended for the last time;
and aiming at any one history object in the reference object set, selecting a course which is learned by the history object after learning the course which is learned by the object to be recommended most recently from the learning path of the history object, and taking the course selected from the learning path as a course matched with the current learning state information of the object to be recommended.
In a possible implementation manner, the determining, from the candidate courses corresponding to each reference object set, a target course that needs to be recommended to the object to be recommended includes:
and taking the alternative courses corresponding to each reference object set as target courses needing to be recommended to the object to be recommended.
In a possible implementation manner, the determining, from the candidate courses corresponding to each reference object set, a target course that needs to be recommended to the object to be recommended includes:
according to the requirement information in the first characteristic information of the object to be recommended, taking an alternative course which is matched with the requirement information of the object to be recommended in the alternative courses corresponding to each reference object set as a target course which needs to be recommended to the object to be recommended; and/or
And according to the capability information of the object to be recommended, taking the candidate courses which are not learned by the object to be recommended in the candidate courses corresponding to each reference object set as target courses to be recommended to the object to be recommended.
In a possible implementation manner, the recommending the determined target course to the object to be recommended includes:
and recommending the determined target courses to the object to be recommended according to the recommendation coefficient corresponding to each target course from large to small.
In one possible implementation manner, the recommendation coefficient corresponding to the target course is determined according to the following manner:
taking the product of the similarity of the object to be recommended and a historical object in a reference object set corresponding to the target course and a weight value corresponding to the target course as a recommendation coefficient corresponding to the target course;
the weight value is the ratio of the number of times of the target course appearing to the number of the historical objects in the reference object set when the course matched with the current learning state information of the object to be recommended is selected from the learning path of each historical object in the reference object set corresponding to the target course.
In a second aspect, an embodiment of the present invention provides an online course recommending apparatus, including:
the determining module is used for determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical object participating in online learning;
the composition module is used for composing the historical objects with the similarity greater than a set threshold value with the object to be recommended into a plurality of reference object sets according to the similarity between the object to be recommended and each historical object; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
the selection module is used for selecting a course matched with the current learning state information of the object to be recommended from the learning path of each historical object in the reference object set, which is used for expressing the course learning sequence, aiming at any one reference object set, and taking the course with the largest occurrence frequency in the selected courses as the alternative course corresponding to the reference object set;
and the recommending module is used for determining a target course needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set and recommending the determined target course to the object to be recommended.
In a third aspect, an embodiment of the present invention provides an online course recommendation system, including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to:
determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning;
according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
aiming at any one reference object set, selecting a course matched with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence, and taking the course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set;
and determining target courses needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set, and recommending the determined target courses to the object to be recommended.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method according to the first aspect.
The technical scheme provided by the embodiment of the invention at least has the following beneficial effects:
according to the online course recommendation method provided by the embodiment of the invention, the similarity between the object to be recommended and each historical object is determined according to the first characteristic information of the object to be recommended and the second characteristic information of the historical object participating in online learning, and the historical objects with the similarity larger than a set threshold value with the object to be recommended are combined into a plurality of reference object sets according to the determined similarity; the similarity between the history objects in the same reference object set and the objects to be recommended is the same, for any one reference object set, a course matched with the current learning state information of the objects to be recommended is obtained from the learning path of each history object in the reference object set, which is used for representing the course learning sequence, the most courses in the selected courses are used as the alternative courses corresponding to the reference object set, the target course needing to be recommended to the objects to be recommended is determined again from the alternative courses, and the determined target course is recommended to the objects to be recommended. Therefore, the course which accords with the current learning state of the object to be recommended can be selected from the learning path of the historical user which is similar to the object to be recommended according to the current learning state of the object to be recommended, personalized and specialized course recommendation is realized, and the use experience of the user is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention and are not to be construed as limiting the invention.
FIG. 1 is a flow diagram illustrating an online lesson method in accordance with an exemplary embodiment;
FIG. 2 is a diagram illustrating the results of a performance test question in accordance with one illustrative embodiment;
FIG. 3 is a diagram illustrating a ranked recommended target course, according to an example embodiment;
FIG. 4 is a flow diagram illustrating a first method for completing online course recommendation, according to an exemplary embodiment;
FIG. 5 is a flow diagram illustrating a second method for online course recommendation completion, according to an exemplary embodiment;
FIG. 6 is a block diagram illustrating an online course recommendation apparatus in accordance with an exemplary embodiment;
FIG. 7 is a block diagram illustrating an online course recommendation system in accordance with an exemplary embodiment.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
Based on the above problem, an embodiment of the present invention provides a method for recommending online courses, as shown in fig. 1, the method includes the following steps:
step S101, determining the similarity between an object to be recommended and each historical object according to first characteristic information of the object to be recommended and second characteristic information of the historical objects participating in online learning;
step S102, according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value;
the similarity between the historical object in the same reference object set and the object to be recommended is the same;
step S103, aiming at any one reference object set, selecting a course matched with the current learning state information of the object to be recommended from the learning path of each historical object in the reference object set, wherein the learning path is used for expressing the course learning sequence, and taking the course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set;
step S104, determining target courses needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set, and recommending the determined target courses to the object to be recommended.
The first characteristic information of the user to be recommended and the second characteristic information of the history object participating in history learning can be the following information:
information 1, student basic information.
Wherein, the student basic information comprises part or all of the following information: name, gender, age, contact.
Information 2, student group attribute information.
Wherein, the student group attribute information comprises part or all of the following information: industry field, professional direction, job category.
Information 3, student requirement information.
Wherein, the student requirement information comprises part or all of the following information: work skills, skill level, personal interest preferences.
Wherein, the student platform use information comprises part or all of the following information: learning courses, course classification, learning progress, class work completion condition and learning duration.
In the embodiment of the invention, when the user registers the online learning platform, all or part of the information 1, the information 2 and the information 3 in the first characteristic information needs to be filled.
When it is determined that a subject to be recommended needs course recommendation, a reference object set composed of history objects with similarity greater than a set threshold with the subject to be recommended is acquired according to first characteristic information of the subject to be recommended and second characteristic information of the history objects participating in online learning.
Specifically, the similarity between the object to be recommended and the historical object is determined according to the first characteristic information of the object to be recommended and the second characteristic information of the historical object which participates in online learning.
According to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning, a user characteristic data set and/or a user portrait of the object to be recommended and each historical object are generated;
and calculating the similarity between the object to be recommended and each historical object according to the feature data set and/or the user portrait of the object to be recommended and each historical object.
In the implementation, an optional implementation manner is that a similarity formula is used to calculate a similarity between the object to be recommended and each historical object, where the similarity formula may be a Pearon coefficient and/or a cosine similarity formula.
After the similarity between the object to be recommended and each historical object is determined, the historical objects with the similarity larger than a set threshold value with the object to be recommended are combined into a plurality of reference object sets.
And the similarity between the historical object in the same reference object set and the object to be recommended is the same.
In the implementation, for example, if the threshold is set to 0.9, the similarity between the history object a and the object to be recommended is 0.98, the similarity between the history object B and the object to be recommended is 0.98, the similarity between the history object C and the object to be recommended is 0.93, the similarity between the history object D and the object to be recommended is 0.89, and the similarity between the history object E and the object to be recommended is 0.93, the history object a and the history object B form the reference object set a, and the history object C and the history object E form the reference object set B.
Here, the threshold is set in advance by a person skilled in the art based on empirical values, and is not limited specifically.
And aiming at any one reference object set in the obtained multiple reference objects, selecting a course matched with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence.
In the embodiment of the invention, the course matched with the current learning state information can be selected according to the different learning state information of the object to be recommended.
Specifically, a course matched with the current learning state information is selected according to the following learning state information of the object to be recommended:
the learning state information 1 and the current learning state information of the object to be recommended are first participated in learning.
In implementation, after determining that course recommendation is needed for an object to be recommended, which participates in learning for the first time, for any reference object set of the object to be recommended, a course which is learned first in a learning path of any historical object in the reference object set is taken as a course matched with current learning state information of the object to be recommended.
For example, if the learning path of the history object a in the reference object set a is "SQL base-SQL high-order-DB 2", the lesson "SQL base" learned first in the learning path of the history object a is taken as the lesson matching the current learning state information of the object to be recommended, and the learning path of the history object B is "DB 2-SQL base-SQL high-order", the lesson "DB 2" learned first in the learning path of the history object B is taken as the lesson matching the current learning state information of the object to be recommended.
The learning state information 2 and the current learning state information of the object to be recommended are the information that the online learning is already participated in.
In the implementation, when it is determined that course recommendation is needed for an object to be recommended that has participated in online learning, a course that the object to be recommended has learned most recently is acquired first, a course that the object to be recommended has learned most recently is selected from learning paths of each history object in a reference object set for any one reference object set of the object to be recommended, and the course selected from the learning paths is taken as a course that matches current learning state information of the object to be recommended.
For example, the obtained course that the object to be recommended has learned last time is "high basis", the learning path of the historical object a in the reference object set a is "high basis-linear algebra-complex function", then the "linear algebra" learned after the "high basis" learned last time by the object to be recommended in the learning path is taken as the course matched with the current learning state information of the object to be recommended, the learning path of the historical object B is "linear algebra-high basis-probability theory", and then the "probability theory" learned after the "high basis" learned last time by the object to be recommended in the learning path is taken as the course matched with the current learning state information of the object to be recommended.
And after a plurality of courses which are selected from any one reference object set and are matched with the current learning state information of the object to be recommended, taking the course with the largest occurrence number as an alternative course corresponding to the reference object set.
For example, in the reference object set B, the selected courses that match the current learning state information of the object to be recommended are "composition elementary level", "reading understanding intermediate level", and "finishing filling empty elementary level", where the number of times that the course "composition elementary level" appears is 10, the number of times that the course "reading understanding intermediate level" appears is 15, and the number of times that the finishing filling empty level "appears is 12, the course" reading understanding intermediate level "with the largest number of occurrences is taken as the candidate course corresponding to the reference object set B. In the reference object set C, the selected courses matched with the current learning state information of the object to be recommended are "english listening comprehension elementary", reading comprehension elementary "and" english translation elementary ", wherein the number of times of occurrence of the course" english listening comprehension elementary "is 13, the number of times of occurrence of the course" reading comprehension elementary "is 11, and the number of times of occurrence of the course" english translation elementary "is 14, and then the course" english translation elementary "with the largest number of occurrences is taken as the candidate course corresponding to the reference object set C.
In order to enable the course finally recommended to the object to be recommended to better conform to the current learning state of the object to be recommended, in the embodiment of the present invention, after the corresponding alternative courses are obtained from all the reference object sets, the target course finally required to be recommended to the object to be recommended needs to be determined again.
Specifically, a target course needing to be recommended to an object to be recommended is determined from the alternative courses corresponding to each reference object set.
An optional implementation manner is that the alternative course corresponding to each reference object set is taken as a target course to be recommended to the object to be recommended.
In implementation, after the corresponding alternative courses are obtained from all the reference object sets, all the alternative courses are taken as target courses to be recommended to the object to be recommended.
For example, the reference object set of the object to be recommended is a reference object set a, a reference object set B, and a reference object set C, where the alternative course corresponding to the reference object set a is "high-number medium-level", the alternative course corresponding to the reference object set B is "complex function primary", and the alternative course corresponding to the reference object set C is "calculus primary", and then the alternative courses "high-number medium-level", "complex function primary", and "calculus primary" are all used as the target courses that need to be recommended to the object to be recommended.
In the embodiment of the invention, the obtained alternative courses corresponding to each reference object can be screened, and the screened alternative courses are recommended to the user to be recommended as the target courses.
Specifically, the target course to be recommended to the object to be recommended may be determined from the alternative courses corresponding to each reference object according to part or all of the following manners:
the method 1 includes that according to the requirement information in the first characteristic information of the object to be recommended, the alternative courses matched with the requirement information of the object to be recommended in the alternative courses corresponding to each reference object set are taken as target courses to be recommended to the object to be recommended.
In implementation, according to the requirement information in the first characteristic information of the object to be recommended, the course corresponding to the requirement information is determined, and the course which is the same as the course corresponding to the requirement information of the object to be recommended in the alternative courses corresponding to each reference object set is taken as a target course to be recommended to the object to be recommended.
For example, taking the requirement information in the first characteristic information of the object to be recommended as the personal preference information as an example, the obtained candidate courses corresponding to each reference object set of the object to be recommended are "SQL base", "SQL high order", "DB 2", "Hadoop", the personal preference information of the object to be recommended is "big data analyst", the determined courses corresponding to the "big data analyst" are "DB 2", "Hadoop", and the courses "DB 2" and "Hadoop" that are the same as the courses corresponding to the personal preference information in the candidate courses are taken as the target courses to be recommended to the object to be recommended.
And 2, according to the capability information of the object to be recommended, taking the candidate courses which are not learned by the object to be recommended in the candidate courses corresponding to each reference object set as target courses to be recommended to the object to be recommended.
The embodiment of the invention provides an implementation mode for optionally obtaining the capability information of an object to be recommended, which is to complete a set of capability test questions generated according to alternative courses corresponding to each reference object set by the object to be recommended after determining that the object to be recommended needs to be recommended for the courses, and take the test result of the object to be recommended as the capability information of the object to be recommended.
In the implementation, according to the test result of the ability test questions generated by the alternative courses corresponding to each reference object set completed by the object to be recommended, the alternative courses corresponding to the ability test questions with the test results meeting the preset conditions are used as the alternative courses which are not yet learned by the object to be recommended, and finally, the alternative courses which are not yet learned are recommended to the object to be recommended as the target courses which need to be recommended to the object to be recommended.
Here, the preset conditions are preset by those skilled in the art according to their own experience, and are not limited in particular.
For example, the acquired candidate courses corresponding to the reference object set of the object to be recommended are "SQL foundation" and "c language foundation", the preset condition is that the number of error problems is greater than 4, the test result of the capability test problem completed by the object to be recommended and generated according to the candidate course corresponding to each reference object set is shown in fig. 2, 1 to 5 are the capability test problems generated according to the candidate course "SQL foundation", and 6 to 10 are the capability test problems generated according to the candidate course "c language foundation", wherein the result of the user test is that the number of error problems of the capability test problem of the candidate course "SQL foundation" is 5, the number of error problems of the capability test problem of the candidate course "c language foundation" is 1, and then the candidate course "SQL foundation" with the number of error problems greater than 4 is taken as the target course to be recommended to the object to be recommended.
And after target courses needing to be recommended to the object to be recommended are determined from the alternative courses corresponding to each reference set, recommending the determined target courses to the object to be recommended.
Before recommending the determined target course to the object to be recommended, the embodiment of the invention can also sequence the determined target course and recommend the sequenced target course to the object to be recommended.
According to an optional implementation manner, according to a recommendation coefficient corresponding to each target course, the determined target courses are recommended to an object to be recommended according to a sequence of the recommendation coefficients from large to small.
Specifically, the recommendation coefficient of the target course is determined according to the following manner:
taking the product of the similarity of the object to be recommended and the historical object in the reference object set corresponding to the target course and the weight value corresponding to the target course as the recommendation coefficient corresponding to the target course;
the weight value is the ratio of the number of times of the target course appearing to the number of the historical objects in the reference object set when the course matched with the current learning state information of the object to be recommended is selected from the learning path of each historical object in the reference object set corresponding to the target course.
For example, the similarity between the object to be recommended and the history object in the reference set a corresponding to the target course "high number primary" is 0.9, when a course matching the current learning state information of the object to be recommended is selected from the learning path of each history object in the reference set a corresponding to the target course "high number primary", the frequency of occurrence of the target course "high number primary" is 9, the number of history objects in the reference set a is 10, the weight value corresponding to the target course "high number primary" is 9/10, the product of the similarity and the weight value is used as a recommendation coefficient, and finally the recommendation coefficient is obtained as follows: 0.9 × (9/10) ═ 0.81.
And after the recommendation coefficients of all the target courses are obtained, recommending the target courses to be recommended according to the sequence of the recommendation coefficients from large to small.
For example, the recommendation coefficient of the target course "SQL primary" is 0.95, the recommendation coefficient of the target course "SQL middle level" is 0.91, the recommendation coefficient of the target course "DB 2" is 0.88, the recommendation coefficient of the target course "Hadoop" is 0.79, and the target courses sorted in the order of the recommendation coefficients from large to small are shown in fig. 3.
Fig. 4 is a flowchart of a complete method for recommending online courses, taking the current learning state information of an object to be recommended as an example for first online learning, and specifically includes the following steps:
step S401, determining that an object to be recommended needs course recommendation;
step S402, determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning;
step S403, according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value;
the similarity between the historical object in the same reference object set and the object to be recommended is the same;
s404, aiming at each historical object in any reference object set, selecting a first-learned course in a learning path of the historical object;
step S405, the curriculum with the largest occurrence frequency in the selected curriculums is used as an alternative curriculum corresponding to the reference object set;
step S406, determining a target course needing to be recommended to an object to be recommended from the alternative courses corresponding to each reference object set;
and step S407, recommending the determined target courses to the object to be recommended according to the recommendation coefficients corresponding to each target course from large to small.
Fig. 5 is a flowchart of a complete online course recommendation method, taking the current learning state information of the object to be recommended as an example of participating in online learning, and specifically includes the following steps:
step S501, determining that an object to be recommended needs course recommendation;
step S502, determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning;
step S503, according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value;
the similarity between the historical object in the same reference object set and the object to be recommended is the same;
step S504, obtaining a course which is learned by the object to be recommended for the last time;
step S505, aiming at each historical object in any reference object set, selecting a course which is learned by a selected historical object after learning a course which is learned by an object to be recommended most recently from the learning path of the historical object;
step S506, the curriculum with the largest occurrence frequency in the selected curriculums is used as an alternative curriculum corresponding to the reference object set;
step S507, determining a target course needing to be recommended to an object to be recommended from alternative courses corresponding to each reference object set;
and step S508, recommending the determined target courses to the object to be recommended according to the recommendation coefficients corresponding to each target course from large to small.
Based on the same inventive concept, the embodiment of the present invention further provides a device, and as the principle of the device for recommending online courses is similar to the online course recommending method provided by the embodiment of the present invention, the implementation of the device may refer to the implementation of the method, and repeated details are not described again.
FIG. 6 is a block diagram illustrating an online course recommender, according to an exemplary embodiment. Referring to fig. 6, the apparatus includes a determination module 600, a composition module 601, a selection module 602, and a recommendation module 603.
The determining module 600 determines similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical object participating in online learning;
a composition module 601, configured to compose, according to the similarity between the object to be recommended and each historical object, a plurality of reference object sets from the historical objects whose similarity with the object to be recommended is greater than a set threshold; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
a selecting module 602, configured to select, for any reference object set, a course matching with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set, where the learning path is used to represent a course learning sequence, and use a course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set;
the recommending module 603 determines a target course to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set, and recommends the determined target course to the object to be recommended.
Optionally, the current learning state information of the object to be recommended is first participating in online learning;
the selecting module 602 is specifically configured to:
and aiming at any one history object in the reference object set, taking the firstly learned course in the learning path of the history object as the course matched with the current learning state information of the object to be recommended.
Optionally, the current learning state information of the object to be recommended is that online learning is already participated in;
the selecting module 602 is specifically configured to:
acquiring a course which is learned by the object to be recommended for the last time;
and aiming at any one history object in the reference object set, selecting a course which is learned by the history object after learning the course which is learned by the object to be recommended most recently from the learning path of the history object, and taking the course selected from the learning path as a course matched with the current learning state information of the object to be recommended.
Optionally, the recommending module 603 is specifically configured to:
and taking the alternative courses corresponding to each reference object set as target courses needing to be recommended to the object to be recommended.
Optionally, the recommending module 603 is specifically configured to:
according to the requirement information in the first characteristic information of the object to be recommended, taking an alternative course which is matched with the requirement information of the object to be recommended in the alternative courses corresponding to each reference object set as a target course which needs to be recommended to the object to be recommended; and/or
And according to the capability information of the object to be recommended, taking the candidate courses which are not learned by the object to be recommended in the candidate courses corresponding to each reference object set as target courses to be recommended to the object to be recommended.
Optionally, the recommending module 603 is specifically configured to:
and recommending the determined target courses to the object to be recommended according to the recommendation coefficient corresponding to each target course from large to small.
Optionally, the recommendation coefficient corresponding to the target course is determined according to the following manner:
taking the product of the similarity of the object to be recommended and a historical object in a reference object set corresponding to the target course and a weight value corresponding to the target course as a recommendation coefficient corresponding to the target course;
the weight value is the ratio of the number of times of the target course appearing to the number of the historical objects in the reference object set when the course matched with the current learning state information of the object to be recommended is selected from the learning path of each historical object in the reference object set corresponding to the target course.
FIG. 7 is a block diagram illustrating an online course recommendation system 700, according to an example embodiment, including:
a processor 701;
a memory 702 for storing the processor-executable instructions;
wherein the processor 701 is configured to: when the one or more programs are executed by the one or more processors 701, the one or more processors 701 are caused to perform the following:
determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning;
according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
aiming at any one reference object set, selecting a course matched with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence, and taking the course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set;
and determining target courses needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set, and recommending the determined target courses to the object to be recommended.
Optionally, the current learning state information of the object to be recommended is first participating in online learning;
the processor 701 is configured to:
and aiming at any one history object in the reference object set, taking the firstly learned course in the learning path of the history object as the course matched with the current learning state information of the object to be recommended.
Optionally, the current learning state information of the object to be recommended is that online learning is already participated in;
the processor 701 is configured to:
acquiring a course which is learned by the object to be recommended for the last time;
and aiming at any one history object in the reference object set, selecting a course which is learned by the history object after learning the course which is learned by the object to be recommended most recently from the learning path of the history object, and taking the course selected from the learning path as a course matched with the current learning state information of the object to be recommended.
Optionally, the processor 701 is configured to:
and taking the alternative courses corresponding to each reference object set as target courses needing to be recommended to the object to be recommended.
Optionally, the processor 701 is configured to:
according to the requirement information in the first characteristic information of the object to be recommended, taking an alternative course which is matched with the requirement information of the object to be recommended in the alternative courses corresponding to each reference object set as a target course which needs to be recommended to the object to be recommended; and/or
And according to the capability information of the object to be recommended, taking the candidate courses which are not learned by the object to be recommended in the candidate courses corresponding to each reference object set as target courses to be recommended to the object to be recommended.
Optionally, the processor 701 is configured to:
and recommending the determined target courses to the object to be recommended according to the recommendation coefficient corresponding to each target course from large to small.
Optionally, the processor 701 is configured to determine a recommendation coefficient corresponding to the target course according to the following manner:
taking the product of the similarity of the object to be recommended and a historical object in a reference object set corresponding to the target course and a weight value corresponding to the target course as a recommendation coefficient corresponding to the target course;
the weight value is the ratio of the number of times of the target course appearing to the number of the historical objects in the reference object set when the course matched with the current learning state information of the object to be recommended is selected from the learning path of each historical object in the reference object set corresponding to the target course.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. An online course recommendation method, comprising:
determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning;
according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
aiming at any one reference object set, selecting a course matched with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence, and taking the course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set;
and determining target courses needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set, and recommending the determined target courses to the object to be recommended.
2. The method of claim 1, wherein the current learning state information of the object to be recommended is first participating in online learning;
the selecting a course matching with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence comprises the following steps:
and aiming at any one history object in the reference object set, taking the firstly learned course in the learning path of the history object as the course matched with the current learning state information of the object to be recommended.
3. The method of claim 1, wherein the current learning status information of the object to be recommended is that online learning is already participated in;
the selecting a course matching with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence comprises the following steps:
acquiring a course which is learned by the object to be recommended for the last time;
and aiming at any one history object in the reference object set, selecting a course which is learned by the history object after learning the course which is learned by the object to be recommended most recently from the learning path of the history object, and taking the course selected from the learning path as a course matched with the current learning state information of the object to be recommended.
4. The method according to any one of claims 1 to 3, wherein the determining a target course to be recommended to the object to be recommended from the candidate courses corresponding to each reference object set includes:
and taking the alternative courses corresponding to each reference object set as target courses needing to be recommended to the object to be recommended.
5. The method according to any one of claims 1 to 3, wherein the determining a target course to be recommended to the object to be recommended from the candidate courses corresponding to each reference object set includes:
according to the requirement information in the first characteristic information of the object to be recommended, taking an alternative course which is matched with the requirement information of the object to be recommended in the alternative courses corresponding to each reference object set as a target course which needs to be recommended to the object to be recommended; and/or
And according to the capability information of the object to be recommended, taking the candidate courses which are not learned by the object to be recommended in the candidate courses corresponding to each reference object set as target courses to be recommended to the object to be recommended.
6. The method as claimed in claim 5, wherein the recommending the determined target course to the object to be recommended comprises:
and recommending the determined target courses to the object to be recommended according to the recommendation coefficient corresponding to each target course from large to small.
7. The method as claimed in claim 6, wherein the recommendation coefficient corresponding to the target course is determined according to the following manner:
taking the product of the similarity of the object to be recommended and a historical object in a reference object set corresponding to the target course and a weight value corresponding to the target course as a recommendation coefficient corresponding to the target course;
the weight value is the ratio of the number of times of the target course appearing to the number of the historical objects in the reference object set when the course matched with the current learning state information of the object to be recommended is selected from the learning path of each historical object in the reference object set corresponding to the target course.
8. An online course recommendation apparatus, comprising:
the determining module is used for determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical object participating in online learning;
the composition module is used for composing the historical objects with the similarity greater than a set threshold value with the object to be recommended into a plurality of reference object sets according to the similarity between the object to be recommended and each historical object; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
the selection module is used for selecting a course matched with the current learning state information of the object to be recommended from the learning path of each historical object in the reference object set, which is used for expressing the course learning sequence, aiming at any one reference object set, and taking the course with the largest occurrence frequency in the selected courses as the alternative course corresponding to the reference object set;
and the recommending module is used for determining a target course needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set and recommending the determined target course to the object to be recommended.
9. An online course recommendation system, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to: when executed by the one or more processors, cause the one or more processors to perform the following:
determining the similarity between the object to be recommended and each historical object according to the first characteristic information of the object to be recommended and the second characteristic information of the historical objects participating in online learning;
according to the similarity between the object to be recommended and each historical object, forming a plurality of reference object sets by the historical objects with the similarity larger than a set threshold value; the similarity between the historical object in the same reference object set and the object to be recommended is the same;
aiming at any one reference object set, selecting a course matched with the current learning state information of the object to be recommended from the learning path of each history object in the reference object set for representing the course learning sequence, and taking the course with the largest occurrence frequency in the selected courses as an alternative course corresponding to the reference object set;
and determining target courses needing to be recommended to the object to be recommended from the alternative courses corresponding to each reference object set, and recommending the determined target courses to the object to be recommended.
10. A computer-readable storage medium having stored thereon computer instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911115500.9A CN110990691A (en) | 2019-11-14 | 2019-11-14 | Online course recommendation method and device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911115500.9A CN110990691A (en) | 2019-11-14 | 2019-11-14 | Online course recommendation method and device and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110990691A true CN110990691A (en) | 2020-04-10 |
Family
ID=70084590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911115500.9A Pending CN110990691A (en) | 2019-11-14 | 2019-11-14 | Online course recommendation method and device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110990691A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111581529A (en) * | 2020-05-07 | 2020-08-25 | 之江实验室 | Course recommendation method and device combining student fitness and course collocation degree |
| CN111966902A (en) * | 2020-08-18 | 2020-11-20 | 联想(北京)有限公司 | Recommendation control method for class learning and electronic equipment |
| CN112541845A (en) * | 2020-12-15 | 2021-03-23 | 泰康保险集团股份有限公司 | Online training method and device, electronic equipment and storage medium |
| CN113743645A (en) * | 2021-07-16 | 2021-12-03 | 广东财经大学 | Online education course recommendation method based on path factor fusion |
| CN113918812A (en) * | 2021-10-11 | 2022-01-11 | 北京量子之歌科技有限公司 | Course learning path determination method, device, equipment and storage medium |
| CN114418807A (en) * | 2022-03-30 | 2022-04-29 | 北京英华在线科技有限公司 | Course recommendation method and system of online education platform based on historical scores |
| CN114510617A (en) * | 2022-01-27 | 2022-05-17 | 哈尔滨工业大学 | Online course learning behavior determination method and device |
| CN114936953A (en) * | 2022-05-20 | 2022-08-23 | 海信集团控股股份有限公司 | Member determination method for learning discussion room and electronic equipment |
| CN115511677A (en) * | 2022-10-18 | 2022-12-23 | 天津景润网络科技有限公司 | Intelligent education resource platform allocation method and system |
| WO2023279677A1 (en) * | 2021-07-06 | 2023-01-12 | 上海商汤智能科技有限公司 | Curriculum customization method, device, apparatus, storage medium and program |
| CN116228483A (en) * | 2023-05-06 | 2023-06-06 | 中诚华隆计算机技术有限公司 | Learning path recommendation method and device based on quantum drive |
| CN116521936A (en) * | 2023-06-30 | 2023-08-01 | 云南师范大学 | Course recommendation method and device based on user behavior analysis and storage medium |
| CN117112116A (en) * | 2023-10-16 | 2023-11-24 | 成都市蓉通数智信息技术有限公司 | User management system based on digital government affairs |
| CN117273259A (en) * | 2023-06-06 | 2023-12-22 | 郭润奇 | Online course learning path recommendation method and device |
| CN117830046A (en) * | 2024-03-06 | 2024-04-05 | 长春电子科技学院 | Online course data cloud management system based on Internet |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528656A (en) * | 2016-10-20 | 2017-03-22 | 杨瀛 | Student history and real-time learning state parameter-based course recommendation realization method and system |
| CN109858806A (en) * | 2019-01-30 | 2019-06-07 | 网易（杭州）网络有限公司 | Method, apparatus, medium and the electronic equipment of data processing |
| CN109934748A (en) * | 2019-03-25 | 2019-06-25 | 京工博创（北京）科技有限公司 | A kind of personalized course method for customizing based under the conditions of big data |
| CN110222254A (en) * | 2019-04-26 | 2019-09-10 | 平安科技（深圳）有限公司 | Course recommended method, device, equipment and computer readable storage medium |
-
2019
- 2019-11-14 CN CN201911115500.9A patent/CN110990691A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528656A (en) * | 2016-10-20 | 2017-03-22 | 杨瀛 | Student history and real-time learning state parameter-based course recommendation realization method and system |
| CN109858806A (en) * | 2019-01-30 | 2019-06-07 | 网易（杭州）网络有限公司 | Method, apparatus, medium and the electronic equipment of data processing |
| CN109934748A (en) * | 2019-03-25 | 2019-06-25 | 京工博创（北京）科技有限公司 | A kind of personalized course method for customizing based under the conditions of big data |
| CN110222254A (en) * | 2019-04-26 | 2019-09-10 | 平安科技（深圳）有限公司 | Course recommended method, device, equipment and computer readable storage medium |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111581529A (en) * | 2020-05-07 | 2020-08-25 | 之江实验室 | Course recommendation method and device combining student fitness and course collocation degree |
| CN111581529B (en) * | 2020-05-07 | 2023-07-14 | 之江实验室 | Course recommendation method and device combining student fitness and course collocation degree |
| CN111966902A (en) * | 2020-08-18 | 2020-11-20 | 联想(北京)有限公司 | Recommendation control method for class learning and electronic equipment |
| CN112541845A (en) * | 2020-12-15 | 2021-03-23 | 泰康保险集团股份有限公司 | Online training method and device, electronic equipment and storage medium |
| CN112541845B (en) * | 2020-12-15 | 2023-12-01 | 泰康保险集团股份有限公司 | Online training method and device, electronic equipment and storage medium |
| WO2023279677A1 (en) * | 2021-07-06 | 2023-01-12 | 上海商汤智能科技有限公司 | Curriculum customization method, device, apparatus, storage medium and program |
| CN113743645A (en) * | 2021-07-16 | 2021-12-03 | 广东财经大学 | Online education course recommendation method based on path factor fusion |
| CN113743645B (en) * | 2021-07-16 | 2024-02-02 | 广东财经大学 | Online education course recommendation method based on path factor fusion |
| CN113918812A (en) * | 2021-10-11 | 2022-01-11 | 北京量子之歌科技有限公司 | Course learning path determination method, device, equipment and storage medium |
| CN114510617A (en) * | 2022-01-27 | 2022-05-17 | 哈尔滨工业大学 | Online course learning behavior determination method and device |
| CN114418807A (en) * | 2022-03-30 | 2022-04-29 | 北京英华在线科技有限公司 | Course recommendation method and system of online education platform based on historical scores |
| CN114418807B (en) * | 2022-03-30 | 2022-06-28 | 北京英华在线科技有限公司 | Course recommendation method and system of online education platform based on historical score |
| CN114936953A (en) * | 2022-05-20 | 2022-08-23 | 海信集团控股股份有限公司 | Member determination method for learning discussion room and electronic equipment |
| CN115511677A (en) * | 2022-10-18 | 2022-12-23 | 天津景润网络科技有限公司 | Intelligent education resource platform allocation method and system |
| CN116228483A (en) * | 2023-05-06 | 2023-06-06 | 中诚华隆计算机技术有限公司 | Learning path recommendation method and device based on quantum drive |
| CN117273259A (en) * | 2023-06-06 | 2023-12-22 | 郭润奇 | Online course learning path recommendation method and device |
| CN117273259B (en) * | 2023-06-06 | 2024-05-31 | 郭润奇 | Online course learning path recommendation method and device |
| CN116521936A (en) * | 2023-06-30 | 2023-08-01 | 云南师范大学 | Course recommendation method and device based on user behavior analysis and storage medium |
| CN116521936B (en) * | 2023-06-30 | 2023-09-01 | 云南师范大学 | Course recommendation method and device based on user behavior analysis and storage medium |
| CN117112116A (en) * | 2023-10-16 | 2023-11-24 | 成都市蓉通数智信息技术有限公司 | User management system based on digital government affairs |
| CN117112116B (en) * | 2023-10-16 | 2024-02-02 | 成都市蓉通数智信息技术有限公司 | User management system based on digital government affairs |
| CN117830046A (en) * | 2024-03-06 | 2024-04-05 | 长春电子科技学院 | Online course data cloud management system based on Internet |
| CN117830046B (en) * | 2024-03-06 | 2024-05-07 | 长春电子科技学院 | Online course data cloud management system based on Internet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110990691A (en) | Online course recommendation method and device and computer storage medium | |
| CN107451199B (en) | Question recommendation method, device and equipment | |
| US11417232B2 (en) | Method, apparatus, and computer program for operating machine-learning framework | |
| CN106557576B (en) | Prompt message recommendation method and device based on artificial intelligence | |
| US8463174B2 (en) | System and methods for sequencing learning objects based upon query and user relevancy | |
| KR20200135892A (en) | Method, apparatus and computer program for providing personalized educational curriculum and contents through user learning ability | |
| US10984794B1 (en) | Information processing system, information processing apparatus, information processing method, and recording medium | |
| CN111858906B (en) | Problem recommendation method and device, electronic equipment and computer readable storage medium | |
| CN111353037A (en) | Topic generation method and device and computer readable storage medium | |
| CN114116998A (en) | Reply sentence generation method and device, computer equipment and storage medium | |
| CN111475628A (en) | Session data processing method, device, computer equipment and storage medium | |
| KR101745874B1 (en) | System and method for a learning course automatic generation | |
| JP2014115427A (en) | Extraction method, extraction device and extraction program | |
| US11138895B2 (en) | System and method for facilitating creation of an educational test based on prior performance with individual test questions | |
| CN117312628A (en) | Method and device for recommending exercise course, storage medium and electronic equipment | |
| CN109684436B (en) | Knowledge correlation method and application | |
| Wu et al. | Instructing large language models to identify and ignore irrelevant conditions | |
| Haddaji et al. | Toward the selection of the appropriate e-learning personalization strategy | |
| CN113763767A (en) | Learning test question pushing method and device, computer equipment and storage medium | |
| JP2017207691A (en) | Correct answer ratio prediction method of multiple-choice question | |
| CN110929163A (en) | Course recommendation method and device, computer equipment and storage medium | |
| CN112328894A (en) | Behavior guiding method and device, computer equipment and storage medium | |
| CN113158020A (en) | Video recommendation method and device | |
| CN110851478A (en) | Menu creation method and device | |
| CN111858863A (en) | Reply recommendation method, reply recommendation device and electronic equipment |
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 |