CN108108419A - A kind of information recommendation method, device, equipment and medium - Google Patents
A kind of information recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN108108419A CN108108419A CN201711346196.XA CN201711346196A CN108108419A CN 108108419 A CN108108419 A CN 108108419A CN 201711346196 A CN201711346196 A CN 201711346196A CN 108108419 A CN108108419 A CN 108108419A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- relation
- users
- weak
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
Abstract
The embodiment of the invention discloses a kind of information recommendation method, device, equipment and media, are related to Internet communication technology field.This method includes：Behavioral data according to user clusters user；Based on the relation between cluster result and user, according to the information of a user in a classification, pair pass through same weak relational users indirect association with the user, and belong to the user of other classifications into the recommendation of row information, wherein weak relational users are the user there are relation at least two users to belong to a different category.The embodiment of the present invention provides a kind of information recommendation method, device, equipment and medium, and the recommendation of possible interested new category of interest content is carried out to user.
Description
Technical field
The present embodiments relate to Internet communication technology field more particularly to a kind of information recommendation method, device, equipment
And medium.
Background technology
Feed streams are recommended very fiery at present, are better understood from user demand, and it is feed stream exhibitions to recommend better information to user
Existing key, wherein feed are extended in RSS subscription for receiving the newer interface of the information source.It can be appreciated that
It is to meet the information outlets for wishing to be continuously obtained the format standard that oneself newer demand provides with some form.
The recommendation method of current feed streams, is normally based on user's history behavior and is recommended, if for example, before getting
User checks operation to what animation class interest content carried out, then can be based on animation class interest content afterwards and related letter is carried out to user
The recommendation of breath.
But the above-mentioned recommendation method based on user behavior, user can not be carried out may interested new interest class
The recommendation of other content.
The content of the invention
The embodiment of the present invention provides a kind of information recommendation method, device, equipment and medium, to carry out to feel emerging to user
The recommendation of the new category of interest content of interest.
In a first aspect, an embodiment of the present invention provides a kind of information recommendation method, this method includes：
Behavioral data according to user clusters user；
Based on the relation between cluster result and user, according to the information of a user in a classification, pair pass through with the user
Same weak relational users indirect association, and belong to the user of other classifications into the recommendation of row information, wherein weak relational users are
There are the users of relation at least two users that belong to a different category.
Further, based on the relation between cluster result and user, according to the information of a user in a classification, pair with
The user belongs to the user of other classifications into the recommendation of row information by same weak relational users indirect association, wherein weak
Relational users be at least two users to belong to a different category there are the user of relation before, further include：
Based on the behavioral data, at least one label of each user-association；
According to the similarity between at least one label of user-association, the relation between user is determined.
Further, based on the behavioral data, each at least one label of user-association is included：
The point of reading content is read according to user and/or comment operates, by the corresponding label of the reading content with it is described
User-association.
Further, the behavioral data according to user, which carries out user cluster, includes：
According at least one label of user-association, the user is clustered；Or
According to the weight of the relation between user, the user is clustered.
Further, based on the relation between cluster result and user, according to the information of a user in a classification, pair with should
User belongs to the user of other classifications into the recommendation of row information by same weak relational users indirect association, wherein weak pass
It is that user is the user there are relation at least two users to belong to a different category, including：
If the user is determined as weak relation and used by least two users of the user with belonging to a different category there are relation
Family；
Any user being connected with the weak relational users is determined as information source user；
By with the weak relational users there are in the user of relation, in addition to described information source user generic user
User as user to be recommended；
According to the information of described information source user, information recommendation is carried out to the user to be recommended.
Further, the weak relational users are there are relation at least two users to belong to a different category, and are located at
The user at the connection edge to cluster where the different classes of user.
Second aspect, the embodiment of the present invention additionally provide a kind of information recommending apparatus, which includes：
Cluster module clusters user for the behavioral data according to user；
Recommending module is right according to the information of a user in a classification for based on the relation between cluster result and user
With the user by same weak relational users indirect association, and belong to the user of other classifications into the recommendation of row information, wherein
Weak relational users are the user there are relation at least two users to belong to a different category.
Further, described information recommendation apparatus further includes：
Label determining module, for based on the relation between cluster result and user, according to a user in a classification
Information pair with the user by same weak relational users indirect association, and belongs to user's pushing away into row information of other classifications
Recommend, wherein weak relational users be at least two users to belong to a different category there are the user of relation before, based on the row
For data, at least one label of each user-association；
Relationship determination module for the similarity between at least one label according to user-association, is determined between user
Relation.
Further, recommending module includes：
Weak relation determination unit, if for a user and at least two users to belong to a different category there are relation, it will
The user is determined as weak relational users；
Information determination unit, for any user being connected with the weak relational users to be determined as information source user；
Determination unit to be recommended, for by with the weak relational users there are in the user of relation, except described information source
User beyond user generic user is as user to be recommended；
Information recommendation unit, for the information according to described information source user, to the user to be recommended into row information
Recommend.
The third aspect, the embodiment of the present invention additionally provide a kind of equipment, and the equipment includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes the information recommendation method as described in any in the embodiment of the present invention.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer readable storage medium, are stored thereon with computer
Program realizes the information recommendation method as described in any in the present invention implementation when program is executed by processor.
The embodiment of the present invention is based on weak relational users, by by weak relational users indirect association, and positioned at multiple classifications
In user between establish weak relation.The information for belonging to an a kind of other user that weak relation is connected, as possible interested
Information recommendation give, the user for belonging to other classifications of weak relation connection.User is obtained may be interested new
Classification information.
Description of the drawings
Fig. 1 is a kind of flow chart for information recommendation method that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart of information recommendation method provided by Embodiment 2 of the present invention；
Fig. 3 is the interest relation structure diagram between a kind of multiple users provided by Embodiment 2 of the present invention；
Fig. 4 is a kind of structure diagram for information recommending apparatus that the embodiment of the present invention three provides；
Fig. 5 is a kind of structure diagram for equipment that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrated only in description, attached drawing.
Embodiment one
Fig. 1 is a kind of flow chart for information recommendation method that the embodiment of the present invention one provides.The present embodiment is applicable to pair
User carries out the situation of information recommendation, is based especially in the recommendation of feed streams.This method can be by a kind of information recommending apparatus
It performs, which can be realized by the mode of software and/or hardware.Referring to Fig. 1, information recommendation method provided in this embodiment
Including：
S110, the behavioral data according to user cluster user.
User behavior data is determined by recommendation.Specifically, if recommendation is interest class related content, user's row
For that can be user to the point read operation of reading content and/or comment on operation；If recommendation is good friend, user behavior can be with
The interactive record between user good friend, for example, in wechat circle of friends user its good friend is delivered the reading of content, thumb up, reprint or
Comment operation；If recommendation is commodity, user behavior can be shopping record of user etc..
Optionally, user can be clustered based on the word frequency of keyword in user behavior data, such as can basis
The frequency that keyword basketball occurs in reading content in user's reading content judges whether that by the user's cluster be basketball classification
In.Wherein can the word in user behavior data or phrase be directly determined as keyword, by the sentence in user behavior data
Son or chapter are segmented and are removed stop words processing, to obtain the keyword of word or phrase granularity.
User can also be clustered based on the similarity of keyword in user behavior data, such as the row of the first user
Include for keyword in data：Basketball, NBA, Yao Ming, Bryant, amusement, keyword includes in the behavioral data of second user：Basket
Ball, NBA, Bryant, stock market, keyword includes in the behavioral data of the 3rd user：Amusement, craft, makeup, beauty.Because first
User's quantity identical with keyword in behavioral data in second user is more, with keyword phase in behavioral data in the 3rd user
Same negligible amounts, so gathering the first user and second user for one kind.
S120, based on the relation between cluster result and user, according to the information of a user in a classification, pair and the user
By same weak relational users indirect association, and belong to the user of other classifications into the recommendation of row information.
Wherein, weak relational users are the user there are relation at least two users to belong to a different category.
Specifically, if fourth user is connected with the 5th user, the 5th user is connected with the 6th user, and fourth user belongs to
The first kind in cluster result, the 6th user belong to the second class in cluster result, then the 5th user be weak relational users, the 4th
There are weak relations with the 6th user by user.By the keyword of the behavioral data according to fourth user, to the 6th user into row information
Recommend；Or the keyword of the behavioral data according to the 6th user, information recommendation is carried out to fourth user；Or using fourth user as
Friend relation that may be present recommends the 6th user；Or recommend the 4th using the 6th user as friend relation that may be present
User.
Optionally, the situation that weak relational users are connected with two users is described above.Next connected with weak relational users
There are three the situation of user, the situation that weak relational users are connected with multiple users illustrates.If fourth user, the 5th use
Family, the 6th with the 7th user with being connected per family, and fourth user and the 5th user belong to the first kind, and the 6th user belongs to the second class,
The 7th user is then determined as weak relational users, there are weak relation, the 5th users and the 6th between fourth user and the 6th user
There is also weak relations by user；According to the information of the 6th user to fourth user and the 5th user into the recommendation of row information；Or according to
The information of fourth user recommends the 6th user；Or the 6th user is recommended according to the information of the 5th user.
It is understood that cause it to same there are there are certain similitudes, this similitude between the user of weak relation
The interested possibility of one information is larger.Based on this delicate relation, information recommendation is carried out to the opposing party according to a wherein side,
It can achieve the effect that improve the accuracy rate recommended.
Wherein, the content of recommendation can be the recommendation based on interest class or the recommendation based on friend relation, also may be used
To be recommendation based on shopping class etc., the present embodiment can be applied to several scenes accordingly, and the present embodiment is to this and without limit
It is fixed.
By taking class of doing shopping is recommended as an example, user behavior data can be the shopping record of user, according to commodity in shopping record
Similarity user is clustered, and establish customer relationship；Weak relational users are determined according to cluster result and customer relationship, into
And determine that there are two users of weak relation；Give the commercial product recommending of wherein user purchase to another user.
The technical solution of the embodiment of the present invention, based on weak relational users, by being located at by weak relational users indirect association
Weak relation is established between user in multiple classifications.The information for belonging to an a kind of other user that weak relation is connected, as can
The interested information recommendation of energy is given, the user for belonging to other classifications of weak relation connection.User is obtained may sense
The information of the new classification of interest.
Further, need to establish the relation between user before this, the relation between user can be by same
Forwarding, reading or the comment of content determine；It can also directly be determined by friend relation.
Optionally, the relation between user can be determined according to the similarity of keyword in user behavior data.Specifically,
If there are same keyword between two users, for two users' opening relationships.The weight of relation is according to the number of same keyword
Amount determines.
Relation between user determines：
Based on the behavioral data, at least one label of each user-association；
According to the similarity between at least one label of user-association, the relation between user is determined.
Wherein, label can be determined directly by keyword in user behavior data, such as by above-mentioned keyword in user's row
It is more than the keyword of setting word frequency threshold value as label for the word frequency in data.Or using the classification of user's reading content as
Label, if such as reading content is the content of basketball subclass under Sport Class, closed basketball and/or physical culture as the user
The label of connection.The definite method of label is also many herein, and the present embodiment is to this without limiting.
Further, based on the behavioral data, each at least one label of user-association is included：
The point of reading content is read according to user and/or comment operates, by the corresponding label of the reading content with it is described
User-association.
Further, the behavioral data according to user, which carries out user cluster, includes：
According at least one label of user-association, the user is clustered；Or
According to the weight of the relation between user, the user is clustered.
Specifically, based on the relation between cluster result and user, according to the information of a user in a classification, pair with the use
Family belongs to the user of other classifications into the recommendation of row information by same weak relational users indirect association, wherein weak relation
User is the user there are relation at least two users to belong to a different category, including：
If the user is determined as weak relation and used by least two users of the user with belonging to a different category there are relation
Family；
Any user being connected with the weak relational users is determined as information source user；
By with the weak relational users there are in the user of relation, in addition to described information source user generic user
User as user to be recommended；
According to the information of described information source user, information recommendation is carried out to the user to be recommended.
It is significant to note that if the simple weak relation using whole, the quantity for causing weak relation is very big,
It is difficult to be utilized.Therefore, weak relational users are further defined to：The weak relational users be with belong to a different category at least two
A user is there are relation, and the user at the connection edge to cluster where the different classes of user.Wherein it is located at described
The connection edge that different classes of place clusters represents that there are the comparable inhomogeneity another characteristics of interest-degree by the user.
To be better understood from the connection edge to cluster, illustratively, if in the behavioral data of a user basketball word frequency
Much larger than the word frequency of table tennis, then the user will be clustered to the position from the centre distance relative close that clusters where basketball class；
If the word frequency of basketball and the word frequency of table tennis are suitable in the behavioral data of user, the user will be clustered to described in basketball class
Cluster and rattle the position for connecting edge that ball place clusters.
To user whether be located at the different classes of place cluster connection edge determination methods can there are many, example
Such as, if the word frequency in the associated multiple label words of a user behavior data there are at least two label words is located at setting word frequency model
It encloses, it is determined that the user is located at the connection edge to cluster belonging to above-mentioned at least two labels word.
Embodiment two
Fig. 2 is a kind of flow chart of information recommendation method provided by Embodiment 2 of the present invention.The present embodiment is in above-mentioned reality
On the basis of applying example, it is recommended as a kind of alternative of typical case scene with feed streams.It is provided in this embodiment referring to Fig. 2
Information recommendation method includes：
S210, in the case where feed reads situation, the point of reading content is read according to user and/or comment operates, is read described
Read the corresponding label of content and the user-association.
Specifically, can be operated according to the point read operation and comment of user, user is calculated for emerging under feed classification
Interesting degree, and the relatively interested feed classification of user is filtered out as label and the user-association.
S220, according to the similarity between at least one label of user-association, determine the relation and relation between user
Weight.
Wherein, by the relation between user, the interest relational graph of user can be constructed.
S230, the weight according to the relation between user, cluster the user.
Optionally, can be clustered according to the density of interest relation in the interest relational graph of user, it can also be according to emerging
The weight of interesting relation is clustered.
If S240, a user and at least two users that belong to a different category are there are relation, and there are interest-degrees by the user
The comparable inhomogeneity another characteristic (namely the connection edge to cluster where the different classes of user), then use this
Family is determined as weak relational users.
Wherein, there are the restrictions of the comparable inhomogeneity another characteristic of interest-degree by user so that weak relational users are energy
Enough users touched up to a variety of feed contents.
S250, any user being connected with the weak relational users is determined as information source user.
S260, by with the weak relational users there are in the user of relation, except described information source user generic is used
User beyond family is as user to be recommended.
S270, the information according to described information source user carry out information recommendation to the user to be recommended.
Wherein, the mode of specific information recommendation and content are not defined.
Illustratively, referring to Fig. 3, A, C, D, E, F and G represent different user respectively, and line is represented between user there are relation,
Numerical value on line represents the power of relation, can specifically be determined according to the similarity size between the label of user-association.If
Relation weight gathering for one kind more than 50, then A, B and C can gather for the first kind, D, E and G can gather for the second class.Because F connects
B and E are connected to, and B belongs to the first kind, E belongs to the second class, while F is located at the connection edge of above-mentioned two classification, then is determined as F
Weak relational users, there are weak relations between B and E.It, can be to wherein the opposing party into row information according to the information of either one in B and E
Recommendation.
Wherein, F is located at the connection edge of above-mentioned two classification, represent F have the first kind the first label and the second class the
Two labels, and the interest-degree of the first label is suitable with the interest-degree of the second label.Specific cluster principle can be according to actual needs
It is set, above are only citing, do not play any restriction effect.
The technical solution of the embodiment of the present invention, by by weak relational users be further defined to the weak relational users be with
At least two users to belong to a different category are located at the connection edge to cluster where the different classes of user there are relation
User.Then determined according to the weak relational users there are the user of weak relation, to carry out the recommendation of feed streams.Because by into one
Weak relation after the restriction of step has the comparable inhomogeneity another characteristic of interest-degree so that between its two users connected
Correlation degree it is stronger, so as to recommend accuracy rate higher.It solves the simple weak relation using whole simultaneously, will cause weak
The quantity of relation is very big, it is difficult to the problem of utilizing.
It should be noted that the technical teaching based on above-described embodiment, those skilled in the art have motivation by above-mentioned implementation
Mode is combined, to improve the recommendation of the accuracy rate and new category of interest content recommended user information.
Embodiment three
Fig. 4 is a kind of structure diagram for information recommending apparatus that the embodiment of the present invention three provides.Referring to Fig. 4, this implementation
The information recommending apparatus that example provides includes：Cluster module 10 and recommending module 20.
Wherein, cluster module 10 cluster user for the behavioral data according to user；
Recommending module 20, for based on the relation between cluster result and user, according to the information of a user in a classification,
Pair with the user by same weak relational users indirect association, and belong to the user of other classifications into the recommendation of row information,
In weak relational users be user at least two users to belong to a different category there are relation.
The technical solution of the embodiment of the present invention, based on weak relational users, by being located at by weak relational users indirect association
Weak relation is established between user in multiple classifications.The information for belonging to an a kind of other user that weak relation is connected, as can
The interested information recommendation of energy is given, the user for belonging to other classifications of weak relation connection.User is obtained may sense
The information of the new classification of interest.
Further, described information recommendation apparatus further includes：Label determining module and relationship determination module.
Wherein, label determining module, for based on the relation between cluster result and user, being used according in a classification one
The information at family pair with the user by same weak relational users indirect association, and belongs to the users of other classifications into row information
Recommendation, wherein weak relational users be at least two users to belong to a different category there are the user of relation before, based on institute
Behavioral data is stated, at least one label of each user-association；
Relationship determination module for the similarity between at least one label according to user-association, is determined between user
Relation.
Further, recommending module 20 includes：Weak relation determination unit, information determination unit, determination unit to be recommended and
Information recommendation unit.
Wherein, weak relation determination unit, if for a user and at least two users that belong to a different category there are relation,
The user is then determined as weak relational users；
Information determination unit, for any user being connected with the weak relational users to be determined as information source user；
Determination unit to be recommended, for by with the weak relational users there are in the user of relation, except described information source
User beyond user generic user is as user to be recommended；
Information recommendation unit, for the information according to described information source user, to the user to be recommended into row information
Recommend.
Further, label determining module includes：Tag determination unit.
Wherein, tag determination unit for reading and/or commenting on to operate to the point of reading content according to user, is read described
Read the corresponding label of content and the user-association.
Further, cluster module 10 is specifically used for：
According at least one label of user-association, the user is clustered；Or
According to the weight of the relation between user, the user is clustered.
Further, the weak relational users are there are relation at least two users to belong to a different category, and are located at
The user at the connection edge to cluster where the different classes of user.
Example IV
Fig. 5 is a kind of structure diagram for equipment that the embodiment of the present invention four provides.Fig. 5 shows to be used for realizing this
The block diagram of the example devices 12 of invention embodiment.The equipment 12 that Fig. 5 is shown is only an example, should not be to of the invention real
The function and use scope for applying example bring any restrictions.
As shown in figure 5, equipment 12 is showed in the form of universal computing device.The component of equipment 12 can include but unlimited
In：One or more processor or processing unit 16, system storage 28, connection different system component (are deposited including system
Reservoir 28 and processing unit 16) bus 18.
Bus 18 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Equipment 12 typically comprises various computing systems readable medium.These media can be it is any can be by equipment 12
The usable medium of access, including volatile and non-volatile medium, moveable and immovable medium.
System storage 28 can include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Equipment 12 may further include it is other it is removable/nonremovable,
Volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing irremovable
, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although not shown in Fig. 5, use can be provided
In to moving the disc driver of non-volatile magnetic disk (such as " floppy disk ") read-write and to moving anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 can include at least one program product,
The program product has one group of (for example, at least one) program module, these program modules are configured to perform each implementation of the invention
The function of example.
Program/utility 40 with one group of (at least one) program module 42 can be stored in such as memory 28
In, such program module 42 include but not limited to operating system, one or more application program, other program modules and
Program data may include the realization of network environment in each or certain combination in these examples.Program module 42 is usual
Perform the function and/or method in embodiment described in the invention.
Equipment 12 can also communicate with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.),
Can also be enabled a user to one or more equipment interacted with the equipment 12 communication and/or with enable the equipment 12 with
Any equipment (such as network interface card, modem etc.) communication that one or more of the other computing device communicates.It is this logical
Letter can be carried out by input/output (I/O) interface 22.Also, equipment 12 can also by network adapter 20 and one or
The multiple networks of person (such as LAN (LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown in the figure,
Network adapter 20 is communicated by bus 18 with other modules of equipment 12.It should be understood that it although not shown in the drawings, can combine
Equipment 12 uses other hardware and/or software module, includes but not limited to：Microcode, device driver, redundant processing unit,
External disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 is stored in program in system storage 28 by operation, so as to perform various functions application and
Data processing, such as realize the information recommendation method that the embodiment of the present invention is provided.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The information recommendation method as described in any in above-described embodiment is realized when program is executed by processor, this method includes：
Behavioral data according to user clusters user；
Based on the relation between cluster result and user, according to the information of a user in a classification, pair pass through with the user
Same weak relational users indirect association, and belong to the user of other classifications into the recommendation of row information, wherein weak relational users are
There are the users of relation at least two users that belong to a different category.
The arbitrary of one or more computer-readable media may be employed in the computer storage media of the embodiment of the present invention
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device or arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes：Tool
There are one or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or storing program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal,
Wherein carry computer-readable program code.Diversified forms may be employed in the data-signal of this propagation, including but it is unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium beyond storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
It can write to perform the computer that operates of the present invention with one or more programming languages or its combination
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully performs, partly perform on the user computer on the user computer, the software package independent as one performs, portion
Divide and partly perform or perform on a remote computer or server completely on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer or, it may be connected to outer computer (such as is carried using Internet service
Pass through Internet connection for business).
Note that it above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various apparent variations,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
It can include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (11)
1. a kind of information recommendation method, which is characterized in that including：
Behavioral data according to user clusters user；
Based on the relation between cluster result and user, according to the information of a user in a classification, pair pass through with the user same
Weak relational users indirect association, and belong to the user of other classifications into the recommendation of row information, wherein weak relational users are and category
In at least two different classes of users, there are the users of relation.
2. information recommendation method according to claim 1, which is characterized in that based on the pass between cluster result and user
System according to the information of a user in a classification, pair with the user by same weak relational users indirect association, and belongs to other
The user of classification into row information recommendation, wherein weak relational users are that there are relations at least two users that belong to a different category
User before, further include：
Based on the behavioral data, at least one label of each user-association；
According to the similarity between at least one label of user-association, the relation between user is determined.
3. information recommendation method according to claim 2, which is characterized in that based on the behavioral data, to each described
At least one label of user-association includes：
The point of reading content is read according to user and/or comment operates, by the corresponding label of the reading content and the user
Association.
4. information recommendation method according to claim 2, which is characterized in that the behavioral data according to user carries out user
Cluster includes：
According at least one label of user-association, the user is clustered；Or
According to the weight of the relation between user, the user is clustered.
5. information recommendation method according to claim 1, which is characterized in that based on the pass between cluster result and user
System according to the information of a user in a classification, pair with the user by same weak relational users indirect association, and belongs to other
The user of classification into row information recommendation, wherein weak relational users are that there are relations at least two users that belong to a different category
User, including：
If the user is determined as weak relational users by least two users of the user with belonging to a different category there are relation；
Any user being connected with the weak relational users is determined as information source user；
By with the weak relational users there are in the user of relation, the use in addition to described information source user generic user
Family is as user to be recommended；
According to the information of described information source user, information recommendation is carried out to the user to be recommended.
6. information recommendation method according to claim 1, which is characterized in that the weak relational users are with belonging to inhomogeneity
Other at least two user is there are relation, and the user at the connection edge to cluster where the different classes of user.
7. a kind of information recommending apparatus, which is characterized in that including：
Cluster module clusters user for the behavioral data according to user；
Recommending module, for based on the relation between cluster result and user, according to the information of a user in a classification, pair with should
User belongs to the user of other classifications into the recommendation of row information by same weak relational users indirect association, wherein weak pass
It is that user is the user there are relation at least two users to belong to a different category.
8. information recommending apparatus according to claim 7, which is characterized in that further include：
Label determining module, for based on the relation between cluster result and user, according to the information of a user in a classification,
Pair with the user by same weak relational users indirect association, and belong to the user of other classifications into the recommendation of row information,
In weak relational users be at least two users to belong to a different category there are the user of relation before, based on the behavior number
According to at least one label of each user-association；
Relationship determination module for the similarity between at least one label according to user-association, determines the pass between user
System.
9. information recommending apparatus according to claim 7, which is characterized in that recommending module includes：
Weak relation determination unit, if using this there are relation for a user and at least two users to belong to a different category
Family is determined as weak relational users；
Information determination unit, for any user being connected with the weak relational users to be determined as information source user；
Determination unit to be recommended, for by with the weak relational users there are in the user of relation, except described information source user
User beyond generic user is as user to be recommended；
For the information according to described information source user, information recommendation is carried out to the user to be recommended for information recommendation unit.
10. a kind of equipment, which is characterized in that the equipment includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now information recommendation method as described in any in claim 1-6.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The information recommendation method as described in any in claim 1-6 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711346196.XA CN108108419B (en) | 2017-12-15 | 2017-12-15 | Information recommendation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711346196.XA CN108108419B (en) | 2017-12-15 | 2017-12-15 | Information recommendation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108108419A true CN108108419A (en) | 2018-06-01 |
| CN108108419B CN108108419B (en) | 2021-01-26 |
Family
ID=62216135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711346196.XA Active CN108108419B (en) | 2017-12-15 | 2017-12-15 | Information recommendation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108108419B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109862069A (en) * | 2018-12-13 | 2019-06-07 | 百度在线网络技术（北京）有限公司 | Message treatment method and device |
| CN109886300A (en) * | 2019-01-17 | 2019-06-14 | 北京奇艺世纪科技有限公司 | A kind of user's clustering method, device and equipment |
| CN110866183A (en) * | 2019-11-06 | 2020-03-06 | 北京字节跳动网络技术有限公司 | Social interface recommendation method and device, electronic equipment and storage medium |
| CN112148984A (en) * | 2020-09-30 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for capturing instant interest of user |
| CN112711699A (en) * | 2019-10-24 | 2021-04-27 | 上海哔哩哔哩科技有限公司 | User division method, system, computer device and readable storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335363A (en) * | 2014-05-28 | 2016-02-17 | 华为技术有限公司 | Object pushing method and system |
| US20160163223A1 (en) * | 2014-11-20 | 2016-06-09 | Dharma Systems Inc. | System and method to enable pursuit of happiness |
| WO2016165058A1 (en) * | 2015-04-13 | 2016-10-20 | Hewlett-Packard Development Company,L.P. | Social prediction |
| CN106168953A (en) * | 2016-06-02 | 2016-11-30 | 中国人民解放军国防科学技术大学 | Blog article towards weak relation social networks recommends method |
| CN106228371A (en) * | 2016-07-18 | 2016-12-14 | 南京坦道信息科技有限公司 | A kind of social network analysis based on the ultra-large user associating frequency and associate index and family relation recognizer |
| CN107180073A (en) * | 2017-03-31 | 2017-09-19 | 百度在线网络技术（北京）有限公司 | POI recommends method, device, equipment and computer-readable recording medium |
| CN107220328A (en) * | 2017-05-23 | 2017-09-29 | 南京大学 | The video recommendation method of weak relation and strong relation based on social networks |
| CN107220902A (en) * | 2017-06-12 | 2017-09-29 | 东莞理工学院 | The cascade scale forecast method of online community network |
| CN107301181A (en) * | 2016-04-14 | 2017-10-27 | 腾讯科技（深圳）有限公司 | Account recommends method and device |
-
2017
- 2017-12-15 CN CN201711346196.XA patent/CN108108419B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335363A (en) * | 2014-05-28 | 2016-02-17 | 华为技术有限公司 | Object pushing method and system |
| US20160163223A1 (en) * | 2014-11-20 | 2016-06-09 | Dharma Systems Inc. | System and method to enable pursuit of happiness |
| WO2016165058A1 (en) * | 2015-04-13 | 2016-10-20 | Hewlett-Packard Development Company,L.P. | Social prediction |
| CN107301181A (en) * | 2016-04-14 | 2017-10-27 | 腾讯科技（深圳）有限公司 | Account recommends method and device |
| CN106168953A (en) * | 2016-06-02 | 2016-11-30 | 中国人民解放军国防科学技术大学 | Blog article towards weak relation social networks recommends method |
| CN106228371A (en) * | 2016-07-18 | 2016-12-14 | 南京坦道信息科技有限公司 | A kind of social network analysis based on the ultra-large user associating frequency and associate index and family relation recognizer |
| CN107180073A (en) * | 2017-03-31 | 2017-09-19 | 百度在线网络技术（北京）有限公司 | POI recommends method, device, equipment and computer-readable recording medium |
| CN107220328A (en) * | 2017-05-23 | 2017-09-29 | 南京大学 | The video recommendation method of weak relation and strong relation based on social networks |
| CN107220902A (en) * | 2017-06-12 | 2017-09-29 | 东莞理工学院 | The cascade scale forecast method of online community network |
Non-Patent Citations (3)
| Title |
|---|
| LANTIAN GUO 等: "Exploiting Fine-Grained Co-Authorship for Personalized Citation Recommendation", 《IEEE ACCESS》 * |
| 张秀举: "社交网络中的弱关系推荐方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈克寒 等: "基于用户聚类的异构社交网络推荐算法", 《计算机学报》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109862069A (en) * | 2018-12-13 | 2019-06-07 | 百度在线网络技术（北京）有限公司 | Message treatment method and device |
| CN109862069B (en) * | 2018-12-13 | 2020-06-09 | 百度在线网络技术（北京）有限公司 | Message processing method and device |
| CN109886300A (en) * | 2019-01-17 | 2019-06-14 | 北京奇艺世纪科技有限公司 | A kind of user's clustering method, device and equipment |
| CN112711699A (en) * | 2019-10-24 | 2021-04-27 | 上海哔哩哔哩科技有限公司 | User division method, system, computer device and readable storage medium |
| CN112711699B (en) * | 2019-10-24 | 2023-04-07 | 上海哔哩哔哩科技有限公司 | User division method, system, computer device and readable storage medium |
| CN110866183A (en) * | 2019-11-06 | 2020-03-06 | 北京字节跳动网络技术有限公司 | Social interface recommendation method and device, electronic equipment and storage medium |
| CN110866183B (en) * | 2019-11-06 | 2023-06-13 | 北京字节跳动网络技术有限公司 | Social interface recommendation method and device, electronic equipment and storage medium |
| CN112148984A (en) * | 2020-09-30 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for capturing instant interest of user |
| CN112148984B (en) * | 2020-09-30 | 2023-11-10 | 微梦创科网络科技（中国）有限公司 | Method and system for capturing instant interests of user |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108108419B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6711500B2 (en) | Voiceprint identification method and apparatus | |
| CN108108419A (en) | A kind of information recommendation method, device, equipment and medium | |
| US20190026367A1 (en) | Navigating video scenes using cognitive insights | |
| WO2017124116A1 (en) | Searching, supplementing and navigating media | |
| CN107995536A (en) | A kind of method, apparatus, equipment and computer-readable storage medium for extracting video preview | |
| CN108540826A (en) | Barrage method for pushing, device, electronic equipment and storage medium | |
| CN109710805A (en) | Video interactive method and device based on interest cluster | |
| US10097664B2 (en) | Recommending media items based on purchase history | |
| CN109348302A (en) | Connect wheat user recommended method, device, server and storage medium in live streaming | |
| CN105635519B (en) | Method for processing video frequency, apparatus and system | |
| CN109614625A (en) | Determination method, apparatus, equipment and the storage medium of the title text degree of correlation | |
| CN108363556A (en) | A kind of method and system based on voice Yu augmented reality environmental interaction | |
| US20180012237A1 (en) | Inferring user demographics through categorization of social media data | |
| CN107908641A (en) | A kind of method and system for obtaining picture labeled data | |
| CN109558513A (en) | A kind of content recommendation method, device, terminal and storage medium | |
| CN109101601A (en) | Using recommended method, device, mobile terminal and storage medium | |
| CN108289230A (en) | A kind of recommendation method, apparatus, equipment and the storage medium of TV shopping content | |
| CN108573393A (en) | Comment information processing method, device, server and storage medium | |
| US10397168B2 (en) | Confusion reduction in an online social network | |
| CN109815482A (en) | A kind of method, apparatus, equipment and the computer storage medium of news interaction | |
| CN109561212A (en) | A kind of merging method of release information, device, equipment and storage medium | |
| CN109670078A (en) | A kind of method, apparatus, equipment and the storage medium of determining video display sequence | |
| CN108235126A (en) | It is inserted into the method and apparatus of recommendation information in video | |
| CN109801104A (en) | A kind of advertising information methods of exhibiting of unaware | |
| CN108282534A (en) | Information-pushing method, device, electronic equipment and computer storage media |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |