CN109800300A - learning content recommendation method and system - Google Patents
learning content recommendation method and system Download PDFInfo
- Publication number
- CN109800300A CN109800300A CN201910014982.2A CN201910014982A CN109800300A CN 109800300 A CN109800300 A CN 109800300A CN 201910014982 A CN201910014982 A CN 201910014982A CN 109800300 A CN109800300 A CN 109800300A
- Authority
- CN
- China
- Prior art keywords
- user
- learning
- information
- knowledge
- personal
- 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 35
- 239000000284 extract Substances 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000001228 spectrum Methods 0.000 description 8
- 238000013507 mapping Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the field of education products, and discloses a learning content recommendation method and a learning content recommendation system, wherein the method comprises the following steps: generating a standard knowledge graph according to the learning record information of a large number of users; acquiring personal information of a user and a learning and browsing record of the user; creating a personal knowledge graph of the user according to the personal information of the user, the learning browsing record of the user and the standard knowledge graph; and recommending the learning content to the user according to the personal knowledge graph and the standard knowledge graph of the user. According to the method, a standard knowledge graph is generated according to the acquired learning record information of a large number of users, then a personal knowledge graph of the users is generated according to the learning browsing record of the users and the standard knowledge graph, finally, knowledge points which are not mastered by the users are obtained according to the personal knowledge graph and the standard knowledge graph of the users, learning contents related to the knowledge points which are not mastered are recommended to the users, and therefore the purposes of accurately acquiring the learning requirements of the users and recommending the related learning contents to the users are achieved.
Description
Technical field
The invention belongs to education product technical field, in particular to a kind of learning Content recommended method and system.
Background technique
With the rapid development of intelligent terminal and network technology, the mode of mobile learning is carried out using intelligent mobile terminal
It is gradually valued by the people, and mobile learning is important by the one kind for becoming modern society as a kind of new mode of learning
Habit mode and means.
Currently, different types of user carries out mobile learning for convenience, a large amount of differences have been included in intelligence learning equipment
The learning Content of type；And the growth of the type and quantity with learning Content, user requires a great deal of time and energy
Oneself learning Content interested and required is searched in the learning Content of magnanimity, the efficiency that causes learning Content to be searched and accurate
Spend it is lower, to affect the usage experience of user.
Summary of the invention
The object of the present invention is to provide a kind of learning Content recommended method and system, realizes and quickly and efficiently recommend to user
The purpose of learning Content.
Technical solution provided by the invention is as follows:
On the one hand, a kind of learning Content recommended method is provided, comprising:
Standard knowledge map is generated according to the learning records information of a large number of users；
The study of the personal information and user that obtain user browses record；
Record and the standard knowledge map, creation are browsed according to the study of the personal information of the user, the user
The personal knowledge map of the user；
According to the personal knowledge map of the user and the standard knowledge map, Xiang Suoshu user recommends learning Content.
It is further preferred that described specifically wrap according to the learning records information of a large number of users generation standard knowledge map
It includes:
Obtain the learning records information and corresponding user information of a large number of users；
Classified according to the user information to the learning records information；
Mark the incidence relation between the learning records information and user type；
Mark the knowledge point of every learning records in the learning records information；
Mark the incidence relation between the knowledge point；
According to the relationship relationship between the learning records information and user type, the incidence relation between the knowledge point
Generate standard knowledge map.
It is further preferred that the knowledge point of every learning records specifically includes in the label learning records information:
Obtain the corresponding instructional video of every learning records；
Extract the text information of the slide instruction in the instructional video；
The knowledge point of every learning records is marked according to the text information.
It is further preferred that the personal information according to the user, the study browsing record of the user and described
Standard knowledge map, the personal knowledge map for creating the user specifically include:
According to the personal information of the user, the user type of the user is obtained；
User type relevant to the user type of the user is searched in the standard knowledge map；
The user is determined according to the incidence relation between the corresponding knowledge point node of the relevant user type
Practise the incidence relation between the knowledge point in browsing record；
The personal knowledge figure of the user is created according to the incidence relation between the knowledge point in the study browsing record
Spectrum.
It is further preferred that described according to the personal knowledge map and the standard knowledge map, Xiang Suoshu user is pushed away
Learning Content is recommended to specifically include:
The knowledge point that the user has grasped is determined according to the personal knowledge map；
It is searched and the adjacent knowledge point in knowledge point grasped in the standard knowledge map；
Recommend the corresponding learning Content in the adjacent knowledge point to user.
On the other hand, a kind of learning Content recommender system is also provided, comprising:
Standard knowledge map generation module, for generating standard knowledge map according to the learning records information of a large number of users；
User profile acquisition module, for obtaining the personal information of user and the study browsing record of user；
Personal knowledge map creation module, for browsing note according to the personal information of the user, the study of the user
Record and the standard knowledge map, create the personal knowledge map of the user；
Learning Content recommending module, for the personal knowledge map and the standard knowledge map according to the user, to
The user recommends learning Content.
It is further preferred that the standard knowledge map generation module includes:
Information acquisition unit, for obtaining the learning records information and corresponding user information of a large number of users；
Taxon, for being classified according to the user information to the learning records information；
Marking unit, for marking the incidence relation between the learning records information and user type；Mark
Practise the knowledge point of every learning records in record information；Mark the incidence relation between the knowledge point；
Standard knowledge map generation unit, for being closed according to the relationship between the learning records information and user type
Incidence relation between system, the knowledge point generates standard knowledge map.
It is further preferred that the marking unit includes:
Instructional video obtains subelement, for obtaining the corresponding instructional video of every learning records；
Text information extracts subelement, for extracting the text information of the slide instruction in the instructional video；
Subelement is marked, for marking the knowledge point of every learning records according to the text information.
It is further preferred that the personal knowledge map creation module includes:
User type acquiring unit obtains the user type of the user for the personal information according to the user；
Searching unit, for searching user class relevant to the user type of the user in the standard knowledge map
Type；
Incidence relation determination unit, for according to the association between the corresponding knowledge point node of the relevant user type
Relationship determines the incidence relation between the knowledge point in the study browsing record of the user；
Personal knowledge map creating unit, for according to the incidence relation between the knowledge point in the study browsing record
Create the personal knowledge map of the user.
It is further preferred that the learning Content recommending module includes:
Knowledge point determination unit, for determining knowledge point that the user has grasped according to the personal knowledge map；
Knowledge point searching unit, it is adjacent with the knowledge point grasped for being searched in the standard knowledge map
Knowledge point；
Learning Content recommendation unit, for recommending the corresponding learning Content in the adjacent knowledge point to user.
Compared with prior art, a kind of learning Content recommended method and system provided by the invention have below beneficial to effect
Fruit:
1, the present invention first generates standard knowledge map according to the learning records information of the mass users got, then basis
The study browsing record and standard knowledge map of user generate the personal knowledge map of user, finally according to the personal knowledge of user
Map and standard knowledge map obtain the knowledge point that user does not grasp, and relevant to the knowledge point that do not grasp to user's recommendation
Learning Content, to realize the accurate learning demand for obtaining user and recommend the purpose of relational learning content to user.
2, in a preferred embodiment, by being divided the learning records information class of user type of mass users
Class, so that the knowledge point in the standard knowledge map generated is also classified according to user type, as the individual for getting user
After the study browsing record of information and user, relevant user can be searched in standard knowledge map according to the personal information of user
Then type determines the study browsing note of user according to the incidence relation between the corresponding knowledge point node of relevant user type
The incidence relation between knowledge point in record simplifies the process for obtaining the incidence relation between knowledge point, to be quickly generated
The personal knowledge map of user improves treatment effeciency.
3, in a preferred embodiment, by recommending the adjacent knowledge in knowledge point grasped with user to user
Point family can be used regularly to be learnt, avoid user from desultorily learning, know so that user be made to better grasp
Know point.
Detailed description of the invention
Below by clearly understandable mode, preferred embodiment is described with reference to the drawings, to a kind of learning Content recommendation side
Above-mentioned characteristic, technical characteristic, advantage and its implementation of method and system are further described.
Fig. 1 is a kind of flow diagram of the first embodiment of learning Content recommended method of the present invention；
Fig. 2 is a kind of flow diagram of the second embodiment of learning Content recommended method of the present invention；
Fig. 3 is a kind of schematic diagram of the standard knowledge map of learning Content recommended method of the present invention；
Fig. 4 is a kind of flow diagram of the 3rd embodiment of learning Content recommended method of the present invention；
Fig. 5 is a kind of flow diagram of the fourth embodiment of learning Content recommended method of the present invention；
Fig. 6 is a kind of flow diagram of 5th embodiment of learning Content recommended method of the present invention；
Fig. 7 is a kind of flow diagram of the sixth embodiment of learning Content recommended method of the present invention；
Fig. 8 is a kind of flow diagram of 7th embodiment of learning Content recommended method of the present invention；
Fig. 9 is a kind of structural schematic block diagram of the embodiment of learning Content recommender system of the present invention.
Drawing reference numeral explanation
100, standard knowledge map generation module；110, information acquisition unit；
120, taxon；130, marking unit；
131, instructional video obtains subelement；132, text information extracts subelement；
133, subelement is marked；140, standard knowledge map generation unit；
200, User profile acquisition module；300, personal knowledge map creation module；
310, user type acquiring unit；320, searching unit；
330, incidence relation determination unit；340, personal knowledge map creating unit；
400, learning Content recommending module；410, knowledge point determination unit；
420, knowledge point searching unit；430, learning Content recommendation unit.
Specific embodiment
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, Detailed description of the invention will be compareed below
A specific embodiment of the invention.It should be evident that drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing, and obtain other embodiments.
To make simplified form, part related to the present invention is only schematically shown in each figure, they are not represented
Its practical structures as product.In addition, there is identical structure or function in some figures so that simplified form is easy to understand
Component only symbolically depicts one of those, or has only marked one of those.Herein, "one" is not only indicated
" only this ", can also indicate the situation of " more than one ".
The first embodiment provided according to the present invention, as shown in Figure 1, a kind of learning Content recommended method, comprising:
S100 generates standard knowledge map according to the learning records information of a large number of users；
S200 obtains the personal information of user and the study of user browses record；
S300 browses record and the standard knowledge map according to the personal information of the user, the study of the user,
Create the personal knowledge map of the user；
S400 recommends in study according to the personal knowledge map and the standard knowledge map of the user, Xiang Suoshu user
Hold.
Specifically, intelligence learning equipment such as private tutor's machine collects the study note that mass users generate in intelligence learning equipment
It records information and forms large database concept, standard knowledge map is then generated according to the magnanimity learning records information being collected into.Standard knowledge
Include several nodes in map, one knowledge point of each node on behalf, in standard knowledge map also comprising each knowledge point it
Between incidence relation, such as upper and lower level grade relationship (comprising with by inclusion relation), coordination.
When intelligence learning equipment gets the personal information of active user (using the user of the intelligence learning equipment) and works as
When the study of preceding user browses record, after getting the knowledge point for including in study browsing record, according in standard knowledge map
Knowledge point between incidence relation, determine user generate study browsing record in knowledge point between incidence relation, so
Afterwards according to the personal knowledge map of the incidence relation creation user between the knowledge point in study browsing record.
After obtaining standard knowledge map and the personal knowledge map of user, known according to the personal knowledge map and standard of user
Know map and obtain the user knowledge point grasped and the knowledge point that do not grasp, right rear line recommends the knowledge that do not grasp with user
The relevant learning Content of point.
The present invention first generates standard knowledge map according to the learning records information of mass users got, then according to
The study browsing record and standard knowledge map at family generate the personal knowledge map of user, finally according to the personal knowledge figure of user
Spectrum and standard knowledge map obtain the knowledge point that user does not grasp, and recommend relevant to the knowledge point that do not grasp to user
Content is practised, to realize the accurate learning demand for obtaining user and recommend the purpose of relational learning content to user.
The second embodiment provided according to the present invention, as shown in Fig. 2, a kind of learning Content recommended method, comprising:
The learning records information and corresponding user information of S110 acquisition a large number of users；
S120 classifies to the learning records information according to the user information；
S130 marks the incidence relation between the learning records information and user type；
S140 marks the knowledge point of every learning records in the learning records information；
S150 marks the incidence relation between the knowledge point；
S160 is according to the relationship relationship between the learning records information and user type, being associated between the knowledge point
Relationship generates standard knowledge map；
S200 obtains the personal information of user and the study of user browses record；
S300 browses record and the standard knowledge map according to the personal information of the user, the study of the user,
Create the personal knowledge map of the user；
S400 recommends in study according to the personal knowledge map and the standard knowledge map of the user, Xiang Suoshu user
Hold.
Specifically, intelligence learning equipment such as private tutor's machine collects the study note that mass users generate in intelligence learning equipment
Information and corresponding user information are recorded to form large database concept, is then classified according to user information to learning records information,
I.e. class of user type classifies to learning records information, and being associated between learning records information and user type is marked after classification
Then relationship marks the incidence relation between the knowledge point and knowledge point of every learning records in learning records information, most
Standard knowledge figure is generated according to the incidence relation between learning records information and user type, the incidence relation between knowledge point afterwards
Spectrum.
Illustratively, the study including student in the learning records information and corresponding user information of ground mass users is collected
Record information, the learning records information of the professionals of various industries, learning records information of full-time mother etc..By the sea of collection
Amount learning records information is classified according to the user information of user, i.e., learning records information class of user type is classified,
The learning records information that student generates is divided into the learning records information that a kind of, various industries professionals generate to be respectively divided into
The learning records information that a kind of, full-time mother generates is divided into one kind.Pupil can also be divided into a kind of, junior middle school is estranged in student
It is divided into a kind of, university student for a kind of, high school student and is divided into one kind.
After learning records information is classified according to user type, student's class is generated according to the learning records information of all students
Knowledge mapping under not generates the knowledge graph under corresponding classification according to the learning records information of the professionals of various industries respectively
Spectrum generates the knowledge mapping under corresponding classification according to the learning records information of full-time mother, then by the knowledge under each classification
Map form one completely include various class of subscribers standard knowledge map, the standard knowledge map of generation as shown in figure 3,
The first nodes of standard knowledge map are various class of subscribers respectively, and the knowledge of multiple ranks is separately included under each class of subscriber
Point node.
The 3rd embodiment provided according to the present invention, as shown in figure 4, a kind of learning Content recommended method, comprising:
The learning records information and corresponding user information of S110 acquisition a large number of users；
S120 classifies to the learning records information according to the user information；
S130 marks the incidence relation between the learning records information and user type；
S141 obtains the corresponding instructional video of every learning records；
S142 extracts the text information of the slide instruction in the instructional video；
S143 marks the knowledge point of every learning records according to the text information；
S150 marks the incidence relation between the knowledge point；
S160 is according to the relationship relationship between the learning records information and user type, being associated between the knowledge point
Relationship generates standard knowledge map；
S200 obtains the personal information of user and the study of user browses record；
S300 browses record and the standard knowledge map according to the personal information of the user, the study of the user,
Create the personal knowledge map of the user；
S400 recommends in study according to the personal knowledge map and the standard knowledge map of the user, Xiang Suoshu user
Hold.
Specifically, the education resource in intelligence learning equipment is typically all video, and is known in each video comprising multiple
Know point.It include a plurality of learning records, the corresponding one or more religions of every learning records in the learning records information of the user of acquisition
Video is learned to need first to obtain every learning records pair to mark the knowledge point of every learning records in learning records information
The instructional video answered, then extracts the text information of the slide instruction in instructional video, and slide instruction can pass through screenshotss
It obtains, the text information in screenshot picture (slide instruction) is then identified by picture recognition technology, teaching can be obtained
The text information of all lantern slides in video.
After obtaining the text information of the slide instruction in instructional video, taught according to the text information of slide instruction
Knowledge point involved in video is learned, then the knowledge point according to involved in instructional video marks the knowledge point of every learning records.
The fourth embodiment provided according to the present invention, as shown in figure 5, a kind of learning Content recommended method, comprising:
The learning records information and corresponding user information of S110 acquisition a large number of users；
S120 classifies to the learning records information according to the user information；
S130 marks the incidence relation between the learning records information and user type；
S140 marks the knowledge point of every learning records in the learning records information；
S150 marks the incidence relation between the knowledge point；
S160 is according to the relationship relationship between the learning records information and user type, being associated between the knowledge point
Relationship generates standard knowledge map；
S200 obtains the personal information of user and the study of user browses record；
S310 obtains the user type of the user according to the personal information of the user；
S320 searches user type relevant to the user type of the user in the standard knowledge map；
S330 determines the user according to the incidence relation between the corresponding knowledge point node of the relevant user type
Study browsing record in knowledge point between incidence relation；
S340 knows according to the individual that the incidence relation between the knowledge point in the study browsing record creates the user
Know map；
S400 recommends in study according to the personal knowledge map and the standard knowledge map of the user, Xiang Suoshu user
Hold.
Specifically, the knowledge point node in standard knowledge map is classified according to class of subscriber, when getting user's
After personal information, the user type of user is first obtained according to the personal information of user, the personal information of user can be in user's registration
It is obtained when account, the personal information of user may include the age of user, gender, occupation, work position etc., according to the individual of user
The user type that information obtains can be one or more.
After obtaining the user type of user, user class relevant to the user type of user is searched in standard knowledge map
Type searches user type relevant to multiple user type when user type is multiple respectively in standard knowledge map；
Relevant user type refers to and identical user type or similar user type.
After finding relevant user type in standard knowledge map, corresponded under classification according to relevant user type
Incidence relation between the node of knowledge point determines the incidence relation between the knowledge point in the study browsing record of user.
After obtaining the incidence relation between the knowledge point in study browsing record user can be created according to the incidence relation
Personal knowledge map.
In the present embodiment, by the way that the learning records information class of user type of mass users is classified, so that generating
Standard knowledge map in knowledge point also classify according to user type, when the personal information and user for getting user
After study browsing record, relevant user type can be searched in standard knowledge map according to the personal information of user, then root
The knowledge in the study browsing record of user is determined according to the incidence relation between the corresponding knowledge point node of relevant user type
Incidence relation between point simplifies the process for obtaining the incidence relation between knowledge point, to be quickly generated the individual of user
Knowledge mapping improves treatment effeciency.
The 5th embodiment provided according to the present invention, as shown in fig. 6, a kind of learning Content recommended method, comprising:
S100 generates standard knowledge map according to the learning records information of a large number of users；
S200 obtains the personal information of user and the study of user browses record；
S300 browses record and the standard knowledge map according to the personal information of the user, the study of the user,
Create the personal knowledge map of the user；
S410 determines the knowledge point that the user has grasped according to the personal knowledge map；
S420 is searched and the adjacent knowledge point in knowledge point grasped in the standard knowledge map；
S430 recommends the corresponding learning Content in the adjacent knowledge point to user.
Specifically, after creation standard knowledge map and the personal knowledge map of user, first according in personal knowledge map
Knowledge point node determine the knowledge point that user has grasped, the knowledge point then grasped according to user is in standard knowledge map
The adjacent knowledge point node of knowledge point node searched and grasped, adjacent knowledge point node refer to the higher level of knowledge point node
Knowledge point node, junior's knowledge point node or knowledge point node arranged side by side (the knowledge point node of same level).It gets adjacent
After the node of knowledge point, then learning Content relevant to adjacent knowledge point node is obtained, such as study video, then recommends use
Family.
In the present embodiment, by recommending the adjacent knowledge point in knowledge point grasped with user to user, family can be used
Regularly learnt, user is avoided desultorily to learn, so that user be made to better grasp knowledge point.
The sixth embodiment provided according to the present invention, as shown in fig. 7, a kind of learning Content recommended method, comprising:
The learning records information and corresponding user information of S110 acquisition a large number of users；
S120 classifies to the learning records information according to the user information；
S130 marks the incidence relation between the learning records information and user type；
S140 marks the knowledge point of every learning records in the learning records information；
S150 marks the incidence relation between the knowledge point；
S160 is according to the relationship relationship between the learning records information and user type, being associated between the knowledge point
Relationship generates standard knowledge map；
S200 obtains the personal information of user and the study of user browses record；
S300 browses record and the standard knowledge map according to the personal information of the user, the study of the user,
Create the personal knowledge map of the user；
S410 determines the knowledge point that the user has grasped according to the personal knowledge map；
S420 is searched and the adjacent knowledge point in knowledge point grasped in the standard knowledge map；
S430 recommends the corresponding learning Content in the adjacent knowledge point to user.
The specific descriptions of each step in the present embodiment are described in detail in above-mentioned corresponding embodiment,
No detailed explanation will be given here.
The 7th embodiment provided according to the present invention, as shown in figure 8, a kind of learning Content recommended method, comprising:
The learning records information and corresponding user information of S110 acquisition a large number of users；
S120 classifies to the learning records information according to the user information；
S130 marks the incidence relation between the learning records information and user type；
S141 obtains the corresponding instructional video of every learning records；
S142 extracts the text information of the slide instruction in the instructional video；
S143 marks the knowledge point of every learning records according to the text information；
S150 marks the incidence relation between the knowledge point；
S160 is according to the relationship relationship between the learning records information and user type, being associated between the knowledge point
Relationship generates standard knowledge map；
S200 obtains the personal information of user and the study of user browses record；
S300 browses record and the standard knowledge map according to the personal information of the user, the study of the user,
Create the personal knowledge map of the user；
S410 determines the knowledge point that the user has grasped according to the personal knowledge map；
S420 is searched and the adjacent knowledge point in knowledge point grasped in the standard knowledge map；
S430 recommends the corresponding learning Content in the adjacent knowledge point to user.
The specific descriptions of each step in the present embodiment are described in detail in above-mentioned corresponding embodiment,
No detailed explanation will be given here.
The 8th embodiment provided according to the present invention, a kind of learning Content recommended method, comprising:
The learning records information and corresponding user information of S110 acquisition a large number of users；
S120 classifies to the learning records information according to the user information；
S130 marks the incidence relation between the learning records information and user type；
S140 marks the knowledge point of every learning records in the learning records information；
S150 marks the incidence relation between the knowledge point；
S160 is according to the relationship relationship between the learning records information and user type, being associated between the knowledge point
Relationship generates standard knowledge map；
S200 obtains the personal information of user and the study of user browses record；
S310 obtains the user type of the user according to the personal information of the user；
S320 searches user type relevant to the user type of the user in the standard knowledge map；
S330 determines the user according to the incidence relation between the corresponding knowledge point node of the relevant user type
Study browsing record in knowledge point between incidence relation；
S340 knows according to the individual that the incidence relation between the knowledge point in the study browsing record creates the user
Know map；
S410 determines the knowledge point that the user has grasped according to the personal knowledge map；
S420 is searched and the adjacent knowledge point in knowledge point grasped in the standard knowledge map；
S430 recommends the corresponding learning Content in the adjacent knowledge point to user.
The specific descriptions of each step in the present embodiment are described in detail in above-mentioned corresponding embodiment,
No detailed explanation will be given here.
The 9th embodiment provided according to the present invention, as shown in figure 9, a kind of learning Content recommender system, comprising:
Standard knowledge map generation module 100, for generating standard knowledge figure according to the learning records information of a large number of users
Spectrum；
User profile acquisition module 200, for obtaining the personal information of user and the study browsing record of user；
Personal knowledge map creation module 300, for being browsed according to the personal information of the user, the study of the user
Record and the standard knowledge map, create the personal knowledge map of the user；
Learning Content recommending module 400, for the personal knowledge map and the standard knowledge map according to the user,
Recommend learning Content to the user.
Specifically, intelligence learning equipment such as private tutor's machine collects the study note that mass users generate in intelligence learning equipment
It records information and forms large database concept, standard knowledge map is then generated according to the magnanimity learning records information being collected into.Standard knowledge
Include several nodes in map, one knowledge point of each node on behalf, in standard knowledge map also comprising each knowledge point it
Between incidence relation, such as upper and lower level grade relationship (comprising with by inclusion relation), coordination.
When intelligence learning equipment gets the personal information of active user (using the user of the intelligence learning equipment) and works as
When the study of preceding user browses record, after getting the knowledge point for including in study browsing record, according in standard knowledge map
Knowledge point between incidence relation, determine user generate study browsing record in knowledge point between incidence relation, so
Afterwards according to the personal knowledge map of the incidence relation creation user between the knowledge point in study browsing record.
After obtaining standard knowledge map and the personal knowledge map of user, known according to the personal knowledge map and standard of user
Know map and obtain the user knowledge point grasped and the knowledge point that do not grasp, right rear line recommends the knowledge that do not grasp with user
The relevant learning Content of point.
The present invention first generates standard knowledge map according to the learning records information of mass users got, then according to
The study browsing record and standard knowledge map at family generate the personal knowledge map of user, finally according to the personal knowledge figure of user
Spectrum and standard knowledge map obtain the knowledge point that user does not grasp, and recommend relevant to the knowledge point that do not grasp to user
Content is practised, to realize the accurate learning demand for obtaining user and recommend the purpose of relational learning content to user.
Preferably, the standard knowledge map generation module 100 includes:
Information acquisition unit 110, for obtaining the learning records information and corresponding user information of a large number of users；
Taxon 120, for being classified according to the user information to the learning records information；
Marking unit 130, for marking the incidence relation between the learning records information and user type；Described in label
The knowledge point of every learning records in learning records information；Mark the incidence relation between the knowledge point；
Standard knowledge map generation unit 140, for according to the relationship between the learning records information and user type
Incidence relation between relationship, the knowledge point generates standard knowledge map.
Specifically, intelligence learning equipment such as private tutor's machine collects the study note that mass users generate in intelligence learning equipment
Information and corresponding user information are recorded to form large database concept, is then classified according to user information to learning records information,
I.e. class of user type classifies to learning records information, and being associated between learning records information and user type is marked after classification
Then relationship marks the incidence relation between the knowledge point and knowledge point of every learning records in learning records information, most
Standard knowledge figure is generated according to the incidence relation between learning records information and user type, the incidence relation between knowledge point afterwards
Spectrum.
Illustratively, the study including student in the learning records information and corresponding user information of ground mass users is collected
Record information, the learning records information of the professionals of various industries, learning records information of full-time mother etc..By the sea of collection
Amount learning records information is classified according to the user information of user, i.e., learning records information class of user type is classified,
The learning records information that student generates is divided into the learning records information that a kind of, various industries professionals generate to be respectively divided into
The learning records information that a kind of, full-time mother generates is divided into one kind.Pupil can also be divided into a kind of, junior middle school is estranged in student
It is divided into a kind of, university student for a kind of, high school student and is divided into one kind.
After learning records information is classified according to user type, student's class is generated according to the learning records information of all students
Knowledge mapping under not generates the knowledge graph under corresponding classification according to the learning records information of the professionals of various industries respectively
Spectrum generates the knowledge mapping under corresponding classification according to the learning records information of full-time mother, then by the knowledge under each classification
Map form one completely include various class of subscribers standard knowledge map, the standard knowledge map of composition as shown in figure 3,
The first nodes of standard knowledge map are various class of subscribers respectively, and the knowledge of multiple ranks is separately included under each class of subscriber
Point node.
Preferably, the marking unit 130 includes:
Instructional video obtains subelement 131, for obtaining the corresponding instructional video of every learning records；
Text information extracts subelement 132, for extracting the text information of the slide instruction in the instructional video；
Subelement 133 is marked, for marking the knowledge point of every learning records according to the text information.
Specifically, the education resource in intelligence learning equipment is typically all video, and is known in each video comprising multiple
Know point.It include a plurality of learning records, the corresponding one or more religions of every learning records in the learning records information of the user of acquisition
Video is learned to need first to obtain every learning records pair to mark the knowledge point of every learning records in learning records information
The instructional video answered, then extracts the text information of the slide instruction in instructional video, and slide instruction can pass through screenshotss
It obtains, the text information in screenshot picture (slide instruction) is then identified by picture recognition technology, teaching can be obtained
The text information of all lantern slides in video.
After obtaining the text information of the slide instruction in instructional video, taught according to the text information of slide instruction
Knowledge point involved in video is learned, then the knowledge point according to involved in instructional video marks the knowledge point of every learning records.
Preferably, the personal knowledge map creation module 300 includes:
User type acquiring unit 310 obtains the user class of the user for the personal information according to the user
Type；
Searching unit 320, for searching use relevant to the user type of the user in the standard knowledge map
Family type；
Incidence relation determination unit 330, for according between the corresponding knowledge point node of the relevant user type
Incidence relation determines the incidence relation between the knowledge point in the study browsing record of the user；
Personal knowledge map creating unit 340, for according to the association between the knowledge point in the study browsing record
Relationship creates the personal knowledge map of the user.
Specifically, the knowledge point node in standard knowledge map is classified according to class of subscriber, when getting user's
After personal information, the user type of user is first obtained according to the personal information of user, the personal information of user can be in user's registration
It is obtained when account, the personal information of user may include the age of user, gender, occupation, work position etc., according to the individual of user
The user type that information obtains can be one or more.
After obtaining the user type of user, user class relevant to the user type of user is searched in standard knowledge map
Type searches user type relevant to multiple user type when user type is multiple respectively in standard knowledge map；
Relevant user type refers to and identical user type or similar user type.
After finding relevant user type in standard knowledge map, corresponded under classification according to relevant user type
Incidence relation between the node of knowledge point determines the incidence relation between the knowledge point in the study browsing record of user.
After obtaining the incidence relation between the knowledge point in study browsing record user can be created according to the incidence relation
Personal knowledge map.
In the present embodiment, by the way that the learning records information class of user type of mass users is classified, so that generating
Standard knowledge map in knowledge point also classify according to user type, when the personal information and user for getting user
After study browsing record, relevant user type can be searched in standard knowledge map according to the personal information of user, then root
The knowledge in the study browsing record of user is determined according to the incidence relation between the corresponding knowledge point node of relevant user type
Incidence relation between point simplifies the process for obtaining the incidence relation between knowledge point, to be quickly generated the individual of user
Knowledge mapping improves treatment effeciency.
Preferably, the learning Content recommending module 400 includes:
Knowledge point determination unit 410, for determining knowledge point that the user has grasped according to the personal knowledge map；
Knowledge point searching unit 420, it is tight with the knowledge point grasped for being searched in the standard knowledge map
Adjacent knowledge point；
Learning Content recommendation unit 430, for recommending the corresponding learning Content in the adjacent knowledge point to user.
Specifically, after creation standard knowledge map and the personal knowledge map of user, first according in personal knowledge map
Knowledge point node determine the knowledge point that user has grasped, the knowledge point then grasped according to user is in standard knowledge map
The adjacent knowledge point node of knowledge point node searched and grasped, adjacent knowledge point node refer to the higher level of knowledge point node
Knowledge point node, junior's knowledge point node or knowledge point node arranged side by side (the knowledge point node of same level).It gets adjacent
After the node of knowledge point, then learning Content relevant to adjacent knowledge point node is obtained, such as study video, then recommends use
Family.
In the present embodiment, by recommending the adjacent knowledge point in knowledge point grasped with user to user, family can be used
Regularly learnt, user is avoided desultorily to learn, so that user be made to better grasp knowledge point.
It should be noted that above-described embodiment can be freely combined as needed.The above is only of the invention preferred
Embodiment, it is noted that for those skilled in the art, in the premise for not departing from the principle of the invention
Under, several improvements and modifications can also be made, these modifications and embellishments should also be considered as the scope of protection of the present invention.
Claims (10)
1. a kind of learning Content recommended method characterized by comprising
Standard knowledge map is generated according to the learning records information of a large number of users；
The study of the personal information and user that obtain user browses record；
Record and the standard knowledge map are browsed according to the study of the personal information of the user, the user, described in creation
The personal knowledge map of user；
According to the personal knowledge map of the user and the standard knowledge map, Xiang Suoshu user recommends learning Content.
2. a kind of learning Content recommended method according to claim 1, which is characterized in that described according to a large number of users
Learning records information generate standard knowledge map specifically include:
Obtain the learning records information and corresponding user information of a large number of users；
Classified according to the user information to the learning records information；
Mark the incidence relation between the learning records information and user type；
Mark the knowledge point of every learning records in the learning records information；
Mark the incidence relation between the knowledge point；
It is generated according to the relationship relationship between the learning records information and user type, the incidence relation between the knowledge point
Standard knowledge map.
3. a kind of learning Content recommended method according to claim 2, which is characterized in that the label learning records
The knowledge point of every learning records specifically includes in information:
Obtain the corresponding instructional video of every learning records；
Extract the text information of the slide instruction in the instructional video；
The knowledge point of every learning records is marked according to the text information.
4. a kind of learning Content recommended method according to claim 2, which is characterized in that according to the user
People's information, the study browsing of the user records and the standard knowledge map, creates the personal knowledge map tool of the user
Body includes:
According to the personal information of the user, the user type of the user is obtained；
User type relevant to the user type of the user is searched in the standard knowledge map；
Determine that the study of the user is clear according to the incidence relation between the corresponding knowledge point node of the relevant user type
Look at record in knowledge point between incidence relation；
The personal knowledge map of the user is created according to the incidence relation between the knowledge point in the study browsing record.
5. a kind of learning Content recommended method according to claim 1-4, which is characterized in that described according to
Personal knowledge map and the standard knowledge map, Xiang Suoshu user recommend learning Content to specifically include:
The knowledge point that the user has grasped is determined according to the personal knowledge map；
It is searched and the adjacent knowledge point in knowledge point grasped in the standard knowledge map；
Recommend the corresponding learning Content in the adjacent knowledge point to user.
6. a kind of learning Content recommender system characterized by comprising
Standard knowledge map generation module, for generating standard knowledge map according to the learning records information of a large number of users；
User profile acquisition module, for obtaining the personal information of user and the study browsing record of user；
Personal knowledge map creation module, for according to the study browsing record of the personal information of the user, the user and
The standard knowledge map creates the personal knowledge map of the user；
Learning Content recommending module, for the personal knowledge map and the standard knowledge map according to the user, Xiang Suoshu
User recommends learning Content.
7. a kind of learning Content recommender system according to claim 6, which is characterized in that the standard knowledge map generates
Module includes:
Information acquisition unit, for obtaining the learning records information and corresponding user information of a large number of users；
Taxon, for being classified according to the user information to the learning records information；
Marking unit, for marking the incidence relation between the learning records information and user type；The study is marked to remember
Record the knowledge point of every learning records in information；Mark the incidence relation between the knowledge point；
Standard knowledge map generation unit, for according to the relationship relationship between the learning records information and user type, institute
The incidence relation stated between knowledge point generates standard knowledge map.
8. a kind of learning Content recommender system according to claim 7, which is characterized in that the marking unit includes:
Instructional video obtains subelement, for obtaining the corresponding instructional video of every learning records；
Text information extracts subelement, for extracting the text information of the slide instruction in the instructional video；
Subelement is marked, for marking the knowledge point of every learning records according to the text information.
9. a kind of learning Content recommender system according to claim 7, which is characterized in that the personal knowledge map creation
Module includes:
User type acquiring unit obtains the user type of the user for the personal information according to the user；
Searching unit, for searching user type relevant to the user type of the user in the standard knowledge map；
Incidence relation determination unit, for according to the incidence relation between the corresponding knowledge point node of the relevant user type
Determine the incidence relation between the knowledge point in the study browsing record of the user；
Personal knowledge map creating unit, for being created according to the incidence relation between the knowledge point in the study browsing record
The personal knowledge map of the user.
10. according to a kind of described in any item learning Content recommender systems of claim 6-9, which is characterized in that in the study
Holding recommending module includes:
Knowledge point determination unit, for determining knowledge point that the user has grasped according to the personal knowledge map；
Knowledge point searching unit, for being searched and the adjacent knowledge in knowledge point grasped in the standard knowledge map
Point；
Learning Content recommendation unit, for recommending the corresponding learning Content in the adjacent knowledge point to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910014982.2A CN109800300A (en) | 2019-01-08 | 2019-01-08 | learning content recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910014982.2A CN109800300A (en) | 2019-01-08 | 2019-01-08 | learning content recommendation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109800300A true CN109800300A (en) | 2019-05-24 |
Family
ID=66558679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910014982.2A Pending CN109800300A (en) | 2019-01-08 | 2019-01-08 | learning content recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109800300A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125640A (en) * | 2019-12-23 | 2020-05-08 | 江苏金智教育信息股份有限公司 | Knowledge point learning path recommendation method and device |
| CN111177413A (en) * | 2019-12-30 | 2020-05-19 | 北京谦仁科技有限公司 | Learning resource recommendation method and device and electronic equipment |
| CN111898020A (en) * | 2020-06-18 | 2020-11-06 | 济南浪潮高新科技投资发展有限公司 | Knowledge learning system recommendation method, device and medium based on BERT and LSTM |
| CN112148696A (en) * | 2019-06-26 | 2020-12-29 | 广东小天才科技有限公司 | Learning content sharing method and intelligent device |
| CN112329964A (en) * | 2020-11-24 | 2021-02-05 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for pushing information |
| CN112685645A (en) * | 2021-01-13 | 2021-04-20 | 敖客星云(北京)科技发展有限公司 | Intelligent education recommendation method, system, equipment and medium based on knowledge graph |
| CN113536111A (en) * | 2021-06-11 | 2021-10-22 | 北京十一贝科技有限公司 | Insurance knowledge content recommendation method and device and terminal equipment |
| WO2023065211A1 (en) * | 2021-10-21 | 2023-04-27 | 华为技术有限公司 | Information acquisition method and apparatus |
| CN116235165A (en) * | 2020-08-14 | 2023-06-06 | 西门子股份公司 | Method and device for intelligently providing recommendation information |
| US20230325884A1 (en) * | 2020-09-19 | 2023-10-12 | Huawei Technologies Co., Ltd. | Advertisement Display Method and Electronic Device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043073A1 (en) * | 2013-09-29 | 2015-04-02 | 北大方正集团有限公司 | Key knowledge point recommendation method and system |
| CN106503172A (en) * | 2016-10-25 | 2017-03-15 | 天闻数媒科技（湖南）有限公司 | The method and apparatus that learning path recommended by knowledge based collection of illustrative plates |
| CN106991197A (en) * | 2017-05-30 | 2017-07-28 | 海南大学 | The study point and learning path of a kind of target drives of knowledge based collection of illustrative plates recommend method |
| CN107545791A (en) * | 2017-08-29 | 2018-01-05 | 广州思涵信息科技有限公司 | A kind of system and method that classroom instruction knowledge mapping is automatically generated using courseware |
| CN108052672A (en) * | 2017-12-29 | 2018-05-18 | 北京师范大学 | Promote structural knowledge map construction system and method using group study behavior |
-
2019
- 2019-01-08 CN CN201910014982.2A patent/CN109800300A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043073A1 (en) * | 2013-09-29 | 2015-04-02 | 北大方正集团有限公司 | Key knowledge point recommendation method and system |
| CN106503172A (en) * | 2016-10-25 | 2017-03-15 | 天闻数媒科技（湖南）有限公司 | The method and apparatus that learning path recommended by knowledge based collection of illustrative plates |
| CN106991197A (en) * | 2017-05-30 | 2017-07-28 | 海南大学 | The study point and learning path of a kind of target drives of knowledge based collection of illustrative plates recommend method |
| CN107545791A (en) * | 2017-08-29 | 2018-01-05 | 广州思涵信息科技有限公司 | A kind of system and method that classroom instruction knowledge mapping is automatically generated using courseware |
| CN108052672A (en) * | 2017-12-29 | 2018-05-18 | 北京师范大学 | Promote structural knowledge map construction system and method using group study behavior |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148696A (en) * | 2019-06-26 | 2020-12-29 | 广东小天才科技有限公司 | Learning content sharing method and intelligent device |
| CN111125640B (en) * | 2019-12-23 | 2023-09-29 | 江苏金智教育信息股份有限公司 | Knowledge point learning path recommendation method and device |
| CN111125640A (en) * | 2019-12-23 | 2020-05-08 | 江苏金智教育信息股份有限公司 | Knowledge point learning path recommendation method and device |
| CN111177413A (en) * | 2019-12-30 | 2020-05-19 | 北京谦仁科技有限公司 | Learning resource recommendation method and device and electronic equipment |
| CN111898020A (en) * | 2020-06-18 | 2020-11-06 | 济南浪潮高新科技投资发展有限公司 | Knowledge learning system recommendation method, device and medium based on BERT and LSTM |
| CN116235165A (en) * | 2020-08-14 | 2023-06-06 | 西门子股份公司 | Method and device for intelligently providing recommendation information |
| US20230325884A1 (en) * | 2020-09-19 | 2023-10-12 | Huawei Technologies Co., Ltd. | Advertisement Display Method and Electronic Device |
| CN112329964A (en) * | 2020-11-24 | 2021-02-05 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for pushing information |
| CN112329964B (en) * | 2020-11-24 | 2024-03-29 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for pushing information |
| CN112685645A (en) * | 2021-01-13 | 2021-04-20 | 敖客星云(北京)科技发展有限公司 | Intelligent education recommendation method, system, equipment and medium based on knowledge graph |
| CN113536111A (en) * | 2021-06-11 | 2021-10-22 | 北京十一贝科技有限公司 | Insurance knowledge content recommendation method and device and terminal equipment |
| CN113536111B (en) * | 2021-06-11 | 2024-06-07 | 北京十一贝科技有限公司 | Recommendation method and device for insurance knowledge content and terminal equipment |
| WO2023065211A1 (en) * | 2021-10-21 | 2023-04-27 | 华为技术有限公司 | Information acquisition method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800300A (en) | learning content recommendation method and system | |
| CN109359215B (en) | Video intelligent pushing method and system | |
| CN106528656B (en) | A kind of method and system for realizing that course is recommended based on student's history and real-time learning state parameter | |
| CN109388746A (en) | A kind of education resource intelligent recommendation method based on learner model | |
| CN108920544A (en) | A kind of personalized position recommended method of knowledge based map | |
| CN108596472A (en) | A kind of the artificial intelligence tutoring system and method for natural sciences study | |
| Ghauth et al. | Measuring learner's performance in e-learning recommender systems | |
| Jando et al. | Personalized E-Learning model: A systematic literature review | |
| CN112395403B (en) | Knowledge graph-based question and answer method, system, electronic equipment and medium | |
| CN111177304B (en) | Method and terminal for automatically generating user exercises | |
| CN104133817A (en) | Online community interaction method and device and online community platform | |
| CN105389622A (en) | Multi-constraint learning path recommendation method based on knowledge map | |
| CN106934071A (en) | Recommendation method and device based on Heterogeneous Information network and Bayes's personalized ordering | |
| CN107169043A (en) | A kind of knowledge point extraction method and system based on model answer | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| CN107544973A (en) | A kind of method and apparatus that data are handled | |
| CN113806630A (en) | Attention-based multi-view feature fusion cross-domain recommendation method and device | |
| CN102708164B (en) | Method and system for calculating movie expectation | |
| CN107085618A (en) | Study point and learning path towards the 5W target drives based on data collection of illustrative plates, Information Atlas and knowledge mapping are recommended | |
| CN109903127A (en) | Group recommendation method and device, storage medium and server | |
| CN110990662B (en) | Domain expert selection method based on citation network and scientific research cooperation network | |
| CN105930490A (en) | Intelligent selecting system for teaching resources | |
| CN109145083A (en) | A kind of candidate answers choosing method based on deep learning | |
| CN117171350A (en) | Knowledge graph-based personalized course learning environment construction method and device | |
| CN103034728B (en) | Social network academic resources interaction platform is utilized to carry out the method for information interaction |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |
|
| RJ01 | Rejection of invention patent application after publication |