CN102075573A - Method and system for automatically recommending learning partner in distance education social network service (ESNS) - Google Patents
Method and system for automatically recommending learning partner in distance education social network service (ESNS) Download PDFInfo
- Publication number
- CN102075573A CN102075573A CN2011100028198A CN201110002819A CN102075573A CN 102075573 A CN102075573 A CN 102075573A CN 2011100028198 A CN2011100028198 A CN 2011100028198A CN 201110002819 A CN201110002819 A CN 201110002819A CN 102075573 A CN102075573 A CN 102075573A
- Authority
- CN
- China
- Prior art keywords
- partner
- study
- user
- candidate
- educational level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for automatically recommending a learning partner in a distance education social networks service (ESNS). The method comprises the following steps of: 1, automatically receiving learning partner recommendation application of a user side; 2, responding to the learning partner recommendation application, automatically acquiring user information, and dividing the user information into user individual information, academic information and learning partner information; 3, acquiring the tightness of a candidate learning partner and the user according to the user individual information, the academic information and the learning partner information; and 4, acquiring the candidate learning partner according to the tightness of the candidate learning partner and the user and automatically recommending and displaying the candidate learning partner to the user. By the method and the system, the learning partner in the ESNS can be automatically recommended.
Description
Technical field
The present invention relates to the partner's recommended technology in the social networks, particularly relate to study partner's auto recommending method and system thereof in a kind of long-distance education social networks.
Background technology
(Social Networks Service's social networks SNS) couples together people by this carrier of network, forms the group with a certain characteristics.SNS simulates or rebuilds the interpersonal relationships network in the real society based on real social relationships.It increases understanding and the contact of individual to the friend in its social relation network by helping to it is found that and expand its social relationships, thereby excites the wish of their collaborative work each other, study and amusement.Be in the state of separation between long-distance education middle school student and teacher, student and the student, the student obtains knowledge by autonomous learning.Because learning behavior is solitarily dull, lacks affection exchange, makes the student produce the mood of being weary of studying easily, causes learning efficiency and achievement to descend, even may lose confidence and the interest that continues study.Social networks is applied on the existing distance education platform, by in accepting the student of long-distance education, setting up study group, getting to know the atmosphere that modes such as learning the partner is built collective study, can promote the student to help each other and learn jointly that SNS provides a kind of new the Internet that utilizes to set up the friend-making and the AC mode of social networks.
Study partner's interpolation is similar to the interpolation of good friend in the common social networks, and common mode comprises: independently select and system recommendation, mainly carry out relevant matches according to user's personal information and select or recommend.But the user in the long-distance education social networks (being the long-distance education student) has its exclusive characteristics, the user is from various parts of the country, mostly do not know each other mutually, lack interpersonal relationships in the real society as the basis, so traditional friend recommendation method is difficult at long-distance education social networks (Education Social NetworksService, ESNS) be suitable in, ESNS is based on the social networking system of long-distance education.
Summary of the invention
The object of the present invention is to provide auto recommending method and the system thereof of study partner in a kind of long-distance education social networks, be used for solving the problem that existing partner's recommend method can't be suitable in long-distance education social networks ESNS, realize the automatic recommendation of study partner among the long-distance education social networks ESNS.
To achieve these goals, the invention provides study partner auto recommending method in a kind of long-distance education social networks, it is characterized in that, comprising:
Step 1, the study partner that the automatic reception user side sends recommends application;
Step 2 responds described study partner and recommends application, obtains user profile automatically and described user profile is divided into userspersonal information, school work information, study buddy information;
Step 3 is obtained the tightness that the candidate learns partner and user according to described userspersonal information, described school work information, described study buddy information;
Step 4, the tightness of learning partner and user according to described candidate is obtained the candidate and is learnt the partner, and described candidate is learnt the partner recommend and be shown to described user side automatically.
Described study partner auto recommending method, wherein,
In the described step 1, also comprise:
Described study partner recommends to apply for initiatively to be sent or the user sends after logining the page of described long-distance education social networks automatically by the user.
Described study partner auto recommending method, wherein,
In the described step 3, also comprise:
Obtain personal information matching degree, school work information matches degree, the study partnership matching degree that the candidate learns partner and user respectively according to described userspersonal information, described school work information, described study buddy information, and obtain the step that described candidate learns partner and user's tightness according to described personal information matching degree, described school work information matches degree, described study partnership matching degree.
Described study partner auto recommending method, wherein,
The described step of obtaining the personal information matching degree comprises:
To add among the described userspersonal information with study progress indicator in the customer contact school work information closely, when the candidate learns the partner when identical with index among the userspersonal information, the numerical value of this index is designated as 1, not not simultaneously, the numerical value of this index is designated as 0, then the numerical value of each index be multiply by separately weight after addition learn partner and user's personal information matching degree as the candidate.
Described study partner auto recommending method, wherein,
The described step of obtaining school work information matches degree comprises:
Described school work information is summed up in the point that respectively in six educational level key elements, and corresponding weights is set respectively for each educational level key element;
That obtains each educational level key element respectively refers to target value, multiply by addition after the weight of this educational level key element and obtains value that should the educational level key element, and the value of each educational level key element is corresponded to orthohexagonal six summits;
The value of each educational level key element is converted into the line segment length of this orthohexagonal center to the radial direction of respective vertices, and the starting point of this line segment is this orthohexagonal center, and terminal point is a hexagonal summit, obtains hexagonal educational level model.
Described study partner auto recommending method, wherein,
The described step of obtaining school work information matches degree comprises:
Take out the maximum in the value of identical educational level key element in the educational level model that the candidate learns partner and user respectively, as the length of orthohexagonal center to hexagonal summit, form a new hexagon, calculate this new hexagonal area S1, this orthohexagonal area S, school work information matches degree=S1/S.
Described study partner auto recommending method, wherein,
The described step of obtaining school work information matches degree comprises:
The difference of the value of identical educational level key element in difference calculated candidate study partner and user's the educational level model, obtain the difference addition result P of each educational level key element after taking absolute value, school work information matches degree=1-P/ (value that the excellent level of 6* is corresponding), value that wherein should excellent level correspondence is the index of educational level key element pairing value when being excellent.
Described study partner auto recommending method, wherein,
The described step of obtaining study partnership matching degree comprises:
The relation of learning by the candidate between partner and user's study partner is obtained described study partnership matching degree.
Described study partner auto recommending method, wherein,
In the described step 3, also comprise:
Calculate the tightness that described candidate learns partner and user with following formula:
The candidate learns tightness=personal information matching degree * a%+ school work information matches degree * b%+ study partnership matching degree * c% of partner and user
Wherein, a, b, c are positive number, a%+b%+c%=1.
Described study partner auto recommending method, wherein,
In the described step 4, also comprise:
The tightness of learning partner and user according to described candidate obtains the candidate and learns partner's collection, and learns the partner according to user's the candidate who shows varying number that is provided with.
To achieve these goals, the present invention also provides the automatic commending system of study partner in a kind of long-distance education social networks, it is characterized in that, comprising:
Application automatic reception module is used for the study partner that the automatic reception user side sends and recommends application;
The automatic acquisition module of information connects described application automatic reception module, and the study partner who is used to respond the user recommends application, obtains user profile automatically;
Information is divided module automatically, connects the automatic acquisition module of described information, is used for described user profile is divided into userspersonal information, school work information, study buddy information;
Study partner tightness computing module connects described information and divides module automatically, is used for obtaining the tightness that the candidate learns partner and user according to described userspersonal information, described school work information, described study buddy information;
Automatically recommend display module, connect described study partner tightness computing module, be used for obtaining the candidate and learn the partner, and described candidate is learnt the partner recommend and be shown to described user side automatically according to the tightness that described candidate learns partner and user.
The automatic commending system of described study partner wherein, also comprises:
The educational level model building module connects described information and divides module automatically, is used for described school work information is summed up in the point that six educational level key elements respectively, and for each educational level key element corresponding weights is set respectively; That obtains each educational level key element respectively refers to target value, multiply by addition after the weight of this educational level key element and obtains value that should the educational level key element, and the value of each educational level key element is corresponded to orthohexagonal six summits; The value of each educational level key element is converted into the line segment length of this orthohexagonal center to the radial direction of respective vertices, and the starting point of this line segment is this orthohexagonal center, and terminal point is a hexagonal summit, obtains hexagonal educational level model.
The automatic commending system of described study partner, wherein,
Described study partner tightness computing module also comprises:
Personal information matching degree computing module is used for obtaining the personal information matching degree that the candidate learns partner and user according to described userspersonal information;
School work information matches degree computing module connects described educational level model building module, is used for the educational level model according to the user, the educational level model that the candidate learns the partner, obtains the school work information matches degree that the candidate learns partner and user;
Study partnership matching degree computing module is used for obtaining the study partnership matching degree that the candidate learns partner and user respectively according to described study buddy information;
The tightness computing module, connect described personal information matching degree computing module, described school work information matches degree computing module, described study partnership matching degree computing module, be used for obtaining the tightness that described candidate learns partner and user according to described personal information matching degree, described school work information matches degree, described study partnership matching degree.
The automatic commending system of described study partner, wherein,
Described personal information matching degree computing module will add among the described userspersonal information with study progress indicator in the customer contact school work information closely, when the candidate learns the partner when identical with index among the userspersonal information, the numerical value of this index is designated as 1, not not simultaneously, the numerical value of this index is designated as 0, then the numerical value of each index be multiply by separately weight after addition learn partner and user's personal information matching degree as the candidate.
The automatic commending system of described study partner, wherein,
Described school work information matches degree computing module also comprises:
Complementary type school work information matches degree module, be used for taking out respectively the maximum in the value of the identical educational level key element of educational level model that the candidate learns partner and user, as the length of orthohexagonal center to the hexagon summit, form a new hexagon, calculate this new hexagonal area S1, this orthohexagonal area S, then school work information matches degree=S1/S;
Similar type school work information matches degree module, be used for the respectively difference of the value of calculated candidate study partner's and user the identical educational level key element of educational level model, difference addition with each educational level key element after taking absolute value obtains P, then school work information matches degree=1-P/ (value that the excellent level of 6* is corresponding), value that wherein should excellent level correspondence is the index of educational level key element pairing value when being excellent.
The automatic commending system of described study partner, wherein,
The relation that described study partnership matching degree computing module is learnt by the candidate between partner and user's study partner is obtained described study partnership matching degree.
The automatic commending system of described study partner, wherein,
Described tightness computing module calculates the tightness that described candidate learns partner and user with following formula:
The candidate learns tightness=personal information matching degree * a%+ school work information matches degree * b%+ study partnership matching degree * c% of partner and user
Wherein, a, b, c are positive number, a%+b%+c%=1.
The recommend method that the present invention is directed to good friend in traditional social networks can not be applicable to the limitation of study partner's recommendation among the ESNS, study automatic commending system of partner and method in a kind of long-distance education social networks are provided, solve the problem that existing partner's recommend method can't be suitable in long-distance education social networks ESNS, realized the automatic recommendation of study partner among the long-distance education social networks ESNS.
Description of drawings
Fig. 1 is an educational level illustraton of model of the present invention;
Fig. 2 is a study partner auto recommending method flow chart of the present invention;
Fig. 3 is the automatic commending system structure chart of study partner of the present invention;
The educational level complementary type study partner's that Fig. 4 (a), Fig. 4 (b) be respectively user's of the present invention educational level model, recommend for the user educational level model;
The similar type study of the educational level partner's that Fig. 5 (a), Fig. 5 (b) be respectively user's of the present invention educational level model, recommend for the user educational level model.
Embodiment
Describe the present invention below in conjunction with the drawings and specific embodiments, but not as a limitation of the invention.
As shown in Figure 2, be study partner auto recommending method flow chart of the present invention.The concrete steps of this flow process are as follows:
Step S201, at first the study partner that sends of automatic reception user side recommends application.
In this step, the study partner recommend application to comprise that the user initiatively applies for or user's login page after send application automatically;
Step S202, the study partner who responds the user then recommends application, obtains user profile from information database automatically, and sets up user's educational level model.
In this step, the user profile of obtaining automatically is divided into userspersonal information, school work information, the tripartite surface information of study buddy information, and utilizes school work information to set up user's educational level model;
Step S203, obtain the school work information matches degree that the candidate learns partner and user according to user's educational level model, obtain personal information matching degree, the study partnership matching degree that the candidate learns partner and user respectively according to userspersonal information, study buddy information, finally calculate the tightness that the candidate learns partner and user according to personal information matching degree, school work information matches degree, study partnership matching degree;
Step S204, learn the height of partner and user's tightness according to the candidate and judge that the candidate learns the possibility that the partner becomes the study partner, tightness is high more, then the candidate learn the partner become study the partner possibility big more, otherwise, tightness is low more, then the candidate to learn the possibility that the partner becomes the study partner more little, and the candidate is learnt the partner returns automatically and recommend user side.
Further, among the above-mentioned steps S203, also comprise: personal information matching degree calculation procedure.
The userspersonal information comprises: specialty, and company, the age, sex, the local, hobby is liked books, likes indexs such as course.To add the personal information matching degree of coming calculated candidate study partner and user among the userspersonal information with study progress indicator in the customer contact school work information closely.Concrete computational methods are: the candidate learns the partner when identical with a certain index among the userspersonal information, the numerical value of this index is designated as 1, not not simultaneously, the numerical value of index is designated as 0, then the numerical value of each index be multiply by separately weight after addition learn partner and user's personal information matching degree as the candidate.The weighted value of each index can be made amendment according to actual needs, as long as guarantee that total weight is 1.Userspersonal information's index and weight correspondence table are as shown in table 1 below:
Table 1
| The userspersonal information | Weight |
| Specialty | 0.2 |
| Company | 0.1 |
| Age | 0.1 |
| Sex | 0.05 |
| The local | 0.1 |
| Hobby | 0.1 |
| Like books | 0.05 |
| Like course | 0.1 |
| The identical course learning progress of learning | 0.2 |
| Total weight | 1 |
Associative list 1, to learn the partner only identical in " specialty ", " hobby ", " the identical course learning progress of learning " three indexs as the candidate, when other indexs were all inequality, then the candidate learnt personal information matching degree=1*0.2+0*0.1+0*0.1+0*0.05+0*0.1+1*0.1+0*0.05+0*0.1+1*0.2=0.5 of partner and user.
Further, among the above-mentioned steps S203, also comprise: school work information matches degree calculation procedure.
User's school work information spinner will comprise: average line duration, on average login frequency, and participate in network courses learning time, participate in the online exchange time, ratio is finished in operation, study schedule, the number of times of posting in the forum, money order receipt to be signed and returned to the sender number of times in the forum, average modules learn time, the average performance value of operation.
" synthesis is said " that the monograph of publishing in 2005 with reference to the Kirby of Harvard University professor " study power " proposes, and Zhong Zhixian, in the article that Du Anqi delivered in 2008 " the interpersonal management of match uncle: the study power that promotes distance learning person " to the viewpoint of educational level inscape, in present Chinese long-distance education, the availability of study behavioral data in the The network teaching platform, designed at the educational level model of accepting the long-distance education student, wherein the educational level key element comprises six aspects: study willpower, attitude towards study, Learning Motive, learning method, learning efficiency, creative thinking.User's school work information is summed up in the point that respectively in the six big educational level key elements, and respective weights is set.Each index obtains excellent according to dependency rule (seeing following table 2 for details), very, in, difference, (adjustable size of each level setting value is whole for the value of certain grade correspondence in 05 grades, but want the size of guarantee value to conform to) with the height of grade, multiply by the value that addition after the respective weights obtains each educational level key element, 6 educational level key elements are corresponded to orthohexagonal 6 summits, and (this regular hexagon is the educational level model based, its center is the pairing values of following table 2 middle grades " excellent " to the radius length on each summit, be set at 4 among the present invention), the value of each educational level key element is converted into the line segment length of orthohexagonal center to the radial direction of respective vertices, the starting point of line segment is orthohexagonal center, terminal point is the hexagonal summit that obtains, the gained hexagon is student's an educational level model, as shown in Figure 1.
Educational level modelling table is as shown in table 2 below:
Table 2
Associative list 2, specific descriptions are obtained the computational methods of the value of educational level key element " study willpower ":
The index of study willpower comprises: land the total time (week is the time all) of platform, the study plan of formulating and the matching degree of actual conditions.
User's the total time of landing platform (week is the time all)＞=40 minutes, then this refers to that target value is 2, the study plan of formulating and the matching degree of actual conditions are 80%, and then this refers to that target value is 3, value=2*0.5 (the weight)+3*0.5 (weight)=2.5 of study willpower.
Difference according to student's educational level model, can recommend the similar type study of educational level complementary type study partner (as Fig. 4 (a), Fig. 4 (b)) partner (as Fig. 5 (a), Fig. 5 (b)) for the user automatically with educational level, system default is recommended educational level complementary type study partner for the user, the user can initiatively apply for recommending the similar type study of educational level partner into it, wherein Fig. 4 (a) is a user's of the present invention educational level model, and Fig. 4 (b) learns partner's educational level model for the educational level complementary type that the user recommends; Fig. 5 (a) is a user's of the present invention educational level model, and Fig. 5 (b) learns partner's educational level model for the similar type of educational level that the user recommends.
The computational methods of educational level complementary type study partner and user's school work information matches degree: take out the maximum in the value of identical educational level key element in the educational level model that the candidate learns partner and user respectively, as the length of orthohexagonal center to the hexagon summit, form a new hexagon, calculate its area and be designated as S1, orthohexagonal area is designated as S.The type school work information matches degree=S1/S.
The computational methods of the similar type of educational level study partner and user's school work information matches degree: calculated candidate is learnt the difference of the value of identical educational level key element in partner and user's the educational level model respectively, difference addition with 6 educational level key elements after taking absolute value is designated as P, the type school work information matches degree=1-P/ (the corresponding value of the excellent level of 6*)=1-P/24, wherein the corresponding value of this excellent level is the index of educational level key element pairing value when being excellent, and the corresponding value of excellent herein level is 4.
Further, among the above-mentioned steps S203, also comprise: study partnership matching degree calculation procedure.
The relation that user's study partnership matching degree is learnt by the candidate between partner and user's study partner is calculated, if the candidate learns to comprise in partner's the study partner set user's study partner, be that the candidate learns the partner and with the user identical study partner arranged, then each identical study partner remembers that study partnership matching degree value is a set point (as being 5%), can add up, maximum is 100%.Among the study partner as A C is arranged, among the study partner of B C is arranged also, C is A and the common study partner of B, and the study partnership matching degree of A and B increases by 5%.So, final accumulation result is learnt partner and user's study partnership matching degree as the candidate.Wherein, the big I of set point according to the actual requirements or concrete condition and make corresponding adjustment is not defined as 5%.
Further, among the above-mentioned steps S203, also comprise: the candidate learns partner and user's tightness calculation procedure, and this tightness adopts following formula to calculate:
The candidate learns tightness=personal information matching degree * a%+ school work information matches degree * b%+ study partnership matching degree * c% of partner and user.
Coefficient a%, b% in the above-mentioned formula, c% are under 1 the prerequisite satisfying summation, can be according to the actual requirements or concrete condition and make corresponding adjustment, and as being 20%, 40%, 40% or 25%, 35%, 40%, wherein a, b, c are positive number.
Further, among the above-mentioned steps S204, also comprise: the size of learning partner and user's tightness according to each candidate obtains the candidate and learns partner's collection, can show that according to user's setting the candidate of varying number learns the partner and is back to user side!
As shown in Figure 3, be the automatic commending system structure chart of study partner of the present invention.This system 300 comprises: application automatic reception module 30, the automatic acquisition module 31 of information, information are divided module 32, educational level model building module 33 automatically, learn partner's tightness computing module 34, are recommended display module 35 automatically.
Application automatic reception module 30 is used for the study partner that the automatic reception user side sends and recommends application;
The study partner recommends to apply for initiatively to be sent or the user sends after logining the page of described long-distance education social networks automatically by the user.
The automatic acquisition module 31 of information connects application automatic reception module 30, and the study partner who is used to respond the user recommends application, and obtains user profile from information database 310 automatically.
Information is divided memory module 32, the automatic acquisition module 31 of link information, the user profile that is used for obtaining is divided into userspersonal information, school work information, study buddy information automatically, and is stored in respectively in userspersonal information's database 321, school work information database 322, the study buddy information database 323.
Wherein, the userspersonal information comprises: specialty, and company, the age, sex, the local, hobby is liked books, likes indexs such as course.User's school work information spinner will comprise: average line duration, on average login frequency, and participate in network courses learning time, participate in the online exchange time, ratio is finished in operation, study schedule, the number of times of posting in the forum, money order receipt to be signed and returned to the sender number of times in the forum, average modules learn time, the average performance value of operation.
Educational level model building module 33, link information are divided module 32 automatically, are used to utilize the school work information that obtains to set up user's educational level model, specifically:
User's school work information is summed up in the point that respectively in the six big educational level key elements, and respective weights is set.Each index obtains excellent according to dependency rule (know clearly and see the above table 2), very, in, difference, (adjustable size of each level setting value is whole for the value of certain grade correspondence in 05 grades, but want the size of guarantee value to conform to) with the height of grade, multiply by the value that addition after the respective weights obtains each educational level key element, 6 educational level key elements are corresponded to orthohexagonal 6 summits, and (this regular hexagon is the educational level model based, its center is the pairing value of last table 2 middle grade " excellent " to the radius length on each summit, be set at 4 among the present invention), the value of each educational level key element is converted into the line segment length of orthohexagonal center to the radial direction of respective vertices, the starting point of line segment is orthohexagonal center, terminal point is the hexagonal summit that obtains, and the gained hexagon is student's an educational level model.
Study partner tightness computing module 34, link information is divided module 32, educational level model building module 33 automatically, be used for obtaining the school work information matches degree that the candidate learns partner and user according to user's educational level model, and obtain personal information matching degree, the study partnership matching degree that the candidate learns partner and user respectively according to userspersonal information, study buddy information, according to personal information matching degree, school work information matches degree, learn the partnership matching degree and finally calculate the tightness that the candidate learns partner and user;
Further, study partner tightness computing module 34 comprises again: personal information matching degree computing module 341, school work information matches degree computing module 342, study partnership matching degree computing module 343, tightness computing module 344.
Personal information matching degree computing module 341 is used for and will adds the personal information matching degree of coming calculated candidate study partner and user among the userspersonal information with customer contact school work information closely study progress indicator.Specifically: the candidate learns the partner when identical with a certain index among the userspersonal information, the numerical value of this index is designated as 1, not not simultaneously, the numerical value of this index is designated as 0, then the numerical value of each index be multiply by separately weight after addition learn partner and user's personal information matching degree as the candidate.The weighted value of each index can be made amendment according to actual needs, as long as guarantee that total weight is 1.
School work information matches degree computing module 342 is used for the educational level model according to the user, the educational level model that the candidate learns the partner, obtains the school work information matches degree that the candidate learns partner and user.School work information matches degree comprises similar type study partner to user's school work information matches degree, educational level of educational level complementary type study partner and user's school work information matches degree.
Further, school work information matches degree computing module 342 comprises again: complementary type school work information matches degree module 3421, similar type school work information matches degree module 3432.
Complementary type school work information matches degree module 3421, be used to calculate educational level complementary type study partner and user's school work information matches degree, it is the maximum of taking out respectively in the value of identical educational level key element in the educational level model that the candidate learns partner and user, as the length of orthohexagonal center to the hexagon summit, form a new hexagon, calculate its area and be designated as S1, orthohexagonal area is designated as S.The type school work information matches degree=S1/S.
Similar type school work information matches degree module 3432, be used to calculate similar type study partner of educational level and user's school work information matches degree, it is to distinguish the difference that calculated candidate is learnt the value of identical educational level key element in partner and user's the educational level model, difference addition with 6 educational level key elements after taking absolute value is designated as P, the type school work information matches degree=1-P/ (the corresponding value of the excellent level of 6*)=1-P/24, wherein the corresponding value of this excellent level is the index of educational level key element pairing value when being excellent, and the corresponding value of excellent herein level is 4.
Study partnership matching degree computing module 343, be used for learning the study partnership matching degree that relation between partner and user's study partner is calculated the user according to the candidate, if the candidate learns to comprise in partner's the study partner set user's study partner, be that the candidate learns the partner and with the user identical study partner arranged, then each identical study partner remembers that study partnership matching degree value is a set point (as being 5%), can add up, maximum is 100%.Among the study partner as A C is arranged, among the study partner of B C is arranged also, C is A and the common study partner of B, and the study partnership matching degree of A and B increases by 5%.So, final accumulation result is learnt partner and user's study partnership matching degree as the candidate.Wherein, the big I of set point according to the actual requirements or concrete condition and make corresponding adjustment is not defined as 5%.
The candidate learns tightness=personal information matching degree * a%+ school work information matches degree * b%+ study partnership matching degree * c% of partner and user.
Coefficient a%, b% in the above-mentioned formula, c% are under 1 the prerequisite satisfying summation, can be according to the actual requirements or concrete condition and make corresponding adjustment, and as being 20%, 40%, 40% or 25%, 35%, 40%, wherein a, b, c are positive number.
Automatically recommend display module 35, connectionist learning partner tightness computing module 34 is used for obtaining the candidate according to the tightness that the candidate learns partner and user and learns the partner, and the candidate learnt the partner recommend and be shown to the user automatically.
The size of automatically recommending display module 35 also to learn partner and user's tightness according to each candidate obtains the candidate and learns the partner and collect, and can show that according to user's setting the candidate of varying number learns the partner and is back to user side.
Further, automatically recommend display module 35 to judge that according to the height that the candidate learns partner and user's tightness the candidate learns the possibility that the partner becomes the study partner, tightness is high more, then the candidate learn the partner become study the partner possibility big more, otherwise, tightness is low more, then the candidate learn the partner become study the partner possibility more little.
The recommend method that the present invention is directed to good friend in traditional social networks can not be applicable to the limitation of study partner's recommendation among the ESNS, commending system and the method for study partner in a kind of long-distance education social networks are provided, have realized the automatic recommendation of study partner among the long-distance education social networks ESNS.
Certainly; the present invention also can have other various embodiments; under the situation that does not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection range of the appended claim of the present invention.
Claims (17)
1. learn partner's auto recommending method in a long-distance education social networks, it is characterized in that, comprising:
Step 1, the study partner that the automatic reception user side sends recommends application;
Step 2 responds described study partner and recommends application, obtains user profile automatically and described user profile is divided into userspersonal information, school work information, study buddy information;
Step 3 is obtained the tightness that the candidate learns partner and user according to described userspersonal information, described school work information, described study buddy information;
Step 4, the tightness of learning partner and user according to described candidate is obtained the candidate and is learnt the partner, and described candidate is learnt the partner recommend and be shown to described user side automatically.
2. study partner auto recommending method according to claim 1 is characterized in that,
In the described step 1, also comprise:
Described study partner recommends to apply for initiatively to be sent or the user sends after logining the page of described long-distance education social networks automatically by the user.
3. study partner auto recommending method according to claim 1 and 2 is characterized in that,
In the described step 3, also comprise:
Obtain personal information matching degree, school work information matches degree, the study partnership matching degree that the candidate learns partner and user respectively according to described userspersonal information, described school work information, described study buddy information, and obtain the step that described candidate learns partner and user's tightness according to described personal information matching degree, described school work information matches degree, described study partnership matching degree.
4. study partner auto recommending method according to claim 3 is characterized in that,
The described step of obtaining the personal information matching degree comprises:
To add among the described userspersonal information with study progress indicator in the customer contact school work information closely, when the candidate learns the partner when identical with index among the userspersonal information, the numerical value of this index is designated as 1, not not simultaneously, the numerical value of this index is designated as 0, then the numerical value of each index be multiply by separately weight after addition learn partner and user's personal information matching degree as the candidate.
5. study partner auto recommending method according to claim 3 is characterized in that,
The described step of obtaining school work information matches degree comprises:
Described school work information is summed up in the point that respectively in six educational level key elements, and corresponding weights is set respectively for each educational level key element;
That obtains each educational level key element respectively refers to target value, multiply by addition after the weight of this educational level key element and obtains value that should the educational level key element, and the value of each educational level key element is corresponded to orthohexagonal six summits;
The value of each educational level key element is converted into the line segment length of this orthohexagonal center to the radial direction of respective vertices, and the starting point of this line segment is this orthohexagonal center, and terminal point is a hexagonal summit, obtains hexagonal educational level model.
6. study partner auto recommending method according to claim 5 is characterized in that,
The described step of obtaining school work information matches degree comprises:
Take out the maximum in the value of identical educational level key element in the educational level model that the candidate learns partner and user respectively, as the length of orthohexagonal center to hexagonal summit, form a new hexagon, calculate this new hexagonal area S1, this orthohexagonal area S, school work information matches degree=S1/S.
7. study partner auto recommending method according to claim 5 is characterized in that,
The described step of obtaining school work information matches degree comprises:
The difference of the value of identical educational level key element in difference calculated candidate study partner and user's the educational level model, obtain the difference addition result P of each educational level key element after taking absolute value, school work information matches degree=1-P/ (value that the excellent level of 6* is corresponding), value that wherein should excellent level correspondence is the index of educational level key element pairing value when being excellent.
8. study partner auto recommending method according to claim 3 is characterized in that,
The described step of obtaining study partnership matching degree comprises:
The relation of learning by the candidate between partner and user's study partner is obtained described study partnership matching degree.
9. according to claim 4,5,6,7 or 8 described study partner auto recommending methods, it is characterized in that,
In the described step 3, also comprise:
Calculate the tightness that described candidate learns partner and user with following formula:
The candidate learns tightness=personal information matching degree * a%+ school work information matches degree * b%+ study partnership matching degree * c% of partner and user
Wherein, a, b, c are positive number, a%+b%+c%=1.
10. according to claim 1,2,4,5,6,7 or 8 described study partner auto recommending methods, it is characterized in that,
In the described step 4, also comprise:
The tightness of learning partner and user according to described candidate obtains the candidate and learns partner's collection, and learns the partner according to user's the candidate who shows varying number that is provided with.
11. the automatic commending system of study partner is characterized in that in the long-distance education social networks, comprising:
Application automatic reception module is used for the study partner that the automatic reception user side sends and recommends application;
The automatic acquisition module of information connects described application automatic reception module, and the study partner who is used to respond the user recommends application, obtains user profile automatically;
Information is divided module automatically, connects the automatic acquisition module of described information, is used for described user profile is divided into userspersonal information, school work information, study buddy information;
Study partner tightness computing module connects described information and divides module automatically, is used for obtaining the tightness that the candidate learns partner and user according to described userspersonal information, described school work information, described study buddy information;
Automatically recommend display module, connect described study partner tightness computing module, be used for obtaining the candidate and learn the partner, and described candidate is learnt the partner recommend and be shown to described user side automatically according to the tightness that described candidate learns partner and user.
12. the automatic commending system of study partner according to claim 11 is characterized in that, also comprises:
The educational level model building module connects described information and divides module automatically, is used for described school work information is summed up in the point that six educational level key elements respectively, and for each educational level key element corresponding weights is set respectively; That obtains each educational level key element respectively refers to target value, multiply by addition after the weight of this educational level key element and obtains value that should the educational level key element, and the value of each educational level key element is corresponded to orthohexagonal six summits; The value of each educational level key element is converted into the line segment length of this orthohexagonal center to the radial direction of respective vertices, and the starting point of this line segment is this orthohexagonal center, and terminal point is a hexagonal summit, obtains hexagonal educational level model.
13. the automatic commending system of study partner according to claim 12 is characterized in that,
Described study partner tightness computing module also comprises:
Personal information matching degree computing module is used for obtaining the personal information matching degree that the candidate learns partner and user according to described userspersonal information;
School work information matches degree computing module connects described educational level model building module, is used for the educational level model according to the user, the educational level model that the candidate learns the partner, obtains the school work information matches degree that the candidate learns partner and user;
Study partnership matching degree computing module is used for obtaining the study partnership matching degree that the candidate learns partner and user respectively according to described study buddy information;
The tightness computing module, connect described personal information matching degree computing module, described school work information matches degree computing module, described study partnership matching degree computing module, be used for obtaining the tightness that described candidate learns partner and user according to described personal information matching degree, described school work information matches degree, described study partnership matching degree.
14. the automatic commending system of study partner according to claim 13 is characterized in that,
Described personal information matching degree computing module will add among the described userspersonal information with study progress indicator in the customer contact school work information closely, when the candidate learns the partner when identical with index among the userspersonal information, the numerical value of this index is designated as 1, not not simultaneously, the numerical value of this index is designated as 0, then the numerical value of each index be multiply by separately weight after addition learn partner and user's personal information matching degree as the candidate.
15. the automatic commending system of study partner according to claim 13 is characterized in that, described school work information matches degree computing module also comprises:
Complementary type school work information matches degree module, be used for taking out respectively the maximum in the value of the identical educational level key element of educational level model that the candidate learns partner and user, as the length of orthohexagonal center to the hexagon summit, form a new hexagon, calculate this new hexagonal area S1, this orthohexagonal area S, then school work information matches degree=S1/S;
Similar type school work information matches degree module, be used for the respectively difference of the value of calculated candidate study partner's and user the identical educational level key element of educational level model, difference addition with each educational level key element after taking absolute value obtains P, then school work information matches degree=1-P/ (value that the excellent level of 6* is corresponding), value that wherein should excellent level correspondence is the index of educational level key element pairing value when being excellent.
16. the automatic commending system of study partner according to claim 13 is characterized in that,
The relation that described study partnership matching degree computing module is learnt by the candidate between partner and user's study partner is obtained described study partnership matching degree.
17. according to claim 13, the automatic commending system of 14 or 15 described study partners, it is characterized in that,
Described tightness computing module calculates the tightness that described candidate learns partner and user with following formula:
The candidate learns tightness=personal information matching degree * a%+ school work information matches degree * b%+ study partnership matching degree * c% of partner and user
Wherein, a, b, c are positive number, a%+b%+c%=1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100028198A CN102075573A (en) | 2011-01-07 | 2011-01-07 | Method and system for automatically recommending learning partner in distance education social network service (ESNS) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100028198A CN102075573A (en) | 2011-01-07 | 2011-01-07 | Method and system for automatically recommending learning partner in distance education social network service (ESNS) |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102075573A true CN102075573A (en) | 2011-05-25 |
Family
ID=44033914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100028198A Pending CN102075573A (en) | 2011-01-07 | 2011-01-07 | Method and system for automatically recommending learning partner in distance education social network service (ESNS) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102075573A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013075583A1 (en) * | 2011-11-25 | 2013-05-30 | 腾讯科技（深圳）有限公司 | Method, device and storage medium for adding friends |
| CN103150323A (en) * | 2012-12-20 | 2013-06-12 | 杭州友谦网络科技有限公司 | Method and device for processing and importing personal information data |
| CN103166834A (en) * | 2011-12-15 | 2013-06-19 | 北京千橡网景科技发展有限公司 | Method and equipment recommending friends to social network user based on location |
| CN103428169A (en) * | 2012-05-17 | 2013-12-04 | 腾讯科技（深圳）有限公司 | Method and system for recommending users in SNS community |
| CN103514161A (en) * | 2012-06-15 | 2014-01-15 | 上海蓝卓教育信息科技有限公司 | Intelligent trainee matching system and method |
| CN104170316A (en) * | 2012-01-05 | 2014-11-26 | 国际商业机器公司 | Goal-oriented user matching among social networking environments |
| CN105702109A (en) * | 2016-03-29 | 2016-06-22 | 华南师范大学 | Internet-of-things operation teaching method and Internet-of-things operation teaching system |
| CN106022931A (en) * | 2016-04-19 | 2016-10-12 | 李麟飞 | Public welfare social contact recommending method |
| CN106175129A (en) * | 2016-08-09 | 2016-12-07 | 宁波力芯科信息科技有限公司 | A kind of intelligent school table and strange land based on intelligent school table study matching process |
| CN106682035A (en) * | 2015-11-11 | 2017-05-17 | 中国移动通信集团公司 | Individualized learning recommendation method and device |
| WO2017084455A1 (en) * | 2015-11-18 | 2017-05-26 | 腾讯科技（深圳）有限公司 | User recommendation method and apparatus |
| CN107369115A (en) * | 2017-08-17 | 2017-11-21 | 厦门劢联科技有限公司 | A kind of adaptive operation distribution method and system |
| CN107463679A (en) * | 2017-08-07 | 2017-12-12 | 石林星 | A kind of information recommendation method and device |
| CN108804462A (en) * | 2017-05-03 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Method, apparatus and server are recommended in a kind of advertisement |
| CN108985952A (en) * | 2018-06-25 | 2018-12-11 | 武汉滴滴网络科技有限公司 | A kind of social network relationships circle division methods |
| CN109543026A (en) * | 2018-12-12 | 2019-03-29 | 广东小天才科技有限公司 | Analytic content acquisition method of mathematical formula and family education equipment |
| CN110046798A (en) * | 2019-03-08 | 2019-07-23 | 北京马尔马拉科技有限公司 | A kind of big data social activity processing system and processing method |
| CN111311997A (en) * | 2020-04-01 | 2020-06-19 | 孙梦菲 | Interaction method based on network education resources |
| CN112437121A (en) * | 2020-11-04 | 2021-03-02 | 濮阳职业技术学院 | English study room based on Internet of things |
| CN112581161A (en) * | 2020-12-04 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Object selection method and device, storage medium and electronic equipment |
| CN113051300A (en) * | 2021-03-05 | 2021-06-29 | 深圳市鹰硕技术有限公司 | Online learning method and device based on learning partner matching |
-
2011
- 2011-01-07 CN CN2011100028198A patent/CN102075573A/en active Pending
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013075583A1 (en) * | 2011-11-25 | 2013-05-30 | 腾讯科技（深圳）有限公司 | Method, device and storage medium for adding friends |
| CN103166834A (en) * | 2011-12-15 | 2013-06-19 | 北京千橡网景科技发展有限公司 | Method and equipment recommending friends to social network user based on location |
| CN104170316B (en) * | 2012-01-05 | 2018-01-23 | 国际商业机器公司 | Match method, system and the computer readable storage devices of user |
| CN104170316A (en) * | 2012-01-05 | 2014-11-26 | 国际商业机器公司 | Goal-oriented user matching among social networking environments |
| US10268653B2 (en) | 2012-01-05 | 2019-04-23 | International Business Machines Corporation | Goal-oriented user matching among social networking environments |
| CN103428169A (en) * | 2012-05-17 | 2013-12-04 | 腾讯科技（深圳）有限公司 | Method and system for recommending users in SNS community |
| CN103514161A (en) * | 2012-06-15 | 2014-01-15 | 上海蓝卓教育信息科技有限公司 | Intelligent trainee matching system and method |
| CN103150323B (en) * | 2012-12-20 | 2017-02-08 | 杭州友谦网络科技有限公司 | Method and device for processing and importing personal information data |
| CN103150323A (en) * | 2012-12-20 | 2013-06-12 | 杭州友谦网络科技有限公司 | Method and device for processing and importing personal information data |
| CN106682035A (en) * | 2015-11-11 | 2017-05-17 | 中国移动通信集团公司 | Individualized learning recommendation method and device |
| WO2017084455A1 (en) * | 2015-11-18 | 2017-05-26 | 腾讯科技（深圳）有限公司 | User recommendation method and apparatus |
| CN105702109A (en) * | 2016-03-29 | 2016-06-22 | 华南师范大学 | Internet-of-things operation teaching method and Internet-of-things operation teaching system |
| CN105702109B (en) * | 2016-03-29 | 2019-03-05 | 华南师范大学 | Internet of Things net operation teaching method and system |
| CN106022931A (en) * | 2016-04-19 | 2016-10-12 | 李麟飞 | Public welfare social contact recommending method |
| CN106175129A (en) * | 2016-08-09 | 2016-12-07 | 宁波力芯科信息科技有限公司 | A kind of intelligent school table and strange land based on intelligent school table study matching process |
| CN108804462B (en) * | 2017-05-03 | 2021-08-27 | 腾讯科技（深圳）有限公司 | Advertisement recommendation method and device and server |
| CN108804462A (en) * | 2017-05-03 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Method, apparatus and server are recommended in a kind of advertisement |
| CN107463679A (en) * | 2017-08-07 | 2017-12-12 | 石林星 | A kind of information recommendation method and device |
| CN107369115A (en) * | 2017-08-17 | 2017-11-21 | 厦门劢联科技有限公司 | A kind of adaptive operation distribution method and system |
| CN108985952A (en) * | 2018-06-25 | 2018-12-11 | 武汉滴滴网络科技有限公司 | A kind of social network relationships circle division methods |
| CN109543026A (en) * | 2018-12-12 | 2019-03-29 | 广东小天才科技有限公司 | Analytic content acquisition method of mathematical formula and family education equipment |
| CN110046798A (en) * | 2019-03-08 | 2019-07-23 | 北京马尔马拉科技有限公司 | A kind of big data social activity processing system and processing method |
| CN111311997A (en) * | 2020-04-01 | 2020-06-19 | 孙梦菲 | Interaction method based on network education resources |
| CN111311997B (en) * | 2020-04-01 | 2022-03-15 | 孙梦菲 | Interaction method based on network education resources |
| CN112437121A (en) * | 2020-11-04 | 2021-03-02 | 濮阳职业技术学院 | English study room based on Internet of things |
| CN112437121B (en) * | 2020-11-04 | 2022-08-05 | 濮阳职业技术学院 | English study room based on Internet of things |
| CN112581161A (en) * | 2020-12-04 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Object selection method and device, storage medium and electronic equipment |
| CN112581161B (en) * | 2020-12-04 | 2024-01-19 | 上海明略人工智能(集团)有限公司 | Object selection method and device, storage medium and electronic equipment |
| CN113051300A (en) * | 2021-03-05 | 2021-06-29 | 深圳市鹰硕技术有限公司 | Online learning method and device based on learning partner matching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102075573A (en) | Method and system for automatically recommending learning partner in distance education social network service (ESNS) | |
| CN110795619B (en) | Multi-target-fused educational resource personalized recommendation system and method | |
| CN109241454B (en) | Interest point recommendation method fusing social network and image content | |
| CN103488714B (en) | Book recommendation method and system based on social networking | |
| CN104881800A (en) | Mobile-crowd-sourcing-sensing-based motivation system realization method | |
| CN111445362A (en) | Learner-centered adaptive learning system | |
| CN104133817A (en) | Online community interaction method and device and online community platform | |
| CN107657034A (en) | A kind of event social networks proposed algorithm of social information enhancing | |
| CN107423406A (en) | A kind of construction method of campus student relational network | |
| Jo et al. | Generalized friendship paradox in networks with tunable degree-attribute correlation | |
| CN107045533A (en) | Educational resource based on label recommends method and system | |
| CN112784163A (en) | RS 24-based personalized POIs recommendation method | |
| Caso et al. | Users Ranking in Online Social Networks to Support POIs Selection in Small Groups. | |
| Li | Quality Evaluation Method of College Graduates' Innovation and Entrepreneurship Education Based on the Principle of Brain Neurology. | |
| CN107391637B (en) | Group recommendation method aiming at geographic social information | |
| CN104616225A (en) | Method of building learning incentive mechanism of online community learning system | |
| CN106157150B (en) | Information processing method and information processing apparatus | |
| CN103177343B (en) | A kind of method and system of information processing | |
| CN115392058A (en) | Method for constructing digital twin model based on evolutionary game in industrial Internet of things | |
| CN116822813A (en) | Task allocation method, device, equipment and storage medium in space crowdsourcing | |
| Organ | Practice over the private teaching institutions selection problem in one of secondary schools with using multiple attribute decision making method of TOPSIS | |
| CN108021645A (en) | It is a kind of based on the potential friend recommendation method for choosing friends preference and matrix decomposition | |
| CN103179215A (en) | Method and system for informationized education cloud | |
| Yuan et al. | Research on group POIs recommendation fusion of users' gregariousness and activity in LBSN | |
| Zhang | Exploration of Digital Transformation Path of Civic Education Management in Colleges and Universities in the Information Age |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110525 |