CN106126640B - Content-data method for pushing and device - Google Patents
Content-data method for pushing and device Download PDFInfo
- Publication number
- CN106126640B CN106126640B CN201610464422.3A CN201610464422A CN106126640B CN 106126640 B CN106126640 B CN 106126640B CN 201610464422 A CN201610464422 A CN 201610464422A CN 106126640 B CN106126640 B CN 106126640B
- Authority
- CN
- China
- Prior art keywords
- data
- content
- clicking rate
- content data
- highest
- 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
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
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of content-data method for pushing and devices, belong to data processing field.The described method includes: N number of first content data are pushed to first terminal cluster tool at random, N is positive integer;Stop pushing the first content data in the first predetermined time interval, and obtains the feedback data of N number of first content data;According to the feedback data, the second content-data pushed next time is determined from N number of first content data;Second content-data is pushed into second terminal cluster tool;Solving content-data that is determining according to the feedback data obtained in real time and pushing may be content-data inferior, the problem of leading to the pusher of premium content data can be reduced, reach the chance for reducing and pushing content-data inferior, improves the effect of the pusher meeting of premium content data.
Description
Technical field
The present invention relates to data processing field, in particular to a kind of content-data method for pushing and device.
Background technique
With the fast development of information technology and Internet technology, various terminal device that can connect internet at
For the important channel for obtaining content-data in user's life and work.Server is by being using eventually to terminal device pushed information
The user of end equipment provides content-data.
In the prior art, push is generally by way of sampling push, at random by several content numbers when pushing for the first time
According to being pushed to section terminating equipment, then the feedback data of the content-data of each push is acquired in real time, calculated according to feedback data
The real-time clicking rate of the content-data of each push, the content-data pushed next time is determined according to real-time clicking rate, then
Push content-data is repeated, acquisition feedback data, real-time clicking rate is calculated and determines to push next time according to real-time clicking rate
Content-data process, until whole terminal devices were all pushed content-data.
In the implementation of the present invention, the inventor finds that the existing technology has at least the following problems: content-data is from pushing away
It is sent to the terminal device of user, then click this section of process checked to user to have a fixed response time, time delay is generally 10 minutes
More than, real-time clicking rate calculated at this time cannot really reflect user to the degree of concern of the content-data of push, according to
The content-data of real-time clicking rate determination and push may be content-data inferior, cause the pusher of premium content data that can subtract
It is few.
Summary of the invention
In order to solve problems in the prior art, the embodiment of the invention provides a kind of content-data method for pushing and devices.
The technical solution is as follows:
According to the first aspect of the invention, a kind of content-data method for pushing is provided, which comprises
N number of first content data are pushed into first terminal cluster tool at random, N is positive integer;
Stop pushing the first content data in the first predetermined time interval, and obtains N number of first content number
According to feedback data;
According to the feedback data, the second content number pushed next time is determined from N number of first content data
According to;
Second content-data is pushed into second terminal cluster tool.
According to the second aspect of the invention, a kind of content-data driving means is provided, described device includes:
First pushing module, for N number of first content data to be pushed to first terminal cluster tool at random, N is positive whole
Number;
First obtains module, pushes the first content data for stopping in the first predetermined time interval, and obtain
The feedback data of N number of first content data;
First determining module, for being determined next time from N number of first content data according to the feedback data
Second content-data of push;
Second pushing module, for second content-data to be pushed to second terminal cluster tool.
Technical solution provided in an embodiment of the present invention has the benefit that
By the way that pause after N number of first content data-pushing to first terminal cluster tool is pushed the first data content, and
And the feedback data of N number of first content data is obtained in the predetermined time interval of pause push, under being determined according to feedback data
The second content-data of second terminal cluster tool is once pushed to, due to pushing to terminal device from content-data, then arrives quilt
Click checks that this section of process can have time delay, and the feedback data obtained in real time can not really reflect user to the content of push
The degree of concern of data, if determine the content-data pushed according to the feedback data obtained in real time next time, it is determined that go out
The content-data pushed next time may be content-data inferior, obtain N number of first content data again after postponing a period of time
Feedback data can reduce feedback data and user to the mistake between the true degree of concern of the content of push to a certain extent
Difference, so that being the machine of premium content data according to the content-data pushed that the feedback data obtained after delay is determined next time
Meeting is bigger, has reached the chance for reducing and pushing content-data inferior, improves the effect of the pusher meeting of premium content data.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the implementation environment schematic diagram for the content-data method for pushing that an illustrative embodiment of the invention provides;
Fig. 2 is the method flow diagram for the content-data method for pushing that an illustrative embodiment of the invention provides;
Fig. 3 A is the method flow diagram for the content-data method for pushing that another exemplary embodiment of the invention provides;
Fig. 3 B is the implementation diagram for the content-data method for pushing that another exemplary embodiment of the invention provides;
Fig. 4 is the block diagram for the content-data driving means that an illustrative embodiment of the invention provides;
Fig. 5 is the block diagram for the content-data driving means that another exemplary embodiment of the invention provides.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Referring to FIG. 1, it illustrates a kind of structural schematic diagrams of implementation environment provided in an embodiment of the present invention.The implementation ring
Border includes: recommender system 110 and terminal device 120, in which:
Recommender system 110 is for providing the background system of content-data.Recommender system 110 is in different times to difference
Terminal device set push content-data.Content-data refers to the data transmitted in the form of resource in a network, such as
Document, video, audio, webpage etc..
Terminal device 120 is the equipment with data transmit-receive function, such as laptop, smart phone.Terminal device
120 can receive the content-data of the push of recommender system 110 and show in the display interface;It is checked when content-data is clicked
Afterwards, terminal device 120 can send the feedback data of content-data to recommender system 110, and feedback data is to indicate content-data
The data of the case where suffered operation, such as: content-data is clicked the time checked.
The quantity of terminal device 120 is at least 1.
Recommender system 110 and terminal device 120 are connected by cable network or wireless network.
Referring to FIG. 2, it illustrates a kind of streams of content-data method for pushing shown in an exemplary embodiment of the invention
Cheng Tu.Come in the recommender system that the present embodiment is applied in implementation environment with the content-data method for pushing for example, such as Fig. 2
It is shown, the content-data method for pushing the following steps are included:
In step 201, N number of first content data are pushed into first terminal cluster tool at random, N is positive integer.
Content-data refers to the data transmitted in the form of resource in a network, such as document, video, audio, webpage
Deng.
The N number of first content data for pushing to first terminal cluster tool are different.
It optionally, include at least one terminal device in first terminal cluster tool.
Optionally, if there is M terminal device in first terminal cluster tool, N number of first content data are pushed into M at random
A terminal device, each content-data push to M/N terminal device.
In step 202, stop push first content data in the first predetermined time interval, and obtain in N number of first
Hold the feedback data of data.
Feedback data is data the case where indicating operation suffered by content-data, for example content-data is clicked and checks
Time, the hits of content-data.
In step 203, it according to feedback data, is determined push second next time in from N number of first content data
Hold data.
Optionally, the second content-data is one in N number of first content data.
In step 204, the second content-data is pushed into second terminal cluster tool.
Optionally, the terminal device in second terminal cluster tool is not to be pushed the terminals of first content data to set
It is standby, alternatively, the section terminating equipment in second terminal cluster tool was pushed first content data, section terminating equipment not by
Pushed first content data.
In conclusion content-data method for pushing provided in an embodiment of the present invention, by by N number of first content data-pushing
The first data content of pause push after to first terminal cluster tool, and N is obtained in the predetermined time interval of pause push
The feedback data of a first content data pushes in the second of second terminal cluster tool next time according to feedback data determination
Hold data, due to pushing to terminal device from content-data, then check that this section of process can have time delay to being clicked, in real time acquisition
Feedback data can not really reflect user to the degree of concern of the content-data of push, if anti-according to what is obtained in real time
Feedback data determine the content-data pushed next time, it is determined that the content-data pushed next time gone out may be content number inferior
According to the feedback data of N number of first content data is obtained after postponing a period of time again, feedback data can be reduced to a certain extent
With user to the error between the true degree of concern of the content of push, so that being determined according to the feedback data obtained after delay
The content-data pushed next time be premium content data chance it is bigger, reached the machine for reducing and pushing content-data inferior
Meeting improves the effect of the pusher meeting of premium content data.
Fig. 3 A is please referred to, it illustrates another content-data method for pushing shown in an exemplary embodiment of the invention
Flow chart.Come in the recommender system that the present embodiment is applied in implementation environment with the content-data method for pushing for example, such as
Shown in Fig. 3 A, the content-data method for pushing the following steps are included:
In step 301, N number of first content data are pushed into first terminal cluster tool at random, N is positive integer.
Content-data refers to the data transmitted in the form of resource in a network, such as document, video, audio, webpage
Deng.
The N number of first content data for pushing to first terminal cluster tool are different.
It optionally, include at least one terminal device in first terminal cluster tool.
Optionally, if there is M terminal device in first terminal cluster tool, N number of first content data are pushed into M at random
A terminal device, each content-data push to M/N terminal device.Wherein, M is positive integer, and N is positive integer.
In step 302, stop push first content data in the first predetermined time interval, and obtain in N number of first
Hold the feedback data of data.
Feedback data is data the case where indicating operation suffered by content-data, for example content-data is clicked and checks
Time, the hits of content-data.
The pause push first content data in the first predetermined time interval, and first is received eventually in first time interval
The feedback data for N number of first content data that terminal device in end equipment set is sent.
In step 303, the clicking rate of each first content data is calculated.
If first content data i is pushed to m terminal device, the point of first content data i is obtained according to feedback data
Hitting number is p, then the clicking rate of first content data i is p/m.Wherein, m is positive integer, and p is the integer more than or equal to 0.
The corresponding first content data of highest clicking rate are determined as the second content-data.There are several types of feelings for the step
Condition:
When highest clicking rate is one greater than the quantity of predetermined threshold and the corresponding first content data of highest clicking rate,
Execute step 304;When the data that highest clicking rate is greater than predetermined threshold and the corresponding first content data of highest clicking rate are greater than
At one, step 305a is executed;When highest clicking rate is not more than predetermined threshold, executes step 306 or execute step 307.
Optionally, predetermined threshold is preset, and predetermined threshold can also be modified according to the actual situation.
In step 304, if highest clicking rate is greater than predetermined threshold and the corresponding first content data of highest clicking rate
Quantity is one, then the corresponding first content data of highest clicking rate is determined as the second content-data.
In step 305a, if highest clicking rate is greater than predetermined threshold and the corresponding first content data of highest clicking rate
The corresponding first content data of highest clicking rate are then pushed to third terminal cluster tool by quantity at least two at random.
Optionally, the terminal device in third terminal cluster tool is all terminals for not being pushed first content data
A part in equipment.For example, the terminal device for not being pushed first content data shares 1000, third terminal equipment collection
Terminal device in conjunction shares 100.
Optionally, if highest clicking rate is greater than predetermined threshold and the quantity of the corresponding first content data of highest clicking rate is
K shares f terminal device in third terminal cluster tool, then each first content data-pushing to f/k terminal device, the
Each terminal device in three terminal device set is pushed a content-data, wherein f, k are positive integer.For example, highest point
Hitting rate is 20%, and there are three the corresponding first content data of highest clicking rate, respectively content-data 1, content-data 2, content
Data 3 have 90 terminal devices in third terminal cluster tool, these three first content data-pushings to 90 terminals are set
Standby, each content-data pushes to 30 terminal devices, and each terminal device in third terminal cluster tool is pushed one
Content-data.
In step 305b, stop push first content data in the second predetermined time interval, and obtain from first
To the feedback coefficient of N number of first content data in the period of this end time for stopping push at the beginning of secondary push
According to.
Optionally, the second predetermined time interval is equal to the first predetermined time interval or the second predetermined time interval is not equal to
First predetermined time interval.Such as first predetermined time interval be 12 minutes, the second predetermined time interval be 2 minutes or second
Predetermined time interval is 12 minutes.
As shown in Figure 3B, it is assumed that be 15:04:02 at the beginning of pushing for the first time, be spaced the push of stopping in 12 minutes first
Content-data, namely stop push first content data in period T1, that is, 15:04:02 to 15:16:02 and obtain in N number of
Highest clicking rate is calculated greater than predetermined threshold according to feedback data in the feedback data for holding data, and highest clicking rate is corresponding
First content data quantity be two, 15:16:50 to third terminal cluster tool push highest clicking rate corresponding two
A first content data are spaced the push first content data of stopping in 6 minutes, namely in period T2, that is, 15:16:50 to 15:22:
Stop push first content data in 20, and obtains N number of content-data out of the period S2, that is, 15:04:02 to 15:22:20
Feedback data.
Recommender system gets the hits of each first content data from feedback data, is obtaining in N number of first
After the feedback data for holding data, the clicking rate of each first content data is recalculated, namely re-execute the steps 303.
Within step 306, random to push highest clicking rate corresponding first if highest clicking rate is not more than predetermined threshold
Content-data.
When highest clicking rate is not more than predetermined threshold, there are two types of situations:
One, highest clicking rate is one no more than the quantity of predetermined threshold and the corresponding first content data of highest clicking rate
It is a.
Two, highest clicking rate is at least no more than the quantity of predetermined threshold and the corresponding first content data of highest clicking rate
Two.
The step is implemented as follows:
It one, is one no more than the quantity of predetermined threshold and the corresponding first content data of highest clicking rate when highest clicking rate
When a, using the corresponding first content data of highest clicking rate as the second content-data.
Two, at least no more than the quantity of predetermined threshold and the corresponding first content data of highest clicking rate when highest clicking rate
When being two, the corresponding first content data of highest clicking rate are pushed into third terminal cluster tool at random;It is predetermined in third
Time interval stops push first content data, and obtains the knot for stopping push to this at the beginning of pushing from first time
The feedback data of N number of first content data in the period of beam time.Recommender system is obtaining N number of first content data
After feedback data, the clicking rate of each first content data is recalculated, namely re-execute the steps 303.
It should be noted that the ordinal numbers such as " one, two " as mentioned in the embodiments of the present invention, unless based on context it is certain
The suitable meaning of expression, it should be understood that only play differentiation and be used.
Optionally, the terminal device in third terminal cluster tool is all terminals for not being pushed first content data
A part in equipment.For example, the terminal device for not being pushed first content data shares 1000, third terminal equipment collection
Terminal device in conjunction shares 100.
Optionally, third predetermined time interval is equal to second less than the first predetermined time interval, third predetermined time interval
Predetermined time interval or third predetermined time interval are not equal to the second predetermined time interval.Such as: the first predetermined time interval is
12 minutes, the second predetermined time interval was 5 minutes, and third predetermined time interval is 1 minute or 5 minutes.
As shown in Figure 3B, it is assumed that be 15:04:02 at the beginning of pushing for the first time, be spaced the push of stopping in 12 minutes first
Content-data, namely stop push first content data in period T1, that is, 15:04:02 to 15:16:02 and obtain in N number of
Highest clicking rate is calculated less than predetermined threshold according to feedback data in the feedback data for holding data, and highest clicking rate is corresponding
First content data quantity be two, 15:16:50 to third terminal cluster tool push highest clicking rate corresponding two
A first content data are spaced the push first content data of stopping in 6 minutes, namely in period T2, that is, 15:16:50 to 15:22:
Stop push first content data in 20, and obtains N number of content-data out of the period S2, that is, 15:04:02 to 15:22:20
Feedback data.
After reaching the predetermined time, if highest clicking rate is still not more than predetermined threshold, stop pushing first content data.
In the given time, after the clicking rate for calculating each first content data, compare highest clicking rate and predetermined threshold
Value thens follow the steps 304 or step 305a if highest clicking rate is greater than predetermined threshold, if highest clicking rate is not more than predetermined threshold
Value then recycles and executes step 306, until highest clicking rate is greater than highest threshold value.If highest is clicked after reaching the predetermined time
Rate still less and predetermined threshold, then stops pushing first content data, alternatively, if highest clicking rate is not more than predetermined threshold,
Execute step 307.
Optionally, the predetermined time is pre-set, and the predetermined time can be modified according to the actual needs of business.
In step 307, if highest clicking rate is not more than predetermined threshold, stop pushing first content data.
If highest clicking rate is not more than predetermined threshold, recommender system thinks N number of first content data all without arrival business
Desired effect, then stop push first content data.
In step 308, the second content-data is pushed into second terminal cluster tool.
In conclusion content-data method for pushing provided in an embodiment of the present invention, by by N number of first content data-pushing
The first data content of pause push after to first terminal cluster tool, and N is obtained in the predetermined time interval of pause push
The feedback data of a first content data pushes in the second of second terminal cluster tool next time according to feedback data determination
Hold data, due to pushing to terminal device from content-data, then check that this section of process can have time delay to being clicked, in real time acquisition
Feedback data can not really reflect user to the degree of concern of the content-data of push, if anti-according to what is obtained in real time
Feedback data determine the content-data pushed next time, it is determined that the content-data pushed next time gone out may be content number inferior
According to the feedback data of N number of first content data is obtained after postponing a period of time again, feedback data can be reduced to a certain extent
With user to the error between the true degree of concern of the content of push, so that being determined according to the feedback data obtained after delay
The content-data pushed next time be premium content data chance it is bigger, reached the machine for reducing and pushing content-data inferior
Meeting improves the effect of the pusher meeting of premium content data.
In addition, the embodiment of the present invention is also by the way that after reaching the predetermined time, highest clicking rate is still not more than predetermined threshold
In the case of, stop push content-data, avoids repeating to push identical content-data, reduce recommender system because of unnecessary calculating
The loss of bring performance.
In an illustrative example, it is assumed that have 10 first content data 1-10, recommender system is in 12:00 first:
00 1000 terminal devices into first terminal cluster tool push first content data 1-10, each first content data quilt
First terminal cluster tool is pushed to, each first content data-pushing to 100 terminal devices, each terminal device only receives
One first content data.
Stop push content-data 12 minutes, in 12 minutes for stopping push, waits first content data to be clicked and look into
It sees, the feedback data of recommender system reception content data 1-10 after waiting 12 minutes, calculates each first content clickstream data
Rate, the clicking rate for calculating first content data 1 is 5%, and the clicking rate of first content data 2 is 10%, first content data 3
Clicking rate be 12%, the clicking rates of first content data 4 is 5%, and the clicking rate of first content data 5 is 13%, in first
The clicking rate for holding data 6 is 18%, and the clicking rate of first content data 7 is 12%, and the clicking rate of first content data 8 is
20%, the clicking rate of first content data 9 is 5%, and the clicking rate of first content data 10 is 1%.
There are several types of situations:
If one, predetermined threshold is 19%, highest clicking rate is 20%, and first content data 8 are determined as push next time
Second content-data pushes first content data 8 to second terminal cluster tool.
If two, predetermined threshold is 19%, it is assumed that the clicking rate of above-mentioned first content data 9 is 20%, then highest clicking rate
20% corresponding first content data have 2, are first content data 8 and first content data 9, by 8 He of first content data
First content data 9 push to third terminal cluster tool, stop push first content data 4 minutes, in 4 points for stopping pushing
It in clock, waits first content data to be clicked and checks, the feedback data of recommender system reception content data 1-10 waits 4 minutes and ties
Shu Hou calculates the clicking rate of each first content data, if the quantity of the corresponding first content data of highest clicking rate is at this time
One, then the corresponding first content data of highest clicking rate is determined as the second content-data, is pushed away to second terminal cluster tool
The second content-data is sent, otherwise, then by the corresponding several first content data-pushings of highest clicking rate to the 4th terminal device collection
It closing, the terminal device in the 4th terminal device set is a part in all terminal devices for not being pushed content-data,
Continue to stop the step of push obtains feedback data and calculates the clicking rate of each first content data, until highest clicking rate pair
The quantity for the content-data answered is one.
If three, predetermined threshold is 22%, highest clicking rate is 20% less than predetermined threshold, and highest clicking rate 20% is corresponding
First content data only one, be first content data 8, then first content data 8 are pushed into third terminal cluster tool,
Stop push first content data 5 minutes, in 5 minutes for stopping push, waits first content data to be clicked and check, recommend
The feedback data of system reception content data 1-10 after waiting 5 minutes, calculates each first content clickstream data rate, if this
When to calculate the clicking rate of first content data 1 be 6%, the clicking rates of first content data 2 is 11%, first content data 3
Clicking rate be 11%, the clicking rates of first content data 4 is 5%, and 5 clicking rate of first content data is 13%, first content
The clicking rate of data 6 is 18%, and the clicking rate of first content data 7 is 12%, and the clicking rate of first content data 8 is 23%,
The clicking rate of first content data 9 is 5%, and the clicking rate of first content data 10 is 1%, and highest clicking rate is 23%, then will
First content data 8 are determined as the second content-data, push first content data 8 to second terminal cluster tool.If predetermined
In moment time 12:30:00, highest clicking rate is calculated at this time still less than 22%, then again by highest clicking rate corresponding first
Content-data pushes to the 4th terminal device set, the terminal device in the 4th terminal device set be it is all be not pushed in
Hold a part in the terminal device of data, continue to stop push acquisition feedback data and calculates the point of each first content data
The step of hitting rate, if reaching moment predetermined time 12:30:00, calculated highest clicking rate then stops pushing still less than 22%
First content data.
If four, predetermined threshold is 22%, highest clicking rate is 20% less than predetermined threshold, shows that first content data all do not have
There is the expected standard for reaching business, then stops pushing first content data.
If five, predetermined threshold is 22%, it is assumed that the clicking rate of above-mentioned first content data 9 is 20%, then highest clicking rate
20% is less than predetermined threshold, and the corresponding first content data of highest clicking rate 20% have 2, is first content data 8 and the
First content data 8 and first content data 9 are pushed to third terminal cluster tool, stop push first by one content-data 9
It content-data 4 minutes, in 4 minutes for stopping push, waits first content data to be clicked and checks, recommender system reception content
The feedback data of data 1-10 after waiting 4 minutes, calculates the clicking rate of each first content data, further according to being calculated
Clicking rate determine subsequent the step of needing to be implemented.
Following is apparatus of the present invention embodiment, can be used for executing embodiment of the present invention method.Corresponding apparatus of the present invention are real
Undisclosed details in example is applied, embodiment of the present invention method is please referred to.
Referring to FIG. 4, it illustrates the structural block diagrams of content-data driving means provided by one embodiment of the present invention.
The content-data driving means can be pushed away by being implemented in combination with for software, hardware or both as the above-mentioned content-data that can provide
Take all or part of the recommender system of business.As shown in figure 4, the device includes:
First pushing module 410, for N number of first content data to be pushed to first terminal cluster tool at random, N is positive
Integer.
First obtains module 420, for stopping push first content data in the first predetermined time interval, and obtains N
The feedback data of a first content data.
First determining module 430, for determining to push from N number of first content data according to feedback data next time
The second content-data.
Second pushing module 440, for the second content-data to be pushed to second terminal cluster tool.
In conclusion content-data driving means provided in an embodiment of the present invention, by by N number of first content data-pushing
The first data content of pause push after to first terminal cluster tool, and N is obtained in the predetermined time interval of pause push
The feedback data of a first content data pushes in the second of second terminal cluster tool next time according to feedback data determination
Hold data, due to pushing to terminal device from content-data, then check that this section of process can have time delay to being clicked, in real time acquisition
Feedback data can not really reflect user to the degree of concern of the content-data of push, if anti-according to what is obtained in real time
Feedback data determine the content-data pushed next time, it is determined that the content-data pushed next time gone out may be content number inferior
According to the feedback data of N number of first content data is obtained after postponing a period of time again, feedback data can be reduced to a certain extent
With user to the error between the true degree of concern of the content of push, so that being determined according to the feedback data obtained after delay
The content-data pushed next time be premium content data chance it is bigger, reached the machine for reducing and pushing content-data inferior
Meeting improves the effect of the pusher meeting of premium content data.
Referring to FIG. 5, the structure box of the content-data driving means provided it illustrates another embodiment of the present invention
Figure.The content-data driving means can provide content number as above-mentioned by being implemented in combination with for software, hardware or both
According to all or part of the recommender system of Push Service.As shown in figure 5, the device includes:
First pushing module 510, for N number of first content data to be pushed to first terminal cluster tool at random, N is positive
Integer.
First obtains module 520, for stopping push first content data in the first predetermined time interval, and obtains N
The feedback data of a first content data.
First determining module 530, for determining to push from N number of first content data according to feedback data next time
The second content-data.
Second pushing module 540, for the second content-data to be pushed to second terminal cluster tool.
Optionally, the first determining module 530, comprising:
Computing unit 531, for calculating the clicking rate of each first content data.
Content-data determination unit 532, for the corresponding first content data of highest clicking rate to be determined as the second content
Data.
Optionally, content-data determination unit 532, is also used to:
If it is one that highest clicking rate, which is greater than predetermined threshold and the quantity of the corresponding first content data of highest clicking rate,
The corresponding first content data of highest clicking rate are determined as the second content-data.
Optionally, content-data determination unit 532, is also used to:
If highest clicking rate is greater than predetermined threshold and the quantity of the corresponding first content data of highest clicking rate is at least two
It is a, then the corresponding first content data of highest clicking rate are pushed into third terminal cluster tool at random;
The device further include:
Second obtains module 550, for stopping push first content data in the second predetermined time interval, and obtains
Stop the anti-of N number of first content data in the period of the end time pushed at the beginning of pushing from first time to this
Present data.
Module 560 is repeated, for the step of executing the clicking rate for calculating each first content data.
Optionally, content-data determination unit 532, is also used to:
If highest clicking rate is not more than predetermined threshold, random to push the corresponding first content data of highest clicking rate, or,
Stop push first content data.
Optionally, content-data determination unit 532, is also used to:
When the quantity of the corresponding first content data of highest clicking rate is one, using highest clicking rate as the second content
Data.
When the quantity at least two of the corresponding first content data of highest clicking rate, by highest clicking rate corresponding
One content-data pushes to third terminal cluster tool at random.
Optionally, the device further include:
Third obtains module 570, for stopping push first content data in third predetermined time interval, and obtains
Stop the anti-of N number of first content data in the period of the end time pushed at the beginning of pushing from first time to this
Present data.
Module 560 is repeated, for the step of executing the clicking rate for calculating each first content data.
Optionally, the device further include:
Stop pushing module 580, for after reaching the predetermined time, if highest clicking rate is still not more than predetermined threshold,
Stop push first content data.
In conclusion content-data driving means provided in an embodiment of the present invention, by by N number of first content data-pushing
The first data content of pause push after to first terminal cluster tool, and N is obtained in the predetermined time interval of pause push
The feedback data of a first content data pushes in the second of second terminal cluster tool next time according to feedback data determination
Hold data, due to pushing to terminal device from content-data, then check that this section of process can have time delay to being clicked, in real time acquisition
Feedback data can not really reflect user to the degree of concern of the content-data of push, if anti-according to what is obtained in real time
Feedback data determine the content-data pushed next time, it is determined that the content-data pushed next time gone out may be content number inferior
According to the feedback data of N number of first content data is obtained after postponing a period of time again, feedback data can be reduced to a certain extent
With user to the error between the true degree of concern of the content of push, so that being determined according to the feedback data obtained after delay
The content-data pushed next time be premium content data chance it is bigger, reached the machine for reducing and pushing content-data inferior
Meeting improves the effect of the pusher meeting of premium content data.
In addition, the embodiment of the present invention is also by the way that after reaching the predetermined time, highest clicking rate is still not more than predetermined threshold
In the case of, stop push content-data, avoids repeating to push identical content-data, reduce server because of unnecessary calculating band
The performance loss come.
It should be understood that content-data driving means provided by the above embodiment is when pushing content-data, only more than
The division progress of each functional module is stated for example, can according to need and in practical application by above-mentioned function distribution by difference
Functional module complete, i.e., the internal structure of equipment is divided into different functional modules, with complete it is described above whole or
Person's partial function.In addition, content-data driving means provided by the above embodiment belongs to content-data method for pushing embodiment
Same design, specific implementation process are detailed in embodiment of the method, and which is not described herein again.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of content-data method for pushing, which is characterized in that the described method includes:
N number of first content data are pushed into first terminal cluster tool at random, N is positive integer;
Stop pushing the first content data in the first predetermined time interval, and obtains N number of first content data
Feedback data;
Calculate the clicking rate of each first content data;
If it is one that highest clicking rate, which is greater than predetermined threshold and the quantity of the corresponding first content data of the highest clicking rate,
It is a, then the corresponding first content data of the highest clicking rate are determined as the second content-data;
If highest clicking rate is at least greater than the quantity of predetermined threshold and the corresponding first content data of the highest clicking rate
It is two, then the corresponding first content data of the highest clicking rate is pushed into third terminal cluster tool, institute at random
It states the terminal device in third terminal cluster tool and was not pushed the first content data;
Stop pushing the first content data in the second predetermined time interval, and obtains at the beginning of from pushing first time
Between to this stop push end time period in N number of first content data feedback data;
The step of executing the clicking rate for calculating each first content data;
Second content-data is pushed into second terminal cluster tool.
2. the method according to claim 1, wherein the clicking rate for calculating each first content data
Later, the method also includes:
If the highest clicking rate is not more than predetermined threshold, the corresponding first content number of the highest clicking rate is pushed
According to or, stopping pushing the first content data.
3. according to the method described in claim 2, it is characterized in that, the push highest clicking rate corresponding described first
Content-data, comprising:
When the quantity of the corresponding first content data of the highest clicking rate be one when, using the highest clicking rate as
Second content-data;
When the quantity at least two of the corresponding first content data of the highest clicking rate, by the highest clicking rate
The corresponding first content data push to the third terminal cluster tool at random.
4. according to the method described in claim 3, it is characterized in that, described when in the highest clicking rate corresponding described first
When holding the quantity at least two of data, the corresponding first content data of the highest clicking rate are pushed into third at random
After terminal device set, the method also includes:
Stop pushing the first content data in third predetermined time interval, and obtains at the beginning of from pushing first time
Between to this stop push end time period in N number of first content data feedback data;
The step of executing the clicking rate for calculating each first content data.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
After reaching the predetermined time, if the highest clicking rate is still not more than the predetermined threshold, stop pushing described first
Content-data.
6. a kind of content-data driving means, which is characterized in that described device includes:
First pushing module, for N number of first content data to be pushed to first terminal cluster tool at random, N is positive integer;
First obtains module, pushes the first content data for stopping in the first predetermined time interval, and obtain the N
The feedback data of a first content data;
Computing unit, for calculating the clicking rate of each first content data;
Content-data determination unit, if being greater than predetermined threshold and the highest clicking rate corresponding described for highest clicking rate
The quantity of one content-data is one, then the corresponding first content data of the highest clicking rate is determined as the second content
Data;
The content-data determination unit, if being also used to, highest clicking rate is greater than predetermined threshold and the highest clicking rate is corresponding
The quantity at least two of the first content data, then it is the corresponding first content data of the highest clicking rate are random
Third terminal cluster tool is pushed to, the terminal device in the third terminal cluster tool was not pushed the first content
Data;
Second obtains module, pushes the first content data for stopping in the second predetermined time interval, and obtain from
To N number of first content data in the period of this end time for stopping push at the beginning of pushing for the first time
Feedback data;
Module is repeated, for the step of executing the clicking rate for calculating each first content data;
Second pushing module, for second content-data to be pushed to second terminal cluster tool.
7. device according to claim 6, which is characterized in that the content-data determination unit is also used to:
If the highest clicking rate is not more than predetermined threshold, the corresponding first content of the highest clicking rate is pushed at random
Data, or, stopping pushing the first content data.
8. device according to claim 7, which is characterized in that the content-data determination unit is also used to:
When the quantity of the corresponding first content data of the highest clicking rate be one when, using the highest clicking rate as
Second content-data;
When the quantity at least two of the corresponding first content data of the highest clicking rate, by the highest clicking rate
The corresponding first content data push to the third terminal cluster tool at random.
9. device according to claim 8, which is characterized in that described device further include:
Third obtains module, pushes the first content data for stopping in third predetermined time interval, and obtain from
To N number of first content data in the period of this end time for stopping push at the beginning of pushing for the first time
Feedback data;
Module is repeated, for the step of executing the clicking rate for calculating each first content data.
10. device according to claim 9, which is characterized in that described device further include:
Stop pushing module, for after reaching the predetermined time, if the highest clicking rate is still not more than the predetermined threshold,
Stop pushing the first content data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610464422.3A CN106126640B (en) | 2016-06-23 | 2016-06-23 | Content-data method for pushing and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610464422.3A CN106126640B (en) | 2016-06-23 | 2016-06-23 | Content-data method for pushing and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106126640A CN106126640A (en) | 2016-11-16 |
CN106126640B true CN106126640B (en) | 2019-01-22 |
Family
ID=57268606
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610464422.3A Active CN106126640B (en) | 2016-06-23 | 2016-06-23 | Content-data method for pushing and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106126640B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107273508B (en) * | 2017-06-20 | 2020-07-10 | 北京百度网讯科技有限公司 | Information processing method and device based on artificial intelligence |
CN107392054A (en) * | 2017-08-23 | 2017-11-24 | 爱爱网(深圳)电子商务有限公司 | The method and apparatus that a kind of privacy is read |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104298673A (en) * | 2013-07-17 | 2015-01-21 | 腾讯科技(深圳)有限公司 | Method, device and system for carrying out statistics on push effect of application program |
CN105023172A (en) * | 2015-07-03 | 2015-11-04 | 叶秀兰 | Advertisement push system based on server push |
CN105427139A (en) * | 2015-12-31 | 2016-03-23 | 腾讯科技(深圳)有限公司 | Information processing method and server |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9043919B2 (en) * | 2008-10-21 | 2015-05-26 | Lookout, Inc. | Crawling multiple markets and correlating |
-
2016
- 2016-06-23 CN CN201610464422.3A patent/CN106126640B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104298673A (en) * | 2013-07-17 | 2015-01-21 | 腾讯科技(深圳)有限公司 | Method, device and system for carrying out statistics on push effect of application program |
CN105023172A (en) * | 2015-07-03 | 2015-11-04 | 叶秀兰 | Advertisement push system based on server push |
CN105427139A (en) * | 2015-12-31 | 2016-03-23 | 腾讯科技(深圳)有限公司 | Information processing method and server |
Also Published As
Publication number | Publication date |
---|---|
CN106126640A (en) | 2016-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109819048B (en) | Data synchronization method, device, terminal and storage medium | |
CN110012302A (en) | A kind of network direct broadcasting monitoring method and device, data processing method | |
CN106067043A (en) | A kind of performance test methods and system | |
CN106126640B (en) | Content-data method for pushing and device | |
WO2014176919A1 (en) | Method and system for displaying recommended pages by terminal device | |
CN110019386A (en) | A kind of stream data processing method and equipment | |
CN110458681A (en) | A kind of method, apparatus, server and the storage medium of data reconciliation decision | |
US20200394904A1 (en) | Metering data management system and computer readable recording medium | |
CN109257244A (en) | Transfer control method, the apparatus and system of user behavior data | |
CN109388589A (en) | A kind of method, equipment and storage medium adjusting cache partitions ratio | |
CN107018039B (en) | Method and device for testing performance bottleneck of server cluster | |
CN103338131A (en) | Method and equipment for testing log transmitting loss rate | |
CN117009283A (en) | Multi-core multi-chip data processing method, device, chip and storage medium | |
CN109120731B (en) | Universal communication method, system and device | |
US20230063599A1 (en) | Edge computing network, data transmission method and apparatus, device and storage medium | |
CN107798009A (en) | Data aggregation method, apparatus and system | |
JP6243906B2 (en) | Method and device for providing communication connections for multiple candidate applications within a mobile device | |
CN109818851A (en) | A kind of information persistence method, device and electronic equipment | |
CN105389205B (en) | A kind of information processing method and electronic equipment | |
CN104301806A (en) | Video recognition method, device and system | |
US9479579B2 (en) | Grouping processing method and system | |
JP2015528260A5 (en) | ||
CN103888586A (en) | Data transmission method and terminal | |
CN106230928A (en) | A kind of method and device of files passe | |
CN114253710A (en) | Processing method of computing request, intelligent terminal, cloud server, equipment and medium |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20221123 Address after: 1402, Floor 14, Block A, Haina Baichuan Headquarters Building, No. 6, Baoxing Road, Haibin Community, Xin'an Street, Bao'an District, Shenzhen, Guangdong 518133 Patentee after: Shenzhen Yayue Technology Co.,Ltd. Address before: 2, 518000, East 403 room, SEG science and Technology Park, Zhenxing Road, Shenzhen, Guangdong, Futian District Patentee before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |
|
TR01 | Transfer of patent right |