CN105279204B - Information-pushing method and device - Google Patents
Information-pushing method and device Download PDFInfo
- Publication number
- CN105279204B CN105279204B CN201410360003.6A CN201410360003A CN105279204B CN 105279204 B CN105279204 B CN 105279204B CN 201410360003 A CN201410360003 A CN 201410360003A CN 105279204 B CN105279204 B CN 105279204B
- Authority
- CN
- China
- Prior art keywords
- content
- platform
- user
- similarity
- target
- 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.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This application discloses a kind of information-pushing methods, comprising: obtains the object content of the first platform, and obtains the seed user of the first platform according to object content；First behavioural information and at least one second behavioural information of the seed user on the first platform and at least one second platform are obtained respectively；Object content, which is obtained, according to seed user, the first behavioural information and at least one second behavioural information is associated with the first similarity between content at least one at least one second platform；And the target audience of object content is positioned according to the first similarity, and object content is pushed into target audience.The information-pushing method of the embodiment of the present application, it effectively utilizes and combines user on different platforms to the behavioral data of different content, cross-platform ground selection target audient is realized, in the case where Current Content and content platform few seed user, effectively expands target audience.Disclosed herein as well is a kind of information push-delivery apparatus.
Description
Technical field
This application involves technical field of electronic commerce more particularly to a kind of information-pushing methods and device.
Background technique
E-commerce in recent years has obtained swift and violent development, and advertisement is also obtained as the main profit model of e-commerce
Development at full speed；And wherein, the displaying advertisement accounting of no user's direct action expression also accounts for significant proportion, and this ratio
Continue the growth of holding high speed.For showing the advertiser of advertisement, how preferably to find the potentially possible of oneself accurately and bring
The user of conversion (such as click or trade) reduces unnecessary advertising input to realize the maximization for launching effect,
With direct and important meaning.
General advertiser is commodity corresponding in sale advertising, in order to win more Sales Volume of Commodities or click；
Advertiser is often desirable to the advertising display by oneself of maximum possible to may be to its interested user (namely potential visitor
Family).If giving the showing advertisement of advertiser to all flows, obviously having most of flows is waste, this is not advertisement
It is main to want to see.For example, one is sold the advertiser of " female's one-piece dress ", he needs for the advertising display stream of each " female's one-piece dress "
Amount pay corresponding cost, so he can wish oneself " female's one-piece dress " showing advertisement to may to " female's one-piece dress " generate friendship
Easy user can only may generate the user of transaction without being presented to, in this way, he can be preferably flat in this advertisement to " mobile phone "
Development is gone down under platform.Certainly, the corresponding advertiser of different types of advertisement they wish positioning audience flow may also be complete
How difference for the different types of corresponding audience flow of advertisement master positioning brings challenge to an outstanding advertising platform.
Currently, positioning there are two ways to corresponding target audience is the most frequently used: being advertiser's exploitation one is advertising platform
The general interest classification of ascribed characteristics of population (such as gender, age, purchasing power) of customer flow etc. and user, advertising platform according to
The different ascribed characteristicses of population and interest classification of each advertiser's selection give its showing advertisement to regioselective customer flow.It is another
Kind be showed in user's set using existing advertising platform take selection and seed user (had with existing targeted advertisements click or
The user of person's trading activity) similar user, the similar behavior for referring to the user by recording under Current ad platform
Record calculate two users similarity (such as included angle cosine), and using the user high with seed user similarity as target by
Many users carry out advertisement promotion to target audience user later.
But the problem is that: the very big problem of above-mentioned first method is to be launched by advertiser's unrestricted choice oneself
Some fundamental types (user tag) of the user of advertisement, and these fundamental types launch advertiser the effect of advertisement, extensively
The user tag of dispensing can only be selected by staining effect according to prior artificial subjective judgement and after launching by accusing master, but this user
Label is often not have direct corresponding relationship with the advertising display effect of advertiser, and the target audience for leading to potential conversion is inaccurate
Really；Can only remove selection flow for above-mentioned second in the user for having advertising display under Current ad platform, this obviously excessively by
Limit, potentially easily generate transaction flow may significant portion being covered by Current ad platform, especially pair
In one newly advertising platform, this phenomenon is particularly acute, and has significant limitation.
Summary of the invention
The purpose of the application is intended to solve above-mentioned one of technical problem at least to a certain extent.
For this purpose, the purpose of the application is to propose a kind of information-pushing method.This method is effectively utilized and is combined
User realizes cross-platform ground selection target audient on different platforms to the behavioral data of different content, in current
Hold and the few seed user of content platform in the case where, effectively expand target audience.
Further object is to propose a kind of information push-delivery apparatus.
In order to achieve the above object, the information-pushing method that the application one side embodiment proposes, comprising: obtain the first platform
Object content, and obtain according to the object content seed user of first platform；The seed user is obtained respectively to exist
The first behavioural information and at least one second behavioural information on first platform and at least one second platform；According to described
Seed user, first behavioural information and at least one described second behavioural information obtain the object content and it is described at least
The first similarity between at least one association content on one the second platform；And institute is positioned according to first similarity
The target audience of object content is stated, and the object content is pushed into the target audience.
The information-pushing method of the embodiment of the present application can obtain the seed of the first platform according to the object content of the first platform
User, and according to the first behavioural information on the first platform of seed user, seed user, seed user at least one second
At least one second behavioural information on platform obtains in object content is associated with at least one at least one second platform
The first similarity between appearance, and pushed according to the target audience of the first similarity positioning object content, and by object content
To the target audience, effectively utilizes and combine user on different platforms to the behavioral data of different content, realize
Cross-platform ground selection target audient effectively expands in the case where Current Content and content platform few seed user
Target audience.
In order to achieve the above object, the information push-delivery apparatus that the application another aspect embodiment proposes, comprising: first obtains mould
Block for obtaining the object content of the first platform, and obtains according to the object content seed user of first platform；The
Two obtain module, for obtaining the first row of the seed user on first platform and at least one second platform respectively
For information and at least one second behavioural information；Third obtains module, for being believed according to the seed user, first behavior
Breath and at least one described second behavioural information obtain at least one on the object content and at least one described second platform
The first similarity between a association content；Locating module, for positioning the object content according to first similarity
Target audience；And pushing module, for the object content to be pushed to the target audience.
The information push-delivery apparatus of the embodiment of the present application can obtain the seed of the first platform according to the object content of the first platform
User, and according to the first behavioural information on the first platform of seed user, seed user, seed user at least one second
At least one second behavioural information on platform obtains in object content is associated with at least one at least one second platform
The first similarity between appearance, and pushed according to the target audience of the first similarity positioning object content, and by object content
To the target audience, effectively utilizes and combine user on different platforms to the behavioral data of different content, realize
Cross-platform ground selection target audient effectively expands in the case where Current Content and content platform few seed user
Target audience.
The additional aspect of the application and advantage will be set forth in part in the description, and will partially become from the following description
It obtains obviously, or recognized by the practice of the application.
Detailed description of the invention
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, wherein
Fig. 1 is the flow chart according to the information-pushing method of the application one embodiment；
Fig. 2 is the flow chart according to the information-pushing method of the application another embodiment；
Fig. 3 is the flow chart according to the information-pushing method of the application another embodiment；
Fig. 4 is the structural schematic diagram according to the information push-delivery apparatus of the application one embodiment；
Fig. 5 is the structural schematic diagram according to the information push-delivery apparatus of the application another embodiment；
Fig. 6 is the structural schematic diagram according to the information push-delivery apparatus of the application another embodiment.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.
Currently, for the displaying content platform (such as advertising platform) newly risen for one, or the displaying new for one
For content (as shown advertisement) is promoted, obtained advertising display performance data are a small amount of, and for advertisement reaction table
The flow of existing positive (for example generating click) or user are even more few；It wherein, can be by these reacting its advertisement on a small quantity
The user of the flow of performance positive (generating click) is known as the target audience of the advertisement.Obviously, if target audience is too small,
It is just unable to satisfy the flow demand that advertiser launches advertisement, the target of advertiser is by the showing advertisement of oneself to a large amount of and right
Its advertisement has the user of positive performance (such as click, trade).A small amount of existing target audience how is effectively utilized, goes to navigate to
Bigger potentially possible generation clicks the user of even transaction to expand target audience's set and be a problem to be solved.
For this purpose, present applicant proposes a kind of information-pushing method and devices.Specifically, it below with reference to the accompanying drawings describes according to this
Apply for the information-pushing method and device of embodiment.
Fig. 1 is the flow chart according to the information-pushing method of the application one embodiment.As shown in Figure 1, the information pushes
Method may comprise steps of:
S101 obtains the object content of the first platform, and the seed user of the first platform is obtained according to object content.Its
In, in embodiments herein, seed user can be regarded as having on Current Content platform (such as advertising platform) and click very
To the target audience of transaction.
For example, by taking object content is targeted advertisements, platform is advertising platform as an example, the mesh of advertiser's dispensing can be passed through
Mark advertisement with positioning advertising Current ad release platform seed user, will such as be clicked under Current ad platform (or
It is transformed) specify seed user of the user (viewer) of targeted advertisements as the affiliated advertiser of targeted advertisements.It can be seen that kind
For child user is compared to other users, there is higher clicking rate (even conversion ratio) to the advertisement of advertiser.For example, advertisement
Advertisement f1, f2 that main A is launched on Current ad platform ... fk, consumer a, b click f1, and consumer c, d click f2,
Consumer e clicks fk, then a and b is the seed user of the advertisement f1 of A, and the seed user for the advertisement f2 that c and d are A, e is A's
The seed user of advertisement fk.
S102 obtains first behavioural information of the seed user on the first platform and at least one second platform and extremely respectively
Few second behavioural information.Wherein, in embodiments herein, the first behavioural information and the second behavioural information can wrap respectively
Include one of the number of click, the number of transaction, the time of click and time of transaction etc. or a variety of.
Specifically, the behavioural information that seed user is clicked or converts the content on the first platform can be obtained, for example, seed
User a has clicked on the number of content f1, f2 on the first platform and/or has clicked the time, and it is flat that seed user b clicks first
Content fk and/or click time on platform etc.；Meanwhile it can also obtain seed user and click or convert at least one second platform
On content behavioural information, for example, seed user a clicks content o1, o2 on the second platform and/or clicks the time, kind
Child user b clicks the content o3 on the second platform and/or clicks the time, and seed user d, e click interior on the second platform
Hold o4 and/or click the time etc..
S103, according to seed user, the first behavioural information and at least one second behavioural information acquisition object content and extremely
The first similarity between at least one association content on few second platform.Wherein, in embodiments herein, until
Few association content can be the content that seed user is clicked and/or traded at least one second platform.
Specifically, click and/or trading activity of the object content on the first platform, and kind can be directed to by seed user
Child user at least one association content corresponding to the click and/or the behaviors such as transaction on the second platform, establishes object content
The first similarity being associated between content at least one, that is, establish the similarity between cross-platform content.
S104, the target audience of object content is positioned according to the first similarity, and object content is pushed to target audience.
Specifically, can according to the first similarity between cross-platform content, by with high other of object content similarity
Content on platform, and will be to the crowd for having positive performance (such as clicking, transaction) in indirect target as indirect target content
Multi-user gathers as indirect target audient, can select most possible mesh of clicking or trade from indirect target audient set later
Object content, can be pushed to the target audience by the target audience for marking content in this way；Wherein, other described platform differences are in described
First platform and second platform.
The information-pushing method of the embodiment of the present application can obtain the seed of the first platform according to the object content of the first platform
User, and according to the first behavioural information on the first platform of seed user, seed user, seed user at least one second
At least one second behavioural information on platform obtains in object content is associated with at least one at least one second platform
The first similarity between appearance, and pushed according to the target audience of the first similarity positioning object content, and by object content
To the target audience, effectively utilizes and combine user on different platforms to the behavioral data of different content, realize
Cross-platform ground selection target audient effectively expands in the case where Current Content and content platform few seed user
Target audience.
Fig. 2 is the flow chart according to the information-pushing method of the application another embodiment.As shown in Fig. 2, the information pushes away
Delivery method may include:
S201 obtains the object content of the first platform, and the seed user of the first platform is obtained according to object content.
S202 obtains first behavioural information of the seed user on the first platform and at least one second platform and extremely respectively
Few second behavioural information.
S203 establishes user-content square according to seed user, the first behavioural information and at least one second behavioural information
Battle array, wherein user-content matrix includes the corresponding relationship between seed user, object content and at least one association content.
It specifically, can be for the click or conversion of content of the seed user on the first platform and at least one second platform
Situation forms user-content matrix.It, can be according to kind for platform is advertising platform for example, using object content as targeted advertisements
Child user a, b, c, d, e respectively to Current ad platform advertisement f1, f2 ..., fk and other advertising platform advertisements o1, o2, o3,
The click of o4 or conversion situation form user-content matrix.Wherein, user-content matrix can carry out table by following matrix
Show:
Wherein, the W in matrix is contribution degree of the seed user to advertisement, is timely by the number of seed user click advertisement
Between come what is determined, if seed user a clicks targeted advertisements f1, then seed user a can be under to the contribution degree Waf1 of advertisement f1
Face formula (1) is calculated:
Waf1=cnt (a, f1)/(log (1+ | N (a) |)) (1)
Wherein, cnt (a, f1) is the number that seed user a clicks advertisement f1, and N (a) is the advertisement that seed user a was clicked
Sum.In addition, seed user a is also contemplated that time factor to the contribution degree Waf1 of advertisement f1, at this point, cnt (a, f1) is seed
User a clicks the time of advertisement f1, can be calculated by following formula (2):
Wherein, N indicates that seed user a clicks advertisement f1 in the time number of days of statistics and is total to n times；I is subscript, indicates the
I click；MDaysi indicates that seed user a i-th clicks number of days of the advertisement f1 apart from current time.
S204 obtains object content and at least one according to preset cosine angle similarity model and user-content matrix
The first similarity between at least one association content on a second platform.
Wherein, in embodiments herein, preset cosine angle similarity model are as follows:
Wherein, f is object content, and U (f) is the user's set for clicking f, o be at least one second platform at least
One association content, U (o) are the user's set for clicking o, WaContribution for user a to the user a each content clicked
Degree, similar to user a to the contribution degree of advertisement f, WaIt can be calculated by following formula:
Wa=1/ (log (1+ | N (a) |)) (4).
For example, the first phase between object content and other content of platform can be calculated according to user-content matrix and formula (3)
Like degree, that is, calculate the similarity between f and o.In this way by common click user (i.e. U (f) ∩ U (o)), establish entirely different
Similarity between the content of platform.Wherein, for each object content f, itself and another platform can be calculated by formula (3)
The first similarity between upper content o.
S205, the target audience of object content is positioned according to the first similarity, and object content is pushed to target audience.
The information-pushing method of the embodiment of the present application, can according to seed user, the first behavioural information and at least one second
Behavioural information establishes user-content matrix, and obtains mesh according to preset cosine angle similarity model and user-content matrix
It marks content and is associated with the first similarity between content at least one at least one second platform, that is, pass through common click
User can position object content according to the first similarity later with the similarity between the content established on entirely different platform
Target audience improves the accuracy of target audience's positioning.
Fig. 3 is the flow chart according to the information-pushing method of the application another embodiment.As shown in figure 3, the information pushes away
Delivery method may include:
S301 obtains the object content of the first platform, and the seed user of the first platform is obtained according to object content.
S302 obtains first behavioural information of the seed user on the first platform and at least one second platform and extremely respectively
Few second behavioural information.
S303 establishes user-content square according to seed user, the first behavioural information and at least one second behavioural information
Battle array, wherein user-content matrix includes the corresponding relationship between seed user, object content and at least one association content.
S304 obtains object content and at least one according to preset cosine angle similarity model and user-content matrix
The first similarity between at least one association content on a second platform.
S305 determines at least one indirect target at least one second platform according to the first similarity and object content
Content.
Specifically, the determination of the first similarity and the object content that can be associated with by object content at least one between content
At least one association content at least one similar second platform is as indirect target content.It should be appreciated that indirect target
Content can be to be associated with content on other platforms high with object content similarity.
S306 obtains the corresponding indirect target audient of at least one indirect target content, and according to indirect target audient, extremely
A few indirect target content and preset user calculate indirect target audient and at least one to the fancy grade model of content
The second similarity between indirect target content.
Wherein, in embodiments herein, fancy grade model of the preset user to content are as follows:
Wherein, t is the number of days for the time gap present time that user x click on content o occurs, and W (t) is user x in distance
The number of click on content o when t days current.
For example, the corresponding indirect target audient of at least one indirect target content can first be obtained, can at least one
It is clicked on two platforms or the user x of transformed indirect target content o will be candidate (i.e. indirect target audient) as target audience.
Later, the second similarity between indirect target audient x and indirect target content o can be calculated according to above-mentioned formula (5).
S307, the target audience of object content is determined according to the first similarity and the second similarity, and object content is pushed away
It send to target audience.
Specifically, can be similar to indirect target audient's according to the first similarity and the second similarity calculation object content
Degree.If the similarity of object content and indirect target audient are greater than preset threshold, it can determine that indirect target audient is target
The target audience of content, and object content can be pushed to the target audience.
For example, the first similarity and the indirect target audient between content can be associated with according to object content at least one
With the second similarity between at least one indirect target content, come determine current platform object content audient, Ji Ketong
Cross the similarity of formula (6) Lai Jianli object content f and indirect target audient x below:
Score (f, x)=sim (f, o) * Score (o, x) (6)
Wherein it is possible to understand, indirect target audient x was not clicked directly on or transformed object content f.
In this way, can get similar between each object content and all users for having interbehavior on another platform
Degree, for example, the similarity of the content o on object content f and other platforms is 0.5, indirect target audient x and content o have directly
Interbehavior and similarity are 0.3, then can be calculated object content f's and indirect target audient x by above-mentioned formula (6)
Similarity is 0.15.Later, it can be ranked up by similarity, be more than the user of some given threshold as in target using similarity
The target audience of appearance, and object content is pushed into these target audiences.Efficiently utilize as a result, the users of other platforms with
The interbehavior of advertisement expands audient's range of targeted advertisements dispensing significantly, and obtains than random dispensing and preferably launch effect
Fruit；Moreover, advertiser can also select to determine similar between dispensing advertisement and target audience according to the dispensing budget of oneself
Threshold value is spent, effectively to control dispensing range.
The information-pushing method of the embodiment of the present application, can be determined according to the first similarity and object content at least one second
At least one indirect target content on platform, can obtain the corresponding indirect target audient of indirect target content later, and according to
Indirect target audient, indirect target content and preset user to the fancy grade model of content calculate indirect target audient and
Connect the second similarity between object content, finally, can be determined according to the first similarity and the second similarity object content and
The similarity between target audience is connect, it, can when the similarity between object content and indirect target audient is greater than preset threshold
It determines that indirect target audient is the target audience of object content, improves the accuracy of the audience selection of object content, thus
Improve the accuracy of information push.
In addition, the application also proposed a kind of information push-delivery apparatus.
Fig. 4 is the structural schematic diagram according to the information push-delivery apparatus of the application one embodiment.As shown in figure 4, the information
Driving means may include: that the first acquisition module 10, second obtains module 20, third obtains module 30, locating module 40 and pushes away
Send module 50.
Specifically, the first acquisition module 10 can be used for obtaining the object content of the first platform, and be obtained according to object content
The seed user of first platform.Wherein, in embodiments herein, seed user can be regarded as Current Content platform (such as
Advertising platform) on have click even transaction target audience.
For example, by taking object content is targeted advertisements, platform is advertising platform as an example, the first acquisition module 10 can pass through
Advertiser launch targeted advertisements with positioning advertising in the seed user of Current ad release platform, such as will be in Current ad platform
The lower seed use clicked (or transformed) and specify the user (viewer) of targeted advertisements as the affiliated advertiser of targeted advertisements
Family.It can be seen that thering is higher clicking rate (even to turn the advertisement of advertiser for seed user is compared to other users
Rate).For example, advertiser A launched on Current ad platform advertisement f1, f2 ... fk, consumer a, b click f1, disappear
Expense person c, d click f2, and consumer e clicks fk, then a and b is the seed user of the advertisement f1 of A, the advertisement f2 that c and d are A
Seed user, e are the seed user of the advertisement fk of A.
Second acquisition module 20 can be used for obtaining seed user respectively on the first platform and at least one second platform
First behavioural information and at least one second behavioural information.Wherein, in embodiments herein, the first behavioural information and second
Behavioural information can respectively include one of number, the number of transaction, the time of click and time of transaction for clicking etc. or more
Kind.
More specifically, the second acquisition module 20 can obtain the row that seed user is clicked or converts the content on the first platform
For information, for example, seed user a has clicked on the number of content f1, f2 on the first platform and/or has clicked time, seed
User b clicks content fk and/or click time on the first platform etc.；Meanwhile it can also obtain seed user and click or turn
Change the behavioural information of the content at least one second platform, for example, seed user a clicks other platform (i.e. the second advertisements
Platform) on content o1, o2 and/or click the time, when seed user b clicks content o3 on other platforms and/or clicks
Between, seed user d, e click the content o4 on other platforms and/or click the time etc..
Third, which obtains module 30, can be used for being obtained according to seed user, the first behavioural information and at least one second behavioural information
Object content is taken to be associated with the first similarity between content at least one at least one second platform.Wherein, in this Shen
In embodiment please, what at least one association content can be clicked and/or be traded at least one second platform for seed user
Content.
More specifically, third, which obtains module 30, to be directed to click of the object content on the first platform by seed user
And/or trading activity and seed user corresponding to the click and/or the behaviors such as transaction on the second platform at least one be associated with
Content is established the first similarity that object content is associated between content at least one, that is, is established between cross-platform content
Similarity.
Locating module 40 can be used for positioning the target audience of object content according to the first similarity.Pushing module 50 can be used for
Object content is pushed into target audience.More specifically, locating module 40 can according to the first similarity between cross-platform content,
Using the content on other platforms high with object content similarity as indirect target content, and will be to having in indirect target
Numerous users of forward direction performance (such as click, trade) gather as indirect target audient, can collect later from indirect target audient
The target audience of most possible click or transacting targeted content is selected in conjunction, such pushing module 50 can push to object content
The target audience.
Further, in one embodiment of the application, as shown in figure 5, it may include establishing that the third, which obtains module 30,
Unit 31 and acquiring unit 32.Establishing unit 31 can be used for according to seed user, the first behavioural information and at least one second row
User-content matrix is established for information, wherein user-content matrix includes that seed user, object content are associated with at least one
Corresponding relationship between content.Acquiring unit 32 can be used for according to preset cosine angle similarity model and user-content square
Battle array obtains object content and is associated with the first similarity between content at least one at least one second platform.
Wherein, in embodiments herein, preset cosine angle similarity model are as follows:
Wherein, f is object content, and U (f) is the user's set for clicking f, o be at least one second platform at least
One association content, U (o) are the user's set for clicking o, WaContribution for user a to the user a each content clicked
Degree.
It can be for content of the seed user on the first platform and at least one second platform more specifically, establishing unit 31
Click or conversion situation, form user-content matrix.For example, platform is that advertising platform is using object content as targeted advertisements
Example, can according to seed user a, b, c, d, e respectively to Current ad platform advertisement f1, f2 ..., fk and other advertising platforms it is wide
The click or conversion situation for accusing o1, o2, o3, o4 form user-content matrix.Wherein, user-content matrix can be by following
Matrix is indicated:
Wherein, the W in matrix is contribution degree of the seed user to advertisement, is timely by the number of seed user click advertisement
Between come what is determined, if seed user a clicks targeted advertisements f1, then seed user a can be under to the contribution degree Waf1 of advertisement f1
Face formula (1) is calculated:
Waf1=cnt (a, f1)/(log (1+ | N (a) |)) (1)
Wherein, cnt (a, f1) is the number that seed user a clicks advertisement f1, and N (a) is the advertisement that seed user a was clicked
Sum.In addition, seed user a is also contemplated that time factor to the contribution degree Waf1 of advertisement f1, at this point, cnt (a, f1) is seed
User a clicks the time of advertisement f1, can be calculated by following formula (2):
Wherein, N indicates that seed user a clicks advertisement f1 in the time number of days of statistics and is total to n times；I is subscript, indicates the
I click；MDaysi indicates that seed user a i-th clicks number of days of the advertisement f1 apart from current time.
Acquiring unit 32 can calculate between object content and other content of platform according to user-content matrix and formula (3)
First similarity calculates the similarity between f and o.In this way by common click user (i.e. U (f) ∩ U (o)), establish
Similarity between the content of full different platform.Wherein, for each object content f, can be calculated by formula (3) its with it is another
The first similarity on one platform between content o.The target audience that object content can be positioned according to the first similarity in this way, improves
The accuracy of target audience's positioning.
Further, in one embodiment of the application, as shown in fig. 6, the locating module 40 may include first determining
Unit 41, acquiring unit 42, computing unit 43 and the second determination unit 44.Specifically, the first determination unit 41 can be used for basis
First similarity and object content determine at least one indirect target content at least one second platform.Acquiring unit 42 can
For obtaining the corresponding indirect target audient of at least one indirect target content.Computing unit 43 can be used for according to indirect target by
Many, at least one indirect target content and preset user to the fancy grade model of content calculate indirect target audient at least
The second similarity between one indirect target content.Second determination unit 44 can be used for similar according to the first similarity and second
Spend the target audience for determining object content.
Wherein, in embodiments herein, fancy grade model of the preset user to content are as follows:
Wherein, t is the number of days for the time gap present time that user x click on content o occurs, and W (t) is user x in distance
The number of click on content o when t days current.
For example, what the first determination unit 41 can be associated between content by object content at least one is first similar
At least one on determining at least one second platform similar with object content of degree is associated with content as indirect target content.It answers
Work as understanding, indirect target content can be to be associated with content on other platforms high with object content similarity.Acquiring unit 42
The corresponding indirect target audient of at least one indirect target content can first be obtained, can be clicked at least one second platform or
The user x of the transformed indirect target content o of person will be candidate (i.e. indirect target audient) as target audience.Later, computing unit
43 can be calculated the second similarity between indirect target audient x and indirect target content o according to above-mentioned formula (5).
Second determination unit 44 can be specifically for according to the first similarity and the second similarity calculation object content and indirectly
The similarity of target audience.If the similarity of object content and indirect target audient are greater than preset threshold, second determines list
Member 44 can determine that indirect target audient is the target audience of object content.For example, the second determination unit 44 can be according to object content
It is associated with at least one between the first similarity between content and indirect target audient and at least one indirect target content
Second similarity, come determine current platform object content audient, can by following formula (6) Lai Jianli object content f with
The similarity of indirect target audient x:
Score (f, x)=sim (f, o) * Score (o, x) (6)
Wherein it is possible to understand, indirect target audient x was not clicked directly on or transformed object content f.
In this way, can get similar between each object content and all users for having interbehavior on another platform
Degree, for example, the similarity of the content o on object content f and other platforms is 0.5, indirect target audient x and content o have directly
Interbehavior and similarity are 0.3, then can be calculated object content f's and indirect target audient x by above-mentioned formula (6)
Similarity is 0.15.Later, it can be ranked up by similarity, be more than the user of some given threshold as in target using similarity
The target audience of appearance, and object content is pushed into these target audiences.Efficiently utilize as a result, the users of other platforms with
The interbehavior of advertisement expands audient's range of targeted advertisements dispensing significantly, and obtains than random dispensing and preferably launch effect
Fruit；Moreover, advertiser can also select to determine similar between dispensing advertisement and target audience according to the dispensing budget of oneself
Threshold value is spent, effectively to control dispensing range.
The information push-delivery apparatus of the embodiment of the present application can obtain the seed of the first platform according to the object content of the first platform
User, and according to the first behavioural information on the first platform of seed user, seed user, seed user at least one second
At least one second behavioural information on platform obtains in object content is associated with at least one at least one second platform
The first similarity between appearance, and pushed according to the target audience of the first similarity positioning object content, and by object content
To the target audience, effectively utilizes and combine user on different platforms to the behavioral data of different content, realize
Cross-platform ground selection target audient effectively expands in the case where Current Content and content platform few seed user
Target audience.
In the description of the present application, it is to be understood that term " first ", " second " are used for description purposes only, and cannot
It is interpreted as indication or suggestion relative importance or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In the description of the present application, " multiple "
It is meant that at least two, such as two, three etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it should not be understood as the limitation to the application, those skilled in the art within the scope of application can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (16)
1. a kind of information-pushing method, which comprises the following steps:
The object content of the first platform is obtained, and obtains the seed user of first platform according to the object content；
Obtain the seed user the first behavioural information of first platform and at least one second platform at least
One the second behavioural information；
It is obtained in the target according to the seed user, first behavioural information and at least one described second behavioural information
Hold and is associated with the first similarity between content at least one at least one described second platform；And
The target audience of the object content is positioned according to first similarity, and the object content is pushed into the mesh
Mark audient；Wherein, the target audience for positioning the object content according to first similarity includes: according to cross-platform interior
The first similarity between appearance, using the content on other platforms high with the object content similarity as in indirect target
Hold, and gather to the numerous users for having positive performance in the indirect target as indirect target audient, later from described
The target audience is selected in indirect target audient set, wherein other described platform differences are in first platform and described
Second platform.
2. information-pushing method as described in claim 1, which is characterized in that first behavioural information and second behavior
Information respectively includes one of number, the number of transaction, the time of click and time of transaction for clicking or a variety of.
3. information-pushing method as described in claim 1, which is characterized in that at least one described association content is the seed
The content that user clicks and/or traded at least one described second platform.
4. information-pushing method as described in claim 1, which is characterized in that described according to the seed user, described first
Behavioural information and at least one described second behavioural information obtain the object content and at least one described second platform up to
The first similarity between few association content, comprising:
User-content is established according to the seed user, first behavioural information and at least one described second behavioural information
Matrix, wherein the user-content matrix include the seed user, the object content with it is described at least one be associated in
Corresponding relationship between appearance；
According to preset cosine angle similarity model and the user-content matrix obtain the object content and it is described at least
The first similarity between at least one association content on one the second platform.
5. information-pushing method as claimed in claim 4, which is characterized in that the preset cosine angle similarity model
Are as follows:
Wherein, f is the object content, and U (f) is the user's set for clicking f, and o is at least one described second platform
At least one association content, U (o) are the user's set for clicking o, WaEach content that the user a was clicked for user a
Contribution degree.
6. information-pushing method as described in claim 1, which is characterized in that described according to first similarity positioning
The target audience of object content specifically includes:
At least one indirect target at least one described second platform is determined according to first similarity and object content
Content；
The corresponding indirect target audient of at least one described indirect target content is obtained, and according to the indirect target audient, institute
State at least one indirect target content and preset user to the fancy grade model of content calculate the indirect target audient with
The second similarity between at least one described indirect target content；
The target audience of the object content is determined according to first similarity and second similarity.
7. information-pushing method as claimed in claim 6, which is characterized in that fancy grade of the preset user to content
Model are as follows:
Wherein, t is the number of days for the time gap present time that user x click on content o occurs, and W (t) is user x apart from current t
It when click on content o number.
8. information-pushing method as claimed in claim 6, which is characterized in that described according to first similarity and described
Two similarities determine the target audience of the object content, comprising:
According to the phase of object content and the indirect target audient described in first similarity and second similarity calculation
Like degree；
If the similarity of the object content and the indirect target audient are greater than preset threshold, it is determined that the indirect target
Audient is the target audience of the object content.
9. a kind of information push-delivery apparatus characterized by comprising
First obtains module, for obtaining the object content of the first platform, and it is flat according to object content acquisition described first
The seed user of platform；
Second obtains module, for obtaining the seed user in the first behavioural information of first platform and at least one
At least one second behavioural information on second platform；
Third obtains module, for according to the seed user, first behavioural information and at least one described second behavior
Object content described in acquisition of information with that at least one at least one described second platform is associated between content is first similar
Degree；
Locating module, for positioning the target audience of the object content according to first similarity；Wherein, described according to institute
Stating the first similarity and positioning the target audience of the object content includes: to be incited somebody to action according to the first similarity between cross-platform content
Content with the object content similarity on other high platforms, and will be to the indirect target as indirect target content
The numerous users for inside having positive performance gather as indirect target audient, select from indirect target audient set later
The target audience, wherein other described platform differences are in first platform and second platform；And
Pushing module, for the object content to be pushed to the target audience.
10. information push-delivery apparatus as claimed in claim 9, which is characterized in that first behavioural information and second row
One of number, the number of transaction, the time of click and time of transaction for respectively including clicking for information is a variety of.
11. information push-delivery apparatus as claimed in claim 9, which is characterized in that at least one described association content is described kind
The content that child user is clicked and/or traded at least one described second platform.
12. information push-delivery apparatus as claimed in claim 9, which is characterized in that the third obtains module and includes:
Unit is established, for according to the seed user, first behavioural information and at least one described second behavioural information
Establish user-content matrix, wherein the user-content matrix include the seed user, the object content and it is described extremely
Corresponding relationship between few association content；
Acquiring unit, for obtaining the target according to preset cosine angle similarity model and the user-content matrix
Content is associated with the first similarity between content at least one at least one described second platform.
13. information push-delivery apparatus as claimed in claim 12, which is characterized in that the preset cosine angle similarity model
Are as follows:
Wherein, f is the object content, and U (f) is the user's set for clicking f, and o is at least one described second platform
At least one association content, U (o) are the user's set for clicking o, WaEach content that the user a was clicked for user a
Contribution degree.
14. information push-delivery apparatus as claimed in claim 9, which is characterized in that the locating module includes:
First determination unit, for being determined at least one described second platform according to first similarity and object content
At least one indirect target content；
Acquiring unit, for obtaining the corresponding indirect target audient of at least one described indirect target content；
Computing unit, for according to the indirect target audient, at least one described indirect target content and preset user couple
The fancy grade model of content calculates the second phase between the indirect target audient and at least one described indirect target content
Like degree；
Second determination unit, for determining the target of the object content according to first similarity and second similarity
Audient.
15. information push-delivery apparatus as claimed in claim 14, which is characterized in that hobby journey of the preset user to content
Spend model are as follows:
Wherein, t is the number of days for the time gap present time that user x click on content o occurs, and W (t) is user x apart from current t
It when click on content o number.
16. information push-delivery apparatus as claimed in claim 14, which is characterized in that second determination unit is specifically used for:
According to the phase of object content and the indirect target audient described in first similarity and second similarity calculation
Like degree；
If the similarity of the object content and the indirect target audient are greater than preset threshold, it is determined that the indirect target
Audient is the target audience of the object content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410360003.6A CN105279204B (en) | 2014-07-25 | 2014-07-25 | Information-pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410360003.6A CN105279204B (en) | 2014-07-25 | 2014-07-25 | Information-pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105279204A CN105279204A (en) | 2016-01-27 |
| CN105279204B true CN105279204B (en) | 2019-04-09 |
Family
ID=55148224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410360003.6A Active CN105279204B (en) | 2014-07-25 | 2014-07-25 | Information-pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105279204B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3407285B1 (en) * | 2016-05-05 | 2023-06-28 | Tencent Technology (Shenzhen) Company Limited | Target user orientation method and device, and computer storage medium |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294778B (en) * | 2016-08-11 | 2019-09-10 | 北京小米移动软件有限公司 | Information-pushing method and device |
| CN107871244B (en) * | 2016-09-28 | 2021-08-20 | 腾讯科技（深圳）有限公司 | Method and device for detecting advertising effect |
| CN106530015B (en) * | 2016-12-08 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information delivery control method and device |
| CN106919692B (en) * | 2017-03-07 | 2021-02-19 | 阿里巴巴（中国）有限公司 | Method and device for pushing message |
| CN107341222B (en) * | 2017-06-28 | 2020-04-07 | 清华大学 | Cross-platform theme association method, device and equipment |
| CN107590691B (en) * | 2017-09-06 | 2021-01-15 | 晶赞广告（上海）有限公司 | Information publishing method and device, storage medium and terminal |
| CN108038217B (en) * | 2017-12-22 | 2021-05-11 | 北京星选科技有限公司 | Information recommendation method and device |
| WO2020021376A1 (en) | 2018-07-26 | 2020-01-30 | Global File Systems Holdings, Llc | User-managed content and advertising delivery based on similarity cohorts |
| CN109447731B (en) * | 2018-09-18 | 2024-10-18 | 平安科技（深圳）有限公司 | Cross-platform product recommendation method, device, computer equipment and storage medium |
| CN110135916A (en) * | 2019-05-23 | 2019-08-16 | 北京优网助帮信息技术有限公司 | A kind of similar crowd recognition method and system |
| CN110503467B (en) * | 2019-08-15 | 2022-11-22 | 深圳市云积分科技有限公司 | Cross-platform consumer group acquisition method and device |
| WO2021092803A1 (en) * | 2019-11-13 | 2021-05-20 | 深圳市欢太科技有限公司 | Push user determination method and apparatus, server, and storage medium |
| CN111582906A (en) * | 2020-03-26 | 2020-08-25 | 口碑(上海)信息技术有限公司 | Target user information acquisition method and device and electronic equipment |
| CN112102133B (en) * | 2020-11-16 | 2021-02-12 | 深圳市易博天下科技有限公司 | Efficient recruitment method, device and system based on information delivery and electronic equipment |
| CN112287236A (en) * | 2020-11-19 | 2021-01-29 | 每日互动股份有限公司 | Text message pushing method and device, computer equipment and storage medium |
| CN112446765A (en) * | 2020-12-01 | 2021-03-05 | 平安科技（深圳）有限公司 | Product recommendation method and device, electronic equipment and computer-readable storage medium |
| CN114996575B (en) * | 2022-05-30 | 2024-09-20 | 北京达佳互联信息技术有限公司 | Resource information pushing method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102163211A (en) * | 2010-02-23 | 2011-08-24 | 索尼公司 | Information processing device, importance calculation method, and program |
| CN102236654A (en) * | 2010-04-26 | 2011-11-09 | 广东开普互联信息科技有限公司 | Web useless link filtering method based on content relevancy |
| CN103426101A (en) * | 2013-07-31 | 2013-12-04 | 广州市动景计算机科技有限公司 | Generating method and device for verification code |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100057546A1 (en) * | 2008-08-30 | 2010-03-04 | Yahoo! Inc. | System and method for online advertising using user social information |
-
2014
- 2014-07-25 CN CN201410360003.6A patent/CN105279204B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102163211A (en) * | 2010-02-23 | 2011-08-24 | 索尼公司 | Information processing device, importance calculation method, and program |
| CN102236654A (en) * | 2010-04-26 | 2011-11-09 | 广东开普互联信息科技有限公司 | Web useless link filtering method based on content relevancy |
| CN103426101A (en) * | 2013-07-31 | 2013-12-04 | 广州市动景计算机科技有限公司 | Generating method and device for verification code |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3407285B1 (en) * | 2016-05-05 | 2023-06-28 | Tencent Technology (Shenzhen) Company Limited | Target user orientation method and device, and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105279204A (en) | 2016-01-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105279204B (en) | Information-pushing method and device | |
| Doyle | A dictionary of marketing | |
| Jee | The perception of discount sales promotions–A utilitarian and hedonic perspective | |
| Crompton | Conceptualization and alternate operationalizations of the measurement of sponsorship effectiveness in sport | |
| Belch et al. | The future of creativity in advertising | |
| WO2010059867A3 (en) | Methods and systems of measuring the effectiveness of advertising content and producing standardized advertising content effectiveness scores | |
| Paulson et al. | Efficient large-scale internet media selection optimization for online display advertising | |
| WO2011116301A3 (en) | Systems and methods to distribute advertisement opportunities to merchants | |
| US20150371256A1 (en) | Systems, methods, and apparatus for in-store analytics and offline attribution | |
| WO2008144286A1 (en) | Authored-in advertisements for documents | |
| US20090259540A1 (en) | System for partitioning and pruning of advertisements | |
| TW201229943A (en) | Hint-enabled search advertisements | |
| JP2009276377A (en) | Advertisement providing method, advertisement providing device and advertisement providing program | |
| CN106030639A (en) | Dynamic content delivery for real-time trends | |
| Dowthwaite | Crowdfunding webcomics: the role of incentives and reciprocity in monetising free content | |
| Gold | The digital advertising guide | |
| Barbosa | Contemporary trends in innovative marketing strategies | |
| JP2007334661A (en) | Advertisement information providing system | |
| Akel et al. | Adoption of online advertising by small and medium enterprises | |
| Harden et al. | Marketing by the numbers: how to measure and improve the ROI of any campaign | |
| Blackburn et al. | Social Media Data Analytics–Using Big Data for Big Consumer Reach | |
| Sciarrino et al. | To market, to market: How creative treatments of in-store branded content impact sales | |
| Kahindi et al. | Effect Of In-Store Promotion On Performance Of Supermarkets In Nakuru East And Nakuru West Sub-Counties, Kenya | |
| Shinde et al. | A Review Of Challenges And Opportunities In Adopting Dooh Technology For Advertising: A Business Perspective Through Tam | |
| CN202838428U (en) | Device positioning identifying code advertisements based on cookie |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |