CN106227743A - Advertisement target group touches and reaches ratio estimation method and device - Google Patents
Advertisement target group touches and reaches ratio estimation method and device Download PDFInfo
- Publication number
- CN106227743A CN106227743A CN201610548202.9A CN201610548202A CN106227743A CN 106227743 A CN106227743 A CN 106227743A CN 201610548202 A CN201610548202 A CN 201610548202A CN 106227743 A CN106227743 A CN 106227743A
- Authority
- CN
- China
- Prior art keywords
- data
- sample
- users
- attribute
- user
- 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of advertisement target group to touch to reach ratio estimation method and device, and wherein method includes: obtaining the Sample Storehouse data in Hbase data base, Sample Storehouse data include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Attribute data includes the data of at least one attribute of sample of users；In acquisition Hbase data base, before current time, in the first preset time period, the Monitoring Data of the first user colony reached is touched in advertisement；Use Hadoop framework that the Monitoring Data of first user colony and Sample Storehouse data are carried out distributed matcher, obtain and enliven Sample Storehouse data；Touched the Monitoring Data of the second user group reached according to advertisement in the second preset time period before enlivening the weighted value of each sample populations in Sample Storehouse data and current time to calculate the tactile of target group in the second user group and reach ratio, thus by Hbase data base and the employing of Hadoop framework, the customer volume of monitoring can be increased, and improve computation rate and computational efficiency by Distributed Calculation.
Description
Technical field
The present invention relates to communication technical field, particularly relate to a kind of advertisement target group and touch and reach ratio estimation method and dress
Put.
Background technology
At present, touching advertisement target group and reach in the method that ratio is estimated, the advertisement throwing in advertiser is supervised
Survey, obtain advertisement and touched the Monitoring Data of the user group reached, Monitoring Data is saved in MySQL number with the form of MongoDB
According in storehouse, Monitoring Data is mated with investigating the Sample Storehouse data obtained in advance, obtain Sample Storehouse data and Monitoring Data
Between common factor, and then occured simultaneously by this to calculate and obtain the tactile of target group in Sample Storehouse data and reach ratio.
But in prior art, MySQL database can only support to store sample data or the Monitoring Data of million users, difficult
To meet the storage demand that the Monitoring Data of ten million user reached is touched in advertisement；It addition, the data of MySQL database typically store
In Single-Server internal memory, doing the tactile ratio calculation that reaches in Single-Server internal memory, calculating speed is slow, is not suitable for millions data
Calculating, thus reduce assessment speed and assessment efficiency.
Summary of the invention
The present invention provides a kind of advertisement target group to touch to reach ratio estimation method and device, be used for solving to comment in prior art
Estimate speed and assess inefficient problem.
The first aspect of the invention is to provide a kind of advertisement target group and touches and reach ratio estimation method, including:
Obtaining the Sample Storehouse data in Hbase data base, described Sample Storehouse data include: the attribute number of each sample of users
According to this and correspondence advertising equipment mark；Described attribute data includes the data of at least one attribute of described sample of users；
In acquisition Hbase data base, before current time, in the first preset time period, the first user colony reached is touched in advertisement
Monitoring Data, the Monitoring Data of described first user colony includes: in first user colony the attribute data of each user with
And the advertising equipment mark of correspondence；
Hadoop framework is used to carry out distributed by the Monitoring Data of described first user colony with described Sample Storehouse data
Coupling, obtains and enlivens Sample Storehouse data, and described Sample Storehouse data of enlivening include: each enliven the attribute data of sample of users with
And the advertising equipment mark of correspondence；
Obtaining and described enliven the weighted value of each sample populations in Sample Storehouse data, each in described sample populations enlivens
Sample of users has the first identical attribute；
Before obtaining current time, in the second preset time period, the Monitoring Data of the second user group reached is touched in advertisement；
Mesh in described second user group is calculated according to the described weighted value enlivening each sample populations in Sample Storehouse data
Mark the tactile of colony reaches ratio.
Further, described acquisition Sample Storehouse data, including:
Obtain the attribute data of each sample of users and the advertising equipment mark of correspondence；
Judge whether the attribute data of described sample of users exists default attribute, and the data of the attribute preset are
No is empty；
If there is default attribute in the attribute data of described sample of users, and the data of the attribute preset are not empty, then
The attribute data of described sample of users and the advertising equipment mark of correspondence are stored in described Sample Storehouse.
Further, described employing Hadoop framework is by the Monitoring Data of described first user colony and described Sample Storehouse number
According to carrying out distributed matcher, obtain and enliven Sample Storehouse data, including:
For each sample of users in described Sample Storehouse data, it is judged that the Monitoring Data of described first user colony is
The advertising equipment mark of the no attribute data including described sample of users and correspondence；
If the Monitoring Data of described first user colony includes the attribute data of described sample of users and correspondence
Advertising equipment identifies, it is determined that described sample of users is for enlivening sample of users；
If the Monitoring Data of described first user colony does not include attribute data and the correspondence of described sample of users
Advertising equipment mark, it is determined that described sample of users is inactive sample of users.
Further, described acquisition is described enlivens the weighted value of each sample populations in Sample Storehouse data, described sample cluster
Each in body enlivens sample of users and has the first identical attribute, including:
Obtain the attribute data of all users, according to described first attribute, all users are divided, obtain each group
Body and the accounting of each colony；
Obtain and described enliven the accounting of each sample populations in Sample Storehouse data；
For described each sample populations enlivened in Sample Storehouse data, by the accounting of described sample populations and all users
Attribute data in the ratio of accounting of corresponding colony be defined as the weighted value of described sample populations；Described sample populations and institute
The colony stating correspondence has the first identical attribute.
Further, described according to the described weighted value calculating described second enlivening each sample populations in Sample Storehouse data
In user group, the tactile of target group reaches ratio, including:
Obtaining and enliven the target group in Sample Storehouse data, each sample of users of enlivening in described target group has default
Attribute data and correspondence advertising equipment mark；
To enliven weighted value sum corresponding to sample of users corresponding with each user in the second user group by each in target group
The ratio of weighted value sum be defined as the tactile of target group in described second user group and reach ratio.
In the present invention, it is provided that a kind of advertisement target group touches and reaches ratio estimation method, by obtaining in Hbase data base
Sample Storehouse data, described Sample Storehouse data include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Institute
State the data that attribute data includes at least one attribute of described sample of users；Obtain in Hbase data base current time it
In front first preset time period, the Monitoring Data of the first user colony reached is touched in advertisement；Use Hadoop framework by described first
The Monitoring Data of user group and described Sample Storehouse data carry out distributed matcher, obtain and enliven Sample Storehouse data；According to active
In Sample Storehouse data, before the weighted value of each sample populations and current time, advertisement is touched and is reached in the second preset time period
The Monitoring Data of the second user group calculates the tactile ratio that reaches of target group in the second user group, thus by Hbase data
Storehouse and the employing of Hadoop framework, it is possible to increase the customer volume of monitoring, and improve computation rate and calculating by Distributed Calculation
Efficiency.
The second aspect of the invention is to provide a kind of advertisement target group and touches and reach ratio estimation device, including:
First acquisition module, for obtaining the Sample Storehouse data in Hbase data base, described Sample Storehouse data include:
The attribute data of each sample of users and the advertising equipment mark of correspondence；Described attribute data includes described sample of users extremely
The data of a few attribute；
Second acquisition module, is used for obtaining in Hbase data base before current time advertisement institute in the first preset time period
Touching the Monitoring Data of the first user colony reached, the Monitoring Data of described first user colony includes: in first user colony
The attribute data of each user and the advertising equipment mark of correspondence；
Matching module, for using Hadoop framework by the Monitoring Data of described first user colony and described Sample Storehouse number
According to carrying out distributed matcher, obtaining and enliven Sample Storehouse data, described Sample Storehouse data of enlivening include: each enlivens sample of users
Attribute data and correspondence advertising equipment mark；
3rd acquisition module, described enlivens the weighted value of each sample populations in Sample Storehouse data, described sample for obtaining
Each in in-group enlivens sample of users and has the first identical attribute；
4th acquisition module, before obtaining current time, in the second preset time period, the second user reached is touched in advertisement
The Monitoring Data of colony；
Computing module, for calculating described second according to the described weighted value enlivening each sample populations in Sample Storehouse data
In user group, the tactile of target group reaches ratio.
Further, described first acquisition module includes:
First acquiring unit, the advertising equipment mark of attribute data and correspondence for obtaining each sample of users；
Whether the first judging unit, exist default attribute in the attribute data judging described sample of users, and
Whether the data of the attribute preset are empty；
It is stored in unit, for there is default attribute in the attribute data of described sample of users, and the attribute preset
When data are not empty, the attribute data of described sample of users and the advertising equipment mark of correspondence are stored in described Sample Storehouse.
Further, described matching module includes:
Second judging unit, for for each sample of users in described Sample Storehouse data, it is judged that described first user
Whether the Monitoring Data of colony includes the attribute data of described sample of users and the advertising equipment mark of correspondence；
First determines unit, for including the genus of described sample of users in the Monitoring Data of described first user colony
Property data and correspondence advertising equipment mark time, determine that described sample of users is for enlivening sample of users；
Second determines unit, for not including described sample of users in the Monitoring Data of described first user colony
When the advertising equipment of attribute data and correspondence identifies, determine that described sample of users is inactive sample of users.
Further, described 3rd acquisition module includes:
All users, for obtaining the attribute data of all users, are entered by second acquisition unit according to described first attribute
Row divides, and obtains the accounting of each colony and each colony；
3rd acquiring unit, described enlivens the accounting of each sample populations in Sample Storehouse data for obtaining；
3rd determines unit, for for described each sample populations enlivened in Sample Storehouse data, by described sample cluster
The ratio of the accounting of the colony that the accounting of body is corresponding with the attribute data of all users is defined as the weighting of described sample populations
Value；Described sample populations has the first identical attribute with described corresponding colony.
Further, described computing module includes:
4th acquiring unit, enlivens the target group in Sample Storehouse data for obtaining, each work in described target group
The sample of users that jumps has the advertising equipment mark of default attribute data and correspondence；
4th determines unit, for enlivening weighted value sum corresponding to sample of users and the second user by each in target group
During in colony, the ratio of the weighted value sum that each user is corresponding is defined as described second user group, the tactile of target group reaches ratio.
In the present invention, it is provided that a kind of advertisement target group touches and reaches ratio estimation device, by obtaining in Hbase data base
Sample Storehouse data, described Sample Storehouse data include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Institute
State the data that attribute data includes at least one attribute of described sample of users；Obtain in Hbase data base current time it
In front first preset time period, the Monitoring Data of the first user colony reached is touched in advertisement；Use Hadoop framework by described first
The Monitoring Data of user group and described Sample Storehouse data carry out distributed matcher, obtain and enliven Sample Storehouse data；According to active
In Sample Storehouse data, before the weighted value of each sample populations and current time, advertisement is touched and is reached in the second preset time period
The Monitoring Data of the second user group calculates the tactile ratio that reaches of target group in the second user group, thus by Hbase data
Storehouse and the employing of Hadoop framework, it is possible to increase the customer volume of monitoring, and improve computation rate and calculating by Distributed Calculation
Efficiency.
Accompanying drawing explanation
Fig. 1 touches the flow chart reaching one embodiment of ratio estimation method for the advertisement target group that the present invention provides；
Fig. 2 touches the flow chart reaching ratio estimation another embodiment of method for the advertisement target group that the present invention provides；
Fig. 3 touches the structural representation reaching one embodiment of ratio estimation device for the advertisement target group that the present invention provides；
Fig. 4 touches the structural representation reaching ratio estimation another embodiment of device for the advertisement target group that the present invention provides
Figure；
Fig. 5 touches the structural representation reaching ratio estimation another embodiment of device for the advertisement target group that the present invention provides
Figure；
Fig. 6 touches the structural representation reaching ratio estimation another embodiment of device for the advertisement target group that the present invention provides
Figure；
Fig. 7 touches the structural representation reaching ratio estimation another embodiment of device for the advertisement target group that the present invention provides
Figure.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
Fig. 1 touches the flow chart reaching one embodiment of ratio estimation method for the advertisement target group that the present invention provides, such as Fig. 1
Shown in, including:
Step 101, obtains the Sample Storehouse data in Hbase data base, and described Sample Storehouse data include: each sample of users
Attribute data and correspondence advertising equipment mark；Described attribute data includes at least one attribute of described sample of users
Data.
The advertisement target group that the present invention provides touches that to reach the executive agent of ratio estimation method can be advertisement target group
Touching and reach ratio estimation device, advertisement target group touches and reaches ratio estimation device and be specifically as follows hardware device or be arranged on hardware
Software etc. on equipment, can be configured as required.
Wherein, Hbase data base can support mass memory and rapid extraction, and the row of Hbase are extendible, and
And unrestricted, it is possible to meet Sample Storehouse data and the storage of detection data and extraction demand.Need to illustrate, sample
The attribute data of this user specifically may include that the sex of sample of users, age, marital status, education, Income situation etc.
The data of attribute.Corresponding advertising equipment mark can be the mark for throwing in the terminal units such as the computer of advertisement, mobile phone.Electricity
The type of the advertisement thrown in the terminal sadness such as brain, mobile phone can be banner banner or television advertising OTV etc..
Wherein, sample of users can be the user obtained by investigation.Advertisement target group touches and reaches ratio estimation device and obtain
After getting the attribute data of the sample of users that investigation obtains and the advertising equipment mark of correspondence, can first mix the sample with the genus at family
Property data and correspondence advertising equipment mark store with the form of MongoDB, then check the attribute number of sample of users
Whether there is preset attribute according to, and whether value corresponding to preset attribute is empty, and the form of value corresponding to preset attribute
The most correct；If there is not preset attribute in the attribute data of sample of users, or value corresponding to preset attribute is empty, then carry out
Supplement；If the form of the value that preset attribute is corresponding is incorrect, then modify；Supplement or after amendment, mix the sample with the genus at family
Property data and correspondence advertising equipment mark be stored in Sample Storehouse.If the attribute data of sample of users exists preset attribute, and
The value that preset attribute is corresponding is not empty, and the form of value corresponding to preset attribute is correct, the most directly mixes the sample with the attribute number at family
According to this and correspondence advertising equipment mark be stored in Sample Storehouse.
Step 102, in acquisition Hbase data base, before current time, in the first preset time period, first reached is touched in advertisement
The Monitoring Data of user group, the Monitoring Data of described first user colony includes: the genus of each user in first user colony
Property data and correspondence advertising equipment mark.
Wherein, the first preset time period can be the time period such as three months or half a year.
Step 103, uses Hadoop framework the Monitoring Data of described first user colony to be entered with described Sample Storehouse data
Row distributed matcher, obtains and enlivens Sample Storehouse data, and described Sample Storehouse data of enlivening include: each enlivens the genus of sample of users
Property data and correspondence advertising equipment mark.
Wherein, step 103 specifically may include that for each sample of users in described Sample Storehouse data, it is judged that described
Whether the Monitoring Data of first user colony includes the attribute data of described sample of users and the advertising equipment mark of correspondence
Know；If the advertisement of the attribute data and correspondence including described sample of users in the Monitoring Data of described first user colony sets
Standby mark, it is determined that described sample of users is for enlivening sample of users；If the Monitoring Data of described first user colony does not includes
There are the attribute data of described sample of users and the advertising equipment mark of correspondence, it is determined that described sample of users is inactive sample
User.
Step 104, obtains and described enlivens the weighted value of each sample populations in Sample Storehouse data, in described sample populations
Each enlivens sample of users and has the first identical attribute.
Wherein, due to the randomness of sample collection, the composition of residents of sample is uncertain, the normal equipment with in society
It is inconsistent for using composition of residents, in order to ensure crowd's accounting and the concordance of crowd's accounting, the step in society of Sample Storehouse
104 specifically may include that the attribute data obtaining all users, divide all users according to described first attribute,
To each colony and the accounting of each colony；Obtain and described enliven the accounting of each sample populations in Sample Storehouse data；For
Described each sample populations enlivened in Sample Storehouse data, by the accounting of the described sample populations attribute data with all users
The ratio of the accounting of corresponding colony is defined as the weighted value of described sample populations；Described sample populations and described corresponding colony
There is the first identical attribute.
Concrete, all users can refer to the user of the terminal units such as mobile phone, the computer that can get.First attribute can
Think any one or more attributes in sex, age, marital status, education, Income situation etc..Each colony accounts for
Than referring to number of users and the ratio of total number of users in colony.
Step 105, before obtaining current time, in the second preset time period, the prison of the second user group reached is touched in advertisement
Survey data.
Wherein, the second preset time period can be one day, the time period such as two days.
Step 106, calculates described second user according to the described weighted value enlivening each sample populations in Sample Storehouse data
In colony, the tactile of target group reaches ratio.
Wherein, target group are to enliven the colony in Sample Storehouse data, and each sample of users of enlivening in target group has
The attribute data preset and the advertising equipment mark of correspondence.
Further, before step 106, advertisement target group touches and reaches ratio estimation device and can also judge in target group
Number of users whether less than preset value, this sentences the second preset time period is to illustrate, if in target group as a example by one day
Number of users is less than Preset Time, then advertisement target group touches and reaches ratio estimation device and can obtain current time one before a day
In it time period, advertisement is touched the detection data of the second user group reached and is carried out the tactile calculating reaching ratio of target group.
It addition, the tactile ratio estimation device that reaches of advertisement target group can also be by above-mentioned result of calculation synchronized update to externally
Api interface shows, to ensure the concordance of data everywhere.
The advertisement target group that the present embodiment provides touches and reaches in ratio estimation method, by obtaining in Hbase data base
Sample Storehouse data, described Sample Storehouse data include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Institute
State the data that attribute data includes at least one attribute of described sample of users；Obtain in Hbase data base current time it
In front first preset time period, the Monitoring Data of the first user colony reached is touched in advertisement；Use Hadoop framework by described first
The Monitoring Data of user group and described Sample Storehouse data carry out distributed matcher, obtain and enliven Sample Storehouse data；According to active
In Sample Storehouse data, before the weighted value of each sample populations and current time, advertisement is touched and is reached in the second preset time period
The Monitoring Data of the second user group calculates the tactile ratio that reaches of target group in the second user group, thus by Hbase data
Storehouse and the employing of Hadoop framework, it is possible to increase the customer volume of monitoring, and improve computation rate and calculating by Distributed Calculation
Efficiency.
Fig. 2 touches the flow chart reaching ratio estimation another embodiment of method for the advertisement target group that the present invention provides, as
Shown in Fig. 2, on the basis of embodiment illustrated in fig. 1, step 106 may include that
Step 1061, obtains and enlivens the target group in Sample Storehouse data, and each sample that enlivens in described target group is used
Family has the advertising equipment mark of default attribute data and correspondence.
Step 1062, by target group each enliven in weighted value sum corresponding to sample of users and the second user group each
The ratio of the weighted value sum that user is corresponding is defined as the tactile of target group in described second user group and reaches ratio.
Such as, if the number of users in the second user group is n, the number of users in target group is m, then target group
The tactile weighted value sum reaching colony corresponding to weighted value sum that ratio is target group corresponding to m user/n user.
A kind of advertisement target group of the present embodiment offer touches and reaches ratio estimation method, by obtaining in Hbase data base
Sample Storehouse data, described Sample Storehouse data include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Institute
State the data that attribute data includes at least one attribute of described sample of users；Obtain in Hbase data base current time it
In front first preset time period, the Monitoring Data of the first user colony reached is touched in advertisement；Use Hadoop framework by described first
The Monitoring Data of user group and described Sample Storehouse data carry out distributed matcher, obtain and enliven Sample Storehouse data；Obtain active
Target group in Sample Storehouse data, each in described target group enlivens sample of users and has default attribute data and right
The advertising equipment mark answered；By in target group each enliven in weighted value sum corresponding to sample of users and the second user group each
The ratio of the weighted value sum that user is corresponding is defined as the tactile ratio that reaches of target group in described second user group, thus passes through
Hbase data base and the employing of Hadoop framework, it is possible to increase the customer volume of monitoring, and improve calculating speed by Distributed Calculation
Rate and computational efficiency.
One of ordinary skill in the art will appreciate that: all or part of step realizing above-mentioned each method embodiment can be led to
The hardware crossing programmed instruction relevant completes.Aforesaid program can be stored in a computer read/write memory medium.This journey
Sequence upon execution, performs to include the step of above-mentioned each method embodiment；And aforesaid storage medium includes: ROM, RAM, magnetic disc or
The various media that can store program code such as person's CD.
Fig. 3 touches the structural representation reaching one embodiment of ratio estimation device for the advertisement target group that the present invention provides,
As it is shown on figure 3, include:
First acquisition module 31, for obtaining the Sample Storehouse data in Hbase data base, wraps in described Sample Storehouse data
Include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Described attribute data includes described sample of users
The data of at least one attribute；
Second acquisition module 32, is used for obtaining advertisement in the first preset time period before current time in Hbase data base
Being touched the Monitoring Data of the first user colony reached, the Monitoring Data of described first user colony includes: first user colony
In the attribute data of each user and the advertising equipment mark of correspondence；
Matching module 33, for using Hadoop framework by the Monitoring Data of described first user colony and described Sample Storehouse
Data carry out distributed matcher, obtain and enliven Sample Storehouse data, and described Sample Storehouse data of enlivening include: each enlivens sample and uses
The attribute data at family and the advertising equipment mark of correspondence；
3rd acquisition module 34, described enlivens the weighted value of each sample populations in Sample Storehouse data for obtaining, described
Each in sample populations enlivens sample of users and has the first identical attribute；
4th acquisition module 35, before obtaining current time, in the second preset time period, the second use reached is touched in advertisement
The Monitoring Data of family colony；
Computing module 36, for calculating described the according to the described weighted value enlivening each sample populations in Sample Storehouse data
In two user groups, the tactile of target group reaches ratio.
Wherein, the advertisement target group that the present invention provides touches and reaches ratio estimation device and be specifically as follows hardware device or peace
The software etc. being contained on hardware device, can be configured as required.Hbase data base can support mass memory and fast
Speed is extracted, and the row of Hbase are extendible, and unrestrictedly, it is possible to meet Sample Storehouse data and the storage of detection data
And extraction demand.Need illustrate, the attribute data of sample of users specifically may include that sample of users sex,
The data of the attributes such as age, marital status, education, Income situation.Corresponding advertising equipment mark can be to be used for throwing in
The mark of the terminal units such as the computer of advertisement, mobile phone.The type of the advertisement thrown in the terminal sadness such as computer, mobile phone can be horizontal
Width advertisement banner or television advertising OTV etc..
The advertisement target group that the present embodiment provides touches and reaches ratio estimation device, by obtaining the sample in Hbase data base
This database data, described Sample Storehouse data include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Described
Attribute data includes the data of at least one attribute of described sample of users；In acquisition Hbase data base before current time
In first preset time period, the Monitoring Data of the first user colony reached is touched in advertisement；Hadoop framework is used to use described first
The Monitoring Data of family colony and described Sample Storehouse data carry out distributed matcher, obtain and enliven Sample Storehouse data；According to enlivening sample
In this database data, before the weighted value of each sample populations and current time, in the second preset time period, reached is touched in advertisement
The Monitoring Data of two user groups calculates the tactile ratio that reaches of target group in the second user group, thus by Hbase data base
Employing with Hadoop framework, it is possible to increase the customer volume of monitoring, and improve computation rate by Distributed Calculation and calculate effect
Rate.
Further, as shown in Figure 4, the advertisement target group that Fig. 4 provides for the present invention touches that to reach ratio estimation device another
The structural representation of individual embodiment, on the basis of embodiment illustrated in fig. 3, described first acquisition module 31 includes:
First acquiring unit 311, the advertising equipment mark of attribute data and correspondence for obtaining each sample of users；
Whether the first judging unit 312, exist default attribute in the attribute data judging described sample of users, with
And whether the data of the attribute preset are empty；
It is stored in unit 313, for there is default attribute in the attribute data of described sample of users, and the attribute preset
Data when not being empty, the attribute data of described sample of users and the advertising equipment mark of correspondence are stored in described Sample Storehouse
In.
Further, as it is shown in figure 5, the advertisement target group that Fig. 5 provides for the present invention touches, to reach ratio estimation device another
The structural representation of individual embodiment, on the basis of embodiment illustrated in fig. 3, described matching module 33 includes:
Second judging unit 331, for for each sample of users in described Sample Storehouse data, it is judged that described first uses
Whether the Monitoring Data of family colony includes the attribute data of described sample of users and the advertising equipment mark of correspondence；
First determines unit 332, for including described sample of users in the Monitoring Data of described first user colony
Attribute data and correspondence advertising equipment mark time, determine that described sample of users is for enlivening sample of users；
Second determines unit 333, uses for not including described sample in the Monitoring Data of described first user colony
When the attribute data at family and the advertising equipment of correspondence identify, determine that described sample of users is inactive sample of users.
Further, as shown in Figure 6, the advertisement target group that Fig. 6 provides for the present invention touches that to reach ratio estimation device another
The structural representation of individual embodiment, on the basis of embodiment illustrated in fig. 3, described 3rd acquisition module 34 includes:
Second acquisition unit 341, for obtaining the attribute data of all users, according to described first attribute to all users
Divide, obtain the accounting of each colony and each colony；
3rd acquiring unit 342, described enlivens the accounting of each sample populations in Sample Storehouse data for obtaining；
3rd determines unit 343, for for described each sample populations enlivened in Sample Storehouse data, by described sample
The ratio of the accounting of the colony that the accounting of colony is corresponding with the attribute data of all users is defined as adding of described sample populations
Weights；Described sample populations has the first identical attribute with described corresponding colony.
Further, as it is shown in fig. 7, the advertisement target group that Fig. 7 provides for the present invention touches, to reach ratio estimation device another
The structural representation of individual embodiment, on the basis of embodiment illustrated in fig. 3, described computing module 36 includes:
4th acquiring unit 361, enlivens the target group in Sample Storehouse data for obtaining, each in described target group
Enliven sample of users and there is the advertising equipment mark of default attribute data and correspondence；
4th determines unit 362, for enlivening, by each in target group, the weighted value sum and second that sample of users is corresponding
During in user group, the ratio of the weighted value sum that each user is corresponding is defined as described second user group, the tactile of target group reaches
Ratio.
Further, computing module 36 calculates institute according to the described weighted value enlivening each sample populations in Sample Storehouse data
Stating before target group in the second user group tactile reach ratio, advertisement target group touches and reaches ratio estimation device and can also judge
Whether the number of users in target group is less than preset value, and this sentences the second preset time period is to illustrate as a example by one day, if mesh
Number of users in mark colony is less than Preset Time, then advertisement target group touches and reaches ratio estimation device and can obtain current time one
In the time period before it, advertisement is touched the detection data of the second user group reached and is carried out the tactile of target group and reach ratio
Calculating.
It addition, the tactile ratio estimation device that reaches of advertisement target group can also be by above-mentioned result of calculation synchronized update to externally
Api interface shows, to ensure the concordance of data everywhere.
The advertisement target group that the present embodiment provides touches and reaches in ratio estimation device, by obtaining in Hbase data base
Sample Storehouse data, described Sample Storehouse data include: the attribute data of each sample of users and the advertising equipment mark of correspondence；Institute
State the data that attribute data includes at least one attribute of described sample of users；Obtain in Hbase data base current time it
In front first preset time period, the Monitoring Data of the first user colony reached is touched in advertisement；Use Hadoop framework by described first
The Monitoring Data of user group and described Sample Storehouse data carry out distributed matcher, obtain and enliven Sample Storehouse data；According to active
In Sample Storehouse data, before the weighted value of each sample populations and current time, advertisement is touched and is reached in the second preset time period
The Monitoring Data of the second user group calculates the tactile ratio that reaches of target group in the second user group, thus by Hbase data
Storehouse and the employing of Hadoop framework, it is possible to increase the customer volume of monitoring, and improve computation rate and calculating by Distributed Calculation
Efficiency.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, it is not intended to limit；To the greatest extent
The present invention has been described in detail by pipe with reference to foregoing embodiments, it will be understood by those within the art that: it depends on
So the technical scheme described in foregoing embodiments can be modified, or the most some or all of technical characteristic is entered
Row equivalent；And these amendments or replacement, do not make the essence of appropriate technical solution depart from various embodiments of the present invention technology
The scope of scheme.
Claims (10)
1. an advertisement target group touches and reaches ratio estimation method, it is characterised in that including:
Obtaining the Sample Storehouse data in Hbase data base, described Sample Storehouse data include: the attribute data of each sample of users with
And the advertising equipment mark of correspondence；Described attribute data includes the data of at least one attribute of described sample of users；
In acquisition Hbase data base, before current time, in the first preset time period, the prison of the first user colony reached is touched in advertisement
Surveying data, the Monitoring Data of described first user colony includes: the attribute data of each user and right in first user colony
The advertising equipment mark answered；
Use Hadoop framework that the Monitoring Data of described first user colony and described Sample Storehouse data are carried out distributed matcher,
Acquisition enlivens Sample Storehouse data, and described Sample Storehouse data of enlivening include: each enlivens the attribute data of sample of users and right
The advertising equipment mark answered；
Obtaining and described enliven the weighted value of each sample populations in Sample Storehouse data, each in described sample populations enlivens sample
User has the first identical attribute；
Before obtaining current time, in the second preset time period, the Monitoring Data of the second user group reached is touched in advertisement；
Target complex in described second user group is calculated according to the described weighted value enlivening each sample populations in Sample Storehouse data
The tactile of body reaches ratio.
Method the most according to claim 1, it is characterised in that described acquisition Sample Storehouse data, including:
Obtain the attribute data of each sample of users and the advertising equipment mark of correspondence；
Judge whether the attribute data of described sample of users exists default attribute, and whether the data of the attribute preset are
Empty；
If there is default attribute in the attribute data of described sample of users, and the data of the attribute preset are not empty, then by institute
The advertising equipment mark of the attribute data and correspondence of stating sample of users is stored in described Sample Storehouse.
Method the most according to claim 1, it is characterised in that described employing Hadoop framework is by described first user colony
Monitoring Data and described Sample Storehouse data carry out distributed matcher, obtain and enliven Sample Storehouse data, including:
For each sample of users in described Sample Storehouse data, it is judged that whether the Monitoring Data of described first user colony wraps
Include the attribute data of described sample of users and the advertising equipment mark of correspondence；
If the Monitoring Data of described first user colony includes the attribute data of described sample of users and the advertisement of correspondence
Device identification, it is determined that described sample of users is for enlivening sample of users；
If the Monitoring Data of described first user colony does not include the attribute data of described sample of users and the wide of correspondence
Accuse device identification, it is determined that described sample of users is inactive sample of users.
Method the most according to claim 1, it is characterised in that described acquisition is described enlivens each sample in Sample Storehouse data
The weighted value of colony, each in described sample populations enlivens sample of users and has the first identical attribute, including:
Obtain the attribute data of all users, according to described first attribute, all users divided, obtain each colony with
And the accounting of each colony；
Obtain and described enliven the accounting of each sample populations in Sample Storehouse data；
For described each sample populations enlivened in Sample Storehouse data, by the genus of the accounting of described sample populations Yu all users
Property data in the ratio of accounting of corresponding colony be defined as the weighted value of described sample populations；Described sample populations is right with described
The colony answered has the first identical attribute.
Method the most according to claim 1, it is characterised in that described enliven each sample in Sample Storehouse data according to described
The weighted value of colony calculates the tactile of target group in described second user group and reaches ratio, including:
Obtaining and enliven the target group in Sample Storehouse data, each sample of users of enlivening in described target group has default genus
Property data and correspondence advertising equipment mark；
Weighted value sum corresponding to sample of users and corresponding the adding of each user in the second user group is enlivened by each in target group
The ratio of weights sum is defined as the tactile of target group in described second user group and reaches ratio.
6. an advertisement target group touches and reaches ratio estimation device, it is characterised in that including:
First acquisition module, for obtaining the Sample Storehouse data in Hbase data base, described Sample Storehouse data include: various kinds
The attribute data of this user and the advertising equipment mark of correspondence；Described attribute data includes at least the one of described sample of users
The data of individual attribute；
Second acquisition module, is used for obtaining in Hbase data base before current time advertisement in the first preset time period and is touched and reach
The Monitoring Data of first user colony, the Monitoring Data of described first user colony includes: respectively use in first user colony
The attribute data at family and the advertising equipment mark of correspondence；
Matching module, for using Hadoop framework the Monitoring Data of described first user colony to be entered with described Sample Storehouse data
Row distributed matcher, obtains and enlivens Sample Storehouse data, and described Sample Storehouse data of enlivening include: each enlivens the genus of sample of users
Property data and correspondence advertising equipment mark；
3rd acquisition module, described enlivens the weighted value of each sample populations in Sample Storehouse data, described sample cluster for obtaining
Each in body enlivens sample of users and has the first identical attribute；
4th acquisition module, before obtaining current time, in the second preset time period, the second user group reached is touched in advertisement
Monitoring Data；
Computing module, for calculating described second user according to the described weighted value enlivening each sample populations in Sample Storehouse data
In colony, the tactile of target group reaches ratio.
Device the most according to claim 6, it is characterised in that described first acquisition module includes:
First acquiring unit, the advertising equipment mark of attribute data and correspondence for obtaining each sample of users；
Whether the first judging unit, exist default attribute in the attribute data judging described sample of users, and preset
The data of attribute be whether empty；
It is stored in unit, for there is default attribute in the attribute data of described sample of users, and the data of the attribute preset
When not being empty, the attribute data of described sample of users and the advertising equipment mark of correspondence are stored in described Sample Storehouse.
Device the most according to claim 6, it is characterised in that described matching module includes:
Second judging unit, for for each sample of users in described Sample Storehouse data, it is judged that described first user colony
Monitoring Data in whether include the advertising equipment mark of the attribute data of described sample of users and correspondence；
First determines unit, for including the attribute number of described sample of users in the Monitoring Data of described first user colony
According to this and correspondence advertising equipment mark time, determine that described sample of users is for enlivening sample of users；
Second determines unit, for not including the attribute of described sample of users in the Monitoring Data of described first user colony
When the advertising equipment of data and correspondence identifies, determine that described sample of users is inactive sample of users.
Device the most according to claim 6, it is characterised in that described 3rd acquisition module includes:
All users, for obtaining the attribute data of all users, are carried out drawing by second acquisition unit according to described first attribute
Point, obtain the accounting of each colony and each colony；
3rd acquiring unit, described enlivens the accounting of each sample populations in Sample Storehouse data for obtaining；
3rd determines unit, for for described each sample populations enlivened in Sample Storehouse data, by described sample populations
The ratio of the accounting of the colony that accounting is corresponding with the attribute data of all users is defined as the weighted value of described sample populations；Institute
State sample populations, with described corresponding colony, there is the first identical attribute.
Device the most according to claim 6, it is characterised in that described computing module includes:
4th acquiring unit, enlivens the target group in Sample Storehouse data for obtaining, and each in described target group enlivens sample
This user has the advertising equipment mark of default attribute data and correspondence；
4th determines unit, for enlivening weighted value sum corresponding to sample of users and the second user group by each in target group
In the ratio of weighted value sum corresponding to each user be defined as the tactile of target group in described second user group and reach ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610548202.9A CN106227743B (en) | 2016-07-12 | 2016-07-12 | Advertisement target group touching reaches ratio estimation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610548202.9A CN106227743B (en) | 2016-07-12 | 2016-07-12 | Advertisement target group touching reaches ratio estimation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106227743A true CN106227743A (en) | 2016-12-14 |
| CN106227743B CN106227743B (en) | 2019-09-24 |
Family
ID=57520166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610548202.9A Active CN106227743B (en) | 2016-07-12 | 2016-07-12 | Advertisement target group touching reaches ratio estimation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106227743B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064209A (en) * | 2018-06-28 | 2018-12-21 | 四川斐讯信息技术有限公司 | A kind of advertisement placement method and server based on portfolio |
| CN109101562A (en) * | 2018-07-13 | 2018-12-28 | 中国平安人寿保险股份有限公司 | Find method, apparatus, computer equipment and the storage medium of target group |
| CN110428277A (en) * | 2019-06-26 | 2019-11-08 | 平安科技（深圳）有限公司 | The touching of recommended products reaches method, storage medium and program product |
| CN110796465A (en) * | 2018-08-03 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Resource display equipment determining method, advertisement display screen determining method and device |
| CN113079057A (en) * | 2021-03-12 | 2021-07-06 | 北京明略昭辉科技有限公司 | Flow monitoring system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663617A (en) * | 2012-03-20 | 2012-09-12 | 亿赞普(北京)科技有限公司 | Method and system for prediction of advertisement clicking rate |
| CN102880688A (en) * | 2012-09-14 | 2013-01-16 | 北京百度网讯科技有限公司 | Method, device and equipment for evaluating webpage |
| CN103971257A (en) * | 2013-01-28 | 2014-08-06 | 北京思博途信息技术有限公司 | Estimation method and system for internet media combination putting effect |
| US20150066646A1 (en) * | 2013-08-27 | 2015-03-05 | Yahoo! Inc. | Spark satellite clusters to hadoop data stores |
| CN104794184A (en) * | 2014-12-15 | 2015-07-22 | 安徽四创电子股份有限公司 | Illegal car identifying method utilizing Bayesian classification algorithm based on massive data |
| CN104933591A (en) * | 2014-03-17 | 2015-09-23 | 北京学之途网络科技有限公司 | Method and device for achieving advertisement putting based on real-time data |
| CN105184611A (en) * | 2015-09-08 | 2015-12-23 | 精硕世纪科技（北京）有限公司 | Advertising effect quantification method and display system |
| CN105653645A (en) * | 2015-12-28 | 2016-06-08 | 精硕世纪科技（北京）有限公司 | Network information attention assessment method and device |
-
2016
- 2016-07-12 CN CN201610548202.9A patent/CN106227743B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663617A (en) * | 2012-03-20 | 2012-09-12 | 亿赞普(北京)科技有限公司 | Method and system for prediction of advertisement clicking rate |
| CN102880688A (en) * | 2012-09-14 | 2013-01-16 | 北京百度网讯科技有限公司 | Method, device and equipment for evaluating webpage |
| CN103971257A (en) * | 2013-01-28 | 2014-08-06 | 北京思博途信息技术有限公司 | Estimation method and system for internet media combination putting effect |
| US20150066646A1 (en) * | 2013-08-27 | 2015-03-05 | Yahoo! Inc. | Spark satellite clusters to hadoop data stores |
| CN104933591A (en) * | 2014-03-17 | 2015-09-23 | 北京学之途网络科技有限公司 | Method and device for achieving advertisement putting based on real-time data |
| CN104794184A (en) * | 2014-12-15 | 2015-07-22 | 安徽四创电子股份有限公司 | Illegal car identifying method utilizing Bayesian classification algorithm based on massive data |
| CN105184611A (en) * | 2015-09-08 | 2015-12-23 | 精硕世纪科技（北京）有限公司 | Advertising effect quantification method and display system |
| CN105653645A (en) * | 2015-12-28 | 2016-06-08 | 精硕世纪科技（北京）有限公司 | Network information attention assessment method and device |
Non-Patent Citations (2)
| Title |
|---|
| ZHI QIU ET AL.: "Research of Hadoop-based data flow management system", 《THE JOURNAL OF CHINA UNIVERSITIES OF POSTS AND TELECOMMUNICATIONS》 * |
| 束雯: "广播电视广告监管系统应用", 《信息通信》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064209A (en) * | 2018-06-28 | 2018-12-21 | 四川斐讯信息技术有限公司 | A kind of advertisement placement method and server based on portfolio |
| CN109101562A (en) * | 2018-07-13 | 2018-12-28 | 中国平安人寿保险股份有限公司 | Find method, apparatus, computer equipment and the storage medium of target group |
| CN109101562B (en) * | 2018-07-13 | 2023-07-21 | 中国平安人寿保险股份有限公司 | Method, device, computer equipment and storage medium for searching target group |
| CN110796465A (en) * | 2018-08-03 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Resource display equipment determining method, advertisement display screen determining method and device |
| CN110428277A (en) * | 2019-06-26 | 2019-11-08 | 平安科技（深圳）有限公司 | The touching of recommended products reaches method, storage medium and program product |
| CN110428277B (en) * | 2019-06-26 | 2023-05-30 | 平安科技（深圳）有限公司 | Touch method of recommended product, storage medium and program product |
| CN113079057A (en) * | 2021-03-12 | 2021-07-06 | 北京明略昭辉科技有限公司 | Flow monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106227743B (en) | 2019-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106227743A (en) | Advertisement target group touches and reaches ratio estimation method and device | |
| US10643110B2 (en) | Systems and methods for inferential sharing of photos | |
| CN110992169B (en) | Risk assessment method, risk assessment device, server and storage medium | |
| CN109474483A (en) | A kind of detection method, detection device and the terminal device of unit exception situation | |
| CN108921221A (en) | Generation method, device, equipment and the storage medium of user characteristics | |
| CN107515890A (en) | A kind of method and terminal for identifying resident point | |
| CN104932966B (en) | Detect that application software downloads the method and device of brush amount | |
| CN107992595A (en) | Learning content recommendation method and device and intelligent equipment | |
| CN108197570A (en) | A kind of demographic method, device, electronic equipment and storage medium | |
| CN107193598A (en) | Application starting method, mobile terminal and computer readable storage medium | |
| CN109274639A (en) | The recognition methods of open platform abnormal data access and device | |
| Akbaş et al. | Social network generation and friend ranking based on mobile phone data | |
| CN111078742B (en) | User classification model training method, user classification method and device | |
| CN109669995A (en) | Data storage, quality calculation method, device, storage medium and server | |
| CN110245980A (en) | The method and apparatus for determining target user's exiting form based on neural network model | |
| CN109194689A (en) | Abnormal behaviour recognition methods, device, server and storage medium | |
| CN108182009A (en) | Terminal, pressure detection method and pressure detecting system | |
| TW201926087A (en) | Question pushing method and device | |
| CN115408696A (en) | Application identification method and electronic equipment | |
| CN110363206A (en) | Cluster, data processing and the data identification method of data object | |
| CN109816410A (en) | The analysis method and device of advertisement major product audience | |
| CN107451036A (en) | Input reminding method, device and equipment | |
| CN109582834A (en) | Data Risk Forecast Method and device | |
| CN104346341B (en) | A kind of realization data and the associated method and device of dependent event | |
| CN106815062A (en) | A kind of business pipelined data processing method and processing device |
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 | ||
| CB02 | Change of applicant information |
Address after: 100041 Beijing, Shijingshan District Xing Xing street, building 30, room 3, building 9, room 9014 Applicant after: Jing Shuo Technology (Beijing) Limited by Share Ltd Address before: 100010 Beijing city Dongcheng District bamboo rod alley No. 1 9 1007 Applicant before: JINGSHUO CENTURY TECHNOLOGY (BEIJING) CO., LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201229 Address after: Floor 29, 30, 31, 32, No. 701, Yunjin Road, Xuhui District, Shanghai, 200030 Patentee after: Shanghai minglue artificial intelligence (Group) Co.,Ltd. Address before: Room 9014, 9 / F, building 3, yard 30, Shixing street, Shijingshan District, Beijing 100041 Patentee before: ADMASTER TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| TR01 | Transfer of patent right |