CN106910082A - It is a kind of to transfer the method and apparatus that advertisement is pushed - Google Patents
It is a kind of to transfer the method and apparatus that advertisement is pushed Download PDFInfo
- Publication number
- CN106910082A CN106910082A CN201510982576.7A CN201510982576A CN106910082A CN 106910082 A CN106910082 A CN 106910082A CN 201510982576 A CN201510982576 A CN 201510982576A CN 106910082 A CN106910082 A CN 106910082A
- Authority
- CN
- China
- Prior art keywords
- information classification
- advertisement
- browser
- current information
- current
- 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
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
- G06Q30/0241—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
- G06Q30/0263—Targeted advertisements based upon Internet or website rating
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method and apparatus that advertisement is pushed are transferred the invention discloses a kind of.Methods described includes:Receive the current information classification that browser sends, the current information classification is analyzed the behavioural characteristic data produced when user accesses current web page and is obtained in real time by the browser, and the web advertisement of the correspondence current information classification is transferred based on the current information classification;The web advertisement is sent to the browser, the browser is included on the current web page web advertisement.By above-mentioned mechanism, according to the behavioural characteristic data of the newest generation of browser, obtaining current information classification in real time carries out real-time advertisement recommendation to user's current web page, current information classification can preferably identify user's current behavior, the advertisement more related to user's current behavior can be recommended, such that it is able to improve the clicking rate of the advertisement of recommendation.
Description
Technical field
The present invention relates to software technology field, and in particular to a kind of to transfer the method that advertisement is pushed, and
It is a kind of to transfer the device that advertisement is pushed.
Background technology
Due to developing rapidly for internet, advertisement is delivered on webpage becomes the important means of current publicity.
When delivering advertisement on webpage, the interest characteristics of each user can be first excavated, further according to user's
Hobby carries out targetedly advertisement, so as to improve advertisement delivery effect.
And in the hobby of digging user, be generally based on off-line data excavation, that is, need to be collected into use
The full dose historical data at family, then carries out excavating the behavior of user, further obtains the interest of user
Hobby, then the hobby for user is delivered.
But because user behavior is the i.e. interest focus of user's the previous day and current emerging with ageing
Interesting focus is likely to be different, therefore, for historical behavior analysis user interest, simultaneously non-user is current
The interest of concern, then the clicking rate of advertisement can be then influenceed based on current this push mode, advertisement is thrown
The effect put is undesirable.
The content of the invention
In view of the above problems, it is proposed that the present invention overcomes above mentioned problem or at least in part to provide one kind
What is solved the above problems transfers the method that advertisement is pushed, and a kind of transfers the device that advertisement is pushed.
According to one aspect of the present invention, there is provided a kind of to transfer the method that advertisement is pushed, including:
The current information classification that browser sends is received, the current information classification is divided in real time by the browser
Analysis user accesses the behavioural characteristic data produced during current web page and obtains;
The web advertisement of the correspondence current information classification is transferred based on the current information classification;
The web advertisement is sent to the browser, the browser is included the web advertisement
On the current web page.
Alternatively, the behavioural characteristic data are obtained by the record that the browser transfers access log in real time.
Alternatively, the behavioural characteristic data buffer storage is in the first buffer queue, by the browser from described
Extracted in first buffer queue.
Alternatively, the behavioural characteristic data include search keyword;
The current information classification is obtained by following steps:
The browser analyzes the search keyword and obtains at least one information category and obtain correspondence in real time
Class weight value, then extract the information category of predetermined number as the current information classification.
Alternatively, the current information classification is obtained by following steps:
At least one information category and corresponding class weight value are cached to second and delayed by the browser
In depositing queue;The information category of predetermined number is extracted from second buffer queue again as described current
Information category, and extract corresponding class weight value.
Alternatively, the behavioural characteristic data are analyzed described, after acquisition current information classification,
Specifically also include:
The browser utilizes the historical information classification of the current information classification more new record.
Alternatively, in the webpage that the correspondence current information classification is transferred based on the current information classification
Before advertisement, including:
The web advertisement is classified.
Alternatively, the webpage for transferring the correspondence current information classification based on the current information classification is wide
Accuse, specially:
The content-data of the advertisement of the correspondence current information classification, or advertisement are transferred from advertising database
Storage address, or advertisement identification information.
According to another aspect of the present invention, there is provided a kind of to transfer the device that advertisement is pushed, wherein,
Including:
Receiver module, the current information classification for receiving browser transmission, the current information classification is by institute
State browser and analyze the behavioural characteristic data acquisition produced during user's access current web page in real time;
Module is transferred, the webpage for transferring the correspondence current information classification based on the current information classification
Advertisement;
Sending module, for the web advertisement to be sent into the browser, makes the browser described
Web advertisement is displayed on the current web page.
Alternatively, the behavioural characteristic data are obtained by the record that the browser transfers access log in real time.
Alternatively, the behavioural characteristic data buffer storage is in the first buffer queue, by the browser from described
Extracted in first buffer queue.
Alternatively, the behavioural characteristic data include search keyword;
The current information classification is obtained by following steps:
The browser analyzes the search keyword and obtains at least one information category and obtain correspondence in real time
Class weight value, then extract the information category of predetermined number as the current information classification.
Alternatively, the current information classification is obtained by following steps:
At least one information category and corresponding class weight value are cached to second and delayed by the browser
In depositing queue;The information category of predetermined number is extracted from second buffer queue again as described current
Information category, and extract corresponding class weight value.
Alternatively, the behavioural characteristic data are analyzed described, after acquisition current information classification,
Specifically also include:
The browser utilizes the historical information classification of the current information classification more new record.
Alternatively, it is described transfer module before, including:
Sort module, for the web advertisement to be classified.
Alternatively, it is described to transfer module, specifically for transferring the correspondence current information from advertising database
The content-data of the advertisement of classification, or advertisement storage address, or advertisement identification information.
According to embodiments of the invention, the current information classification that browser sends, the current information class are received
The behavioural characteristic data produced when user accesses current web page are not analyzed in real time by the browser to obtain, and are based on
The current information classification transfers the web advertisement of the correspondence current information classification;By web advertisement hair
The browser is given, the browser is included on the current web page web advertisement.Pass through
Above-mentioned mechanism, according to the behavioural characteristic data of the newest generation of browser, in real time obtain current information classification to
Family current web page carries out real-time advertisement recommendation, and current information classification can preferably identify user's current behavior,
The advertisement more related to user's current behavior can be recommended, such that it is able to improve the clicking rate of the advertisement of recommendation.
Described above is only the general introduction of technical solution of the present invention, in order to better understand technology of the invention
Means, and being practiced according to the content of specification, and in order to allow above and other objects of the present invention,
Feature and advantage can become apparent, below especially exemplified by specific embodiment of the invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are for ability
Domain those of ordinary skill will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and simultaneously
It is not considered as limitation of the present invention.And in whole accompanying drawing, identical is denoted by the same reference numerals
Part.In the accompanying drawings:
Fig. 1 shows according to embodiments of the present invention 1 flow chart for transferring the method that advertisement is pushed;
Fig. 2 shows according to embodiments of the present invention 1 structured flowchart for transferring the device that advertisement is pushed;
Fig. 3 shows according to embodiments of the present invention 2 structured flowchart for transferring the device that advertisement is pushed.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although being shown in accompanying drawing
The exemplary embodiment of the disclosure, it being understood, however, that may be realized in various forms the disclosure without should be by
Embodiments set forth here is limited.Conversely, there is provided these embodiments are able to be best understood from this
It is open, and can by the scope of the present disclosure it is complete convey to those skilled in the art.
Embodiment 1
With reference to Fig. 1, according to embodiments of the present invention 1 flow for transferring the method that advertisement is pushed is shown
Figure, the method specifically may comprise steps of:
Step 101, the current information classification for receiving browser transmission, the current information classification are browsed by described
Device analyzes user and accesses the behavioural characteristic data acquisition produced during current web page in real time.
User access current web page when, the behavior of generation include but is not limited to be:User is input into current web page
The behavior of search keyword, user click on the behavior of peer link in current web page and other are any applicatory
Behavior.Illustrated with search inquiry behavior, the type of action of behavioural characteristic data including user behavior,
The keyword of current web page input, link address, access behavior generation that peer link is clicked in current web page
The information such as temporal information.The web page access behavior of different user can be by the IP address of residing terminal, net
The page identifier of client, user login information or other can arbitrarily identify the information of user.
In implementing, due to all behaviors for producing when user accesses current web page in access log, because
This behavioural characteristic data is obtained by the record that the browser transfers access log in real time.
For example, the step of behavioural characteristic data in step 101 can be performed by scribe result collection systems,
The application is applied to, can be stored to a central storage system (example from collector journal on various Log Sources
Such as distributed file system) on, in order to carry out concentrating statistical analysis treatment.And can be " dividing for daily record
Cloth is collected, and is uniformly processed " an expansible, fault-tolerant scheme high is provided, when the net of central storage system
When network or machine break down, daily record is dumped into local or another position, work as central storage system
After recovery, the daily record of unloading can be retransmitted to central storage system.
Behavioural characteristic data can also actually have a plurality of, for example, trigger the behavioral data of search, access webpage
Behavioral data, click on the behavioral data etc. of advertisement.In order to ensure obtain behavioural characteristic data speed and
The coordination of the speed of behavioural characteristic data is processed, the behavioural characteristic data buffer storage of acquisition can be delayed described first
Deposit queueInEnter row buffering, then extracted from first buffer queue by the browser.To have
Effect prevents from being counted caused by the too fast at least one obtained in being processed slowly excessively with behavioural characteristic data of behavioural characteristic data
According to losing or data are blocked, it is ensured that data handling procedure is normally carried out.
And the first buffer queue can be a kind of storage device, it is mainly used in storing behavioural characteristic data.
In addition, the number of behavioural characteristic data can be configured according to actual needs.In the embodiment of the present invention,
From first buffer queue behavioural characteristic can be carried out by the way of wall scroll extracts behavioural characteristic data
Data are extracted.
Preferably, the step of analytical behavior characteristic can be performed by strom real time processing systems.Specifically,
Can be pre-designed one in real time calculating topological structure, topological structure is then submitted into server set
Group, by main controlled node distribution code in server cluster, assigns the task to the execution of other working nodes.One
Individual topology includes two kinds of servers of difference in functionality of spout (data source) and bolt (data manipulation), its
Middle spout sends message, and the responsible data flow by pending behavioural characteristic data is in the form of tuple tuples
Send;And bolt is then responsible for changing these data flows, the operations such as analysis, filtering are completed in bolt,
Data flow can also be sent to other bolt by bolt itself at random, wherein, every treatment of information can be obtained
To guarantee, if certain processing failure can re-read and process from data source, and occur in commission wrong
Mistake, also task can be redistributed by storm.
By above-mentioned framework, strom can realize fault-tolerant calculating real-time, distributed and high, be applied to
The application, can process the behavioural characteristic data processing for continually obtaining, and result is written into phase
In should storing.
After browser obtains behavioural characteristic data, then behavioural characteristic data can in real time be analyzed and be worked as
Preceding information category.
The mode that browser is analyzed to behavioural characteristic data, mainly including participle, classification and label etc..
In implementing, one or more behavioural characteristic Data Concurrents can be processed, obtained for difference
The current information classification of multiple behavioural characteristic data of access request operation.
In addition, current information classification may not only one of which information category, may comprising multiple information categories,
And each information category is to that should have respective weighted value.
When current information classification includes multiple information categories, can extract meet preset range (for example
More than certain threshold value) information category as current information classification, the Rule Extraction that can also be set according to other,
It is not limited herein.
So that behavioural characteristic data include search keyword as an example, i.e.,:Produced when user accesses current web page
Behavior is user when current web page is input into the behavior of search keyword, and corresponding behavioural characteristic data include defeated
The search keyword for entering.So described current information classification is obtained by following steps:Browser is from the row
It is characterized the search keyword that user described in extracting data is input into the current web page.The browser reality
When analyze the search keyword, obtain at least one information category and obtain corresponding class weight value,
Then the information category of predetermined number is extracted as the current information classification.In addition, also can extract out it is right
The weighted value answered.
Specifically, the search keyword that browser will can be extracted is input into preset classification forecast model, then
Obtain at least one information category and obtain corresponding class weight value.
In the embodiment of the present invention, when a search keyword is input into forecast model of classifying, may predict
Go out one or more information categories, each information category has corresponding class weight value.For example, the pass of input
Key information is " Beijing ", and the information category that prediction is obtained is probably city, the Chinese capital and host place of the Olympics three
Kind, wherein, the corresponding class weight value of city category may be 1, the corresponding class weight of the Chinese capital classification
Value may be 2, and the corresponding class weight value in host place of the Olympics may be 3.The present invention is only illustrated herein,
It is not limited.
Additionally, can also be stored as the current information classification of acquisition and corresponding class weight value by browser
Specific data form, is easy to follow-up data transfer.
In addition, in order to avoid the phenomenon of data congestion, it is ensured that data handling procedure is normally carried out.It is described
Browser can be cached to the second buffer queue at least one information category and corresponding class weight value
In;The information category of predetermined number is extracted from second buffer queue again as the current information class
Not, and corresponding class weight value is extracted.
Second buffer queue can also be a kind of storage device, be mainly used in caching is obtained at least one
Current information classification and corresponding class weight value.
Can be by the current information classification extracted from second buffer queue and corresponding classification power
Weight values are stored to service computer room, import online real-time data base.Wherein, predetermined number can be according to actual need
It is configured.It should be noted that when the data extracted from second buffer queue can also include
Between information, the temporal information can be timestamp information.
In the embodiment of the present invention, the current letter can be extracted using wall scroll from second buffer queue
The mode of breath classification and corresponding class weight value carries out data extraction, can specifically use two-stage queue frame
Structure pattern, will extract from the current information classification according to behavioural characteristic data prediction and from the second buffer queue
Current information classification packet receive, merge incremental update to external storage, i.e., using process model ledger line journey
The mode that model is combined is write in many computer rooms.
In addition, after current information classification is obtained, browser can also be using the current information classification more
The historical information classification of new record.
The historical information classification for how utilizing the current information classification more new record is described below.
First, browser, will be same according at least one information category and corresponding class weight value
Current class weighted value and history class weight value under information category are merged, described after being merged
Historical information classification and the history class weight value.
In the embodiment of the present invention, according in the behavioural characteristic data record generation access request IP address,
The identifier or program login name of terminal or search client, determine that current access operation behavior is corresponding specific
User.Compare current information classification and historical information classification, when historical information classification includes current information classification
When, the class weight value for same information category is updated, by the volume class weight of same information category
Value is merged;When historical information classification does not include current information classification, one is added in the data of record
New information category, and record corresponding class weight value, the historical information classification after being merged and
The history class weight value.
Secondly, according to the temporal information of the historical information classification, the history class weight value after merging is entered
Row decay calculation, the history class weight value after being decayed.
Two kinds of modes of decay calculation are introduced separately below:
Attenuation of the first kind mode:
Browser, can be by certain time interval, i.e., according to other actual conditions such as user behavior treating capacity
Certain frequency, periodically carries out decay calculation to the history class weight value for recording, and updates the history classification
Weighted value.For example, certain time is directed to, and when the quantity of the behavioural characteristic data for the treatment of is larger, can be
Time interval is set to 4 hours, and 6 decay calculations were performed equivalent to 1 day;When the behavioural characteristic number for the treatment of
According to quantity it is smaller when, time interval can be set to 1 hour, equivalent to 1 day perform 1 decremeter
Calculate.The present invention is not limited herein, every feasible suitable for enforceable implementation method of the invention.
In implementing, carried out in the preceding class weight value and history class weight value to same information category
After merging, decay calculation is carried out to history class weight value.In implementing, a decay system can be preset
Number, during decay calculation, attenuation coefficient is always certain value, it is possible to use weighted value decay below
Computing formula calculates the class weight value after decay:
W=(W1+CW0)
Wherein, W0It is history class weight value, W1It is current class weighted value, C is have with time factor
The attenuation coefficient of pass, is also final attenuation coefficient, by causing most real-time behavior weight higher, it is ensured that
The time effect of behavior weight, W is the history class weight value after decay calculation.
Above-mentioned decay strategy realizes the data outside cleaning certain hour window, in order to ensure to allow in resource
In the case of, the historical behavior data of record are the newest and maximally effective data for user, can be right
The historical behavior data of record are cleared up.
In implementing, the historical information classification can be cleared up in the way of periodic cleaning, it is also possible to every
During secondary more new historical class weight value, the historical information classification is cleared up.The present invention is only herein to be illustrated,
It is not limited.
Data in certain hour window set in advance can be cleared up, Prune Policies can be according to reality
Border demand is set, and in the embodiment of the present application, historical information classification can be cleared up according to temporal information,
For example, clearance time information is the historical information classification in certain hour window, cleaning history class weight symbol
The history classification information (being, for example, less than certain threshold value) of preset range is closed, other business can also be further searched for
It is relatively low to commercial value for the information related to commercial value of history classification information record in system
History classification information is cleared up.Such as ad click rate of history classification information, such as entertains the advertisement point of class
Ad click rate of the rate less than fashion class is hit, then the less history classification information of clicking rate can be cleared up.
The mode of above-mentioned cleaning can select an execution and multiple can also combine execution.
It should be noted that for processed offline, the processing procedure of user data is most crucial part,
But in real-time processing, the collection of user data, treatment, and output all turns into the crucial ring of whole flow process
Section.Each link is required for considering comprehensive.Embodiments of the invention are applied commercial product team DMP's
During the project that behavioural characteristic data are accessed in real time.Behavioural characteristic data are the second by the delay reduction of original a day
The delay of rank.
Attenuation of the second kind mode:
In the embodiment of the present invention, can be in the preceding class weight value and history class weight to same information category
While value is merged, the class weight value to merging carries out decay calculation.In implementing, can be with
A default attenuation coefficient, during decay calculation, attenuation coefficient is always certain value, it is possible to use below
Weighted value decay calculation formula calculate decay after class weight value:
Wherein, W0' is t0The history class weight value at moment, W1' " are t1The current class weight at moment
Value, α ' are attenuation coefficient, the attenuation coefficient relevant with time factor, it is ensured that the time effect of behavior weight
Should, most real-time behavior weight is higher, and W ' are the history class weight value after decay calculation.
Step 102, the web advertisement that the correspondence current information classification is transferred based on the current information classification.
Web page server is transferred after the current information classification for receiving feedback in preset advertising database
With the advertisement of current information categorical match, wherein, the matching way of advertisement and information category can be according to reality
Demand sets, and can be classified for various advertisements in advance, directly selects and belongs to the wide of current information classification
Accuse as recommended advertisements.What is specifically extracted from advertising database can be that the content-data of advertisement (is for example schemed
The content of the actual displaying such as piece, video, word), or advertisement storage address, or advertisement
Identification information, the information of extraction is inserted into the webpage source file of current web page and then is shown, specific next
Say, advertisement can directly be rendered according to ad content data, storage address or mark letter according to advertisement
Breath is further rendered after extracting ad content data.
Step 103, the web advertisement is sent to the browser, makes the browser that the webpage is wide
Announcement is displayed on the current web page.
According to embodiments of the invention, the current information classification that browser sends, the current information class are received
The behavioural characteristic data produced when user accesses current web page are not analyzed in real time by the browser to obtain, and are based on
The current information classification transfers the web advertisement of the correspondence current information classification;By web advertisement hair
The browser is given, the browser is included on the current web page web advertisement.Pass through
Above-mentioned mechanism, according to the behavioural characteristic data of the newest generation of browser, in real time obtain current information classification to
Family current web page carries out real-time advertisement recommendation, and current information classification can preferably identify user's current behavior,
The advertisement more related to user's current behavior can be recommended, such that it is able to improve the clicking rate of the advertisement of recommendation.
Embodiment 2
With reference to Fig. 2, according to embodiments of the present invention 1 structure for transferring the device that advertisement is pushed is shown
Block diagram, can specifically include:
Receiver module 21, for receive browser transmission current information classification, the current information classification by
The browser analyzes user and accesses the behavioural characteristic data acquisition produced during current web page in real time.
User access current web page when, the behavior of generation include but is not limited to be:User is input into current web page
The behavior of search keyword, user click on the behavior of peer link in current web page and other are any applicatory
Behavior.Illustrated with search inquiry behavior, the type of action of behavioural characteristic data including user behavior,
The keyword of current web page input, link address, access behavior generation that peer link is clicked in current web page
The information such as temporal information.The web page access behavior of different user can be by the IP address of residing terminal, net
The page identifier of client, user login information or other can arbitrarily identify the information of user.
In implementing, due to all behaviors for producing when user accesses current web page in access log, because
This behavioural characteristic data is obtained by the record that the browser transfers access log in real time.
Behavioural characteristic data can also actually have a plurality of, for example, trigger the behavioral data of search, access webpage
Behavioral data, click on the behavioral data etc. of advertisement.In order to ensure obtain behavioural characteristic data speed and
The coordination of the speed of behavioural characteristic data is processed, the behavioural characteristic data buffer storage of acquisition can be delayed described first
Deposit and enter row buffering in queue, then extracted from first buffer queue by the browser.To have
Effect prevents from being counted caused by the too fast at least one obtained in being processed slowly excessively with behavioural characteristic data of behavioural characteristic data
According to losing or data are blocked, it is ensured that data handling procedure is normally carried out.
And the first buffer queue can be a kind of storage device, it is mainly used in storing behavioural characteristic data.
In addition, the number of behavioural characteristic data can be configured according to actual needs.In the embodiment of the present invention,
From first buffer queue behavioural characteristic can be carried out by the way of wall scroll extracts behavioural characteristic data
Data are extracted.
After browser obtains behavioural characteristic data, then behavioural characteristic data can in real time be analyzed and be worked as
Preceding information category.
The mode that browser is analyzed to behavioural characteristic data, mainly including participle, classification and label etc..
In implementing, one or more behavioural characteristic Data Concurrents can be processed, obtained for difference
The current information classification of multiple behavioural characteristic data of access request operation.
In addition, current information classification may not only one of which information category, may comprising multiple information categories,
And each information category is to that should have respective weighted value.
When current information classification includes multiple information categories, can extract meet preset range (for example
More than certain threshold value) information category as current information classification, the Rule Extraction that can also be set according to other,
It is not limited herein.
So that behavioural characteristic data include search keyword as an example, i.e.,:Produced when user accesses current web page
Behavior is user when current web page is input into the behavior of search keyword, and corresponding behavioural characteristic data include defeated
The search keyword for entering.So described current information classification is obtained by following steps:Browser is from the row
It is characterized the search keyword that user described in extracting data is input into the current web page.The browser reality
When analyze the search keyword, obtain at least one information category and obtain corresponding class weight value,
Then the information category of predetermined number is extracted as the current information classification.In addition, also can extract out it is right
The weighted value answered.
In addition, in order to avoid the phenomenon of data congestion, it is ensured that data handling procedure is normally carried out.It is described
Browser can be cached to the second buffer queue at least one information category and corresponding class weight value
In;The information category of predetermined number is extracted from second buffer queue again as the current information class
Not, and corresponding class weight value is extracted.
Second buffer queue can also be a kind of storage device, be mainly used in caching is obtained at least one
Current information classification and corresponding class weight value.
Can be by the current information classification extracted from second buffer queue and corresponding classification power
Weight values are stored to service computer room, import online real-time data base.Wherein, predetermined number can be according to actual need
It is configured.It should be noted that when the data extracted from second buffer queue can also include
Between information, the temporal information can be timestamp information.
In the embodiment of the present invention, the current letter can be extracted using wall scroll from second buffer queue
The mode of breath classification and corresponding class weight value carries out data extraction, can specifically use two-stage queue frame
Structure pattern, will extract from the current information classification according to behavioural characteristic data prediction and from the second buffer queue
Current information classification packet receive, merge incremental update to external storage, i.e., using process model ledger line journey
The mode that model is combined is write in many computer rooms.
Further, since after current information classification is obtained, can also be updated using the current information classification
The historical information classification of record.
Module 22 is transferred, the net for transferring the correspondence current information classification based on the current information classification
Page advertisement;Preferably, described to transfer module 22, specifically for being transferred from advertising database, correspondence is described to be worked as
The content-data of the advertisement of preceding information category, or advertisement storage address, or advertisement identification information.
Sending module 23, for the web advertisement to be sent into the browser, makes the browser by institute
Web advertisement is stated to be displayed on the current web page.
According to embodiments of the invention, the current information classification that browser sends, the current information class are received
The behavioural characteristic data produced when user accesses current web page are not analyzed in real time by the browser to obtain, and are based on
The current information classification transfers the web advertisement of the correspondence current information classification;By web advertisement hair
The browser is given, the browser is included on the current web page web advertisement.Pass through
Above-mentioned mechanism, according to the behavioural characteristic data of the newest generation of browser, in real time obtain current information classification to
Family current web page carries out real-time advertisement recommendation, and current information classification can preferably identify user's current behavior,
The advertisement more related to user's current behavior can be recommended, such that it is able to improve the clicking rate of the advertisement of recommendation.
Embodiment 3
With reference to Fig. 3, according to embodiments of the present invention 1 structure for transferring the device that advertisement is pushed is shown
Block diagram, can specifically include:
Receiver module 31, for receive browser transmission current information classification, the current information classification by
The browser analyzes user and accesses the behavioural characteristic data acquisition produced during current web page in real time;
Sort module 32, for the web advertisement to be classified.
Module 33 is transferred, the net for transferring the correspondence current information classification based on the current information classification
Page advertisement;
Preferably, it is described to transfer module 33, specifically for transferring the correspondence current letter from advertising database
Cease the identification information of the content-data of the advertisement of classification, or advertisement storage address, or advertisement.
Sending module 34, for the web advertisement to be sent into the browser, makes the browser by institute
Web advertisement is stated to be displayed on the current web page.
According to embodiments of the invention, the current information classification that browser sends, the current information class are received
The behavioural characteristic data produced when user accesses current web page are not analyzed in real time by the browser to obtain, and are based on
The current information classification transfers the web advertisement of the correspondence current information classification;By web advertisement hair
The browser is given, the browser is included on the current web page web advertisement.Pass through
Above-mentioned mechanism, according to the behavioural characteristic data of the newest generation of browser, in real time obtain current information classification to
Family current web page carries out real-time advertisement recommendation, and current information classification can preferably identify user's current behavior,
The advertisement more related to user's current behavior can be recommended, such that it is able to improve the clicking rate of the advertisement of recommendation.
Because described device embodiment essentially corresponds to the embodiment of the method shown in earlier figures, therefore the present embodiment
Description in not detailed part, may refer to the related description in previous embodiment, just do not repeat herein.
Algorithm and display be not intrinsic with any certain computer, virtual system or miscellaneous equipment provided herein
It is related.Various general-purpose systems can also be used together with based on teaching in this.As described above, structure
It is obvious to make the structure required by this kind of system.Additionally, the present invention is not also directed to any certain programmed
Language.It is understood that, it is possible to use various programming languages realize the content of invention described herein, and
The description done to language-specific above is to disclose preferred forms of the invention.
In specification mentioned herein, numerous specific details are set forth.It is to be appreciated, however, that this hair
Bright embodiment can be put into practice in the case of without these details.In some instances, not in detail
Known method, structure and technology are shown, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help understand one in each inventive aspect or
Multiple, in above to the description of exemplary embodiment of the invention, each feature of the invention is sometimes by one
Rise and be grouped into single embodiment, figure or descriptions thereof.However, should not be by the method for the disclosure
It is construed to reflect following intention:I.e. the present invention for required protection requirement ratio institute in each claim is clear and definite
The more features of feature of record.More precisely, as the following claims reflect, hair
Bright aspect is all features less than single embodiment disclosed above.Therefore, it then follows specific embodiment
Claims be thus expressly incorporated in the specific embodiment, wherein each claim conduct in itself
Separate embodiments of the invention.
Those skilled in the art be appreciated that the module in the equipment in embodiment can be carried out it is adaptive
Change to answering property and they are arranged in one or more equipment different from the embodiment.Can be reality
Apply module or unit or component in example and be combined into a module or unit or component, and in addition can be it
Be divided into multiple submodule or subelement or sub-component.Except in such feature and/or process or unit
It is at least some exclude each other outside, can using any combinations to this specification (including adjoint right will
Ask, make a summary and accompanying drawing) disclosed in all features and so disclosed any method or equipment it is all
Process or unit are combined.Unless expressly stated otherwise, this specification (including adjoint claim,
Summary and accompanying drawing) disclosed in each feature can or similar purpose identical, equivalent by offer alternative features
To replace.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other
Some included features are rather than further feature, but the combination meaning of the feature of different embodiments in embodiment
Taste and is within the scope of the present invention and is formed different embodiments.For example, in following claim
In book, the one of any of embodiment required for protection mode can use in any combination.
All parts embodiment of the invention can realize with hardware, or with one or more processor
The software module of upper operation is realized, or is realized with combinations thereof.It will be understood by those of skill in the art that
Can realize being implemented according to the present invention using microprocessor or digital signal processor (DSP) in practice
The some or all functions of some or all parts in the recommendation apparatus of the web advertisement of example.The present invention
It is also implemented as some or all equipment or device journey for performing method as described herein
Sequence (for example, computer program and computer program product).It is such to realize that program of the invention be stored
On a computer-readable medium, or can have one or more signal form.Such signal can
Obtained with being downloaded from internet website, or provided on carrier signal, or carried in any other form
For.
It should be noted that above-described embodiment the present invention will be described rather than limiting the invention, and
And those skilled in the art can design replacement implementation without departing from the scope of the appended claims
Example.In the claims, any reference symbol being located between bracket should not be configured to claim
Limitation.Word "comprising" does not exclude the presence of element or step not listed in the claims.Before element
Word "a" or "an" does not exclude the presence of element as multiple.The present invention can by means of include it is some not
Realized with the hardware of element and by means of properly programmed computer.If listing the unit of equipment for drying
In, several in these devices can be embodied by same hardware branch.Word first,
Two and third use do not indicate that any order.These words can be construed to title.
The invention provides A1, a kind of transfer the method that advertisement is pushed, it is characterised in that methods described
Including:
The current information classification that browser sends is received, the current information classification is divided in real time by the browser
Analysis user accesses the behavioural characteristic data produced during current web page and obtains;
The web advertisement of the correspondence current information classification is transferred based on the current information classification;
The web advertisement is sent to the browser, the browser is included the web advertisement
On the current web page.
A2, the method as described in A1, it is characterised in that the behavioural characteristic data pass through the browser
The record for transferring access log in real time is obtained.
A3, the method as described in A1, it is characterised in that the behavioural characteristic data buffer storage is in the first caching
In queue, extracted from first buffer queue by the browser.
A4, the method as described in A1, it is characterised in that the behavioural characteristic data include search keyword;
The current information classification is obtained by following steps:
The browser analyzes the search keyword and obtains at least one information category and obtain correspondence in real time
Class weight value, then extract the information category of predetermined number as the current information classification.
A5, the method as described in A4, it is characterised in that the current information classification is obtained by following steps
:
At least one information category and corresponding class weight value are cached to second and delayed by the browser
In depositing queue;The information category of predetermined number is extracted from second buffer queue again as described current
Information category, and extract corresponding class weight value.
A6, the method as described in A5, it is characterised in that the behavioural characteristic data are divided described
Analysis, obtains after current information classification, specifically also includes:
The browser utilizes the historical information classification of the current information classification more new record.
A7, the method as described in A1, it is characterised in that transferred based on the current information classification described
Before the web advertisement of the correspondence current information classification, including:
The web advertisement is classified.
A8, the method as described in A1, it is characterised in that it is described transferred based on the current information classification it is right
The web advertisement of the current information classification is answered, specially:
The content-data of the advertisement of the correspondence current information classification, or advertisement are transferred from advertising database
Storage address, or advertisement identification information.
Present invention also offers B9, a kind of transfer the device that advertisement is pushed, it is characterised in that including:
Receiver module, the current information classification for receiving browser transmission, the current information classification is by institute
State browser and analyze the behavioural characteristic data acquisition produced during user's access current web page in real time;
Module is transferred, the webpage for transferring the correspondence current information classification based on the current information classification
Advertisement;
Sending module, for the web advertisement to be sent into the browser, makes the browser described
Web advertisement is displayed on the current web page.
B10, the device as described in B9, it is characterised in that the behavioural characteristic data pass through the browser
The record for transferring access log in real time is obtained.
B11, the device as described in B9, it is characterised in that the behavioural characteristic data buffer storage is in the first caching
In queue, extracted from first buffer queue by the browser.
B12, the device as described in B9, it is characterised in that the behavioural characteristic data include search keyword;
The current information classification is obtained by following steps:
The browser analyzes the search keyword and obtains at least one information category and obtain correspondence in real time
Class weight value, then extract the information category of predetermined number as the current information classification.
B13, the device as described in B12, it is characterised in that the current information classification is obtained by following steps
:
At least one information category and corresponding class weight value are cached to second and delayed by the browser
In depositing queue;The information category of predetermined number is extracted from second buffer queue again as described current
Information category, and extract corresponding class weight value.
B14, the device as described in B13, it is characterised in that the behavioural characteristic data are divided described
Analysis, obtains after current information classification, specifically also includes:
The browser utilizes the historical information classification of the current information classification more new record.
B15, the device as described in B9, it is characterised in that it is described transfer module before, including:
Sort module, for the web advertisement to be classified.
B16, the device as described in B9, it is characterised in that described to transfer module, specifically for from advertisement number
According to the content-data of the advertisement that the correspondence current information classification is transferred in storehouse, or advertisement storage address, or
The identification information of person's advertisement.
Claims (10)
1. it is a kind of to transfer the method that advertisement is pushed, it is characterised in that methods described includes:
The current information classification that browser sends is received, the current information classification is divided in real time by the browser
Analysis user accesses the behavioural characteristic data produced during current web page and obtains;
The web advertisement of the correspondence current information classification is transferred based on the current information classification;
The web advertisement is sent to the browser, the browser is included the web advertisement
On the current web page.
2. the method for claim 1, it is characterised in that the behavioural characteristic data are by described clear
The record that device of looking at transfers access log in real time is obtained.
3. the method for claim 1, it is characterised in that the behavioural characteristic data buffer storage is first
In buffer queue, extracted from first buffer queue by the browser.
4. the method for claim 1, it is characterised in that the behavioural characteristic data include that search is closed
Keyword;
The current information classification is obtained by following steps:
The browser analyzes the search keyword and obtains at least one information category and obtain correspondence in real time
Class weight value, then extract the information category of predetermined number as the current information classification.
5. method as claimed in claim 4, it is characterised in that the current information classification is by following step
It is rapid to obtain:
At least one information category and corresponding class weight value are cached to second and delayed by the browser
In depositing queue;The information category of predetermined number is extracted from second buffer queue again as described current
Information category, and extract corresponding class weight value.
6. method as claimed in claim 5, it is characterised in that the behavioural characteristic data are entered described
Row analysis, obtains after current information classification, specifically also includes:
The browser utilizes the historical information classification of the current information classification more new record.
7. the method for claim 1, it is characterised in that described based on the current information classification
Before transferring the web advertisement of the correspondence current information classification, including:
The web advertisement is classified.
8. the method for claim 1, it is characterised in that described to be adjusted based on the current information classification
The web advertisement of the correspondence current information classification is taken, specially:
The content-data of the advertisement of the correspondence current information classification, or advertisement are transferred from advertising database
Storage address, or advertisement identification information.
9. it is a kind of to transfer the device that advertisement is pushed, it is characterised in that including:
Receiver module, the current information classification for receiving browser transmission, the current information classification is by institute
State browser and analyze the behavioural characteristic data acquisition produced during user's access current web page in real time;
Module is transferred, the webpage for transferring the correspondence current information classification based on the current information classification
Advertisement;
Sending module, for the web advertisement to be sent into the browser, makes the browser described
Web advertisement is displayed on the current web page.
10. device as claimed in claim 9, it is characterised in that the behavioural characteristic data are by described
The record that browser transfers access log in real time is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510982576.7A CN106910082A (en) | 2015-12-23 | 2015-12-23 | It is a kind of to transfer the method and apparatus that advertisement is pushed |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510982576.7A CN106910082A (en) | 2015-12-23 | 2015-12-23 | It is a kind of to transfer the method and apparatus that advertisement is pushed |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106910082A true CN106910082A (en) | 2017-06-30 |
Family
ID=59206227
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510982576.7A Pending CN106910082A (en) | 2015-12-23 | 2015-12-23 | It is a kind of to transfer the method and apparatus that advertisement is pushed |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106910082A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108737524A (en) * | 2018-05-10 | 2018-11-02 | 佛山欧神诺云商科技有限公司 | A kind of enterprise information push method |
CN109886716A (en) * | 2017-12-06 | 2019-06-14 | 北京奇虎科技有限公司 | A kind of advertisement pushing method and system |
CN110020360A (en) * | 2017-11-09 | 2019-07-16 | 北京京东尚科信息技术有限公司 | The method that user behavior characteristics are extracted, system and server |
CN112231590A (en) * | 2020-10-15 | 2021-01-15 | 中国联合网络通信集团有限公司 | Content recommendation method, system, computer device and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101216825A (en) * | 2007-12-29 | 2008-07-09 | 朱廷劭 | Indexing key words extraction/ prediction method, on-line advertisement recommendation method and device |
CN103440259A (en) * | 2013-07-31 | 2013-12-11 | 亿赞普(北京)科技有限公司 | Network advertisement push method and device |
-
2015
- 2015-12-23 CN CN201510982576.7A patent/CN106910082A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101216825A (en) * | 2007-12-29 | 2008-07-09 | 朱廷劭 | Indexing key words extraction/ prediction method, on-line advertisement recommendation method and device |
CN103440259A (en) * | 2013-07-31 | 2013-12-11 | 亿赞普(北京)科技有限公司 | Network advertisement push method and device |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020360A (en) * | 2017-11-09 | 2019-07-16 | 北京京东尚科信息技术有限公司 | The method that user behavior characteristics are extracted, system and server |
CN109886716A (en) * | 2017-12-06 | 2019-06-14 | 北京奇虎科技有限公司 | A kind of advertisement pushing method and system |
CN108737524A (en) * | 2018-05-10 | 2018-11-02 | 佛山欧神诺云商科技有限公司 | A kind of enterprise information push method |
CN108737524B (en) * | 2018-05-10 | 2020-11-24 | 佛山欧神诺云商科技有限公司 | Enterprise information pushing method |
CN112231590A (en) * | 2020-10-15 | 2021-01-15 | 中国联合网络通信集团有限公司 | Content recommendation method, system, computer device and storage medium |
CN112231590B (en) * | 2020-10-15 | 2023-06-27 | 中国联合网络通信集团有限公司 | Content recommendation method, system, computer device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11580104B2 (en) | Method, apparatus, device, and storage medium for intention recommendation | |
US12001439B2 (en) | Information service for facts extracted from differing sources on a wide area network | |
CN106447371A (en) | Webpage advertisement recommendation method and device | |
JP6494777B2 (en) | Method and device for selecting data content to be pushed to a terminal | |
CN108874812B (en) | Data processing method, server and computer storage medium | |
CN101808102B (en) | Operating record tracing system and method based on cloud computing | |
CN102354315A (en) | Generation method of site navigation page and device thereof | |
CN110300084B (en) | IP address-based portrait method and apparatus, electronic device, and readable medium | |
CN102831114B (en) | Realize method and the device of internet user access Statistic Analysis | |
CN102667761A (en) | Scalable cluster database | |
CN105183873A (en) | Malicious clicking behavior detection method and device | |
US20230153839A1 (en) | Selecting digital media assets based on transitions across categories | |
CN105930363A (en) | HTML5 webpage based user behavior analysis method and device | |
US8844031B1 (en) | Detecting spam events in event management systems | |
WO2015161226A1 (en) | Systems and methods for generating network intelligence through real-time analytics | |
CN106709033A (en) | Business multimedia data processing method and device | |
EP2959410A1 (en) | Content virality determination and visualization | |
CN106910082A (en) | It is a kind of to transfer the method and apparatus that advertisement is pushed | |
CN108229994A (en) | A kind of information-pushing method and device | |
Assenmacher et al. | A two-phase framework for detecting manipulation campaigns in social media | |
US8180752B2 (en) | Apparatus and methods for managing a social media universe | |
CN110175264A (en) | Construction method, server and the computer readable storage medium of video user portrait | |
CN106528851A (en) | Intelligent recommendation method and device | |
CN109688205A (en) | The hold-up interception method and device of web page resources | |
US20230017678A1 (en) | Dual-optimization of targeted digital assets under volume and position constraints |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170630 |