CN109213933A - Content item recommendation method, apparatus, equipment and storage medium - Google Patents
Content item recommendation method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN109213933A CN109213933A CN201810932321.3A CN201810932321A CN109213933A CN 109213933 A CN109213933 A CN 109213933A CN 201810932321 A CN201810932321 A CN 201810932321A CN 109213933 A CN109213933 A CN 109213933A
- Authority
- CN
- China
- Prior art keywords
- content item
- collection
- content
- client
- item
- 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
Abstract
This application discloses a kind of content item recommendation method, apparatus, equipment and storage mediums, belong to Internet technical field.The described method includes: obtaining collection of content items, collection of content items includes at least one first content item；Obtain the local clicking rate of first content item in collection of content items, wherein, the local clicking rate of first content item is clicking rate of the client in the first client set to first content item, first client set includes n destination client, and destination client is to have carried out the client of object run to the second content item；It is ranked up according to the first content item in the local clicking rate collection of content items of first content item in collection of content items；According to the first content item that the sequencing that first content item in collection of content items arranges is in destination client recommended content items set.The accuracy of content item recommendation can be improved in technical solution provided by the embodiments of the present application.
Description
Technical field
This application involves Internet technical field, in particular to a kind of content item recommendation method, apparatus, equipment and storage are situated between
Matter.
Background technique
Currently, recommend suitable content item for user, allow the user to conveniently and efficiently to navigate to itself interested
The mode of content item is increasingly common in people's daily life, wherein content item can for video, news or
E-book etc..
In the related technology, the online time and click volume of the available content item of server, and according to the online time
Content item is ranked up with click volume, to extract newest most popular content item, then server can be newest by this
Most popular content item recommendation is to user.
Although these are newest most popular interior however, server can recommend newest most popular content item for user
Hold item to be but likely to not be content item interested to user, therefore, the accuracy of content item recommendation is poor in the related technology.
Summary of the invention
The embodiment of the present application provides a kind of content item recommendation method, apparatus, equipment and storage medium, can solve content
The poor problem of the accuracy that item is recommended.The technical solution is as follows:
On the one hand, a kind of content item recommendation method is provided, which comprises
Collection of content items is obtained, the collection of content items includes at least one first content item；
Obtain the local clicking rate of first content item described in the collection of content items, wherein the first content item
Local clicking rate is clicking rate of the client to the first content item in the first client set, the first client collection
Closing includes n destination client, and the destination client is to have carried out the client of object run, n to the second content item to be positive
Integer；
According to the local clicking rate of first content item described in the collection of content items to the institute in the collection of content items
First content item is stated to be ranked up；
The sequencing arranged according to first content item described in the collection of content items is destination client recommendation
The first content item in the collection of content items.
On the one hand, a kind of content item recommendation device is provided, described device includes:
First obtains module, and for obtaining collection of content items, the collection of content items includes at least one first content item；
Second obtains module, for obtaining the local clicking rate of first content item described in the collection of content items, wherein
The local clicking rate of the first content item is clicking rate of the client in the first client set to the first content item,
The first client set includes n destination client, and the destination client is to have carried out target behaviour to the second content item
The client of work, n are positive integer；
Sorting module, the local clicking rate for the first content item according to the collection of content items is to the content
The first content item in item set is ranked up；
Recommending module, the sequencing for the arrangement of the first content item according to the collection of content items are the mesh
Mark client recommends the first content item in the collection of content items.
On the one hand, a kind of server is provided, the server includes: processor and memory, is deposited in the memory
Contain at least one instruction；
Described instruction is loaded by the processor and is executed to realize content item recommendation method provided by the embodiments of the present application.
On the one hand, provide a kind of computer readable storage medium, be stored in the computer readable storage medium to
A few instruction；
Described instruction is loaded by processor and is executed to realize content item recommendation method provided by the embodiments of the present application.
Technical solution bring beneficial effect provided by the embodiments of the present application includes at least:
By obtaining collection of content items, and according to the local clicking rate of first content item in collection of content items to the content item
First content item in set is ranked up, and is then target according to the sequencing that first content item in collection of content items arranges
Client recommends the first content item in the collection of content items, wherein the local clicking rate of first content item is the first client
For client in set to the clicking rate of the first content item, which includes n to the progress of the second content item
The destination client of object run, since the clicking rate of content item can characterize user to the interested possibility of the content item
Property, therefore, similarly, the local clicking rate of first content item can characterize the corresponding user in destination client, that is to say to
The interested user of two content items, to the interested possibility of first content item, so, server is according to first content item
First content item in local clicking rate collection of content items is ranked up, and according to put in order for destination client recommend in
Hold the mode of the first content item in item set, it is ensured that the first content item that server recommends destination client is to the
The interested possible interested content item of user institute of two content items that is to say, the corresponding user institute in the destination client may
The accuracy recommended first content item thus can be improved in interested content item.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of schematic diagram of implementation environment provided by the embodiments of the present application.
Fig. 2 is a kind of flow chart of content item recommendation method provided by the embodiments of the present application.
Fig. 3 is a kind of flow chart of content item recommendation method provided by the embodiments of the present application.
Fig. 4 is a kind of schematic diagram of content item recommendation method provided by the embodiments of the present application.
Fig. 5 is a kind of schematic diagram of content item recommendation method provided by the embodiments of the present application.
Fig. 6 is a kind of schematic diagram at first content item interface provided by the embodiments of the present application.
Fig. 7 is a kind of schematic diagram at first content item interface provided by the embodiments of the present application.
Fig. 8 is a kind of schematic diagram at first content item interface provided by the embodiments of the present application.
Fig. 9 is a kind of schematic diagram at first content item interface provided by the embodiments of the present application.
Figure 10 is a kind of block diagram of content item recommendation device provided by the embodiments of the present application.
Figure 11 is a kind of structural schematic diagram of server provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with attached drawing to the application embodiment party
Formula is described in further detail.
In order to allow users to conveniently and efficiently navigate to itself interested content item, server usually can be according to one
The content that fixed Generalization bounds obtain a certain number of content items from the database of content items of self maintained, and will acquire
Item recommends user.Wherein, content item can be video, news or e-book etc..
By taking content item is short-sighted frequency as an example, server can safeguard short video database, can in the short video database
To be stored with a large amount of short-sighted frequency, server can obtain a fixed number from the short video database according to certain Generalization bounds
The short-sighted frequency of amount, and the short-sighted frequency acquired in display server in short video display interface, which are obtained short
Video recommendations are to user, to guarantee that user can conveniently and efficiently navigate to itself sense by browsing short video display interface
The short-sighted frequency of interest.Wherein, which can be the homepage of the short-sighted frequency broadcasting channel of video playing application, institute
It calls short-sighted frequency and refers to that video length is less than the video of a certain duration threshold value, for example, short-sighted frequency can be video length less than 10
The video of minute." video length " of a certain video refers to duration needed for completely playing the video, that is to say, the video
Start to the duration between ending.
In the related technology, each content item stored in the database of content items of the available self maintained of server it is upper
Line duration and click volume, and according to default rule, online time and click volume using content item are that content item is given a mark,
Then, server can obtain newest most popular content item, server according to the score of content item from database of content items
It can be by the newest most popular content item recommendation to user.
However, newest most popular content item is likely to not be the interested content item of user, therefore, the relevant technologies pair
The accuracy of content item recommendation is poor, this causes user to be difficult to navigate to itself interested content according to the recommendation of server
?.
The embodiment of the present application provides a kind of content item recommendation method, and the accuracy of content item recommendation can be improved, thus
It allows users to more easily navigate to itself interested content item according to the recommendation of server.In the content item recommendation method
In, the available collection of content items of server, and according to the local clicking rate of first content item in collection of content items to the content
First content item in item set is ranked up, and is then mesh according to the sequencing that first content item in collection of content items arranges
Mark client recommends the first content item in the collection of content items, wherein the local clicking rate of first content item is the first client
Client in the set of end to the clicking rate of the first content item, the first client set include n to the second content item into
The destination client of object run is gone, since the clicking rate of content item can characterize user to the interested possibility of the content item
Property, therefore, similarly, the local clicking rate of first content item can characterize the corresponding user in destination client, that is to say to
The interested user of two content items, to the interested possibility of first content item, so, server is according to first content item
First content item in local clicking rate collection of content items is ranked up, and according to put in order for destination client recommend in
Hold the mode of the first content item in item set, it is ensured that the first content item that server recommends destination client is to the
The interested possible interested content item of user institute of two content items that is to say, the corresponding user institute in the destination client may
The accuracy recommended first content item thus can be improved in interested content item.
In the following, by being illustrated to implementation environment involved by content item methods of exhibiting provided by the embodiments of the present application.
Fig. 1 is a kind of schematic diagram of implementation environment involved by content item methods of exhibiting provided by the embodiments of the present application,
As shown in Figure 1, the implementation environment may include that server 101 and at least one client 102 (illustrate only 5 clients in Fig. 1
End is 102).
Wherein, which may include destination client, which is to the second content item
The client of object run is carried out.Optionally, which can be clicking operation, browse operation or video playing behaviour
Make etc., when the second content item is video collection, which can be the behaviour played out to the video in video collection
Make.
As shown in Figure 1, server 101 can execute step S1, and in step sl, the available target visitor of server 101
The clicking rate of first content item (that is to say that the part of first content item in collection of content items is clicked in the collection of content items of family end
Rate), then, server 101 can execute step S2, and in step s 2, server 101 can be according in collection of content items first
First content item in the collection of content items is ranked up by the local clicking rate of content item, and then server 101 can execute
Step S3, in step s3, server 101 can recommend the first content item in collection of content items to mesh according to putting in order
It marks in client.
It should be noted that the server 101 in implementation environment shown in Fig. 1 can be a server, be also possible to by
The server cluster of multiple servers composition.
Referring to FIG. 2, it illustrates a kind of flow chart of content item recommendation method provided by the embodiments of the present application, the content
Item recommended method can be applied in server 101 shown in FIG. 1.As shown in Fig. 2, the content item recommendation method may include with
Lower step:
Step 201, server obtain collection of content items.
The collection of content items includes at least one first content item, the first content item for including in the collection of content items be to
The content item recommended.
The first content item that the collection of content items includes can be video, news or e-book etc..The application's
In one embodiment, the first content item which includes can be short-sighted frequency, when so-called short-sighted frequency refers to video
The long video less than the first duration threshold value, the first duration threshold value can be set by technical staff, the embodiment of the present application pair
It is not specifically limited, and optionally, which can be 5 minutes or 10 minutes etc..
Step 202, server obtain the local clicking rate of first content item in collection of content items.
Optionally, in the available collection of content items of server each first content item local clicking rate, wherein first
The local clicking rate of content item refers to the client in the first client set to the clicking rate of the first content item.
The first client set may include n destination client, and n is positive integer, which is to second
Content item has carried out the client of object run.
The clicking rate of content item refers to the ratio of the click volume of the content item and the light exposure of the content item, so-called content
The click volume of item refers to the number clicked to certain content item, and the light exposure of so-called content item is referred to certain content
The corresponding number for showing link, picture, descriptive text etc. and showing user of item.
Optionally, which is also possible to video, news or e-book etc., and, second content item
Type can be identical with the type of first content item.For example, the second content item is also video if first content item is video,
If first content item is e-book, the second content item is also e-book.
In one embodiment of the application, which can be video collection, which may include
At least one long video, so-called long video refer to that video length is greater than the video of the second duration threshold value, the second duration threshold value
The first duration threshold value can be greater than, which can be set by technical staff, the embodiment of the present application to it not
It is specifically limited, optionally, which can be 30 minutes or 40 minutes etc..In the embodiment of the present application, institute
Calling video collection can be collection of TV plays, variety collection of drama, animation collection of drama or series of movies etc..
The object run may include clicking operation, browse operation or video play operation etc., optionally, in second
When appearance item is video collection, which may include the operation to the video playing in video collection more than target duration,
Further, which can be to be more than target to each of at least two videos in video collection video playing
The operation of duration, generically for, which can be chase after to video collection acute operation.It should be pointed out that
Goal duration can be set in advance by technical staff, and the embodiment of the present application is not specifically limited it.
In the local clicking rate collection of content items of step 203, server according to first content item in collection of content items
First content item is ranked up.
Optionally, server can be according to the local clicking rate of first content item each in collection of content items to the content item
First content item in set is ranked up.
Step 204, server are pushed away according to the sequencing that first content item in collection of content items arranges for destination client
Recommend the first content item in collection of content items.
Optionally, when first content item is short-sighted frequency, server can be according to first content item in collection of content items
Arrangement sequencing obtains a certain number of first content items from the collection of content items, and shows in short video display interface
The first content item got.
In conclusion content item recommendation method provided by the embodiments of the present application, by obtaining collection of content items, and according to interior
The local clicking rate for holding first content item in item set is ranked up the first content item in the collection of content items, then basis
The sequencing that first content item arranges in collection of content items is that the first content in the collection of content items is recommended in destination client
, wherein the local clicking rate of first content item is click of the client to the first content item in the first client set
Rate, which includes n and has carried out the destination client of object run to the second content item, due to content item
Clicking rate can characterize user to the interested possibility of the content item, therefore, similarly, the local clicking rate of first content item
The corresponding user in destination client can be characterized, that is to say to the interested user of the second content item, to the first content item sense
A possibility that interest, so, server is according to the first content item in the local clicking rate collection of content items of first content item
It is ranked up, and according to putting in order as the mode of the first content item in the recommended content items set of destination client, Ke Yibao
Card server recommend the first content item of destination client by the interested user of the second content item possibility it is interested
Content item that is to say that the corresponding possible interested content item of user institute in the destination client thus can be improved to first
The accuracy of content item recommendation.
Referring to FIG. 3, it illustrates a kind of flow chart of content item recommendation method provided by the embodiments of the present application, the content
Item recommended method can be applied in server 101 shown in FIG. 1.As shown in figure 3, the content item recommendation method may include with
Lower step:
Step 301, server obtain collection of content items.
As described above, database of content items can have been safeguarded in server, and in the embodiment of the present application, the content item data
At least one first content item is can store in library.
In one possible implementation, all stored in the available database of content items of server
One content item, all first content items constitute collection of content items described above.
In alternatively possible implementation, since the certain first content items stored in database of content items are users
A possibility that interested content item, is smaller, for example, the age interested possibility of first content item user more remote compared with
Small, the interested possibility of first content item user of clicking rate or the lower unexpected winner of click volume is lower.Therefore, after in order to reduce
The computational burden of server in continuous step, server can be lesser by the interested possibility of user from database of content items
First content item filters out, to obtain the higher a part of first content item of the interested possibility of user.Wherein, the user
The interested higher a part of first content item of possibility constitutes collection of content items described above.
For example, clicking rate in database of content items can be less than the first content item mistake of a certain clicking rate threshold value by server
It filters, to obtain a part of first content item that clicking rate is more than a certain clicking rate threshold value, which is more than certain point
A part of first content item for hitting rate threshold value constitutes the collection of content items；In another example server can be by content item data
The first content item that online time is greater than a certain duration threshold value in library filters out, to obtain online time less than a certain duration
A part of first content item of threshold value, a part of first content item which is less than a certain duration threshold value constitutes should
Collection of content items；In another example click volume in database of content items can be less than in the first of a certain click volume threshold value by server
Hold item to filter out, to obtain a part of first content item that click volume is more than a certain click volume threshold value, which is more than
A part of first content item of a certain click volume threshold value constitutes the collection of content items.
Step 302, server obtain the local clicking rate of first content item in collection of content items.
In the embodiment of the present application, the part of each first content item is clicked in the available collection of content items of server
Rate, as described above, the local clicking rate of first content item refer to the destination client in the first client set to this first
The clicking rate of content item.The first client set may include n destination client, be video collection in the second content item
When, which is the client to the video playing in video collection more than target duration, wherein in video collection
Video playing duration be more than that target duration illustrates that the destination client produces the video in video collection and chases after acute behavior,
Illustrate that the corresponding user in destination client is interested in the video collection.
In the following, the embodiment of the present application will obtain the skill of the local clicking rate of first content item in collection of content items to server
Art process is illustrated, wherein the technical process may comprise steps of:
A1, server obtain the first client set.
In the embodiment of the present application, all clients that server is serviced can form the second client set, should
Second client set may include multiple client, the multiple client that server can include from the second client set
Middle screening obtains destination client, and the destination client that screening is obtained forms the first client set, wherein target customer
End refers to having carried out the second content item the client of object run.
B1, server receive the exposure record that each destination client is sent in the first client set.
Wherein, the exposure describe the first content item in the collection of content items of destination client it is corresponding connection,
The number that picture or descriptive matter in which there are shown.It that is to say, which describes destination client collection of content items
In first content item light exposure.
C1, server receive the click record that each destination client is sent in the first client set.
Wherein, which describes time that the first content item in the collection of content items of destination client is clicked
Number, that is to say, which describes the click volume of the first content item in the collection of content items of destination client.
The exposure record that d1, server are sent according to destination client in the first client set calculates in collection of content items
The partial exposure amount of each first content item.
Wherein, the partial exposure amount of first content item refers to all targets in the first client set in collection of content items
Light exposure the sum of of the client to the first content item.
The click record that e1, server are sent according to destination client in the first client set calculates in collection of content items
The local click volume of each first content item.
Wherein, the local click volume of first content item refers to all targets in the first client set in collection of content items
Click volume the sum of of the client to the first content item.
F1, server calculate the local clicking rate of each first content item in collection of content items.
Wherein, local click volume and office of the local clicking rate of first content item for the first content item in collection of content items
The ratio of portion's light exposure.
As described above, the clicking rate of content item refers to the ratio of the click volume of the content item and the light exposure of the content item
Value, it follows that just illustrating that user after watching the content item, clicks the content item if the clicking rate of content item is higher
Possibility is higher, that is to say, that user is higher to the interested possibility of the content item；And if the clicking rate of content item is lower,
A possibility that just illustrating user after watching the content item, clicking the content item is lower.That is, user is to the content item
Interested possibility is lower.In other words, the clicking rate of content item can characterize user to the interested possibility of the content item
Property.
Therewith similarly, the local clicking rate of first content item can characterize the corresponding user in destination client (hereinafter referred to as
For target user) to the interested possibility of first content item, wherein since target user is carried out to the second content item
The user of object run, that is to say, which is to the interested user of the second content item, therefore, first content item
Local clicking rate can be characterized to the interested user of the second content item to the interested possibility of first content item.
For example, first content item is that short-sighted frequency " discriminates certain and passes the 20th collection flower if the second content item is video collection " discriminating certain biography "
Wadding ", target user is to have carried out the user of object run to video collection " discriminating certain biography ", wherein the object run can be pair
Video playing in video collection " discriminating certain biography " is more than the operation of target duration, that is to say, that target user is to video collection
" discriminating certain biography " interested user, then the local clicking rate of above-mentioned first content item, which can characterize, feels video collection " discriminating certain biography "
The user of interest is to short-sighted frequency " discriminate certain and pass the 20th collection titbit " interested possibility.
In following step, server can be according to the local clicking rate of first content item in the collection of content items
One content item is ranked up, and is that the first content item in the collection of content items is recommended in destination client according to ranking results,
It is equally to recommend the interested user of the second content item the first content item in the collection of content items.In this manner it is possible to
The accuracy that server recommends first content item is improved, to allow users to the more easily recommendation according to server
Navigate to itself interested first content item.
For example, may include 1000 destination clients in the first client set, wherein 200 destination clients pair
The displaying of short-sighted frequency " discriminate certain and pass the 20th collection titbit ", which links, to be shown, and, show that number is 1,100 destination clients
Short-sighted frequency " discriminate certain and pass the 20th collection titbit " is clicked, and, number of clicks is 2, " is discriminated by the short-sighted frequency is calculated
Certain passes the 20th collection titbit " local clicking rate be 50%, the local clicking rate of the short-sighted frequency " discriminate certain and pass the 20th collection titbit " can be with
It is the highest first content item of local clicking rate in first content item set, then in following step, server can be short by this
Video " discriminate certain and pass the 20th collection titbit " is recommended in the destination client for including in the first client set.
In other words, in following step, the embodiment of the present application can have same interest according to certain second content item
User in a part of user to the interested degree of first content item, to have the institute of same interest to second content item
There is user to recommend first content item.
In the embodiment of the present application, the first content item in collection of content items can be opposite at least one first label
It answers, which is used to describe the content of first content item, and the second content item can be corresponding at least one second label,
Second label is used to describe the content of the second content item.Optionally, at least one first label and at least one second mark
There are identical labels in label, and in other words, there are same or similar for the content of the content of the second content item and first content item
Part.
For example, first content item can be short-sighted frequency, which can be corresponding with 3 the first labels, this 3 first
Label is respectively " discriminating certain biography ", " Sun " and " titbit ", and the second content item can be video collection, which can be with 4
A second label is corresponding, which can be " discriminating certain biography ", " Sun ", " old to build certain " and " serious drama ", wherein this 3
There are identical label " discriminating certain biography " and " Suns " in a first label and 4 second labels.
There are the same or similar parts for the content and the content of first content item for guaranteeing the second content item, that is to say guarantee
There are identical labels at least one first label and at least one second label, and server can be made to first content item
Recommend more accurate.It certainly, in the embodiment of the present application, can also at least one first label and at least one second label
Identical label is not present, in this manner it is ensured that server is more diversified to the recommendation of first content item.
In the local clicking rate collection of content items of step 303, server according to first content item in collection of content items
First content item is ranked up.
In one possible implementation, server can be according to the sequence of local clicking rate from high to low to content item
First content item in set is ranked up.
However, in many cases, the local clicking rate of first content item can not sufficiently accurately reflect that target is used
Family is to the interested possibility of first content item.
For example, some first content item is more popular, all clients that server is serviced are to its clicking rate
50%, but the destination client in the first client set (that is to say the office of the first content item for 30% to its clicking rate
30%) portion's clicking rate is that in this case, although the local clicking rate of the first content item is higher, it is relative to clothes
All clients for being serviced of business device are smaller for the clicking rate of the first content item, this explanation, target user compared to
It is actually lesser to the interested possibility of first content item for general user, in this case, first content
The local clicking rate of item can not accurately reflect target user to the interested possibility of first content item.
In order to accurately characterize target user to the interested possibility of first content item, in alternatively possible reality
In existing mode, server can combine the local clicking rate of the global clicking rate of first content item and first content item pair
First content item in collection of content items is ranked up, wherein this implementation may comprise steps of:
A2, server obtain the second client set.
As described above, all clients that server is serviced can form the second client set, second visitor
Family end set may include multiple client.
B2, server receive the exposure record that each client is sent in the second client set.
Wherein, the exposure describe the corresponding displaying of the first content item in client collection of content items link,
The number that picture or descriptive matter in which there etc. are shown, that is to say, which describes in client collection of content items
First content item light exposure.
C2, server receive the click record that each client is sent in the second client set.
Wherein, which describes the number that the first content item in client collection of content items is clicked,
It that is to say, which describes the click volume of the first content item in client collection of content items.
The exposure record that d2, server are sent according to client in the second client set calculates each in collection of content items
The global light exposure of first content item.
Wherein, the global light exposure of certain first content item refers to all visitors in the second client set in collection of content items
Light exposure the sum of of the family end to the first content item.
The click record that e2, server are sent according to client in the second client set calculates each in collection of content items
The global click volume of first content item.
Wherein, the global click volume of certain first content item refers to all visitors in the second client set in collection of content items
Click volume the sum of of the family end to the first content item.
F2, server calculate the global clicking rate of each first content item in collection of content items.
Wherein, in collection of content items certain first content item global clicking rate be the first content item global click volume with
The ratio of global light exposure.In other words, the global clicking rate of first content item is the client pair in the second client set
The clicking rate of the first content item.
G2, server obtain the promotion degree of first content item in collection of content items.
The promotion degree of each first content item in the available collection of content items of server, wherein certain in collection of content items
The promotion degree of first content item refers to the local clicking rate of the first content item and the ratio of global clicking rate.
As shown in the above description, if the promotion degree of first content item is higher (for example, being greater than 1), illustrate target user's phase
It is higher to the interested possibility of first content item for general user, and if the promotion degree of first content item is lower
(for example, be equal to 1 or less than 1), then for illustrating target user compared to general user, to this first content item is interested can
Energy property is fair or lower.Therefore, the promotion degree of first content item can relatively accurately reflect target user to first content
The interested possibility of item.
H2, server are according to the first content item in the promotion degree collection of content items of first content item in collection of content items
It is ranked up.
In one possible implementation, server can be according to the sequence collection of content items of promotion degree from high to low
In first content item be ranked up.
However, in many cases, the promotion degree of first content item also can not sufficiently accurately reflect target user couple
The interested possibility of first content item.
For example, if certain first content item more unexpected winner, server are not recommended always destination client, then, mesh
Marking client will be smaller to the light exposure of the first content item.In this case, even if destination client is to this in first
Hold item click volume it is smaller, the local clicking rate of the first content item be also likely to it is higher, at this point, the promotion of the first content item
Degree is just higher, however, target user is smaller to the interested possibility of first content item.
In order to more accurately characterize target user to the interested possibility of first content item, alternatively possible
In implementation, server can combine the promotion degree of the local click volume ratio of first content item and first content item
First content item in collection of content items is ranked up, wherein this implementation may comprise steps of:
H21, server obtain the local click volume of first content item in collection of content items.
The local click volume of each first content item in the available collection of content items of server.Wherein, the skill of step h21
Similarly, details are not described herein for the embodiment of the present application for the technical process of art process and step e1.
H22, server obtain the global click volume of first content item in collection of content items.
The global click volume of each first content item in the available collection of content items of server.Wherein, the skill of step h22
Similarly, details are not described herein for the embodiment of the present application for the technical process of art process and step e2.
H23, server obtain the local click volume ratio of first content item in collection of content items.
The local click volume ratio of each first content item in the available collection of content items of server, wherein content item
The local click volume ratio of certain first content item is the local click volume of the first content item and the ratio of global click volume in set
Value.
H24, server obtain the recommendation of first content item in collection of content items.
The recommendation of each first content item in the available collection of content items of server, wherein certain in collection of content items
The recommendation of first content item is the product of local the click volume ratio and promotion degree of the first content item.
When first content item more unexpected winner for target user, the local click volume of the first content item compared with
Small, therefore, the local click volume ratio of the first content item is also smaller, so the first content can be used in the embodiment of the present application
Local click volume ratio the promotion degree of the first content item is modified, enable the recommendation of first content item compared with
Adequately reflect target user to the interested possibility of first content item.
H25, server are ranked up according to the first content item in recommendation sequence collection of content items from high to low.
In order to make reader be readily appreciated that technical solution provided by the embodiments of the present application, in the following, the embodiment of the present application will combine
The technical process of first content item sequence in collection of content items is illustrated server by Fig. 4 and Fig. 5.
As shown in figure 4, the exposure record and click record of the available all clients itself serviced of server, and
Afterwards, server can be determined according to the click record for all clients that itself is serviced and be carried out to the video in video collection A
The client played, that is to say destination client, meanwhile, server can record from the exposure of all clients received
It is recorded with clicking the exposure record for extracting destination client in record and clicking, then, server can be according to target customer
The exposure at end records and clicks record and obtains short video collection B, the short-sighted frequency in the short video collection B it is corresponding at least one the
There is at least one identical label of the second label corresponding with video collection A in one label, server can be from target customer
Destination client is obtained to the light exposure and click of the short-sighted frequency in short video collection B in the exposure record and click record at end
Amount, server can calculate short-sighted frequency according to light exposure and click volume of the destination client to the short-sighted frequency in short video collection B
The promotion degree of short-sighted frequency and local click volume ratio in set B, and according to the promotion degree of short-sighted frequency and part in short video collection B
The product of click volume ratio is ranked up the short-sighted frequency in short video collection B, then, server can according to put in order by
Short video recommendations in short video collection B are to destination client.
As shown in figure 5, the exposure record and click record of the available all clients itself serviced of server, and
Afterwards, server can be determined according to the click record for all clients that itself is serviced and be carried out to the video in video collection A
The client played, that is to say destination client, meanwhile, server can record from the exposure of all clients received
It is recorded with clicking the exposure record for extracting destination client in record and clicking, then, server can be according to target customer
The exposure at end records and clicks record and obtains short video collection C, the short-sighted frequency in the short video collection C it is corresponding at least one the
At least one identical label of the second label corresponding with video collection A can be not present in one label, server can be from mesh
Mark the exposure record of client and clicking obtained in record destination client to the light exposure of the short-sighted frequency in short video collection C and
Click volume, server can calculate short according to light exposure and click volume of the destination client to the short-sighted frequency in short video collection C
The promotion degree of short-sighted frequency and local click volume ratio in video collection C, and according to the promotion degree of short-sighted frequency in short video collection C and
The product of local click volume ratio is ranked up the short-sighted frequency in short video collection C, and then, server can be suitable according to arranging
Sequence is by the short video recommendations in short video collection C to destination client.
Step 304, when receive destination client transmission first content item interface acquisition instruction when, server obtain
Preceding n first content item in collection of content items after being ranked up, n is positive integer.
In one embodiment of the application, when first content item is short-sighted frequency, which can be
Short video display interface, when entering the short video display interface, destination client can send acquisition instruction, clothes to server
Device be engaged in after receiving the acquisition instruction, n first content item before being obtained from the collection of content items after sequence, namely
It is n short-sighted frequencies before obtaining.
Step 305, server send the displaying link of the preceding n first content item to destination client.
Wherein, the preceding n first content item displaying link for for destination client in first content item interface into
Row is shown.
Fig. 6 to Fig. 9 is a kind of schematic diagram at illustrative first content item interface provided by the embodiments of the present application, this first
Content item interface is short video display interface, and as shown in Figures 6 to 9, short video display interface may include first content item
Show link L.
In conclusion content item recommendation method provided by the embodiments of the present application, by obtaining collection of content items, and according to interior
The local clicking rate for holding first content item in item set is ranked up the first content item in the collection of content items, then basis
The sequencing that first content item arranges in collection of content items is that the first content in the collection of content items is recommended in destination client
, wherein the local clicking rate of first content item is click of the client to the first content item in the first client set
Rate, which includes n and has carried out the destination client of object run to the second content item, due to content item
Clicking rate can characterize user to the interested possibility of the content item, therefore, similarly, the local clicking rate of first content item
The corresponding user in destination client can be characterized, that is to say to the interested user of the second content item, to the first content item sense
A possibility that interest, so, server is according to the first content item in the local clicking rate collection of content items of first content item
It is ranked up, and according to putting in order as the mode of the first content item in the recommended content items set of destination client, Ke Yibao
Card server recommend the first content item of destination client by the interested user of the second content item possibility it is interested
Content item that is to say that the corresponding possible interested content item of user institute in the destination client thus can be improved to first
The accuracy of content item recommendation.
Referring to FIG. 10, this is interior it illustrates a kind of block diagram of content item recommendation device 400 provided by the embodiments of the present application
Hold the server 101 that item recommendation apparatus 400 can be Fig. 1, also can be set in the server 101 of Fig. 1.As shown in Figure 10,
The content item recommendation device 400 may include: that the first acquisition module 401, second obtains module 402, sorting module 403 and recommends
Module 404.
The first acquisition module 401, for obtaining collection of content items, which includes at least one first content
?.
The second acquisition module 402, for obtaining the local clicking rate of first content item in the collection of content items, wherein
The local clicking rate of the first content item is client in the first client set to the clicking rate of the first content item, this
One client set includes n destination client, which is to have carried out the client of object run to the second content item
End, n is positive integer.
The sorting module 403, for according to the local clicking rate of first content item in the collection of content items to the content item
First content item in set is ranked up.
The recommending module 404, the sequencing for being arranged according to first content item in the collection of content items are the target
Client recommends the first content item in the collection of content items.
In one embodiment of the application, the sorting module 403, comprising:
First acquisition submodule, for obtaining the global clicking rate of first content item in the collection of content items, this is in first
Hold clicking rate of the global clicking rate of item for the client in the second client set to the first content item, first client
Set is the subset of the second client set；
Second acquisition submodule, for obtaining the promotion degree of first content item in the collection of content items, the first content item
Promotion degree be the local clicking rate of the first content item and the ratio of global clicking rate；
Sorting sub-module, for according to the promotion degree of first content item in the collection of content items in the collection of content items
First content item is ranked up.
In one embodiment of the application, which is used for: obtaining first content item in the collection of content items
Local click volume ratio, the local click volume ratio of the first content item is the local click volume of the first content item and global
The ratio of click volume, the local click volume of the first content item are the client in the first client set to the first content
The click volume of item, the global click volume of the first content item are the client in the second client set to the first content item
Click volume；The recommendation of first content item in the collection of content items is obtained, the recommendation of the first content item is this in first
Hold the product of local the click volume ratio and promotion degree of item；According to the sequence of recommendation from high to low in the collection of content items
First content item is ranked up.
In one embodiment of the application, the recommending module 404, for receiving the of destination client transmission
When the acquisition instruction at one content item interface, the preceding n first content item in the collection of content items after being ranked up is obtained, n is
Positive integer；The displaying link of the preceding n first content item, the displaying of the preceding n first content item are sent to the destination client
Link for the destination client in the first content item interface for being shown.
First content item and at least one the first label phase in one embodiment of the application, in the collection of content items
Corresponding, which is used to describe the content of the first content item, and second content item is opposite at least one second label
It answers, which is used to describe the content of second content item；At least one first label and at least one second mark
There are identical labels in label.
In one embodiment of the application, which is video of the video length less than the first duration threshold value,
Second content item is video collection, which includes the video that at least one video length is greater than the second duration threshold value,
The first duration threshold value is less than the second duration threshold value.
In one embodiment of the application, it is more than mesh which, which includes to the video playing in the video collection,
Mark the operation of duration.
In conclusion content item recommendation device provided by the embodiments of the present application, by obtaining collection of content items, and according to interior
The local clicking rate for holding first content item in item set is ranked up the first content item in the collection of content items, then basis
The sequencing that first content item arranges in collection of content items is that the first content in the collection of content items is recommended in destination client
, wherein the local clicking rate of first content item is click of the client to the first content item in the first client set
Rate, which includes n and has carried out the destination client of object run to the second content item, due to content item
Clicking rate can characterize user to the interested possibility of the content item, therefore, similarly, the local clicking rate of first content item
The corresponding user in destination client can be characterized, that is to say to the interested user of the second content item, to the first content item sense
A possibility that interest, so, server is according to the first content item in the local clicking rate collection of content items of first content item
It is ranked up, and according to putting in order as the mode of the first content item in the recommended content items set of destination client, Ke Yibao
Card server recommend the first content item of destination client by the interested user of the second content item possibility it is interested
Content item that is to say that the corresponding possible interested content item of user institute in the destination client thus can be improved to first
The accuracy of content item recommendation.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Figure 11 is a kind of structural schematic diagram of server shown according to an exemplary embodiment.The server 500 wraps
Include central processing unit (CPU) 501, the system including random access memory (RAM) 502 and read-only memory (ROM) 503 is deposited
Reservoir 504, and the system bus 505 of connection system storage 504 and central processing unit 501.The server 500 also wraps
The basic input/output (I/O system) 506 for helping that information is transmitted between each device in computer is included, and for depositing
Store up the mass-memory unit 507 of operating system 513, application program 514 and other program modules 515.
The basic input/output 506 includes display 508 for showing information and inputs letter for user
The input equipment 509 of such as mouse, keyboard etc of breath.Wherein the display 508 and input equipment 509 are all by being connected to
The input and output controller 510 of system bus 505 is connected to central processing unit 501.The basic input/output 506
Can also include input and output controller 510 with for receive and handle from keyboard, mouse or electronic touch pen etc. it is multiple its
The input of his equipment.Similarly, input and output controller 510 also provides output to display screen, printer or other kinds of defeated
Equipment out.
The mass-memory unit 507 is by being connected to the bulk memory controller (not shown) of system bus 505
It is connected to central processing unit 501.The mass-memory unit 507 and its associated computer-readable medium are server
500 provide non-volatile memories.That is, the mass-memory unit 507 may include such as hard disk or CD-ROM
The computer-readable medium (not shown) of driver etc.
Without loss of generality, the computer-readable medium may include computer storage media and communication media.Computer
Storage medium includes information such as computer readable instructions, data structure, program module or other data for storage
The volatile and non-volatile of any method or technique realization, removable and irremovable medium.Computer storage medium includes
RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storages its technologies, CD-ROM, DVD or other optical storages, tape
Box, tape, disk storage or other magnetic storage devices.Certainly, skilled person will appreciate that the computer storage medium
It is not limited to above-mentioned several.Above-mentioned system storage 504 and mass-memory unit 507 may be collectively referred to as memory.
According to the various embodiments of the application, the server 500 can also be arrived by network connections such as internets
Remote computer operation on network.Namely server 500 can be by the network interface that is connected on the system bus 505
Unit 511 is connected to network 512, in other words, Network Interface Unit 511 also can be used be connected to other kinds of network or
Remote computer system (not shown).
The memory further includes that one or more than one program, the one or more programs are stored in
In memory, central processing unit 501 is realized shown in each embodiment of the application by executing one or more programs
Content item recommendation method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory of instruction, above-metioned instruction can be executed as the processor of server to complete shown in each embodiment of the application
Content item recommendation method.For example, the non-transitorycomputer readable storage medium can be ROM, random access memory
(RAM), CD-ROM, tape, floppy disk and optical data storage devices etc..
Application embodiment additionally provides a kind of computer readable storage medium, which is non-volatile memories Jie
Matter is stored at least one instruction, at least one section of program, code set or instruction set in the storage medium, at least one instruction,
At least one section of program, the code set or the instruction set is loaded by processor and is executed to realize that the above embodiments of the present application such as provide
Content item recommendation method.
The embodiment of the present application also provides a kind of computer program product, it is stored with instruction in the computer program product,
When run on a computer, it enables a computer to execute the content item recommendation method that the above embodiments of the present application provide.
The embodiment of the present application also provides a kind of chip, which includes programmable logic circuit and/or program instruction, when
The chip is able to carry out the content item recommendation method of the above embodiments of the present application offer when running.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely the preferred embodiments of the application, not to limit the application, it is all in spirit herein and
Within principle, any modification, equivalent replacement, improvement and so on be should be included within the scope of protection of this application.
Claims (15)
1. a kind of content item recommendation method, which is characterized in that the described method includes:
Collection of content items is obtained, the collection of content items includes at least one first content item；
Obtain the local clicking rate of first content item described in the collection of content items, wherein the part of the first content item
Clicking rate is clicking rate of the client to the first content item in the first client set, the first client set packet
N destination client is included, the destination client is to have carried out the client of object run to the second content item, and n is positive integer；
According to the local clicking rate of first content item described in the collection of content items to described in the collection of content items
One content item is ranked up；
The sequencing arranged according to first content item described in the collection of content items is described in the destination client is recommended
The first content item in collection of content items.
2. the method according to claim 1, wherein the first content according to the collection of content items
The local clicking rate of item is ranked up the first content item in the collection of content items, comprising:
Obtain the global clicking rate of first content item described in the collection of content items, the global clicking rate of the first content item
It is the client in the second client set to the clicking rate of the first content item, the first client set is described
The subset of two client set；
Obtain the promotion degree of first content item described in the collection of content items, the promotion degree of the first content item is described the
The ratio of the local clicking rate of one content item and global clicking rate；
According to the promotion degree of first content item described in the collection of content items in described first in the collection of content items
Hold item to be ranked up.
3. according to the method described in claim 2, it is characterized in that, the first content according to the collection of content items
The promotion degree of item is ranked up the first content item in the collection of content items, comprising:
Obtain the local click volume ratio of first content item described in the collection of content items, the partial points of the first content item
The amount of hitting ratio is the local click volume of the first content item and the ratio of global click volume, the partial points of the first content item
The amount of hitting is client in the first client set to the click volume of the first content item, the first content item it is complete
Office's click volume is click volume of the client in the second client set to the first content item；
Obtain the recommendation of first content item described in the collection of content items, the recommendation of the first content item is described the
The product of local the click volume ratio and promotion degree of one content item；
The first content item in the collection of content items is ranked up according to the sequence of the recommendation from high to low.
4. method according to any one of claims 1 to 3, which is characterized in that the first content item in the collection of content items
Corresponding at least one first label, first label is used to describe the content of the first content item, in described second
Appearance item is corresponding at least one second label, and second label is used to describe the content of second content item；It is described extremely
There are identical labels in few first label and at least one described second label.
5. method according to any one of claims 1 to 3, which is characterized in that the first content item is less than for video length
The video of first duration threshold value, second content item are video collection, and the video collection includes at least one video length
Greater than the video of the second duration threshold value；
The first duration threshold value is less than the second duration threshold value.
6. according to the method described in claim 5, it is characterized in that, the object run includes to the view in the video collection
Frequency plays more than the operation of target duration.
7. method according to any one of claims 1 to 3, which is characterized in that described according to the collection of content items
The sequencing of first content item arrangement is that the first content item in the collection of content items is recommended in the destination client,
Include:
When receiving the acquisition instruction at the first content item interface that the destination client is sent, the institute after being ranked up is obtained
The preceding n first content item in collection of content items is stated, n is positive integer；
The displaying link of the preceding n first content item, the exhibition of the preceding n first content item are sent to the destination client
Show link for being shown in first content item interface for the destination client.
8. a kind of content item recommendation device, which is characterized in that described device includes:
First obtains module, and for obtaining collection of content items, the collection of content items includes at least one first content item；
Second obtains module, for obtaining the local clicking rate of first content item described in the collection of content items, wherein described
The local clicking rate of first content item is clicking rate of the client in the first client set to the first content item, described
First client set includes n destination client, and the destination client is to have carried out object run to the second content item
Client, n are positive integer；
Sorting module, the local clicking rate for the first content item according to the collection of content items is to the content item collection
The first content item in conjunction is ranked up；
Recommending module, the sequencing for the arrangement of the first content item according to the collection of content items are the target visitor
Recommend the first content item in the collection of content items in family end.
9. device according to claim 8, which is characterized in that the sorting module, comprising:
First acquisition submodule, for obtaining the global clicking rate of first content item described in the collection of content items, described
The global clicking rate of one content item is client in the second client set to the clicking rate of the first content item, described the
One client set is the subset of the second client set；
Second acquisition submodule, for obtaining the promotion degree of first content item described in the collection of content items, in described first
The promotion degree for holding item is the local clicking rate of the first content item and the ratio of global clicking rate；
Sorting sub-module, the promotion degree for the first content item according to the collection of content items is to the collection of content items
In the first content item be ranked up.
10. device according to claim 9, which is characterized in that the sorting sub-module is used for:
Obtain the local click volume ratio of first content item described in the collection of content items, the partial points of the first content item
The amount of hitting ratio is the local click volume of the first content item and the ratio of global click volume, the partial points of the first content item
The amount of hitting is client in the first client set to the click volume of the first content item, the first content item it is complete
Office's click volume is click volume of the client in the second client set to the first content item；
Obtain the recommendation of first content item described in the collection of content items, the recommendation of the first content item is described the
The product of local the click volume ratio and promotion degree of one content item；
The first content item in the collection of content items is ranked up according to the sequence of the recommendation from high to low.
11. according to any device of claim 8 to 10, which is characterized in that the first content in the collection of content items
Corresponding at least one first label, first label is for describing the content of the first content item, and described second
Content item is corresponding at least one second label, and second label is used to describe the content of second content item；It is described
There are identical labels at least one first label and at least one described second label.
12. according to any device of claim 8 to 10, which is characterized in that the first content item is that video length is small
In the video of the first duration threshold value, second content item is video collection, when the video collection includes at least one video
The long video for being greater than the second duration threshold value；
The first duration threshold value is less than the second duration threshold value.
13. device according to claim 12, which is characterized in that the object run includes in the video collection
Video playing is more than the operation of target duration.
14. a kind of server, which is characterized in that the server includes processor and memory, is stored in the memory
At least one instruction；
Described instruction is loaded by the processor and is executed to realize the content item recommendation side as described in claim 1 to 7 is any
Method.
15. a kind of computer readable storage medium, which is characterized in that be stored at least one in the computer readable storage medium
Item instruction；
Described instruction is loaded by processor and is executed to realize the content item recommendation method as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810932321.3A CN109213933B (en) | 2018-08-14 | 2018-08-14 | Content item recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810932321.3A CN109213933B (en) | 2018-08-14 | 2018-08-14 | Content item recommendation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109213933A true CN109213933A (en) | 2019-01-15 |
| CN109213933B CN109213933B (en) | 2023-03-21 |
Family
ID=64988319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810932321.3A Active CN109213933B (en) | 2018-08-14 | 2018-08-14 | Content item recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109213933B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767429A (en) * | 2020-06-29 | 2020-10-13 | 北京奇艺世纪科技有限公司 | Video recommendation method and device and electronic equipment |
| CN111858969A (en) * | 2019-04-29 | 2020-10-30 | 腾讯科技（深圳）有限公司 | Multimedia data recommendation method and device, computer equipment and storage medium |
| CN114398559A (en) * | 2022-03-24 | 2022-04-26 | 北京达佳互联信息技术有限公司 | Content item recommendation method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140006407A1 (en) * | 2012-06-29 | 2014-01-02 | Google Inc. | Content placement criteria expansion |
| CN105872629A (en) * | 2016-03-18 | 2016-08-17 | 合网络技术（北京）有限公司 | Content recommendation method, apparatus and system |
| CN108228784A (en) * | 2017-12-28 | 2018-06-29 | 暴风集团股份有限公司 | Video recommendation method and device, electronic equipment, storage medium, program |
-
2018
- 2018-08-14 CN CN201810932321.3A patent/CN109213933B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140006407A1 (en) * | 2012-06-29 | 2014-01-02 | Google Inc. | Content placement criteria expansion |
| CN105872629A (en) * | 2016-03-18 | 2016-08-17 | 合网络技术（北京）有限公司 | Content recommendation method, apparatus and system |
| CN108228784A (en) * | 2017-12-28 | 2018-06-29 | 暴风集团股份有限公司 | Video recommendation method and device, electronic equipment, storage medium, program |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858969A (en) * | 2019-04-29 | 2020-10-30 | 腾讯科技（深圳）有限公司 | Multimedia data recommendation method and device, computer equipment and storage medium |
| CN111858969B (en) * | 2019-04-29 | 2023-12-12 | 深圳市雅阅科技有限公司 | Multimedia data recommendation method, device, computer equipment and storage medium |
| CN111767429A (en) * | 2020-06-29 | 2020-10-13 | 北京奇艺世纪科技有限公司 | Video recommendation method and device and electronic equipment |
| CN111767429B (en) * | 2020-06-29 | 2023-06-02 | 北京奇艺世纪科技有限公司 | Video recommendation method and device and electronic equipment |
| CN114398559A (en) * | 2022-03-24 | 2022-04-26 | 北京达佳互联信息技术有限公司 | Content item recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109213933B (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Seaver | Captivating algorithms: Recommender systems as traps | |
| CN107888950B (en) | A kind of method and system for recommending video | |
| CN108197331B (en) | User interest exploration method and device | |
| US8489527B2 (en) | Method and apparatus for neuropsychological modeling of human experience and purchasing behavior | |
| US8869042B2 (en) | Recommendation engine | |
| US9141982B2 (en) | Method and apparatus for collaborative upload of content | |
| CN103747343B (en) | The method and apparatus that resource is recommended at times | |
| KR101471940B1 (en) | Apparatus, System, Method and Computer Readable Recording Media Storing the Program for Related Recommendation of TV Program Contents and Web Contents | |
| CN102630052B (en) | Real time streaming-oriented television program recommendation system | |
| Bright et al. | The life and death of political news: Measuring the impact of the audience agenda using online data | |
| US20090150786A1 (en) | Media content tagging on a social network | |
| US20130080565A1 (en) | Method and apparatus for collaborative upload of content | |
| CN107980129A (en) | Global commending system for overlapping media catalog | |
| CN106131703A (en) | A kind of method of video recommendations and terminal | |
| CN106294830A (en) | The recommendation method and device of multimedia resource | |
| CN108260008A (en) | A kind of video recommendation method, device and electronic equipment | |
| CN109213933A (en) | Content item recommendation method, apparatus, equipment and storage medium | |
| CN108307239A (en) | A kind of video content recommendation method and apparatus | |
| US20150073940A1 (en) | System and method for online shopping from social media and do-it-yourself (diy) video files | |
| CN105302880A (en) | Content correlation recommendation method and apparatus | |
| CN106792172A (en) | A kind of method of internet television personalized recommendation video | |
| Antelmi et al. | Understanding user engagement with entertainment media: A case study of the twitter behaviour of game of thrones (got) fans | |
| WO2012146627A1 (en) | Method and apparatus for collaborative upload of content | |
| CN110020108A (en) | Network resource recommended method, device, computer equipment and storage medium | |
| CN107341172B (en) | Video profit calculation modeling device and method and video recommendation device and method |
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 |