CN106372151A - Message push method and message push device based on user gender recognition - Google Patents
Message push method and message push device based on user gender recognition Download PDFInfo
- Publication number
- CN106372151A CN106372151A CN201610767429.2A CN201610767429A CN106372151A CN 106372151 A CN106372151 A CN 106372151A CN 201610767429 A CN201610767429 A CN 201610767429A CN 106372151 A CN106372151 A CN 106372151A
- Authority
- CN
- China
- Prior art keywords
- sex
- targeted customer
- user
- predetermined
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a message push method and a message push device based on user gender recognition. The method comprises: acquiring a message to be pushed; determining a target user to be pushed; acquiring utilization behavior data S related to a pre-determined application APP of the target user; calculating a gender parameter x of the target user according to the S and a pre-determined gender ratio vector b; determining the gender of the target user according to the x and a pre-set threshold value; and pushing the message to be pushed according to the gender of the target user. By adopting the technical scheme, the gender of users in a target user group can be accurately judged, so that the message to be pushed is pushed according to the gender of the user, and the accuracy of a message push process based on the gender is high; and the promotion effect of the message is better and the waste of resources is reduced.
Description
Technical field
The present invention relates to networking technology area, more particularly to a kind of information push method based on the identification of user's sex and
Device.
Background technology
During the message of mobile network pushes, when user uses on mobile device (such as mobile phone, panel computer etc.)
Certain have message push position application program (application, app) when, have one request be sent to from this mobile device right
Answer agential server, and agent needs to determine to push what kind of message to user.Such as advertisement pushing process, when
User using on mobile device certain have advertisement position application program when, the server of corresponding ad-agency can receive this shifting
The request that dynamic equipment sends, and ad-agency needs to determine to throw in what kind of advertisement to this advertisement position.
And because some message are high with the sex degree of association of user, sex PUSH message therefore according to user so that
Promote more targetedly, thus more preferable promotion effect can be brought.For example, for the advertisement related to cosmetics, women's dress etc.,
Consumer due to cosmetics and women's dress mostly is women, so such advertisement pushing can be brought more preferable receipts to female user
Benefit.
In prior art, generally according to the usage behavior to app for the user, this is determined using the clustering algorithm based on model
The sex of user, it is, the usage behavior training pattern to app according to the user of known sex in a large number, thus obtaining certain
The sex of this user, such as mixed Gauss model, logic after one user is to the usage behavior of app, can be obtained using this model
Regression algorithm etc..But, the total quantity of the app being used by a large number of users is very big, the quantity of the app that unique user uses
Seldom, there is the use number of users of the app of sex identification value (i.e. user gender tendency is larger) less, lead to a large number of users pair
The probability distribution of the usage behavior of app can not accurately deduce, thus determines user's sex using based on the clustering algorithm of model
Accuracy is very low, so leads to the accuracy rate that gender-based message pushes process relatively low preferable to promote effect it is difficult to reach
Really, cause the wasting of resources.
Content of the invention
The embodiment of the invention discloses a kind of information push method based on the identification of user's sex and device, existing in order to solve
There is the problem of the inaccurate message promotion effect difference leading to of user's sex identification in information push method and the wasting of resources.Technical side
Case is as follows:
In a first aspect, embodiments providing a kind of information push method based on the identification of user's sex, described side
Method includes:
PUSH message is treated in acquisition；
Determine targeted customer to be pushed；
Obtain usage behavior data s with regard to predetermined application program app of described targeted customer；
According to s and predetermined sex ratio vector b, calculate sex parameter x of described targeted customer, wherein, b is root
Vectorial with regard to the sex ratio of the usage behavior data determination of described predetermined app according to user known to sex；
Determine the sex of described targeted customer according to x and default threshold value；
Sex according to described targeted customer treats PUSH message described in pushing.
Optionally, described determine that the sex of described targeted customer includes according to x and default threshold value:
Judge whether x is more than the first predetermined threshold value；
If it is, determining that described targeted customer is male；
If it is not, then judging whether x is less than the second predetermined threshold value；
If x is less than described second predetermined threshold value it is determined that described targeted customer is women；
Wherein, described first predetermined threshold value and described second predetermined threshold value plus and be equal to 1.
Optionally, described usage behavior data s is:
The data matrix s usage behavior data of described predetermined app being made up of described targeted customer, wherein, s
Matrix for m × n, each of s element sijFor targeted customer j in the first preset time period using predetermined appi
Number of times, i=1,2 ... m, j=1,2 ... n.
Optionally, the determination mode of described sex ratio vector b includes:
According to known to described sex, user builds data matrix with regard to the usage behavior data of described predetermined app
T, wherein, t is the matrix of m × l, each of t element tilKnown to sex, user l uses in the second preset time period
The number of times of predetermined appi, i=1,2 ... m, l=1,2 ... l；
Corresponding male user ratio b of each described predetermined app is calculated according to below equationi, i=1,2 ... m；
Wherein, tikThe element corresponding to user being male for sex in the i-th row in data matrix t；
Determine described sex ratio vector b=(b1, b2…bm)’.
Optionally, described according to s and predetermined sex ratio vector b, calculate described targeted customer sex parameter x
Particularly as follows:
Described sex parameter x is calculated according to formula sx=b.
Second aspect, the embodiment of the present invention additionally provides a kind of message pusher based on the identification of user's sex, described
Device includes:
Treat PUSH message acquisition module, treat PUSH message for obtaining；
Targeted customer's determining module, for determining targeted customer to be pushed；
Behavioral data s acquisition module, for obtaining the making with regard to predetermined application program app of described targeted customer
Use behavioral data s；
Sex parameter x determining module, for according to s and predetermined sex ratio vector b, calculating described targeted customer
Sex parameter x, wherein, b be according to known to sex user with regard to described predetermined app usage behavior data determine
Sex ratio vector；
Sex determining module, for determining the sex of described targeted customer according to x and default threshold value；
Message pushing module, for treating PUSH message described in the sex push according to described targeted customer.
Optionally, described sex determining module includes:
First judging unit, for judging whether x is more than the first predetermined threshold value；
First determining unit, for when x is more than described first predetermined threshold value, determining that described targeted customer is male；
Second judging unit, for when x is not more than described first predetermined threshold value, judging whether x is less than the second default threshold
Value；
Second determining unit, for when x is less than described second predetermined threshold value, determining that described targeted customer is women；
Wherein, described first predetermined threshold value and described second predetermined threshold value plus and be equal to 1.
Optionally, described usage behavior data s is:
The data matrix s usage behavior data of described predetermined app being made up of described targeted customer, wherein, s
Matrix for m × n, each of s element sijFor targeted customer j in the first preset time period using predetermined appi
Number of times, i=1,2 ... m, j=1,2 ... n.
Optionally, described device also includes:
Sex ratio vector b determining module, for user according to known to described sex with regard to described predetermined app
Usage behavior data build data matrix t, wherein, t be m × l matrix, each of t element tilUse known to sex
Family l is in the second preset time period using the number of times of predetermined appi, i=1,2 ... m, l=1,2 ... l；
Corresponding male user ratio b of each described predetermined app is calculated according to below equationi, i=1,2 ... m；
Wherein, tikThe element corresponding to user being male for sex in the i-th row in data matrix t；
Determine described sex ratio vector b=(b1, b2…bm)’.
Optionally, described sex parameter x determining module specifically for:
Described sex parameter x is calculated according to formula sx=b.
In this programme, obtain first and treat PUSH message, determine targeted customer to be pushed, then obtain the pass of targeted customer
In usage behavior data s of predetermined application program app, according to s and predetermined sex ratio vector b, calculate mesh
Sex parameter x of mark user, and determine the sex of described targeted customer according to x and default threshold value, finally according to targeted customer
Sex push described in treat PUSH message, due to accurately can be sentenced to the sex of user in potential user group using this programme
Disconnected, and then PUSH message is treated according to the sex push of user, make gender-based message push the accuracy rate height of process, message
Promotion effect more preferably, reduces the waste of resource.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, acceptable
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of flow chart of information push method based on the identification of user's sex provided in an embodiment of the present invention；
Fig. 2 is a kind of structural representation of message pusher based on the identification of user's sex provided in an embodiment of the present invention
Figure.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of not making creative work
Embodiment, broadly falls into the scope of protection of the invention.
Push the accuracy rate of process, and then the promotion effect of raising message in order to improve gender-based message, reduce money
The waste in source, embodiments provides a kind of information push method based on the identification of user's sex and device.
First to provided in an embodiment of the present invention a kind of based on user's sex identification information push method be introduced.Need
It is noted that the embodiment of the present invention provided a kind of based on user's sex identification information push method can apply to treat
The corresponding agential server of PUSH message, hereinafter referred to as server.
As shown in figure 1, a kind of information push method based on the identification of user's sex, comprise the following steps:
S101, obtains and treats PUSH message；
What server obtained treats that PUSH message can be for being arbitrarily pushed to the message of user, and such as advertisement, video pushes away
Recommend message, commercial product recommending message etc., here is not specifically limited.This treats that PUSH message can be that server local preserves,
Can be obtained from network or data base with server.Concrete acquisition modes can be existing any acquisition modes, and here is not done to be had
Body limits.
S102, determines targeted customer to be pushed；
Push position due to treating that PUSH message corresponds to the one or several message on certain application program app, server obtains
After PUSH message, the service condition that the corresponding application program of PUSH message can be treated according to this, determine target to be pushed
User, for example, when certain user opens this application program it may be determined that this user is targeted customer to be pushed.
Screening conditions can certainly be preset, when user meets this sieve to the operation behavior of above-mentioned application program
When selecting condition, just can determine that this user is targeted customer to be pushed.For example, can preset this screening conditions is
User browses a certain plate in this application program, then when this user browses this plate, server just can determine this use
Family is targeted customer to be pushed.
It is understood that above-mentioned targeted customer to be pushed can be a user or multiple user.Wait to push away
The particular number of the targeted customer sending is to be determined according to practical situation, for example, if having preset screening conditions, then when
How many user front meets this screening conditions to the operation behavior of above-mentioned application program, and the quantity of targeted customer to be pushed is just
For how many.
S103, obtains usage behavior data s with regard to predetermined application program app of described targeted customer；
Specifically, above-mentioned usage behavior data s is: by above-mentioned targeted customer to above-mentioned predetermined app using row
The data matrix s constituting for data, wherein, s is the matrix of m × n, each of s element sijDefault first for targeted customer j
Using the number of times of predetermined appi, i=1,2 ... m, j=1,2 ... n in time cycle.
In practical application, above-mentioned predetermined app can be common for some, confirmable using user's sex
App, such as some bookings app etc..The quantity of this predetermined app can be true according to practical situation by those skilled in the art
Fixed, can be hundreds of individual or more.And for this predetermined app quantity little in the case of, provided by the present invention
Scheme is also the sex that can accurately identify targeted customer, and it is not absolutely required to substantial amounts of predetermined app uses row
For data, the quantity of for example predetermined app can be 3 or 5 etc., and here is not specifically limited.May be appreciated
It is that the quantity of this predetermined app is m, when the quantity of this predetermined app is 3, then data matrix s's
Line number is 3.And the columns n of data matrix s is the quantity of above-mentioned targeted customer.
Each of this data matrix s element sijFor targeted customer j in the first preset time period using true in advance
The number of times of fixed appi, wherein, i=1,2 ... m, j=1,2 ... n.It should be noted that for this first preset time period
Occurrence can determine, here is not done to be had by those skilled in the art according to the actually used situation of above-mentioned predetermined app
Body limits.However, to ensure that the accuracy to the identification of the sex of targeted customer, this first preset time period be difficult too short, excellent
Elect one week as, one month etc..
For example, if this first preset time period is one week, predetermined app quantity is 3, respectively
App1, app2 and app3, targeted customer's quantity is 4, and respectively targeted customer 1, targeted customer 2, targeted customer 3 and target are used
Family 4.Targeted customer 1 used the number of times of app1, app2 and app3 to be respectively in one week 3 times, 2 times and 2 times, and targeted customer 2 exists
Number of times using app1, app2 and app3 is respectively 2 times, 1 time and 4 times in one week, targeted customer 3 in one week using app1,
The number of times of app2 and app3 is respectively 1 time, 2 times and 3 times, and targeted customer 4 used the number of times of app1, app2 and app3 in one week
It is respectively 1 time, 3 times and 2 times.So server just can obtain usage behavior data s and is
S104, according to s and predetermined sex ratio vector b, calculates sex parameter x of described targeted customer；
Wherein, b be according to known to sex user with regard to described predetermined app usage behavior data determine property
Other ratio vector.
Specifically, the determination mode of sex ratio vector b may include that
According to known to described sex, user builds data matrix with regard to the usage behavior data of described predetermined app
T, wherein, t is the matrix of m × l, each of t element tilKnown to sex, user l uses in the second preset time period
The number of times of predetermined appi, i=1,2 ... m, l=1,2 ... l；
Corresponding male user ratio b of each described predetermined app is calculated according to below equationi, i=1,2 ... m；
Wherein, tikThe element corresponding to user being male for sex in the i-th row in data matrix t；
Determine described sex ratio vector b=(b1, b2…bm)’.
Above-mentioned data matrix t is that server user according to known to sex goes with regard to using of above-mentioned predetermined app
The data matrix building for data.It should be noted that above-mentioned second preset time period can be by those skilled in the art's root
According to user known to above-mentioned sex, being determined, here is not specifically limited to the actually used situation of predetermined app.It but is
Ensure the accuracy of the sex identification to targeted customer, this first preset time period is difficult too short, can be one week, one
Month etc..In practical application, this second preset time period generally can be identical with above-mentioned first preset time period.
Each of data matrix t element tilKnown to sex user l in the second preset time period using in advance
The number of times of the appi determining, wherein, i=1,2 ... m, l=1,2 ... l.Because the line number of data matrix t is predetermined with this
The quantity of app is identical, so the line number of this data matrix t is also identical with the line number of above-mentioned data matrix s.This data matrix
The columns of t is the quantity of user known to sex, can be 20 or 30 etc., here is not specifically limited.
For example, for convenience of calculating, the quantity setting user known to sex is as 3.If this second Preset Time week
Phase is one week, and predetermined app is 3, respectively app1, app2 and app3, user known to sex respectively user 1,
User 2 and user 3, wherein, user 1 is male, and user 2 and user 3 are women.User 1 in one week use app1, app2 and
The number of times of app3 is respectively 4 times, 2 times and 1 time, user 2 one week in using the number of times respectively 2 times of app1, app2 and app3,
1 time and 3 times, user 3 used the number of times of app1, app2 and app3 to be respectively in one week 4 times, 3 times and 1 time.So server
Just user 1,2 and 3 can be built with regard to the usage behavior data of above-mentioned predetermined app1,2 and 3 according to known to sex
To data matrix t it is
After determining this data matrix t, server just can be according to formula:
Calculate corresponding male user ratio b of each predetermined appi, wherein, i=1,2 ... m.
Specifically, tikRepresent that in the i-th row in data matrix t, sex is the element corresponding to user of male.So each
Corresponding male user ratio b of predetermined appiBe male user in above-mentioned second preset time period to this in advance
The access times of app determining are predetermined to this in above-mentioned second preset time period with all sex known users
The ratio of total access times of app.It is understood that corresponding male user ratio b of this predetermined appiIt is bigger,
Then represent that male user uses the tendency of this predetermined app bigger.
Taking above-mentioned data matrix t as a example, server based on data matrixAnd formulaCan calculate
To corresponding male user ratio b of each predetermined appi.Specifically, by can be calculated the corresponding male user of app1
RatioApp2 corresponding male user ratioApp3 corresponding male user ratio
Further, corresponding male user ratio b of each predetermined app according to above-mentioned determinationi, server is just
Can determine sex ratio vector b=(b1, b2…bm)’.For example, app1, app2 and app3 corresponding male user ratio b1、b2
And b3It is respectivelyWithSo this sex ratio vector b isNamely
It should be noted that this can be built data matrix t and sex ratio vector b by server in advance is saved in this
Ground, for example, can be saved in the data base locally building in advance, called with facilitating to search at any time, make calculating process quicker
Accurately.At the same time it can also update the type and quantity of this predetermined app at any time, and then adjust this data matrix t and sex
Ratio vector b, to obtain more accurate targeted customer's sex recognition result.
After determining sex ratio vector b, server can be according to above-mentioned usage behavior data s and this sex ratio vector
B, calculates sex parameter x of above-mentioned targeted customer.Specifically, this sex parameter x can be calculated according to formula sx=b.Need
Bright, sex parameter x is sex parameter vector corresponding with the quantity of above-mentioned targeted customer, and the quantity of targeted customer is many
Few, just include several values in this sex parameter x, the value of each value is general interior in interval [0,1].
It should be noted that when the quantity of above-mentioned predetermined app is less than the quantity of above-mentioned targeted customer, using row
Line number for data s is just less than its columns, i.e. m < n, then above-mentioned formula sx=b is a underdetermined equation, now can make
Solve sex parameter x with quadratic programming.Specifically, | | sx-b | | can be made by solution2X value when minimum is determining sex
Parameter x.Need further exist for illustrating, Quadratic Programming Solution problem is Mathematical method commonly used in the art, and here is not made
Illustrate.
For example, if calculated usage behavior data s isSex ratio vector b be
So just can be according to formulaIt is calculated sex parameter x.First can be by usage behavior
Data s is normalized and obtains matrixThen pass through above-mentioned formula sx=b
The sex parameter being calculated targeted customer 1 is about 0.8184, and the sex parameter of targeted customer 2 is about 0, the property of targeted customer 3
Other parameter is about 0, and the sex parameter of targeted customer 4 is about 0.3329.
S105, determines the sex of described targeted customer according to x and default threshold value；
Specifically, can determine the sex of above-mentioned targeted customer in the following manner:
Judge whether x is more than the first predetermined threshold value；
If it is, determining that described targeted customer is male；
If it is not, then judging whether x is less than the second predetermined threshold value；
If x is less than described second predetermined threshold value it is determined that described targeted customer is women；
Wherein, described first predetermined threshold value and described second predetermined threshold value plus and be equal to 1.
It should be noted that this first predetermined threshold value and the second predetermined threshold value all can be by those skilled in the art according to mesh
The quantity of mark user and usage behavior data s with regard to predetermined app to determine, here is not specifically limited.By sending out
The substantial amounts of experiment experience of a person of good sense is learnt, this first predetermined threshold value is preferably 0.5, at this point for the judgement ratio of the sex of targeted customer
Relatively accurate, and can interpolate that out the sex of most of targeted customers.
Specifically, after server calculates the sex parameter of targeted customer, can be by this sex parameter and the first default threshold
Value is compared, if this sex parameter is more than this first predetermined threshold value, then can determine this corresponding target of sex parameter
User is male.For example, if the first predetermined threshold value is 0.5, sex parameter is 0.63, then this corresponding target of sex parameter is used
Family is male.
If it should be noted that targeted customer is multiple, then just can be respectively by the sex of the plurality of targeted customer
Parameter is compared with this first predetermined threshold value.Such as targeted customer is above-mentioned targeted customer 1, targeted customer 2, targeted customer 3
With targeted customer 4, the first predetermined threshold value is 0.5, then just can be successively by targeted customer 1, targeted customer 2, targeted customer 3 and
The sex parameter of targeted customer 4 is compared with this first predetermined threshold value respectively.Sex parameter due to targeted customer 1 is
0.8184, more than the first predetermined threshold value 0.5, then just can determine that targeted customer 1 is male, because targeted customer 2, target are used
The sex parameter of family 3 and targeted customer 4 is both less than the first predetermined threshold value 0.5, then just can further be judged.
When judging that sex parameter x is not more than the first predetermined threshold value, can determine whether whether x presets less than second
Threshold value, if less than, then just can determine that the corresponding targeted customer of this sex parameter x is women.
For example, if this first predetermined threshold value is 0.5, due to this first predetermined threshold value and this second predetermined threshold value plus
With equal to 1, so this second predetermined threshold value is 0.5, the sex due to targeted customer 2, targeted customer 3 and targeted customer 4 is joined
Number is respectively less than this second predetermined threshold value 0.5 it is possible to determine that targeted customer 2, targeted customer 3 and targeted customer 4 are women.
It should be noted that in some cases, because the first predetermined threshold value is different with the setting of the second predetermined threshold value, can
The sex unascertainable situation of certain or some targeted customer can occur, now can suitably adjust the first predetermined threshold value and
Second predetermined threshold value.
S106, treats PUSH message according to the sex push of described targeted customer.
After determining the sex of targeted customer, server just can push according to the sex of this targeted customer above-mentioned to be waited to push away
Send message.For example, if this treats that PUSH message is women's dress advertisement, because the consumer of women's dress mostly is women, then just can root
According to the sex of targeted customer, this is treated that PUSH message is pushed to the targeted customer that sex is women, or is pushed to sex for female
Property targeted customer number of times more, and the number of times being pushed to the targeted customer that sex is male is few.
It should be noted that server can select not treat that PUSH message is pushed to by above-mentioned according to the sex of targeted customer
Targeted customer, does not push and treats that the operation of PUSH message may be considered a kind of mode that PUSH message is treated in push, exactly because clothes
Business device can according to the sex selection of targeted customer very low to some and targeted customer's degree of association treat that PUSH message does not push away
Send, so further increasing the accuracy rate that message pushes process, the promotion effect of message more preferably, reduce further to resource
Waste and push cost.
Need further exist for illustrating, due in some cases, it is possible that the property of certain or some targeted customers
Situation about cannot accurately not determine, then in order to expand the promotion effect of message, can need to treat above-mentioned according to actual push
PUSH message is pushed to the targeted customer that sex cannot accurately determine.
It can be seen that in the scheme that provided of the present embodiment, obtaining first and treat PUSH message, determine targeted customer to be pushed, so
Obtain usage behavior data s with regard to predetermined application program app of targeted customer afterwards, according to s and predetermined property
Other ratio vector b, calculates sex parameter x of targeted customer, and determines the property of described targeted customer according to x and default threshold value
Not, the sex finally according to targeted customer push described in treat PUSH message, due to can be in potential user group using this programme
The sex of user is accurately judged, and then treats PUSH message according to the sex push of user, so that gender-based message is pushed
The accuracy rate of process is high, and the promotion effect of message more preferably, reduces the waste of resource.
Corresponding to said method embodiment, the embodiment of the present invention additionally provide a kind of based on user's sex identification message push away
Send device, below the embodiment of the present invention is also provided a kind of based on user's sex identification message pusher be introduced.Need
It is noted that provided in an embodiment of the present invention a kind of based on user's sex identification message pusher can apply to wait to push away
Send message corresponding agential server.
A kind of message pusher based on the identification of user's sex, described device includes:
Treat PUSH message acquisition module 210, treat PUSH message for obtaining；
Targeted customer's determining module 220, for determining targeted customer to be pushed；
Behavioral data s acquisition module 230, for obtain described targeted customer with regard to predetermined application program app
Usage behavior data s；
Sex parameter x determining module 240, for according to s and predetermined sex ratio vector b, calculating described target
Sex parameter x of user；
Wherein, b be according to known to sex user with regard to described predetermined app usage behavior data determine property
Other ratio vector.
Sex determining module 250, for determining the sex of described targeted customer according to x and default threshold value；
Message pushing module 260, for treating PUSH message described in the sex push according to described targeted customer.
It can be seen that in the scheme of the present embodiment offer, obtaining first and treat PUSH message, determine targeted customer to be pushed, then
Obtain usage behavior data s with regard to predetermined application program app of targeted customer, according to s and predetermined sex
Ratio vector b, sex parameter x of calculating targeted customer, and the sex of described targeted customer is determined according to x and default threshold value,
Finally according to targeted customer sex push described in treat PUSH message, due to can be to user in potential user group using this programme
Sex accurately judged, and then pushed according to the sex of user and treat PUSH message, make gender-based message push process
Accuracy rate high, the promotion effect of message more preferably, reduces the waste of resource.
In one embodiment of the invention, sex determining module 250 may include that
First judging unit (not shown), for judging whether x is more than the first predetermined threshold value；
First determining unit (not shown), for when x is more than described first predetermined threshold value, determining that described target is used
Family is male；
Second judging unit (not shown), for when x is not more than described first predetermined threshold value, judging whether x is little
In the second predetermined threshold value；
Second determining unit (not shown), for when x is less than described second predetermined threshold value, determining that described target is used
Family is women；
Wherein, described first predetermined threshold value and described second predetermined threshold value plus and be equal to 1.
In one embodiment of the invention, described usage behavior data s is:
The data matrix s usage behavior data of described predetermined app being made up of described targeted customer, wherein, s
Matrix for m × n, each of s element sijFor targeted customer j in the first preset time period using predetermined appi
Number of times, i=1,2 ... m, j=1,2 ... n.
In one embodiment of the invention, described device can also include:
Sex ratio vector b determining module (not shown), for user according to known to described sex with regard to described
The usage behavior data of predetermined app builds data matrix t, and wherein, t is the matrix of m × l, each of t element tilFor
User y known to sex in the second preset time period using the number of times of predetermined appi, i=1,2 ... m, l=1,
2…l；
Corresponding male user ratio b of each described predetermined app is calculated according to below equationi, i=1,2 ... m；
Wherein, tikThe element corresponding to user being male for sex in the i-th row in data matrix t；
Determine described sex ratio vector b=(b1, b2…bm)’.
In one embodiment of the invention, described sex parameter x determining module 240 specifically for:
Described sex parameter x is calculated according to formula sx=b.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation are made a distinction with another entity or operation, and not necessarily require or imply these entities or deposit between operating
In any this actual relation or order.And, term " inclusion ", "comprising" or its any other variant are intended to
Comprising of nonexcludability, wants so that including a series of process of key elements, method, article or equipment and not only including those
Element, but also include other key elements being not expressly set out, or also include for this process, method, article or equipment
Intrinsic key element.In the absence of more restrictions, the key element that limited by sentence "including a ..." it is not excluded that
Also there is other identical element including in the process of described key element, method, article or equipment.
Each embodiment in this specification is all described by the way of related, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.Real especially for device
For applying example, because it is substantially similar to embodiment of the method, so description is fairly simple, referring to embodiment of the method in place of correlation
Part illustrate.
One of ordinary skill in the art will appreciate that realizing all or part of step in said method embodiment is can
Completed with the hardware instructing correlation by program, described program can be stored in computer read/write memory medium,
The storage medium obtaining designated herein, such as: rom/ram, magnetic disc, CD etc..
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit protection scope of the present invention.All
Any modification, equivalent substitution and improvement made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention
Interior.
Claims (10)
1. a kind of information push method based on the identification of user's sex is it is characterised in that methods described includes:
PUSH message is treated in acquisition；
Determine targeted customer to be pushed；
Obtain usage behavior data s with regard to predetermined application program app of described targeted customer；
According to s and predetermined sex ratio vector b, calculate sex parameter x of described targeted customer, wherein, b is according to property
Not known user is with regard to the sex ratio vector of the usage behavior data determination of described predetermined app；
Determine the sex of described targeted customer according to x and default threshold value；
Sex according to described targeted customer treats PUSH message described in pushing.
2. the method for claim 1 is it is characterised in that described determine described targeted customer according to x and default threshold value
Sex include:
Judge whether x is more than the first predetermined threshold value；
If it is, determining that described targeted customer is male；
If it is not, then judging whether x is less than the second predetermined threshold value；
If x is less than described second predetermined threshold value it is determined that described targeted customer is women；
Wherein, described first predetermined threshold value and described second predetermined threshold value plus and be equal to 1.
3. method as claimed in claim 1 or 2 is it is characterised in that described usage behavior data s is:
The data matrix s usage behavior data of described predetermined app being made up of described targeted customer, wherein, s is m
The matrix of × n, each of s element sijFor targeted customer j in the first preset time period using predetermined appi's
Number of times, i=1,2 ... m, j=1,2 ... n.
4. method as claimed in claim 3 is it is characterised in that the determination mode of described sex ratio vector b includes:
According to known to described sex, user builds data matrix t with regard to the usage behavior data of described predetermined app, its
In, t is the matrix of m × l, each of t element tilKnown to sex user l in the second preset time period using in advance
The number of times of the appi determining, i=1,2 ... m, l=1,2 ... l；
Corresponding male user ratio b of each described predetermined app is calculated according to below equationi, i=1,2 ... m；
Wherein, tikThe element corresponding to user being male for sex in the i-th row in data matrix t；
Determine described sex ratio vector b=(b1, b2…bm)’.
5. method as claimed in claim 1 or 2 it is characterised in that described according to s and predetermined sex ratio vector b,
Calculate sex parameter x of described targeted customer particularly as follows:
Described sex parameter x is calculated according to formula sx=b.
6. a kind of message pusher based on the identification of user's sex is it is characterised in that described device includes:
Treat PUSH message acquisition module, treat PUSH message for obtaining；
Targeted customer's determining module, for determining targeted customer to be pushed；
Behavioral data s acquisition module, for obtaining going with regard to using of predetermined application program app of described targeted customer
For data s；
Sex parameter x determining module, for according to s and predetermined sex ratio vector b, calculating the property of described targeted customer
Other parameter x, wherein, b be according to known to sex user with regard to described predetermined app usage behavior data determine property
Other ratio vector；
Sex determining module, for determining the sex of described targeted customer according to x and default threshold value；
Message pushing module, for treating PUSH message described in the sex push according to described targeted customer.
7. device as claimed in claim 6 is it is characterised in that described sex determining module includes:
First judging unit, for judging whether x is more than the first predetermined threshold value；
First determining unit, for when x is more than described first predetermined threshold value, determining that described targeted customer is male；
Second judging unit, for when x is not more than described first predetermined threshold value, judging whether x is less than the second predetermined threshold value；
Second determining unit, for when x is less than described second predetermined threshold value, determining that described targeted customer is women；
Wherein, described first predetermined threshold value and described second predetermined threshold value plus and be equal to 1.
8. device as claimed in claims 6 or 7 is it is characterised in that described usage behavior data s is:
The data matrix s usage behavior data of described predetermined app being made up of described targeted customer, wherein, s is m
The matrix of × n, each of s element sijFor targeted customer j in the first preset time period using predetermined appi's
Number of times, i=1,2 ... m, j=1,2 ... n.
9. device as claimed in claim 8 is it is characterised in that described device also includes:
Sex ratio vector b determining module, for user's making with regard to described predetermined app according to known to described sex
Build data matrix t with behavioral data, wherein, t is the matrix of m × l, each of t element tilKnown to sex, user l exists
Using the number of times of predetermined appi, i=1,2 ... m, l=1,2 ... l in second preset time period；
Corresponding male user ratio b of each described predetermined app is calculated according to below equationi, i=1,2 ... m；
Wherein, tikThe element corresponding to user being male for sex in the i-th row in data matrix t；
Determine described sex ratio vector b=(b1, b2…bm)’.
10. device as claimed in claims 6 or 7 it is characterised in that described sex parameter x determining module specifically for:
Described sex parameter x is calculated according to formula sx=b.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610767429.2A CN106372151B (en) | 2016-08-30 | 2016-08-30 | A kind of information push method and device based on the identification of user's gender |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610767429.2A CN106372151B (en) | 2016-08-30 | 2016-08-30 | A kind of information push method and device based on the identification of user's gender |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106372151A true CN106372151A (en) | 2017-02-01 |
| CN106372151B CN106372151B (en) | 2019-10-08 |
Family
ID=57901543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610767429.2A Active CN106372151B (en) | 2016-08-30 | 2016-08-30 | A kind of information push method and device based on the identification of user's gender |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106372151B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764997A (en) * | 2018-05-25 | 2018-11-06 | 北京京东金融科技控股有限公司 | Take in recognition methods, device and computer readable storage medium |
| CN109063433A (en) * | 2018-07-09 | 2018-12-21 | 中国联合网络通信集团有限公司 | Recognition methods, device and the readable storage medium storing program for executing of fictitious users |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541590A (en) * | 2011-12-14 | 2012-07-04 | 奇智软件（北京）有限公司 | Software recommending method and system |
| CN103164470A (en) * | 2011-12-15 | 2013-06-19 | 盛大计算机（上海）有限公司 | Directional application method based on user gender distinguished results and system thereof |
| WO2014014409A1 (en) * | 2012-07-20 | 2014-01-23 | Lee Yang Wai Alvin | Method for targeted and viral advertising |
| CN103838884A (en) * | 2014-03-31 | 2014-06-04 | 联想(北京)有限公司 | Information processing equipment and information processing method |
-
2016
- 2016-08-30 CN CN201610767429.2A patent/CN106372151B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541590A (en) * | 2011-12-14 | 2012-07-04 | 奇智软件（北京）有限公司 | Software recommending method and system |
| CN103164470A (en) * | 2011-12-15 | 2013-06-19 | 盛大计算机（上海）有限公司 | Directional application method based on user gender distinguished results and system thereof |
| WO2014014409A1 (en) * | 2012-07-20 | 2014-01-23 | Lee Yang Wai Alvin | Method for targeted and viral advertising |
| CN103838884A (en) * | 2014-03-31 | 2014-06-04 | 联想(北京)有限公司 | Information processing equipment and information processing method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764997A (en) * | 2018-05-25 | 2018-11-06 | 北京京东金融科技控股有限公司 | Take in recognition methods, device and computer readable storage medium |
| CN109063433A (en) * | 2018-07-09 | 2018-12-21 | 中国联合网络通信集团有限公司 | Recognition methods, device and the readable storage medium storing program for executing of fictitious users |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106372151B (en) | 2019-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Aker et al. | The promise (and pitfalls) of ICT for agriculture initiatives | |
| Hyde et al. | A distance-based uncertainty analysis approach to multi-criteria decision analysis for water resource decision making | |
| Meade et al. | Forecasting in telecommunications and ICT—A review | |
| Aiyar et al. | Growth slowdowns and the middle-income trap | |
| CN108364085A (en) | A kind of take-away distribution time prediction technique and device | |
| CN109479005A (en) | Method and system for realizing block chain | |
| CN109767259A (en) | Based on operation event promotion method, apparatus, equipment and the medium for burying point data | |
| CN107730196A (en) | Project scheduling management method and terminal device | |
| CN103150696A (en) | Method and device for selecting potential customer of target value-added service | |
| CN109410032A (en) | A kind of information processing method, server and computer storage medium | |
| CN107728878A (en) | Display methods, terminal and the computer-readable recording medium of application icon | |
| CN113778286B (en) | Application control display method and device, storage medium and electronic equipment | |
| CN107247775A (en) | A kind of data-updating method, device and electronic equipment | |
| CN109117980A (en) | Data pre-fill method, device and equipment | |
| CN110033357A (en) | Credit product recommended method and system | |
| CN106372151A (en) | Message push method and message push device based on user gender recognition | |
| Chapman et al. | Continuous product innovation: A comparison of key elements across different contingency sets | |
| CN109583937A (en) | A kind of Products Show method and apparatus | |
| CN108055387A (en) | Recommendation information display method and device, electronic equipment and readable storage medium | |
| Dubé et al. | Recent advances in structural econometric modeling: Dynamics, product positioning and entry | |
| CN107346323A (en) | The method and label recommendations device of a kind of label recommendations | |
| CN110210885A (en) | Excavate method, apparatus, equipment and the readable storage medium storing program for executing of potential customers | |
| CN106412796A (en) | Recommending method and system | |
| CN110245070B (en) | Test user screening method, device, computer equipment and storage medium | |
| Kóczy | The core can be accessed with a bounded number of blocks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |