CN114841750A

CN114841750A - Advertisement bidding method, equipment and computer storage medium

Info

Publication number: CN114841750A
Application number: CN202210540410.XA
Authority: CN
Inventors: 谢栋; 陈达贵; 陈纯杰
Original assignee: Alibaba China Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2022-05-17
Filing date: 2022-05-17
Publication date: 2022-08-02

Abstract

The embodiment of the application provides an advertisement bidding method, equipment and a computer storage medium. The method comprises the following steps: acquiring original bidding information provided for target flow when an advertiser to be supported participates in advertising bidding; determining platform preferential information provided by the platform for the advertiser to be supported; determining target bidding information based on the platform discount information and the original bidding information, wherein the target bidding information is larger than the original bidding information; and performing advertisement bidding operation based on the target bidding information. According to the technical scheme, the advertisement supporting operation can be automatically carried out on the advertiser to be supported without any manual operation of the advertiser, so that the using efficiency of the platform preferential information is effectively improved, and the platform preferential information is directly related to the loss of the platform, so that the loss of the platform can be controlled within a preset range through the platform preferential information, the condition that the platform is greatly lost can be avoided, and the flexible reliability of the method is guaranteed.

Description

Advertisement bidding method, equipment and computer storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for advertisement bidding, and a computer storage medium.

Background

With the rapid development of science and technology, the influence of information popularization is getting larger, and for an advertisement popularization platform, Real Time Bidding (RTB) becomes a novel advertisement putting form, specifically, Bidding auction is performed on advertisement slots, the quality of single display of advertisements in the internet is emphasized, different prices are given according to the display value evaluation, that is, one advertisement slot often selects exposed advertisement content in a Bidding manner. In a real-time bidding advertising system, a bidding mechanism of an advertisement often needs to target short-term efficiency indexes such as show (RPM) Per thousand times, total commodity transaction Value (GMV) and the like, and all advertisers are treated with the same idea.

In practical applications, the platform often needs to lose a certain short-term efficiency index to support a certain batch or a certain type of advertisers, such as: new advertisers or pre-churn advertisers may need to be supported as customers grow. At present, when a platform supports a specific advertiser, the platform often directly issues a certain amount of coupons to an account of the advertiser, and the purpose of supporting the advertiser is achieved through the coupons. However, since the coupon is sent from the advertisement promotion platform to the account of the advertiser, the coupon is used only by the manual operation of the advertiser, so that the link from the issuance to the use of the coupon is long, and the problems of low coupon use efficiency and poor platform controllability exist.

Disclosure of Invention

The embodiment of the application provides an advertisement bidding method, equipment and a computer storage medium, which can automatically support an advertiser to be supported, and ensure the quality and effect of advertisement supporting operation.

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

acquiring original bidding information provided for target flow when an advertiser to be supported participates in advertising bidding;

determining platform preferential information provided by the platform for the advertiser to be supported;

determining target bidding information based on the platform discount information and the original bidding information, wherein the target bidding information is larger than the original bidding information;

and performing advertisement bidding operation based on the target bidding information.

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

the first obtaining module is used for obtaining original bidding information provided by an advertiser to be supported for the target flow when the advertiser participates in the advertising bidding;

the first determination module is used for determining platform preference information provided by a platform for the advertiser to be supported;

the first determination module is configured to determine target bidding information based on the platform offer information and the original bidding information, where the target bidding information is greater than the original bidding information;

and the first processing module is used for carrying out advertisement bidding operation based on the target bidding information.

In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor; wherein the memory is configured to store one or more computer instructions that, when executed by the processor, implement the method of bidding for ads of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, which causes a computer to implement the advertisement bidding method according to the first aspect when executed.

In a fifth aspect, an embodiment of the present invention provides a computer program product, including: a computer program which, when executed by a processor of an electronic device, causes the processor to carry out the steps of the method for bidding on advertisements as described above in relation to the first aspect.

In a sixth aspect, an embodiment of the present invention provides an advertisement bidding method, including:

determining an advertisement putting index corresponding to the advertiser to be supported and platform preferential information provided by a platform for the advertiser to be supported;

based on the platform discount information and the advertisement putting index, determining discount distribution information corresponding to the target flow;

and determining the target bidding information based on the discount distribution information and the original bidding information, wherein the target bidding information is used for carrying out advertisement bidding operation.

In a seventh aspect, an embodiment of the present invention provides an advertisement bidding apparatus, including:

the second acquisition module is used for acquiring original bidding information provided for target flow when the advertiser to be supported participates in the advertising bidding;

the second determination module is used for determining the advertisement putting index corresponding to the advertiser to be supported and platform discount information provided by the platform for the advertiser to be supported;

the second determining module is configured to determine, based on the platform offer information and the advertisement delivery indicator, offer distribution information corresponding to the target traffic;

and the second processing module is used for determining the target bidding information based on the discount distribution information and the original bidding information, and the target bidding information is used for carrying out advertisement bidding operation.

In an eighth aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor; wherein the memory is configured to store one or more computer instructions that, when executed by the processor, implement the method of bidding for ads of the sixth aspect.

In a ninth aspect, an embodiment of the present invention provides a computer storage medium for storing a computer program, which makes a computer implement the advertisement bidding method according to the sixth aspect when executed.

In a tenth aspect, an embodiment of the present invention provides a computer program product, including: a computer program that, when executed by a processor of an electronic device, causes the processor to execute the steps in the advertisement bidding method according to the sixth aspect.

According to the advertisement bidding method, the device and the computer storage medium provided by the embodiment of the application, original bidding information provided for target flow when an advertiser to be supported participates in advertisement bidding is obtained; the platform preferential information provided by the platform for the advertiser to be supported is determined, then the target bidding information is automatically determined based on the platform preferential information and the original bidding information, and the advertisement bidding operation is carried out based on the target bidding information, so that the advertisement supporting operation for the advertiser to be supported can be automatically carried out based on the platform preferential information without any manual operation of the advertiser to be supported, the use efficiency of the platform preferential information is effectively improved, and the platform preferential information is directly related to the loss of the platform, so that the loss of the platform can be controlled within a preset range through the platform preferential information for the platform, the condition of large loss of the platform can be effectively avoided, the quality and effect of the advertisement bidding supporting operation are improved, and the practicability of the method is further improved, is beneficial to the popularization and the application of the market.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a schematic diagram illustrating an application scenario of an advertisement bidding method according to an exemplary embodiment of the present application;

FIG. 2 is a flowchart illustrating a method for bidding for advertisements according to an exemplary embodiment of the present application;

FIG. 3 is a schematic flow chart illustrating the process of obtaining original bid information provided by advertisers to be supported for target traffic when participating in bid for advertisements according to an exemplary embodiment of the present application;

fig. 4 is a schematic flowchart illustrating a process of determining target bidding information based on the platform offer information and the original bidding information according to an exemplary embodiment of the present application;

FIG. 5 is a schematic illustration of a target bid distribution according to an exemplary embodiment of the present application;

FIG. 6 is a flowchart illustrating another method of bidding for advertisements according to an exemplary embodiment of the present application;

FIG. 7 is a schematic diagram illustrating an advertisement bidding method according to an exemplary embodiment of the present application;

FIG. 8 is a flowchart illustrating a method for bidding for advertisements according to another exemplary embodiment of the present application;

fig. 9 is a schematic structural diagram of an advertisement bidding apparatus according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of an electronic device corresponding to the advertisement bidding apparatus shown in fig. 9;

fig. 11 is a schematic structural diagram of an advertisement bidding apparatus according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of an electronic device corresponding to the advertisement bidding apparatus shown in fig. 11.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a" and "an" typically include at least two, but do not exclude the inclusion of at least one.

It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.

It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of additional like elements in the article or system in which the element is included.

In addition, the sequence of steps in each method embodiment described below is only an example and is not strictly limited.

Definition of terms:

every thousand impressions (Revenue Per mill, RPM for short) are used to identify the estimates for every 1000 impressions.

The commodity transaction total (Gross Merchandisc Value, GMV for short) is used for identifying the transaction total within a certain time period.

BCB: budget Constrained scaling, a class of constraint optimization problems and methods for solving the same.

In order to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the following briefly describes the related art:

for an advertisement promotion platform, in a real-time bidding advertisement system, an advertisement slot often selects exposed specific advertisement content in a bidding manner, that is, an advertiser with a high bid can obtain an advertisement promotion opportunity. In the real-time bidding advertisement system, the bidding mechanism of the advertisement usually needs to target short-term efficiency indexes such as show (revnue Per mill, abbreviated as RPM) and total commodity transaction (Gross merchandisc Value, abbreviated as GMV), and all advertisers are treated with the same idea.

In practical applications, the platform often needs to lose a certain short-term efficiency index to support a certain group or a certain type of advertisers, such as: new advertisers or pre-churn advertisers need to be supported as customers grow to improve retention. At present, when a platform supports a specific advertiser, the platform often directly issues a certain amount of coupons to an account of the advertiser, and the purpose of supporting the advertiser is achieved through the coupons. However, the above implementation has the following drawbacks:

(1) because the way that the platform issues the coupons for each advertiser is simple and rough, the platform easily causes a serious Martha effect on the supporting operation of the advertisers, namely the supporting strength obtained by the head advertiser in the list of the advertisers is far greater than that of the middle-long-tail advertisers.

(2) The platform loss is uncontrollable, and the platform loss is not taken as a limiting factor in the conventional coupon support method, so that the fluctuation of the platform loss is easy to cause.

(3) Because advertisement bidding is a complex process, after the advertiser acquires the coupon, different benefits can be acquired by using the coupon in different ways; in addition, because the coupon is sent from the platform to the account of the advertiser, the coupon can be used only by manual operation of the advertiser, so that a link from issuing to using the coupon is easy to be long, and the problems of low coupon use efficiency and poor platform controllability exist.

In order to solve the above technical problem, the present embodiment provides an advertisement bidding method, an apparatus and a computer storage medium, wherein an execution subject of the method may be an advertisement bidding device, and the advertisement bidding device is communicatively connected to a client/requester to implement an advertisement bidding operation, and in particular, refer to fig. 1:

the client/request end may be any computing device with certain data transmission capability, and in particular, the client/request end may be a mobile phone, a personal computer PC, a tablet computer, a set application program, or the like. Further, the basic structure of the client may include: at least one processor. The number of processors depends on the configuration and type of client. The client may also include a Memory, which may be volatile, such as RAM, or non-volatile, such as Read-Only Memory (ROM), flash Memory, etc., or may include both types. The memory typically stores an Operating System (OS), one or more application programs, and may also store program data and the like. In addition to the processing unit and the memory, the client includes some basic configurations, such as a network card chip, an IO bus, a display component, and some peripheral devices. Alternatively, some peripheral devices may include, for example, a keyboard, a mouse, a stylus, a printer, and the like. Other peripheral devices are well known in the art and will not be described in detail herein.

The advertisement bidding device is a device that can provide an advertisement bidding service in a network virtual environment, and generally refers to a device that performs information planning and advertisement bidding operations using a network. In physical implementation, the advertisement bidding device can be any device capable of providing a computing service, responding to a service request for advertising bidding, and performing an advertisement bidding service based on the service request, such as: can be cluster servers, regular servers, cloud hosts, virtual centers, and the like. The advertisement bidding device mainly comprises a processor, a hard disk, a memory, a system bus and the like, and is similar to a general computer framework.

In the embodiment, the client/requester may be connected to the advertisement bidding device through a network, and the network connection may be a wireless or wired network connection. If the client/requester is communicatively connected to the advertisement bidding device, the network format of the mobile network may be any one of 2G (gsm), 2.5G (gprs), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G + (LTE +), WiMax, 5G, and 6G.

In this embodiment of the present application, a client/a request end may obtain original bid information provided for a target traffic when participating in an advertisement bid with each advertiser to be supported, and specifically, this embodiment does not limit a specific implementation manner of obtaining the original bid information provided for the target traffic by the request end. In other examples, the original bid information provided for the target traffic may be stored in a third device, which is in communication with the requester, and the original bid information provided for the target traffic may be actively or passively obtained by the third device.

After the original bidding information provided for the target traffic is acquired, the original bidding information provided for the target traffic can be sent to the advertisement bidding device, so that the advertisement bidding device can perform bidding support operation on the advertiser to be supported according to the original bidding information provided for the target traffic.

The advertisement bidding device is used for acquiring original bidding information provided for target flow when an advertiser to be supported participates in advertisement bidding; the target traffic may be 1-granularity traffic, 24-hour traffic, 12-hour traffic, or traffic in a preset time period, and in order to support an advertisement bidding operation of an advertiser to be supported, platform benefit information provided by a platform for the advertiser to be supported may be determined, specifically, the advertisement platform may provide certain platform benefit information for the advertiser to be supported, it should be noted that different advertisers to be supported may correspond to the same or different platform benefit information, in some examples, the same platform benefit information may be allocated to different advertisers, and the platform benefit information may include coupon information, discount card information, and the like.

After the platform preferential information and the original bidding information are obtained, the platform preferential information and the original bidding information can be analyzed and processed to determine target bidding information, the target bidding information is often larger than the original bidding information, then advertisement bidding operation can be performed based on the target bidding information, and therefore the method effectively achieves that when an advertiser to be supported performs advertisement bidding operation based on the original bidding information, the advertisement bidding operation is automatically performed for the advertiser to be supported based on the platform, and finally the advertisement bidding operation can be performed with the target bidding information higher than the original bidding information, so that the success rate and the effect of the advertisement bidding operation can be improved.

According to the technical scheme provided by the embodiment, original bidding information provided for target flow when an advertiser to be supported participates in advertising bidding is obtained; the platform preferential information provided by the platform for the advertiser to be supported is determined, then the target bidding information is automatically determined based on the platform preferential information and the original bidding information, and the advertisement bidding operation is carried out based on the target bidding information, so that the advertisement supporting operation for the advertiser to be supported can be automatically carried out based on the platform preferential information without any manual operation of the advertiser to be supported, the use efficiency of the platform preferential information is effectively improved, and the platform preferential information is directly related to the loss of the platform, so that the loss of the platform can be controlled within a preset range through the platform preferential information for the platform, the condition of large loss of the platform can be effectively avoided, the quality and effect of the advertisement bidding supporting operation are improved, and the practicability of the method is further improved, is beneficial to the popularization and the application of the market.

Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The features of the embodiments and examples described below may be combined with each other without conflict between the embodiments. In addition, the sequence of steps in each method embodiment described below is only an example and is not strictly limited.

FIG. 2 is a flowchart illustrating a method for bidding for advertisements according to an exemplary embodiment of the present application; referring to fig. 2, the embodiment provides an advertisement bidding method, and an implementation subject of the method may be an advertisement bidding apparatus, and when the method is implemented specifically, the advertisement bidding apparatus may be implemented as an advertisement demand platform or an advertisement transaction platform, and it is understood that the advertisement bidding apparatus may be implemented as software or a combination of software and hardware. Specifically, the advertisement bidding method may include:

step S201: and obtaining original bidding information provided for target flow when the advertiser to be supported participates in the advertisement bidding.

Step S202: and determining platform preferential information provided by the platform for the advertiser to be supported.

Step S203: and determining target bidding information based on the platform preference information and the original bidding information, wherein the target bidding information is larger than the original bidding information.

Step S204: and performing advertisement bidding operation based on the target bidding information.

The following is a detailed description of specific implementation manners and implementation effects of the above steps:

When each advertiser carries out advertisement bidding operation, each advertiser can place the advertisement requirement on a demand side platform, the internet media places the advertisement flow resource of the advertiser into an advertisement trading platform, the advertisement trading platform can complete bidding purchasing operation on the advertisement flow resource, and then the advertisement demand platform is in butt joint with the advertisement trading platform to complete bidding purchasing. Specifically, when the internet media receives an access request of a user, a request for placing an advertisement is sent to an advertisement trading platform, the advertisement trading platform obtains advertisement bids of a plurality of different advertisers from at least one demand party platform, and meanwhile, the advertisement to be placed is determined according to the advertisement bids and is placed in the internet media.

As can be seen from the above, in the process of bidding for the advertisement by each advertiser, the advertisement bidding apparatus (which may correspond to the above advertisement trading platform) can obtain the original bidding information provided by each advertiser to be supported for the target traffic when participating in the advertisement bidding, where the target traffic may be any one of the following: the flow rate corresponding to 1 user click operation, the flow rate corresponding to a preset time period (for example, the flow rate corresponding to 12 hours, the flow rate corresponding to 24 hours, and the flow rate corresponding to 1 hour), and the flow rate corresponding to the click operations of a preset number of users (the flow rate corresponding to 10 user click operations, the flow rate corresponding to 100 user click operations, the flow rate corresponding to 1000 user click operations, and the like). It will be appreciated that the same or different raw bid information may be presented when different advertisers bid on targeted traffic.

In addition, when each advertiser (including the advertiser to be supported who needs to support and the ordinary advertiser who does not need to support) bids on the target flow, in order to realize the support operation of the advertiser to be supported, the original bidding information provided for the target flow when the advertiser to be supported participates in the advertisement bidding can be obtained, firstly, the advertiser to be supported included in all the advertisers can be identified, the original bidding information provided for the target flow when the advertiser to be supported participates in the advertisement bidding can be stored in a preset area or preset equipment (for example, a demand side platform), and at this time, the original bidding information provided for the target flow by the advertiser to be supported can be obtained by accessing the preset area or the preset equipment.

After the original bidding information provided by the advertiser to be supported is acquired, in order to realize the bidding support operation of the advertiser to be supported, the platform (which may be an advertisement transaction platform) may provide corresponding platform discount information for each advertiser to be supported, where the platform discount information may be coupon information, discount coupon information, and the like, and when the platform provides corresponding platform discount information for each advertiser to be supported, different advertisers may correspond to the same or different platform discount information.

It should be noted that the platform benefit information is related to the loss that the platform can bear, and can be stored in the platform, and after the platform provides the platform benefit information for the advertiser to be supported, the platform benefit information does not need to be sent to the corresponding advertiser to be supported, so that the advertisement supporting operation of the advertiser to be supported can be automatically performed without manual participation of the advertiser, and thus the problems that in the prior art, the coupon is long in link from issuing to using, and the coupon use efficiency is low are effectively solved.

In addition, the specific obtaining manner of the platform benefit information corresponding to the advertiser to be supported is not limited in this embodiment, in some examples, the platform benefit information may be provided by the platform for the advertiser to be supported in advance, after the platform provides corresponding platform benefit information for each advertiser to be supported in advance based on a preset rule, the identity of the advertiser to be supported and the platform benefit information may be stored in a preset area of the platform in an associated manner, after the original bidding information provided by the advertiser to be supported for the target traffic is obtained, the identity of the advertiser to be supported may be obtained first, and then the preset area is accessed based on the identity, so that the platform benefit information provided by the platform for the advertiser to be supported may be determined.

In other examples, the platform benefit information may be distributed in real time by the platform according to the feature information of the advertiser to be supported, at this time, after the original bidding information provided by the advertiser to be supported for the target traffic is obtained, the identity and the support strength feature of the advertiser to be supported may be obtained first, wherein the support strength feature may be obtained by analyzing and processing parameters of the advertiser to be supported, such as the activity degree of the platform, the product transaction amount, and the product transaction amount in a preset time period, and after the identity and the support strength feature are obtained, the identity and the support strength feature may be analyzed and processed, so that the platform benefit information provided by the platform for the advertiser to be supported may be determined.

Specifically, a machine learning model for determining that the platform provides the platform preference information for the advertiser to be supported is trained in advance, and after the identity and the supporting strength characteristics are obtained, the identity and the supporting strength characteristics can be input into the machine learning model, so that the platform preference information output by the machine learning model can be obtained. Or, a preset rule or a preset algorithm for determining that the platform provides the platform benefit information for the advertiser to be supported is pre-configured, and after the identity and the support strength characteristic are obtained, the identity and the support strength characteristic can be analyzed and processed by using the preset rule or the preset algorithm, so that the platform benefit information provided by the platform for the advertiser to be supported can be determined.

For any implementation manner of determining the platform benefit information provided by the platform for the advertiser to be supported, the platform can provide corresponding platform benefit information for the advertiser to be supported based on a preset rule or by using a preset algorithm, and the preset rule or the preset algorithm can be flexibly adjusted and set based on the requirements of users or platforms, so that the determination manner of the platform benefit information is flexible and changeable for each advertiser to be supported, and appropriate support operation of the same degree can be performed for most advertisers to be supported, thereby effectively avoiding the situation that the support operation of the advertisers easily causes serious Martian effect.

Because the platform benefit information is used for identifying that the platform supports the advertiser to be supported, after the platform benefit information and the original bidding information are obtained, the platform benefit information and the original bidding information can be analyzed and processed, so that the target bidding information can be determined, and the obtained target bidding information is larger than the original bidding information, wherein the platform benefit information can have different expression forms, and when the platform benefit information is a parameter which has the same attribute and the same quantity unit as the original bidding information, the target bidding information can be the sum of the platform benefit information and the original bidding information, for example: the original bidding information is 1 yuan/flow, the platform benefit information may be 0.2 yuan/flow, and in this case, the target bidding information may be (1+0.2) yuan/flow which is 1.2 yuan/flow.

In other examples, the platform offer information may be a value greater than 1, and in this case, the target bid information may be a product value of the platform offer information and the original bid information, for example, the original bid information is 1 element/flow, and the platform offer information may be 1.2, and in this case, the target bid information may be (1 × 1.2) element/flow — 1.2 element/flow.

In still other examples, the platform offer information may be a value greater than zero and less than 1, and in this case, the target bid information may be a ratio of the original bid information to the platform offer information, for example, the original bid information is 1 element/flow, and the platform offer information may be 0.8, and in this case, the target bid information may be (1/0.8) element/flow-1.25 element/flow.

As can be seen from the above, when the platform offer information has different expression forms, different implementation manners may be adopted to determine the target bid information, and of course, a person skilled in the art may also analyze the original bid information and the platform offer information in other manners to determine the target bid information, as long as the accuracy and reliability of obtaining the target bid information can be ensured, which is not described herein again.

After the target bidding information is acquired, the advertisement bidding operation can be performed based on the target bidding information, so that the supporting operation of the advertisement bidding behavior of the advertiser to be supported is realized.

In some examples, during or after the supporting operation of the advertisement bidding behavior of the advertiser to be supported, the supporting operation of the platform for the advertiser to be supported may make the advertiser to be supported have no perception, and at this time, for the advertiser to be supported, the specific perception may be: when the advertisement bidding operation is carried out through the original bidding information, the promotion effect and the income which are beyond the promotion effect and the income which can be brought by the original bidding information can be obtained on the platform, namely, the better promotion effect and the income can be obtained, thereby being beneficial to improving the retention probability of the advertiser to be supported on the platform.

In other examples, after the advertisement bidding operation is performed based on the target bidding information, the platform can make the advertiser to be supported aware of the support operation, at this time, in the process of or after the advertisement bidding operation is performed based on the target bidding information, support prompt information corresponding to the target bidding information can be generated, the support prompt information is used for prompting the advertiser to be supported that the support operation has been performed for the advertiser, specifically, the support prompt information can also include support strength information, and the support strength information can be embodied by a difference value between the target bidding information and the original bidding information, a ratio of the target bidding information to the original bidding information, and the like; after the supporting prompt message is generated, the supporting prompt message can be sent to the advertiser to be supported, so that the advertiser to be supported can sense the active supporting operation of the platform, the retention probability of the advertiser to be supported on the platform can be improved, and the development of the platform is facilitated.

According to the advertisement bidding method provided by the embodiment, the platform preferential information provided by the platform for the advertiser to be supported is determined by acquiring the original bidding information provided by the advertiser to be supported for the target flow when the advertiser to be supported participates in the advertisement bidding, and because the platform preferential information is related to the platform loss, when the advertisement supporting operation is carried out based on the platform preferential information, the platform loss is conveniently enabled to be within a controllable range, and meanwhile, the condition that the loss of the advertisement platform is large is effectively avoided; in addition, different advertisers to be supported can correspond to the same or different platform preferential information, the situation that the advertiser is easy to cause serious Martian effect when supporting operation is carried out can be avoided when the same platform preferential information is distributed to different advertisers to be supported, after the original bidding information and the platform preferential information are obtained, the target bidding information can be automatically determined based on the platform preferential information and the original bidding information, and the advertisement bidding operation is carried out based on the target bidding information, so that the platform preferential information can be automatically used without manual participation of the advertiser in the bidding process of the advertiser, the problems that the coupon is long in the link from issuing to using and the coupon using efficiency is low in the prior art can be effectively solved, and the flexibility and the reliability of the advertisement bidding supporting operation are further ensured, the practicability of the method is improved, and the method is favorable for popularization and application in the market.

FIG. 3 is a schematic flow chart illustrating the process of obtaining original bid information provided by advertisers to be supported for target traffic when participating in bid for advertisements according to an exemplary embodiment of the present application; on the basis of the foregoing embodiment, referring to fig. 3, the embodiment provides an implementation manner for obtaining original bidding information through an estimated click rate and an estimated conversion rate of a target traffic, and specifically, the obtaining of the original bidding information provided for the target traffic when an advertiser to be supported participates in an advertisement bidding in the embodiment may include:

step S301: advertisers to be supported are obtained from a plurality of advertisers.

The advertisers to be supported can be new advertisers, advertisers with loss risk, advertisers who have lost and are not active enough, and the like, and particularly, the advertisers to be supported can be determined by analyzing and processing based on subscription information between each advertiser and a platform and activity degree on the platform.

Because the common advertiser does not need to carry out the supporting operation, in order to realize the advertisement supporting operation of the advertiser to be supported which needs to be supported, a plurality of advertisers participating in the advertisement bidding operation can be obtained firstly, and then the advertiser to be supported is obtained from the plurality of advertisers. In some examples, obtaining an advertiser to be supported among a plurality of advertisers may include: acquiring a preset rule or a machine learning model for determining advertisers to be supported, and determining subscription information between each advertiser to be supported and a platform and behavior data on the platform; and analyzing and processing the subscription information and the behavior data by using a preset rule or a machine learning model so as to identify the advertisers to be supported, wherein the advertisers are included in the plurality of advertisers.

In other examples, the advertiser to be supported may be confirmed in advance by an operator, at this time, the identification of the advertiser to be supported may be stored in a preset area, after the original bidding information of the advertiser to be supported is obtained, the identification of the advertiser to be supported may be determined, and then the advertiser to be supported included in the plurality of advertisers may be obtained by accessing the preset area through the identification of the advertiser to be supported.

Step S302: when the advertiser to be supported participates in the advertisement bidding, the target flow needing to be supported is determined.

For the advertiser to be supported, the corresponding flow rate when the advertiser participates in the advertisement bidding can be multiple, that is, one advertiser to be supported can participate in multiple advertisement bidding projects based on the requirement, and for all the advertisement bidding projects participating in the advertisement bidding projects, the following situations can be met: (1) the successful advertisement bidding items can be bid without supporting operation; (2) a support operation is required to be able to bid on a successful advertisement bid item. For the advertisement bidding item in the above-mentioned case (1), since the advertiser to be supported can successfully bid to obtain the ad slot, the supporting operation for the advertisement bidding item is not needed; for the advertisement bidding item in the above (2) case, the support operation can affect whether the bidding of the advertisement bidding item is successful, that is, the support operation has practical significance, and at this time, the support operation can be performed on the advertisement bidding item in the above (2) case.

It should be noted that the bid terms of the advertisement in which the advertiser to be supported participates may also include bid terms of the advertisement that will not succeed, and specifically may include: the method comprises the steps that an advertisement bidding project which cannot be successfully bid under the condition of non-support and an advertisement bidding project which cannot be successfully bid under the condition of support are not supported, and for the advertisement bidding project which cannot be successfully bid, because an advertiser to be supported does not bid successfully, even if the advertisement bidding project of the advertiser to be supported is supported, because the bidding operation of the advertiser to be supported is not successful, the support operation at the moment has no practical significance, and no loss occurs on a platform, so that the application scene of supporting the advertiser to be supported does not need to be considered for the advertisement bidding project which cannot be successfully bid.

As can be seen from the above, for the advertiser to be supported, the supporting operation is not performed on all the participating advertisement bidding behaviors or advertisement bidding items, but is performed on some specific advertisement bidding behaviors or advertisement bidding items, so that the actual meaning of the supporting operation can be improved. In order to support certain specific advertisement bidding operations, when an advertiser to be supported participates in an advertisement bidding, a target flow rate to be supported can be determined, and the target flow rate to be supported corresponds to a specific advertisement bidding item or advertisement bidding behavior in which the advertiser to be supported participates.

The specific implementation manner of determining the target flow to be supported is not limited in this embodiment, and in some examples, the target flow to be supported may be predetermined by platform operation and maintenance personnel, at this time, the platform operation and maintenance personnel may store different advertisers to be supported and the corresponding target flow to be supported in a preset region, and the target flow to be supported may be obtained by accessing the preset region, so that the accuracy and reliability of determining the target flow to be supported are effectively ensured.

In still other examples, the target traffic to be supported may be determined by a real-time analysis process, and in this case, when the advertiser to be supported participates in the bid, determining the target traffic to be supported may include: acquiring all preset flow of advertisers to be supported participating in advertisement bidding; identifying all first preset flows which cannot bid successfully in all the preset flows; and determining all the first preset flow rates as target flow rates.

In particular, all traffic for each advertiser participating in an ad bid may be stored in the platform in association with the advertiser's identification, and, therefore, after the platform acquires the original bidding information provided by the advertiser to be supported, all preset flow correlated with the identity of the advertiser to be supported can be acquired by accessing a preset area, wherein, all the preset flows can include all the first preset flows which can not be bid successfully and all the second preset flows which can be bid successfully, since all of the second preset flows can bid successfully without a backup operation, and in order to reduce the loss of the platform, no support operation is required for the second preset flow rate, and since the first preset flow rate cannot bid successfully, a support operation is required, and all the first preset flows can be determined as target flows, so that the accuracy and reliability of determining the target flows are effectively ensured.

It should be noted that after all the preset flows are obtained, in order to accurately identify all the first preset flows which cannot be bid successfully in all the preset flows, bid success rates corresponding to all the preset flows can be obtained, and the bid success rates are often related to original bid information provided by advertisers to be supported and bid information provided by other competitive advertisers; after the bidding success rate of each preset flow is obtained, the bidding success rate can be analyzed and compared with a preset threshold (80%, 90%, 95% and the like), when the bidding success rate is greater than or equal to the preset threshold, the bidding success rate of the preset flow is higher, and the preset flow can be determined as a second preset flow; when the bidding success rate is smaller than the preset threshold, the bidding success rate of the preset flow is low, and the preset flow can be determined as the first preset flow, so that the accuracy and reliability of determining the first preset flow are ensured, and the accuracy of determining the target flow based on the first preset flow is further improved.

Step S303: and obtaining the estimated click rate and the estimated conversion rate corresponding to the target flow.

After the target flow is obtained, the target flow can be analyzed to obtain an estimated click rate and an estimated conversion rate corresponding to the target flow, where the estimated click rate is a ratio of estimated times to displayed times of a certain content on a web page, and the estimated click rate can reflect the attention degree of the certain content on the web page and is often used to measure the attraction degree of an advertisement. The estimated conversion rate is an estimated proportion of the conversion formed by the netizens who click the advertisement to enter the promotion website, and can reflect the direct income of the advertisement.

Specifically, the embodiment does not limit the specific implementation manner of obtaining the estimated click rate and the estimated conversion rate corresponding to the target flow rate, in some examples, an association relationship exists between the target flow rate and the estimated click rate and the estimated conversion rate, the association relationship and the estimated click rate and the estimated conversion rate corresponding to the association relationship may be stored in a preset area, and at this time, the estimated click rate and the estimated conversion rate corresponding to the target flow rate may be obtained by accessing the preset area.

In other examples, a preset algorithm and a machine learning model for determining the estimated click rate and the estimated conversion rate are configured in advance, and after the target flow is obtained, the target flow can be analyzed and processed by using the preset algorithm and the machine learning model, so that the estimated conversion rate and the estimated conversion rate corresponding to the target flow can be obtained.

In still other examples, obtaining the predicted click rate and the predicted conversion rate corresponding to the target traffic may include: acquiring a historical behavior portrait of a historical user for a target flow; and determining the estimated click rate and the estimated conversion rate corresponding to the target flow based on the historical behavior portrait.

For the preset flow rate, the click rate and the conversion rate of the preset flow rate within the preset time period are frequently repeatedly changed, for example: the click rate and the conversion rate corresponding to the preset flow are often the same as or similar to those corresponding to the preset flow in yesterday, so that the estimated click rate and the estimated conversion rate corresponding to the target flow can be determined based on historical operating data.

In order to accurately determine the estimated click rate and the estimated conversion rate corresponding to the target flow, a historical behavior picture of a historical user for the target flow can be acquired, the historical user can be all users who operate the target flow within a preset historical time period (within 1 day, 1 week or 1 month of history), the historical behavior picture of the historical user can be stored in a preset area in association with the target flow, then the historical behavior picture of the historical user for the target flow can be acquired by accessing the preset area, and the historical behavior picture can include information such as historical browsing records, historical click records and attribute information of the historical user.

After the historical behavior portrait is obtained, the historical behavior portrait and the target flow can be analyzed and processed to determine the estimated click rate and the estimated conversion rate corresponding to the target flow, in the concrete implementation, a preset rule or a machine learning model used for determining the estimated click rate and the estimated conversion rate corresponding to the target flow is preset, after the historical behavior portrait and the target flow are obtained, the historical behavior portrait and the target flow can be analyzed and processed by the preset rule or the machine learning model, and therefore the estimated click rate and the estimated conversion rate corresponding to the target flow can be stably obtained.

Step S304: and acquiring original bidding information provided by the advertiser to be supported based on the estimated click rate and the estimated conversion rate.

After the estimated click rate and the estimated conversion rate are obtained, the advertiser to be supported can perform bidding operation based on the estimated click rate and the estimated conversion rate, so that original bidding information provided by the advertiser to be supported can be obtained. It should be noted that different advertisers to be supported can provide different bidding information based on the estimated click rate and the estimated conversion rate, and generally, the higher the estimated click rate is, the higher the obtained bidding information is, and the higher the estimated conversion rate is, the higher the obtained bidding information is.

In the embodiment, the advertiser to be supported is obtained from the advertisers, when the advertiser to be supported participates in advertisement bidding, the target flow rate to be supported is determined, then the estimated click rate and the estimated conversion rate corresponding to the target flow rate are obtained, and the original bidding information provided by the advertiser to be supported is obtained based on the estimated click rate and the estimated conversion rate, so that the original bidding information provided by the advertiser to be supported is effectively obtained based on the estimated click rate and the estimated conversion rate, and the accuracy and the reliability of obtaining the original bidding information are further ensured.

Fig. 4 is a schematic flowchart of determining target bidding information based on platform offer information and original bidding information according to an exemplary embodiment of the present application; on the basis of the foregoing embodiment, referring to fig. 4, this embodiment provides another implementation manner for determining target bid information, and specifically, the determining target bid information based on platform offer information and original bid information in this embodiment may include:

step S401: and acquiring an advertisement putting index corresponding to the advertiser to be supported.

When the advertisement support operation is performed on the advertiser to be supported, the support indexes concerned by different advertisers can be different, for example: the exposure of some advertisers paying attention to the advertisements, the click rate of some advertisers paying attention to the advertisements and the volume of the deals of some advertisers paying attention to the advertisements; therefore, in order to satisfy the focus of different advertisers, an advertisement placement index corresponding to the advertiser to be supported may be obtained, where the advertisement placement index includes at least one of the following: the advertisement putting method comprises an exposure index, a click index and a deal index, wherein the exposure index is used for identifying the exposure of the advertisement to be put, the click index is used for identifying the click amount of the advertisement to be put, and the deal index is used for identifying the deal amount promoted based on the advertisement to be put.

Step S402: and determining preferential distribution information corresponding to the target flow based on the platform preferential information and the advertisement putting indexes.

After the platform preferential information is acquired, the advertisement bidding operation of an advertiser to be supported can be supported based on the platform preferential information, in order to acquire larger support benefits and effects, the platform preferential information can be applied according to certain distribution, specifically, after the platform preferential information and the advertisement delivery indexes are acquired, the platform preferential information and the advertisement delivery indexes can be analyzed and processed to determine preferential distribution information corresponding to target traffic, and the preferential distribution information is used for identifying specific information for supporting the target traffic at different moments.

In some examples, the embodiment provides an implementation manner for analyzing and processing platform benefit information and advertisement delivery indexes by using a preset rule and a machine learning model, so as to obtain benefit distribution information, and specifically, determining, based on the platform benefit information and the advertisement delivery indexes, the benefit distribution information corresponding to a target traffic may include: the method comprises the steps of obtaining a machine learning model which is trained in advance and used for determining preferential distribution information, and inputting the platform preferential information, the advertisement putting index and the target flow into the machine learning model after obtaining the platform preferential information, the advertisement putting index and the target flow, so that the preferential distribution information of the target flow output by the machine learning model can be obtained.

In still other examples, since the advertisement delivery indicator corresponds to a certain historical distribution information, and the support quality and effect have a direct relationship with the advertisement delivery indicator, this embodiment provides an implementation manner for determining the offer distribution information based on the historical distribution information corresponding to the advertisement delivery indicator, specifically, determining the offer distribution information corresponding to the target traffic based on the platform offer information and the advertisement delivery indicator may include: acquiring historical distribution information of advertisement putting indexes; and determining preferential distribution information corresponding to the target flow based on the platform preferential information and the historical distribution information.

Since the advertisement placement indicators focused on by different advertisers may be different, the distribution or variation trend of the advertisement placement indicators in a short period is often the same or similar to the advertisement placement indicators, for example: yesterday's distribution and trend of change of the advertising placement indicators are similar to those of the previous day. Therefore, in order to enable the benefit of supporting the advertiser to be supported to be larger, the historical distribution information of the advertisement putting index can be obtained, and the historical distribution information can be obtained by analyzing and processing the historical data of the advertisement putting index; after the platform benefit information and the historical distribution information are acquired, the platform benefit information and the historical distribution information may be analyzed to determine the benefit distribution information corresponding to the target traffic, and in some examples, the benefit distribution information corresponding to the target traffic may be the same as or similar to the historical distribution information of the advertisement delivery indicator. As shown in fig. 5, when the quality and effect of the advertisement placement indicator are high, a high supporting strength can be given to the advertiser to be supported; when the quality and the effect of the advertisement putting index are lower, the lower supporting strength can be provided for the advertiser to be supported.

In other examples, referring to fig. 5, since the benefit distribution information is composed of a plurality of sub-benefit information, the embodiment provides an implementation manner for obtaining the benefit distribution information by determining the plurality of sub-benefit information, specifically, determining the benefit distribution information corresponding to the target traffic based on the platform benefit information and the advertisement delivery indicator may include: determining a plurality of sub-offer information corresponding to the target traffic on the traffic granularity based on the advertisement delivery index and the platform offer information; and determining the preferential distribution information corresponding to the target flow based on the plurality of sub-preferential information.

The target flow rate may be a flow rate of a single granularity or a flow rate of multiple granularities, for example, when the target flow rate is a flow rate corresponding to a single click operation, the target flow rate at this time is a flow rate of a single granularity; when the target flow rate is a flow rate corresponding to a plurality of click operations, the target flow rate at this time is a flow rate of a plurality of granularities. Therefore, the target traffic may correspond to one piece of sub-benefit information or a plurality of pieces of sub-benefit information, and in an actual application process, the target traffic often includes traffic of a plurality of granularities, and at this time, the target traffic corresponds to a plurality of pieces of sub-benefit information, and the plurality of pieces of sub-benefit information may constitute one piece of benefit distribution information.

In order to accurately determine the benefit distribution information corresponding to the target traffic, after the advertisement delivery index and the platform benefit information are obtained, the advertisement delivery index and the platform benefit information may be analyzed, specifically, a preset rule and a pre-trained machine learning model may be utilized to analyze the advertisement delivery index and the platform benefit information to determine a plurality of sub-benefit information corresponding to the target traffic on the traffic granularity, and then the benefit distribution information corresponding to the target traffic may be determined based on the plurality of sub-benefit information.

In another example, this embodiment provides an implementation manner for determining a plurality of sub-offer information by establishing a constraint optimization problem, and specifically, the determining a plurality of sub-offer information corresponding to target traffic on traffic granularity based on an advertisement delivery index and platform offer information in this embodiment may include: constructing a constraint optimization problem by taking the platform discount information as constraint, the advertisement delivery index as an optimization target and the sub-discount information on the flow granularity as variables; based on a constraint optimization problem, a plurality of sub-offer information corresponding to a target traffic in a traffic granularity is determined.

The total loss of the platform is related to the platform preferential information provided by the platform for each advertiser to be supported, specifically, the sum of all the platform preferential information provided by the platform for all the iterative support advertisers is the total loss of the platform, and in order to enable the platform loss to be within a controllable range, the platform preferential information can be used as a constraint. In order to enable the supporting operation performed for the advertiser to be supported to obtain higher profit and effect, the platform preferential information is used as the constraint, the advertisement putting index is used as the optimization target, and the sub-preferential information on the traffic granularity is used as the variable, so that the constraint optimization information used for determining the preferential distribution information is constructed.

After the constraint optimization problem is established, sub-offer information corresponding to target traffic on a traffic granularity may be determined based on the constraint optimization problem, and the sub-offer information at different times may be the same or different, for example: for the target traffic of about 3 am, since the amount of users about 3 am is small, the obtained promotion income and effect are low, and therefore, the sub-benefit information included in the benefit distribution information can be configured to be low support strength, for example: the offer sub-offer information may be 0.1 yuan/flow. For target traffic of about 10 pm, since the amount of users is large at about 10 pm and the obtained promotion benefit and effect are high, the sub-benefit information included in the benefit distribution information can be configured to be high support strength, for example: the sub-offer information may be 0.5 yuan/flow. Therefore, on the premise that the platform loss can be within a controllable range, the method and the device effectively achieve the purpose that the plurality of sub-discount information which is most suitable for the to-be-supported advertiser and aims at the target flow are obtained, and further improve the accuracy of determining the plurality of sub-discount information.

It should be noted that, for any one of the above implementation manners of obtaining the offer distribution information, the obtained offer distribution information may include sub-offer information corresponding to a plurality of different time instants and different traffic flows, and a sum of all sub-offer information in the offer distribution information is less than or equal to the platform offer information, so that a situation of large platform loss can be effectively avoided.

Step S403: and determining target bidding distribution based on the discount distribution information and the original bidding information.

After the offer distribution information and the original bidding information are obtained, the offer distribution information and the original bidding information may be analyzed to determine a target bidding distribution, where the offer distribution information includes a plurality of sub-offer information, and therefore the target bidding distribution obtained based on the offer distribution information and the original bidding information also includes a plurality of sub-bidding information, specifically, the sub-bidding information may be a sum of the sub-offer information and the original bidding information, and the target bidding distribution may be obtained through the determined plurality of sub-bidding information, and in some examples, a variation trend of the target bidding distribution is the same as or similar to a variation trend of the offer distribution information, as shown in fig. 5.

In the embodiment, the advertisement delivery indexes corresponding to the advertisers to be supported are obtained, the preferential distribution information corresponding to the target flow is determined based on the platform preferential information and the advertisement delivery indexes, and the target bidding distribution is determined based on the preferential distribution information and the original bidding information, so that the accuracy and reliability of determining the target bidding distribution are effectively ensured, the quality and effect of supporting the advertisers to be supported can be ensured, the advertisement income and effect obtained based on the supporting operation can be improved to the greatest extent, and the stability and reliability of the advertisement bidding operation based on the target bidding distribution are further improved.

FIG. 6 is a flowchart illustrating another method of bidding for advertisements according to an exemplary embodiment of the present application; on the basis of the foregoing embodiment, referring to fig. 6, after determining the preferential distribution information corresponding to the target traffic, this embodiment further provides an implementation manner capable of flexibly adjusting the preferential distribution information based on the demand, so as to improve the quality and the effect of supporting the advertiser to be supported based on the preferential distribution information, and specifically, the method in this embodiment may further include:

step S601: and acquiring information smoothness of the preferential distribution information.

For the benefit distribution information, since the benefit distribution information can identify the distribution condition of using the platform benefit information, in order to ensure that the application of the platform benefit information is relatively smooth, after the benefit distribution information is acquired, the benefit distribution information may be analyzed to obtain the information smoothness corresponding to the benefit distribution information.

In some examples, obtaining the information smoothness of the offer distribution information may include: the curve corresponding to the preferential distribution information is acquired based on the preferential distribution information, and the curvature of the curve is determined, in general, the smaller the curvature is, the smoother the curve is, and the larger the curvature is, the smoother the curve is, so that after the curvature of the curve is acquired, the smoothness of the curve can be determined based on the curvature of the curve, and the smoothness of the curve is determined as the information smoothness of the preferential distribution information, so that the accurate reliability of determining the information smoothness is effectively realized.

In still other examples, obtaining information smoothness of offer distribution information may include: determining any two adjacent sub-discount information based on the discount distribution information; determining a discount information deviation between the two sub discount information; and determining the information smoothness of the preference distribution information based on the preference information deviation.

Specifically, since the offer distribution information may include a plurality of sub-offer information, in order to accurately obtain information smoothness of the offer distribution information, the offer distribution information may be analyzed and identified to determine any two adjacent sub-offer information, and it should be noted that one offer distribution information is often corresponding to a set of a plurality of groups of adjacent sub-offer information. And then, the two sub-discount information can be analyzed and processed to determine the discount information deviation between the two sub-discount information, and the discount information deviation is used for identifying the difference between the two adjacent sub-discount information.

Because one piece of preferential distribution information corresponds to a plurality of preferential information deviations, and the plurality of preferential information deviations can embody the information smoothness of the preferential distribution information, after the preferential information deviations are obtained, all adjacent preferential information deviations can be analyzed to determine the information smoothness of the preferential distribution information, and specifically, when the difference value between any two adjacent preferential information deviations is less than or equal to a preset threshold value, the preferential distribution information corresponding to the two preferential information deviations can be determined to be smooth; if the difference between any two preference information deviations is greater than the preset threshold, it can be determined that the preference distribution information corresponding to the two preference information deviations is not very smooth.

Step S602: and when the information smoothness is smaller than the preset smoothness, adjusting the preference distribution information based on the preset smoothness so as to improve the information smoothness of the preference distribution information.

After the information smoothness is obtained, the information smoothness and the preset smoothness can be analyzed and compared, when the information smoothness is smaller than the preset smoothness, the smoothness of the preference distribution information is lower, in order to enable the use of the platform preference information to be smoother and avoid the use of the platform preference information from being greatly floated, the preference distribution information can be adjusted based on the preset smoothness so as to improve the smoothness of the preference distribution information.

Specifically, the offer distribution information may include a preset parameter for adjusting smoothness of information, and at this time, adjusting the offer distribution information based on the preset smoothness may include: acquiring preset parameters corresponding to the preferential distribution information, wherein the preset parameters can change along with the change of the flow; the preset parameters are adjusted based on a preset smoothness, for example: the preset parameters can be increased or decreased to improve the information smoothness of the preferential distribution information.

In still other examples, when the smoothness of the information is greater than or equal to the preset smoothness, it indicates that the smoothness of the offer distribution information is higher, and at this time, when the platform offer information is applied based on the offer distribution information, the offer distribution information may be applied more smoothly or more smoothly, which is beneficial to improving the use effect of the platform offer information and obtaining higher advertisement revenue.

In this embodiment, by obtaining the information smoothness of the preference distribution information, when the smoothness of the preference distribution information is low, the preference distribution information may be adjusted to improve the information smoothness of the preference distribution information; when the smoothness of the preference distribution information is higher, the platform preference information can be directly applied based on the preference distribution information, so that the using effect of the platform preference information is effectively ensured, higher advertising revenue can be ensured, and the practicability of the method is further improved.

In specific application, the embodiment of the application provides an advertiser supporting method for a real-time bidding advertisement system from the viewpoint of a platform, and the supporting method can model the advertiser supporting problem into a constraint optimization problem, so that the advertisement putting effect of an advertiser to be supported can be optimized by taking platform loss as constraint. Specifically, referring to fig. 7, the method may include:

step 1: the real-time bidding advertisement system can acquire continuous user access flow.

Step 2: and analyzing and processing the user access flow by using a real-time prediction module in the real-time bidding advertisement system to obtain the estimated click rate (pctr) and the estimated conversion rate (pcvr).

For each obtained user access flow (Page View, PV for short), a real-time prediction module (or a real-time prediction model) in the real-time bidding advertisement system can process the user access flow and/or historical data, so as to obtain a predicted click rate (pctr) and a predicted conversion rate (pcvr), specifically, when the real-time prediction module obtains n types of user access flows, the prediction module performs prediction analysis on the n types of user access flows, so as to obtain the predicted click rate and the predicted conversion rate corresponding to the n types of user access flows, for example: the 1 st user access flow corresponds to pctr1 and pcvr1, the 2 nd user access flow corresponds to pctr2 and pcvr2, the 3 rd user access flow corresponds to pctr3 and pcvr3, the n-1 st user access flow corresponds to pctr n-1 and pcvr n-1, and the n th user access flow corresponds to pctr n and pcvr n.

And 3, step 3: and the advertiser to be supported can bid according to the estimated click rate (pctr) and the estimated conversion rate (pcvr) obtained by the real-time prediction module to obtain the original bidding information.

In order to realize the supporting operation for the advertisers to be supported, the platform can determine one or more advertisers as the advertisers to be supported according to a preset target or a preset rule, when the advertisers to be supported bid according to the estimated click rate and the estimated conversion rate, the original bidding information of the bidding is positively correlated with the estimated click rate and the estimated conversion rate, namely the higher the estimated click rate is, the higher the original bidding information is; the higher the estimated conversion rate, the higher the original bid information.

For example, after each advertiser to be supported obtains that the 1 st user access traffic corresponds to pctr1 and pcvr1, the 2 nd user access traffic corresponds to pctr2 and pcvr2, the 3 rd user access traffic corresponds to pctr3 and pcvr3, the n-1 st user access traffic corresponds to pctr n-1 and pcvr n-1, and the nth user access traffic corresponds to pctr n and pcvr n, the advertiser to be supported can bid based on pctr1 and pcvr1, so as to obtain original bid information bid 1; similarly, advertisers to be supported can bid on pctr2 and pcvr2, obtaining original bid information bid 2; bidding is carried out based on pctr3 and pcvr3, and original bidding information bid3 is obtained; bidding is carried out based on pctr n-1 and pcvr n-1 to obtain original bidding information bid n-1; bidding is performed based on pctr n and pcvr n, and original bid information bid is obtained.

And 4, step 4: and determining platform preferential information provided by the platform for each advertiser to be supported.

In order to realize the supporting operation of each advertiser to be supported, the platform can provide platform preferential information for each advertiser to be supported, in some examples, total loss information C which can be supported by the platform can be obtained first, quantity information N of the advertiser to be supported is determined, the platform preferential information provided by the platform for each advertiser to be supported is determined based on the quantity information N and the total loss information C, specifically, the platform preferential information can be the ratio of the total loss information to the quantity information, namely C is C/N, at the moment, the platform provides the same platform preferential information for each advertiser to be supported, and therefore the serious Martian's effect caused by the fact that different preferential information is provided for different advertisers can be effectively avoided.

And 5: and determining target bidding information corresponding to each advertiser to be supported based on platform preferential information provided by the platform for each advertiser to be supported and original bidding information provided by each advertiser to be supported.

Specifically, for the advertiser to be supported, when the advertiser to be supported participates in the advertisement bidding, the competitive capacity of the advertiser to the high-quality traffic can be effectively enhanced by adding one virtual coupon c (corresponding to the platform coupon information) on the basis of the original bidding information of the advertiser to be supported, and at this time, after the platform coupon information and the original bidding information are obtained, the sum of the platform coupon information and the original bidding information can be determined as the target bidding information.

For example, if the platform offer information corresponding to the advertiser 1 to be supported is c1 and the original bid information is bid1, it may be determined that the target bid information bid 1' bid1+ c 1. Similarly, the platform offer information corresponding to the advertiser 2 to be supported is c2, and when the original bid information is bid2, it may be determined that the target bid information bid 2' is bid2+ c 2. The platform offer information corresponding to the advertiser 3 to be supported is c3, and when the original bid information is bid3, it may be determined that the target bid information bid 3' bid3+ c 3. The platform offer information corresponding to the advertiser n-1 to be supported is c n-1, and when the original bid information is bid n-1, the target bid information bid n-1' bid n-1+ c n-1 can be determined. The platform offer information corresponding to the advertiser n to be supported is c n, and when the original bid information is bid n, the target bid information bid n ═ bid n + c n may be determined.

Step 6: an advertisement bidding module in the real-time bidding advertisement system acquires target bidding information corresponding to each advertiser to be supported and carries out advertisement bidding operation based on the target bidding information.

Specifically, after the advertisement bidding module obtains the target bidding information corresponding to each advertiser to be supported, all the target bidding information can be ranked from high to low, and then based on the ranking information, it can be determined which advertisers can bid successfully in the advertisement bidding operation, so that the advertisement exposure opportunity can be obtained. After the advertiser to be supported successfully bids, the fee deduction price after the advertiser is clicked can be calculated based on the advertisement exposure opportunity successfully bidding, then fee deduction operation is carried out based on the fee deduction price, in some examples, the fee deduction price after the advertiser is clicked can be calculated in a divalent charging mode, and when actual fee deduction operation is carried out, platform discount information (corresponding to the virtual coupon c) can be subtracted from the price of the target bidding information, and at the moment, the platform bears the cost of the platform discount information.

In addition, after the platform preferential information provided for each advertiser to be supported based on the platform, the original bidding information provided by each advertiser to be supported and the platform preferential information corresponding to each advertiser to be supported can be obtained, so that when the target bidding information corresponding to each advertiser to be supported is determined, in order to ensure the accuracy and reliability of the determination of the target bidding information, the advertiser supporting problem in the real-time bidding advertisement system is defined as the following constraint optimization problem:

in order to avoid the long tail effect of the platform on the supporting operation of each advertiser, the supporting operation can be performed for each advertiser to be supported, and the advertisement putting effect is maximized, specifically, a constraint optimization problem can be established for each advertiser to be supported, after the platform preferential information (corresponding to the platform loss) corresponding to each advertiser to be supported is determined, the supporting preferential target (including but not limited to exposure, click rate or volume of transaction) corresponding to the advertiser to be supported can be determined, then the platform loss can be used as the constraint, the advertisement putting effects such as exposure, click, volume and the like of the advertiser can be optimized as the optimization target, the sub-preferential information c of the flow granularity is used as the optimization variable, and the platform can reasonably distribute the virtual coupon c on the flow granularity under the constraint of the platform loss, so as to maximize the exposure, click, volume and the like of the advertiser, Click, bargain and the like.

Specifically, the constraint optimization problem can be solved by using a primal-dual (primal-dual) method to obtain a relational expression of the virtual coupon c about the traffic values of pctr, pcvr, and the like:

wherein i is the flow granularity which needs to be supported in one day, and x ⁱ For identifying whether a flow needs to be supported, x ⁱ ≥0，i＝1，2，3......，N；x ⁱ 1, i ≦ 1, 2, 3.. cndot, N; at x ⁱ When the number of the advertisements to be supported is 1, the supporting operation needs to be carried out for the flow, and generally, x is the number of the advertisers to be supported ⁱ ＝1；

Used for identifying the value brought by the supporting operation after the supporting operation is carried out on the advertiser to be supported,specifically, when the optimization target is pv,

when the optimization goal is the amount of clicks,

when the optimization objective is volume,

in order to enable the platform loss to be within a controllable range, the total loss C acceptable by the platform can be obtained, when the platform supports all the advertisers to be supported, the sum of the support information corresponding to all the advertisers to be supported is less than or equal to the total loss, and for each advertiser to be supported, the sum of the support information for the advertiser to be supported at different times in a day is less than or equal to the platform preference information provided by the platform for the advertiser to be supported, namely sigma _i x ⁱ *ΔE ⁱ C is less than or equal to c, wherein, Delta E ⁱ Sub-preference information, sigma, for a single advertiser to be supported for the platform _i x ⁱ *ΔE ⁱ The system comprises a platform, a platform and a plurality of advertisers, wherein the platform is used for identifying the sum of supporting for a single advertiser to be supported in one day, C is platform preferential information provided by the platform for each advertiser to be supported, and the sum of the platform preferential information corresponding to all the advertisers to be supported is less than or equal to the total loss C which can be accepted by the platform.

Since the application of the platform preferential information according to which distribution has a direct influence on the supporting effect of the advertiser, in order to obtain a better supporting effect, historical distribution information of advertisement delivery indexes can be acquired, and then preferential distribution information corresponding to the target traffic is determined based on the platform preferential information and the historical distribution information, specifically,

wherein p is ^* Is a preset parameter which can vary with the flow rate, p ^* May be a default value or may be as appropriateThe experience of the user is set, S _i Is as described above

Historical distribution information for identifying ad placement indicators,

and the preferential distribution information used for identifying the corresponding target flow is the same as the historical distribution information.

After acquiring the preferential distribution information, the platform preferential information can be applied based on the preferential distribution information, in order to enable the application of the platform preferential information distributed to the advertiser to be supported to be smoother, after acquiring the preferential distribution information, the smoothness of the preferential distribution information can be determined, and if the smoothness of the preferential distribution information is poor, the preset variable P in the relational expression of dynamically adjusting the virtual coupon c can be regulated and controlled by utilizing proportion (P), integral (I) and differential (D) ^* The smoothness of the preferential distribution information can be improved, and therefore smooth utilization of platform loss can be achieved.

According to the technical scheme provided by the application embodiment, each advertiser to be supported is independently modeled into an independent constraint optimization problem and is solved on the flow granularity, so that the supporting operation of the advertiser to be supported can be realized, higher supporting efficiency can be obtained, the problem of the Matai effect can be effectively solved, and the adverse effect of the Matai effect can be avoided when each advertiser to be supported is supported; in addition, the technical scheme can meet a plurality of requirements of users, such as: demands such as gravitation magic cube customer migration, flow greenhouse, rapid push of customer retention optimization and the like; in addition, through the technical scheme, the platform loss can be stably restrained in the preset range, the problem that the platform loss is uncontrollable is effectively solved, the stable development of the platform is guaranteed, the practicability of the technical scheme is further improved, and the popularization and the application of the market are facilitated.

FIG. 8 is a flowchart of a method for advertising bidding in accordance with another exemplary embodiment of the present application; referring to fig. 8, the embodiment provides another advertisement bidding method, and an implementation subject of the method may be an advertisement bidding apparatus, and when the method is implemented specifically, the advertisement bidding apparatus may be implemented as an advertisement demand platform or an advertisement transaction platform, and it is understood that the advertisement bidding apparatus may be implemented as software or a combination of software and hardware. Specifically, the advertisement bidding method may include:

step S801: and obtaining original bidding information provided for target flow when the advertiser to be supported participates in the advertisement bidding.

The specific implementation manner and implementation effect of obtaining the original bidding information in this embodiment are similar to those of step S201 in the foregoing embodiment, and the above statements may be specifically referred to, and are not repeated here.

Step S802: and determining the advertisement putting index corresponding to the advertiser to be supported and the platform preferential information provided by the platform for the advertiser to be supported.

The specific determination manner and the implementation effect of the platform benefit information in this embodiment are similar to the specific implementation manner and the implementation effect of step S202 in the foregoing embodiment, and the above statements may be specifically referred to, and are not repeated here.

Step S803: and determining preferential distribution information corresponding to the target flow based on the platform preferential information and the advertisement putting indexes.

Step S804: and determining target bidding information based on the preferential distribution information and the original bidding information, wherein the target bidding information is used for carrying out advertisement bidding operation.

The specific determination manner and implementation effect of steps S802 to S804 in this embodiment are similar to the specific implementation manner and implementation effect of steps S402 to S404 in the foregoing embodiment, and the above statements may be specifically referred to, and are not repeated herein.

The method in this embodiment may further include other methods in the embodiments shown in fig. 1 to fig. 7, and reference may be made to the related descriptions of the embodiments shown in fig. 1 to fig. 7 for parts of this embodiment that are not described in detail. The implementation process and technical effect of the technical solution refer to the descriptions in the embodiments shown in fig. 1 to 7, and are not described herein again.

The advertisement bidding method provided by the embodiment determines the advertisement delivery index corresponding to the advertiser to be supported and the platform discount information provided by the platform for the advertiser to be supported by obtaining the original bidding information provided for the target flow when the advertiser to be supported participates in the advertisement bidding, and determines preferential distribution information corresponding to the target traffic based on the platform preferential information and the advertisement delivery index, then, target bidding information can be determined based on the preferential distribution information and the original bidding information, the obtained target bidding information is used for carrying out advertisement bidding operation, thereby effectively realizing that the supporting problem of the advertiser can be modeled into a constraint optimization problem, preferential distribution information on the flow granularity is determined through the advertisement putting index, thus being beneficial to improving the supporting efficiency, further improving the practicability of the method and being beneficial to the popularization and application of the market.

Fig. 9 is a schematic structural diagram of an advertisement bidding apparatus according to an embodiment of the present application; referring to fig. 9, the present embodiment provides an advertisement bidding apparatus capable of executing the advertisement bidding method shown in fig. 1, and in particular, the advertisement bidding apparatus may include:

the first obtaining module 11 is configured to obtain original bidding information provided for target traffic when an advertiser to be supported participates in advertisement bidding;

the first determining module 12 is configured to determine platform preference information provided by the platform for the advertiser to be supported;

the first determining module 12 is configured to determine target bidding information based on the platform offer information and the original bidding information, where the target bidding information is greater than the original bidding information;

and the first processing module 13 is configured to perform an advertisement bidding operation based on the target bidding information.

In some examples, when the first obtaining module 11 obtains the original bidding information provided for the target traffic when the advertiser to be supported participates in the bidding of the advertisement, the first obtaining module 11 is configured to: acquiring advertisers to be supported from a plurality of advertisers; when an advertiser to be supported participates in an advertisement bidding, determining target flow needing to be supported; acquiring an estimated click rate and an estimated conversion rate corresponding to the target flow; and acquiring original bidding information provided by the advertiser to be supported based on the estimated click rate and the estimated conversion rate.

In some examples, when the first obtaining module 11 determines the target traffic needing to be supported when the advertiser to be supported participates in the advertisement bidding, the first obtaining module 11 is configured to: acquiring all preset flow of advertisers to be supported participating in advertisement bidding; identifying all first preset flows which cannot bid successfully in all the preset flows; and determining all the first preset flow rates as target flow rates.

In some examples, when the first obtaining module 11 obtains the estimated click rate and the estimated conversion rate corresponding to the target flow rate, the first obtaining module 11 is configured to: acquiring a historical behavior portrait of a historical user for a target flow; and determining the estimated click rate and the estimated conversion rate corresponding to the target flow based on the historical behavior portrait.

In some examples, when the first determination module 12 determines the target bid information based on the platform offer information and the original bid information, the first determination module 12 is configured to: acquiring an advertisement putting index corresponding to an advertiser to be supported; based on the platform preferential information and the advertisement putting index, preferential distribution information corresponding to the target flow is determined; and determining target bidding distribution based on the discount distribution information and the original bidding information.

In some examples, the advertisement placement metrics include at least one of: exposure index, click index, deal index.

In some examples, when the first determination module 12 determines the offer distribution information corresponding to the target traffic based on the platform offer information and the advertisement placement metrics, the first determination module 12 is configured to: acquiring historical distribution information of advertisement putting indexes; and determining preferential distribution information corresponding to the target flow based on the platform preferential information and the historical distribution information.

In some examples, when the first determination module 12 determines the offer distribution information corresponding to the target traffic based on the platform offer information and the advertisement placement metrics, the first determination module 12 is configured to: determining a plurality of sub-offer information corresponding to the target traffic on the traffic granularity based on the advertisement delivery index and the platform offer information; and determining the preferential distribution information corresponding to the target flow based on the plurality of sub-preferential information.

In some examples, the sum of all sub-offer information in the offer distribution information is less than or equal to the platform offer information.

In some examples, when first determination module 12 determines, based on the advertisement placement metrics and the platform offer information, a plurality of sub-offer information corresponding to the target traffic at the traffic granularity, first determination module 12 is to: constructing a constraint optimization problem by taking the platform discount information as constraint, the advertisement delivery index as an optimization target and the sub-discount information on the flow granularity as variables; based on a constrained optimization problem, a plurality of sub-offer information corresponding to a target traffic at a traffic granularity is determined.

In some examples, after determining the offer distribution information corresponding to the target traffic, the first obtaining module 11 and the first processing module 13 in this embodiment are configured to perform the following steps:

the first obtaining module 11 is configured to obtain information smoothness of the preferential distribution information;

the first processing module 13 is configured to, when the information smoothness is less than the preset smoothness, adjust the benefit distribution information based on the preset smoothness to improve the information smoothness of the benefit distribution information.

In some examples, when the first obtaining module 11 obtains the information smoothness of the offer distribution information, the first obtaining module 11 is configured to perform: determining any two adjacent sub-discount information based on the discount distribution information; determining a discount information deviation between the two sub discount information; and determining the information smoothness of the preference distribution information based on the preference information deviation.

The advertising bidding device shown in fig. 9 can execute the method of the embodiment shown in fig. 1-7, and the detailed description of this embodiment can refer to the related description of the embodiment shown in fig. 1-7. The implementation process and technical effect of the technical solution refer to the descriptions in the embodiments shown in fig. 1 to 7, and are not described herein again.

In one possible design, the structure of the ad bidding apparatus shown in fig. 9 may be implemented as an electronic device, which may be a cluster server, a regular server, a cloud host, a virtual center, or the like. As shown in fig. 10, the electronic device may include: a first processor 21 and a first memory 22. Wherein the first memory 22 is used for storing programs of corresponding electronic devices for executing the advertisement bidding method provided in the embodiments shown in fig. 1-7, and the first processor 21 is configured for executing the programs stored in the first memory 22.

The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the first processor 21, are capable of performing the steps of: acquiring original bidding information provided for target flow when an advertiser to be supported participates in advertising bidding; determining platform preferential information provided by the platform for the advertiser to be supported; determining target bidding information based on the platform discount information and the original bidding information, wherein the target bidding information is larger than the original bidding information; and performing advertisement bidding operation based on the target bidding information.

Further, the first processor 21 is also used to execute all or part of the steps in the embodiments shown in fig. 1-7.

The electronic device may further include a first communication interface 23 for communicating with other devices or a communication network.

In addition, the embodiment of the present invention provides a computer storage medium for storing computer software instructions for an electronic device, which includes a program for executing the advertisement bidding method in the method embodiments shown in fig. 1 to 7.

Furthermore, an embodiment of the present invention provides a computer program product, including: computer program which, when executed by a processor of an electronic device, causes the processor to carry out the method of advertising bidding in the method embodiment shown in fig. 1-7.

Fig. 11 is a schematic structural diagram of an advertisement bidding apparatus according to an embodiment of the present application; referring to fig. 11, the present embodiment provides an advertisement bidding apparatus capable of executing the advertisement bidding method shown in fig. 8, and in particular, the advertisement bidding apparatus may include:

a second obtaining module 31, configured to obtain original bidding information provided for target traffic when an advertiser to be supported participates in an advertisement bidding;

the second determining module 32 is configured to determine an advertisement delivery index corresponding to the advertiser to be supported and platform preference information provided by the platform for the advertiser to be supported;

a second determining module 32, configured to determine, based on the platform benefit information and the advertisement delivery index, benefit distribution information corresponding to the target traffic;

and the second processing module 33 is configured to determine target bidding information based on the discount distribution information and the original bidding information, where the target bidding information is used to perform an advertisement bidding operation.

The method of the embodiment shown in fig. 8 can be performed by the ad bidding device shown in fig. 11, and reference may be made to the related description of the embodiment shown in fig. 8 for a part not described in detail in this embodiment. The implementation process and technical effect of the technical solution refer to the description in the embodiment shown in fig. 8, and are not described herein again.

In one possible design, the structure of the ad bidding apparatus shown in fig. 11 may be implemented as an electronic device, which may be a cluster server, a regular server, a cloud host, a virtual center, or the like. As shown in fig. 12, the electronic device may include: a second processor 41 and a second memory 42. Wherein the second memory 42 is used for storing a program of a corresponding electronic device for executing the advertisement bidding method provided in the embodiment shown in fig. 8, and the second processor 41 is configured for executing the program stored in the second memory 42.

The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the second processor 41, are capable of performing the steps of: acquiring original bidding information provided for target flow when an advertiser to be supported participates in advertising bidding; determining an advertisement putting index corresponding to the advertiser to be supported and platform preferential information provided by a platform for the advertiser to be supported; based on the platform preferential information and the advertisement putting index, determining preferential distribution information corresponding to the target flow; and determining target bidding information based on the preferential distribution information and the original bidding information, wherein the target bidding information is used for carrying out advertisement bidding operation.

Further, the second processor 41 is also used to execute all or part of the steps in the embodiment shown in fig. 8.

The electronic device may further include a second communication interface 43 for communicating with other devices or a communication network.

In addition, the embodiment of the present invention provides a computer storage medium for storing computer software instructions for an electronic device, which includes a program for executing the advertisement bidding method in the embodiment of the method shown in fig. 8.

Furthermore, an embodiment of the present invention provides a computer program product, including: a computer program which, when executed by a processor of an electronic device, causes the processor to perform the method of advertising bidding in the method embodiment of fig. 8.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. With this understanding in mind, the above-described technical solutions and/or portions thereof that contribute to the prior art may be embodied in the form of a computer program product, which may be embodied on one or more computer-usable storage media having computer-usable program code embodied therein (including but not limited to disk storage, CD-ROM, optical storage, etc.).

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media (trans) such as modulated data signals and carrier waves.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An advertisement bidding method, comprising:

2. The method of claim 1, wherein obtaining original bid information provided for targeted traffic when advertisers to be supported participate in ad bidding comprises:

acquiring the advertisers to be supported from a plurality of advertisers;

when the advertiser to be supported participates in the advertisement bidding, determining the target flow needing to be supported;

obtaining an estimated click rate and an estimated conversion rate corresponding to the target flow;

and acquiring original bidding information provided by the advertiser to be supported based on the estimated click rate and the estimated conversion rate.

3. The method of claim 2, wherein determining the target traffic to support when the advertiser to be supported participates in an advertisement bid comprises:

acquiring all preset flow of the advertisers to be supported participating in the advertisement bidding;

identifying all first preset flows which cannot bid successfully in all the preset flows;

and determining all the first preset flow rates as the target flow rates.

4. The method of claim 2, wherein obtaining a predicted click rate and a predicted conversion rate corresponding to the target traffic comprises:

acquiring a historical behavior portrait of a historical user aiming at the target flow;

and determining the estimated click rate and the estimated conversion rate corresponding to the target flow based on the historical behavior portrait.

5. The method of claim 1, wherein determining target bid information based on the platform offer information and the original bid information comprises:

acquiring an advertisement putting index corresponding to the advertiser to be supported;

and determining the target bidding distribution based on the discount distribution information and the original bidding information.

6. The method of claim 5, wherein the advertising metrics comprise at least one of: exposure index, click index, deal index.

7. The method of claim 5, wherein determining the offer distribution information corresponding to the target traffic based on the platform offer information and advertisement placement metrics comprises:

acquiring historical distribution information of the advertisement putting indexes;

and determining preferential distribution information corresponding to the target flow based on the platform preferential information and the historical distribution information.

8. The method of claim 5, wherein determining the offer distribution information corresponding to the target traffic based on the platform offer information and advertisement placement metrics comprises:

determining a plurality of sub-offer information corresponding to the target traffic on a traffic granularity based on the advertisement delivery index and the platform offer information;

and determining the preferential distribution information corresponding to the target flow based on the plurality of sub-preferential information.

9. The method of claim 7 or 8, wherein the sum of all sub-offer information in the offer distribution information is less than or equal to the platform offer information.

10. The method of claim 8, wherein determining a plurality of sub-offers corresponding to the target traffic at a traffic granularity based on the advertisement placement metrics and the platform offer information comprises:

constructing a constraint optimization problem by taking the platform discount information as constraint, the advertisement putting index as an optimization target and sub-discount information on flow granularity as variables;

determining a plurality of sub-offer information corresponding to the target traffic at a traffic granularity based on the constrained optimization problem.

11. The method of claim 5, wherein after determining offer distribution information corresponding to the target traffic, the method further comprises:

acquiring information smoothness of the preference distribution information;

and when the information smoothness is smaller than a preset smoothness, adjusting the preference distribution information based on the preset smoothness so as to improve the information smoothness of the preference distribution information.

12. The method of claim 11, wherein obtaining information smoothness of the offer distribution information comprises:

determining any two adjacent sub-discount information based on the discount distribution information;

determining a discount information deviation between the two sub discount information;

and determining the information smoothness of the preference distribution information based on the preference information deviation.

13. An advertisement bidding method, comprising:

14. An electronic device, comprising: a memory, a processor; wherein the memory is to store one or more computer instructions that, when executed by the processor, implement the method of bidding for an advertisement according to any one of claims 1-12.