CN108734498A - A kind of advertisement sending method and device - Google Patents
A kind of advertisement sending method and device Download PDFInfo
- Publication number
- CN108734498A CN108734498A CN201710272047.7A CN201710272047A CN108734498A CN 108734498 A CN108734498 A CN 108734498A CN 201710272047 A CN201710272047 A CN 201710272047A CN 108734498 A CN108734498 A CN 108734498A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- user
- data
- tool
- user tag
- 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 OR CALCULATING; 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
- G06Q30/0257—User requested
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (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)
- Information Transfer Between Computers (AREA)
Abstract
This application discloses a kind of advertisement sending method and devices.This method includes：It receives the advertisement that tool-class application APP is sent and pulls request；When the user tag of the tool-class APP is not present in pre-stored user tag library, according to the installation list applist data of the tool-class APP, the user tag is determined；According to the user tag, determine and the matched advertisement of the user tag；Give the advertisement pushing to the tool-class APP.According to the technical solution of the embodiment of the present application, user tag is determined by the applist data of tool-class APP, so as to which tool-class APP will be given with the matched advertisement pushing of user tag, and then realizes and the accurate advertisement of tool-class APP is pushed.
Description
Technical field
The present disclosure relates generally to field of computer technology, and in particular to mobile Internet field more particularly to a kind of advertisement
Method for pushing and device.
Background technology
With universal and network speed the promotion of mobile intelligent terminal (mobile phone, tablet computer etc.), moving advertising is as a kind of
Emerging advertisement mode also rapidly develops therewith.
Currently, the APP that many APP (Application, application program) application markets download to can be pushed extensively to user
It accuses, common method is to carry out the data mining of user tag by collecting the daily behavior data of user, and arrive to excavate
User tag be according to carry out advertisement pushing.There are following defects in this way：
The service such as social APP, content APP and search APP class APP can collect the daily behavior data of user, have digging
The ability of user tag is dug, but for tool-class APP, the logon data that only small part user leaves can be used as user to mark
Label can not collect the daily behavior data of user, therefore can not carry out the data mining of user tag by common method,
Do not have the ability for excavating user tag, therefore cannot achieve the accurate advertisement push to tool-class APP.
Invention content
In view of drawbacks described above in the prior art or deficiency, it is intended to provide a kind of can realize to the accurate of tool-class APP
The scheme of advertisement pushing.
In a first aspect, the embodiment of the present application provides a kind of advertisement sending method, including：
It receives the advertisement that tool-class application APP is sent and pulls request；
When the user tag of the tool-class APP is not present in pre-stored user tag library, according to the tool
The installation list applist data of class APP, determine the user tag；
According to the user tag, determine and the matched advertisement of the user tag；
Give the advertisement pushing to the tool-class APP.
Second aspect, the embodiment of the present application also provides a kind of advertisement pushing devices, including：
Receiving unit, the advertisement that class application APP used to receive tools is sent pull request；
Tag determination unit, for when there is no the users of the tool-class APP to mark in pre-stored user tag library
When label, according to the installation list applist data of the tool-class APP, the user tag is determined；
Advertisement determination unit, for according to the user tag, determining and the matched advertisement of the user tag；
Push unit, for giving the advertisement pushing to the tool-class APP.
The third aspect the embodiment of the present application also provides a kind of computer equipment, including one or more processors and is deposited
Reservoir；Wherein：
The memory includes the instruction that can be executed by the processor so that the above-mentioned advertisement of processor execution pushes away
Delivery method.
Advertisement pushing scheme provided by the embodiments of the present application determines that user marks by the applist data of tool-class APP
Label so as to give tool-class APP with the matched advertisement pushing of user tag, and then are realized to the accurate wide of tool-class APP
Accuse push.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is shown in which that the exemplary system architecture of the embodiment of the present application can be applied；
Fig. 2 shows the exemplary process diagrams according to the advertisement sending method of the embodiment of the present application；
Fig. 3 shows the exemplary block diagram of the advertisement pushing device according to another embodiment of the application；And
Fig. 4 shows the structural schematic diagram of the computer system of the server suitable for being used for realizing the embodiment of the present application.
Specific implementation mode
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, is illustrated only in attached drawing and invent relevant part.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Referring to FIG. 1, it illustrates the exemplary system architectures 100 that can apply the embodiment of the present application.
As shown in Figure 1, system architecture 100 may include terminal device 101,102, network 103 and server 104,105,
106 and 107.Network 103 between terminal device 101,102 and server 104,105,106,107 providing communication link
Medium.Network 103 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
User 110 can be interacted by network 103 with server 104,105,106,107 with using terminal equipment 101,102,
To access various services, such as browsing webpage, downloading data etc..Various clients can be installed on terminal device 101,102
Using such as the application of uniform resource position mark URL cloud service can be accessed, including but not limited to browser, security application etc..
Terminal device 101,102 can be various electronic equipments, including but not limited to PC, smart mobile phone, intelligence
TV, tablet computer, personal digital assistant, E-book reader etc..
Server 104,105,106,107 can be to provide the server of various services.Server can be in response to user
Service request and service is provided.It is appreciated that a server can provide one or more services, same service also may be used
To be provided by multiple servers.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
As mentioned in the background, the prior art generally carries out user by collecting the daily behavior data of user
The data mining of label, and be to carry out advertisement pushing according to APP with the user tag excavated.However, for tool-class
APP, in addition to the logon data that small part user leaves can be used as user tag, remaining major part user to be only capable of excavating it
App installs list (applist), and the data mining of user tag can not be carried out by common method, does not have excavation user
The ability of label, therefore cannot achieve the accurate advertisement push to tool-class APP.
In view of the drawbacks described above of the prior art, the embodiment of the present application provides a kind of advertisement pushing scheme, passes through tool-class
The applist data of APP determine user tag, so as to which tool-class APP will be given with the matched advertisement pushing of user tag, into
And it realizes and the accurate advertisement of tool-class APP is pushed.
The method for describing the embodiment of the present application below in conjunction with flow chart.
With reference to figure 2, it illustrates the exemplary process diagrams according to the advertisement sending method of the application one embodiment.Fig. 2
Shown in method can be in Fig. 1 server end execute.
As shown in Fig. 2, this method comprises the following steps：
Step 210, it receives the advertisement that tool-class APP is sent and pulls request.
In the embodiment of the present application, advertisement pull request transmission opportunity can be, but not limited to for：
1, user is when using tool-class APP, and when tool-class APP completes certain specified function, tool-class APP is to server
End sends advertisement and pulls request, by taking certain mobile phone safe assistant APP as an example, when mobile phone safe assistant APP completion mobile phone rubbish is clear
After reason, just advertisement is sent to server end and pull request；
2, tool-class APP at runtime, advertisement is sent according to the pre-set sending cycle of its developer to server end
Pull request.
Step 220, when the user tag of tool-class APP is not present in pre-stored user tag library, according to tool
The applist data of class APP, determine user tag.
In the embodiment of the present application, step 220 can be, but not limited to realize as follows：
First, the applist data of tool-class APP are obtained；
Wherein, the applist data of tool-class APP can obtain tool-class APP progress data minings.Still with certain
For mobile phone safe assistant, the applist data that data mining obtains are carried out to it and can be, but not limited to include cleaning rubbish number
According to.
Then, according to the label model for distinguishing user tag being previously obtained, applist data are learnt,
Obtain the corresponding user tag of applist data.
Wherein, label model can obtain as follows：
First, applist sample datas and user attribute data corresponding with applist sample datas are obtained；
User attribute data may include one in natural quality data, social property data and geographical location attribute data
Item is multinomial, wherein：
Natural quality data may include：Gender, age and constellation etc.；
Social property data may include：Marital status, occupation, interest, education, assets, job hunting and health status etc.；
Geographical location attribute data may include：Continent, country, province, city and region etc..
Then, using applist sample datas as input feature vector, user attribute data is as model label, into row label
Model training generates label model.
In the embodiment of the present application when carrying out label model training, can with but be not limited to calculate using following machine learning
Method：
LR (Logistic Regression, logistic regression), GBDT (Gradient Boosting Decision
Tree, regression tree), FM (Factorization Machines, Factorization machine), GP (Gaussian Process, Gauss mistake
Journey), DNN (Deep Neural Network, deep neural network), depth autoencoder network, Softmax etc..
By in natural quality data gender and for the age,
Gender divides men and women, frequently as discrete data, LR, FM scheduling algorithm can be used as the study label of gender label；
Age is numeric type data, commonly uses fixed interval by its discretization, depth own coding may be selected, DNN scheduling algorithms add
Learning models of the upper softmax as age label.
It should be noted that after determining user tag, which can be stored in user tag library, with
When the continuous advertisement for receiving tool-class APP transmissions again pulls request after an action of the bowels, can be extracted directly from user tag library should
User tag.
Further, since the interest of user may change, for example tool-class APP is when clearing up rubbish, in the past
Clear up rubbish it is most be game class APP, crossed a period of time cleaning rubbish it is most become video class APP, this just illustrates
The interest of user is shifted to a certain extent, therefore user tag can also change therewith.And hence it is also possible to according to
The update cycle of setting carries out more the user tag being stored in user tag library using the applist data of tool-class APP
Newly.
In addition, in the embodiment of the present application, in addition to applist data can be utilized to determine user tag, this can also be obtained
The user data of user terminal where tool-class APP, and user is determined according to above-mentioned applist data and the user data jointly
Label.
Wherein, user data can be, but not limited to include：
The user preference data excavated based on the tool-class APP initial data provided, from its in addition to tool-class APP
The user social contact data (such as in some page residence time, often access website etc.) and user behavior number that its APP is obtained
According to one or more in (for example advertisement pulls behavior and click behavior etc.).
Step 230, it according to determining user tag, determines and the matched advertisement of user tag.
In the embodiment of the present application, it can be, but not limited to realize as follows：
First way：
The similarity between the user tag of tool-class APP and the advertisement tag of pre-set each advertisement is calculated separately,
And the advertisement that similarity is not less than to default similarity is determined as and the matched advertisement of user tag.
Wherein, the numberical range of similarity is 0 to 1, and when similarity is 0, user tag and advertisement tag are entirely different,
When similarity is 1, user tag is identical with advertisement tag.For example, default similarity is set as 1, user tag has
Male, teenage, student, game, the U.S., advertiser is that some advertisement of oneself is also provided with identical advertisement tag, then using
The similarity of family label and the advertisement tag is 1, then the advertisement is and the matched advertisement of user tag.
The second way：
User tag and the input of the characteristic of advertisement of pre-set each advertisement is matched wide with user tag for determining
In the machine learning model of announcement, obtain and the matched advertisement of user tag.
Step 240, determining advertisement pushing is given to tool-class APP.
In the embodiment of the present application in addition to by the advertisement pushing determined to tool-class APP other than, some explorations can also be carried out
Property advertisement issue, changed with exploring and meeting the uncertain of user preferences.For example, according to EE (Exploitation&
Exploration, exploration and exploration) strategy, from other advertisements in addition to the matched advertisement of user tag, selection
Tool-class APP is given at least one advertisement pushing；Wherein, the classification of the advertisement of selection and the classification with the matched advertisement of user tag
It is different.
It should be noted that although describing the operation of the method for the present invention with particular order in the accompanying drawings, this is not required that
Or imply and must execute these operations according to the particular order, it could the realization phase or have to carry out operation shown in whole
The result of prestige.On the contrary, the step of describing in flow chart, which can change, executes sequence.Additionally or alternatively, it is convenient to omit certain
Multiple steps are merged into a step and executed, and/or a step is decomposed into execution of multiple steps by step.
With further reference to Fig. 3, it illustrates the example arrangements according to the advertisement pushing device of the application one embodiment
Block diagram.The device 300 may include：
Receiving unit 310, the advertisement that class application APP used to receive tools is sent pull request；
First tag determination unit 320, for when there is no the tool-class APP's in pre-stored user tag library
When user tag, according to the installation list applist data of the tool-class APP, the user tag is determined；
Advertisement determination unit 330, for according to the user tag, determining and the matched advertisement of the user tag；
First push unit 340, for giving the advertisement pushing to the tool-class APP.
Wherein, first tag determination unit 320, including：
First acquisition module 3210, the applist data for obtaining the tool-class APP；
First study module 3220, for the label model for distinguishing user tag that basis is previously obtained, to described
Applist data are learnt, and the corresponding user tag of the applist data is obtained.
Optionally, described device further includes：
Label model generation unit 350, for obtain applist sample datas and with the applist sample datas pair
The user attribute data answered；Using the applist sample datas as input feature vector, the user attribute data is as model mark
Label carry out label model training, generate the label model.
Wherein, the user attribute data includes：
It is one or more in natural quality data, social property data and geographical location attribute data.
Wherein, the advertisement determination unit 330, is used for：
It calculates separately similar between the user tag of the tool-class APP and the advertisement tag of pre-set each advertisement
Degree；The advertisement that the similarity is not less than to default similarity is determined as and the matched advertisement of the user tag；Or
By the user tag and the input of the characteristic of advertisement of pre-set each advertisement for determining and the user tag
In the machine learning model of matched advertisement, obtain and the matched advertisement of the user tag.
Optionally, the tag determination unit 320 may include：
Second acquisition module 3230, the applist data for obtaining the tool-class APP and the tool-class APP institutes
In the user data of user terminal；The user data includes：It is excavated based on the tool-class APP initial data provided
User preference data, from the user social contact data and user behavior data that other APP in addition to the tool-class APP are obtained
It is one or more；
Second study module 3240, for the label model for distinguishing user tag that basis is previously obtained, to described
Applist data and the user data are learnt, and the user tag is obtained.
Optionally, described device further includes：
Second push unit 360, for from other advertisements in addition to the matched advertisement of the user tag, choosing
The tool-class APP is given at least one advertisement pushing；Wherein, the classification of the advertisement of selection and matched wide with the user tag
The classification of announcement is different.
It should be appreciated that the systems or unit described in device 300 and each step in the method with reference to the description of figure 2
It is corresponding.It is equally applicable to device 300 and unit wherein included above with respect to the operation and feature of method description as a result,
This is repeated no more.
Below with reference to Fig. 4, it illustrates the computer systems 400 suitable for the server for realizing the embodiment of the present application
Structural schematic diagram.
As shown in figure 4, computer system 400 includes central processing unit (CPU) 401, it can be read-only according to being stored in
Program in memory (ROM) 402 or be loaded into the program in random access storage device (RAM) 403 from storage section 408 and
Execute various actions appropriate and processing.In RAM 403, also it is stored with system 400 and operates required various programs and data.
CPU 401, ROM 402 and RAM 403 are connected with each other by bus 404.Input/output (I/O) interface 405 is also connected to always
Line 404.
It is connected to I/O interfaces 405 with lower component：Importation 406 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 407 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.；Storage section 408 including hard disk etc.；
And the communications portion 409 of the network interface card including LAN card, modem etc..Communications portion 409 via such as because
The network of spy's net executes communication process.Driver 410 is also according to needing to be connected to I/O interfaces 405.Detachable media 411, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 410, as needed in order to be read from thereon
Computer program be mounted into storage section 408 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer software above with reference to the process of Fig. 2 descriptions
Program.For example, embodiment of the disclosure includes a kind of computer program product comprising be tangibly embodied in machine readable media
On computer program, the computer program includes the program code of method for executing Fig. 2.In such embodiment
In, which can be downloaded and installed by communications portion 409 from network, and/or from 411 quilt of detachable media
Installation.
Flow chart in attached drawing and block diagram, it is illustrated that according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it wants
It is noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, Ke Yiyong
The dedicated hardware based system of defined functions or operations is executed to realize, or can be referred to specialized hardware and computer
The combination of order is realized.
Being described in unit or module involved in the embodiment of the present application can be realized by way of software, can also
It is realized by way of hardware.Described unit or module can also be arranged in the processor.These units or module
Title does not constitute the restriction to the unit or module itself under certain conditions.
As on the other hand, present invention also provides a kind of computer readable storage medium, the computer-readable storage mediums
Matter can be computer readable storage medium included in device described in above-described embodiment；Can also be individualism, not
The computer readable storage medium being fitted into equipment.There are one computer-readable recording medium storages or more than one journey
Sequence, described program are used for executing the formula input method for being described in the application by one or more than one processor.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from the inventive concept, it is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (15)
1. a kind of advertisement sending method, which is characterized in that the method includes：
It receives the advertisement that tool-class application APP is sent and pulls request；
When the user tag of the tool-class APP is not present in pre-stored user tag library, according to the tool-class APP
Installation list applist data, determine the user tag；
According to the user tag, determine and the matched advertisement of the user tag；
Give the advertisement pushing to the tool-class APP.
2. according to the method described in claim 1, it is characterized in that, the installation list according to the tool-class APP
Applist data determine the user tag, including：
Obtain the applist data of the tool-class APP；
According to the label model for distinguishing user tag being previously obtained, the applist data are learnt, institute is obtained
State user tag.
3. according to the method described in claim 2, it is characterized in that, the label model obtains as follows：
Obtain applist sample datas and user attribute data corresponding with the applist sample datas；
Using the applist sample datas as input feature vector, the user attribute data is as model label, into row label mould
Type training generates the label model.
4. according to the method described in claim 3, it is characterized in that, the user attribute data includes：
It is one or more in natural quality data, social property data and geographical location attribute data.
5. according to the method described in claim 1, it is characterized in that, described according to the user tag, the determining and user
The advertisement of tag match, including：
Calculate separately the similarity between the user tag of the tool-class APP and the advertisement tag of pre-set each advertisement；
The advertisement that the similarity is not less than to default similarity is determined as and the matched advertisement of the user tag；Or
The user tag and the input of the characteristic of advertisement of pre-set each advertisement are matched for determining with the user tag
Advertisement machine learning model in, obtain and the matched advertisement of the user tag.
6. according to the method described in claim 1, it is characterized in that, the installation list according to the tool-class APP
Applist data determine the user tag, including：
Obtain the user data of the applist data and the places tool-class APP user terminal of the tool-class APP；It is described
User data includes：Based on the user preference data that the tool-class APP initial data provided is excavated, from except the tool
It is one or more in user social contact data and user behavior data that other APP except class APP are obtained；
According to the label model for distinguishing user tag being previously obtained, to the applist data and the user data
Learnt, obtains the user tag.
7. according to the method described in claim 1, being pulled it is characterized in that, receiving the advertisement that tool-class application APP is sent
After request, the method further includes：
According to exploration and exploration EE strategies, from other advertisements in addition to the matched advertisement of the user tag, choosing
Take at least one advertisement pushing to the tool-class APP；Wherein, the classification of the advertisement of selection and matched with the user tag
The classification of advertisement is different.
8. a kind of advertisement pushing device, which is characterized in that described device includes：
Receiving unit, the advertisement that class application APP used to receive tools is sent pull request；
Tag determination unit is used for when the user tag of the tool-class APP is not present in pre-stored user tag library,
According to the installation list applist data of the tool-class APP, the user tag is determined；
Advertisement determination unit, for according to the user tag, determining and the matched advertisement of the user tag；
First push unit, for giving the advertisement pushing to the tool-class APP.
9. device according to claim 8, which is characterized in that the tag determination unit, including：
First acquisition module, the applist data for obtaining the tool-class APP；
First study module, for the label model for distinguishing user tag that basis is previously obtained, to the applist numbers
According to being learnt, the user tag is obtained.
10. device according to claim 9, which is characterized in that described device further includes：
Label model generation unit, for obtaining applist sample datas and user corresponding with the applist sample datas
Attribute data；Using the applist sample datas as input feature vector, the user attribute data is carried out as model label
Label model is trained, and the label model is generated.
11. device according to claim 10, which is characterized in that the user attribute data includes：
It is one or more in natural quality data, social property data and geographical location attribute data.
12. device according to claim 8, which is characterized in that the advertisement determination unit is used for：
Calculate separately the similarity between the user tag of the tool-class APP and the advertisement tag of pre-set each advertisement；
The advertisement that the similarity is not less than to default similarity is determined as and the matched advertisement of the user tag；Or
The user tag and the input of the characteristic of advertisement of pre-set each advertisement are matched for determining with the user tag
Advertisement machine learning model in, obtain and the matched advertisement of the user tag.
13. device according to claim 8, which is characterized in that the tag determination unit, including：
Second acquisition module, user where the applist data and the tool-class APP for obtaining the tool-class APP are whole
The user data at end；The user data includes：The user preferences excavated based on the tool-class APP initial data provided
Data, from addition to the tool-class APP other APP obtain user social contact data and user behavior data in one or
It is multinomial；
Second study module, for the label model for distinguishing user tag that basis is previously obtained, to the applist numbers
Learnt according to the user data, obtains the user tag.
14. device according to claim 8, which is characterized in that described device further includes：
Second push unit, for tactful according to EE, from other advertisements in addition to the matched advertisement of the user tag,
At least one advertisement pushing is chosen to the tool-class APP；Wherein, it the classification of the advertisement of selection and is matched with the user tag
Advertisement classification it is different.
15. a kind of computer equipment, including one or more processors and memory；It is characterized in that：
The memory includes can be by instruction that the processor executes so that the processor perform claim requires 1 to 7
Method described in meaning one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710272047.7A CN108734498B (en) | 2017-04-24 | 2017-04-24 | Advertisement pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710272047.7A CN108734498B (en) | 2017-04-24 | 2017-04-24 | Advertisement pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108734498A true CN108734498A (en) | 2018-11-02 |
| CN108734498B CN108734498B (en) | 2021-05-28 |
Family
ID=63934374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710272047.7A Active CN108734498B (en) | 2017-04-24 | 2017-04-24 | Advertisement pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108734498B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110910178A (en) * | 2019-11-28 | 2020-03-24 | 中国建设银行股份有限公司 | Method and device for generating advertisement |
| CN111581366A (en) * | 2020-05-09 | 2020-08-25 | 北京百度网讯科技有限公司 | User intent determination method, apparatus, electronic device, and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103745382A (en) * | 2013-12-27 | 2014-04-23 | 中国联合网络通信有限公司广东省分公司 | Method, device and system of pushing an APP application group of advertising of smart city |
| CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
| CN104111975A (en) * | 2014-06-20 | 2014-10-22 | 深信服网络科技（深圳）有限公司 | Information pushing method and device |
| CN104966215A (en) * | 2015-07-01 | 2015-10-07 | 小米科技有限责任公司 | Advertisement information push method and apparatus |
| CN105677719A (en) * | 2015-12-29 | 2016-06-15 | 小米科技有限责任公司 | Application management method and apparatus |
| CN105956872A (en) * | 2016-04-18 | 2016-09-21 | 乐视控股（北京）有限公司 | Accurate advertisement inputting method and accurate advertisement inputting device based on industry of population |
-
2017
- 2017-04-24 CN CN201710272047.7A patent/CN108734498B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090888A (en) * | 2013-12-10 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for analyzing user behavior data |
| US20160379268A1 (en) * | 2013-12-10 | 2016-12-29 | Tencent Technology (Shenzhen) Company Limited | User behavior data analysis method and device |
| CN103745382A (en) * | 2013-12-27 | 2014-04-23 | 中国联合网络通信有限公司广东省分公司 | Method, device and system of pushing an APP application group of advertising of smart city |
| CN104111975A (en) * | 2014-06-20 | 2014-10-22 | 深信服网络科技（深圳）有限公司 | Information pushing method and device |
| CN104966215A (en) * | 2015-07-01 | 2015-10-07 | 小米科技有限责任公司 | Advertisement information push method and apparatus |
| CN105677719A (en) * | 2015-12-29 | 2016-06-15 | 小米科技有限责任公司 | Application management method and apparatus |
| CN105956872A (en) * | 2016-04-18 | 2016-09-21 | 乐视控股（北京）有限公司 | Accurate advertisement inputting method and accurate advertisement inputting device based on industry of population |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110910178A (en) * | 2019-11-28 | 2020-03-24 | 中国建设银行股份有限公司 | Method and device for generating advertisement |
| CN111581366A (en) * | 2020-05-09 | 2020-08-25 | 北京百度网讯科技有限公司 | User intent determination method, apparatus, electronic device, and readable storage medium |
| CN111581366B (en) * | 2020-05-09 | 2023-08-29 | 北京百度网讯科技有限公司 | User intention determining method, device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108734498B (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10846617B2 (en) | Context-aware recommendation system for analysts | |
| CN105320766B (en) | Information-pushing method and device | |
| CN109815416A (en) | Method for pushing, the device of related information, electronic equipment and storage medium | |
| CN109359247A (en) | Content delivery method and storage medium, computer equipment | |
| CN110765352B (en) | User interest identification method and device | |
| CN109388548A (en) | Method and apparatus for generating information | |
| CN109495552A (en) | Method and apparatus for updating clicking rate prediction model | |
| CN105160545A (en) | Delivered information pattern determination method and device | |
| CN112650942A (en) | Product recommendation method, device, computer system and computer-readable storage medium | |
| CN109101309A (en) | For updating user interface method and device | |
| CN113706202A (en) | Recall strategy generating method based on low-steady-state user identification and early warning | |
| CN114117227A (en) | Operation maintenance method, system, electronic equipment and storage medium | |
| CN112749323B (en) | A method and device for constructing user portrait | |
| US20170371900A1 (en) | Generic card feature extraction based on card rendering as an image | |
| CN113449175B (en) | Hot spot data recommendation method and device | |
| Kavikondala et al. | Automated retraining of machine learning models | |
| CN113743636B (en) | Target operation prediction method and device, electronic equipment and storage medium | |
| CN108734498A (en) | A kind of advertisement sending method and device | |
| CN110399564B (en) | Account classification method and device, storage medium and electronic device | |
| CN116861038A (en) | Multi-platform-based consumer data integration system and integration method thereof | |
| CN112269942A (en) | Method, device and system for recommending object and electronic equipment | |
| CN113761878B (en) | Method and apparatus for outputting information | |
| CN112446738A (en) | Advertisement data processing method, device, medium and electronic equipment | |
| CN112395109A (en) | Clipboard content processing method and device | |
| CN118210975A (en) | Object list recommendation method and device, electronic equipment and readable storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181221 Address after: Room 708, 7th floor, No. 10 Building, 30 Shixing Street, Shijingshan District, Beijing Applicant after: Beijing Xiaoxiong Bowang Technology Co., Ltd. Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |