CN106469146A - A kind of checking system recommended using social group and system - Google Patents
A kind of checking system recommended using social group and system Download PDFInfo
- Publication number
- CN106469146A CN106469146A CN201510493029.2A CN201510493029A CN106469146A CN 106469146 A CN106469146 A CN 106469146A CN 201510493029 A CN201510493029 A CN 201510493029A CN 106469146 A CN106469146 A CN 106469146A
- Authority
- CN
- China
- Prior art keywords
- group
- interest similarity
- user
- social
- random
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 claims abstract description 83
- 238000012795 verification Methods 0.000 claims abstract description 25
- 239000000203 mixture Substances 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims description 75
- 238000010276 construction Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000000205 computational method Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000011524 similarity measure Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010068052 Mosaicism Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 210000003765 sex chromosome Anatomy 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The verification method recommended using social group and system that the present invention provides, by being analyzed to the first Interest Similarity of group social in social platform and the second Interest Similarity of the random random group forming, or the second Interest Similarity of the random user pair of the first Interest Similarity by multiple users couple in social group and random composition is analyzed, it is verified when the first Interest Similarity then determines higher than the second Interest Similarity, it is experimentally confirmed the effectiveness recommended using social group, particularly when carrying out video recommendations, effectiveness is more preferable.
Description
Technical field
The present invention relates to internet arena, particularly to a kind of checking system recommended using social group
System and system.
Background technology
With the arrival in web2.0 epoch, user is for the individual demand of various internet products or service
Increasingly protrude it is recommended that system is widely used in meeting users ' individualized requirement, be academic circles at present and industry
Boundary's popular research and application.Classic algorithm for example collaborative filtering, Cempetency-based education, based on population system
Meter is learned and is filtered, filtered by substantial amounts of research based on social information and use, the wherein side based on collaborative filtering
Method is commending system algorithm the most frequently used at present.
Collaborative filtering includes, based on neighborhood and based on model two subclasses, being wherein based on neighborhood method again
Including the recommendation based on user and two kinds of the recommendation based on article.With the collaborative filtering recommending based on user it is
Example, its ultimate principle is, according to the preference to article or information for all users, finds and active user
Taste " neighbours " user similar with preference, is using the algorithm calculating " K- neighbours " in general application；
Then, the history preference information based on this K neighbour, is that active user is recommended.
Collaborative filtering also has some obvious defects wide variety of simultaneously, for being based on
Neighborhood and the collaborative filtering based on model, the sparse sex chromosome mosaicism of cold start-up problem data is significant impact
The problem of its performance.In addition, for the algorithm based on neighborhood, because will be in crowd when finding similar neighborhood
Search in multi-user, the extensibility of its algorithm is a very big challenge.
Although going to calculate the interest similarity between user and user, thus finding between traditional collaborative filtering
Most like user, has the high accuracy of comparison, has three defects here：
1. when userbase big to a certain extent when, looking for its similar users to each user to be recommended is
One very time-consuming work, has had a strong impact on the extensibility of algorithm；
2. a most like user of searching often limits the multiformity of recommendation results, and occurs very
The phenomenon warming up, such result affects Consumer's Experience very much, because while the clicking rate of backing is higher,
But user is also desirable for recommendation results with a greater variety simultaneously；
3. the cold start-up problem for new user is it is impossible to be selected by calculating the similarity between user behavior
Similar users, thus recommendation cannot be made.
Content of the invention
In view of this, embodiments provide a kind of verification method recommended using social group
And system.
A kind of purpose of the present invention is to provide a kind of verification method recommended using social group, including：
Obtain multiple social activity groups, wherein, the plurality of social activity group is respectively positioned under same social platform；
Obtain the first Interest Similarity of the plurality of social activity group；
Obtain at random the user of described social platform and form corresponding with described social activity group multiple with a group of planes
Group, described random group is corresponded with described social activity group；
Obtain the second Interest Similarity of the plurality of random group；
It is verified when described first Interest Similarity is more than the second Interest Similarity.
Alternatively, described the first Interest Similarity obtaining the plurality of social activity group, including：
Obtain group's Interest Similarity of each social group；
Using the meansigma methodss of group's Interest Similarity of multiple social activity groups as the first Interest Similarity；
Described the second Interest Similarity obtaining the plurality of random group, including：
Obtain group's Interest Similarity of each random group；
Using the meansigma methodss of group's Interest Similarity of multiple random groups as the second Interest Similarity.
Alternatively, the described group's Interest Similarity obtaining each social group, including：
N user in same social activity group is calculated in the way of combination of twoIndividual user interest
Similarity；
Will be describedThe meansigma methodss of individual user interest similarity are similar as group's interest of this social group
Degree；
The described group's Interest Similarity obtaining each random group, including：
N user in same random group is calculated in the way of combination of twoIndividual user interest
Similarity；
Will be describedThe meansigma methodss of individual user interest similarity are similar as group's interest of this random group
Degree.
Alternatively, described social activity group is QQ group, and described social platform is QQ chat application.
Another kind of purpose of the present invention is to provide a kind of checking system recommended using social group, its
It is characterised by, including：
First acquisition unit, for obtaining multiple social activity groups, wherein, the equal position of the plurality of social activity group
Under same social platform；
Second acquisition unit, for obtaining the first Interest Similarity of the plurality of social activity group；
3rd acquiring unit, for the random user's composition obtaining described social platform and described social activity group
Corresponding multiple random group, described random group is corresponded with described social activity group；
4th acquiring unit, for obtaining the second Interest Similarity of the plurality of random group；
Decision unit, for being verified when described first Interest Similarity is more than the second Interest Similarity.
Alternatively, described second acquisition unit is additionally operable to obtain group's Interest Similarity of each social group
And using the meansigma methodss of group's Interest Similarity of multiple social activity groups as the first Interest Similarity；
Described 4th acquiring unit is additionally operable to obtain group's Interest Similarity of each random group and will be many
The meansigma methodss of group's Interest Similarity of individual random group are as the second Interest Similarity.
Alternatively, described second acquisition unit is additionally operable to n user in same social activity group with two-by-two
The mode of combination is calculatedIndividual user interest similarity and will be describedIndividual user interest similarity
Meansigma methodss as this social group group's Interest Similarity；
Described 4th acquiring unit is additionally operable to n user in same random group with the side of combination of two
Formula is calculatedIndividual user interest similarity and will be describedThe meansigma methodss of individual user interest similarity
Group's Interest Similarity as this random group.
A kind of purpose of the present invention is the verification method providing another kind to be recommended using social group, bag
Include：
Build multiple users couple, the user of described user couple co-owns at least one social group；
Obtain first Interest Similarity of the plurality of user couple；
In the social platform that described social activity group is located, random acquisition user builds with described user to number
Identical random user pair；
Obtain the second Interest Similarity of multiple random users pair；
It is verified when the first Interest Similarity is more than the second Interest Similarity.
Alternatively, described the first Interest Similarity obtaining the plurality of user couple, including：
Obtain the user interest similarity of each user couple；
Using the meansigma methodss of described user interest similarity as the first Interest Similarity；
Described the second Interest Similarity obtaining multiple random users pair, including：
Obtain the random user Interest Similarity of each random user pair；
Using the meansigma methodss of described random user Interest Similarity as the second Interest Similarity.
Alternatively, described social activity group is QQ group, and described social platform is QQ chat application.
A kind of purpose of the present invention is the checking system providing another kind to be recommended using social group, bag
Include：
First construction unit, for building multiple users couple, the user of described user couple co-owns at least
In one social group；
First acquisition unit, for obtaining first Interest Similarity of the plurality of user couple；
Second construction unit, for obtaining user's structure by random in the social platform at described social activity group place
Build with described user to number identical random user pair；
Second acquisition unit, for obtaining the second Interest Similarity of multiple random users pair；
Decision unit, for being verified when the first Interest Similarity is more than the second Interest Similarity.
Alternatively, described first acquisition unit obtains the user interest similarity of each user couple and by institute
The meansigma methodss stating user interest similarity are as the first Interest Similarity；
Described second acquisition unit obtains the random user Interest Similarity of each random user pair and incites somebody to action
The meansigma methodss of described random user Interest Similarity are as the second Interest Similarity.The utilization that the present invention provides
Verification method and system that social group is recommended, by emerging to the first of group social in social platform
Second Interest Similarity of the random group of interesting similarity and random composition is analyzed, or by social activity
Second interest phase of the random user pair of first Interest Similarity of multiple users couple and random composition in group
It is analyzed like degree, is verified when the first Interest Similarity then determines higher than the second Interest Similarity, lead to
Cross the effectiveness that experiment proves to be recommended using social group, particularly effective when carrying out video recommendations
Property is more preferable.
Brief description
Fig. 1 is a kind of a kind of stream of embodiment of the verification method recommended using social group of the present invention
Cheng Tu；
Fig. 2 is a kind of a kind of stream of embodiment of the verification method recommended using social group of the present invention
Cheng Tu；
Fig. 3 is a kind of a kind of knot of embodiment of the checking system recommended using social group of the present invention
Composition；
Fig. 4 is a kind of embodiment of the verification method that present invention another kind is recommended using social group
Flow chart；
Fig. 5 is a kind of embodiment of the verification method that present invention another kind is recommended using social group
Flow chart；
Fig. 6 is a kind of embodiment of the checking system that present invention another kind is recommended using social group
Structure chart.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, real below in conjunction with the present invention
Apply the accompanying drawing in example, the technical scheme in the embodiment of the present invention is clearly and completely described it is clear that
Described embodiment is only the embodiment of a present invention part, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained under the premise of not making creative work
The every other embodiment obtaining, all should belong to the scope of protection of the invention.
Term " first " in description and claims of this specification and above-mentioned accompanying drawing, " second ", "
Three " " 4th " etc. is for distinguishing similar object, without for describing specific order or successively secondary
Sequence.It should be appreciated that such data using can be exchanged, in the appropriate case so that enforcement described herein
Example can with except here illustrate or description content in addition to order implement.Additionally, term " inclusion "
" having " and their any deformation, it is intended that covering non-exclusive comprising, for example, comprise
The process of series of steps or unit, method, system, product or equipment are not necessarily limited to clearly to list
Those steps or unit, but may include clearly not listing or for these processes, method,
Product or the intrinsic other steps of equipment or unit.
In conjunction with a kind of verification method recommended using social group that shown in Fig. 1, the present invention provides
A kind of embodiment, including：
S101, acquisition multiple social activity groups, wherein, the plurality of social activity group is respectively positioned on same social activity
Under platform.
Social group can be the set of some users based on certain purpose composition, i.e. social group
In user there is certain identical characteristic, for example：The football social activity group of football fan's composition, or
The XX university of alumnus's composition of the social group of reading of person's reading fan's composition or XX university
Social group, social group is located under same social platform, and described social platform can be public network
Application in network, such as QQ chat application platform, wechat platform etc., then corresponding social activity group can
Being the QQ group under QQ chat application platform, or the wechat group under wechat platform, specifically do not limit.
S102, the first Interest Similarity of acquisition the plurality of social activity group.
First Interest Similarity of social group can be for the user in this social group to certain things sense
Level of interest, by understanding that in this social group, user interest is located, is easy to statistics and uses, for example：Foot
In the social group of ball fan, user compares concentration to the interest of football, referred to herein as the first interest
Total after the set that similarity can be understood as multiple social activity groups, obtain the first Interest Similarity
Can be obtained by drawing group's Interest Similarity of each of this multiple social activity group social group respectively
, specifically can be using modes such as meansigma methodss or weighted calculation, specifically not limit.
S103, obtain at random user's composition of described social platform corresponding with described social group multiple with
Group of planes group, described random group is corresponded with described social activity group.
User in the social group being mentioned above is the user's set based on certain purpose composition, for example,
Hobby is identical or school is identical, in step s 103, grabs at random in the customer data base of social platform
Take family and form random group, random group is corresponded with social group, that is, the number of random group with
The number of social group is identical, and each random group can correspond to a social group, and corresponding
Random group in user's number identical with user's number of social group, for example：One social group
In have 100 users, then also have 100 users, ability in group immediately corresponding with this social group
Domain personnel should be appreciated that and specifically repeat no more.
S104, the second Interest Similarity of the plurality of random group of acquisition.
Multiple quantity in multiple random groups is identical with the number of the social group using during test, right
Number in the social group using is not defined, and can flexibly select as needed, needs explanation
It is that herein, the second Interest Similarity is also that the composition set of multiple random group is common, that is, distinguish
Calculate group's Interest Similarity of random group of each of multiple random groups, then by random to these
Group group's Interest Similarity carry out being calculated the second Interest Similarity, concrete calculating can adopt
The meansigma methodss of group's Interest Similarity of multiple random groups, or be weighted and obtain, specifically may be used
Selected with flexible, do not limit herein.
S105, when described first Interest Similarity be more than the second Interest Similarity when be verified.
It is compared after obtaining the first Interest Similarity and the second Interest Similarity, the mode comparing is permissible
Using numeric ratio relatively, that is, the numerical value of the first Interest Similarity can lead to more than the resin of the second Interest Similarity
Cross checking it is also possible to by drawing distribution pattern, analyze distribution situation, according to the concentration of distribution situation
To determine with dispersion, distribution concentration degree height is then verified.
The verification method recommended using social group that the present invention provides, by society in social platform
The second Interest Similarity handing over the first Interest Similarity of group and the random group of random composition is carried out point
Analysis, the first Interest Similarity then determines higher than the second Interest Similarity and is verified, and is experimentally confirmed profit
The effectiveness recommended with social group, particularly when carrying out video recommendations, effectiveness is more preferable.
Another in conjunction with the verification method recommended using social group that shown in Fig. 2, the present invention provides
Plant embodiment, including：
S201, acquisition multiple social activity groups, wherein, the plurality of social activity group is respectively positioned on same social activity
Under platform.
Step S201 is similar with step S101, does not repeat herein.
S202, obtain group's Interest Similarity of each social group.
Group's Interest Similarity of social group can reflect that the hobby of user in this social group is identical
Degree, can pass through the use in this social group to the group's Interest Similarity in same social activity group
The mode of family combination of two calculates the user interest similarity of any two user, by calculated user
Interest Similarity calculates meansigma methodss as group's Interest Similarity of this social group, specifically, one
Individual social activity group includes n user, to n user in same social activity group with the side of combination of two
Formula is calculatedIndividual user interest similarity, will be describedThe meansigma methodss conduct of individual user interest similarity
Group's Interest Similarity of this social group, understands, for example for convenience：Three are had in one social group
Individual user, by the way of combination of two, has three kinds of compound modes, calculates these three compound modes respectively
Corresponding user interest similarity, then using these three user interest Similarity Measure meansigma methodss as this society
Hand over group's Interest Similarity of group.
S203, using multiple social activity groups group's Interest Similarity meansigma methodss as the first Interest Similarity.
By group's Interest Similarity of each social group can be obtained in S202 then these are social
Group's Interest Similarity of group carries out mean value calculation and obtains the first Interest Similarity, it should be noted that
Calculate the number that meansigma methodss are the social groups adopting can flexibly select, be not defined herein.
S204, obtain at random user's composition of described social platform corresponding with described social group multiple with
Group of planes group, described random group is corresponded with described social activity group.
Using the social group being set up based on certain purpose so that social group has one in above step
Determine specificity, in order to reasonably verify the feasibility being pushed using social group, here social flat
Random acquisition user in platform, the number of these users corresponding social activity group and user number are set,
So that the random user's composition obtaining and the social random group of group size identical.
S205, obtain group's Interest Similarity of each random group；
Calculate the method for group's similarity of random group and the method for the group's similarity calculating social group
Similar, n user in same random group is calculated in the way of combination of twoIndividual user
Interest Similarity, will be describedThe meansigma methodss of individual user interest similarity are emerging as the group of this random group
Interesting similarity, does not repeat herein.
S206, using the meansigma methodss of group's Interest Similarity of multiple random groups as the second Interest Similarity.
Here the number of random group is corresponding with the number of social group, and ability and those of ordinary skill should
Understand, specifically do not limit.
S207, when described first Interest Similarity be more than the second Interest Similarity when be verified.
Step S207 is similar with described step S105, does not repeat herein.
Alternatively, in the present embodiment, described social activity group is QQ group, and described social platform is chatted for QQ
Application.
In conjunction with shown in Fig. 3, a kind of verification method recommended using social group presented hereinabove, this
Invention is also corresponding to propose a kind of checking system recommended using social group, including：
First acquisition unit 301, for obtaining multiple social activity groups, wherein, the plurality of social activity group is equal
Under same social platform；
Second acquisition unit 302, for obtaining the first Interest Similarity of the plurality of social activity group；
3rd acquiring unit 303, for the random user's composition obtaining described social platform and described social group
Organize corresponding multiple random group, described random group is corresponded with described social activity group；
4th acquiring unit 304, for obtaining the second Interest Similarity of the plurality of random group；
Decision unit 305, leads to for the checking when described first Interest Similarity is more than the second Interest Similarity
Cross.
Alternatively, described second acquisition unit 302 is additionally operable to obtain group's interest phase of each social group
Seemingly spend and using the meansigma methodss of group's Interest Similarity of multiple social activity groups as the first Interest Similarity.
Described 4th acquiring unit 304 be additionally operable to obtain group's Interest Similarity of each random group and
Using the meansigma methodss of group's Interest Similarity of multiple random groups as the second Interest Similarity.
It is to be carried out using multiple social activity groups in conjunction with the verification method shown in Fig. 4, being mentioned above, below
A kind of verification method recommended using social group in same social activity group is also provided, including：
S401, the multiple users couple of structure, the user of described user couple co-owns at least one social group
In.
The quantity building user couple can meet the quantitative requirement in statistics, it is to avoid because quantity is few
The result cogency is reduced, two users of each user's centering co-own at least one society
Hand over group, for example, user's centering includes party A-subscriber and party B-subscriber, party A-subscriber can have football hobby group
Like group with basketball, party B-subscriber also has football hobby group and basketball hobby group, then party A-subscriber and party B-subscriber
Jointly owned social activity group is two, and this user is two to jointly owned social activity group, point
It is not football hobby group and basketball hobby group, that is, each user is to having at least one common social group,
One user couple jointly owned social activity group can and another user couple jointly owned social group
Group is different, and for example, a user is football hobby group to jointly owned social activity group, and another
User to jointly owned be basketball hobby group, co-own identical social activity group in user can consider
Based on necessarily identical purpose or have certain identical attribute, that is, intimate degree is higher, hobby
Can have something in common, for social group can using conventional social tool, such as QQ chat group,
Wechat chat group or mhkc etc., identify oneself with the user in these groups and can be based on certain purpose, for example
Identical hobby or the fellow-villager from same place etc., for example, it is possible to build 100 users couple, to this not
It is defined.
S402, first Interest Similarity of the plurality of user couple of acquisition.
Using the multiple users building to as a user pair set, obtain the first of this user pair set
Interest Similarity, can first to user to carrying out calculating user interest similarity, then by these users' couple
User interest similarity carries out being calculated the first Interest Similarity, and the mode of calculating can be averaged
Or weighted calculation etc., the Interest Similarity of user can be embodied by the operation of user, for example,
User's viewing record, speculates the hobby of user, user interest similarity by the type watching film
Computational methods can adopt cosine similarity method, by the information material of two users of user's centering
Set up two texts, set up two vectors according to two content of text, calculate this two vectorial cosine values,
Between [- 1,1], cosine value more levels off to 1 to the scope of cosine value, represents two vectorial directions and gets over convergence
More consistent in 0, two vectorial direction, the similarity of corresponding text is also higher, then two users are described
User interest similarity higher, it will be understood by those skilled in the art that do not repeat herein.
In S403, the social platform that described social activity group is located, random acquisition user builds and described user
To number identical random user pair.
User in social platform randomly draw structure random user pair, the number of random user pair with society
Hand over group in build user couple number identical, for example, in social group user build user to for
100, then the number of random user pair also correspond to 100, do not limit herein.
S404, the second Interest Similarity of the multiple random users pair of acquisition.
Using multiple random users to the second Interest Similarity obtaining this entirety as entirety, obtaining
Before obtaining the second Interest Similarity, first can calculate the random user interest of every a pair of random user pair respectively
Similarity, then the random user Interest Similarity of these random users pair is carried out being calculated the second interest
Similarity, calculation specifically can not limited using averaging or weighted calculation etc..
S405, when the first Interest Similarity be more than the second Interest Similarity when be verified.
Calculated first Interest Similarity and the second Interest Similarity are compared, when the first interest
Similarity is then verified when being more than the second Interest Similarity, may certify that by the use of social group as recommendation
During mode, the hobby of user is more close, meets the demand recommended.
The verification method recommended using social group that the present invention provides, by multiple in social group
Second Interest Similarity of the random user pair of first Interest Similarity of user couple and random composition is carried out point
Analysis, the first Interest Similarity then determines higher than the second Interest Similarity and is verified, and is experimentally confirmed profit
The effectiveness recommended with social group, particularly when carrying out video recommendations, effectiveness is more preferable.
In conjunction with shown in Fig. 5, the present invention additionally provides one using the verification method that social group is recommended
Plant embodiment, including：
S501, the multiple users couple of structure, the user of described user couple co-owns at least one social group
In.
Step S501 is similar with step S401, is not repeated herein.
S502, obtain the user interest similarity of each user couple.
The user interest similarity obtaining user couple is described in step S402, is not gone to live in the household of one's in-laws on getting married herein
State.
S503, using the meansigma methodss of described user interest similarity as the first Interest Similarity.
By each user to being calculated user interest Similarity Measure meansigma methodss, using meansigma methodss as many
First Interest Similarity of individual user couple.
In S504, the social platform that described social activity group is located, random acquisition user builds and described user
To number identical random user pair.
Step S504 is similar with step S403, does not repeat herein.
S505, obtain the random user Interest Similarity of each random user pair.
The calculation of random user Interest Similarity can participate in the computational methods of user interest similarity,
It is calculated using cosine similarity, do not repeated herein.
S506, using the meansigma methodss of described random user Interest Similarity as the second Interest Similarity.
The random user Interest Similarity of each random user pair is carried out mean value calculation, will calculate
Use to meansigma methodss as the second Interest Similarity.
S507, when the first Interest Similarity be more than the second Interest Similarity when be verified.
Alternatively, described social activity group is QQ group, and described social platform is QQ chat application.
In conjunction with shown in Fig. 6, a kind of corresponding checking recommended using social group presented hereinabove
Method, builds multiple users to verifying in same social activity group, below corresponding using social
A kind of embodiment of the checking system that group is recommended, including：
First construction unit 601, for building multiple users couple, the user of described user couple co-own to
In a few social group；
First acquisition unit 602, for obtaining first Interest Similarity of the plurality of user couple；
Second construction unit 603, for obtaining user by random in the social platform at described social activity group place
Build with described user to number identical random user pair；
Second acquisition unit 604, for obtaining the second Interest Similarity of multiple random users pair；
Decision unit 605, for being verified when the first Interest Similarity is more than the second Interest Similarity.
Alternatively, described first acquisition unit 602 obtain each user couple user interest similarity and
Using the meansigma methodss of described user interest similarity as the first Interest Similarity；
Alternatively, described second acquisition unit 603 obtains the random user interest of each random user pair
Similarity and using the meansigma methodss of described random user Interest Similarity as the second Interest Similarity.
Those skilled in the art can be understood that, for convenience and simplicity of description, above-mentioned retouches
The specific work process of the system, apparatus, and unit stated, may be referred to the correspondence in preceding method embodiment
Process, will not be described here.
It should be understood that disclosed system in several embodiments provided herein, device and
Method, can realize by another way.For example, device embodiment described above is only shown
Meaning property, for example, the division of described unit, only a kind of division of logic function, actual can when realizing
There to be other dividing mode, for example multiple units or assembly can in conjunction with or be desirably integrated into another
System, or some features can ignore, or do not execute.Another, shown or discussed each other
Coupling direct-coupling or communication connection can be the INDIRECT COUPLING of device or unit by some interfaces
Or communication connection, can be electrical, mechanical or other forms.
The described unit illustrating as separating component can be or may not be physically separate, make
For the part that unit shows can be or may not be physical location, you can with positioned at a place,
Or can also be distributed on multiple NEs.Can select according to the actual needs part therein or
The whole unit of person is realizing the purpose of this embodiment scheme.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention,
Can also be that unit is individually physically present it is also possible to two or more units are integrated in a list
In unit.Above-mentioned integrated unit both can be to be realized in the form of hardware, it would however also be possible to employ software function list
The form of unit is realized.
One of ordinary skill in the art will appreciate that all or part step in the various methods of above-described embodiment
Suddenly the program that can be by complete come the hardware to instruct correlation, and this program can be stored in a computer can
Read in storage medium, storage medium can include：Read only memory (ROM, Read Only Memory),
Random access memory (RAM, Random Access Memory), disk or CD etc..
One of ordinary skill in the art will appreciate that realizing all or part of step in above-described embodiment method
The program that can be by completes come the hardware to instruct correlation, and described program can be stored in a kind of computer
In readable storage medium storing program for executing, storage medium mentioned above can be read only memory, disk or CD etc..
Above a kind of verification method recommended using social group provided by the present invention and system are entered
Go and be discussed in detail, for one of ordinary skill in the art, according to the thought of the embodiment of the present invention,
All will change in specific embodiment and range of application, in sum, this specification content should not
It is interpreted as limitation of the present invention.
Claims (12)
1. a kind of verification method recommended using social group is it is characterised in that include：
Obtain multiple social activity groups, wherein, the plurality of social activity group is respectively positioned under same social platform；
Obtain the first Interest Similarity of the plurality of social activity group；
Obtain at random the user of described social platform and form corresponding with described social activity group multiple with a group of planes
Group, described random group is corresponded with described social activity group；
Obtain the second Interest Similarity of the plurality of random group；
It is verified when described first Interest Similarity is more than the second Interest Similarity.
2. the verification method recommended using social group according to claim 1, its feature exists
In, described the first Interest Similarity obtaining the plurality of social activity group, including：
Obtain group's Interest Similarity of each social group；
Using the meansigma methodss of group's Interest Similarity of multiple social activity groups as the first Interest Similarity；
Described the second Interest Similarity obtaining the plurality of random group, including：
Obtain group's Interest Similarity of each random group；
Using the meansigma methodss of group's Interest Similarity of multiple random groups as the second Interest Similarity.
3. the verification method recommended using social group according to claim 2, its feature exists
In, the described group's Interest Similarity obtaining each social group, including：
N user in same social activity group is calculated in the way of combination of twoIndividual user interest
Similarity；
Will be describedThe meansigma methodss of individual user interest similarity are similar as group's interest of this social group
Degree；
The described group's Interest Similarity obtaining each random group, including：
N user in same random group is calculated in the way of combination of twoIndividual user interest
Similarity；
Will be describedThe meansigma methodss of individual user interest similarity are similar as group's interest of this random group
Degree.
4. the verification method recommended using social group according to claim 1, its feature exists
In described social activity group is QQ group, and described social platform is QQ chat application.
5. a kind of checking system recommended using social group is it is characterised in that include：
First acquisition unit, for obtaining multiple social activity groups, wherein, the equal position of the plurality of social activity group
Under same social platform；
Second acquisition unit, for obtaining the first Interest Similarity of the plurality of social activity group；
3rd acquiring unit, for the random user's composition obtaining described social platform and described social activity group
Corresponding multiple random group, described random group is corresponded with described social activity group；
4th acquiring unit, for obtaining the second Interest Similarity of the plurality of random group；
Decision unit, for being verified when described first Interest Similarity is more than the second Interest Similarity.
6. the checking system recommended using social group according to claim 5, its feature exists
It is additionally operable to obtain group's Interest Similarity of each social group in, described second acquisition unit and will be many
The meansigma methodss of group's Interest Similarity of individual social activity group are as the first Interest Similarity；
Described 4th acquiring unit is additionally operable to obtain group's Interest Similarity of each random group and will be many
The meansigma methodss of group's Interest Similarity of individual random group are as the second Interest Similarity.
7. the checking system recommended using social group according to claim 6, its feature exists
In described second acquisition unit is additionally operable to n user in same social activity group with the side of combination of two
Formula is calculatedIndividual user interest similarity and will be describedThe meansigma methodss of individual user interest similarity
Group's Interest Similarity as this social group；
Described 4th acquiring unit is additionally operable to n user in same random group with the side of combination of two
Formula is calculatedIndividual user interest similarity and will be describedThe meansigma methodss of individual user interest similarity
Group's Interest Similarity as this random group.
8. a kind of verification method recommended using social group is it is characterised in that include：
Build multiple users couple, the user of described user couple co-owns at least one social group；
Obtain first Interest Similarity of the plurality of user couple；
In the social platform that described social activity group is located, random acquisition user builds with described user to number
Identical random user pair；
Obtain the second Interest Similarity of multiple random users pair；
It is verified when the first Interest Similarity is more than the second Interest Similarity.
9. the verification method recommended using social group according to claim 8, its feature exists
In, described the first Interest Similarity obtaining the plurality of user couple, including：
Obtain the user interest similarity of each user couple；
Using the meansigma methodss of described user interest similarity as the first Interest Similarity；
Described the second Interest Similarity obtaining multiple random users pair, including：
Obtain the random user Interest Similarity of each random user pair；
Using the meansigma methodss of described random user Interest Similarity as the second Interest Similarity.
10. the verification method recommended using social group according to claim 8, its feature
It is, described social activity group is QQ group, and described social platform is QQ chat application.
A kind of 11. checking systems recommended using social group are it is characterised in that include：
First construction unit, for building multiple users couple, the user of described user couple co-owns at least
In one social group；
First acquisition unit, for obtaining first Interest Similarity of the plurality of user couple；
Second construction unit, for obtaining user's structure by random in the social platform at described social activity group place
Build with described user to number identical random user pair；
Second acquisition unit, for obtaining the second Interest Similarity of multiple random users pair；
Decision unit, for being verified when the first Interest Similarity is more than the second Interest Similarity.
12. checking systems recommended using social group according to claim 11, its feature
It is, described first acquisition unit obtains the user interest similarity of each user couple and by described user
The meansigma methodss of Interest Similarity are as the first Interest Similarity；
Described second acquisition unit obtains the random user Interest Similarity of each random user pair and incites somebody to action
The meansigma methodss of described random user Interest Similarity are as the second Interest Similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510493029.2A CN106469146A (en) | 2015-08-12 | 2015-08-12 | A kind of checking system recommended using social group and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510493029.2A CN106469146A (en) | 2015-08-12 | 2015-08-12 | A kind of checking system recommended using social group and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106469146A true CN106469146A (en) | 2017-03-01 |
Family
ID=58213440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510493029.2A Pending CN106469146A (en) | 2015-08-12 | 2015-08-12 | A kind of checking system recommended using social group and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106469146A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109547225A (en) * | 2018-10-30 | 2019-03-29 | 咪咕互动娱乐有限公司 | A kind of multiplexing method of group, device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090193015A1 (en) * | 2008-01-28 | 2009-07-30 | Samsung Electronics Co., Ltd. | Method and appartus for adaptively updating recommend user group |
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN102664744A (en) * | 2012-03-19 | 2012-09-12 | 西安电子科技大学 | Group-sending recommendation method in network message communication |
| CN103218366A (en) * | 2012-01-20 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and system for recommending download resources |
| CN104050258A (en) * | 2014-06-15 | 2014-09-17 | 中国传媒大学 | Group recommendation method based on interest groups |
-
2015
- 2015-08-12 CN CN201510493029.2A patent/CN106469146A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090193015A1 (en) * | 2008-01-28 | 2009-07-30 | Samsung Electronics Co., Ltd. | Method and appartus for adaptively updating recommend user group |
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN103218366A (en) * | 2012-01-20 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and system for recommending download resources |
| CN102664744A (en) * | 2012-03-19 | 2012-09-12 | 西安电子科技大学 | Group-sending recommendation method in network message communication |
| CN104050258A (en) * | 2014-06-15 | 2014-09-17 | 中国传媒大学 | Group recommendation method based on interest groups |
Non-Patent Citations (3)
| Title |
|---|
| LINAS BALTRUNAS ET AL: "Group Recommendations with Rank Aggregation and Collaborative Filtering", 《PROCEEDINGS OF THE FOURTH ACM CONFERENCE ON RECOMMENDER SYSTEMS》 * |
| SIHEM AMER-YAHIA ET AL: "Group Recommendation: Semantics and Efficiency", 《PROCEEDINGS OF THE VLDB ENDOWMENT》 * |
| TOON DE PESSEMIER ET AL: "Comparison of group recommendation algorithms", 《MULTIMEDIA TOOLS AND APPLICATIONS》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109547225A (en) * | 2018-10-30 | 2019-03-29 | 咪咕互动娱乐有限公司 | A kind of multiplexing method of group, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103514304B (en) | Project recommendation method and device | |
| Badri Satya et al. | Uncovering fake likers in online social networks | |
| CN106649540B (en) | Video recommendation method and system | |
| US20150370814A1 (en) | System and method for analyzing user device information | |
| Zeng et al. | Can dissimilar users contribute to accuracy and diversity of personalized recommendation? | |
| CN108520303A (en) | A kind of recommendation system building method and device | |
| Kaur et al. | Shilling attack models in recommender system | |
| Perera et al. | Topological structure of manufacturing industry supply chain networks | |
| CN105335409A (en) | Target user determination method and device and network server | |
| CA3034030A1 (en) | System and method for analyzing user device information | |
| CN110033097B (en) | Method and device for determining association relation between user and article based on multiple data fields | |
| CN105809275A (en) | Item scoring prediction method and apparatus | |
| CN104408640A (en) | Application software recommending method and apparatus | |
| CN104182544B (en) | The dimension method for decomposing and device of analytical database | |
| Borzymek et al. | Trust and distrust prediction in social network with combined graphical and review-based attributes | |
| CN112100221A (en) | Information recommendation method and device, recommendation server and storage medium | |
| CN106886559A (en) | The collaborative filtering method of good friend's feature and similar users feature is incorporated simultaneously | |
| Hajibagheri et al. | Social networks community detection using the shapley value | |
| Alshahrani et al. | Top-k influential users selection based on combined katz centrality and propagation probability | |
| Guo et al. | Safer: Social capital-based friend recommendation to defend against phishing attacks | |
| CN106469146A (en) | A kind of checking system recommended using social group and system | |
| CN106651564B (en) | Target client acquisition method and system | |
| CN105718573B (en) | A kind of concern relation for user interest is extracted and mask method | |
| Carvalho et al. | Generation of coalition structures to provide proper groups' formation in group recommender systems | |
| CN110490598A (en) | Method for detecting abnormality, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170301 |
|
| RJ01 | Rejection of invention patent application after publication |