CN112446717B - Advertisement putting method and device - Google Patents
Advertisement putting method and device Download PDFInfo
- Publication number
- CN112446717B CN112446717B CN201910798337.4A CN201910798337A CN112446717B CN 112446717 B CN112446717 B CN 112446717B CN 201910798337 A CN201910798337 A CN 201910798337A CN 112446717 B CN112446717 B CN 112446717B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- website
- determining
- click rate
- candidate
- 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.)
- Active
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
- G06Q30/0277—Online advertisement
-
- 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
- G06Q30/0273—Determination of fees for advertising
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
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 application provides an advertisement putting method and device, wherein the method comprises the following steps: receiving an advertisement delivery request of a website, wherein the advertisement delivery request comprises: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; determining the flow value of the website according to the related information of the website; determining each candidate advertisement and click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website; according to the click rate estimated probability and bid of each candidate advertisement, the advertisement to be put is determined, and the method can put the advertisement aiming at the flow of different values, so that the advertisement putting efficiency is improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and apparatus for advertisement delivery.
Background
The current advertisement delivery system mainly delivers advertisements based on search words or user interests, does not consider traffic values, delivers the same advertisements aiming at traffic with different values, is difficult to deliver the advertisements aiming at traffic with different values, and reduces advertisement delivery efficiency.
Disclosure of Invention
The present application aims to solve at least to some extent one of the above technical problems.
Therefore, a first object of the present application is to provide an advertisement delivery method, which can deliver advertisements for different value traffic, and improve advertisement delivery efficiency.
A second object of the present application is to provide an advertising device.
A third object of the present application is to propose another advertising device.
A fourth object of the present application is to propose a computer readable storage medium.
A fifth object of the application is to propose a computer programme product.
To achieve the above object, an embodiment of a first aspect of the present application provides an advertisement delivery method, including: receiving an advertisement delivery request of a website, wherein the advertisement delivery request comprises: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; determining the flow value of the website according to the related information of the website; determining each candidate advertisement and click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website; and determining the advertisement to be put according to the estimated probability and the bid of the Click-Through-Rate (CTR) of each candidate advertisement.
According to the advertisement putting method, by receiving the advertisement putting request of the website, the advertisement putting request comprises the following steps: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; determining the flow value of the website according to the related information of the website; determining each candidate advertisement and click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website; and determining the advertisement to be put according to the click rate estimated probability and the bid of each candidate advertisement. The method can be used for delivering advertisements aiming at traffic with different values, and the advertisement delivery efficiency is improved.
To achieve the above object, an embodiment of a second aspect of the present application provides an advertisement delivery device, including: the receiving module is used for receiving an advertisement putting request of a website, and the advertisement putting request comprises: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; the first determining module is used for determining the flow value of the website according to the related information of the website; the second determining module is used for determining each candidate advertisement and the click rate estimated probability of each candidate advertisement according to the flow value of the website and the related information of the website; and the third determining module is used for determining the advertisement to be put according to the click rate estimated probability and the bid of each candidate advertisement.
According to the advertisement putting device provided by the embodiment of the application, by receiving the advertisement putting request of the website, the advertisement putting request comprises: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; determining the flow value of the website according to the related information of the website; determining each candidate advertisement and click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website; and determining the advertisement to be put according to the click rate estimated probability and the bid of each candidate advertisement. The device can realize that advertisements can be put aiming at the flows with different values, and improves the advertisement putting efficiency.
To achieve the above object, an embodiment of a third aspect of the present application provides another advertisement delivery device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed implements the advertising method as described above.
To achieve the above object, a fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the advertisement delivery method as described above.
To achieve the above object, an embodiment of a fifth aspect of the present application proposes a computer program product comprising a computer program which, when executed by a processor, implements the advertisement delivery method as described above.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow diagram of an advertising method according to one embodiment of the application;
FIG. 2 is a flow chart of an advertising method according to another embodiment of the application;
FIG. 3 is a schematic diagram of the structure of a click rate model according to an embodiment of the application;
FIG. 4 is a schematic diagram of an advertising device according to one embodiment of the application;
FIG. 5 is a schematic diagram of an advertisement delivery device according to another embodiment of the present application;
FIG. 6 is a schematic diagram of an advertising device according to yet another embodiment of the present application;
fig. 7 is a schematic diagram of another advertising device according to an embodiment of the application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The advertisement delivery method and device according to the embodiments of the present application are described below with reference to the accompanying drawings. It should be noted that, the implementation main body of the advertisement delivery method in the embodiment of the present application is an advertisement delivery device, and the advertisement delivery device may be specifically an intelligent advertisement delivery system.
Fig. 1 is a flow chart of an advertisement delivery method according to an embodiment of the present application. As shown in fig. 1, the advertisement delivery method includes the steps of:
step 101, receiving an advertisement putting request of a website, wherein the advertisement putting request comprises: identification of websites and website related information; the website-related information includes: website traffic attributes, user access behavior, and a launch resource utilization index.
Specifically, during the process of advertisement delivery, the advertisement delivery device may receive an advertisement delivery request of a website, where the advertisement delivery request may include, but is not limited to, an identifier of the website and website related information, the identifier of the website may be used to uniquely identify the website, and the advertisement delivery device may determine a source of the advertisement delivery request according to the identifier; relevant information for a website may include, but is not limited to, website traffic attributes, user access behavior, and a launch resource utilization index, among others. The website traffic attribute may include, but is not limited to, traffic type, website page uniform resource locator and its content, channel to which the website page belongs, advertisement location in the website page, etc. In the embodiment of the application, the traffic type is search traffic, feed (required) traffic, content-oriented traffic, or the like. For example: hundred degree search traffic, hundred degree feed traffic, hundred degree federation traffic. The user access behavior may be a user access behavior to a website.
And 102, determining the traffic value of the website according to the related information of the website.
As one example, the traffic value of the website may be determined based on the traffic attributes of the website, the user's access behavior, and the released resource utilization index. The traffic value of the website may include, but is not limited to, advertisement click-through rate, purchase rate, etc. of the website.
In the embodiment of the application, the advertisement putting device can count the number of users accessing the website, the access behaviors of the users in the website and the putting resource utilization index, and determine the total click rate or purchase rate of the historical putting advertisements of the website. The access behavior of the user in the website may include, but is not limited to, newly added user in the website, return visit of the user, purchasing behavior of the user, and the like. The delivery resource utilization index may be, but is not limited to, a delivery resource utilization ratio, which may be calculated by the following formula, for example: put resource utilization index = utilized put resources/total put resources.
And step 103, determining each candidate advertisement and the click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website.
Further, the traffic value of the website is determined according to the related information of the website. And then, determining each candidate advertisement and the click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website. .
According to the embodiment of the application, the network branches to be used in the click rate model and each candidate advertisement can be determined according to the flow value of the website, the flow attribute of the website and the utilization index of the released resources; and inputting advertisement information of each candidate advertisement and user access behaviors into network branches to be used in the click rate model to obtain click rate estimated probability of each candidate advertisement. See for details the description of the embodiments that follow.
And 104, determining the advertisement to be put according to the click rate estimated probability and the bid of each candidate advertisement.
Further, the estimated click rate probability of each candidate advertisement is obtained, and then the advertisement to be put can be determined according to the estimated click rate probability and the bid of each candidate advertisement.
Optionally, sorting the candidate advertisements in ascending order according to the product of the click rate estimated probability and the bid; and determining the candidate advertisements ranked in front as advertisements to be put.
That is, in order to improve the advertisement delivery efficiency, the candidate advertisements ranked in front may be determined as the advertisement to be delivered by multiplying the click rate estimated probability of each candidate advertisement by the corresponding preset bid of each candidate advertisement and ranking. Wherein, each candidate advertisement preset bid can be set in advance according to each click of the website.
According to the advertisement putting method, by receiving the advertisement putting request of the website, the advertisement putting request comprises the following steps: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; determining the flow value of the website according to the related information of the website; determining each candidate advertisement and click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website; and determining the advertisement to be put according to the click rate estimated probability and the bid of each candidate advertisement. The method can be used for delivering advertisements aiming at traffic with different values, and the advertisement delivery efficiency is improved.
In the embodiment of the present application, according to the traffic value, the traffic attribute and the delivery resource utilization index of the website, the network branches to be used in the click rate model and each candidate advertisement are determined, optionally, as shown in fig. 2, according to the traffic value, the traffic attribute and the delivery resource utilization index of the website, the specific steps of determining the network branches to be used in the click rate model and each candidate advertisement may be as follows:
in step 201, a value threshold corresponding to the traffic type is obtained.
Step 202, determining whether to terminate the advertisement delivery request according to the traffic value and the value threshold of the website.
In order to further save related resources, improve advertisement delivery efficiency, ensure that advertisement delivery revenue is maximized, when determining network branches to be used in the click-through rate model and each candidate advertisement, it may be determined whether to terminate the advertisement delivery request.
It should be understood that, in the embodiment of the present application, the advertisement delivery device may first obtain the value threshold corresponding to the traffic type in the advertisement delivery request. Then, comparing the flow value of the website with a corresponding value threshold, and if the flow value of the website is smaller than the corresponding value threshold, stopping the advertisement putting request if the advertisement putting income of the website is smaller; if the traffic value of the website is greater than or equal to the corresponding value threshold, the advertisement putting income of the website is larger, and the advertisement putting can be continued.
And 203, when the advertisement putting request is not terminated, determining network branches to be used in the click rate model and candidate advertisements according to the value threshold, the website flow attribute and the putting resource utilization index.
Further, when it is determined that the advertisement delivery request is not terminated, network branches to be used in the click rate model and candidate advertisements may be determined according to the value threshold, the website traffic attribute, and the delivery resource utilization index.
Optionally, determining advertisement related information of the website according to the value threshold, the website flow attribute and the release resource utilization index, wherein the advertisement related information comprises: intent branch combinations, number of candidate cuts, ad creative style combinations; and selecting each candidate advertisement according to the advertisement related information.
In the embodiment of the application, the advertisement putting device can generate the advertisement related information of the website by utilizing the offline pre-trained reinforcement learning model according to the value threshold value corresponding to the flow type, the website flow attribute and the putting resource utilization index, and then can search according to the advertisement related information, thereby selecting each candidate advertisement. Wherein, the offline pre-trained reinforcement learning model can be but is not limited to a pre-trained deep network model, and the advertisement related information can include but is not limited to an intention branch combination, a candidate truncation number and an advertisement creative style combination. The intended branching combination may be, for example: search intent, user interest intent, trending intent, industry intent, and the like. An ad creative style combination may be a presentation element of an ad, such as: title, picture, album, abstract, etc. of the advertisement.
In order to further improve the advertisement putting efficiency, each candidate advertisement is selected according to the advertisement related information, and then the advertisement information and the user access behavior of each candidate advertisement can be input into the network branches to be used in the click rate model to obtain the click rate estimated probability of each candidate advertisement.
It is easy to understand that before the advertisement information and the user access behavior of each candidate advertisement are input into the network branches to be used in the click rate model to obtain the click rate estimated probability of each candidate advertisement, the click rate model can be obtained first, and the click rate model can comprise a plurality of network branches; thereafter, training data is acquired, the training data comprising: advertisement information of advertisement samples, user access behaviors and click rate estimated probability; in order to realize the elastic calculation of the click rate estimated probability of the advertisement, the click rate model can be set based on a multi-layer loss function, and training data is adopted to train the click rate model until the value of the preset loss function is smaller than a preset numerical value. The loss function can be calculated and determined according to the output of each network branch and the click rate estimated probability of the advertisement sample. The value of the predetermined loss function being smaller than the predetermined value may be that the sum of the values of the loss functions of the respective layers is smaller than the predetermined value.
For example, as shown in fig. 3, the network branch structure in the click rate model is shown, when a 4096 network branch+256 network branches are selected when a network branch in the click rate model is selected, the loss function is a loss function 1; when 4096 network branch+2048 network branch+256 network branch is selected, the loss function is loss function 2 at this time; when 4096 network branch+2048 network branch+1024 network branch+256 network branch is selected, the loss function is the loss function 3 at this time; when 4096 network branch+2048 network branch+1024 network branch+512 network branch+256 network branch is selected, the loss function is the loss function 4; the loss function of the whole network branch structure is the combination of the loss function 1, the loss function 2, the loss function 3 and the loss function 4, and the value of the loss function of the network branch structure=the value of the loss function 1+the value of the loss function 2+the value of the loss function 3+the value of the loss function 4.
According to the embodiment of the application, the network branches to be used in the click rate model and each candidate advertisement can be determined according to the flow value of the website, the flow attribute of the website and the utilization index of the released resources; and inputting advertisement information of each candidate advertisement and user access behaviors into network branches to be used in the click rate model to obtain click rate estimated probability of each candidate advertisement. Therefore, related resources can be further saved, the advertising efficiency is improved, and the advertising income maximization is ensured.
Corresponding to the advertisement delivery methods provided by the above embodiments, an embodiment of the present application further provides an advertisement delivery device, and since the advertisement delivery device provided by the embodiment of the present application corresponds to the advertisement delivery method provided by the above embodiments, implementation of the advertisement delivery method described above is also applicable to the advertisement delivery device provided by the embodiment, and will not be described in detail in the embodiment. Fig. 4 is a schematic structural view of an advertisement delivery device according to an embodiment of the present application. As shown in fig. 4, the advertisement delivery device includes: the receiving module 410, the first determining module 420, the second determining module 430, and the third determining module 440.
Wherein, the receiving module 410 is configured to receive an advertisement delivery request of a website, where the advertisement delivery request includes: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; a first determining module 420, configured to determine a traffic value of the website according to the website related information; a second determining module 430, configured to determine each candidate advertisement and a click rate estimated probability of each candidate advertisement according to the traffic value of the website and the website related information; and a third determining module 440, configured to determine the advertisement to be placed according to the click-through rate estimated probability and the bid of each candidate advertisement.
As a possible implementation manner of the embodiment of the present application, as shown in fig. 5, on the basis of the description of fig. 4, the second determining module 430 includes: a determination unit 431 and an input unit 432.
The determining unit 431 is configured to determine a network branch to be used in the click rate model and each candidate advertisement according to the traffic value of the website, the traffic attribute of the website, and the delivery resource utilization index; the input unit 432 is configured to input advertisement information and user access behavior of each candidate advertisement into a network branch to be used in the click rate model, so as to obtain click rate estimated probability of each candidate advertisement.
As one possible implementation of the embodiment of the present application, the website traffic attribute includes: a flow type; the determining unit 431 is specifically configured to obtain a value threshold corresponding to the traffic type; determining whether to terminate the advertisement putting request according to the flow value and the value threshold value of the website; and when the advertisement putting request is not terminated, determining network branches to be used in the click rate model and candidate advertisements according to the value threshold, the website flow attribute and the putting resource utilization index.
As one possible implementation manner of the embodiment of the application, the method for determining each candidate advertisement is to determine advertisement related information of a website according to a value threshold, a website flow attribute and a release resource utilization index, wherein the advertisement related information comprises: intent branch combinations, number of candidate cuts, ad creative style combinations; and selecting each candidate advertisement according to the advertisement related information.
As a possible implementation manner of the embodiment of the present application, the determining unit 431 is specifically further configured to determine whether the flow value is smaller than the value threshold; if the traffic value is less than the value threshold, determining to terminate the advertisement delivery request; if the traffic value is greater than or equal to the value threshold, it is determined that the advertisement delivery request is not terminated.
As a possible implementation manner of the embodiment of the present application, the third determining module 440 is specifically configured to sort each candidate advertisement in ascending order according to the product of the click rate estimated probability and the bid; and determining the candidate advertisements ranked in front as advertisements to be put.
As a possible implementation manner of the embodiment of the present application, as shown in fig. 6, on the basis of the embodiment shown in fig. 4, the advertisement delivery device further includes: an acquisition module 450 and a training module 460.
The acquiring module 450 is configured to acquire a click rate model, where the click rate model includes a plurality of network branches; the obtaining module 450 is further configured to obtain training data, where the training data includes: advertisement information of advertisement samples, user access behaviors and click rate estimated probability; the training module 460 is configured to train the click rate model using training data until a value of a preset loss function is less than a preset numerical value.
As one possible implementation manner of the embodiment of the application, the loss function is calculated and determined according to the output of each network branch and the click rate estimated probability of the advertisement sample.
According to the advertisement putting device provided by the embodiment of the application, by receiving the advertisement putting request of the website, the advertisement putting request comprises: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes; determining the flow value of the website according to the related information of the website; determining each candidate advertisement and click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website; and determining the advertisement to be put according to the click rate estimated probability and the bid of each candidate advertisement. The device can realize that advertisements can be put aiming at the flows with different values, and improves the advertisement putting efficiency.
In order to implement the above embodiment, another advertisement delivery device is further provided in the embodiment of the present application, and fig. 7 is a schematic structural diagram of another advertisement delivery device provided in the embodiment of the present application. The advertisement putting device comprises: memory 1001, processor 1002, and a computer program stored on memory 1001 and executable on processor 1002.
The advertisement delivery method provided in the above-described embodiment is implemented when the processor 1002 executes the program.
Further, the advertisement delivery device further includes:
a communication interface 1003 for communication between the memory 1001 and the processor 1002.
Memory 1001 for storing computer programs that may be run on processor 1002.
Memory 1001 may include high-speed RAM memory and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
And a processor 1002, configured to implement the advertisement delivery method according to the above embodiment when executing the program.
If the memory 1001, the processor 1002, and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001, and the processor 1002 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (Peripheral Component, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 1001, the processor 1002, and the communication interface 1003 are integrated on a chip, the memory 1001, the processor 1002, and the communication interface 1003 may complete communication with each other through internal interfaces.
The processor 1002 may be a central processing unit (Central Processing Unit, abbreviated as CPU) or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC) or one or more integrated circuits configured to implement embodiments of the present application.
In order to achieve the above-described embodiments, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the advertisement delivery method as described above.
To achieve the above embodiments, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the advertisement delivery method as described above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (16)
1. An advertising method, comprising:
receiving an advertisement delivery request of a website, wherein the advertisement delivery request comprises: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes;
determining the flow value of the website according to the related information of the website;
determining each candidate advertisement and click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website;
determining advertisements to be put according to the click rate estimated probability and the bid of each candidate advertisement;
the determining each candidate advertisement and the click rate estimated probability of each candidate advertisement according to the traffic value of the website and the related information of the website comprises the following steps:
determining network branches to be used in a click rate model and candidate advertisements according to the flow value of the website, the flow attribute of the website and the put resource utilization index;
inputting advertisement information of each candidate advertisement and the user access behavior into a network branch to be used in the click rate model to obtain click rate estimated probability of each candidate advertisement;
the click rate model comprises a plurality of network branches, and corresponding loss functions are different when different network branches in the click rate model are selected.
2. The method of claim 1, wherein the website traffic attribute comprises: a flow type;
the determining the network branches to be used in the click rate model and each candidate advertisement according to the traffic value of the website, the traffic attribute of the website and the put resource utilization index comprises the following steps:
acquiring a value threshold corresponding to the flow type;
determining whether to terminate the advertisement delivery request according to the traffic value of the website and the value threshold;
and when the advertisement putting request is not terminated, determining network branches to be used in a click rate model and candidate advertisements according to the value threshold, the website flow attribute and the putting resource utilization index.
3. The method of claim 2, wherein each candidate advertisement is determined by,
determining advertisement related information of the website according to the value threshold, the website flow attribute and the release resource utilization index, wherein the advertisement related information comprises: intent branch combinations, number of candidate cuts, ad creative style combinations;
and selecting each candidate advertisement according to the advertisement related information.
4. The method of claim 2, wherein the determining whether to terminate the advertisement delivery request based on the traffic value of the website and the value threshold comprises:
judging whether the flow value is smaller than the value threshold value or not;
if the traffic value is less than the value threshold, determining to terminate the advertisement delivery request;
and if the flow value is greater than or equal to the value threshold, determining not to terminate the advertisement delivery request.
5. The method of claim 1, wherein determining the advertisement to be served based on the click-through rate pre-estimated probability and the bid for each candidate advertisement comprises:
the candidate advertisements are sequenced in an ascending order according to the product of the click rate estimated probability and the bid;
and determining the candidate advertisements ranked in front as advertisements to be put.
6. The method according to claim 1, wherein before inputting the advertisement information of each candidate advertisement and the user access behavior into the network branch to be used in the click rate model to obtain the click rate estimated probability of each candidate advertisement, the method further comprises:
acquiring a click rate model, wherein the click rate model comprises a plurality of network branches;
acquiring training data, the training data comprising: advertisement information of advertisement samples, user access behaviors and click rate estimated probability;
and training the click rate model by adopting the training data until the value of the preset loss function is smaller than a preset numerical value.
7. The method of claim 6, wherein the loss function is determined based on the output of each network leg and a click-through rate prediction probability calculation for the advertisement samples.
8. An advertising device, comprising:
the receiving module is used for receiving an advertisement putting request of a website, and the advertisement putting request comprises: identification of websites and website related information; the website-related information includes: website flow properties, user access behaviors and release resource utilization indexes;
the first determining module is used for determining the flow value of the website according to the related information of the website;
the second determining module is used for determining each candidate advertisement and the click rate estimated probability of each candidate advertisement according to the flow value of the website and the related information of the website;
the third determining module is used for determining advertisements to be put according to the click rate estimated probability and the bid of each candidate advertisement;
the second determining module includes: a determination unit and an input unit;
the determining unit is used for determining network branches to be used in the click rate model and candidate advertisements according to the flow value of the website, the flow attribute of the website and the put resource utilization index;
the input unit is used for inputting the advertisement information of each candidate advertisement and the user access behavior into the network branches to be used in the click rate model to obtain the click rate estimated probability of each candidate advertisement;
the click rate model comprises a plurality of network branches, and corresponding loss functions are different when different network branches in the click rate model are selected.
9. The apparatus of claim 8, wherein the website traffic attribute comprises: a flow type;
the determination unit is in particular adapted to,
acquiring a value threshold corresponding to the flow type;
determining whether to terminate the advertisement delivery request according to the traffic value of the website and the value threshold;
and when the advertisement putting request is not terminated, determining network branches to be used in a click rate model and candidate advertisements according to the value threshold, the website flow attribute and the putting resource utilization index.
10. The apparatus of claim 9, wherein each candidate advertisement is determined by,
determining advertisement related information of the website according to the value threshold, the website flow attribute and the release resource utilization index, wherein the advertisement related information comprises: intent branch combinations, number of candidate cuts, ad creative style combinations;
and selecting each candidate advertisement according to the advertisement related information.
11. The apparatus according to claim 9, wherein the determining unit is further adapted to,
judging whether the flow value is smaller than the value threshold value or not;
if the traffic value is less than the value threshold, determining to terminate the advertisement delivery request;
and if the flow value is greater than or equal to the value threshold, determining not to terminate the advertisement delivery request.
12. The apparatus of claim 8, wherein the third determining means is specifically configured to,
the candidate advertisements are sequenced in an ascending order according to the product of the click rate estimated probability and the bid;
and determining the candidate advertisements ranked in front as advertisements to be put.
13. The apparatus as recited in claim 8, further comprising: the acquisition module and the training module;
the acquisition module is used for acquiring a click rate model, wherein the click rate model comprises a plurality of network branches;
the acquisition module is further configured to acquire training data, where the training data includes: advertisement information of advertisement samples, user access behaviors and click rate estimated probability;
and the training module is used for training the click rate model by adopting the training data until the value of the preset loss function is smaller than a preset numerical value.
14. The apparatus of claim 10, wherein the loss function is determined based on an output of each network leg and a click-through rate prediction probability calculation for the advertisement samples.
15. An advertising device, comprising:
memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the advertisement delivery method according to any of claims 1-7 when executing the program.
16. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the advertisement delivery method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798337.4A CN112446717B (en) | 2019-08-27 | 2019-08-27 | Advertisement putting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798337.4A CN112446717B (en) | 2019-08-27 | 2019-08-27 | Advertisement putting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112446717A CN112446717A (en) | 2021-03-05 |
| CN112446717B true CN112446717B (en) | 2023-08-11 |
Family
ID=74742253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910798337.4A Active CN112446717B (en) | 2019-08-27 | 2019-08-27 | Advertisement putting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446717B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819550B (en) * | 2021-03-08 | 2024-04-30 | 杭州推啊网络科技有限公司 | Advertisement bidding method and system |
| CN114298728A (en) * | 2021-10-20 | 2022-04-08 | 腾讯科技（深圳）有限公司 | Data processing method and related device |
| CN114841748A (en) * | 2022-05-13 | 2022-08-02 | 北京奇艺世纪科技有限公司 | Advertisement putting method and device, electronic equipment and storage medium |
| CN114897562A (en) * | 2022-05-27 | 2022-08-12 | 北京奇艺世纪科技有限公司 | Advertisement putting method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046532A (en) * | 2015-08-07 | 2015-11-11 | 北京品友互动信息技术有限公司 | Bidding method and device |
| CN108280682A (en) * | 2018-01-16 | 2018-07-13 | 深圳市和讯华谷信息技术有限公司 | Advertisement placement method, terminal and computer readable storage medium |
| CN110033314A (en) * | 2019-03-18 | 2019-07-19 | 北京品友互动信息技术股份公司 | Advertisement data processing method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2614364C (en) * | 2005-08-11 | 2016-09-27 | Contextweb, Inc. | Method and system for placement and pricing of internet-based advertisements or services |
-
2019
- 2019-08-27 CN CN201910798337.4A patent/CN112446717B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046532A (en) * | 2015-08-07 | 2015-11-11 | 北京品友互动信息技术有限公司 | Bidding method and device |
| CN108280682A (en) * | 2018-01-16 | 2018-07-13 | 深圳市和讯华谷信息技术有限公司 | Advertisement placement method, terminal and computer readable storage medium |
| CN110033314A (en) * | 2019-03-18 | 2019-07-19 | 北京品友互动信息技术股份公司 | Advertisement data processing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 李航 ; .突破传统网络营销的3C模式.创新科技.2007,(08),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112446717A (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112446717B (en) | Advertisement putting method and device | |
| CN108491529B (en) | Information recommendation method and device | |
| US20100191758A1 (en) | System and method for improved search relevance using proximity boosting | |
| CN110188350B (en) | Text consistency calculation method and device | |
| CN104504133B (en) | The recommendation method and device of application program | |
| US20100030648A1 (en) | Social media driven advertisement targeting | |
| US20060248072A1 (en) | System and method for spam identification | |
| CN103902697A (en) | Combinatorial search method, client and server | |
| CN106951527B (en) | Song recommendation method and device | |
| CN101071437A (en) | User classifying method, directional advertising launching method, device and system | |
| CN110287440B (en) | Search engine optimization method and device, computer equipment and computer-readable storage medium | |
| CN107203265B (en) | Information interaction method and device | |
| CN107886373B (en) | Advertisement pushing method and device based on keywords and electronic terminal | |
| CN113034241B (en) | Product information recommendation method and computer equipment | |
| CN111177174A (en) | SQL statement generation method, device, equipment and computer readable storage medium | |
| CN109544238A (en) | User behavior method for tracing, device, server and storage medium | |
| CN110515904A (en) | Quality prediction model training method, qualitative forecasting method and the device of media file | |
| CN112423134B (en) | Video content recommendation method and device, computer equipment and storage medium | |
| CN112132601B (en) | Advertisement title rewriting method, apparatus and storage medium | |
| CN108446359B (en) | Information recommendation method and device | |
| CN110515929A (en) | Books methods of exhibiting calculates equipment and storage medium | |
| CN112346951A (en) | Service testing method and device | |
| CN107748801A (en) | News recommends method, apparatus, terminal device and computer-readable recording medium | |
| CN110675205B (en) | Application-based competitive product analysis method and device and storage medium | |
| CN112131417B (en) | Image tag generation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |