CN113159854A

CN113159854A - Exposure data determination method, device, equipment and storage medium

Info

Publication number: CN113159854A
Application number: CN202110477792.1A
Authority: CN
Inventors: 生辉
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-04-30
Filing date: 2021-04-30
Publication date: 2021-07-23

Abstract

The application provides an exposure data determination method, an exposure data determination device, exposure data determination equipment and a storage medium, wherein the method comprises the following steps: acquiring historical bidding data, historical exposure data, a plurality of expected bidding data and historical exposure index data of an object to be released corresponding to the historical bidding data of a target object; determining expected exposure index data of an object to be released corresponding to the plurality of expected bidding data; determining fitting parameters according to the expected exposure index data and the plurality of expected bid data; fitting expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data; and determining exposure data of the target object under different bidding data within a preset time period based on the historical exposure index data, the exposure index fitting data and the historical exposure data. The method and the device can cover exposure estimation of different bidding data, can improve the accuracy of the exposure data estimation, and can facilitate accurate object recommendation by the high-accuracy exposure estimation.

Description

Exposure data determination method, device, equipment and storage medium

Technical Field

The application belongs to the technical field of computers, and particularly relates to an exposure data determination method, device, equipment and storage medium.

Background

For one exposure of an object (e.g., an advertisement), the price that the current object needs to win is equal to the thousand exposure yields (eCPM) of the actual winning object divided by the eCPM of the current object multiplied by the current bid of the current object. In the prior art, the winning bids of the current object in all exposures are generally calculated, and the winning bids in all exposures are ranked from low to high to obtain a cumulative distribution function, i.e. winning rate. And then estimating the exposure of the current object in the next hour according to the winning rate.

However, the winning rate is only a discrete point, and cannot cover all bids, and when the estimated bid does not exist, sampling is needed to realize exposure estimation. However, the sampling estimated cost is high, the system resource consumption is large, and the adjustment coefficients under different bids cannot be restored (namely, the change rate of exposure relative to the reference exposure after the bids are changed); in addition, the sampling estimation has a large amount of dirty data, thereby reducing the accuracy of the exposure estimation.

Disclosure of Invention

In order to solve the above technical problem, the present application provides an exposure data determining method, apparatus, device and storage medium.

In one aspect, the present application provides an exposure data determining method, including:

acquiring historical bidding data, historical exposure data, a plurality of expected bidding data of a target object and historical exposure index data of an object to be released corresponding to the historical bidding data;

determining expected exposure index data of an object to be put corresponding to the plurality of expected bidding data;

determining fitting parameters from the expected exposure indicator data and the plurality of expected bid data;

fitting the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data, wherein the different bidding data comprises the multiple expected bidding data;

and determining exposure data of the target object under the different bidding data within a preset time period based on the historical exposure index data, the exposure index fitting data and the historical exposure data.

In another aspect, an embodiment of the present application provides an exposure data determining apparatus, where the apparatus includes:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring historical bidding data, historical exposure data, a plurality of expected bidding data of a target object and historical exposure index data of an object to be released corresponding to the historical bidding data;

the expected exposure index data determining module is used for determining expected exposure index data of the object to be released corresponding to the plurality of expected bidding data;

a fitting parameter determination module for determining fitting parameters based on the expected exposure indicator data and the plurality of expected bid data;

a fitting module, configured to fit the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data, where the different bidding data includes the multiple expected bidding data;

and the exposure data determining module is used for determining the exposure data of the target object under the different bidding data within a preset time period based on the historical exposure index data, the exposure index fitting data and the historical exposure data.

In another aspect, the present application provides an electronic device for determining exposure data, the electronic device including a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded by the processor and executed to implement the exposure data determining method as described above.

In another aspect, the present application proposes a computer-readable storage medium having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the exposure data determination method as described above.

According to the exposure data determining method, the device, the equipment and the storage medium, fitting parameters are determined through expected exposure index data and a plurality of expected bidding data, the expected exposure index data are fitted based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data, and then exposure data of a target object in a preset time period under different bidding data are estimated through the historical exposure index data, the exposure index fitting data and the historical exposure data. According to the embodiment of the application, exposure index fitting data (such as a winning rate curve) corresponding to different bidding data is obtained through the fitting parameters, the bidding coverage rate is high, the exposure data of the target object under different bids in a preset time period can be simply and conveniently estimated through the exposure index fitting data, and the estimated cost of the exposure data and the consumption of system resources are reduced; in addition, dirty data can be effectively removed in the fitting process, and therefore the accuracy of the exposure data estimation is improved.

Drawings

In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only 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 implementation environment of an exposure data determination method according to an exemplary embodiment.

Fig. 2 is a flowchart illustrating a method of determining exposure data according to an exemplary embodiment.

Fig. 3 is a schematic flowchart illustrating a process of determining expected exposure index data of an object to be placed corresponding to each of the plurality of expected bid data according to an exemplary embodiment.

FIG. 4 is a schematic diagram illustrating a process for determining fitting parameters according to an exemplary embodiment. .

FIG. 5 is a schematic flow chart illustrating a process for determining exposure metric fit data according to an exemplary embodiment.

FIG. 6 is a schematic diagram illustrating exposure metric fit data according to an exemplary embodiment.

Fig. 7 is a flowchart illustrating a process of determining exposure data of the target object under the different bid data within a preset time period according to an exemplary embodiment.

FIG. 8 is a schematic diagram illustrating a bid adjustment interface, according to an exemplary embodiment.

FIG. 9 is a diagram illustrating a potential advertising interface, according to an exemplary embodiment.

FIG. 10 is a bid reference diagram illustrating a client and a viewing star station, according to an example embodiment.

Fig. 11 is a block diagram illustrating an exposure data determining apparatus according to an exemplary embodiment.

Fig. 12 is a block diagram illustrating a hardware configuration of a server of an exposure data determining method according to an exemplary embodiment.

Detailed Description

Cloud technology refers to a hosting technology for unifying serial resources such as hardware, software, network and the like in a wide area network or a local area network to realize calculation, storage, processing and sharing of data.

The cloud technology is a general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied based on a cloud computing business model, can form a resource pool, is used as required, and is flexible and convenient. Background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture-like websites and more web portals. With the high development and application of the internet industry, each article may have its own identification mark and needs to be transmitted to a background system for logic processing, data in different levels are processed separately, and various industrial data need strong system background support and can only be realized through cloud computing. Specifically, cloud technologies include the technical fields of security, big data, databases, industrial applications, networks, storage, management tools, computing, and the like.

Specifically, the embodiment of the application relates to a big data technology in a cloud technology.

In order to make the technical solutions better understood by those skilled in the art, 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 only partial 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.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a schematic diagram illustrating an implementation environment of an exposure data determination method according to an exemplary embodiment. As shown in fig. 1, the implementation environment may include at least a client 01 and a server 02, and the client 01 and the server 02 may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

Wherein the client 01 can be configured to collect historical bid data and a plurality of expected bid data (i.e., new bids) and transmit the historical bid data and the plurality of expected bid data to the server 02. Alternatively, the client 01 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart television, a smart watch, and the like, but is not limited thereto. In particular, the "plurality of expected bid data" refers to at least two expected bid data.

The server 02 may be configured to obtain historical bid data, historical exposure data, multiple expected bid data, and historical exposure index data of an object to be delivered corresponding to the historical bid data of the object, and process the data to obtain exposure data of the target object under different bid data within a preset time period. Optionally, the server 02 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like.

It should be noted that fig. 1 is only one application environment of the exposure data determining method provided in the present application, and in practical applications, other application environments may also be included. For example, the application environment may include only clients.

In order to facilitate understanding of the technical solutions of the embodiments of the present application, some concepts or terms related to the embodiments of the present application are described below:

and (3) advertising bidding: the advertiser is required to pay the cost of the advertisement playing system every time the advertisement is clicked.

Recall (Matching): recalls in the advertisement playing system retrieve advertisements based on targeting.

Coarse row (Ranking): the rough ranking in the advertisement playing system sorts the advertisements based on quick and simple advertisement Click Through Rate (CTR) and advertisement Conversion Rate (CVR).

Refined rib (Re-ranking): the fine ranking in the advertisement playing system ranks the advertisements based on the fast and simple CTR and CVR algorithms.

eCPM: advertising revenue per thousand exposures.

CVR: CVR is the conversion/click-through volume of the advertisement.

CTR: CTR is the actual number of clicks/impressions of an ad.

Fig. 2 is a flowchart illustrating a method of determining exposure data according to an exemplary embodiment. The method may be used in the implementation environment of fig. 1. The present specification provides method steps as described in the examples or flowcharts, but may include more or fewer steps based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In practice, the system or server product may be implemented in a sequential or parallel manner (e.g., parallel processor or multi-threaded environment) according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 2, the method may include:

s101, historical bidding data, historical exposure data, a plurality of expected bidding data and historical exposure index data of the object to be released corresponding to the historical bidding data of the target object are obtained.

Illustratively, the historical bid data can be bids for the target object over a historical time period. Specifically, the historical time period may be a time period (e.g., a previous hour time period) that is a preset time period before the current time.

Illustratively, the historical exposure data may be an exposure of the target subject over a historical period of time (e.g., an exposure of a previous hour).

Illustratively, the plurality of expected bid data can be expected bids for the target object, i.e., new bids that are different from the historical bid data.

For example, the objects to be placed corresponding to the historical bidding data may be: and when the target object bids on the historical bidding data, the objects to be delivered are obtained by the sorting stage in the object platform. It should be noted that, if the target object wins, the target object is the object to be delivered.

For example, the historical exposure index data may be determined by a ratio of exposure data of the object to be delivered over a historical period of time to the number of times it entered the ranking stage to participate in the ranking.

Illustratively, the object may be an object that participates in the bid ordering and is exposed according to the result of the bid ordering. Alternatively, the object may be an advertisement. Specifically, the advertisements include, but are not limited to: picture advertisements, text advertisements, keyword advertisements, rank advertisements, video advertisements, and the like.

Since the data in S101 are all known data in the history time period, the server may directly fetch the data.

Taking an object as an advertisement and a target object as a current advertisement as an example, the historical bidding data can be the bidding of the current advertisement in a historical time period; the historical exposure data may be the exposure of the current advertisement over a historical period of time; the expected bid data may be an expected bid (i.e., a next-to-new bid) entered by the advertiser at a re-pricing interface of the client; the object to be delivered corresponding to the historical bidding data can be a winning advertisement with the top ranking in the fine ranking stage in the advertisement playing system under the historical bidding data; the historical exposure index data may be a historical culling rate, which may be a ratio of the exposure of the winning advertisement over a historical period of time to the number of times it entered the culling stage to participate in the ranking.

In the following, taking the object as an advertisement as an example, the determination process of the historical exposure index data (i.e. the historical precise winning rate) is described in detail:

after the advertisement is born, the advertisement needs to go through the stages of sea election recall, rough ranking, fine ranking, exposure and the like. Assuming that 1 million advertisements remain after 1 million advertisements are recalled and coarsely arranged, the 1 million advertisements can be finely arranged, that is, an ePCM (ePCM can be calculated by CTR, CVR and bid of each advertisement) of each advertisement is estimated, an advertisement with the largest ePCM is obtained, the advertisement with the largest ePCM is a winning advertisement with the highest ranking in the fine arrangement stage, and then the winning advertisement is exposed. Assuming that the winning advertisement was exposed 100 times and it entered the refinement stage for a ranking of 1 ten thousand times, the historical refinement rate of the winning advertisement is 100/1 ten thousand to 1%.

And S103, determining expected exposure index data of the object to be released corresponding to the plurality of expected bid data.

In an optional embodiment, the method may include the step of determining an object to be placed corresponding to each of the plurality of expected bid data, specifically:

and acquiring a plurality of preset objects entering an object fine-ranking stage, wherein the preset objects comprise the target object. Specifically, the "plurality of preset objects" refers to at least two preset objects.

And determining exposure release expenditure resources corresponding to the preset objects under the expected bid data, wherein the exposure release expenditure resources represent the resources released by the preset objects in every thousand exposures.

And sequencing the plurality of preset objects based on the exposure release payment resources to obtain object sequences corresponding to the plurality of expected bid data.

And taking the object with the top rank in the object sequence corresponding to the plurality of expected bid data as the object to be released corresponding to the plurality of expected bid data.

In an alternative embodiment, fig. 3 is a schematic flow chart illustrating a process for determining expected exposure index data of an object to be placed corresponding to each of the plurality of expected bid data according to an exemplary embodiment. As shown in fig. 3, in the step S103, the determining expected exposure index data of the object to be placed corresponding to each of the plurality of expected bid data may include:

and S1031, determining expected exposure data of the object to be released corresponding to the plurality of expected bid data respectively.

S1033, determining the expected exposure index data according to the expected exposure data and the number of times that the corresponding object to be thrown enters the fine-ranking stage.

Specifically, the object to be placed corresponding to each of the plurality of expected bid data may be: and when the target object bids on a plurality of expected bidding data, the object to be delivered is won by the sorting stage in the object platform. Wherein, under each expected bid data, one object to be delivered is won. It should be noted that, if the target object wins, the target object is the object to be delivered.

Alternatively, the expected exposure index data may refer to an expected fine-elimination winning rate, which may be a ratio of the exposure of the object to be delivered in a preset time period to the number of times the object enters the fine-elimination stage to participate in the sorting.

Optionally, the preset time is a time period after the current time by a preset time length. Specifically, the preset duration after the current time is equal to the preset duration before the current time. For example, the preset time period is 1 hour, and the preset time period is the time period of the next hour.

Taking the object as an advertisement as an example, the object to be delivered corresponding to each of the plurality of expected bid data may be: the targeted advertisement ranks the top winning advertisement in a fine ranking stage in the advertisement playing system under a plurality of expected bid data. The expected exposure metric data may refer to an expected culling rate, which may be a ratio of the exposure of the winning advertisement over a preset time period to the number of times it entered the culling stage to participate in the ranking.

In the following, taking an object as an advertisement and a target pair as a current advertisement as an example, a process of determining an object to be delivered and expected exposure index data (i.e., an expected fine-exclusion success rate) corresponding to each of a plurality of expected bid data is described in detail:

assuming that 1 ten thousand advertisements of the current advertisement enter a refinement stage under each expected bid data, estimating ePCMs of each advertisement to obtain the advertisement with the largest ePCM under each expected bid data, wherein the advertisement with the largest ePCM is the winning advertisement with the largest ranking under each expected bid data in the refinement stage, and then exposing the winning advertisement under each expected bid data. Assuming that the winning advertisement is exposed 200 times (i.e., expected exposure data) under a certain expected bid data and the number of times it enters the refinement stage for sorting is 1 ten thousand, the historical refinement rate of the winning advertisement under the expected bid data is 200/1 ten thousand-2%.

And S105, determining a fitting parameter according to the expected exposure index data and the expected bid data.

In the embodiment of the present application, since the corresponding expected exposure index data is obtained for each expected bid data, the number of the expected exposure index data is also multiple. The fitting parameters may be determined from the plurality of expected exposure index data and the plurality of expected bid data. Specifically, the "plurality of expected exposure index data" refers to at least two expected exposure index data.

Taking the target as an advertisement as an example, for one advertisement, when the bid is in the middle and low period, the advertisements competing with the target are many, so the bid yield is high (the slope is large); when bidding in the high segment, there are fewer ads competing with it, and thus the revenue of the bid is less (the slope is small). Such a case where the intermediate and low bid slopes are high and the high bid slopes are low is closer to the cumulative distribution function of the card distribution, and therefore, the exposure index data can be modeled by the cumulative distribution function of the card distribution.

In an alternative embodiment, FIG. 4 is a schematic diagram illustrating a process for determining fitting parameters according to an exemplary embodiment. As shown in fig. 4, in the step S105, the determining a fitting parameter according to the expected exposure index data and the plurality of expected bid data may include:

and S1051, constructing a probability density function corresponding to the fitting parameters based on the plurality of expected bid data and a preset gamma function.

And S1053, carrying out integral operation on the probability density function to obtain a probability distribution function.

And S1055, carrying out Taylor expansion on the probability distribution function to obtain a fitting function.

S1057, determining the fitting parameters based on the expected exposure index data, the plurality of expected bid data and the fitting function.

Illustratively, in the above S1051, the formula of the high probability density function constructed based on the plurality of expected bid data and the preset gamma function may be as follows:

wherein k is a fitting parameter, β is expected bidding data, and Γ is a preset gamma function.

Specifically, the formula of Γ may be as follows:

when x is

When the temperature of the water is higher than the set temperature,

in S1053, the probability density function is integrated to obtain a rate distribution function as follows:

where ω (β, k) is the rate distribution function.

Illustratively, the taylor expansion refers to first-order derivation and second-order derivation of ω (β, k). Then, in step S1055, taylor expansion is performed on the probability distribution function, and the obtained fitting function may be as follows:

in S1057, the expected exposure index data and the plurality of expected bid data are substituted into the fitting function to obtain the fitting parameter k.

Assuming that the plurality of expected bid data are 15, 20, 25 and 30 units, respectively, and the corresponding expected exposure index data are ω (15), ω (20), ω (25) and ω (30), respectively, the fitting parameters k can be obtained by substituting the fitting parameters with 15, 20, 25 and 30, and ω (15), ω (20), ω (25) and ω (30).

And S107, fitting the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data.

In the embodiment of the present disclosure, the expected exposure index data may be fitted according to the fitting parameter k to obtain exposure index fitting data corresponding to different bid data.

Illustratively, the exposure index fitting data may be an exposure index fitting curve. Specifically, when the object is an advertisement, the exposure index fitting data may win a rate curve.

In an alternative embodiment, FIG. 5 is a schematic flow chart illustrating a process for determining exposure metric fit data according to an exemplary embodiment. As shown in fig. 5, in S107, the fitting the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bid data may include:

s1071, fitting the expected exposure index data based on the fitting parameters to obtain fitted exposure index data corresponding to the different bidding data.

S1073, connecting coordinate points formed by the different bidding data and the corresponding fitted exposure index data to obtain the exposure index fitting data.

Assuming that the obtained expected exposure index data are ω (15), ω (20), ω (25), and ω (30), ω (15), ω (20), ω (25), and ω (30) may be fitted to obtain fitted exposure index data of the object to be placed corresponding to the different bid data. And then connecting coordinate points formed by the different bidding data and the corresponding fitted exposure index data by using a curve, thereby obtaining the exposure index fitting data.

Wherein, the different bidding data not only includes the above-mentioned prospective bidding data of 15 yuan, 20 yuan, 25 yuan, 30 yuan, etc., but also includes other bidding data besides the prospective bidding data.

Taking an object as an advertisement as an example, fig. 6 is a schematic diagram illustrating exposure indicator fitting data according to an exemplary embodiment. As shown in fig. 6, fitting the expected exposure index data to remove dirty data and outliers can obtain a winning rate curve under different bid data, and as can be seen from the winning rate curve, the winning rate curve is monotonous (i.e., the bid increases, and the winning rate also increases), and the benefit of the bid is higher (the slope is large) when the bid is in the middle and low stages, and the benefit of the bid is lower (the slope is small) when the bid is in the high stage. The winning rate corresponding to different bidding data can be intuitively obtained through the winning rate curve.

In the embodiment of the application, the expected exposure index data is fitted through the fitting parameters, the fitted exposure index data of the object to be released corresponding to different bids can be obtained, even if some bid data are not the expected bid data, the corresponding fitted exposure index data can still be obtained through parameter fitting, the coverage rate of the bid data is high, and the problems of high cost and high system resource consumption caused by sampling and estimating the unexpected bid data are avoided, so that the cost and the system resource consumption of determining the exposure index data under different bid data are reduced, and the cost and the system resource consumption of determining the subsequent exposure data are reduced; in addition, the fitting process can also correct the known expected exposure index data to remove dirty data and outliers, so that the accuracy of the fitted exposure index data is ensured, and the accuracy of the subsequent display data determination is improved.

And S109, determining exposure data of the target object under the different bidding data within a preset time period based on the historical exposure index data, the exposure index fitting data and the historical exposure data.

In an alternative embodiment, fig. 7 is a flowchart illustrating a method for determining exposure data of the target object under the different bidding data within a preset time period according to an exemplary embodiment. As shown in fig. 7, in the step S109, the determining exposure data of the target object under the different bid data within a preset time period based on the historical exposure index data, the exposure index fitting data, and the historical exposure data may include:

s1091, determining exposure change parameters corresponding to the different bidding data based on the historical exposure index data and the exposure index fitting data.

S1093, determining exposure data of the target object under the different bidding data within the preset time period according to the exposure variation parameter and the historical exposure data.

For example, in the above S1091, a ratio of the fitting data of the exposure index to the historical exposure index data may be calculated to obtain exposure variation parameters corresponding to different bidding data, where the exposure variation parameters are used to determine a variation rate of the exposure with respect to the historical exposure data under the different bidding data. The specific calculation formula may be as follows:

wherein, beta is the data of different bids,

for exposure variation parameters corresponding to the different bid data, ω (β) is the exposure index fitting data corresponding to the different bid data, ω (β)₀) Is historical exposure index data.

For example, in the above S1093, the product of the exposure variation parameter and the historical exposure data may be calculated to obtain the exposure data of the target object under different bidding data. The specific calculation formula may be as follows:

wherein e is historical exposure data.

In the embodiment of the application, because the exposure index fitting data is obtained by fitting in the fitting way, the bid data coverage rate is high, and the method is applicable to all the bid data, the method can be suitable for the estimation of the exposure data under all the bid data on the basis of the exposure index fitting data, and the estimated coverage rate of the exposure data is high; in addition, dirty data and outliers can be removed in the fitting process, and the accuracy of display data estimation under each bidding data is improved. Through statistics, the accuracy rate of Mean Square Error (MSE) of the exposure data determined by the exposure data determination method in the embodiment of the application, which is less than 0.2, can be increased from 70% to 80%, and a good estimation effect is obtained.

In an optional embodiment, when the different bidding data is equal to the historical bidding data, the method may further include:

and using the historical exposure data as the exposure data of the target object under the different bidding data in the preset time.

In practical applications, if the different bid data of the target object in the preset time period is equal to the historical bid data of the target object in the historical time period, i.e. in the case of constant bid, the exposure data in the preset time period can be considered to be equal to the historical exposure data.

For example, if the historical bid data is 10 units, the exposure data is 100 times, and the bid data in a preset time period (for example, the next hour) is also 10 units (that is, the bid data remains unchanged), it can be considered that the exposure data in the preset time period (for example, the next hour) is also 100 times.

Because the exposure data is greatly influenced by the bid data, the exposure data can be considered to be kept unchanged under the condition that the bid data is kept unchanged, the calculation of the exposure data under the condition that the bid data is kept unchanged is reduced, and the consumption of system calculation resources is reduced.

For example, targeting advertisements, FIG. 8 is a schematic diagram of a bid adjustment interface, according to an exemplary embodiment. As shown in fig. 8, the user of the client can input different new bids on the re-pricing interface, and the system can automatically calculate the exposure data of the advertisement at the new bid in the next hour according to the exposure data determination method, and display the exposure data and the exposure boost ratio (the exposure boost ratio of the exposure data at the new bid relative to the historical exposure data) in the bid adjustment interface. In addition, the client will also present a bid boost ratio (i.e., the bid boost ratio of the newly entered bid relative to the historical bid data) at the resale interface.

By displaying the exposure data, the exposure promotion proportion and the bid promotion proportion in the bid adjustment interface, a more accurate bid suggestion can be provided for an advertiser, so that the advertisement obtains better exposure data.

Taking a target object as an advertisement as an example, in an alternative embodiment, fig. 9 is a schematic diagram of a potential advertisement interface according to an exemplary embodiment. As shown in fig. 9, if the bid raising ratio of a certain advertisement is greater than a preset threshold (for example, when the preset threshold is 10%), and when the exposure data estimated in the next hour is raised by more than 2 times of the preset threshold compared with the historical exposure data, the advertisement is considered as a potential advertisement and is displayed in the potential advertisement interface of the client. Because a plurality of advertisements exist in the advertisement playing system, each advertisement can be used as a target advertisement, the bid promotion proportion and the exposure promotion proportion of each advertisement are calculated, and the advertisements meeting the potential advertisement conditions are all marked as potential advertisements. Specifically, the "plurality of advertisements" refers to at least two advertisements.

In the embodiment, the potential advertisement is displayed through the potential advertisement interface, and a more accurate price proposing suggestion can be further provided for the advertiser, so that the advertisement can further acquire better exposure data.

For example, in the case of targeted advertising, FIG. 10 is a schematic diagram illustrating bid reference between a client and a viewing star station, according to an exemplary embodiment. As shown in fig. 10, the current bid is 50.74, and the current exposure is estimated to be 729 times while the current bid remains unchanged; the predictive adjustment to 101.48 dollars can cause a unit bid to win the maximum exposure given a new set of bids.

In an alternative embodiment, an exposure data determination method as disclosed herein, wherein historical bid data, historical exposure index data, exposure data, etc. may be saved on a blockchain.

Fig. 11 is a block diagram illustrating an exposure data determining apparatus according to an exemplary embodiment. As illustrated in fig. 11, the apparatus may include at least:

the obtaining module 201 may be configured to obtain historical bid data, historical exposure data, multiple expected bid data, and historical exposure index data of an object to be delivered corresponding to the historical bid data of the target object.

The expected exposure index data determining module 203 may be configured to determine expected exposure index data of the object to be placed corresponding to each of the plurality of expected bid data.

The fitting parameter determining module 205 may be configured to determine a fitting parameter according to the expected exposure index data and the plurality of expected bid data.

The fitting module 207 may be configured to fit the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data.

The exposure data determining module 209 may be configured to determine exposure data of the target object under the different bidding data within a preset time period based on the historical exposure index data, the exposure index fitting data, and the historical exposure data, where the different bidding data includes the plurality of expected bidding data.

In an exemplary embodiment, the fitting parameter determining module 205 may include:

and a probability density function constructing unit, configured to construct a probability density function corresponding to the fitting parameter based on the plurality of expected bid data and a preset gamma function.

The probability distribution function determining unit may be configured to perform an integral operation on the probability density function to obtain a probability distribution function.

And the fitting function determining unit can be used for performing Taylor expansion on the probability distribution function to obtain a fitting function.

And a fitting parameter determination unit configured to determine the fitting parameter based on the expected exposure index data, the plurality of expected bid data, and the fitting function.

In an exemplary embodiment, the fitting module 207 may include:

and the exposure index data fitting unit can be used for fitting the expected exposure index data based on the fitting parameters to obtain fitted exposure index data corresponding to the different bidding data.

And the exposure index fitting data determining unit can be used for connecting coordinate points formed by the different bidding data and the corresponding fitted exposure index data to obtain the exposure index fitting data.

In an exemplary embodiment, the exposure data determining module 209 may include:

and an exposure change parameter determining unit configured to determine an exposure change parameter corresponding to each of the different bid data based on the historical exposure index data and the exposure index fitting data.

And an exposure data determining unit, configured to determine, according to the exposure variation parameter and the historical exposure data, exposure data of the target object under the different bid data within the preset time period.

In an exemplary embodiment, the apparatus may further include:

the preset object acquisition units may be configured to acquire preset objects entering an object refinement stage, where the preset objects include the target object.

The exposure projection expenditure resource determining unit may be configured to determine exposure projection expenditure resources corresponding to the plurality of preset objects under the plurality of expected bid data, where the exposure projection expenditure resources represent resources that are paid out by each thousand exposures of the preset objects.

The object sequence obtaining unit may be configured to rank the plurality of preset objects based on the exposure release payment resource to obtain an object sequence corresponding to each of the plurality of expected bid data.

The to-be-released object determining unit may be configured to use a top-ranked object in an object sequence corresponding to each of the plurality of expected bid data as the to-be-released object corresponding to each of the plurality of expected bid data.

In an exemplary embodiment, the expected exposure index data determining module 203 may include:

the expected exposure data determining unit may be configured to determine expected exposure data of the object to be delivered corresponding to each of the plurality of expected bid data.

The expected exposure index data determining unit may be configured to determine the expected exposure index data according to the expected exposure data and the corresponding number of times that the object to be delivered enters the fine ranking stage.

In an exemplary embodiment, when the different bidding data is equal to the historical bidding data, the method may further include:

and a second exposure data determination module, configured to use the historical exposure data as exposure data of the target object under the different bid data within the preset time.

It should be noted that the embodiments of the apparatus provided in the embodiments of the present application are based on the same inventive concept as the embodiments of the method described above.

The embodiment of the present application further provides an electronic device for determining exposure data, where the electronic device includes a processor and a memory, where the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the exposure data determining method provided in the above method embodiment.

The present application further provides a computer-readable storage medium, which can be disposed in a terminal to store at least one instruction or at least one program for implementing an exposure data determination method in the method embodiments, where the at least one instruction or the at least one program is loaded and executed by a processor to implement the exposure data determination method provided in the above method embodiments.

Alternatively, in embodiments of the present description, the storage medium may be located at multiple network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing program codes, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

The memory of the embodiments of the present disclosure may be used to store software programs and modules, and the processor may execute various functional applications and data processing by operating the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the device, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as a plurality of magnetic disk storage devices, flash memory devices, or other volatile solid state storage devices. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.

Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to execute the exposure data determination method provided by the above-described method embodiment.

The exposure data determining method, the exposure data determining device, the electronic equipment, the storage medium and the computer program product have the following beneficial effects:

1) in the embodiment of the application, the expected exposure index data is fitted through the fitting parameters, the fitted exposure index data of the objects to be released corresponding to different bids can be obtained, even if some bid data are not the expected bid data, the corresponding fitted exposure index data can still be obtained through parameter fitting, the coverage rate of the bid data is high, and the problems of high cost and high system resource consumption caused by sampling and estimating the unexpected bid data are avoided, so that the cost and the system resource consumption of determining the exposure index data under different bid data are reduced, and the cost and the system resource consumption of determining the exposure data are further reduced.

2) Because the exposure index fitting data is obtained by fitting the cumulative distribution function distributed by the card, the bid data coverage rate is higher, and the method is applicable to all the bid data, so that the method can be suitable for the estimation of the exposure data under all the bid data on the basis of the exposure index fitting data, and the estimated coverage rate of the exposure data is higher; in addition, dirty data and outliers can be removed in the fitting process, and the accuracy of display data estimation under each bidding data is improved. Through statistics, the accuracy of the Mean Square Error (MSE) of the exposure data determined by the exposure data determination method in the embodiment of the application, which is less than 0.2, can be improved from 70% to 80% compared with the accuracy of the Mean Square Error (MSE) of the exposure data determined by the exposure data determination method in the embodiment of the application, which is not less than 0.2, and a relatively good estimation effect is obtained.

3) In the embodiment of the application, an effective price raising suggestion tool is provided for putting the pre-estimated products through the display bid adjustment interface and the potential advertisement interface. By statistics, advertisers average call exposure pre-estimation related services 10 ten thousand times per day. Among them, 80% can get satisfactory positive feedback according to the advertiser who proposes the bid of potential advertisement product.

The embodiment of the exposure data determination method provided by the embodiment of the application can be executed in a terminal, a computer terminal, a server or a similar arithmetic device. Taking the example of running on a server, fig. 12 is a block diagram of a hardware configuration of a server of an exposure data determination method according to an exemplary embodiment. As shown in fig. 12, the server 300 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 310 (the CPUs 310 may include but are not limited to Processing devices such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 330 for storing data, one or more storage media 320 (e.g., one or more storage media storing applications 323 or data 322)More than one mass storage device). Memory 330 and storage medium 320 may be, among other things, transient or persistent storage. The program stored in the storage medium 320 may include one or more modules, each of which may include a series of instruction operations for the server. Still further, the central processor 310 may be configured to communicate with the storage medium 320 to execute a series of instruction operations in the storage medium 320 on the server 300. The Server 300 may also include one or more power supplies 360, one or more wired or wireless network interfaces 350, one or more input-output interfaces 340, and/or one or more operating systems 321, such as a Windows Server^TM，Mac OS X^TM，Unix^TM，Linux^TM，FreeBSD^TMAnd so on.

The input output interface 340 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the server 300. In one example, the input/output Interface 340 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the input/output interface 340 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

It will be understood by those skilled in the art that the structure shown in fig. 12 is only an illustration and is not intended to limit the structure of the electronic device. For example, server 300 may also include more or fewer components than shown in FIG. 12, or have a different configuration than shown in FIG. 12.

It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device and server embodiments, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.

It will be understood by those skilled in the art that all or part of the steps of implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The present invention is not intended to be limited to the particular embodiments shown and described, but is to be accorded the widest scope consistent with the principles and novel features herein disclosed.

Claims

1. An exposure data determination method, characterized in that the method comprises:

2. The exposure data determination method of claim 1, wherein the determining fitting parameters from the expected exposure indicator data and the plurality of expected bid data comprises:

constructing a probability density function corresponding to the fitting parameters based on the plurality of expected bidding data and a preset gamma function;

carrying out integral operation on the probability density function to obtain a probability distribution function;

performing Taylor expansion on the probability distribution function to obtain a fitting function;

determining the fitting parameters based on the expected exposure indicator data, the plurality of expected bid data, and the fitting function.

3. The method for determining exposure data according to claim 2, wherein the fitting the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bidding data includes:

fitting the expected exposure index data based on the fitting parameters to obtain fitted exposure index data corresponding to the different bidding data;

and connecting coordinate points formed by the different bidding data and the corresponding fitted exposure index data to obtain the exposure index fitting data.

4. The exposure data determination method according to claim 1, wherein the determining exposure data of the target object under the different bid data for a preset time period based on the historical exposure index data, the exposure index fitting data, and the historical exposure data includes:

determining exposure change parameters corresponding to the different bidding data based on the historical exposure index data and the exposure index fitting data;

and determining exposure data of the target object under the different bidding data within the preset time period according to the exposure change parameters and the historical exposure data.

5. The exposure data determination method according to any one of claims 1 to 4, characterized by further comprising:

acquiring a plurality of preset objects entering an object fine-ranking stage, wherein the preset objects comprise the target object;

determining exposure release expenditure resources corresponding to the preset objects under the expected bid data, wherein the exposure release expenditure resources represent resources released by the preset objects in every thousand exposures;

sequencing the plurality of preset objects based on the exposure and delivery expenditure resources to obtain object sequences corresponding to the plurality of expected bid data;

and taking the object with the top ranking in the object sequence corresponding to the plurality of expected bidding data as the object to be delivered corresponding to the plurality of expected bidding data.

6. The exposure data determination method according to claim 5, wherein the determining expected exposure index data of the object to be placed corresponding to each of the plurality of expected bid data includes:

determining expected exposure data of an object to be delivered corresponding to the plurality of expected bid data;

and determining the expected exposure index data according to the expected exposure data and the corresponding times of the object to be launched entering the fine ranking stage.

7. The exposure data determination method according to claim 1 or 6, wherein when the different bid data is equal to the historical bid data, the method further comprises:

and taking the historical exposure data as the exposure data of the target object under the different bidding data in the preset time.

8. An exposure data determination apparatus, characterized in that the apparatus comprises:

9. An electronic device for exposure data determination, characterized in that the electronic device comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded by the processor and executed to implement the exposure data determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, in which at least one instruction or at least one program is stored, which is loaded and executed by a processor to implement the exposure data determination method according to any one of claims 1 to 7.