CN109740861A

CN109740861A - A kind of learning data analysis method and device

Info

Publication number: CN109740861A
Application number: CN201811519639.5A
Authority: CN
Inventors: 李素粉; 赵健东; 刘志华; 杨杰
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2018-12-12
Filing date: 2018-12-12
Publication date: 2019-05-10

Abstract

The embodiment of the present invention discloses a kind of learning data analysis method and device, is related to network technique field, can be analyzed by learning behavior information to Virtual Learning Environment student and course resources information, and generate recommendation course.This method comprises: from basic data, the learning behavior data for presetting tissue in preset time are obtained in management information base；According to basic data and learning behavior data, the analysis list of student's feature is calculated；According to basic data and learning behavior data, the list for enlivening the key index in course and prefecture is calculated；According to basic data and learning behavior data, the tabulation of inactive course is calculated；Inactive course includes corpse course and less learned lesson；According to the basic information of student and learning behavior data, calculates and recommend course.The embodiment of the present invention is applied to learning System.

Description

A kind of learning data analysis method and device

Technical field

The embodiment of the present invention is related to network technique field more particularly to a kind of learning data analysis method and device.

Background technique

Enterprise's Virtual Learning Environment is based on Internet technology, using open on-line study platform model, with education resource For core, meet the various training scene demands of enterprise, construct and instruct the ecosystem in enterprise, enterprise is helped to realize that the talent is leading.With Universal and good application, the enterprise's Virtual Learning Environment of internet have become the important channel of internal education and Knowledge Sharing. User behavior data is to instruct one of main foundation of the platform production and operation, and how to carry out effective data analysis is platform operation The main problem faced.The modeling process of network student's behavioural characteristic is obtained and is maintained and learn in analysis student's behavior The hobby etc. of member eventually forms the model for being used to react student's individual demand, knowledge background or hobby.Obtain student Entertaining hobby, the data such as demand and all interbehaviors, comprehensive summarize to obtain one to be capable of operation by dissecting Student's behavioural characteristic model of computable formatting, and the variation of student's behavior is continuously recorded, with the change of student's hobby Change and then change the process of student's behavioural characteristic model.Currently, the research for enterprise's Virtual Learning Environment is less, it can not be effective Guidance be directed to enterprise's online learning Platform deployment migration efficiency.

Summary of the invention

The embodiment of the present invention provides a kind of learning data analysis method and device, can be by Virtual Learning Environment The learning behavior information and course resources information of member is analyzed, and generates recommendation course.

In order to achieve the above objectives, the present invention adopts the following technical scheme:

In a first aspect, a kind of learning data analysis method is provided, this method comprises: obtaining from management information base pre- If presetting basic data, the learning behavior data of tissue in the time；Wherein, basic data includes the basic information and class of student The resource information of journey, the basic information of student include the ID of student, the post of student, the age of student and the tissue of student Information, the resource information of course include attribute information and the affiliated prefecture of course of course；Learning behavior data include student's Log-on message, the learning records of student and course by learning records；Default tissue includes that at least one subgroup is knitted, every height At least one student that tissue includes is second level student, and default tissue further includes at least one level-one student, and level-one student is pre- Determine the student that all subgroups are knitted in tissue, course includes compulsory course and elective；When preset time includes first default Between with the second preset time, the first preset time is before the second preset time and adjacent；According to basic data and study row For data, the analysis list of student's feature is calculated；Wherein, student's feature include enliven the feature of student, learn increment feature, The feature of inactive student and the feature of abnormal student, enlivening student includes the study according to the study duration, student of student The student of m1 before the sequence for the weighted value that one or more calculating in number and the login times of student generate；Learn increment The login times for the student that the login times of student including knitting in the first preset time subgroup are knitted with the second preset time subgroup Difference, the student knitted in the first preset time subgroup the study person-time student knitted with the second preset time subgroup study people Secondary difference；Inactive student includes the student being not logged in, logs in the student not learnt and learn the less student of number, is learned The study number for practising the less student of number meets: 0 < learns number < preset times threshold value；Abnormal student includes study duration Greater than the student of the first preset duration threshold value, the student being not logged in and learn the less student of duration, study duration is less Student meets: 0 < learns the second preset duration of duration < threshold value；According to basic data and learning behavior data, calculate active The list of course and the key index in prefecture；Wherein, enlivening course includes most popular course and compulsory course, most by joyous Meeting course includes the course for learning m3 before duration sorts；The key index for enlivening course includes: the quantity of study of most popular course Sub- Tissue distribution, completion rate, the completion rate of all required courses, the required course completion rate of level-one student, institute of every required course The completion rate for the required course for thering is the required course completion rate of level-one student, each subgroup to knit；The key index in prefecture includes: most by joyous Meet the sub- Tissue distribution of the quantity of study in prefecture, most popular prefecture includes the prefecture for learning m4 before duration sorts, prefecture it is required The completion rate of class, the completion rate of the required course of the level-one student in each prefecture, the required course that each subgroup is knitted in each prefecture it is complete At rate；According to basic data and learning behavior data, the tabulation of inactive course is calculated；Inactive course includes corpse Course and less learned lesson, wherein a length of zero when the study of corpse course, the study duration of less learned lesson meets: 0 < learns duration < third scheduled duration threshold value；According to the basic information of student and learning behavior data, calculates and recommend course.

In the above-mentioned methods, firstly, from management information base obtain preset time in preset tissue basic data, Learning behavior data；Then, according to basic data and learning behavior data, the analysis list of student's feature is calculated；According to base Plinth data and learning behavior data calculate the list for enlivening the key index in course and prefecture；According to basic data and Learning behavior data calculate the tabulation of inactive course；Inactive course includes corpse course and less learned lesson； Finally, calculating according to the basic information of student and learning behavior data and recommending course.The embodiment of the present invention can be by net The learning behavior information and course resources information of upper learning platform student is analyzed, and generates recommendation course.

Second aspect, provides a kind of learning data analytical equipment, which includes:

Acquiring unit, for from management information base obtain preset time in preset tissue basic data, study Behavioral data；Wherein, basic data includes the basic information of student and the resource information of course, and the basic information of student includes The resource information of the ID of student, the post of student, the age of student and the organizational information of student, course includes the category of course Property information and the affiliated prefecture of course；Learning behavior data include the log-on message of student, the learning records of student and course By learning records；Default tissue includes that at least one subgroup is knitted, each subgroup knit including at least one student be second level Member, default tissue further include at least one level-one student, and level-one student is the student that all subgroups are knitted in predetermined tissue, course packet Include compulsory course and elective；Preset time includes the first preset time and the second preset time, and the first preset time exists It is before second preset time and adjacent.

Processing unit, basic data and learning behavior data for being obtained according to acquiring unit calculate student's feature Analysis list；Wherein, student's feature include enliven the feature of student, learn the feature of increment, the feature of inactive student with And the feature of abnormal student, enlivening student includes according to the study duration of student, the study number of student and the login of student The student of m1 before the sequence for the weighted value that one or more calculating in number generate；Study increment is included in the first preset time The difference of the login times for the student that the login times for the student that subgroup is knitted and the second preset time subgroup are knitted, when first is default Between the student that knits of subgroup the study person-time student knitted with the second preset time subgroup the difference learnt person-time；Inactive student Including be not logged in student, log in the student that does not learn and the less student of study number, the less student's of study number Learn number to meet: 0 < learns number < preset times threshold value；Abnormal student includes that study duration is greater than the first preset duration threshold The student of value, the student being not logged in and the less student of study duration, the less student of study duration meet: when 0 < learns Long the second preset duration of < threshold value.

Processing unit, is also used to the basic data and learning behavior data obtained according to acquiring unit, and calculating enlivens class The list of the key index in journey and prefecture；Wherein, enlivening course includes most popular course and compulsory course, most popular Course includes the course for learning m3 before duration sorts；The key index for enlivening course includes: the quantity of study of most popular course It is sub- Tissue distribution, the completion rate of every required course, the completion rate of all required courses, the required course completion rate of level-one student, all The completion rate for the required course that required course completion rate, each subgroup of level-one student is knitted；The key index in prefecture includes: most popular The sub- Tissue distribution of the quantity of study in prefecture, most popular prefecture include the prefecture for learning m4 before duration sorts, the required course in prefecture Completion rate, the completion rate of the required course of the level-one student in each prefecture, the completion for the required course that each subgroup is knitted in each prefecture Rate.

Processing unit is also used to the basic data and learning behavior data obtained according to acquiring unit, calculates inactive The tabulation of course；Inactive course includes corpse course and less learned lesson, wherein the study duration of corpse course It is zero, the study duration of less learned lesson meets: 0 < learns duration < third scheduled duration threshold value.

Processing unit, the basic information and learning behavior data of the student for being also used to be obtained according to acquiring unit calculate Recommend course.

It is corresponded to it is to be appreciated that the learning data analytical equipment of above-mentioned offer is used to execute first aspect presented above Method, therefore, the attainable beneficial effect of institute can refer to the corresponding method of first aspect above and implement in detail below The beneficial effect of corresponding scheme in mode, details are not described herein again.

The third aspect provides a kind of learning data analytical equipment, includes place in the structure of the learning data analytical equipment Device and memory are managed, memory saves the necessary program instruction sum number of the learning data analytical equipment for coupling with processor According to processor is for executing the program instruction stored in memory, so that the learning data analytical equipment executes first aspect institute The learning data analysis method stated.

Fourth aspect provides a kind of computer storage medium, is stored with computer program code in computer storage medium, When computer program code is run on the learning data analytical equipment as described in the third aspect, so that learning data analysis dress Set the method for executing above-mentioned first aspect.

5th aspect, provides a kind of computer program product, which stores above-mentioned computer software Instruction, when computer software instructions are run on the learning data analytical equipment as described in the third aspect, so that learning data Analytical equipment executes the program of the scheme as described in above-mentioned first aspect.

Detailed description of the invention

Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.

Fig. 1 is that a kind of learning data that the embodiment of the present invention provides analyzes general frame figure；

Fig. 2 is a kind of flow diagram for learning data analysis method that the embodiment of the present invention provides；

Fig. 3 is a kind of structural schematic diagram for learning data analytical equipment that the embodiment of the present invention provides；

Fig. 4 is the structural schematic diagram for another learning data analytical equipment that the embodiment of the present invention provides；

Fig. 5 is the structural schematic diagram for another learning data analytical equipment that the embodiment of the present invention provides.

Specific embodiment

It should be noted that in the embodiment of the present invention, " illustrative " or " such as " etc. words make example, example for indicating Card or explanation.Be described as in the embodiment of the present invention " illustrative " or " such as " any embodiment or design scheme do not answer It is interpreted than other embodiments or design scheme more preferably or more advantage.Specifically, " illustrative " or " example are used Such as " word is intended to that related notion is presented in specific ways.

It should also be noted that, in the embodiment of the present invention, " (English: of) ", " corresponding (English: Corresponding, relevant) " it sometimes can be mixed with " corresponding (English: corresponding) ", it should be pointed out that It is that, when not emphasizing its difference, meaning to be expressed is consistent.

For the ease of clearly describing the technical solution of the embodiment of the present invention, in an embodiment of the present invention, use " the One ", the printed words such as " second " distinguish function and the essentially identical identical entry of effect or similar item, and those skilled in the art can To understand that the printed words such as " first ", " second " are not to be defined to quantity and execution order.

With the popularity of the internet and good application, enterprise's Virtual Learning Environment have become internal education and Knowledge Sharing Important channel.Student's behavioral data is to instruct one of main foundation of the platform production and operation, how to carry out effective data point Analysis is the main problem that platform operation faces.The modeling process of network student's behavioural characteristic is obtained in analysis student's behavior It takes and maintains and the hobby etc. of student, eventually form one and be used to react student's individual demand, knowledge background or hobby Model.The data such as entertaining hobby, demand and all interbehaviors of student are obtained, by dissecting comprehensive summary to obtain one Student's behavioural characteristic model of a computable formatting for capableing of operation, and the variation of student's behavior is continuously recorded, it is adjoint The variation of student's hobby and then the process for changing student's behavioural characteristic model.

Enterprise's Virtual Learning Environment has multiple management person user, is each responsible for a certain range of student's learning behavior management And platform operation, it is to be understood that the information such as study frequency, study schedule and study hot spot of student, and suitable course is recommended To suitable student.Therefore proposition demand is recommended to student's portrait and course.Student's portrait is that one kind delineates target student, connection The effective tool of student's demand and design direction is widely used in each field.Such as Baidu's movement is counted from movement Developer's demand is set out, see clearly student, optimization product, operation promote three aspect go to provide comprehensively analyze intuitive report with And agile development is supported and the support of digitized operation and popularization management.Mobile statistics can help developer to solve to learn Member's attribute becomes increasingly complex, and student's behavior is more and more changeable, and product is getting faster for the period, and it is higher and higher etc. many to promote cost Problem.However, enterprise's Virtual Learning Environment is different from social internet platform, have student's range relatively more fixed and course resources The features such as Relatively centralized, has specific student portrait and recommended requirements.Currently, for enterprise's Virtual Learning Environment research compared with It is few, the Virtual Learning Environment operation of enterprise can not be supported.

Based on above-mentioned technical background and the prior art there are the problem of, referring to Fig.1 shown in, the embodiment of the present invention mentions General frame figure is analyzed for a kind of learning data, mainly includes that layer is recommended in data management layer, data mining layer and study.Data Management level mainly include basic data management module and basic learning behavioral data management module, wherein basic data management Module is responsible for the basic data of management service enterprise Virtual Learning Environment；Basic learning behavioral data management module is responsible for management dimension Protect the basic data learning behavior data of enterprise's Virtual Learning Environment；Wherein, basic data mainly includes the basic information of student And the resource information of course, learning behavior data mainly include the log-on message of student, the learning records of student and course By learning records.Data mining layer includes that student's preference excavates module and curriculum characteristic excavation module.Student's preference is excavated Module mainly includes enlivening student's characteristic analysis unit, study increment feature analytical unit, inactive student's characteristic analysis unit And abnormal student's characteristic analysis unit；It mainly includes feature curriculum analysis unit, compulsory course spy that curriculum characteristic, which excavates module, Levy analytical unit, prefecture learning information analytical unit and inactive curriculum analysis unit.Wherein, student's signature analysis list is enlivened Member is mainly to the signature analysis for enlivening student；Study increment feature analytical unit is mainly knitted to being included in the first preset time subgroup Student login times and the difference of the login times of student knitted of the second preset time subgroup signature analysis, pre- first If the feature of the difference of the study person-time of the study person-time student knitted with the second preset time subgroup of the student of chronon tissue Analysis；The student that inactive student's characteristic analysis unit does not mainly learn the signature analysis of the student including being not logged in, login Signature analysis and the less student of study number signature analysis.Feature curriculum analysis unit is mainly to the spy for enlivening course Sign analysis；Compulsory course characteristic analysis unit is mainly to the signature analysis of compulsory course；Prefecture learning information analytical unit is main It is the signature analysis to the key index in prefecture；Inactive curriculum analysis unit be mainly to the signature analysis of corpse course and The signature analysis of less learned lesson.It includes recommending curriculum module and recommendation evaluation module that layer is recommended in study；Wherein, recommendation class Journey module is that the basic information and learning behavior data based on student calculate recommendation course, and recommending course mainly includes standard class The personalized recommendation course that the standardized recommendation course and personalized course recommendation unit that journey recommendation unit calculates generate. Recommend evaluation module to mainly generate the conversion ratio for recommending course, and whether recommended course is analyzed according to the conversion ratio of recommendation course Learnt by student.

Referring to Fig. 2, the embodiment of the present invention provides a kind of learning data analysis method, this method comprises:

201, from basic data, the learning behavior data for obtaining default tissue in preset time in management information base.

Wherein, basic data includes the basic information of student and the resource information of course, and the basic information of student includes The resource information of the ID of student, the post of student, the age of student and the organizational information of student, course includes the category of course Property information and the affiliated prefecture of course；Learning behavior data include the log-on message of student, the learning records of student and course By learning records；Default tissue includes that at least one subgroup is knitted, each subgroup knit including at least one student be second level Member, default tissue further include at least one level-one student, and level-one student is the student that all subgroups are knitted in predetermined tissue, course packet Include compulsory course and elective；Preset time includes the first preset time and the second preset time, and the first preset time exists It is before second preset time and adjacent.

202, according to basic data and learning behavior data, the analysis list of student's feature is calculated.

Wherein, student's feature includes enlivening the feature of student, learning the feature of increment, the feature of inactive student and different The feature of normal student, enlivening student includes according to the study duration of student, the study number of student and the login times of student In one or more calculating generate weighted value sequence before m1 student；Study increment is included in the first preset time subgroup The difference of the login times for the student that the login times of the student knitted and the second preset time subgroup are knitted, in the first preset time The difference of the study person-time of the study person-time student knitted with the second preset time subgroup of the student of tissue；Inactive student includes The student that is not logged in logs in the student not learnt and the less student of study number, the study of the less student of study number Number meets: 0 < learns number < preset times threshold value；Abnormal student includes that study duration is greater than the first preset duration threshold value Student, the student being not logged in and the less student of study duration, the less student of study duration meet: 0 < learns duration < Second preset duration threshold value.

In one implementation, the embodiment of the present invention provides a kind of side of the analysis list of feature for obtaining and enlivening student The flow diagram of method, the specific steps are as follows:

S211, the study number of student is ranked up from big to small, and determines ranking in preceding n11 of student.

S212, to each ranking the corresponding student of preceding n11 of student study number, student study duration and The login times of student are normalized respectively, and the normalization for generating n11 student learns number, n11 student returns One changes total study duration and the normalization login times of n11 student；Wherein, n11 is positive integer.

S213, the normalization of the normalization study number of student, the total study duration of normalization of student and student is stepped on Record number is weighted summation according to the following formula, generates n11 the first weighted values:

f1_i=α₁A_i+β₁B_i+γ₁C_i；

Wherein, f1 indicates the first weighted value, and A indicates that the normalization of student learns number, and B indicates that the normalization of student is always learned Duration is practised, C indicates the normalization login time of student, α₁+β₁+γ₁=1,0≤α₁,β₁,γ₁≤ 1, i=1,2 ..., n11.

S214, n11 the first weighted values are sorted from large to small, it is corresponding in first m1 of the first weighted value chooses ranking Student generates and enlivens student's list a；Wherein m1 < n11, m1 are positive integer.

In one implementation, the analysis list for learning the feature of increment is mainly used for showing number of persons logging/study people Secondary subgroup knits increment distribution.Specifically calculation includes:

S221, acquisition the second preset time period (being denoted as present period, such as 2018) and the first preset time period (are denoted as With reference to period, such as 2017) data, wherein the data include that preset group knits the number of persons logging knitted with each subgroup, preset group Knit the study duration that the study person-time knitted with each subgroup, default tissue and each subgroup are knitted.

S222, incremental data=present period data-refer to the data of period, such as default tissue increment number of persons logging The number of persons logging for logging in number -2017 years default tissues of=2018 years default tissues；Subgroup knit the increment number of persons logging of i= Subgroup in 2018 knits the number of persons logging for logging in -2017 years subgroups of number and knitting i of i.

Incremental data accounting=subgroup that S223, subgroup knit i knits the incremental data/default tissue incremental data of i；Example Such as, increment number of persons logging accounting=subgroup that subgroup knits i knits increment number of persons logging/default tissue increment number of persons logging of i.According to Above-mentioned calculation, increment number of persons logging accounting, the subgroup that generation subgroup knits i knit the incremental learning person-time accounting and subgroup of i Knit the incremental learning duration accounting of i.Gather { the increment number of persons logging accounting that each subgroup is knitted, the incremental learning that each subgroup is knitted Person-time accounting, the incremental learning duration accounting that each subgroup is knitted } it is the sub- Tissue distribution of number of persons logging/study person-time.

In one implementation, the embodiment of the present invention provides a kind of analysis list of the feature of inactive student, specifically Include:

S231, according to default tissue it is all be not logged in student and be not logged in subgroup belonging to student knit, calculate and generate The analysis list of the feature of inactive student.

It is detailed, according to default tissue it is all be not logged in student and be not logged in subgroup belonging to student knit, calculate life At the analysis list of the feature of inactive student, specific calculation includes: Step1) it obtains the default tissue and is not logged in student (student that login times are 0) sum UnLogN, each subgroup knit and are not logged in student's number SubOrgUnLogN_i, i=1,2 ..., n, n Quantity is knitted for subgroup.Step2 sub- Tissue distribution) is calculated, each subgroup is calculated first and knits and be not logged in student's number accounting SubOrgUnLogShare _i=SubOrgUnLogNi/UnLogN, then subgroup, which is knitted, is not logged in accounting set SubOrgUnLogShare={ SubOrgUnLogShare_i, i=1,2 ..., n } be inactive student feature analysis column Table.

S232, do not learn student according to all logins of default tissue and log in not learning subgroup belonging to student and knit, Calculate the analysis list for generating the feature of inactive student.

It is detailed, according to all logins of default tissue do not learn student's (study number be=login times > 0 0and) with And login does not learn subgroup belonging to student and knits, the subgroup for calculating the inactive student of generation knits arrangement view, circular Include: Step1) it obtains default tissue login and does not learn student's number UnLN, each subgroup knits login and does not learn student's number SubOrgUnLN_i, i=1,2 ..., n, n is that subgroup knits quantity.Step2 sub- Tissue distribution) is calculated, calculation method is the same as according to default Tissue it is all be not logged in student and be not logged in subgroup belonging to student knit, calculate the analysis for generating the feature of inactive student The Step2 of list, details are not described herein again.

S233, the student for being lower than preset threshold according to all study numbers for presetting tissue and study number are lower than default Subgroup belonging to the student of threshold value is knitted, and the analysis list for generating the feature of inactive student is calculated.

It is detailed, according to all study numbers of default tissue lower than preset threshold (0 < study number < preset threshold, in advance If threshold value can according to need setting, default value can also be used) student and study number be lower than preset threshold student Affiliated subgroup is knitted, and the analysis list for generating the feature of inactive student, circular: Step1 are calculated) obtain the tissue Learn student's quantity LowLN that number is lower than threshold value, each son organizes study student's number LowLN that number is lower than threshold value_i, i=1, 2 ..., n, n are that subgroup knits quantity.Step2 sub- Tissue distribution) is calculated, calculation method is not logged in according to default all of tissue It student and is not logged in subgroup belonging to student and knits, calculate the Step2 of the analysis list for the feature for generating inactive student, herein It repeats no more.

In one implementation, the embodiment of the present invention provides a kind of analysis list of the feature of abnormal student.Specific packet It includes::

S241, be more than by the study duration of student the first preset duration threshold value student be stored in set x.

S242, it is determined according to the login times of student from the student's list being not logged in, and is removed according to special student's list After the special student in the student's list being not logged in, it is stored in set y.

Illustratively, special student can include but is not limited to: i.e. by retired student, new registration student and higher management Layer student.Wherein, it can determine which student is by retired student or new registration student, for example, can incite somebody to action according to preset time The distance retired time, the student in six months was determined as retired student i.e.；Can by apart from hiring date in three months Student is determined as new registration student.

S243, the study total duration for having learnt duration and having generated all required courses of student for counting student's required course.

S244, the regulation study duration for counting student's required course generate the regulation total duration of all required courses of student.

S245, according to formula λ_1pThe regulation for having learnt all required courses of total duration/student of all required courses of=student is total Duration calculates the completion rate λ of student's required course_1p, wherein p=1,2 ..., q, q indicate student's sum.

S246, the regulation study duration comparison for having learnt duration and student's required course by student's required course, statistics Member completes the quantity of required course, and the quantity of student's required course is counted according to student's required course.

S247, according to formula λ_2p=student completes quantity/student's required course quantity of required course, calculates student's required course The completion rate λ of quantity_2p。

S248, the completion rate λ for calculating student's required course according to the following formula_p:

λ_p=α₃λ_1p+β₃λ_2p；

Wherein, α₃+β₃=1,0≤α₃,β₃≤1。

S249, by λ_pStudent lower than the 4th preset threshold is stored in set z, and set x, set y and set z are merged Generate the analysis list of the feature of abnormal student.

203, according to basic data and learning behavior data, the column for enlivening the key index in course and prefecture are calculated Table.

Wherein, enlivening course includes most popular course and compulsory course, and most popular course includes study duration row The course of m3 before sequence；Enliven course key index include: most popular course quantity of study sub- Tissue distribution, every it is required The required course of the completion rate of class, the completion rate of all required courses, the required course completion rate of level-one student, all level-one students is completed The completion rate for the required course that rate, each subgroup are knitted；The key index in prefecture includes: that the subgroup of the quantity of study in most popular prefecture is knitted Distribution, most popular prefecture include learn duration sort before m4 prefecture, the completion rate of the required course in prefecture, the one of each prefecture The completion rate of the required course of grade student, the completion rate for the required course that each subgroup is knitted in each prefecture.

In one implementation, the subgroup that the embodiment of the present invention provides a kind of quantity of study for obtaining most popular course is knitted Distribution, the specific steps are as follows:

The arrangement view acquisition modes of the sub- Tissue distribution of the quantity of study of most popular course (or most popular prefecture) are such as Under, obtain most popular course (or most popular prefecture) first, wherein will study duration as the evaluation index of quantity of study, into And according to the index value carry out ranking, obtain most popular course (or most popular prefecture) list, then obtain each course (or Prefecture) study duration (limiting the student in the current predetermined scope of organization) and the information knitted of the affiliated subgroup of student, duration will be learnt As the index of quantity of study, then calculate each subgroup knit in most popular course (or most popular prefecture) quantity of study in Accounting, the sub- Tissue distribution of the quantity of study of as most popular course (or most popular prefecture).

Illustratively, circular is as follows:

S311, most popular course (or most popular prefecture), specific calculating process includes: step1) according to setting when Between range, from basic information database read predetermined tissue student's essential information, learning behavior information and course resources letter The basic informations such as breath, course and prefecture for the study duration of student in the current predetermined scope of organization greater than zero, obtain The study duration CourseLT of course_iWith the study duration CourseAreaLT in prefecture_i, student ID and the affiliated subgroup of student knit The information such as UserOrg.Step2 Top course and the list of the prefecture Top) are calculated.For example, using the study duration of course as quantity of study Evaluation index carries out ranking to course according to the index, and the ID of Topn1 course (i.e. the course quantity of n1 before study duration) is taken to make For the list TopCourseList of most popular course, the ID of the prefecture Topn2 (i.e. the prefecture quantity of n2 before study duration) is made For the list TopCourseArea in most popular prefecture；TopCourseList={ CourseID_i, i=1,2 ... n1 }, TopCourseAreaList={ CourseAreaID_j, j=1,2 ... n2 }, n1 indicate study duration before n1 course quantity and N2 indicates that the prefecture quantity of n2 before study duration, n1, n2 value can be set or be taken according to demand default value.

S312, most popular course the subgroup of quantity of study knit distribution calculation method specifically: step1) according to (s311) The list TopCourseList of the most popular course generated, for each Elements C ourseID therein_i, i=1,2 ... N1 obtains the overall study duration CourseTotLT in the predetermined tissue of the course_i, and obtain each subgroup and knit to the course Study duration, be denoted as SubOrgLT_i1, i1=1,2 ... n, n are that the subgroup under current predetermined tissue knits quantity.Step2 it) calculates Each subgroup is knitted for course CourseID_iStudy duration accounting, be denoted as CourseOrgLTShare_i1, CourseOrgLTShare_i1=SubOrgLT_i1/CourseTotLT_i.Step3) subgroup of most popular course knits distribution list, It is denoted as CourseOrgLTShare, CourseOrgLTShare={ CourseOrgLTShare_i1, i1=1,2 ... n }, n is to work as Subgroup under preceding predetermined tissue knits quantity.In addition, calculating the calculation method of the sub- Tissue distribution of the quantity of study in most popular prefecture It is similar with step S312 to repeat no more, wherein the subgroup in most popular prefecture, which knits distribution list, is denoted as AreaOrgLTShare, AreaOrgLTShare={ CourseOrgLTShare_i2, i2=1,2 ... n }, n is that the subgroup under current organization knits quantity.

S313, for required course key index list, predominantly analysis required course performance specifically include as Lower example:

Step1 the course ID list for) obtaining required course, is stored in set ReqCourseID, ReqCourseID= {ReqCourseID_i, i=1,2 ... I1 }, I1 is the quantity of the required course of current predetermined tissue.Obtain required course ReqCourseID_iStudent's quantity (be denoted as ReqCourseUserN_i, refer to all study required courses in the predetermined scope of organization Student, comprising level-one student and second level student) and student ID (ReqCourseUserID_i= {ReqCourseUserID_i,k, k=1,2 ... ReqCourseUserN_i), and obtain predetermined tissue level-one student's quantity (ReqCourseDirectUserN) and the ID (ReqCourseDirectUserID of level-one student_i= {ReqCourseDirectUserID_{I, k}, k=1,2 ... ReqCourseDirectUserN_i}).Obtain the student of each required course To the performance of its required course, by required student to compulsory course ReqCourseID_iPerformance be denoted as ReqCourseCom_i, ReqCourseCom_i={ ReqCourseCom_i,j, j=1,2 ..., ReqCourseUserN_i, ReqCourseCom_i,j=0 or 1, indicates whether student j learns to complete course i, and being equal to 0 indicates to be equal to 1 without completing study It indicates to complete study.

Step2 the completion rate ReqCourseCom of each required course) is calculated_i, the completion rate of every required course is defined as completing All student quantity of the student's quantity of the required course divided by the required course, i.e. ReqCourseComRatei.

I1 is the quantity of the required course of current predetermined tissue, therefore the completion rate set of each required course is denoted as ReqCourseComRate={ ReqCourseComRatei, i=1,2 ... I1 }.

Step3) the completion rate ReqCourseTotComRate of all required courses is that all required courses are actually completed by student The sum of quantity should be by the sum of student's quantity performed divided by all required courses:

Step4) the required course completion rate of level-one student is used to show that the study of each level-one student of the predetermined tissue to be completed Rate (ReqCourseDirectUserComRatej1, j1=1,2 ..., ReqCourseDirectUserN, ReqCourseDirectUserN be tissue level-one student quantity) and level-one student synthesis performance (ReqCourseDirectUserTotComRate).Specifically, Step4.1) the required course completion rate of level-one student is defined as one The quantity for the required course that grade student actually accomplishes is calculated divided by the quantity for the required course that should be completed are as follows:

Wherein, I1 is the quantity of the required course of current predetermined tissue, X_{I, j1}It is 0,1 variable, if student j1 has learnt course I, and course i is also the required course of the student j1, then X_{I, j1}=1, otherwise X_{I, j1}=0, the denominator of formulaIt indicates to learn The quantity of the required course of member j1.Above-mentioned calculated result is stored in database ReqCourseDirectUserComRate, ReqCourseDirectUserComRate=ReqCourseDirectUserComRatej1, j1=1,2 ..., ReqCourseDirectUserN }, the as required course completion rate of level-one student.Step4.2) the required course of all level-one students Completion rate, that is, level-one student required course integrates completion rate, and be defined as that all level-one students in the predetermined tissue actually accomplish must The sum of quantity of class is repaired divided by the sum of the quantity of required course that should be completed, calculating process are as follows:

Step5) completion rate for the required course that each subgroup is knitted include each subgroup knit to the completion rate of each required course and Each subgroup knits the completion rate to all required courses；Each subgroup, which is knitted, knits pair the completion rate of each required course for showing each subgroup The schedule of each required course, each subgroup are knitted to the completion rate of all required courses for showing that each subgroup is knitted to all required courses Schedule.Wherein each subgroup, which is knitted, is denoted as ReqCourseSubOrgComRatei, j2, i=to the completion rate of each required course 1,2 ... I1, j2=1,2 ..., SubOrgN, I1 are the quantity of the required course of current predetermined tissue, and SubOrgN is current predetermined The subgroup of tissue knits quantity.Each subgroup, which is knitted, is denoted as the completion rate of all required courses ReqCourseSubOrgTolComRatej2, j2=1,2 ..., SubOrgN, SubOrgN are that the subgroup of current organization knits quantity. Circular are as follows: Step5.1) it calculates each subgroup and knits the completion rate to each required course ReqCourseSubOrgComRatei, j2, illustratively, all students that subgroup knits j2 actually accomplish quantity to required course i Divided by quantity performed is answered, calls the calculation method of step2 to calculate the required course completion rate that subgroup is knitted, be calculated The value of ReqCourseSubOrgComRatei, j2 are stored in database ReqCourseSubOrgComRate, as each subgroup Knit the completion rate to each required course.Step5.2 it) calculates each subgroup and knits the completion rate to all required courses ReqCourseSubOrgTolComRatej2 calls the calculation method of step3 to be calculated The value of ReqCourseSubOrgTolComRatej2 is stored in database ReqCourseSubOrgTolComRate, as each Subgroup knits the completion rate to each required course.

S314, the completion rate of the required course in prefecture is shown as unit of prefecture for the list of the key index in prefecture, The completion rate of the required course of the level-one student in each prefecture, the completion rate for the required course that each subgroup is knitted in each prefecture.

Circular is as follows:

Step1) the ID list in acquisition prefecture, deposit set ReqAreaID, ReqAreaID=ReqAreaIDi, i=1, 2 ... I2 }, I2 is the quantity in the prefecture that current predetermined tissue is related to.Obtain the quantity for the required course that prefecture ReqAreaIDi includes (being denoted as ReqAreaCouseNi).The ID list for obtaining the required course that prefecture ReqAreaIDi includes, is denoted as ReqAreaCouseID, ReqAreaCouseID={ ReqAreaCouseIDj, j=1,2 ... ReqAreaCouseNi }.

Step2 the completion rate ReqAreaComRatei for) calculating the required course in each prefecture, is defined as required contained by the prefecture The synthesis completion rate of class,

I1 is the quantity in the prefecture that current predetermined tissue is related to, therefore the completion rate set of the required course in prefecture is denoted as ReqAreaComRate={ ReqAreaComRatei, i=1,2 ... I2 }.

Step3 the completion rate for) calculating the required course of the level-one student in each prefecture, for identifying level-one student in prefecture The overall schedule that required course should be learned, the AreaN that is denoted as ReqAreaDirectUserComRatei, j1, i=1,2 ..., AreaN is the quantity j1=1,2 ..., ReqAreaDirectUserN in the prefecture that current predetermined tissue is related to, ReqAreaDirectUserN is the quantity of level-one student in the predetermined tissue.Completion rate of the student j1 to the required course of prefecture i It is defined as student j1 and actually accomplishes the quantity of required course in the i of prefecture divided by the quantity that should learn required course, calculate:

Wherein X_{I, j1, k}It is 0,1 variable, if student j1 has learnt compulsory course i, and course i is also the required of the student j1 Class, then X_ij1k=1, otherwise X_ij1=0, Y_j1kIt is 0,1 variable, if course k is the compulsory course of student j1, Y_j1,k=1, otherwise Y_j1,k=0, the denominator of formulaIndicate student j1 the required course of prefecture i quantity, ReqAreaCouseNi be the required course in the i of prefecture quantity (required course in prefecture is different establish a capital be student j1 required course, Therefore 0-1 variable Y is used here_j1,kIt distinguishes).By the prefecture schedule of level-one student The calculated result of ReqAreaDirectUserComRatei, j1 are stored in database ReqAreaDirectUserComRate, ReqAreaDirectUserComRate=ReqAreaDirectUserComRatei, j1i=1,2 ... AreaN, j1=1, 2 ..., ReqAreaDirectUserN }, the completion rate of the required course of the level-one student in as each prefecture.

Step4) the completion rate for the required course that each subgroup is knitted in each prefecture, for indicating student that subgroup is knitted to each prefecture The overall schedule of interior required course, be denoted as ReqAreaSubOrgComRatei, j2, i=1,2 ... AreaN, j2=1, The quantity in the prefecture that 2 ..., SubOrgN, AreaN are related to for current predetermined tissue, j2=1,2 ..., SubOrgN, SubOrgN are The quantity that the subgroup of current predetermined tissue is knitted.Calculation method are as follows: subgroup knits the completion rate meter of the required course of the student of j2 to prefecture i Calculation method calls above-mentioned step2 to be calculated, and obtains the completion rate for the required course that each subgroup is knitted in each prefecture The value of ReqAreaSubOrgComRatei, j2 are stored in database ReqAreaSubOrgComRate, ReqAreaSubOrgComRate=ReqAreaSubOrgComRatei, j2, i=1,2 ... AreaN, j2=1,2 ..., SubOrgN }, the completion rate for the required course that each subgroup is knitted in as each prefecture.

204, according to basic data and learning behavior data, the tabulation of inactive course is calculated.

Wherein, inactive course includes corpse course and less learned lesson, a length of zero when the study of corpse course, compared with The study duration of few learned lesson meets: 0 < learns duration < third scheduled duration threshold value.

In one implementation, the acquisition modes of the tabulation of (4.1) corpse course are as follows: obtaining course first The quantity CourseCategoryN of classification and the list CourseCategory=of classification CourseCategoryj, j=1, 2,…,CourseCategoryN}.Step1 the course sum of the corpse course of the extent of competence of the predetermined tissue) is obtained UnLearnCourseN and corresponding each course affiliated classify UnLearnCourseCategoryi1, i1=1,2 ..., UnLearnCourseN.Step2 the distribution for) calculating the classification of corpse course is defined as belonging to classification CourseCategoryj's The quantity of corpse course is denoted as UnLearnCourseCategorySharej, j=1,2 ... divided by the sum of corpse course, CourseCategoryN, Wherein X_{I1, j}It is 0,1 variable, the X if course i1 belongs to classification j_{I, j1, k}= 1, otherwise X_{I, j1}=0.Calculated result is stored in database UnLearnCourseCategoryShare, UnLearnCourseCategoryShare=UnLearnCourseCategorySharej, j=1,2 ..., CourseCategoryN }, the as tabulation of corpse course.

In one implementation, the acquisition modes of the tabulation of (4.2) less learned lesson are as follows: Step1) obtaining Take classification belonging to the total LowLearnCourseN and corresponding each course of less learned lesson LowLearnCourseCategoryi2, i2=1,2 ..., LowLearnCourseN；Step2) calculation method is the same as corpse course Tabulation acquisition modes (4.1) Step2, details are not described herein again.

In one implementation, (4.3) calculate the calculation method of the tabulation of inactive course, total inactive class Journey includes corpse course and less learned lesson.Circular: Step1) calculate inactive course sum are as follows: LowTotCourseN=UnLearnCourseN+LowLearnCourseN.Step2 the category column of inactive course) is calculated The calculation method of table is with the Step2 of (4.1), and details are not described herein again.

205, it according to the basic information of student and learning behavior data, calculates and recommends course.

It obtains and the specific embodiment of course is recommended to include the following steps:

S51, at least one first course recommendation list is generated according to the basic information and learning behavior data of student, often A first course recommendation list is generated by one or more data in basic information data.

In one implementation, step S51 is specifically included:

S5111, the study person-time with each course in post is determined according to the post of student and the learned lesson of student.

S5112, the hot spot course with post is determined according to total study person-time with each course in post, and counts same post Hot spot course quantity.

If S5113, with post hot spot course quantity be greater than the first preset threshold, according to post hot spot course, The learned lesson of student and student's age count student's age of each hot spot course with post.

S5114, age determining each hot spot course with post according to the student of each hot spot course with post The average age of member.

S5115, age deviation is determined according to the following formula, wherein age deviation is the study hot spot course with post Each student age deviation:

D_i=| CY_i-Y₀|；

Wherein, D_iIndicate age deviation, CY_iIndicate average age (i=1,2 ..., n, n of 0 each hot spot course student Indicate the hot spot course quantity with post), Y₀Indicate student's age of each hot spot course.

S5116, statistics age deviation are less than or equal to hot spot course corresponding to the second preset threshold as the first course Recommendation list.

In one implementation, step S51 further includes following steps:

If the duration that S5121, student learn each course is greater than the default study duration of each course, it is determined that student is complete At course learning, and counts the student's quantity for completing each course learning and complete student's quantity of all course learnings.

Illustratively, the default study duration of each course can be set to 80% that each course always learns duration.

S5122, total study person-time that each course is determined according to the learned lesson of student, and according to total of each course Practise person-time determining hot spot course and a hot spot course quantity.

If S5123, hot spot course quantity are greater than third predetermined threshold value, learnt according to the learned lesson of student, student every The duration of a course count the study number of each course, the study duration of each course, the study number of all courses and The study duration of all courses.

S5124, normalizing is carried out to student's quantity of each course learning and student's quantity of all course learnings of completion Change the normalizing study quantity performed that processing generates each course.

Illustratively, the normalizing of certain course learns quantity performed=course learning student quantity/all courses of completion Student's quantity of study.

S5125, the study number of each course and the study number of all courses are normalized generation often The normalizing of a course learns number.

Illustratively, the normalizing of certain course learns number=course study number/all courses study number.

S5126, the study duration of each course and the study duration of all courses are normalized generation often The normalizing of a course learns duration.

Illustratively, the normalizing of certain course learns duration=course study duration/all courses study duration.

S5127, according to formula T_j=1/ (issuing time+1 of current time-j course) obtains the when valid value of each course T_j, wherein j=1,2 ..., m, m are the quantity of all courses.

S5128, to the normalizing of each course study quantity performed, the normalizing study number of each course, each course Normalizing learns the when valid value T of duration and each course_jIt is weighted the weighted value that processing generates each course.

Illustratively, the weighted value=α × course normalizing of certain course learns quantity performed+β × course normalizing Study number+γ × course normalizing learns valid value when the duration+η × course；Wherein, alpha+beta+γ+η=1,0≤α, Beta, gamma, η≤1.

In one implementation, after step S5128 further include: S5.1, by the weighted value of each course from greatly to Minispread, and t before ranking weighted value generation weighted value lists are taken, according to the corresponding course of weighted value in weighted value list Generate the first course recommendation list.

In one implementation, after step S228 further include: S5.2, according to the key of the current strategic direction of enterprise Course corresponding to weighted value of the word to each course excludes, and generates the weighted value of strategic course, and adds to strategic course Weight is ranked up, k the first course recommendation lists of the strategic corresponding course generation of course weighted value before choosing.

In one implementation, at least one first course recommendation list is generated according to basic information data, it can be with Include the following steps:

S5131, according to formula T_j=1/ (issuing time+1 of current time-j course) obtains the when valid value of each course T_j, wherein j=1,2 ..., m, m are the quantity of all courses.

S5132, the when valid value T to all courses_jIt is ranked up from big to small, valid value T when p before choosing_jCorresponding course Generate the first course recommendation list.

S52, the course at least one first course recommendation list is excluded according to Solve Problem, generates at least one A second course recommendation list, wherein the first course recommendation list and the second course recommendation list correspond.

Wherein, Solve Problem specifically includes: excluding to have learned course phase with student at least one first course recommendation list It is more than the course of the first preset ratio like degree ratio.

S53, duplicate checking and superthreshold processing are carried out at least one second course recommendation list, generate final course and recommend column Table.

For step S53, specific implementation is as follows:

S531, by identical course in each second course recommendation list, generate at least one third course recommendation list, And count the course quantity in all third course recommendation lists.

If the course quantity in S532, all third course recommendation lists is less than the 5th preset threshold, statistics is all Course in third course recommendation list generates final course recommendation list.

If the course quantity in all third course recommendation lists is more than the 5th preset threshold, according to each third course Each third course recommendation list is removed corresponding number of class according to the second preset ratio by the course ranking in recommendation list Journey, and generate at least one and eliminate corresponding number of third course recommendation list.

All courses for eliminating corresponding number of third course recommendation list of S533, statistics, which generate final course, to be recommended List.

In a kind of exemplary arrangement, generated according to step S5111~S5116, S5121~S5128, S5.1, S5.2 Three the first course recommendation lists, the final course recommendation list generated according to step S52 and S53 is primarily directed to student group The course that body is standardized is recommended.

In another exemplary arrangement, according to step S5111~S5116, S5121~S5128, S5.1, S5.2, Four the first curriculums tables that S5131, S5132 are generated combine in the prior art based on student's preference methods and collaborative filtering side Two the first course recommendation lists that method generates are mainly needle according to the final course recommendation list that step S52 and S53 are generated Personalized course is carried out to student to recommend.

It should be noted that the preference and the progress of self-study history preference submitted based on student's preference methods according to student Study is recommended, and generates the first course recommendation list according to recommendation results.Wherein, the preference that student submits refers to that student steps on for the first time Land learning platform formula, the preference information submitted according to the prompt of enterprise's Virtual Learning Environment；Self-study history preference refers to system root The user behavior portrait information formed according to student in the browsing of enterprise's Virtual Learning Environment and study history course.Based on cooperateing with Filtering method carries out study recommendation according to system filtration method, generates the first course recommendation list according to recommendation results.Collaborative filtering Refer to the hobby of the group for common experience of having similar tastes and interests using certain, possess to recommend the interested information of student.Collaborative filtering is calculated Method is with its outstanding speed and robustness, and in Global Internet field, there are many application.Based on student's preference methods and collaborative filtering Method specific implementation uses for reference the prior art and realizes that details are not described herein again.

Referring to Fig. 3, the embodiment of the present invention provides a kind of learning data analytical equipment 30, which includes:

Acquiring unit 301, for from management information base obtain preset time in preset tissue basic data, learn Practise behavioral data；Wherein, basic data includes the basic information of student and the resource information of course, the basic information packet of student Including the ID of student, the post of student, the age of student and the organizational information of student, the resource information of course includes course Attribute information and the affiliated prefecture of course；Learning behavior data include the log-on message of student, the learning records of student and class Journey by learning records；Default tissue includes that at least one subgroup is knitted, each subgroup knit including at least one student be second level Student, default tissue further include at least one level-one student, and level-one student is the student that all subgroups are knitted in predetermined tissue, course Including compulsory course and elective；Preset time includes the first preset time and the second preset time, the first preset time It is before the second preset time and adjacent.

Processing unit 302, basic data and learning behavior data for being obtained according to acquiring unit 301, numerology The analysis list of member's feature；Wherein, student's feature includes enlivening the feature of student, the feature for learning increment, inactive student Feature and the feature of abnormal student, enlivening student includes according to the study duration of student, the study number of student and student Login times in one or more calculating generate weighted value sequence before m1 student；It is pre- that study increment is included in first If the difference of the login times for the student that the login times of the student of chronon tissue and the second preset time subgroup are knitted, first The difference of the study person-time of the study person-time student knitted with the second preset time subgroup for the student that preset time subgroup is knitted；It does not live Jump student includes the student being not logged in, logs in the student not learnt and learn the less student of number, and study number is less The study number of student meets: 0 < learns number < preset times threshold value；Abnormal student includes that study duration is default greater than first The student of duration threshold value, the student being not logged in and the less student of study duration, the less student of study duration meet: 0 < Learn the second preset duration of duration < threshold value.

Processing unit 302 is also used to the basic data and learning behavior data obtained according to acquiring unit 301, calculates Enliven the list of the key index in course and prefecture；Wherein, enlivening course includes most popular course and compulsory course, most Welcome course includes the course for learning m3 before duration sorts；The key index for enlivening course includes: most popular course The required course of the sub- Tissue distribution of habit amount, the completion rate of every required course, the completion rate of all required courses, level-one student is completed The completion rate for the required course that rate, the required course completion rate of all level-one students, each subgroup are knitted；The key index in prefecture includes: The sub- Tissue distribution of the quantity of study in most popular prefecture, most popular prefecture include the prefecture for learning m4 before duration sorts, prefecture Required course completion rate, the completion rate of the required course of the level-one student in each prefecture, each subgroup is knitted required in each prefecture The completion rate of class.

Processing unit 302 is also used to the basic data and learning behavior data obtained according to acquiring unit 301, calculates The tabulation of inactive course；Inactive course includes corpse course and less learned lesson, wherein corpse course A length of zero when habit, the study duration of less learned lesson meets: 0 < learns duration < third scheduled duration threshold value.

Processing unit 302, the basic information and learning behavior number of the student for being also used to be obtained according to acquiring unit 301 According to course is recommended in calculating.

In a kind of illustrative implementation, processing unit 302, be also used to according to recommend course the duration of study with The ratio of the regulation study duration of course is recommended to generate the conversion ratio for recommending course.

Since the learning data analytical equipment in the embodiment of the present invention can be applied to implement above method embodiment, because This can be obtained technical effect see also above method embodiment, and details are not described herein for the embodiment of the present invention.

Using integrated unit, Fig. 4 shows the analysis dress of learning data involved in above-described embodiment Set a kind of 30 possible structural schematic diagram.Learning data analytical equipment 30 includes: processing module 401, communication module 402 and deposits Store up module 403.Processing module 401 is for carrying out control management to the movement of learning data analytical equipment 30, for example, processing module 401 for supporting learning data analytical equipment 30 to execute the process 202~205 in Fig. 2.Communication module 402 is for supporting study The communication of data analysis set-up 30 and other entities.Memory module 403 is used to store the program generation of learning data analytical equipment 30 Code and data.

Wherein, processing module 401 can be processor or controller, such as can be central processing unit (central Processing unit, CPU), general processor, digital signal processor (digital signal processor, DSP), Specific integrated circuit (application-specific integrated circuit, ASIC), field programmable gate array It is (field programmable gate array, FPGA) or other programmable logic device, transistor logic, hard Part component or any combination thereof.It may be implemented or execute to combine and various illustratively patrol described in present disclosure Collect box, module and circuit.The processor is also possible to realize the combination of computing function, such as includes one or more micro- places Manage device combination, DSP and the combination of microprocessor etc..Communication module 402 can be transceiver, transmission circuit or communication interface Deng.Memory module 403 can be memory.

When processing module 401 is processor as shown in Figure 5, communication module 402 is the transceiver of Fig. 5, memory module 403 For Fig. 5 memory when, learning data analytical equipment 30 involved in the embodiment of the present application can be study number as described below According to analytical equipment 30.

Referring to Figure 5, which includes: processor 501, transceiver 502,503 and of memory Bus 504.

Wherein, processor 501, transceiver 502, memory 503 are connected with each other by bus 504；Bus 504 can be outer If component connection standard (peripheral component interconnect, PCI) bus or expanding the industrial standard structure (extended industry standard architecture, EISA) bus etc..It is total that the bus can be divided into address Line, data/address bus, control bus etc..Only to be indicated with a thick line in figure, it is not intended that an only bus convenient for indicating Or a type of bus.

Processor 501 can be a general central processor (Central Processing Unit, CPU), micro process Device, application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC) or one or more A integrated circuit executed for controlling application scheme program.

Memory 503 can be read-only memory (Read-Only Memory, ROM) or can store static information and instruction Other kinds of static storage device, random access memory (Random Access Memory, RAM) or letter can be stored The other kinds of dynamic memory of breath and instruction, is also possible to Electrically Erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-only Memory, EEPROM), CD-ROM (Compact Disc Read- Only Memory, CD-ROM) or other optical disc storages, optical disc storage (including compression optical disc, laser disc, optical disc, digital universal Optical disc, Blu-ray Disc etc.), magnetic disk storage medium or other magnetic storage apparatus or can be used in carrying or store to have referring to Enable or data structure form desired program code and can by any other medium of computer access, but not limited to this. Memory, which can be, to be individually present, and is connected by bus with processor.Memory can also be integrated with processor.

Wherein, memory 503 is used to store the application code for executing application scheme, and is controlled by processor 501 System executes.Transceiver 502 is used to receive the content of external equipment input, and processor 501 is used to execute to store in memory 503 Application code, to realize learning data analysis method described in the embodiment of the present application.

It should be understood that magnitude of the sequence numbers of the above procedures are not meant to execute suitable in the various embodiments of the application Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, the implementation without coping with the embodiment of the present application Process constitutes any restriction.

Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed Scope of the present application.

It is apparent to those skilled in the art that for convenience and simplicity of description, the equipment of foregoing description, The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.

In several embodiments provided herein, it should be understood that disclosed system, apparatus and method, it can be with It realizes by another way.For example, apparatus embodiments described above are merely indicative, for example, the unit It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of equipment or unit It closes or communicates to connect, can be electrical property, mechanical or other forms.

The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.

It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.

In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real It is existing.When being realized using software program, can entirely or partly realize in the form of a computer program product.The computer Program product includes one or more computer instructions.On computers load and execute computer program instructions when, all or It partly generates according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated meter Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center Word user line (Digital Subscriber Line, DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another A web-site, computer, server or data center are transmitted.The computer readable storage medium can be computer Any usable medium that can be accessed either includes the numbers such as one or more server, data centers that medium can be used to integrate According to storage equipment.The usable medium can be magnetic medium (for example, floppy disk, hard disk, tape), optical medium (for example, DVD), Or semiconductor medium (such as solid state hard disk (Solid State Disk, SSD)) etc..

The embodiment of the present invention also provides a kind of computer program product, which can be loaded directly into storage In device, and contain software code, which is loaded into via computer and can be realized above-mentioned course after executing Recommended method.

The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain Lid is within the scope of protection of this application.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.

Claims

1. a kind of learning data analysis method characterized by comprising

From basic data, the learning behavior data for obtaining default tissue in preset time in management information base；Wherein, described Basic data includes the basic information of student and the resource information of course, and the basic information of the student includes the student ID, the post of the student, the age of the student and the organizational information of the student, the resource information packet of the course Include attribute information and the affiliated prefecture of the course of the course；The learning behavior data include the login letter of the student Breath, the learning records of the student and the course by learning records；The default tissue includes that at least one subgroup is knitted, Each subgroup knit including at least one student be second level student, the default tissue further includes at least one level-one Member, the level-one student are the student that all subgroups are knitted in the predetermined tissue, and the course includes compulsory course and takes as an elective course Course；The preset time includes the first preset time and the second preset time, and first preset time is pre- described second If before the time and adjacent；

According to the basic data and the learning behavior data, the analysis list of student's feature is calculated；Wherein, the student Feature includes enlivening the feature of student, the feature for learning increment, the feature of inactive student and the feature of abnormal student, described Enlivening student includes according in the study duration of the student, the login times for learning number and the student of the student One or more calculating generate weighted value sequence before m1 student；The study increment be included in described first it is default when Between the difference of the login times of student knitted of subgroup described in the subgroup login times of student and second preset time knitted What the study person-time for the student that value, the subgroup described in first preset time are knitted was knitted with subgroup described in second preset time The difference of the study person-time of student；The inactive student includes the student being not logged in, logs in the student not learnt and study The study number of the less student of number, the less student of the study number meet: 0 < learns number < preset times threshold Value；The exception student includes when learning duration to be greater than student, the student being not logged in and the study of the first preset duration threshold value Long less student, the less student of the study duration meet: 0 < learns the second preset duration of duration < threshold value；

According to the basic data and the learning behavior data, the column for enlivening the key index in course and prefecture are calculated Table；Wherein, the course that enlivens includes most popular course and compulsory course, and the most popular course includes study duration The course of m3 before sorting；The key index for enlivening course includes: that the subgroup of the quantity of study of the most popular course is knitted point It is cloth, the completion rate of every required course, the completion rate of all required courses, the required course completion rate of level-one student, all The completion rate for the required course that required course completion rate, each subgroup of level-one student is knitted；The key index in the prefecture include: most by The sub- Tissue distribution of the quantity of study in prefecture is welcome, the most popular prefecture includes the prefecture for learning m4 before duration sorts, described The completion rate of the required course in prefecture, the completion rate of the required course of the level-one student in each prefecture are each in each prefecture The completion rate for the required course that subgroup is knitted；

According to the basic data and the learning behavior data, the tabulation of inactive course is calculated；It is described inactive Course includes corpse course and less learned lesson, wherein a length of zero when the study of the corpse course, the less study The study duration of course meets: 0 < learns duration < third scheduled duration threshold value；

According to the basic information of the student and the learning behavior data, calculates and recommend course.

2. learning data analysis method according to claim 1, which is characterized in that described according to the basic data, institute It states learning behavior data, fisrt feature analysis list and second feature analysis list to generate and recommend course, later Further include: recommended described in the ratio generation for having learnt duration and the regulation study duration for recommending course of course according to described Recommend the conversion ratio of course.

3. a kind of learning data analytical equipment characterized by comprising

Acquiring unit, for presetting the basic data of tissue, learning behavior in preset time from obtaining in management information base Data；Wherein, the basic data includes the basic information of student and the resource information of course, the basic information of the student The organizational information in the post of ID, the student, the age of the student and the student including the student, the class The resource information of journey includes attribute information and the affiliated prefecture of the course of the course；The learning behavior data include institute State the log-on message of student, the learning records of the student and the course by learning records；The default tissue includes At least one subgroup is knitted, each subgroup knit including at least one student be second level student, the default tissue further includes At least one level-one student, the level-one student are the student that all subgroups are knitted in the predetermined tissue, and the course includes must Repair course and elective；The preset time includes the first preset time and the second preset time, it is described first it is default when Between it is before second preset time and adjacent；

Processing unit, the basic data and the learning behavior data for being obtained according to the acquiring unit calculate The analysis list of student's feature；Wherein, student's feature includes the feature, inactive enlivened the feature of student, learn increment The feature of student and the feature of abnormal student, described to enliven student include study duration according to the student, the student Study number and the student login times in one or more calculating generate weighted value sequence before m1 Member；The study increment includes that the login times for the student that the subgroup described in first preset time is knitted and described second are preset The study for the student that the difference of the login times for the student that subgroup described in time is knitted, the subgroup described in first preset time are knitted The difference of the study person-time of person-time student knitted with subgroup described in second preset time；The inactive student includes not stepping on The student of record logs in the student not learnt and learns the less student of number, the study of the less student of the study number Number meets: 0 < learns number < preset times threshold value；The exception student includes that study duration is greater than the first preset duration threshold The student of value, the student being not logged in and the less student of study duration, the less student of the study duration meet: 0 < Practise the second preset duration of duration < threshold value；

The processing unit, the basic data for being also used to be obtained according to the acquiring unit and the learning behavior number According to calculating enlivens the list of the key index in course and prefecture；Wherein, it is described enliven course include most popular course and Compulsory course, the most popular course include the course for learning m3 before duration sorts；The key index packet for enlivening course It includes: the sub- Tissue distribution of the quantity of study of the most popular course, the completion rate of every required course, all required courses Completion rate, the required course knitted of the required course completion rate of level-one student, the required course completion rate of all level-one students, each subgroup Completion rate；The key index in the prefecture includes: the sub- Tissue distribution of the quantity of study in most popular prefecture, described most popular Prefecture includes the prefecture for learning m4 before duration sorts, the completion rate of the required course in the prefecture, the level-one in each prefecture The completion rate of the required course of member, the completion rate for the required course that each subgroup is knitted in each prefecture；

The processing unit, the basic data for being also used to be obtained according to the acquiring unit and the learning behavior number According to calculating the tabulation of inactive course；The inactive course includes corpse course and less learned lesson, wherein institute It states a length of zero when the study of corpse course, the study duration of the less learned lesson meets: it is predetermined that 0 < learns duration < third Duration threshold value；

The processing unit, the basic information for the student for being also used to be obtained according to the acquiring unit and study row For data, calculates and recommend course.

4. learning data analytical equipment according to claim 3 characterized by comprising

The processing unit is also used to recommend when having learnt duration and the regulation study for recommending course of course according to described Long ratio generates the conversion ratio for recommending course.

5. a kind of learning data analytical equipment, which is characterized in that include processor in the structure of the learning data analytical equipment And memory, the memory save the necessary program of learning data analytical equipment and refer to for coupling with the processor It enables and data, the processor is filled for executing the program instruction stored in the memory so that the learning data is analyzed Set execution such as the described in any item learning data analysis methods of claim 1-2.

6. a kind of computer storage medium, which is characterized in that it is stored with computer program code in the computer storage medium, When the computer program code is run on learning data analytical equipment as claimed in claim 5, so that the study Data analysis set-up executes such as the described in any item learning data analysis methods of claim 1-2.

7. a kind of computer program product, which is characterized in that the computer program product stores computer software instructions, when The computer software instructions on learning data analytical equipment as claimed in claim 5 when running, so that the study number The program such as the described in any item learning data analysis methods of claim 1-2 is executed according to analytical equipment.