CN110163683A - Value user's key index determines method, advertisement placement method and device - Google Patents
Value user's key index determines method, advertisement placement method and device Download PDFInfo
- Publication number
- CN110163683A CN110163683A CN201910441219.8A CN201910441219A CN110163683A CN 110163683 A CN110163683 A CN 110163683A CN 201910441219 A CN201910441219 A CN 201910441219A CN 110163683 A CN110163683 A CN 110163683A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior event
- value
- key index
- user behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention provides a kind of value user's key indexes to determine method, advertisement placement method and device, and value user's key index determines method, comprising: receives the user behavior event from client, and stores the user behavior event;Determine that classification belonging to the user behavior event of storage, the classification are value user or non-value user;Regression analysis is carried out using the user behavior event after generic that determines, obtaining having the user of the client of the relevant information of the user behavior event is the probability for being worth user;It whether is value user's key index according to the relevant information of user behavior event described in the determine the probability.The key index of potential value user can be automatically determined through the above scheme, to reduce the workload of analysis data in the case where improving advertisement and launching precision and reduce error rate.
Description
Technical field
The present invention relates to Internet technical fields more particularly to a kind of value user's key index to determine that method, advertisement are thrown
Put method and device.
Background technique
Currently, advertisement may be launched in different platforms simultaneously for an application product, for example, Google,
Facebook etc..Launch advertisement for a period of time, each platform can respectively carry out data analysis, its respective conclusion is obtained, for example,
Retention ratio or paying customer's ratio under different factors etc..Since the analysis data of different platform may be by the shadow of different factors
It rings, moreover, intercommunication is unable between the data of different platform, so the conclusion that different platform is obtained generally can be different.So, it arrives
The conclusion of which platform of bottom is key index correct, which factor is only user's retention or pays, these all can not
Automatically it learns.The core of existing implementation pattern is manual switching to different platform, and platform display data gives analysis personnel, analyzes people
Member's analysis data simultaneously summarize conclusion, search out high yield event, then launch advertisement by dispensing personnel selection.
However, analysis personnel will spend a lot of time the conclusion for analyzing each platform, and many need across function association can be faced
The communication problem of work, there is also the risks of error.
Summary of the invention
In view of this, the present invention provides a kind of value user's key indexes to determine method, advertisement placement method and device,
To automatically determine the key index of potential value user, to reduce analysis data in the case where improving advertisement and launching precision
Workload and reduce error rate.
According to an aspect of an embodiment of the present invention, it provides a kind of value user's key index and determines method, comprising:
The user behavior event from client of reception, and store the user behavior event;
Determine that classification belonging to the user behavior event of storage, the classification are value user or non-value user;
Regression analysis is carried out using the user behavior event after generic that determines, obtains that there is the user behavior
The user of the client of the relevant information of event is the probability of the value user;
It whether is value user's key index according to the relevant information of user behavior event described in the determine the probability.
Other side according to an embodiment of the present invention provides a kind of advertisement placement method, comprising:
Determine that method determines value user's key index using value user's key index described above;
The determining value user key index is transmitted to advertisement launching platform, so that the advertisement launching platform root
Value user is determined according to the determining value user key index, and will launch the client to the determining value user
The advertisement at end.
Another aspect according to an embodiment of the present invention provides a kind of value user key index determining device, comprising:
User behavior event acquiring unit for receiving the user behavior event from client, and stores the user
Behavior event;
User's taxon, for determining that classification belonging to the user behavior event of storage, the classification are value
User or non-value user;
Regression analysis unit is obtained for carrying out regression analysis using the user behavior event after generic that determines
User to the client of the relevant information with the user behavior event is the probability of the value user;
Key index determination unit, for the user behavior event according to the determine the probability relevant information whether be
It is worth user's key index.
Another aspect according to an embodiment of the present invention provides a kind of computer readable storage medium, is stored thereon with
Computer program, when which is executed by processor the step of realization the various embodiments described above the method.
Another aspect according to an embodiment of the present invention, provides a kind of computer equipment, including memory, processor and
The computer program that can be run on a memory and on a processor is stored, the processor is realized above-mentioned when executing described program
The step of each embodiment the method.
Value user's key index of the invention determines that method, advertisement placement method, value user's key index determine dress
Set, computer readable storage medium and computer equipment, can be realized it is automatic, directly obtained using all clients of a product
It takes most true data to obtain the accurate attribution of value user, can be avoided the authenticity questions of data source with this, and keep away
Exempt from the difference of the attribution conclusion of different platform, reduce the various problems that analysis personnel face, to be launched precisely improving advertisement
The workload of analysis data is reduced in the case where degree and reduces error rate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is that value user's key index of one embodiment of the invention determines the flow diagram of method;
Fig. 2 is the method flow schematic diagram of the dispensing advertisement of a specific embodiment of the invention;
Fig. 3 is the structural schematic diagram of the advertisement delivery system of a specific embodiment of the invention;
Fig. 4 is the structural schematic diagram of value user's key index determining device of one embodiment of the invention.
Specific embodiment
Understand in order to make the object, technical scheme and advantages of the embodiment of the invention clearer, with reference to the accompanying drawing to this hair
Bright embodiment is described in further details.Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but simultaneously
It is not as a limitation of the invention.
Firstly, being explained to the technical term that this specification may relate to:
BigQuery: the very competent tubular type cloud of boarding at the nursery of a kind of data-oriented analysis the quick, economical and practical of purposes, dilatation
End data warehouse;
Mobile applications: it is a kind of using journey to refer to that design is run to smart phone, tablet computer or other mobile devices
Sequence;
Marketing analysis platform: it is a kind of to track, collect mobile applications log, better data point are provided for marketing personnel
The software of analysis and decision support;
Attribution: when attribution refers to some result caused by common (or successive) effect of many factors, various factors is answered
This occupies the great effect for causing the result, and the model to solve the problems, such as attribution and establishing is referred to as attribution model, i.e.,
attribution modeling;
SDK (Software Development Kit, Software Development Kit): SDK is typically all some soft projects
Teacher is the set of developing instrument when specific software package, software frame, hardware platform, operating system etc. establish application software;
Interface: refer to the reference type being defined to agreement;Other types realize interface, to guarantee that it is certain that they are supported
Operation;
It launches: referring to and launch advertisement in advertising platform, a kind of payment obtains the behavior of user;
It retains: enlivening number of days after user installation APP (application program), be the standard of a measurement product revenue potential;
Payment: the behavior that user buys in APP.
Further, design of the invention is described in detail:
Fig. 1 is that value user's key index of one embodiment of the invention determines the flow diagram of method.As shown in Figure 1,
Value user's key index of some embodiments determines the flow diagram of method, it may include:
Step S110: the user behavior event from client is received, and stores the user behavior event;
Step S120: determine that classification belonging to the user behavior event of storage, the classification are value user or non-
It is worth user;
Step S130: regression analysis is carried out using the user behavior event after generic that determines, is obtained with institute
The user for stating the client of the relevant information of user behavior event is the probability of the value user;
Whether step S140: being that value user is crucial according to the relevant information of user behavior event described in the determine the probability
Index.
In above-mentioned steps S110, which can be mounted on terminal device (for example, mobile phone, tablet computer etc.)
Application program (APP).User behavior event can be received from all clients.
Wherein, the specific embodiment for the step of receiving the user behavior event from client may include: to connect in real time
Receive the user behavior event that client is sent by SDK.Wherein, " real-time " can refer to once have the production of user behavior event when client
When raw, so that it may report, each received user behavior event can be stored.
Above-mentioned user behavior event mainly may include the behavior event of the user of the client, and a user behavior event can
To include a behavior event.Behavior event may include: the sequence of screen browsing, click button, stop on a screen
Time, whether application retracted into the content etc. on backstage, concern.In addition, above-mentioned user behavior event may also include User ID (body
Part information), user property etc., wherein the user property may include the relevant information of one or more users, for example, gender,
Age, source place, occupation etc..
Wherein, the specific embodiment for the step of storing the user behavior event may include: by the user behavior
Event is stored into database.It stores by user behavior event to before database, it can be to received user behavior event
It is arranged, for example, being separated, user behavior event ordering to user property to behavior event with Time To Event
It is separated.User behavior event after arrangement can be stored by certain way into database.It can be with using database
Certain format stores user behavior event, for example, by each user behavior event be correspondingly formed one comprising User ID,
The data of user property, behavior event information, different user behavior event are correspondingly formed the data of different items.The database can
To be BigQuery database, or it can be other databases, for example, Redshift, hbase database etc..This kind
BigQuery database can handle mass data in a short time, can be improved with this and divide the user behavior event
Analyse speed.In other embodiments, if the format of received user behavior event is suitble to database by simple process with one
The formula that fixes storage, then may not necessarily process Jing Guo arrangement behavior event.
In above-mentioned steps S120, value user can bring direct or potential value for the client, such as trade
Income, advertising income etc..The value user, which can refer to, retains user, meanwhile, the non-value user can refer to non-stay
Deposit user.Retaining user is the user of a length of setting duration when enlivening, for example, retaining within 2nd, retaining within 7th, retaining within 14th, 28
Retain etc., the user of duration is enlivened if not this, then can be considered non-retention user.In the case, above-mentioned user behavior thing
It may include that set-up time, the user of the client of the user are made the last time using the time of client, user for the first time in part
With the time etc. of client.The time of client and user is used to use time of client the last time for the first time according to user,
Can judge whether the user is a certain retention user for enlivening duration.Above-mentioned retention user may include making for the first time on a certain date
It with client, sets after enlivening duration, still active all users, or may include using client for the first time on each date,
And a length of setting enlivens all users of duration (such as seven days) when enlivening.
In other embodiments, the value user can refer to paying customer, meanwhile, the non-value user can be
Refer to non-payment user.Client can provide some service items and buy for user, if user purchases in active setting duration
Certain service item is bought, then it is believed that the user is that setting enlivens the user to pay in duration, for example, not paying within 7th, 14
It does not pay, pay within 28th.So above-mentioned paying customer can refer to that user enlivens the user to pay in duration in setting,
If enlivened in setting it is non-paid in duration, it is believed that the user is non-payment user, or long-term not paying customer.In this feelings
It under condition, in above-mentioned user behavior event may include whether user is for the first time the client using the time of client, the user
Payment etc..It can calculate the user using calling time in the time of client and the user behavior event for the first time according to user and be
It is no to enliven duration not paying customer for setting.
Read storage user behavior event, the user behavior event may include subscriber identity information, behavior event information,
Customer attribute information etc..Determine classification belonging to the user behavior event of storage, that is, user behavior event is divided into two
Class: value user and non-are worth user.Determine the user's row after classification, obtained belonging to the user behavior event of storage
May include mark for event is the label of what classification, is also non-value user for example, being value user.At this point, determining institute
The user behavior event after belonging to classification may include subscriber identity information, behavior event information, customer attribute information and classification.
Wherein, subscriber identity information can be the ID of the user;Behavior event information may include screen browsing sequence, click by
Button, on a screen residence time, whether application retracted into one or more of backstage, content etc. of concern;User belongs to
Property information may include one or more of gender, age, source place, occupation etc..
In above-mentioned steps S130, the relevant information of the user behavior event can for the behavior event information and/
Or the customer attribute information specifically can be a certain behavior event information, such as sharing movement, alternatively, can be certain
A kind of customer attribute information, for example, occupation or age;Alternatively, can be certain several behavior event information, for example, click on content
And the residence time, alternatively, can be certain several customer attribute information, for example, occupation and age or customer attribute information and row
For the combination of event information, for example, age and click on content.
Can using an information comprising subscriber identity information, behavior event information, customer attribute information and classification as
One sample, alternatively, can be using subscriber identity information, behavior event information and classification as a sample, alternatively, can will use
Family identity information, customer attribute information and classification are as a sample.Customer attribute information and/or behavior thing in each sample
Part information can be used as a factor or be index.Subscriber identity information in each sample can be one kind, behavior thing
Part information can be one kind.Regression analysis can be carried out to the great amount of samples obtained in this way, for example, dualistic logistic regression, line
Property return etc., the corresponding user of combination for obtaining a certain subscriber identity information or several subscriber identity informations be to be worth user
Probability, alternatively, the corresponding user of the combination for obtaining a certain customer attribute information or several customer attribute informations is value user
Probability, alternatively, the combination for obtaining a certain or several customer attribute informations and a certain kind or several subscriber identity informations is corresponding
User be worth user probability.Wherein, gained probability can be used in evaluating this kind of information for a user as value
The contribution of user, can be less than or equal to one and the decimal more than or equal to zero or ratio or probability can be with power
The form of weight values is presented, at this point, the sum of corresponding probability of all factors is one or other definite values.
In some embodiments, step S130, that is, carried out using the user behavior event after generic that determines
Regression analysis, obtaining having the user of the client of the relevant information of the user behavior event is the value user
The specific embodiment of probability, it may include: binary logic time is carried out using the user behavior event after generic that determines
Return analysis, obtaining having the user of the client of the relevant information of the user behavior event is the general of the value user
Rate.
In above-mentioned steps S140, the relevant information (factor) of each user behavior event can correspond to respective probability.
Can be determined by comparing the relevant information (different factors) of different user behavior event by which or which information (because
Element) it can be used as evaluating whether the user of above-mentioned client is the key index for being worth user.Such as before size is come
The corresponding information of several probability is as key index, or will be greater than the corresponding information of probability of setting value and refer to as key
Mark.It can learn which type of user more likely brings potential value by obtained key index, so as to according to pass
Key mark sense respective client launches advertisement, to improve the precision of advertisement positioning.
In the embodiment of the present invention, by obtaining user behavior event from client, and classify to user behavior event,
And carry out regression analysis using sorted user behavior event, can be realized it is automatic, directly utilize all of a product
Client obtains most true data and obtains the accurate attribution of value user, is asked with the authenticity that this can be avoided data source
Topic, and the difference of the attribution conclusion of different platform is avoided, the various problems that analysis personnel face are reduced, thus improving advertisement
The workload of analysis data is reduced in the case where launching precision and reduces error rate.
The embodiment of the invention also provides a kind of advertisement placement method, the advertisement placement method of some embodiments, it may include:
S201: determine that method determines that value user's key refers to using value user key index described in the various embodiments described above
Mark;
S202: being transmitted to advertisement launching platform for the determining value user key index, so that the advertisement is launched
Platform determines value user according to the determining value user key index, and will launch institute to the determining value user
State the advertisement of client.
In above-mentioned steps S201, such as size can be come to the corresponding information of probability of several former as key index,
Or the corresponding information of probability of setting value can be will be greater than as key index.
In above-mentioned steps S202, the value user's key index determined can be transmitted by the interface of advertising platform
To advertising platform (can be existing advertising platform), the existing program that then can use advertising platform finds corresponding program and is
The client launches advertisement;Alternatively, value user's key index described in the various embodiments described above determines program corresponding to method
Code can be with product placement platform, after obtaining value user's key index, and can directly find corresponding program is the client
Launch advertisement in end.It can recorde a large amount of, the diversified information of user on advertising platform, therefore relatively used convenient for finding target
Family.
It, can be by manually according to its empirical verification one in the case that input data when carrying out regression analysis is insufficient
Whether lower gained key index is correct.The user behavior event from each client can be received constantly, in real time, calculated
After key index, in contrast user behavior event later increases, and can use the user behavior event increased
Periodically in this analysis of key index, if key index changes, new key index value advertising platform can be inputted, with into
Row more accurately launch by advertisement.
It can more accurately be client production using the value user key index that the above method determines in the present embodiment
Launch advertisement.
To make those skilled in the art be best understood from the present invention, it will illustrate implementation of the invention with specific embodiment below
Mode.
Fig. 2 is the method flow schematic diagram of the dispensing advertisement of a specific embodiment of the invention.Fig. 3 is that the present invention one is specific real
Apply the structural schematic diagram of the advertisement delivery system of example.Referring to figs. 2 and 3, the method for the dispensing advertisement of a specific embodiment, can wrap
Include step:
1. the behavior event of user is sent to BigQuery database purchase by SDK by mobile application client;
Wherein, Redshift, hbase database be can be or.It is whole that the data that client reports can first pass through data
It manages server and carries out data preparation, storing later to database.
User and non-retention user or paying customer and long-term not paying customer are retained 2. user is divided into;
Wherein, by program automatically to the arrangement of event, principle of classification is second day also opened APP's of user installation
It is considered and retains user.Paying all has specific statistical phenomeon to define.
3. the classification output in step 2 is imported into analysis system, dualistic logistic regression is done by existing user behavior,
It finds user and triggers the critical behavior retained or paid.
It wherein, may include the id and attribute (Sex, Age source province etc.) of user, behavior event, browsing in analysis data
The sequence of screen clicks those buttons, stopped on which screen how long, if will using retract backstage, concern
What.Logical first to cross the existing data building model of input, the user what behavior output has occurred leaves general
Rate is higher, then by the behavior on input new installation user's same day, and exports the weight that user can retain.Analysis system refers to machine
Device learning system, partial function can need to train, by inputting the user behavior event collected and retaining or pay later
The behavioural characteristic taken.It in addition to dualistic logistic regression, can also be analyzed by other models, such as linear regression.It can lead to
It crosses mass data and carries out logistic regression calculating, carry out training pattern, obtained machine learning classification model can be used to receive new use
The relevant information at family, so as to estimate the contribution situation of the new user.
4. result is exported and gives analysis personnel.Analysis personnel then can manually test if it is desired to do manual analysis to result
Demonstrate,prove result.If you do not need to manual analysis, then can enter directly into and issue decision.
Wherein, payment behavior event has used product in the 2nd, 7,14 days, 28 days etc. after client after can be installation.
5. an automatic or key issues decision to release platform, so that release platform is can use analysis decision, targetedly throw
It puts to the specific potential user to mobile process most worthy.
Wherein, advertisement launching platform can have orientation to launch function, such as by thinking 28-35 years old male, finance
Practitioner can prefer a client production, then can tell feature to advertising platform, be delivered to such interconnection by advertising platform
Network users.
In the present embodiment, to the data put in order, is calculated using dualistic logistic regression and retain user or paying customer
Behavioural characteristic, and export to the advantageous analysis result of retention for desk checking.Such as confirm decision, is then issued to release platform.It is logical
Data collection SDK, Data Analysis Platform are crossed, verifying can also be analyzed by human assistance and application scheme is summarized.Utilize machine
Study makes analysis to the data being collected into, and the attribution of decision recommendation or particular result after analysis is directly shown to analysis personnel
Analysis result after marketing personnel only need to analyze result by back forecasting, is fed directly to release platform, is helped with this by model
Release platform does sizing to the optimal user suitable for APP and launches.Realize a system summarize analysis in need data, and
The critical behavior for independently analyzing user only needs artificial nucleus to analysis as a result, dispensing can be issued directly.Greatly reduce analysis
Personnel and the workload for launching personnel, and the communication problem across function cooperation has been spent again.
The identical inventive concept of method is determined based on value user's key index shown in FIG. 1, and the embodiment of the present application is also
A kind of value user key index determining device is provided, as described in following example.Since value user's key index is true
Determine the principle that device solves the problems, such as and determine that method is similar to value user's key index, therefore value user's key index determines
The implementation of device may refer to the implementation that value user's key index determines method, and overlaps will not be repeated.
Fig. 4 is the structural schematic diagram of value user's key index determining device of one embodiment of the invention.As shown in figure 4,
Value user's key index determining device of some embodiments, it may include:
User behavior event acquiring unit 210 for receiving the user behavior event from client, and stores the use
Family behavior event;
User's taxon 220, for determining that classification belonging to the user behavior event of storage, the classification are valence
It is worth user or non-value user;
Regression analysis unit 230, for carrying out regression analysis using the user behavior event after generic that determines,
Obtaining having the user of the client of the relevant information of the user behavior event is the probability for being worth user;
Key index determination unit 240, the relevant information for the user behavior event according to the determine the probability are
No is value user's key index.
The embodiment of the present invention also provides a kind of computer readable storage medium, is stored thereon with computer program, the program
The step of above-described embodiment the method is realized when being executed by processor.
The embodiment of the present invention also provides a kind of computer equipment, including memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, the processor realize above-described embodiment the method when executing described program
Step.
In some embodiments, user behavior event acquiring unit, it may include: user behavior event obtains module, for real
When receive the user behavior event sent by SDK of client.
In some embodiments, user behavior event acquiring unit 210, it may include: user behavior event obtains module, is used for
The user behavior event is stored into database;The database includes BigQuery database.
In some embodiments, the user behavior event after determining generic includes subscriber identity information, behavior thing
Part information, customer attribute information and classification;The relevant information of the user behavior event is the behavior event information or described
Customer attribute information.
In some embodiments, the value user is to retain user, and the non-value user is non-retention user;Or
Person, the value user is paying customer, and the non-value user is non-payment user.
In some embodiments, regression analysis unit 230, it may include: regression analysis module, for utilizing determining generic
The user behavior event afterwards carries out binary logical regression analysis, obtains the relevant information with the user behavior event
The user of the client is the probability of the value user.
The embodiment of the present invention also provides a kind of advertisement delivery system, the advertisement delivery system can include:
It is worth user's key index determining device, for true using value user's key index described in the various embodiments described above
Determine method and determines value user's key index;
Advertisement delivery device, for the value user key index determined to be transmitted to advertisement launching platform, so that
The advertisement launching platform determines value user according to the determining value user key index, and will be to the determining valence
Value user launches the advertisement of the client.
In conclusion value user's key index of the embodiment of the present invention determines method, advertisement placement method, value user
Key index determining device, computer readable storage medium and computer equipment, by obtaining user behavior event from client,
And classify to user behavior event, and carry out regression analysis using sorted user behavior event, it can be realized certainly
It is dynamic, directly obtain most true data using all clients of a product and obtain the accurate attribution of value user, with this energy
The authenticity questions of data source are enough avoided, and avoid the difference of the attribution conclusion of different platform, analysis personnel is reduced and faces
Various problems, thus improve advertisement launch precision in the case where reduce analysis data workload and reduce error rate.
In the description of this specification, reference term " one embodiment ", " specific embodiment ", " some implementations
Example ", " such as ", the description of " example ", " specific example " or " some examples " etc. mean it is described in conjunction with this embodiment or example
Particular features, structures, materials, or characteristics are included at least one embodiment or example of the invention.In the present specification,
Schematic expression of the above terms may not refer to the same embodiment or example.Moreover, the specific features of description, knot
Structure, material or feature can be combined in any suitable manner in any one or more of the embodiments or examples.Each embodiment
Involved in the step of sequence be used to schematically illustrate implementation of the invention, sequence of steps therein is not construed as limiting, can be as needed
It appropriately adjusts.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail it is bright, it should be understood that the above is only a specific embodiment of the present invention, the guarantor being not intended to limit the present invention
Range is protected, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection scope of invention.
Claims (10)
1. a kind of value user's key index determines method characterized by comprising
The user behavior event from client of reception, and store the user behavior event;
Determine that classification belonging to the user behavior event of storage, the classification are value user or non-value user;
Regression analysis is carried out using the user behavior event after generic that determines, obtains that there is the user behavior event
Relevant information the client user be it is described value user probability;
It whether is value user's key index according to the relevant information of user behavior event described in the determine the probability.
2. value user's key index determines method as described in claim 1, which is characterized in that receive the use from client
Family behavior event, comprising:
The user behavior event that real-time reception client is sent by SDK.
3. value user's key index determines method as described in claim 1, which is characterized in that store the user behavior thing
Part, comprising:
The user behavior event is stored into database;The database includes BigQuery database.
4. value user's key index determines method as described in claim 1, which is characterized in that the institute after determining generic
Stating user behavior event includes subscriber identity information, behavior event information, customer attribute information and classification;The user behavior thing
The relevant information of part is the behavior event information or the customer attribute information.
5. value user's key index determines method as described in claim 1, which is characterized in that the value user is to retain
User, and the non-value user is non-retention user;Alternatively, the value user is paying customer, and the non-value is used
Family is non-payment user.
6. value user's key index determines method as described in claim 1, which is characterized in that after determining generic
The user behavior event carry out regression analysis, obtain the client with the relevant information of the user behavior event
User be it is described value user probability, comprising:
Binary logical regression analysis is carried out using the user behavior event after generic that determines, obtains that there is the user
The user of the client of the relevant information of behavior event is the probability of the value user.
7. a kind of advertisement placement method characterized by comprising
Determine that method determines that value user's key refers to using value user's key index such as claimed in any one of claims 1 to 6
Mark;
The determining value user key index is transmitted to advertisement launching platform, so that the advertisement launching platform is according to really
The fixed value user key index determines value user, and will launch the client to the determining value user
Advertisement.
8. a kind of value user key index determining device characterized by comprising
User behavior event acquiring unit for receiving the user behavior event from client, and stores the user behavior
Event;
User's taxon, for determining that classification belonging to the user behavior event of storage, the classification are value user
Or non-value user;
Regression analysis unit is had for carrying out regression analysis using the user behavior event after generic that determines
The user of the client of the relevant information of the user behavior event is the probability of the value user;
Key index determination unit, whether the relevant information for the user behavior event according to the determine the probability is value
User's key index.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
It is realized when row such as the step of any one of claim 1 to 7 the method.
10. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor is realized when executing described program such as any one of claim 1 to 7 the method
The step of.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910441219.8A CN110163683B (en) | 2019-05-24 | 2019-05-24 | Value user key index determination method, advertisement delivery method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910441219.8A CN110163683B (en) | 2019-05-24 | 2019-05-24 | Value user key index determination method, advertisement delivery method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110163683A true CN110163683A (en) | 2019-08-23 |
CN110163683B CN110163683B (en) | 2020-04-14 |
Family
ID=67632770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910441219.8A Active CN110163683B (en) | 2019-05-24 | 2019-05-24 | Value user key index determination method, advertisement delivery method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110163683B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111274907A (en) * | 2020-01-16 | 2020-06-12 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for determining a category label of a user using a category identification model |
CN112184046A (en) * | 2020-10-12 | 2021-01-05 | 上海移卓网络科技有限公司 | Advertisement service user value evaluation method, device, equipment and storage medium |
CN112801693A (en) * | 2021-01-18 | 2021-05-14 | 百果园技术(新加坡)有限公司 | Advertisement characteristic analysis method and system based on high-value user |
CN113918740A (en) * | 2021-11-24 | 2022-01-11 | 北京达佳互联信息技术有限公司 | Event information processing method and device, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080065395A1 (en) * | 2006-08-25 | 2008-03-13 | Ferguson Eric J | Intelligent marketing system and method |
CN105574147A (en) * | 2015-12-15 | 2016-05-11 | 腾讯科技(深圳)有限公司 | Information processing method and server |
CN106203836A (en) * | 2016-07-12 | 2016-12-07 | 中国石油化工股份有限公司 | A kind of appraisal procedure of oil refining enterprise equipment dependability performance management |
CN106295382A (en) * | 2015-05-20 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Information Risk preventing control method and device |
CN106682938A (en) * | 2016-12-23 | 2017-05-17 | 广州帷策智能科技有限公司 | Big-data precision marketing model establishing method and device |
CN109558530A (en) * | 2018-10-23 | 2019-04-02 | 深圳壹账通智能科技有限公司 | User's portrait automatic generation method and system based on data processing |
-
2019
- 2019-05-24 CN CN201910441219.8A patent/CN110163683B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080065395A1 (en) * | 2006-08-25 | 2008-03-13 | Ferguson Eric J | Intelligent marketing system and method |
CN106295382A (en) * | 2015-05-20 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Information Risk preventing control method and device |
CN105574147A (en) * | 2015-12-15 | 2016-05-11 | 腾讯科技(深圳)有限公司 | Information processing method and server |
CN106203836A (en) * | 2016-07-12 | 2016-12-07 | 中国石油化工股份有限公司 | A kind of appraisal procedure of oil refining enterprise equipment dependability performance management |
CN106682938A (en) * | 2016-12-23 | 2017-05-17 | 广州帷策智能科技有限公司 | Big-data precision marketing model establishing method and device |
CN109558530A (en) * | 2018-10-23 | 2019-04-02 | 深圳壹账通智能科技有限公司 | User's portrait automatic generation method and system based on data processing |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111274907A (en) * | 2020-01-16 | 2020-06-12 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for determining a category label of a user using a category identification model |
CN111274907B (en) * | 2020-01-16 | 2023-04-25 | 支付宝(中国)网络技术有限公司 | Method and apparatus for determining category labels of users using category recognition model |
CN112184046A (en) * | 2020-10-12 | 2021-01-05 | 上海移卓网络科技有限公司 | Advertisement service user value evaluation method, device, equipment and storage medium |
CN112801693A (en) * | 2021-01-18 | 2021-05-14 | 百果园技术(新加坡)有限公司 | Advertisement characteristic analysis method and system based on high-value user |
CN113918740A (en) * | 2021-11-24 | 2022-01-11 | 北京达佳互联信息技术有限公司 | Event information processing method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110163683B (en) | 2020-04-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103823908B (en) | Content recommendation method and server based on user preference | |
Han et al. | Segmentation of telecom customers based on customer value by decision tree model | |
CN108154401A (en) | User's portrait depicting method, device, medium and computing device | |
CN110428298A (en) | A kind of shop recommended method, device and equipment | |
CN107730311A (en) | A kind of method for pushing of recommendation information, device and server | |
CN110163683A (en) | Value user's key index determines method, advertisement placement method and device | |
CN110033156A (en) | A kind of determination method and device of business activity effect | |
CN104115178A (en) | Methods and systems for predicting market behavior based on news and sentiment analysis | |
CN106570718A (en) | Information releasing method and releasing system | |
CN106970953B (en) | Network construction management-control method and its platform based on big data analysis | |
CN109636457A (en) | A kind of advertisement placement method, apparatus and system towards high net value client | |
US20200175530A1 (en) | Pathing and attribution in marketing analytics | |
CN107067282B (en) | Consumer product rebate sale marketing management system and use method thereof | |
CN107402944A (en) | Attribution model for content item conversion | |
CN109670855A (en) | The methods of marking and device of information flow platform author | |
CN109993544A (en) | Data processing method, system, computer system and computer readable storage medium | |
Li et al. | Profit earning and monetary loss bidding in online entertainment shopping: the impacts of bidding patterns and characteristics | |
CN109242516A (en) | The single method and apparatus of processing service | |
CN115147144A (en) | Data processing method and electronic equipment | |
CN109426983A (en) | Dodge purchase activity automatic generation method and device, storage medium, electronic equipment | |
CN108985810A (en) | A kind of method and apparatus that party in request's platform carries out advertisement dispensing | |
Preissl et al. | E-life after the dot com bust | |
CN110175883A (en) | A kind of sort method, device, electronic equipment and non-volatile memory medium | |
CN110135975A (en) | A kind of customized information sending method, device, system and the recording medium of credit product | |
CN108416525A (en) | A kind of procedural model method for measuring similarity based on metadata |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |