CN106227743B - Advertisement target group touching reaches ratio estimation method and device - Google Patents
Advertisement target group touching reaches ratio estimation method and device Download PDFInfo
- Publication number
- CN106227743B CN106227743B CN201610548202.9A CN201610548202A CN106227743B CN 106227743 B CN106227743 B CN 106227743B CN 201610548202 A CN201610548202 A CN 201610548202A CN 106227743 B CN106227743 B CN 106227743B
- Authority
- CN
- China
- Prior art keywords
- sample
- data
- users
- attribute
- group
- 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
- G06F16/20—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 touching of advertisement target group up to ratio estimation method and device, and wherein method includes: the sample database data obtained in Hbase database, includes: the attribute data and corresponding advertising equipment mark of each sample of users in sample database data；The data of at least one attribute in attribute data including sample of users；The monitoring data of the first user group reached are touched in advertisement in the first preset time period before current time in acquisition Hbase database；The monitoring data of first user group and sample database data are carried out by distributed matcher using Hadoop frame, acquisition enlivens sample database data；Ratio is reached according to the touching that the weighted value of each sample populations and the monitoring data that the second user group reached is touched in advertisement in the second preset time period before current time calculate target group in second user group in sample database data is enlivened, to pass through the use of Hbase database and Hadoop frame, it is capable of increasing the user volume of monitoring, and computation rate and computational efficiency are improved by distributed computing.
Description
Technical field
The present invention relates to fields of communication technology more particularly to a kind of touching of advertisement target group to reach ratio estimation method and dress
It sets.
Background technique
Currently, the advertisement launched to advertiser is supervised in the method assessed up to ratio advertisement target group touching
It surveys, obtains the monitoring data that the user group reached is touched in advertisement, monitoring data are stored in MySQL number with the format of MongoDB
According in library, monitoring data are matched with obtained sample database data are investigated in advance, obtains sample database data and monitoring data
Between intersection, and then by this intersection calculate obtain sample database data in target group touching reach ratio.
However in the prior art, MySQL database can only support the sample data or monitoring data of million users of storage, difficult
To meet the storage demand that the monitoring data of ten million user reached are touched in advertisement；In addition, the data of MySQL database generally store
In single server memory, touching is done in single server memory up to ratio calculation, calculating speed is slow, is not suitable for millions data
Calculating, thus reduce assessment rate and assessment efficiency.
Summary of the invention
The present invention provides a kind of touching of advertisement target group up to ratio estimation method and device, comments in the prior art for solving
Estimate rate and assesses inefficient problem.
The first aspect of the invention is to provide a kind of touching of advertisement target group up to ratio estimation method, comprising:
The sample database data in Hbase database are obtained, include: the attribute number of each sample of users in the sample database data
Accordingly and corresponding advertising equipment identifies；The data of at least one attribute in the attribute data including the sample of users；
The first user group reached is touched in advertisement in the first preset time period before current time in acquisition Hbase database
Monitoring data, include: the attribute data of each user in the first user group in the monitoring data of first user group with
And corresponding advertising equipment mark；
The monitoring data of first user group and the sample database data are carried out by distribution using Hadoop frame
Matching, acquisition enliven sample database data, it is described enliven in sample database data include: each attribute data for enlivening sample of users with
And corresponding advertising equipment mark；
The weighted value for enlivening each sample populations in sample database data is obtained, it is each active in the sample populations
Sample of users the first attribute having the same；
The monitoring data of the second user group reached are touched in advertisement in the second preset time period before obtaining current time；
Mesh in the second user group is calculated according to the weighted value for enlivening each sample populations in sample database data
The touching for marking group reaches ratio.
Further, the acquisition sample database data, comprising:
Obtain the attribute data and corresponding advertising equipment mark of each sample of users；
Judge to whether there is preset attribute in the attribute data of the sample of users and the data of preset attribute are
No is empty；
If there are preset attributes in the attribute data of the sample of users, and the data of preset attribute are not sky, then
The attribute data of the sample of users and corresponding advertising equipment mark are stored in the sample database.
Further, it is described using Hadoop frame by the monitoring data of first user group and the sample database number
According to distributed matcher is carried out, acquisition enlivens sample database data, comprising:
For each sample of users in the sample database data, judge be in the monitoring data of first user group
No includes the attribute data of the sample of users and corresponding advertising equipment mark；
If including the attribute data of the sample of users in the monitoring data of first user group and corresponding
Advertising equipment mark, it is determined that the sample of users is to enliven sample of users；
If in the monitoring data of first user group not including the attribute data and correspondence of the sample of users
Advertising equipment mark, it is determined that the sample of users be inactive sample of users.
Further, described to obtain the weighted value for enlivening each sample populations in sample database data, the sample cluster
Each in body enlivens sample of users the first attribute having the same, comprising:
The attribute data for obtaining all users divides all users according to first attribute, obtains each group
The accounting of body and each group；
Obtain the accounting for enlivening each sample populations in sample database data；
For each sample populations enlivened in sample database data, by the accounting of the sample populations and all users
Attribute data in the ratio of accounting of corresponding group be determined as the weighted values of the sample populations；The sample populations and institute
State corresponding group's the first attribute having the same.
Further, described to calculate described second according to the weighted value for enlivening each sample populations in sample database data
The touching of target group reaches ratio in user group, comprising:
The target group enlivened in sample database data are obtained, each sample of users of enlivening in the target group is with default
Attribute data and corresponding advertising equipment mark；
To enliven the sum of corresponding weighted value of sample of users corresponding with each user in second user group by each in target group
The ratio of the sum of weighted value be determined as the touching of target group in the second user group up to ratio.
In the present invention, a kind of touching of advertisement target group is provided up to ratio estimation method, by obtaining in Hbase database
Sample database data include: the attribute data and corresponding advertising equipment mark of each sample of users in the sample database data；Institute
State the data of at least one attribute in attribute data including the sample of users；Obtain Hbase database in current time it
The monitoring data of the first user group reached are touched in advertisement in preceding first preset time period；Using Hadoop frame by described first
The monitoring data of user group and the sample database data carry out distributed matcher, and acquisition enlivens sample database data；According to active
The weighted value of each sample populations and advertisement is touched and reached in the second preset time period before current time in sample database data
The touching that the monitoring data of second user group calculate target group in second user group reaches ratio, to pass through Hbase data
The use in library and Hadoop frame is capable of increasing the user volume of monitoring, and improves computation rate and calculating by distributed computing
Efficiency.
The second aspect of the invention is to provide a kind of touching of advertisement target group up to ratio estimation device, comprising:
First obtains module for obtaining the sample database data in Hbase database includes: in the sample database data
The attribute data of each sample of users and corresponding advertising equipment mark；In the attribute data extremely including the sample of users
The data of a few attribute；
Second obtains module, for obtaining in Hbase database before current time advertisement institute in the first preset time period
The monitoring data of the first user group reached are touched, include: in the first user group in the monitoring data of first user group
The attribute data of each user and corresponding advertising equipment mark；
Matching module, for using Hadoop frame by the monitoring data of first user group and the sample database number
According to distributed matcher is carried out, acquisition enlivens sample database data, and described enliven in sample database data includes: each to enliven sample of users
Attribute data and corresponding advertising equipment mark；
Third obtains module, for obtaining the weighted value for enlivening each sample populations in sample database data, the sample
Each in in-group enlivens sample of users the first attribute having the same；
4th obtains module, for the second user reached to be touched in advertisement in the second preset time period before obtaining current time
The monitoring data of group；
Computing module, for calculating described second according to the weighted value for enlivening each sample populations in sample database data
The touching of target group reaches ratio in user group.
Further, the first acquisition module includes:
First acquisition unit, for obtaining the attribute data and corresponding advertising equipment mark of each sample of users；
First judging unit whether there is preset attribute in the attribute data for judging the sample of users, and
Whether the data of preset attribute are empty；
Be stored in unit, in the attribute data of the sample of users there are preset attribute, and preset attribute
When data are not sky, the attribute data of the sample of users and corresponding advertising equipment mark are stored in the sample database.
Further, the matching module includes:
Second judgment unit, for judging first user for each sample of users in the sample database data
It whether include that the attribute data of the sample of users and corresponding advertising equipment identify in the monitoring data of group；
First determination unit, for including the category of the sample of users in the monitoring data of first user group
Property data and corresponding advertising equipment identify when, determine the sample of users be enliven sample of users；
Second determination unit, for not including the sample of users in the monitoring data of first user group
When attribute data and corresponding advertising equipment identify, determine that the sample of users is inactive sample of users.
Further, the third acquisition module includes:
Second acquisition unit, for obtaining the attribute data of all users, according to first attribute to all users into
Row divides, and obtains the accounting of each group and each group；
Third acquiring unit, for obtaining the accounting for enlivening each sample populations in sample database data；
Third determination unit, for being directed to each sample populations enlivened in sample database data, by the sample cluster
The accounting of body is determined as the weighting of the sample populations with the ratio of the accounting of corresponding group in the attribute data of all users
Value；The sample populations and corresponding group's first attribute having the same.
Further, the computing module includes:
4th acquiring unit, each work for obtaining the target group enlivened in sample database data, in the target group
There is the sample of users that jumps preset attribute data and corresponding advertising equipment to identify；
4th determination unit, for enlivening the sum of corresponding weighted value of sample of users and second user for each in target group
The ratio of the sum of corresponding weighted value of each user is determined as the touching of target group in the second user group up to ratio in group.
In the present invention, a kind of touching of advertisement target group is provided up to ratio estimation device, by obtaining in Hbase database
Sample database data include: the attribute data and corresponding advertising equipment mark of each sample of users in the sample database data；Institute
State the data of at least one attribute in attribute data including the sample of users；Obtain Hbase database in current time it
The monitoring data of the first user group reached are touched in advertisement in preceding first preset time period；Using Hadoop frame by described first
The monitoring data of user group and the sample database data carry out distributed matcher, and acquisition enlivens sample database data；According to active
The weighted value of each sample populations and advertisement is touched and reached in the second preset time period before current time in sample database data
The touching that the monitoring data of second user group calculate target group in second user group reaches ratio, to pass through Hbase data
The use in library and Hadoop frame is capable of increasing the user volume of monitoring, and improves computation rate and calculating by distributed computing
Efficiency.
Detailed description of the invention
Fig. 1 is the flow chart that advertisement target group provided by the invention touching reaches ratio estimation method one embodiment；
Fig. 2 is the flow chart that advertisement target group provided by the invention touching reaches another embodiment of ratio estimation method；
Fig. 3 is the structural schematic diagram that advertisement target group provided by the invention touching reaches ratio estimation device one embodiment；
Fig. 4 is the structural representation that advertisement target group provided by the invention touching reaches another embodiment of ratio estimation device
Figure；
Fig. 5 is the structural representation that advertisement target group provided by the invention touching reaches another embodiment of ratio estimation device
Figure；
Fig. 6 is the structural representation that advertisement target group provided by the invention touching reaches another embodiment of ratio estimation device
Figure；
Fig. 7 is the structural representation that advertisement target group provided by the invention touching reaches another embodiment of ratio estimation device
Figure.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart that advertisement target group provided by the invention touching reaches ratio estimation method one embodiment, such as Fig. 1
It is shown, comprising:
Step 101, the sample database data in Hbase database are obtained, include: each sample of users in the sample database data
Attribute data and corresponding advertising equipment mark；It include at least one attribute of the sample of users in the attribute data
Data.
The executing subject of advertisement target group touching up to ratio estimation method provided by the invention can be advertisement target group
Touching reaches ratio estimation device, and advertisement target group touching is specifically as follows hardware device or is mounted on hardware up to ratio estimation device
Software etc. in equipment, can according to need and be configured.
Wherein, Hbase database can support mass memory and rapidly extracting, and the column of Hbase are expansible, and
And without limitation, it can satisfy the storage of sample database data and detection data and extract demand.It needs to be illustrated, sample
The attribute data of this user can specifically include: gender, age, marital status, education, Income situation of sample of users etc.
The data of attribute.Corresponding advertising equipment mark can be the mark of the terminal devices such as computer, mobile phone for launching advertisement.Electricity
The type for the advertisement launched in the terminals sadness such as brain, mobile phone can be banner banner or television advertising OTV etc..
Wherein, sample of users can be for by investigating obtained user.Advertisement target group touching is obtained up to ratio estimation device
After getting attribute data and the corresponding advertising equipment mark of the sample of users that investigation obtains, the category at family can be first mixed the sample with
Property data and corresponding advertising equipment mark stored with the format of MongoDB, then check sample of users attribute number
It whether there is whether preset attribute and the corresponding value of preset attribute are empty and the corresponding value of preset attribute format in
It is whether correct；If it is sky that preset attribute or the corresponding value of preset attribute are not present in the attribute data of sample of users, carry out
Supplement；If the format of the corresponding value of preset attribute is incorrect, modify；After supplement or modification, the category at family is mixed the sample with
Property data and corresponding advertising equipment mark deposit sample database.If in the attribute data of sample of users, there are preset attributes, and
The corresponding value of preset attribute is not sky, and the format of the corresponding value of preset attribute is correct, then directly mixes the sample with the attribute number at family
Accordingly and corresponding advertising equipment mark is stored in sample database.
Step 102, first reached is touched in advertisement in the first preset time period before current time in acquisition Hbase database
The monitoring data of user group include: the category of each user in the first user group in the monitoring data of first user group
Property data and corresponding advertising equipment mark.
Wherein, the first preset time period can be the periods such as three months or half a year.
Step 103, using Hadoop frame by the monitoring data of first user group and the sample database data into
Row distributed matcher, acquisition enliven sample database data, and described enliven in sample database data includes: each category for enlivening sample of users
Property data and corresponding advertising equipment mark.
Wherein, step 103 can specifically include: for each sample of users in the sample database data, described in judgement
In the monitoring data of first user group whether include the sample of users attribute data and corresponding advertising equipment mark
Know；If including that the attribute data of the sample of users and corresponding advertisement are set in the monitoring data of first user group
Standby mark, it is determined that the sample of users is to enliven sample of users；If not including in the monitoring data of first user group
There are the attribute data and corresponding advertising equipment mark of the sample of users, it is determined that the sample of users is inactive sample
User.
Step 104, the weighted value for enlivening each sample populations in sample database data is obtained, in the sample populations
It is each to enliven sample of users the first attribute having the same.
Wherein, due to the randomness of sample collection, the composition of residents of sample be it is uncertain, with equipment normal in society
It is inconsistent, the consistency of crowd's accounting, step in the crowd's accounting and society in order to guarantee sample database using composition of residents
104 can specifically include: obtaining the attribute data of all users, divided, obtained to all users according to first attribute
To the accounting of each group and each group；Obtain the accounting for enlivening each sample populations in sample database data；For
The each sample populations enlivened in sample database data, will be in the attribute data of the accounting of the sample populations and all users
The ratio of the accounting of corresponding group is determined as the weighted value of the sample populations；The sample populations and the corresponding group
First attribute having the same.
Specifically, all users can refer to the user of the terminal devices such as the available mobile phone arrived, computer.First attribute can
Think any one or more attributes in gender, age, marital status, education, Income situation etc..Each group accounts for
Than the ratio for referring to number of users and total number of users in group.
Step 105, the prison of the second user group reached is touched in advertisement in the second preset time period before obtaining current time
Measured data.
Wherein, the second preset time period can be the periods such as one day, two days.
Step 106, the second user is calculated according to the weighted value for enlivening each sample populations in sample database data
The touching of target group reaches ratio in group.
Wherein, target group are the group enlivened in sample database data, and each sample of users of enlivening in target group has
Preset attribute data and corresponding advertising equipment mark.
Further, before step 106, advertisement target group touching can also judge in target group up to ratio estimation device
Number of users whether be less than preset value, this sentence the second preset time period be one day for be illustrated, if in target group
Number of users is less than preset time, then advertisement target group touching reaches one before ratio estimation device available one day current time
The touching that the detection data that the second user group reached is touched in advertisement in its period carries out target group reaches the calculating of ratio.
In addition, advertisement target group touching can also be by above-mentioned calculated result synchronized update to externally up to ratio estimation device
Api interface is shown, to guarantee the consistency of data everywhere.
Advertisement target group touching provided in this embodiment reaches in ratio estimation method, by obtaining in Hbase database
Sample database data include: the attribute data and corresponding advertising equipment mark of each sample of users in the sample database data；Institute
State the data of at least one attribute in attribute data including the sample of users；Obtain Hbase database in current time it
The monitoring data of the first user group reached are touched in advertisement in preceding first preset time period；Using Hadoop frame by described first
The monitoring data of user group and the sample database data carry out distributed matcher, and acquisition enlivens sample database data；According to active
The weighted value of each sample populations and advertisement is touched and reached in the second preset time period before current time in sample database data
The touching that the monitoring data of second user group calculate target group in second user group reaches ratio, to pass through Hbase data
The use in library and Hadoop frame is capable of increasing the user volume of monitoring, and improves computation rate and calculating by distributed computing
Efficiency.
Fig. 2 is the flow chart that advertisement target group provided by the invention touching reaches another embodiment of ratio estimation method, such as
Shown in Fig. 2, on the basis of embodiment shown in Fig. 1, step 106 may include:
Step 1061, the target group enlivened in sample database data are obtained, each sample that enlivens in the target group is used
There is preset attribute data and corresponding advertising equipment to identify at family.
Step 1062, by target group it is each enliven the sum of corresponding weighted value of sample of users with it is each in second user group
The touching that the ratio of the sum of the corresponding weighted value of user is determined as target group in the second user group reaches ratio.
For example, the number of users in target group is m, then target group if the number of users in second user group is n
Touching up to the sum of weighted value that ratio is the corresponding target group of m user/n user corresponding group the sum of weighted value.
The present embodiment provides a kind of touchings of advertisement target group to reach ratio estimation method, by obtaining in Hbase database
Sample database data include: the attribute data and corresponding advertising equipment mark of each sample of users in the sample database data；Institute
State the data of at least one attribute in attribute data including the sample of users；Obtain Hbase database in current time it
The monitoring data of the first user group reached are touched in advertisement in preceding first preset time period；Using Hadoop frame by described first
The monitoring data of user group and the sample database data carry out distributed matcher, and acquisition enlivens sample database data；It obtains active
Target group in sample database data, each in the target group enliven sample of users with preset attribute data and right
The advertising equipment mark answered；By in target group it is each enliven the sum of corresponding weighted value of sample of users with it is each in second user group
The ratio of the sum of the corresponding weighted value of user is determined as the touching of target group in the second user group up to ratio, to pass through
The use of Hbase database and Hadoop frame is capable of increasing the user volume of monitoring, and is improved by distributed computing and calculate speed
Rate and computational efficiency.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Fig. 3 is the structural schematic diagram that advertisement target group provided by the invention touching reaches ratio estimation device one embodiment,
As shown in Figure 3, comprising:
First acquisition module 31 is wrapped in the sample database data for obtaining the sample database data in Hbase database
It includes: the attribute data of each sample of users and corresponding advertising equipment mark；It include the sample of users in the attribute data
At least one attribute data；
Second obtains module 32, for obtaining advertisement in the first preset time period before current time in Hbase database
The monitoring data of the first user group reached are touched, include: the first user group in the monitoring data of first user group
In each user attribute data and corresponding advertising equipment mark；
Matching module 33, for using Hadoop frame by the monitoring data of first user group and the sample database
Data carry out distributed matcher, and acquisition enlivens sample database data, and described enliven in sample database data includes: that each sample that enlivens is used
The attribute data at family and corresponding advertising equipment mark；
Third obtains module 34, described for obtaining the weighted value for enlivening each sample populations in sample database data
Each in sample populations enlivens sample of users the first attribute having the same；
4th obtains module 35, for the reach second use to be touched in advertisement in the second preset time period before obtaining current time
The monitoring data of family group；
Computing module 36, the weighted value for enlivening each sample populations in sample database data according to described calculate described the
The touching of target group reaches ratio in two user groups.
Wherein, advertisement target group touching provided by the invention is specifically as follows hardware device or peace up to ratio estimation device
Software etc. on hardware device, can according to need and be configured.Hbase database can support mass memory and fast
Speed is extracted, and the column of Hbase are expansible, and without limitation, can satisfy the storage of sample database data and detection data
And extract demand.It needs to be illustrated, the attribute data of sample of users can specifically include: the gender of sample of users,
The data of the attributes such as age, marital status, education, Income situation.Corresponding advertising equipment mark can be for for launching
The mark of the terminal devices such as computer, the mobile phone of advertisement.The type for the advertisement launched in the terminals sadness such as computer, mobile phone can be cross
Width advertisement banner or television advertising OTV etc..
Advertisement target group touching provided in this embodiment reaches ratio estimation device, by obtaining the sample in Hbase database
This library data includes: the attribute data and corresponding advertising equipment mark of each sample of users in the sample database data；It is described
The data of at least one attribute in attribute data including the sample of users；It obtains in Hbase database before current time
The monitoring data of the first user group reached are touched in advertisement in first preset time period；Described first is used using Hadoop frame
The monitoring data of family group and the sample database data carry out distributed matcher, and acquisition enlivens sample database data；According to enlivening sample
The weighted value of each sample populations and reached is touched in advertisement in the second preset time period before current time in this library data
The touching that the monitoring data of two user groups calculate target group in second user group reaches ratio, to pass through Hbase database
With the use of Hadoop frame, it is capable of increasing the user volume of monitoring, and improves computation rate by distributed computing and calculates and imitate
Rate.
Further, as shown in figure 4, Fig. 4 is that advertisement target group provided by the invention touching is another up to ratio estimation device
The structural schematic diagram of a embodiment, on the basis of embodiment shown in Fig. 3, the first acquisition module 31 includes:
First acquisition unit 311, for obtaining the attribute data and corresponding advertising equipment mark of each sample of users；
First judging unit 312 whether there is preset attribute in the attribute data for judging the sample of users, with
And whether the data of preset attribute are empty；
Be stored in unit 313, in the attribute data of the sample of users there are preset attribute, and preset attribute
Data when not being sky, the attribute data of the sample of users and corresponding advertising equipment mark are stored in the sample database
In.
Further, as shown in figure 5, Fig. 5 is that advertisement target group provided by the invention touching is another up to ratio estimation device
The structural schematic diagram of a embodiment, on the basis of embodiment shown in Fig. 3, the matching module 33 includes:
Second judgment unit 331, for judging that described first uses for each sample of users in the sample database data
It whether include that the attribute data of the sample of users and corresponding advertising equipment identify in the monitoring data of family group；
First determination unit 332, for including the sample of users in the monitoring data of first user group
Attribute data and corresponding advertising equipment identify when, determine the sample of users be enliven sample of users；
Second determination unit 333, for not including that the sample is used in the monitoring data of first user group
When the attribute data at family and corresponding advertising equipment identify, determine that the sample of users is inactive sample of users.
Further, as shown in fig. 6, Fig. 6 is that advertisement target group provided by the invention touching is another up to ratio estimation device
The structural schematic diagram of a embodiment, on the basis of embodiment shown in Fig. 3, the third obtains module 34 and includes:
Second acquisition unit 341, for obtaining the attribute data of all users, according to first attribute to all users
It is divided, obtains the accounting of each group and each group；
Third acquiring unit 342, for obtaining the accounting for enlivening each sample populations in sample database data；
Third determination unit 343, for being directed to each sample populations enlivened in sample database data, by the sample
The accounting of group is determined as adding for the sample populations with the ratio of the accounting of corresponding group in the attribute data of all users
Weight；The sample populations and corresponding group's first attribute having the same.
Further, as shown in fig. 7, Fig. 7 is that advertisement target group provided by the invention touching is another up to ratio estimation device
The structural schematic diagram of a embodiment, on the basis of embodiment shown in Fig. 3, the computing module 36 includes:
4th acquiring unit 361, it is each in the target group for obtaining the target group enlivened in sample database data
Sample of users is enlivened to identify with preset attribute data and corresponding advertising equipment；
4th determination unit 362, for enlivening the sum of corresponding weighted value of sample of users and second for each in target group
The touching that the ratio of the sum of corresponding weighted value of each user is determined as target group in the second user group in user group reaches
Ratio.
Further, computing module 36 calculates institute according to the weighted value for enlivening each sample populations in sample database data
The touching of target group in second user group is stated up to before ratio, advertisement target group touching can also judge up to ratio estimation device
Whether the number of users in target group is less than preset value, and it is to be illustrated for one day that this, which sentences the second preset time period, if mesh
The number of users marked in group is less than preset time, then advertisement target group touching reaches ratio estimation device available current time one
The touching that the detection data that the second user group reached is touched in advertisement in a period before it carries out target group reaches ratio
Calculating.
In addition, advertisement target group touching can also be by above-mentioned calculated result synchronized update to externally up to ratio estimation device
Api interface is shown, to guarantee the consistency of data everywhere.
Advertisement target group touching provided in this embodiment reaches in ratio estimation device, by obtaining in Hbase database
Sample database data include: the attribute data and corresponding advertising equipment mark of each sample of users in the sample database data；Institute
State the data of at least one attribute in attribute data including the sample of users；Obtain Hbase database in current time it
The monitoring data of the first user group reached are touched in advertisement in preceding first preset time period；Using Hadoop frame by described first
The monitoring data of user group and the sample database data carry out distributed matcher, and acquisition enlivens sample database data；According to active
The weighted value of each sample populations and advertisement is touched and reached in the second preset time period before current time in sample database data
The touching that the monitoring data of second user group calculate target group in second user group reaches ratio, to pass through Hbase data
The use in library and Hadoop frame is capable of increasing the user volume of monitoring, and improves computation rate and calculating by distributed computing
Efficiency.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of advertisement target group touching reaches ratio estimation method characterized by comprising
Obtain the sample database data in Hbase database, include: the attribute data of each sample of users in the sample database data with
And corresponding advertising equipment mark；The data of at least one attribute in the attribute data including the sample of users；
The prison of the first user group reached is touched in advertisement in the first preset time period before current time in acquisition Hbase database
Measured data includes: the attribute data of each user and right in the first user group in the monitoring data of first user group
The advertising equipment mark answered；
The monitoring data of first user group and the sample database data are carried out by distributed matcher using Hadoop frame,
Acquisition enlivens sample database data, and described enliven in sample database data includes: each attribute data for enlivening sample of users and right
The advertising equipment mark answered；
The weighted value for enlivening each sample populations in sample database data is obtained, each in the sample populations enlivens sample
User's the first attribute having the same；
The monitoring data of the second user group reached are touched in advertisement in the second preset time period before obtaining current time；
Target complex in the second user group is calculated according to the weighted value for enlivening each sample populations in sample database data
The touching of body reaches ratio.
2. the method according to claim 1, wherein the acquisition sample database data, comprising:
Obtain the attribute data and corresponding advertising equipment mark of each sample of users；
Judge in the attribute data of the sample of users with the presence or absence of preset attribute and preset attribute data whether be
It is empty；
If there are preset attributes in the attribute data of the sample of users, and the data of preset attribute are not sky, then by institute
The attribute data and corresponding advertising equipment mark for stating sample of users are stored in the sample database.
3. the method according to claim 1, wherein described use Hadoop frame by first user group
Monitoring data and the sample database data carry out distributed matcher, acquisition enliven sample database data, comprising:
For each sample of users in the sample database data, judge whether wrap in the monitoring data of first user group
Include the attribute data and corresponding advertising equipment mark of the sample of users；
If include in the monitoring data of first user group sample of users attribute data and corresponding advertisement
Device identification, it is determined that the sample of users is to enliven sample of users；
If not including the attribute data of the sample of users in the monitoring data of first user group and corresponding wide
Accuse device identification, it is determined that the sample of users is inactive sample of users.
4. the method according to claim 1, wherein the acquisition is described to enliven each sample in sample database data
The weighted value of group, each in the sample populations enliven sample of users the first attribute having the same, comprising:
The attribute data for obtaining all users divides all users according to first attribute, obtain each group with
And the accounting of each group；
Obtain the accounting for enlivening each sample populations in sample database data；
For each sample populations enlivened in sample database data, by the category of the accounting of the sample populations and all users
The ratio of the accounting of corresponding group is determined as the weighted value of the sample populations in property data；The sample populations with it is described right
The group answered the first attribute having the same.
5. the method according to claim 1, wherein described enliven each sample in sample database data according to described
The touching that the weighted value of group calculates target group in the second user group reaches ratio, comprising:
The target group enlivened in sample database data are obtained, each sample of users of enlivening in the target group is with preset category
Property data and corresponding advertising equipment mark；
By in target group it is each enliven the sum of corresponding weighted value of sample of users it is corresponding with each user in second user group plus
The touching that the ratio of weights sum is determined as target group in the second user group reaches ratio.
6. a kind of advertisement target group touching reaches ratio estimation device characterized by comprising
First acquisition module includes: various kinds in the sample database data for obtaining the sample database data in Hbase database
The attribute data of this user and corresponding advertising equipment mark；It include at least the one of the sample of users in the attribute data
The data of a attribute；
Second obtains module, reaches for obtaining in Hbase database before current time advertisement in the first preset time period and touching
The first user group monitoring data, include: respectively to be used in the first user group in the monitoring data of first user group
The attribute data at family and corresponding advertising equipment mark；
Matching module, for using Hadoop frame by the monitoring data of first user group and the sample database data into
Row distributed matcher, acquisition enliven sample database data, and described enliven in sample database data includes: each category for enlivening sample of users
Property data and corresponding advertising equipment mark；
Third obtains module, for obtaining the weighted value for enlivening each sample populations in sample database data, the sample cluster
Each in body enlivens sample of users the first attribute having the same；
4th obtains module, for the second user group reached to be touched in advertisement in the second preset time period before obtaining current time
Monitoring data；
Computing module, for calculating the second user according to the weighted value for enlivening each sample populations in sample database data
The touching of target group reaches ratio in group.
7. device according to claim 6, which is characterized in that described first, which obtains module, includes:
First acquisition unit, for obtaining the attribute data and corresponding advertising equipment mark of each sample of users；
First judging unit whether there is preset attribute in the attribute data for judging the sample of users, and default
The data of attribute whether be empty；
Be stored in unit, in the attribute data of the sample of users there are preset attribute, and data of preset attribute
When being not empty, the attribute data of the sample of users and corresponding advertising equipment mark are stored in the sample database.
8. device according to claim 6, which is characterized in that the matching module includes:
Second judgment unit, for judging first user group for each sample of users in the sample database data
Monitoring data in whether include the sample of users attribute data and corresponding advertising equipment mark；
First determination unit, for including the attribute number of the sample of users in the monitoring data of first user group
When accordingly and corresponding advertising equipment identifies, determine that the sample of users is to enliven sample of users；
Second determination unit, for not including the attribute of the sample of users in the monitoring data of first user group
When data and corresponding advertising equipment identify, determine that the sample of users is inactive sample of users.
9. device according to claim 6, which is characterized in that the third obtains module and includes:
Second acquisition unit draws all users according to first attribute for obtaining the attribute data of all users
Point, obtain the accounting of each group and each group；
Third acquiring unit, for obtaining the accounting for enlivening each sample populations in sample database data；
Third determination unit, for being directed to each sample populations enlivened in sample database data, by the sample populations
Accounting is determined as the weighted value of the sample populations with the ratio of the accounting of corresponding group in the attribute data of all users；Institute
State sample populations and corresponding group's first attribute having the same.
10. device according to claim 6, which is characterized in that the computing module includes:
4th acquiring unit, for obtaining the target group enlivened in sample database data, each in the target group enlivens sample
There is this user preset attribute data and corresponding advertising equipment to identify；
4th determination unit, for enlivening the sum of corresponding weighted value of sample of users and second user group for each in target group
In the ratio of the sum of the corresponding weighted value of each user be determined as the touching of target group in the second user group up to 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 CN106227743A (en) | 2016-12-14 |
| CN106227743B true 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) |
Families Citing this family (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 |
| 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 |
| CN110796465B (en) * | 2018-08-03 | 2023-08-01 | 阿里巴巴集团控股有限公司 | Resource display equipment determining method, advertisement display screen determining method and device |
| 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 |
Citations (7)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10902464B2 (en) * | 2013-08-27 | 2021-01-26 | Verizon Media Inc. | Spark satellite clusters to HADOOP data stores |
-
2016
- 2016-07-12 CN CN201610548202.9A patent/CN106227743B/en active Active
Patent Citations (7)
| 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 |
| 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 |
|---|
| Research of Hadoop-based data flow management system;Zhi Qiu et al.;《The Journal of China Universities of Posts and Telecommunications》;20111231;第18卷;第164-168页 * |
| 广播电视广告监管系统应用;束雯;《信息通信》;20131231(第6期);第284页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106227743A (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106227743B (en) | Advertisement target group touching reaches ratio estimation method and device | |
| CN108287864B (en) | Interest group dividing method, device, medium and computing equipment | |
| CN106126582A (en) | Recommend method and device | |
| CN108230010A (en) | A kind of method and server for estimating ad conversion rates | |
| CN111079006B (en) | Message pushing method and device, electronic equipment and medium | |
| CN107733984A (en) | A kind of method, terminal and computer-readable recording medium for pushing screen locking information | |
| CN113590776B (en) | Knowledge graph-based text processing method and device, electronic equipment and medium | |
| CN110472154A (en) | A kind of resource supplying method, apparatus, electronic equipment and readable storage medium storing program for executing | |
| CN109829020A (en) | Place resource data push method, device, computer equipment and storage medium | |
| CN114496264B (en) | Health index analysis method, device, equipment and medium based on multidimensional data | |
| CN111371767A (en) | Malicious account identification method, malicious account identification device, medium and electronic device | |
| CN108647997A (en) | A kind of method and device of detection abnormal data | |
| CN111178983B (en) | User gender prediction method, device, equipment and storage medium | |
| CN111078742B (en) | User classification model training method, user classification method and device | |
| CN103455555B (en) | Recommendation method and recommendation apparatus based on mobile terminal similarity | |
| CN106033510A (en) | Method and system for identifying user equipment | |
| CN103617146B (en) | A kind of machine learning method and device based on hardware resource consumption | |
| CN109858965A (en) | A kind of user identification method and system | |
| CN110046251A (en) | Community content methods of risk assessment and device | |
| CN110020196A (en) | A kind of customer analysis method and apparatus and calculating equipment based on different data sources | |
| CN106383857A (en) | Information processing method and electronic equipment | |
| CN111382977A (en) | Book purchasing method and device based on user borrowing behavior and storage medium | |
| CN107665202A (en) | Method and device for constructing interest model and electronic equipment | |
| CN104933082B (en) | Evaluation information processing method and its device | |
| CN114139052B (en) | Ranking model training method for intelligent recommendation, intelligent recommendation method and 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 |