CN108734498B

CN108734498B - Advertisement pushing method and device

Info

Publication number: CN108734498B
Application number: CN201710272047.7A
Authority: CN
Inventors: 蒋纬洋; 蒋能学; 王森; 王更生
Original assignee: Beijing Xiaoxiong Bowang Technology Co ltd
Current assignee: Beijing Xiaoxiong Bowang Technology Co., Ltd.
Priority date: 2017-04-24
Filing date: 2017-04-24
Publication date: 2021-05-28
Anticipated expiration: 2037-04-24
Also published as: CN108734498A

Abstract

The application discloses an advertisement pushing method and device. The method comprises the following steps: receiving an advertisement pulling request sent by a tool application program APP; when a user tag of the tool type APP does not exist in a pre-stored user tag library, determining the user tag according to installation list applist data of the tool type APP; determining advertisements matched with the user tags according to the user tags; and pushing the advertisement to the tool APP. According to the technical scheme of this application embodiment, confirm the user label through the applist data of instrument class APP to can give instrument class APP with the advertisement propelling movement that the user label matches, and then realize the accurate advertisement propelling movement to instrument class APP.

Description

Advertisement pushing method and device

Technical Field

The present disclosure relates generally to the field of computer technologies, and in particular, to the field of mobile internet, and in particular, to a method and an apparatus for advertisement delivery.

Background

With the popularization of mobile intelligent terminals (mobile phones, tablet computers and the like) and the increase of network speed, mobile advertisements are rapidly developed as a new advertising mode.

At present, many APPs (Application) downloaded by APP Application markets push advertisements to users, and a common method is to collect daily behavior data of users to perform data mining of user tags and perform advertisement pushing based on the mined user tags. The following disadvantages exist with this approach:

social APP, content APP and search APP and other service type APPs can collect user's daily behavior data, possess the ability of excavating user's label, but to instrument type APP, only the login data that few part users left can be as user label, and it can't collect user's daily behavior data, consequently can't carry out user label's data mining through the method commonly used, does not possess the ability of excavating user label, consequently can't realize the accurate advertisement propelling movement to instrument type APP.

Disclosure of Invention

In view of the foregoing defects or shortcomings in the prior art, it is desirable to provide a scheme capable of implementing accurate advertisement push for a tool APP.

In a first aspect, an embodiment of the present application provides an advertisement push method, including:

receiving an advertisement pulling request sent by a tool application program APP;

when a user tag of the tool type APP does not exist in a pre-stored user tag library, determining the user tag according to installation list applist data of the tool type APP;

determining advertisements matched with the user tags according to the user tags;

and pushing the advertisement to the tool APP.

In a second aspect, an embodiment of the present application further provides an advertisement push apparatus, including:

the receiving unit is used for receiving an advertisement pulling request sent by a tool application program APP;

a tag determining unit, configured to determine, when a user tag of the tool APP does not exist in a pre-stored user tag library, the user tag according to installation list applist data of the tool APP;

the advertisement determining unit is used for determining the advertisement matched with the user label according to the user label;

and the pushing unit is used for pushing the advertisement to the tool APP.

In a third aspect, embodiments of the present application further provide a computer device, including one or more processors and a memory; wherein:

the memory contains instructions executable by the processor to cause the processor to perform the advertisement push method described above.

The advertisement propelling movement scheme that this application embodiment provided, through the applist data determination user label of instrument class APP to can give instrument class APP with the advertisement propelling movement that user label matches, and then realize the accurate advertisement propelling movement to instrument class APP.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 illustrates an exemplary system architecture in which embodiments of the present application may be applied;

FIG. 2 illustrates an exemplary flow diagram of an advertisement push method according to an embodiment of the present application;

FIG. 3 shows a block diagram of an exemplary architecture of an advertisement push device according to another embodiment of the present application; and

FIG. 4 illustrates a schematic block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Referring to FIG. 1, an exemplary system architecture 100 to which embodiments of the present application may be applied is shown.

As shown in fig. 1, system architecture 100 may include

terminal devices

101, 102, network 103, and

servers

104, 105, 106, and 107. The network 103 is the medium used to provide communication links between the

terminal devices

101, 102 and the

servers

104, 105, 106, 107. Network 103 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user 110 may use the

terminal device

101, 102 to interact with the

server

104, 105, 106, 107 via the network 103 to access various services, such as browsing web pages, downloading data, etc. The

terminal devices

101, 102 may have installed thereon various client applications, such as applications that may access a uniform resource locator, URL, cloud service, including but not limited to browsers, security applications, and the like.

The

terminal devices

101, 102 may be various electronic devices including, but not limited to, personal computers, smart phones, smart televisions, tablet computers, personal digital assistants, e-book readers, and the like.

The

servers

104, 105, 106, 107 may be servers that provide various services. The server may provide the service in response to a service request of the user. It will be appreciated that one server may provide one or more services, and that the same service may be provided by multiple servers.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

As mentioned in the background, the prior art generally performs data mining on user tags by collecting daily behavior data of users, and pushes advertisements to APPs based on the mined user tags. However, for the tool APP, except that a small part of login data left by the user can be used as a user tag, most of the remaining users can only dig out their APP installation lists (applist), and cannot dig out data of the user tag through a common method, and the capability of digging out the user tag is not provided, so that accurate advertisement push for the tool APP cannot be realized.

In view of the above defects in the prior art, the embodiment of the present application provides an advertisement push scheme, which determines a user tag through APP data of a tool APP, so that an advertisement matched with the user tag can be pushed to the tool APP, and accurate advertisement push to the tool APP is realized.

The method of the embodiments of the present application will be described below with reference to a flowchart.

Referring to FIG. 2, an exemplary flow diagram of an advertisement push method according to one embodiment of the present application is shown. The method shown in fig. 2 may be performed at the server side in fig. 1.

As shown in fig. 2, the method comprises the steps of:

step 210, receiving an advertisement pulling request sent by the tool APP.

In this embodiment of the present application, the sending timing of the advertisement pulling request may be, but is not limited to:

1. when a user uses a tool APP, the tool APP sends an advertisement pulling request to a server side when the tool APP completes a certain specified function, and after a certain mobile phone safety assistant APP finishes mobile phone garbage cleaning, the user sends the advertisement pulling request to the server side by taking a certain mobile phone safety assistant APP as an example;

2. and when the tool APP runs, sending an advertisement pulling request to the server according to a sending period preset by a developer.

Step 220, when the user tag of the tool type APP does not exist in the pre-stored user tag library, determining the user tag according to the applist data of the tool type APP.

In the embodiment of the present application, step 220 may be implemented, but is not limited to, as follows:

firstly, acquiring applist data of a tool APP;

the applist data of the tool APP may be obtained by data mining of the tool APP. Still taking a certain mobile phone security assistant as an example, the applist data obtained by data mining on the mobile phone security assistant may include, but is not limited to, cleaning up garbage data.

Then, the applist data is learned according to a label model which is obtained in advance and used for distinguishing the user labels, and the user labels corresponding to the applist data are obtained.

The label model can be obtained as follows:

firstly, acquiring applist sample data and user attribute data corresponding to the applist sample data;

the user attribute data may include one or more of natural attribute data, social attribute data, and geographic location attribute data, wherein:

the natural attribute data may include: gender, age, and constellation, etc.;

the social attribute data may include: marital status, occupation, interest, education, assets, job hunting, health status, etc.;

the geographic location attribute data may include: continents, countries, provinces, cities, regions, etc.

And then, taking the applist sample data as an input characteristic and the user attribute data as a model label, and performing label model training to generate a label model.

In the embodiment of the present application, when training the label model, the following machine learning algorithm may be used, but is not limited to:

LR (logical Regression), GBDT (Gradient Boosting Decision Tree), FM (Factorization Machines), GP (Gaussian Process), DNN (Deep Neural Network), Deep self-coding Network, Softmax, and the like.

Taking gender and age in the natural attribute data as an example,

sex is divided into male and female, and is often used as discrete data, and algorithms such as LR and FM can be used as a learning label of a sex label;

the age is numerical data, which is discretized in a common fixed interval, and the learning model of the age label can be selected by adding softmax to algorithms such as depth self-coding and DNN.

It should be noted that, after the user tag is determined, the user tag may be stored in the user tag library, so that when an advertisement pulling request sent by the tool APP is subsequently received, the user tag may be directly extracted from the user tag library.

Further, since the interest of the user may change, for example, when the tool APP cleans up the garbage, the game APP which has been cleaned up most is cleaned up, and the video APP which has been cleaned up most after a period of time becomes, this indicates that the interest of the user is shifted to some extent, and thus the user tag may also change accordingly. Therefore, the user tags stored in the user tag library can be updated by utilizing the applist data of the tool APP according to the set update period.

In addition, in the embodiment of the application, in addition to determining the user tag by using the APP data, the user data of the user terminal where the tool APP is located may also be obtained, and the user tag is determined jointly according to the APP data and the user data.

The user data may include, but is not limited to:

one or more of user preference data mined based on raw data provided by the tool class APP, user social data (such as dwell time on a certain page, frequently visited websites, etc.) obtained from other APPs other than the tool class APP, and user behavior data (such as advertisement pull behavior and click behavior, etc.).

And step 230, determining advertisements matched with the user tags according to the determined user tags.

In the embodiment of the present application, the following implementation may be implemented, but not limited to:

the first mode is as follows:

and respectively calculating the similarity between the user tag of the tool APP and the preset advertisement tag of each advertisement, and determining the advertisement with the similarity not less than the preset similarity as the advertisement matched with the user tag.

The numerical range of the similarity is 0 to 1, when the similarity is 0, the user label and the advertisement label are completely different, and when the similarity is 1, the user label and the advertisement label are completely the same. For example, the preset similarity is set to 1, the user tag is a man, a minor adult, a student, a game, or the united states, and the advertiser sets the same advertisement tag for a certain advertisement of the advertiser, so that the similarity between the user tag and the advertisement tag is 1, and the advertisement is an advertisement matched with the user tag.

The second mode is as follows:

and inputting the user tags and preset advertisement characteristics of the advertisements into a machine learning model for determining the advertisements matched with the user tags to obtain the advertisements matched with the user tags.

And step 240, pushing the determined advertisement to the tool APP.

In the embodiment of the application, besides the determined advertisement is pushed to the tool APP, some exploratory advertisements can be issued to explore and meet the uncertainty change of the user preference. For example, according to an EE (Exploration & Exploitation) policy, at least one advertisement is selected from other advertisements except the advertisement matched with the user tag and pushed to the tool APP; wherein the category of the selected advertisement is different from the category of the advertisement matched with the user label.

It should be noted that while the operations of the method of the present invention are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the steps depicted in the flowcharts may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.

With further reference to fig. 3, a block diagram of an exemplary structure of an advertisement push device according to an embodiment of the present application is shown. The apparatus 300 may include:

a receiving unit 310, configured to receive an advertisement pulling request sent by a tool application APP;

a first tag determining unit 320, configured to determine, when a user tag of the tool APP does not exist in a pre-stored user tag library, the user tag according to the installation list applist data of the tool APP;

an advertisement determination unit 330, configured to determine, according to the user tag, an advertisement that matches the user tag;

a first pushing unit 340, configured to push the advertisement to the tool APP.

Wherein the first tag determining unit 320 includes:

a first obtaining module 3210, configured to obtain applist data of the tool APP;

the first learning module 3220 is configured to learn the applist data according to a tag model that is obtained in advance and used for distinguishing a user tag, so as to obtain the user tag corresponding to the applist data.

Optionally, the apparatus further comprises:

a tag model generating unit 350, configured to obtain an applist sample data and user attribute data corresponding to the applist sample data; and taking the applist sample data as an input characteristic, taking the user attribute data as a model label, and performing label model training to generate the label model.

Wherein the user attribute data comprises:

one or more of natural attribute data, social attribute data, and geographic location attribute data.

Wherein the advertisement determination unit 330 is configured to:

respectively calculating the similarity between the user tag of the tool APP and the preset advertisement tag of each advertisement; determining the advertisement with the similarity not less than the preset similarity as the advertisement matched with the user label; or

And inputting the user label and preset advertisement characteristics of each advertisement into a machine learning model for determining the advertisement matched with the user label to obtain the advertisement matched with the user label.

Optionally, the tag determining unit 320 may include:

a second obtaining module 3230, configured to obtain applist data of the tool APP and user data of a user terminal where the tool APP is located; the user data includes: one or more of user social data and user behavior data obtained from other APPs except the tool class APP based on user preference data mined from original data provided by the tool class APP;

and the second learning module 3240 is configured to learn the applist data and the user data according to a tag model obtained in advance and used for distinguishing the user tag, so as to obtain the user tag.

Optionally, the apparatus further comprises:

the second pushing unit 360 is used for selecting at least one advertisement from other advertisements except the advertisement matched with the user tag and pushing the selected advertisement to the tool APP; wherein the category of the selected advertisement is different from the category of the advertisement matched with the user label.

It should be understood that the subsystems or units recited in the apparatus 300 correspond to the various steps in the method described with reference to fig. 2. Thus, the operations and features described above for the method are equally applicable to the apparatus 300 and the units included therein and will not be described again here.

Referring now to FIG. 4, a block diagram of a computer system 400 suitable for use in implementing a server according to embodiments of the present application is shown.

As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the system 400 are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.

In particular, the process described above with reference to fig. 2 may be implemented as a computer software program, according to an embodiment of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method of fig. 2. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present application may be implemented by software or hardware. The described units or modules may also be provided in a processor. The names of these units or modules do not in some cases constitute a limitation of the unit or module itself.

As another aspect, the present application also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiments; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the formula input methods described herein.

The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by a person skilled in the art that the scope of the invention as referred to in the present application is not limited to the embodiments with a specific combination of the above-mentioned features, but also covers other embodiments with any combination of the above-mentioned features or their equivalents without departing from the inventive concept. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims

1. An advertisement pushing method, characterized in that the method comprises:

when the user tag of the tool type APP does not exist in a pre-stored user tag library, determining the user tag according to the installation list applist data of the tool type APP, including:

acquiring applist data of the tool APP;

learning the applist data according to a label model which is obtained in advance and used for distinguishing user labels to obtain the user labels;

and pushing the advertisement to the tool APP.

2. The method of claim 1, wherein the label model is obtained as follows:

acquiring applist sample data and user attribute data corresponding to the applist sample data;

and taking the applist sample data as an input characteristic, taking the user attribute data as a model label, and performing label model training to generate the label model.

3. The method of claim 2, wherein the user attribute data comprises:

4. The method of claim 1, wherein determining the advertisement matching the user tag according to the user tag comprises:

respectively calculating the similarity between the user tag of the tool APP and the preset advertisement tag of each advertisement;

determining the advertisement with the similarity not less than the preset similarity as the advertisement matched with the user label; or

5. The method according to claim 1, wherein the determining the user tag according to the installation list applist data of the tool class APP comprises:

acquiring applist data of the tool type APP and user data of a user terminal where the tool type APP is located; the user data includes: one or more of user social data and user behavior data obtained from other APPs except the tool class APP based on user preference data mined from original data provided by the tool class APP;

and learning the applist data and the user data according to a label model which is obtained in advance and used for distinguishing the user label to obtain the user label.

6. The method according to claim 1, characterized in that after receiving an advertisement pull request sent by the utility APP, the method further comprises:

according to an exploratory and developing EE strategy, selecting at least one advertisement from other advertisements except the advertisement matched with the user tag and pushing the selected advertisement to the tool APP; wherein the category of the selected advertisement is different from the category of the advertisement matched with the user label.

7. An advertisement push apparatus, characterized in that the apparatus comprises:

a tag determining unit, configured to determine, when a user tag of the tool APP does not exist in a pre-stored user tag library, the user tag according to installation list applist data of the tool APP, where the tag determining unit includes:

the first obtaining module is used for obtaining applist data of the tool APP;

the first learning module is used for learning the applist data according to a label model which is obtained in advance and used for distinguishing user labels to obtain the user labels;

the first pushing unit is used for pushing the advertisement to the tool APP.

8. The apparatus of claim 7, further comprising:

the tag model generation unit is used for acquiring applist sample data and user attribute data corresponding to the applist sample data; and taking the applist sample data as an input characteristic, taking the user attribute data as a model label, and performing label model training to generate the label model.

9. The apparatus of claim 8, wherein the user attribute data comprises:

10. The apparatus of claim 7, wherein the advertisement determination unit is configured to:

11. The apparatus of claim 7, wherein the tag determination unit comprises:

a second obtaining module, configured to obtain applist data of the tool APP and user data of a user terminal where the tool APP is located; the user data includes: one or more of user social data and user behavior data obtained from other APPs except the tool class APP based on user preference data mined from original data provided by the tool class APP;

and the second learning module is used for learning the applist data and the user data according to a label model which is obtained in advance and used for distinguishing the user label, so that the user label is obtained.

12. The apparatus of claim 7, further comprising:

the second pushing unit is used for selecting at least one advertisement from other advertisements except the advertisement matched with the user tag according to an EE strategy and pushing the selected advertisement to the tool APP; wherein the category of the selected advertisement is different from the category of the advertisement matched with the user label.

13. A computer device comprising one or more processors and memory; the method is characterized in that:

the memory contains instructions executable by the processor to cause the processor to perform the method of any one of claims 1 to 6.