The content of the invention
The embodiment of the present invention proposes a kind of teaching resource recommendation method and device thereof, and user terminal can be made to reduce resource
Search time, improve the utilization rate of teaching resource.
A kind of teaching resource provided in an embodiment of the present invention recommends method, comprises the following steps:
Obtain the education activities of user terminal;
The resource matched with described education activities is obtained from teaching resource, recommendation information is then generated;
The recommendation information is sent to user terminal.
Alternatively, before described teaching resource recommends method to perform, the religion of at least one user terminal uploads is received
Data are learned, and the teaching data of reception is incorporated into described teaching resource.
Further, described teaching resource is the teaching resource with multidimensional attribute.
Further, the teaching data by reception in the teaching resource recommendation method carries out the integration of multidimensional attribute
Processing, the step of obtaining the teaching resource with multidimensional attribute includes:
Teaching data is received, and the teaching data is extracted;
Modeling algorithm is selected, and multidimensional teaching data model is set up according to the teaching data after extraction;
Described multidimensional teaching data model is used as the teaching resource with multidimensional attribute.
Further, the multidimensional teaching data model includes the data of three kinds of dimensions:The type dimension of teaching data, religion
Learn the judge dimension of content category dimension and user terminal to teaching data of data.
Further, being obtained and described education activities phase from teaching resource in the teaching resource recommendation method
The resource matched somebody with somebody, the step of then generating recommendation information includes:
Described education activities are carried out with the extraction of activity data;
The activity data of the extraction is pre-processed;
Modeling algorithm is selected, and education activities data model is set up according to pretreated activity data;
The data matched with described education activities data model are obtained in described teaching resource, then generation is pushed away
Recommend information.
Further, the teaching resource recommends method after the step of generating recommendation information, can also will be described
Education activities, and the recommendation information of the generation are stored.
Further, in the education activities described in storage, and the generation recommendation information while, to the institute of storage
There are education activities to carry out the Classified into groups of similarity;
Then by the recommendation information in each group, the user being sent respectively in the group corresponding to each education activities is whole
End.
Based on above-mentioned purpose, present invention also offers a kind of teaching resource recommendation apparatus, including:
Education activities unit, the education activities for receiving and storing user terminal;
Teaching resource unit, for storing teaching resource data;
Intelligent recommendation engine, for being obtained from teaching resource unit and the education activities in described education activities unit
The resource matched, generates recommendation information and is sent to user terminal.
Alternatively, described teaching resource unit receives the teaching data of at least one user terminal uploads, and will connect
The teaching data of receipts carries out integration processing.
Further, described teaching resource unit is the teaching resource with multidimensional attribute.
Further, described teaching resource unit includes receiving module, teaching data abstraction module and modeling module, its
In:
Described receiving module, the teaching data for receiving at least one user terminal uploads;
Described teaching data abstraction module, for extracting teaching data from described receiving module;
Described modeling module, multidimensional teaching number is set up for selecting modeling algorithm, and according to the teaching data after extraction
According to model.
Further, the multidimensional teaching data model includes the data of three kinds of dimensions:The type dimension of teaching data, religion
Learn the judge dimension of content category dimension and user terminal to teaching data of data.
Alternatively, described intelligent recommendation engine include education activities data extraction module, modeling module, matching module and
Output module;Wherein:
Described education activities data extraction module, for extracting activity data from the education activities unit, goes forward side by side
Row pretreatment;
Described modeling module, education activities are set up for selecting modeling algorithm, and according to pretreated activity data
Data model;
Described matching module, for being obtained and described education activities data model phase in the teaching resource unit
The data of matching, generate recommendation information;
Described output module, for the recommendation information of generation to be sent into user terminal.
Further, described intelligent recommendation engine also includes matching module in groups, is connected with described matching module;
Described matching module in groups receives and stores the education activities data model, and the education activities data mould
Type and the recommendation information obtained after the Data Matching in the teaching resource unit.
Further, described matching module in groups will carry out being categorized into for similarity to all education activities of storage
Group, and by the recommendation information in each group, it is sent respectively to the user terminal corresponding to each education activities in the group.
From the above it can be seen that a kind of teaching resource recommendation method and device thereof provided in an embodiment of the present invention, leads to
The resource for obtaining and matching with described education activities from teaching resource is crossed, generation recommendation information is sent to user terminal.From
And, precision very high recommendation information can be provided for user terminal, search of the user terminal to teaching resource is enormously simplify
Handle work.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with specific embodiment, and reference
Accompanying drawing, the present invention is described in more detail.
As shown in fig.1, recommend the schematic flow sheet of method for a kind of teaching resource of the embodiment of the present invention, including:
Step 101, the education activities of user terminal are obtained.
Step 102, the resource matched with described education activities is obtained from teaching resource, recommendation is then generated
Breath.
In one embodiment of the invention, before teaching resource recommendation method is carried out, at least one user terminal
The teaching data of upload is received, and the teaching data of reception is incorporated into described teaching resource.It is preferred that described
Teaching data source be the teaching resource with multidimensional attribute.Wherein, the teaching resource of multidimensional attribute can be by such as
Lower method is obtained:
The first step:Teaching data is received, and the teaching data is extracted, pre-processed.
Wherein it is possible to the data pick-up rule set by regulation engine extracts come the teaching data to reception, rule
Then engine is a kind of component of insertion in the application, and its task is will currently to submit to the teaching number of regulation engine
Tested and compared according to all business rules being carried in regulation engine, find the business met under current data state
Rule is simultaneously activated, then according to the execution logic of the business rule of activation, triggers corresponding operation.
Furthermore it is possible to be pre-processed to the teaching data by extracting, for example, it can will exceed a range of data
The outlier processing deleted;The form of the data of extraction is converted to the pre- of the data conversion of cannonical format of modeling etc.
Handle work.
Second step:Modeling algorithm is selected, and multidimensional teaching data model is set up according to the teaching data after extraction.
Wherein, the modeling algorithm of selection can be using decision Tree algorithms, cluster algorithm etc..It is used as an implementation
Example, the multidimensional teaching data model of foundation can include the data of three kinds of dimensions:A kind of dimension is the type of teaching data, including
Text, image, animation, courseware, video, audio etc., user terminal can be applied to different types in different application scenarios.One
Plant the content category that dimension is teaching data, including affiliated subject, grade, knowledge point, difficulty, keyword etc..The dimension with
The information that user terminal needs has a very strong relevance, and such as teacher is directed to some specific subject, some grade and specific
One knowledge point Making CAI soft.A kind of dimension is judge of the user terminal to teaching data, including scoring, evaluation, download rate, is adopted
With rate etc., the dimension can ensure that the information that the embodiment of the present invention is finally pushed is the higher teaching resource of Comprehensive Evaluation.
3rd step:Described multidimensional teaching data model is used as the teaching resource with multidimensional attribute.
In another embodiment of the present invention, as shown in Fig. 2 teaching resource recommends method when generating recommendation information,
Employ following method:
Step 201, described education activities are carried out with the extraction of activity data.
Step 202, the activity data of the extraction is pre-processed.
Step 203, modeling algorithm is selected, and education activities data model is set up according to pretreated activity data.Its
In, modeling algorithm can be using decision Tree algorithms, cluster algorithm etc., then according to the modeling algorithm and step of selection
Pretreated activity data in 202, sets up education activities data model.
Step 204, obtain what is matched with described education activities data model in the multidimensional teaching data model
Data.Wherein, described multidimensional teaching data model can be obtained by the method in step 102.
Step 205, recommendation information is generated.
Step 103, the recommendation information is sent to user terminal.
It should also be noted that, in another embodiment of the present invention, teaching resource recommends method carrying out step 204
Afterwards, can be by education activities data model and the education activities data model with being obtained after multidimensional teaching data Model Matching
Recommendation information storage, and all education activities data models of storage are carried out with the Classified into groups of similarity.Then, will be each
All recommendation informations of the education activities data model of each in group, are sent in the group corresponding to each education activities data model
User terminal.
As shown in fig.3, being a kind of structural representation of teaching resource recommendation apparatus of the embodiment of the present invention.Teaching resource is pushed away
Recommending device includes:Education activities unit 301, teaching resource unit 302 and intelligent recommendation engine 303;Wherein,
Education activities unit 301, is connected with intelligent recommendation engine 303, can receive the education activities of user terminal, and
It can be stored.
Teaching resource unit 302, is connected with intelligent recommendation engine 303, and be stored with teaching resource data.
Teaching resource unit 302 receives the teaching data for coming from least one user terminal uploads, and can dock
The teaching data of receipts carries out integration processing.
In one embodiment of the invention, as shown in figure 4, teaching resource unit 302 includes receiving module 401, teaching
Data extraction module 402 and modeling module 403.Wherein, receiving module 401 receives the teaching number of at least one user terminal uploads
According to.The data pick-up rule that teaching data abstraction module 402 can be set by regulation engine is come to the religion in receiving module 401
Learn data to be extracted, regulation engine is a kind of component of insertion in the application, its task is by current submission
Teaching data to regulation engine is tested and compared with all business rules for being carried in regulation engine, is found to meet and is worked as
Business rule and activation under preceding data mode, then according to the execution logic of the business rule of activation, trigger corresponding operation.
For example;The extraction of carry out data for the purpose of teacher's Making CAI soft.In addition, teaching data abstraction module 402 can also be to taking out
The teaching data taken is pre-processed.Modeling module 403 selects modeling algorithm, can be calculated using decision Tree algorithms, clustering
Method etc., the data then extracted according to teaching data abstraction module 402 set up multidimensional teaching data model.
It is preferred that multidimensional teaching data model can include the data of three kinds of dimensions, the i.e. type dimension of teaching data, religion
Learn the judge dimension of content category dimension and user terminal to teaching data of data.Wherein, the type dimension of teaching data
Including text, image, animation, courseware, video, audio etc., user terminal can be applied to different classes in different application scenarios
Type.The content category dimension of teaching data includes affiliated subject, grade, knowledge point, difficulty, keyword etc..The dimension is with using
The information that family terminal needs has very strong relevance, and such as teacher is directed to specific some subject, some grade and specific one
Individual knowledge point Making CAI soft.User terminal the judge dimension of teaching data is included scoring, evaluation, download rate, using rate etc., this
Dimension can ensure that the information that the embodiment of the present invention is finally pushed is the higher teaching resource of Comprehensive Evaluation.
Intelligent recommendation engine 303, can be obtained and education activities unit from the teaching resource unit 302 of multidimensional attribute
The resource that education activities in 301 match, then generates recommendation information, is last transmitted to user terminal.
As one embodiment of the present of invention, as shown in figure 5, intelligent recommendation engine 303 includes education activities data pick-up
Module 501, modeling module 502, matching module 503 and output module 504.Wherein, data extraction module 501 is from education activities list
The data pick-up rule extraction activity data set in member 301 by regulation engine.In addition, data extraction module 501 can be with
The teaching data obtained by extraction is pre-processed.Modeling module 502 selects modeling algorithm, then according to pretreated
Activity data sets up education activities data model.Matching module 503 is obtained and education activities number from multidimensional teaching data model
The data matched according to model, generate recommendation information.The recommendation information that matching module 503 is generated is sent to by output module 504
User terminal.
For example, behavior expression of the teacher during Making CAI soft is:1st, teacher likes the courseware style used, and 2, teacher
The subject of teaching and grade, 3, the knowledge point of teachers' attention, 4, the data type often downloaded of teacher.According to teacher in making class
These interest activities during part set up education activities data model, then from well-established multidimensional teaching data model
The teaching resource matched with the education activities data model is obtained, recommendation information is generated.
It should also be noted that, in another embodiment of the present invention, intelligent recommendation engine 303 also includes matching in groups
Module 505, is connected with matching module 503, can receive and store education activities data model, and the education activities data mould
Type and the recommendation information obtained after multidimensional teaching data Model Matching.All education activities of 505 pairs of storages of matching module in groups
Data model carries out the Classified into groups of similarity, then by all recommendation informations of each education activities data model in each group
User terminal in the group corresponding to each education activities data model is sent to by output module 504.Thus, it is possible to be every
Individual user terminal finds potential new teaching resource interested, expands the information of intelligent recommendation engines recommendations.
It can thus be seen that the teaching resource recommendation method and device thereof that the present invention is realized, creative proposes to religion
Learn resource data and carry out integration processing and sets up a multidimensional teaching data model, and to the education activities of user terminal at
Reason sets up education activities model, and the teaching matched with education activities data model is finally obtained from multidimensional teaching data model
Resource data, generates recommendation information and is pushed to user terminal;User terminal is to the information of push in accuracy and satisfaction side
Face, which is obtained for, significantly to be lifted;Also, had the special feature that in actual applications for teaching resource, by teaching resource number
According to a variety of dimensions are divided into, data can be screened from each dimension;At the same time, the present invention can also will have similarity
Education activities model user terminal constitute same interest group, so as to pass through the teaching of the other users terminal in group
Motility model is retrieved as the user terminal and provides potential teaching resource information, improves increasing of the present invention to each user terminal
Value service;Finally, whole described teaching resource recommendation method and device thereof is easy, compact, it is easy to accomplish, and it is whole for user
End provides a kind of the most convenient, practical experience.
It should be noted that in all parts of the controller of the present invention, according to the function that it to be realized to wherein
Part carried out logical partitioning, still, the present invention is not only restricted to this, and all parts can be repartitioned as needed
Or combination, for example, can be single part by some component combinations, or some parts can be further broken into more
Subassembly.
The present invention all parts embodiment can be realized with hardware, or with one or more processor run
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor(DSP)It is some or all in controller according to embodiments of the present invention to realize
The some or all functions of part.The present invention be also implemented as a part for performing method as described herein or
Whole equipment or program of device(For example, computer program and computer program product).Such journey for realizing the present invention
Sequence can be stored on a computer-readable medium, or can have the form of one or more signal.Such signal can
Obtained with being downloaded from internet website, either provide or provided in any other form on carrier signal.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In claims
In, any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" is not excluded for depositing
In element or step not listed in the claims.Word "a" or "an" before element do not exclude the presence of it is multiple this
The element of sample.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer
Realize.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware
Embody.The use of word first, second, and third does not indicate that any order.These words can be construed to
Title.