CN109816410A - The analysis method and device of advertisement major product audience - Google Patents
The analysis method and device of advertisement major product audience Download PDFInfo
- Publication number
- CN109816410A CN109816410A CN201711165999.5A CN201711165999A CN109816410A CN 109816410 A CN109816410 A CN 109816410A CN 201711165999 A CN201711165999 A CN 201711165999A CN 109816410 A CN109816410 A CN 109816410A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- audience
- major product
- data structure
- 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.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention provides the analysis methods and device of a kind of advertisement major product audience, comprising: counts the behavioral data of each network user, and the behavioral data based on each network user and each network user establishes user behavior data library；Multiple first data structures are constructed based on the network user in user behavior data library；Wherein, each first data structure includes different user property feature；The audience of advertisement major product is determined according to the user behavior data in user behavior data library, and the second data structure is constructed based on audience；The determining overlapped data with the second data structure respectively in each first data structure, the user property feature for including based on overlapped data are established user's portrait of audience, are analyzed user's portrait.It is accurately established while data analysis can quickly be carried out based on method provided by the invention with portrait, provides precision data for advertisement dispensing, and then promote the effect that advertisement is launched.
Description
Technical field
The present invention relates to Internet technical fields, a kind of analysis method more particularly to advertisement major product audience and
Device.
Background technique
Enterprise is when carrying out advertisement dispensing, by needing the audience to advertiser to analyze, so as to it is subsequent again
When secondary progress advertisement dispensing, advertisement dispensing is carried out according to the region for meeting the advertisement major product audience feature.
Currently, would generally be divided based on the feature of each user for the analytic process of advertisement major product audience
Analysis, since the data volume of user is larger, entire analytic process is slower, and the accuracy of data analysis is lower.Therefore, how to mention
Guarantee accuracy while rising data analysis performance, is current urgent problem to be solved.
Summary of the invention
The present invention provides a kind of analysis method of advertisement major product audience and device with overcome the above problem or
It at least is partially solved the above problem.
According to an aspect of the invention, there is provided a kind of analysis method of advertisement major product audience, comprising:
The behavioral data of each network user is counted, and is established and is used based on the behavioral data of each network user and each network user
Family behavior database；
Multiple first data structures are constructed based on the network user in the user behavior data library；Wherein, each first number
It include different user property features according to structure；
The audience of advertisement major product is determined according to the user behavior data in the user behavior data library, is based on institute
It states audience and constructs the second data structure；
It determines the overlapped data with second data structure respectively in each first data structure, is based on the overlapping number
According to comprising user property feature establish the audience user portrait, to the user portrait analyze.
Optionally, the network user based in the user behavior data library constructs multiple first data structures, packet
It includes:
Obtain the all-network user in the user behavior data library, to the user property feature of all-network user into
Row analysis；
Multiple first data structures are constructed using sets cardinal algorithm；Wherein, each first data structure includes difference
User property feature.
Optionally, the user property feature includes at least following one: geographical location locating for user's gender, user is used
Family age and user's occupation.
Optionally, the user behavior data according in the user behavior data library determines the audient of advertisement major product
Group, the audience based on the advertisement major product construct the second data structure, comprising:
The task condition for obtaining advertiser's setting, filters out according to the user behavior data library and meets the specified requirements
User be the advertisement major product audience；
Audience based on the advertisement major product constructs the second data structure using sets cardinal algorithm.
Optionally, the task condition include: search key, geographical location locating for user, browsing website type and/or
Application Type.
Optionally, the task condition for obtaining advertiser's setting, filters out according to the user behavior data library and meets
The user of the specified requirements is the audience of the advertisement major product, comprising:
The task condition for obtaining advertiser's setting, is screened in the user behavior data library by the way of inverted index
Meet the user of the task condition out；
The user for meeting the task condition filtered out is counted, the audience of advertisement major product is formed.
Optionally, the overlapped data determined respectively in each first data structure with second data structure, base
User's portrait of the audience is established in the user property feature that the overlapped data includes, draws a portrait and carries out to the user
Analysis, comprising:
The intersection that each first data structure and the second data structure are calculated separately by minHash algorithm, determines each first
The overlapped data of data structure and second data structure；
Determine the user property feature that the overlapped data includes, the user property feature based on the overlapped data is established
The user of the audience of the advertisement major product draws a portrait, and analyzes user portrait.
Optionally, user's portrait of the audience that the advertisement major product is established according to the overlapped data, it is right
After user's portrait is analyzed, further includes:
The analysis of user's portrait is obtained as a result, and the analysis result is stored in designated storage area.
According to another aspect of the present invention, a kind of analytical equipment of advertisement major product audience is additionally provided, comprising:
Statistical module is configured to count the behavioral data of each network user, and is based on each network user and each network user
Behavioral data establish user behavior data library；
First building module, the network user being configured in the user behavior data library construct multiple first data
Structure；Wherein, each first data structure includes different user property feature；
Second building module, configuration determine advertisement major product according to the user behavior data in the user behavior data library
Audience, based on the audience construct the second data structure；
Analysis module is configured in each first data structure determine and the overlapping number of second data structure respectively
According to the user property feature for including based on the overlapped data establishes user's portrait of the audience, draws to the user
As being analyzed.
Optionally, the first building module includes:
Attributive analysis unit is configured to obtain the all-network user in the user behavior data library, to all-network
The user property feature of user is analyzed；
First data structure construction unit is configured to construct multiple first data structures using sets cardinal algorithm；Wherein,
Each first data structure includes different user property feature.
Optionally, the second building module includes:
Acquiring unit is configured to obtain the task condition of advertiser's setting, be filtered out according to the user behavior data library
The user for meeting the specified requirements is the audience of the advertisement major product；
Second data structure construction unit, the audience for being configured to the advertisement major product are calculated using sets cardinal
Method constructs the second data structure.
Optionally, the acquiring unit is additionally configured to:
The task condition for obtaining advertiser's setting, is screened in the user behavior data library by the way of inverted index
Meet the user of the task condition out；
The user for meeting the task condition filtered out is counted, the audience of advertisement major product is formed.
Optionally, the analysis module includes:
Computing unit is configured to calculate separately each first data structure and the second data structure by minHash algorithm
Intersection determines the overlapped data of each first data structure Yu second data structure；
User's portrait analytical unit, is configured to determine the user property feature that the overlapped data includes, based on described heavy
The user property feature of folded data establishes user's portrait of the audience of the advertisement major product, draws a portrait and carries out to the user
Analysis.
Optionally, further includes:
Memory module is configured to obtain the analysis of user's portrait as a result, and being stored in the analysis result specified
In storage region.
According to a further aspect of the invention, a kind of electronic equipment is additionally provided, wherein include:
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Device execution is managed according to the analysis method of advertisement major product audience described in any of the above embodiments.
According to a further aspect of the invention, a kind of computer readable storage medium is additionally provided, wherein the computer
Readable storage medium storing program for executing stores one or more programs, and one or more of programs are set when by the electronics including multiple application programs
When standby execution, so that the electronic equipment executes the analysis side according to advertisement major product audience described in any of the above embodiments
Method.
The present invention provides the analysis methods and device of a kind of advertisement major product audience, based on provided by the invention wide
The analysis method for accusing major product audience, establishes user behavior data library previously according to each network user and user behavior data
Afterwards, can based on the user behavior data library construct include different user attributive character multiple first data structures, by with
The second data structure including the building of advertisement major product audience determines coincidence data, and then is established according to above-mentioned coincidence data
The user of advertisement major product audience draws a portrait, can be to the user property of advertisement major product audience based on user portrait
Feature is accurately analyzed.Advertisement major product audience analysis method head provided by the invention is established by user property feature
Multiple first data structures, can be when subsequent and including advertisement major product audience the second data structure determines coincidence data
Data analysis is quickly carried out, and is accurately established with portrait, provides precision data for advertisement dispensing, and then promote the effect that advertisement is launched
Fruit.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
According to the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will be brighter
The above and other objects, advantages and features of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the analysis method flow diagram of advertisement major product audience according to an embodiment of the present invention；
Fig. 2 is the analysis method flow diagram of advertisement major product audience according to the preferred embodiment of the invention；
Fig. 3 is the analytical equipment structural schematic diagram of advertisement major product audience according to an embodiment of the present invention；
Fig. 4 is the analytical equipment structural schematic diagram of advertisement major product audience according to the preferred embodiment of the invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 is the analysis method flow diagram of advertisement major product audience according to an embodiment of the present invention, such as Fig. 1 institute
Show, the analysis method of advertisement major product audience according to an embodiment of the present invention includes:
Step S102 counts the behavioral data of each network user, and the behavior based on each network user and each network user
Data establish user behavior data library；
Step S104 constructs multiple first data structures based on the network user in user behavior data library；Wherein, each
One data structure includes different user property feature；
Step S106 determines the audience of advertisement major product according to the user behavior data in user behavior data library,
The second data structure is constructed based on above-mentioned audience；
Step S108 determines the overlapped data with the second data structure, based on above-mentioned respectively in each first data structure
The user property feature that overlapped data includes establishes user's portrait of audience, analyzes user's portrait.
The analysis method of advertisement major product audience based on the embodiment of the present invention, previously according to each network user
It can include different user category based on user behavior data library building and after user behavior data establishes user behavior data library
Property feature multiple first data structures, by with include advertisement major product audience building the second data structure determine weight
Data are closed, and then are drawn a portrait according to the user that above-mentioned coincidence data establishes advertisement major product audience, are based on user portrait
The user property feature of advertisement major product audience can accurately be analyzed.Advertisement major product provided in an embodiment of the present invention
Audience analysis method head establishes multiple first data structures by user property feature, can it is subsequent with include advertisement main product
Second data structure of product audience quickly carries out data analysis when determining coincidence data, and accurately establishes with drawing a portrait, and is wide
It accuses to launch and precision data is provided, and then promote the effect that advertisement is launched.
Method provided in an embodiment of the present invention can obtain all network users when establishing user behavior data library, and
The behavioral data for counting all-network user, the user behavior established based on the behavioral data of all-network user and the network user
Database contains all-network user and corelation behaviour data, provides powerful number for analysis advertisement major product audience
According to basis.
When above-mentioned steps S102 constructs multiple first data structures, the all-network that can first obtain in user behavior library is used
Family, and the user property feature of all-network user is analyzed；Multiple first data knots are constructed using sets cardinal algorithm
Structure.
Optionally, user property feature can be understood as the attribute for multiple dimensions that user itself has, and may include
User's gender, age of user, family status, user's occupation, income, native place, work location, frequent activity scene and individual
Hobby etc..The user that will be provided with same user property feature constructs single first data structure, and then based on multiple and different
Multiple first data structures of user property feature construction.
It is mentioned above, sets cardinal algorithm can be used when constructing the first data structure.Radix refers to different in a set
The number of element.HyperLogLog++ algorithm in sets cardinal is the probabilistic algorithm based on Probability Statistics Theory design, can
To realize sets cardinal using less space and higher performance, while can be adjusted control errors by parameter in institute
In the range of it is required that, data structure in HyperLogLog++ algorithm can be easy to and nondestructively calculate two unions of sets
Collection.It in embodiments of the present invention, can be based on different user property feature, that is, different dimensions numbers using sets cardinal algorithm
According to building sets cardinal data.Such as: in gender dimension data, male user constructs a sets cardinal data structure, women
User constructs a sets cardinal data structure；In geography dimension data, the user in each province constructs different radixes
Therefore estimated data structure etc. can construct multiple the first data knots for having different user attributive character based on the above method
Structure.Above multiple first data structures can pre-establish, and construct and complete in advance under online, in the audient crowd drawn a circle to approve with advertiser
The second data structure when seeking common ground, without traversing each dimension data for counting each user, only need two sets cardinal numbers
According to structure digitwise operation, calculated performance can be further promoted.
Preferably, when analyzing advertisement major product audience, need accurately to determine the audient group of advertisement major product
Therefore body before determining advertiser's audience, can provide task condition by advertiser, as locating for search key, user
Geographical location, browsing website type, Application Type, terminal type used by a user, APP downloading situation, APP use feelings
Condition and the ascribed characteristics of population etc..
In the audience for determining advertiser, the task condition of advertiser's setting can be first obtained, using inverted index
Mode filters out the user for meeting above-mentioned task condition in user behavior data library；What statistics filtered out meets above-mentioned taskbar
The user of part constitutes the audience of advertiser's product.
Inverted index is that record is searched according to the value of attribute, is the behavior number according to user in embodiments of the present invention
The user for meeting above-mentioned task condition according to reversed lookup, can be quickly in the user behavior for having mass data based on the above method
Accurately delineation meets the above-mentioned audient crowd for thinking condition in database, and then determines the audience of advertisement major product.Advertisement
After major product audience determines, so that it may which the audience based on advertisement major product is using sets cardinal algorithm building second
Data structure constructs the set of drawn a circle to approve audience.
After building the first data structure and the second data structure respectively, so that it may further in each first data structure
The middle overlapped data with the second data structure determining respectively, the user property feature for including based on above-mentioned overlapped data establish audient
The user of group draws a portrait, and analyzes user's portrait, the analysis to advertisement major product audience can be realized.
It is mentioned above, using the HyperLogLog++ algorithm in sets cardinal algorithm construct respectively the first data structure and
Second data structure, but the algorithm can not directly calculate two intersection of sets collection.And the demand that data are analyzed in ad system,
It is to seek two intersection of sets collection.Such as: male user quantity in the audient crowd of advertiser's condition delineation is calculated, that is, is equal to
Calculate the set and the intersection of sets collection of all male audience crowds of the audient crowd of advertiser's condition delineation.
In order to calculate two intersection of sets collection on sets cardinal algorithm, the present embodiment is in HyperLogLog++ algorithm base
MinHash algorithm is introduced on plinth, extends HyperLogLog++ algorithm, it is made to support the calculating of two set intersections.It calculates
Theory deduction is as follows:
MinHash algorithm:
Jaccard (A, B)=Pr [hmin (A)=hmin (B)]
Wherein: Jaccard (A, B) is Jaccard Index, for calculating the similitude of two set；
H (x): x is mapped to the hash function of an integer；
Hmin (S): the element in set S is after h (x) Hash, the element with minimum hash.
So to set A, B, the condition that hmin (A)=hmin (B) is set up is the element in A ∪ B with minimum hash
Also in A ∩ B.Here there is one it is assumed that h (x) is a good hash function, it has good uniformity, can be
Different elements are mapped to different integers.
So having, Pr [hmin (A)=hmin (B)]=J (A, B), the i.e. similarity of set A and B are set A, B process
The equal probability of minimum hash after hash.
Pr [hmin (A)=hmin (B)] can be acquired by following methods:
Defining hmink (S) is K element in set S with minimum hash.We only need to ask one to each set
Then secondary Hash takes the smallest K element.Calculate the similarity of two set A, B, in exactly set A the smallest K element with
The ratio of the intersection number and union number of the smallest K element in set B.
HyperLogLog++ algorithm can calculate two union of sets collection:
HyperLogLog++=| A ∪ B |
| A ∩ B |=minHash*HyperLogLog++
MinHash algorithm is added in the embodiment of the present invention in sets cardinal algorithm, can quickly calculate the first data knot
The intersection of structure and the second data structure can mentioned with accurate and rapid build advertisement major product audience user's portrait
Guarantee the accuracy of analysis result while rising data analysis performance.
As shown in Fig. 2, can also include further comprises step after step 108 analyzes user's portrait
S110, obtain user portrait analysis as a result, and the analysis result is stored in designated storage area, so that advertiser checks
And advertisement dispensing is carried out based on the analysis results, improve the effect that advertisement is launched.
Above-described embodiment is described in detail below by an example.
Assuming that building user behavior data library to obtain overall network user and user behavior data, and being based on should
User behavior data library constructs the data of 50 dimensions, i.e. 50 the first data structures.Wherein, all-network user is 10
Hundred million, and the audience of the advertisement major product determined is 100 general-purpose families, i.e. the second data structure includes 1,000,000 users.
One, traditional analysis method
Audient is basic unit to the positive number of rows of meeting accordingly, merges the data of all dimensions of each audient, can be based on Hadoop
It realizes, conventional method includes:
1. traversing 1,000,000,000 audients, qualified 1,000,000 audients are found, traversal can consume the regular hour；
2. the data of 50 dimensions after needing the audient to 1,000,000 count respectively, most after finding 1,000,000 audient
The statistical value of this 50 dimension datas is calculated afterwards.Need to calculate 50,000,000 dimensions data (1,000,000 dimensions of * 50=
50000000 dimensions), calculating can also consume a large amount of time.
Two, method provided in this embodiment
1, the sets cardinal data structure of 50 dimension datas calculated in advance using sets cardinal algorithm under line asks friendship
Collection；
2, after drawing a circle to approve 1,000,000 audients according to advertiser's condition, sets cardinal data structure is established to this 1,000,000 audient, this
Part only traverses 1,000,000 audient, calculates hash value to each audient, and than traversal, 1,000,000,000 audients are many fastly；
3, establish advertiser delineation audient's sets cardinal data structure after, under line in advance use sets cardinal algorithm
The sets cardinal data structure of 50 dimension datas calculated seeks common ground, and need to only calculate data (the 1*50 dimension of 50 dimensions
Spend=50 dimensions), calculation amount also greatly reduces.
By analysis it is found that method based on the embodiment of the present invention, is not only calculating the radix including audience
Can be many fastly when estimated data structure, and with the sets cardinal Structure Calculation for having different user characteristic attribute that calculates in advance
When intersection, calculation amount can also greatly reduce, and then improve data analysis efficiency.
Based on the same inventive concept, the embodiment of the invention also provides a kind of analysis of advertisement major product audience dresses
It sets, as shown in figure 3, the analytical equipment for the advertisement major product audience that inventive embodiments provide includes:
Statistical module 10 is configured to count the behavioral data of each network user, and is used based on each network user and each network
The behavioral data at family establishes user behavior data library；
First building module 20, the network user being configured in user behavior data library construct multiple first data knots
Structure；Wherein, each first data structure includes different user property feature；
Second building module 30, configuration determine advertisement major product according to the user behavior data in user behavior data library
Audience constructs the second data structure based on audience；
Analysis module 40 is configured in each first data structure the determining overlapped data with the second data structure respectively,
The user property feature for including based on overlapped data establishes user's portrait of audience, analyzes user's portrait.
In a preferred embodiment of the invention, as shown in figure 4, the first building module 20 includes:
Attributive analysis unit 21 is configured to obtain the all-network user in user behavior data library, use all-network
The user property feature at family is analyzed；
First data structure construction unit 22 is configured to construct multiple first data structures using sets cardinal algorithm；Its
In, each first data structure includes different user property feature.
In a preferred embodiment of the invention, as shown in figure 4, the second building module 30 includes:
Acquiring unit 31 is configured to obtain the task condition of advertiser's setting, filters out symbol according to user behavior data library
The user for closing specified requirements is the audience of advertisement major product；
Second data structure construction unit 32 is configured to the audience of advertisement major product using sets cardinal algorithm
Construct the second data structure.
In a preferred embodiment of the invention, acquiring unit 31 is additionally configured to:
The task condition for obtaining advertiser's setting, filters out symbol by the way of inverted index in user behavior data library
Close the user for stating task condition；
The user for meeting above-mentioned task condition filtered out is counted, the audience of advertisement major product is formed.
In a preferred embodiment of the invention, as shown in figure 4, analysis module 40 further include:
Computing unit 41 is configured to calculate separately each first data structure and the second data structure by minHash algorithm
Intersection, determine the overlapped data of each first data structure and the second data structure；
User's portrait analytical unit 42, is configured to determine the user property feature that overlapped data includes, is based on overlapped data
User property feature establish advertisement major product audience user portrait, to user portrait analyze.
In a preferred embodiment of the invention, as shown in figure 4, above-mentioned apparatus further include:
Memory module 50 is configured to obtain the analysis of user's portrait as a result, and analysis result is stored in designated storage area
In domain.
The embodiment of the invention also provides a kind of electronic equipment, wherein includes:
Processor；And
It is arranged to the memory of storage computer executable instructions, executable instruction executes processor when executed
According to the analysis method of any of the above-described advertisement major product audience.
The embodiment of the invention also provides a kind of computer readable storage mediums, wherein computer readable storage medium is deposited
One or more programs are stored up, one or more programs are when the electronic equipment for being included multiple application programs executes, so that electronics
Equipment executes the analysis method according to any of the above-described advertisement major product audience.
The embodiment of the invention provides the analysis methods and device of a kind of advertisement major product audience, real based on the present invention
The analysis method for applying the advertisement major product audience of example offer is established previously according to each network user and user behavior data and is used
It can include multiple first data of different user attributive character based on user behavior data library building after the behavior database of family
Structure, by determining coincidence data with the second data structure for including the building of advertisement major product audience, and then according to above-mentioned
Coincidence data establishes user's portrait of advertisement major product audience, can be to advertisement major product audient group based on user portrait
The user property feature of body is accurately analyzed.Advertisement major product audience analysis method head provided in an embodiment of the present invention is logical
It crosses user property feature and establishes multiple first data structures, it can be in the second data subsequent and including advertisement major product audience
Data analysis is quickly carried out when structure determination coincidence data, and is accurately established with drawing a portrait, and provides precision data for advertisement dispensing, into
And promote the effect of advertisement dispensing.
Further, minHash algorithm is added in the embodiment of the present invention in sets cardinal algorithm, can quickly calculate
The intersection of one data structure and the second data structure is drawn a portrait with accurate and rapid build advertisement major product audience user,
It can guarantee the accuracy of analysis result while promoting data analysis performance.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any
Can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize point of advertisement major product audience according to an embodiment of the present invention
The some or all functions of some or all components in analysis apparatus.The present invention is also implemented as executing institute here
Some or all device or device programs of the method for description are (for example, computer program and computer program produce
Product).It is such to realize that program of the invention can store on a computer-readable medium, or can have one or more
The form of signal.Such signal can be downloaded from an internet website to obtain, and perhaps be provided on the carrier signal or to appoint
What other forms provides.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
So far, although those skilled in the art will appreciate that present invention has been shown and described in detail herein multiple shows
Example property embodiment still without departing from the spirit and scope of the present invention, still can according to the present disclosure directly
Determine or deduce out many other variations or modifications consistent with the principles of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers all such other variations or modifications.
According to an aspect of the invention, there is provided: a kind of analysis method of advertisement major product audience of A1., comprising:
The behavioral data of each network user is counted, and is established and is used based on the behavioral data of each network user and each network user
Family behavior database；
Multiple first data structures are constructed based on the network user in the user behavior data library；Wherein, each first number
It include different user property features according to structure；
The audience of advertisement major product is determined according to the user behavior data in the user behavior data library, is based on institute
It states audience and constructs the second data structure；
It determines the overlapped data with second data structure respectively in each first data structure, is based on the overlapping number
According to comprising user property feature establish the audience user portrait, to the user portrait analyze.
A2. method according to a1, wherein described more based on network user's building in the user behavior data library
A first data structure, comprising:
Obtain the all-network user in the user behavior data library, to the user property feature of all-network user into
Row analysis；
Multiple first data structures are constructed using sets cardinal algorithm；Wherein, each first data structure includes difference
User property feature.
A3. method according to a1, wherein the user property feature includes at least following one: user's gender is used
Geographical location, age of user locating for family and user's occupation.
A4. method according to a1, wherein described true according to the user behavior data in the user behavior data library
The audience for determining advertisement major product, the audience based on the advertisement major product construct the second data structure, comprising:
The task condition for obtaining advertiser's setting, filters out according to the user behavior data library and meets the specified requirements
User be the advertisement major product audience；
Audience based on the advertisement major product constructs the second data structure using sets cardinal algorithm.
A5. method according to a4, wherein the task condition includes: search key, geography position locating for user
It sets, browse website type and/or Application Type.
A6. method according to a4, wherein the task condition for obtaining advertiser's setting, according to user's row
Filtered out for database meet the specified requirements user be the advertisement major product audience, comprising:
The task condition for obtaining advertiser's setting, is screened in the user behavior data library by the way of inverted index
Meet the user of the task condition out；
The user for meeting the task condition filtered out is counted, the audience of advertisement major product is formed.
A7. according to the described in any item methods of A1-A6, wherein the determining respectively and institute in each first data structure
The overlapped data for stating the second data structure, the user property feature for including based on the overlapped data establish the audience
User's portrait analyzes user portrait, comprising:
The intersection that each first data structure and the second data structure are calculated separately by minHash algorithm, determines each first
The overlapped data of data structure and second data structure；
Determine the user property feature that the overlapped data includes, the user property feature based on the overlapped data is established
The user of the audience of the advertisement major product draws a portrait, and analyzes user portrait.
A8. the method according to A7, wherein the audient that the advertisement major product is established according to the overlapped data
The user of group draws a portrait, after analyzing user portrait, further includes:
The analysis of user's portrait is obtained as a result, and the analysis result is stored in designated storage area.
According to another aspect of the present invention, it additionally provides: a kind of analytical equipment of advertisement major product audience of B9.,
Include:
Statistical module is configured to count the behavioral data of each network user, and is based on each network user and each network user
Behavioral data establish user behavior data library；
First building module, the network user being configured in the user behavior data library construct multiple first data
Structure；Wherein, each first data structure includes different user property feature；
Second building module, configuration determine advertisement major product according to the user behavior data in the user behavior data library
Audience, based on the audience construct the second data structure；
Analysis module is configured in each first data structure determine and the overlapping number of second data structure respectively
According to the user property feature for including based on the overlapped data establishes user's portrait of the audience, draws to the user
As being analyzed.
B10. the device according to B9, wherein described first, which constructs module, includes:
Attributive analysis unit is configured to obtain the all-network user in the user behavior data library, to all-network
The user property feature of user is analyzed；
First data structure construction unit is configured to construct multiple first data structures using sets cardinal algorithm；Wherein,
Each first data structure includes different user property feature.
B11. the device according to B9, wherein described second, which constructs module, includes:
Acquiring unit is configured to obtain the task condition of advertiser's setting, be filtered out according to the user behavior data library
The user for meeting the specified requirements is the audience of the advertisement major product；
Second data structure construction unit, the audience for being configured to the advertisement major product are calculated using sets cardinal
Method constructs the second data structure.
B12. the device according to B11, wherein the acquiring unit is additionally configured to:
The task condition for obtaining advertiser's setting, is screened in the user behavior data library by the way of inverted index
Meet the user of the task condition out；
The user for meeting the task condition filtered out is counted, the audience of advertisement major product is formed.
B13. according to the described in any item devices of B9-B12, wherein the analysis module includes:
Computing unit is configured to calculate separately each first data structure and the second data structure by minHash algorithm
Intersection determines the overlapped data of each first data structure Yu second data structure；
User's portrait analytical unit, is configured to determine the user property feature that the overlapped data includes, based on described heavy
The user property feature of folded data establishes user's portrait of the audience of the advertisement major product, draws a portrait and carries out to the user
Analysis.
B14. device according to b13, wherein further include:
Memory module is configured to obtain the analysis of user's portrait as a result, and being stored in the analysis result specified
In storage region.
According to a further aspect of the invention, it additionally provides: C15. a kind of electronic equipment, wherein include:
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Device execution is managed according to the analysis method of the described in any item advertisement major product audiences of A1 to A8.
According to a further aspect of the invention, it additionally provides: a kind of computer readable storage medium of D16., wherein described
Computer-readable recording medium storage one or more program, it is included multiple application programs that one or more of programs, which are worked as,
When electronic equipment executes, so that the electronic equipment is executed according to the described in any item advertisement major product audiences of A1 to A8
Analysis method.
Claims (10)
1. a kind of analysis method of advertisement major product audience, comprising:
The behavioral data of each network user is counted, and the behavioral data based on each network user and each network user establishes user's row
For database；
Multiple first data structures are constructed based on the network user in the user behavior data library；Wherein, each first data knot
Structure includes different user property feature；
The audience of advertisement major product is determined according to the user behavior data in the user behavior data library, based on it is described by
Many the second data structures of informative population；
It determines the overlapped data with second data structure respectively in each first data structure, is based on the overlapped data packet
The user property feature contained establishes user's portrait of the audience, analyzes user portrait.
2. according to the method described in claim 1, wherein, the network user based in the user behavior data library constructs
Multiple first data structures, comprising:
The all-network user in the user behavior data library is obtained, the user property feature of all-network user is divided
Analysis；
Multiple first data structures are constructed using sets cardinal algorithm；Wherein, each first data structure includes different use
Family attributive character.
3. according to the method described in claim 1, wherein, the user property feature is including at least following one: user's gender,
Geographical location, age of user locating for user and user's occupation.
4. according to the method described in claim 1, wherein, the user behavior data according in the user behavior data library
The audience for determining advertisement major product, the audience based on the advertisement major product construct the second data structure, comprising:
The task condition for obtaining advertiser's setting, the use for meeting the specified requirements is filtered out according to the user behavior data library
Family is the audience of the advertisement major product；
Audience based on the advertisement major product constructs the second data structure using sets cardinal algorithm.
5. according to the method described in claim 4, wherein, the task condition includes: search key, geography position locating for user
It sets, browse website type and/or Application Type.
6. according to the method described in claim 4, wherein, the task condition for obtaining advertiser's setting, according to the user
Behavior database filters out the audience for meeting the user of the specified requirements for the advertisement major product, comprising:
The task condition for obtaining advertiser's setting, filters out symbol in the user behavior data library by the way of inverted index
Close the user of the task condition；
The user for meeting the task condition filtered out is counted, the audience of advertisement major product is formed.
7. method according to claim 1-6, wherein the determining respectively and institute in each first data structure
The overlapped data for stating the second data structure, the user property feature for including based on the overlapped data establish the audience
User's portrait analyzes user portrait, comprising:
The intersection that each first data structure and the second data structure are calculated separately by minHash algorithm determines each first data
The overlapped data of structure and second data structure；
The user property feature that the overlapped data includes is determined, described in the user property feature foundation based on the overlapped data
The user of the audience of advertisement major product draws a portrait, and analyzes user portrait.
8. a kind of analytical equipment of advertisement major product audience, comprising:
Statistical module is configured to count the behavioral data of each network user, and the row based on each network user and each network user
User behavior data library is established for data；
First building module, the network user being configured in the user behavior data library construct multiple first data knots
Structure；Wherein, each first data structure includes different user property feature；
Second building module, configuration according to the user behavior data in the user behavior data library determine advertisement major product by
Many groups construct the second data structure based on the audience；
Analysis module is configured in each first data structure the determining overlapped data with second data structure respectively, base
User's portrait of the audience is established in the user property feature that the overlapped data includes, draws a portrait and carries out to the user
Analysis.
9. a kind of electronic equipment, wherein include:
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the processor when executed
Execute the analysis method of advertisement major product audience according to any one of claims 1 to 7.
10. a kind of computer readable storage medium, wherein the computer-readable recording medium storage one or more program,
One or more of programs are when the electronic equipment for being included multiple application programs executes, so that the electronic equipment executes root
According to the analysis method of the described in any item advertisement major product audiences of claim 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711165999.5A CN109816410A (en) | 2017-11-21 | 2017-11-21 | The analysis method and device of advertisement major product audience |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711165999.5A CN109816410A (en) | 2017-11-21 | 2017-11-21 | The analysis method and device of advertisement major product audience |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109816410A true CN109816410A (en) | 2019-05-28 |
Family
ID=66600364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711165999.5A Pending CN109816410A (en) | 2017-11-21 | 2017-11-21 | The analysis method and device of advertisement major product audience |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816410A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517082A (en) * | 2019-08-29 | 2019-11-29 | 深圳前海微众银行股份有限公司 | Advertisement sending method, device, equipment and computer readable storage medium |
| CN112416945A (en) * | 2020-12-07 | 2021-02-26 | 恩亿科(北京)数据科技有限公司 | Data processing method and system based on big data platform and computer equipment |
| CN113468389A (en) * | 2020-03-30 | 2021-10-01 | 中国移动通信集团河北有限公司 | User portrait establishing method and device based on characteristic sequence comparison |
| CN115222461A (en) * | 2022-09-19 | 2022-10-21 | 杭州数立信息技术有限公司 | Intelligent marketing accurate recommendation method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236867A (en) * | 2011-08-15 | 2011-11-09 | 悠易互通（北京）广告有限公司 | Cloud computing-based audience behavioral analysis advertisement targeting system |
| CN103065260A (en) * | 2013-01-22 | 2013-04-24 | 分众(中国)信息技术有限公司 | Interactive advertisement information management system based on cloud computing |
| CN103268562A (en) * | 2013-05-23 | 2013-08-28 | 中国科学院计算机网络信息中心 | Internet advertisement audience population ascribed characteristic monitoring method and system |
| CN106408329A (en) * | 2016-08-30 | 2017-02-15 | 杭州启冠网络技术有限公司 | Advertisement visitor retrieving method and advertisement putting system |
| CN106504099A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of system for building user's portrait |
| CN106611344A (en) * | 2015-10-23 | 2017-05-03 | 北京国双科技有限公司 | Method and device for mining potential customers |
-
2017
- 2017-11-21 CN CN201711165999.5A patent/CN109816410A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236867A (en) * | 2011-08-15 | 2011-11-09 | 悠易互通（北京）广告有限公司 | Cloud computing-based audience behavioral analysis advertisement targeting system |
| CN103065260A (en) * | 2013-01-22 | 2013-04-24 | 分众(中国)信息技术有限公司 | Interactive advertisement information management system based on cloud computing |
| CN103268562A (en) * | 2013-05-23 | 2013-08-28 | 中国科学院计算机网络信息中心 | Internet advertisement audience population ascribed characteristic monitoring method and system |
| CN106504099A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of system for building user's portrait |
| CN106611344A (en) * | 2015-10-23 | 2017-05-03 | 北京国双科技有限公司 | Method and device for mining potential customers |
| CN106408329A (en) * | 2016-08-30 | 2017-02-15 | 杭州启冠网络技术有限公司 | Advertisement visitor retrieving method and advertisement putting system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517082A (en) * | 2019-08-29 | 2019-11-29 | 深圳前海微众银行股份有限公司 | Advertisement sending method, device, equipment and computer readable storage medium |
| CN113468389A (en) * | 2020-03-30 | 2021-10-01 | 中国移动通信集团河北有限公司 | User portrait establishing method and device based on characteristic sequence comparison |
| CN113468389B (en) * | 2020-03-30 | 2023-04-28 | 中国移动通信集团河北有限公司 | User portrait establishment method and device based on feature sequence comparison |
| CN112416945A (en) * | 2020-12-07 | 2021-02-26 | 恩亿科(北京)数据科技有限公司 | Data processing method and system based on big data platform and computer equipment |
| CN115222461A (en) * | 2022-09-19 | 2022-10-21 | 杭州数立信息技术有限公司 | Intelligent marketing accurate recommendation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10599313B2 (en) | System for high volume data analytic integration and channel-independent advertisement generation | |
| EP3038002B1 (en) | Interactive user interfaces | |
| US20160364770A1 (en) | System for high volume data analytic integration and channel-independent advertisement generation | |
| EP3117347B1 (en) | Systems and methods for rapid data analysis | |
| CN109299090B (en) | Foundation centrality calculating method, system, computer equipment and storage medium | |
| CN111444395B (en) | Method, system and equipment for obtaining relation expression between entities and advertisement recall system | |
| CN109816410A (en) | The analysis method and device of advertisement major product audience | |
| Dinh et al. | An efficient algorithm for mining periodic high-utility sequential patterns | |
| US11170306B2 (en) | Rich entities for knowledge bases | |
| US11341449B2 (en) | Data distillery for signal detection | |
| EP2668590A1 (en) | Identifying categorized misplacement | |
| WO2015066805A1 (en) | Systems and methods for behavioral segmentation of users in a social data network | |
| CN111291191B (en) | Broadcast television knowledge graph construction method and device | |
| US20140247267A1 (en) | Visualization of parallel co-ordinates | |
| US20190318255A1 (en) | Combining Entity Analysis and Predictive Analytics | |
| CN107480268A (en) | Data query method and device | |
| CN110134845A (en) | Project public sentiment monitoring method, device, computer equipment and storage medium | |
| CN109509028A (en) | A kind of advertisement placement method and device, storage medium, computer equipment | |
| US11630881B2 (en) | Data insight automation | |
| US9875288B2 (en) | Recursive filter algorithms on hierarchical data models described for the use by the attribute value derivation | |
| CN108876644A (en) | A kind of similar account calculation method and device based on social networks | |
| US10296928B1 (en) | System and methods for measuring and influencing customer trajectory within a product space | |
| WO2014123929A1 (en) | System and method for classifying a contagious phenomenon propagating on a network | |
| US10672030B2 (en) | Targeted advertisements from intended recipient predictions derived from user information | |
| US10558652B2 (en) | Merging multiproviders in a database calculation scenario |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |