Exposure data determination method, apparatus, device, and storage medium

Abstract

The application provides an exposure data determination method, device and equipment and a storage medium. The method comprises the following steps: obtaining historical bidding data, historical exposure data, a plurality of expected bidding data and historical exposure index data of a to-be-launched object corresponding to the historical bidding data of a target object; determining expected exposure index data of the to-be-launched object corresponding to each of the plurality of expected bidding data; determining fitting parameters according to the expected exposure index data and the plurality of expected bidding data; fitting the 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 application can cover exposure estimation of different bidding data, improve the accuracy of exposure data estimation, and facilitate accurate recommendation of objects based on high-accuracy exposure estimation.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and specifically relates to a method, apparatus, device and storage medium for determining exposure data. Background Technology

[0002] For a single impression of an object (e.g., an ad), the winning bid for that object is equal to the effective cost per mile (eCPM) of the winning object divided by the current object's eCPM, multiplied by the current object's current bid. In existing technology, the winning bid for the current object across all impressions is typically calculated, and these winning bids are sorted from low to high to obtain a cumulative distribution function, i.e., the win rate. Then, the win rate is used to predict the current object's impressions for the next hour.

[0003] However, the aforementioned win rates are only discrete points and cannot cover all bids. When the predicted bid does not exist, sampling is required to achieve exposure prediction. However, sampling prediction is costly, consumes a lot of system resources, and cannot reproduce the adjustment coefficient under different bids (i.e., the rate of change of exposure relative to the baseline exposure after the bid changes). In addition, sampling prediction will have a lot of dirty data, thereby reducing the accuracy of exposure prediction. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a method, apparatus, device, and storage medium for determining exposure data.

[0005] On the one hand, this application proposes a method for determining exposure data, the method comprising:

[0006] Obtain historical bid data, historical exposure data, multiple expected bid data, and historical exposure metric data of the target object corresponding to the historical bid data;

[0007] Determine the expected exposure metrics data for the target audience corresponding to each of the multiple expected bid data;

[0008] Based on the expected exposure index data and the multiple expected bid data, determine the fitting parameters;

[0009] Based on the fitting parameters, the expected exposure index data is fitted to obtain exposure index fitting data corresponding to different bid data, wherein the different bid data includes the multiple expected bid data.

[0010] Based on the historical exposure index data, the exposure index fitting data, and the historical exposure data, the exposure data of the target object under the different bid data within a preset time period is determined.

[0011] On the other hand, embodiments of this application provide an exposure data determination device, the device comprising:

[0012] The acquisition module is used to acquire historical bid data, historical exposure data, multiple expected bid data, and historical exposure metric data of the target object corresponding to the historical bid data;

[0013] The expected exposure metric data determination module is used to determine the expected exposure metric data of the target audience corresponding to each of the multiple expected bid data.

[0014] The fitting parameter determination module is used to determine fitting parameters based on the expected exposure index data and the multiple expected bid data;

[0015] The fitting module is used to fit the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bid data, wherein the different bid data includes the multiple expected bid data.

[0016] The exposure data determination module is used to determine the exposure data of the target object under 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.

[0017] On the other hand, this application proposes 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 at least one program being loaded and executed by the processor to implement the exposure data determination method as described above.

[0018] On the other hand, this application proposes a computer-readable storage medium storing at least one instruction or at least one program, which is loaded and executed by a processor to implement the exposure data determination method as described above.

[0019] The exposure data determination method, apparatus, device, and storage medium proposed in this application determine fitting parameters based on expected exposure index data and multiple expected bid data. Then, based on these fitting parameters, the expected exposure index data is fitted to obtain exposure index fitted data corresponding to different bid data. Finally, using this historical exposure index data, the exposure index fitted data, and the historical exposure data, the exposure data of a target object under different bid data within a preset time period is estimated. Since this application's embodiment obtains exposure index fitted data (e.g., win rate curves) corresponding to different bid data through fitting parameters, the bid coverage is high. This exposure index fitted data allows for simple and convenient estimation of the target object's exposure data under different bids within a preset time period, reducing the cost of exposure data estimation and the consumption of system resources. Furthermore, the fitting process effectively removes dirty data, thereby improving the accuracy of exposure data estimation. Attached Figure Description

[0020] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram illustrating the implementation environment of an exposure data determination method according to an exemplary embodiment.

[0022] Figure 2 This is a flowchart illustrating an exposure data determination method according to an exemplary embodiment.

[0023] Figure 3 This is a schematic diagram illustrating a process for determining the expected exposure metrics data of the target audience corresponding to each of the aforementioned multiple expected bid data, according to an exemplary embodiment.

[0024] Figure 4 This is a schematic diagram illustrating a process for determining fitting parameters according to an exemplary embodiment.

[0025] Figure 5 This is a schematic diagram illustrating a process for determining exposure index fitting data according to an exemplary embodiment.

[0026] Figure 6 The diagram shown is a schematic representation of exposure index fitting data according to an exemplary embodiment.

[0027] Figure 7This is a schematic diagram illustrating a process for determining the exposure data of the target object under different bid data within a preset time period, according to an exemplary embodiment.

[0028] Figure 8 This is a schematic diagram of a bid adjustment interface according to an exemplary embodiment.

[0029] Figure 9 This is a schematic diagram of a potential advertising interface according to an exemplary embodiment.

[0030] Figure 10 This is a schematic diagram illustrating the bidding reference between a client and an observatory according to an exemplary embodiment.

[0031] Figure 11 This is a block diagram of an exposure data determination apparatus according to an exemplary embodiment.

[0032] Figure 12 This is a hardware structure block diagram of a server for an exposure data determination method according to an exemplary embodiment. Detailed Implementation

[0033] Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or local area network to achieve data computing, storage, processing, and sharing.

[0034] Cloud technology is a general term encompassing network technology, information technology, integration technology, management platform technology, and application technology based on the cloud computing business model. It can form resource pools, providing flexible and convenient on-demand access. The backend services of cloud computing systems require substantial computing and storage resources, such as those for video websites, image websites, and many portal websites. With the rapid development and application of the internet industry, every item may eventually possess its own identification mark, requiring transmission to backend systems for logical processing. Data at different levels will be processed separately, and various industry data will require robust system support, which can only be achieved through cloud computing. Specifically, cloud technology includes technical fields such as security, big data, databases, industry applications, networking, storage, management tools, and computing.

[0035] Specifically, the embodiments of this application relate to big data technology in cloud technology.

[0036] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0038] Figure 1 This is a schematic diagram illustrating an implementation environment for an exposure data determination method according to an exemplary embodiment. For example... Figure 1 As shown, the implementation environment may include at least a client 01 and a server 02. The client 01 and the server 02 may be directly or indirectly connected through wired or wireless communication, and this application does not impose any restrictions on this.

[0039] The client 01 can be used to collect historical bidding data and multiple expected bidding data (i.e., new bids), and send the historical bidding data and multiple expected bidding data to the server 02. Optionally, the client 01 can be a smartphone, tablet, laptop, desktop computer, smart TV, smartwatch, etc., but is not limited to these. Specifically, the "multiple expected bidding data" refers to at least two expected bidding data.

[0040] Specifically, server 02 can be used to acquire historical bidding data, historical exposure data, multiple expected bidding data, and historical exposure metric data of the target object corresponding to the historical bidding data. It then processes this data to obtain the exposure data of the target object under different bidding data within a preset time period. Optionally, server 02 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0041] It should be noted that, Figure 1 This is merely one application environment for the exposure data determination method provided in this application. In practical applications, other application environments may also be included. For example, this application environment may only include the client.

[0042] To facilitate understanding of the technical solutions in the embodiments of this application, some concepts or terms involved in the embodiments of this application will be introduced below:

[0043] Ad bidding: The fee that the advertiser needs to pay to the ad playback system for each click on the ad.

[0044] Matching: In an advertising system, matching involves retrieving ads based on targeted audiences.

[0045] Coarse ranking: In an ad playback system, coarse ranking sorts ads based on quick and simple click-through rate (CTR) and conversion rate (CVR).

[0046] Re-ranking: Re-ranking in an ad playback system, which sorts ads based on fast and simple CTR and CVR algorithms.

[0047] eCPM: Revenue per thousand ad impressions.

[0048] CVR: CVR = Ad conversions / Ad clicks.

[0049] CTR: CTR = Actual number of clicks on the ad / Number of impressions.

[0050] Figure 2 This is a flowchart illustrating an exposure data determination method according to an exemplary embodiment. The method can be used for... Figure 1In the implementation environment described herein, the steps of the methods described in the embodiments or flowcharts are provided. However, based on conventional or non-inventive labor, more or fewer steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown in the embodiments or drawings... Figure 2 As shown, the method may include:

[0051] S101. Obtain the target object's historical bid data, historical exposure data, multiple expected bid data, and the historical exposure metric data of the target object corresponding to the above historical bid data.

[0052] For example, the historical bidding data can be the bids for the target object within a historical time period. Specifically, the historical time period can be a time period of a preset duration prior to the current time (e.g., the previous hour).

[0053] For example, the historical exposure data can be the exposure of the target object within a historical time period (e.g., the exposure in the previous hour).

[0054] For example, the multiple expected bid data can be the expected bid for the target object, that is, a new bid that is different from the historical bid data.

[0055] For example, the target object corresponding to the historical bidding data can be: the target object that won the ranking stage in the object platform when the target object's bid is based on the historical bidding data. It should be noted that if the target object wins, then the target object is the target object.

[0056] For example, the historical exposure metric data can be determined by the ratio of the exposure data of the target object in a historical time period to the number of times it entered the ranking stage to participate in the ranking.

[0057] For example, the object can be an object that participates in bidding for ranking and is exposed according to the bidding ranking results. Optionally, the object can be an advertisement. Specifically, the advertisement includes, but is not limited to: image ads, text ads, keyword ads, ranking ads, video ads, etc.

[0058] Since the data in S101 above are all known data within a historical time period, the server can directly retrieve them.

[0059] Taking the ad as the target and the current ad as the target audience, the historical bid data can be the bid of the current ad in the historical time period; the historical impression data can be the impression volume of the current ad in the historical time period; the expected bid data can be the expected bid (i.e., the second-newest bid) entered by the advertiser in the bid adjustment interface of the client; the target audience corresponding to the historical bid data can be the winning ad ranked first in the fine-ranking stage of the ad playback system under the historical bid data; the historical impression metric data can be the historical fine-ranking success rate, which is the ratio of the impression volume of the winning ad in the historical time period to the number of times it entered the fine-ranking stage to participate in the ranking.

[0060] The following section, using target audience advertising as an example, details the process of determining historical exposure metrics data (i.e., historical refined ranking success rate):

[0061] After an ad is created, it goes through several stages: initial screening and retrieval, coarse ranking, fine ranking, and exposure. Assuming that after recalling and coarse ranking 10 million ads, 10,000 ads remain, these 10,000 ads can be fine-ranked. This involves estimating the ePCM (ePCM) of each ad (calculated using CTR, CVR, and bid) and identifying the ad with the highest ePCM. This ad is the winner in the fine ranking stage and is then exposed. Assuming this winning ad is exposed 100 times and participates in the fine ranking stage 10,000 times, its historical fine ranking success rate is 100 / 10,000 = 1%.

[0062] S103. Determine the expected exposure metrics data for each of the above multiple expected bid data for the target audience.

[0063] In an optional embodiment, the above method may include the step of determining the target audience corresponding to each of the multiple expected bid data, specifically:

[0064] Obtain multiple preset objects for the object ranking stage, including the target object. Specifically, "multiple preset objects" refers to at least two preset objects.

[0065] Under the aforementioned multiple expected bid data, the exposure spending resources corresponding to each of the aforementioned multiple preset objects are determined. The aforementioned exposure spending resources represent the resources spent per thousand exposures for the preset objects.

[0066] Based on the aforementioned exposure and ad placement expenditure resources, the aforementioned preset objects are sorted to obtain the object sequence corresponding to each of the aforementioned expected bid data.

[0067] The first object in the sequence of objects corresponding to each of the above expected bid data is taken as the target object to be deployed for each of the above expected bid data.

[0068] In an optional embodiment, Figure 3 This is a schematic diagram illustrating a process for determining the expected exposure metrics data of the target audience corresponding to each of the aforementioned multiple expected bid data, according to an exemplary embodiment. For example... Figure 3 As shown, in S103 above, the expected exposure metrics data for the target audience corresponding to each of the multiple expected bid data can include:

[0069] S1031. Determine the expected exposure data of the target audience corresponding to each of the above multiple expected bid data.

[0070] S1033. Based on the above expected exposure data and the number of times the corresponding target audience enters the above fine-tuning stage, determine the above expected exposure indicator data.

[0071] Specifically, the target audience corresponding to each of the multiple expected bid data can be: the target audience that wins the ranking stage in the object platform when there are multiple expected bid data for the target object. Under each expected bid data, one target audience will win. It should be noted that if the target object wins, then the target object is that target audience.

[0072] Optionally, the expected exposure metric data may refer to the expected ranking success rate, which can be the ratio of the exposure of the target object within a preset time period to the number of times it enters the ranking stage.

[0073] Optionally, the preset time is a time period of a preset duration after the current time. Specifically, the preset duration after the current time is equal to the preset duration before the current time. For example, the preset duration is 1 hour, and the preset time period is the next hour.

[0074] Taking this target as an example, the target to be delivered for each of the multiple expected bid data can be: the winning ad ranked first in the fine-ranking stage of the ad playback system under multiple expected bid data. The expected exposure metric data can refer to the expected fine-ranking success rate, which can be the ratio of the exposure of the winning ad within a preset time period to the number of times it enters the fine-ranking stage for ranking.

[0075] The following section, using the target audience as the ad and the target pair as the current ad as an example, details the process of determining the target audience and expected exposure metrics (i.e., expected ranking success rate) corresponding to each of the multiple expected bid data points:

[0076] Assuming that 10,000 ads enter the fine-tuning stage under various expected bid data, the ePCM of each ad is estimated. The ad with the largest ePCM under each expected bid data is the winning ad ranked first in the fine-tuning stage under each expected bid data. Then, the winning ads under each expected bid data are exposed. For example, if a winning ad is exposed 200 times under a certain expected bid data (i.e., the expected exposure data), and it participates in the fine-tuning stage 10,000 times, then the historical fine-tuning success rate of this winning ad under that expected bid data is 200 / 10,000 = 2%.

[0077] S105. Based on the above expected exposure index data and the above multiple expected bid data, determine the fitting parameters.

[0078] In this embodiment, since each expected bid data will yield corresponding expected exposure metric data, the number of expected exposure metric data is also multiple. Fitting parameters can be determined based on these multiple expected exposure metric data and multiple expected bid data. Specifically, "multiple expected exposure metric data" refers to at least two expected exposure metric data.

[0079] Taking advertising as an example, for an ad, when the bid is in the low to mid range, there are many competing ads, so the profit from increasing the bid is high (large slope); when the bid is in the high range, there are fewer competing ads, so the profit from increasing the bid is lower (small slope). This situation of a high bid slope in the low to mid range and a low bid slope in the high range is quite similar to the cumulative distribution function of the Chi-square distribution. Therefore, the cumulative distribution function of the Chi-square distribution can be used to model exposure index data.

[0080] In an optional embodiment, Figure 4 This is a schematic diagram illustrating a process for determining fitting parameters according to an exemplary embodiment. For example... Figure 4 As shown, in S105 above, determining the fitting parameters based on the expected exposure index data and the multiple expected bid data may include:

[0081] S1051. Based on the above multiple expected bid data and preset gamma function, construct the probability density function corresponding to the above fitting parameters.

[0082] S1053. Integrate the above probability density function to obtain the probability distribution function.

[0083] S1055. Perform a Taylor expansion on the above probability distribution function to obtain the fitting function.

[0084] S1057. Based on the above expected exposure index data, the above multiple expected bid data, and the above fitting function, determine the above fitting parameters.

[0085] For example, in S1051 above, the formula for the high probability density function constructed based on multiple expected bid data and a preset gamma function can be as follows:

[0086]

[0087] Where k is the fitting parameter, β is the expected bid data, and Γ is the preset gamma function.

[0088] Specifically, the formula for Γ can be as follows:

[0089]

[0090] When x is hour,

[0091] For example, in S1053 above, the probability density function is integrated to obtain the following rate distribution function:

[0092]

[0093] Where ω(β,k) is the rate distribution function.

[0094] For example, the Taylor expansion mentioned above refers to taking the first and second derivatives with respect to ω(β,k). Therefore, in S1055 above, performing a Taylor expansion on the probability distribution function yields the following fitting function:

[0095]

[0096] In S1057 above, the expected exposure index data and the above multiple expected bid data are substituted into the fitting function to obtain the fitting parameter k.

[0097] Assuming that the expected bid data are 15 yuan, 20 yuan, 25 yuan and 30 yuan respectively, and the corresponding expected exposure index data are ω(15), ω(20), ω(25) and ω(30) respectively, then by substituting 15, 20, 25, 30 and ω(15), ω(20), ω(25) and ω(30) into the above fitting parameters, the fitting parameter k can be obtained.

[0098] S107. Based on the above fitting parameters, fit the above expected exposure index data to obtain the exposure index fitting data corresponding to different bid data.

[0099] In this embodiment of the disclosure, the above-mentioned expected exposure index data can be fitted according to the fitting parameter k to obtain the exposure index fitting data corresponding to different bid data.

[0100] For example, the exposure metric fitting data can be an exposure metric fitting curve. Specifically, when the object is an advertisement, the exposure metric fitting data can be a win rate curve.

[0101] In an optional embodiment, Figure 5 This is a schematic diagram illustrating a process for determining exposure index fitting data according to an exemplary embodiment. For example... Figure 5 As shown, in S107 above, the process of fitting the expected exposure index data based on the above fitting parameters to obtain exposure index fitting data corresponding to different bid data may include:

[0102] S1071. Based on the above fitting parameters, fit the above expected exposure index data to obtain the fitted exposure index data corresponding to each of the above different bid data.

[0103] S1073. Connect the coordinate points formed by the different bid data and the corresponding fitted exposure index data to obtain the fitted exposure index data.

[0104] Assuming the expected exposure metrics data obtained above are ω(15), ω(20), ω(25), and ω(30), then ω(15), ω(20), ω(25), and ω(30) can be fitted to obtain the fitted exposure metrics data for the target object corresponding to different bid data. Then, the coordinate points formed by different bid data and the corresponding fitted exposure metrics data are connected by a curve to obtain the fitted exposure metrics data.

[0105] The different bid data includes not only the expected bid data of 15 yuan, 20 yuan, 25 yuan, and 30 yuan mentioned above, but also other bid data besides the expected bid data.

[0106] Taking advertising as an example, Figure 6 The diagram shown is a schematic representation of exposure index fitting data according to an exemplary embodiment. Figure 6 As shown, by fitting the expected exposure index data and removing dirty data and outliers, a win rate curve can be obtained under different bid data. This win rate curve shows that it is monotonic (i.e., as the bid increases, the win rate also increases). Furthermore, when the bid is in the low to medium range, the benefit of increasing the bid is higher (slope is steeper), while when the bid is in the high range, the benefit of increasing the bid is lower (slope is shallower). This win rate curve provides a direct visual representation of the win rate corresponding to different bid data.

[0107] In this embodiment, by fitting the expected exposure index data with fitting parameters, the fitted exposure index data for each target object corresponding to different bids can be obtained. Even if some bid data is not the expected bid data, the corresponding fitted exposure index data can still be obtained through parameter fitting. The bid data coverage is high, avoiding the problems of high cost and large system resource consumption caused by sampling and estimating non-expected bid data. This reduces the cost and system resource consumption of determining exposure index data under different bid data, thereby reducing the cost and system resource consumption of subsequent exposure data determination. In addition, the fitting process can also correct the known expected exposure index data to remove dirty data and outliers, thereby ensuring the accuracy of the fitted exposure index data and improving the accuracy of subsequent display data determination.

[0108] S109. Based on the above-mentioned historical exposure index data, the above-mentioned exposure index fitting data, and the above-mentioned historical exposure data, determine the exposure data of the above-mentioned target object under the above-mentioned different bid data within a preset time period.

[0109] In an optional embodiment, Figure 7 This is a schematic diagram illustrating a process for determining the exposure data of the target object under different bidding data within a preset time period, according to an exemplary embodiment. Figure 7 As shown, in S109 above, determining the exposure data of the target object under different bid data within a preset time period based on the historical exposure index data, exposure index fitting data, and historical exposure data may include:

[0110] S1091. Based on the above historical exposure index data and the above exposure index fitting data, determine the exposure change parameters corresponding to the above different bid data.

[0111] S1093. Based on the above exposure change parameters and the above historical exposure data, determine the exposure data of the above target object under the above different bid data within the above preset time period.

[0112] For example, in S1091 above, the ratio of the fitted exposure index data to the historical exposure index data can be calculated to obtain the exposure change parameter corresponding to different bid data. This exposure change parameter standard represents the rate of change of exposure relative to historical exposure data under different bid data. The specific calculation formula can be as follows:

[0113]

[0114] Where β represents different bid data. ω(β) represents the exposure change parameter corresponding to different bid data, ω(β0) represents the fitted data of the exposure index corresponding to different bid data, and ω(β0) represents the historical exposure index data.

[0115] For example, in S1093 above, the product of the exposure change parameter and the historical exposure data can be calculated to obtain the exposure data of the target object under different bid data. The specific calculation formula can be as follows:

[0116]

[0117] Wherein, ∈ represents historical exposure data.

[0118] In this embodiment, since the exposure index fitting data is obtained using the above-described fitting method, the bidding data coverage is high and applicable to all bidding data. Therefore, based on this exposure index fitting data, it can be adapted to the prediction of exposure data under various bidding data, resulting in high coverage of exposure data prediction. Furthermore, since the fitting process can remove dirty data and outliers, the accuracy of display data prediction under various bidding data is improved. Statistically, the accuracy of exposure data with a mean squared error (MSE) < 0.2 determined using the exposure data determination method in this embodiment can be improved from 70% to 80%, achieving a relatively good prediction effect.

[0119] In an optional embodiment, when the aforementioned different bid data is equal to the aforementioned historical bid data, the method may further include:

[0120] The aforementioned historical exposure data will be used as the exposure data of the aforementioned target object under the aforementioned different bid data within the aforementioned preset time period.

[0121] In practical applications, if the different bid data of the target object within a preset time period are equal to its historical bid data within a historical time period, that is, if the bid remains unchanged, the exposure data within the preset time period can be considered equal to the historical exposure data.

[0122] For example, if the historical bid is 10 yuan and the exposure data is 100 times, and the bid data within a preset time period (e.g., the next hour) is also 10 yuan (i.e. the bid data remains unchanged), then it can be assumed that the exposure data within the preset time period (e.g., the next hour) is also 100 times.

[0123] Since exposure data is greatly affected by bidding data, if the bidding data remains unchanged, the exposure data can be assumed to remain unchanged as well. This reduces the calculation of exposure data when the bidding data remains unchanged, thus reducing the consumption of system computing resources.

[0124] Taking the target audience as an example, Figure 8This is a schematic diagram illustrating a bid adjustment interface according to an exemplary embodiment. For example... Figure 8 As shown, users on the client can enter different new bids on this bid adjustment interface. Based on the aforementioned exposure data determination method, the system can automatically calculate the exposure data for the ad under the new bid for the next hour and display this exposure data and the exposure increase percentage (the exposure increase percentage of the new bid relative to historical exposure data) on the bid adjustment interface. In addition, the client will also display the bid increase percentage (i.e., the bid increase percentage of the newly entered bid relative to historical bid data) on the bid adjustment interface.

[0125] By displaying exposure data, exposure increase percentage, and bid increase percentage in the bid adjustment interface, advertisers can be provided with more accurate bid increase suggestions to enable ads to obtain better exposure data.

[0126] Taking the target audience as an example, in one optional embodiment, Figure 9 This is a schematic diagram illustrating a potential advertising interface according to an exemplary embodiment. Figure 9 As shown, if the bid increase percentage for a certain advertisement exceeds a preset threshold (e.g., a preset threshold of 10%), and the estimated exposure data for the next hour is more than twice the preset threshold compared to historical exposure data, then the advertisement can be considered a potential advertisement and displayed in the potential advertisement interface on the client. Since there are multiple advertisements in the ad playback system, each advertisement can be used as a target advertisement, and the bid increase percentage and exposure increase percentage for each advertisement can be calculated. Advertisements that meet the above potential advertisement criteria are all marked as potential advertisements. Specifically, "multiple advertisements" refers to at least two advertisements.

[0127] In this embodiment, displaying the potential ad through the potential ad interface can provide advertisers with more accurate suggestions for increasing prices, thereby enabling the ad to obtain better exposure data.

[0128] Taking the target audience as an example, Figure 10 This is a schematic diagram illustrating the bidding reference between a client and an observatory, according to an exemplary embodiment. For example... Figure 10 As shown, the current bid is 50.74. If the current bid remains unchanged, the estimated current exposure is 729 times. Among the given new bids, it is estimated that adjusting to 101.48 yuan will maximize the exposure per unit bid.

[0129] In an optional embodiment, such as the exposure data determination method disclosed in this application, historical bidding data, historical exposure data, historical exposure index data, and other exposure data can be stored on a blockchain.

[0130] Figure 11This is a block diagram illustrating an exposure data determination apparatus according to an exemplary embodiment. Figure 11 The device may include at least:

[0131] The acquisition module 201 can be used to acquire the historical bid data, historical exposure data, multiple expected bid data, and historical exposure metric data of the target object corresponding to the above historical bid data.

[0132] The expected exposure metric data determination module 203 can be used to determine the expected exposure metric data of the target audience corresponding to each of the above multiple expected bid data.

[0133] The fitting parameter determination module 205 can be used to determine the fitting parameters based on the above-mentioned expected exposure index data and the above-mentioned multiple expected bid data.

[0134] The fitting module 207 can be used to fit the expected exposure index data based on the above fitting parameters to obtain the exposure index fitting data corresponding to different bid data.

[0135] The exposure data determination module 209 can be used to determine the exposure data of the target object under different bid data within a preset time period based on the above-mentioned historical exposure index data, the above-mentioned exposure index fitting data and the above-mentioned historical exposure data. The above-mentioned different bid data includes the above-mentioned multiple expected bid data.

[0136] In one exemplary embodiment, the fitting parameter determination module 205 may include:

[0137] The probability density function construction unit can be used to construct the probability density function corresponding to the above-mentioned fitting parameters based on the above-mentioned multiple expected bid data and preset gamma function.

[0138] The probability distribution function determination unit can be used to perform integral operations on the above probability density function to obtain the probability distribution function.

[0139] The fitting function determination unit can be used to perform a Taylor expansion on the above probability distribution function to obtain the fitting function.

[0140] The fitting parameter determination unit can be used to determine the fitting parameters based on the above-mentioned expected exposure index data, the above-mentioned multiple expected bid data, and the above-mentioned fitting function.

[0141] In one exemplary embodiment, the fitting module 207 described above may include:

[0142] The exposure index data fitting unit can be used to fit the expected exposure index data based on the above fitting parameters to obtain the fitted exposure index data corresponding to the different bid data.

[0143] The exposure index fitting data determination unit can be used to connect the coordinate points formed by the different bid data and the corresponding fitted exposure index data to obtain the exposure index fitting data.

[0144] In one exemplary embodiment, the exposure data determination module 209 described above may include:

[0145] The exposure change parameter determination unit can be used to determine the exposure change parameters corresponding to the different bid data based on the above-mentioned historical exposure index data and the above-mentioned exposure index fitting data.

[0146] The exposure data determination unit can be used to determine the exposure data of the target object under different bid data within the preset time period based on the exposure change parameters and the historical exposure data.

[0147] In one exemplary embodiment, the above-described apparatus may further include:

[0148] Multiple preset object acquisition units can be used to acquire multiple preset objects that have entered the object fine sorting stage, and the multiple preset objects include the target object.

[0149] The exposure campaign expenditure resource determination unit can be used to determine the exposure campaign expenditure resources corresponding to each of the above-mentioned multiple preset objects under the above-mentioned multiple expected bid data. The exposure campaign expenditure resources represent the resources spent per thousand exposures of the preset objects.

[0150] The object sequence acquisition unit can be used to sort the above-mentioned multiple preset objects based on the above-mentioned exposure expenditure resources to obtain the object sequence corresponding to each of the above-mentioned multiple expected bid data.

[0151] The target object determination unit can be used to select the first object in the object sequence corresponding to each of the above multiple expected bid data as the target object corresponding to each of the above multiple expected bid data.

[0152] In one exemplary embodiment, the above-described expected exposure index data determination module 203 may include:

[0153] The expected exposure data determination unit can be used to determine the expected exposure data of the target audience corresponding to each of the above multiple expected bid data.

[0154] The expected exposure metric data determination unit can be used to determine the expected exposure metric data based on the expected exposure data and the number of times the corresponding target audience enters the fine-tuning stage.

[0155] In an exemplary embodiment, when the aforementioned different bid data is equal to the aforementioned historical bid data, the method may further include:

[0156] The second exposure data determination module uses the aforementioned historical exposure data as the exposure data of the target object under the aforementioned different bid data within the aforementioned preset time period.

[0157] It should be noted that the device embodiments provided in this application are based on the same inventive concept as the method embodiments described above.

[0158] This application also provides an electronic device for determining exposure data. The electronic device includes a processor and a memory. The memory stores at least one instruction or at least one program. The processor loads and executes the at least one instruction or at least one program to implement the exposure data determination method provided in the above method embodiments.

[0159] This application also provides a computer-readable storage medium that can be disposed in a terminal to store at least one instruction or at least one program related to implementing an exposure data determination method in the method embodiments. The at least one instruction or at least one program is loaded and executed by a processor to implement the exposure data determination method provided in the above method embodiments.

[0160] Optionally, in the embodiments of this specification, the storage medium may be located in multiple network servers among multiple network servers in a computer network. Optionally, in this embodiment, the above-mentioned storage medium may include, but is not limited to, various media capable of storing program code such as: USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk or optical disk.

[0161] The memory described in this specification can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system, applications required for functions, etc.; the data storage area may store data created based on the use of the device, etc. Furthermore, the memory may include high-speed random access memory, and may also include non-volatile memory, such as multiple 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 with access to the memory.

[0162] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the exposure data determination method provided in the above-described method embodiments.

[0163] The exposure data determination method, apparatus, electronic device, storage medium, and computer program product provided in this application have the following beneficial effects:

[0164] 1) In this embodiment of the application, the expected exposure index data is fitted by fitting parameters to obtain the fitted exposure index data of the target object corresponding to different bids. Even if some bid data is not the expected bid data, the corresponding fitted exposure index data can still be obtained through parameter fitting. The bid data coverage is high, avoiding the problems of high cost and large system resource consumption caused by sampling and estimating non-expected bid data. This reduces the cost and system resource consumption of determining exposure index data under different bid data, thereby reducing the cost and system resource consumption of determining exposure data.

[0165] 2) Since the exposure index fitting data is obtained by fitting the cumulative distribution function of the aforementioned chi-square distribution, the bidding data coverage is high and applicable to all bidding data. Therefore, based on this exposure index fitting data, it can be adapted to the prediction of exposure data under various bidding data, and the coverage of exposure data prediction is high. In addition, since the fitting process can remove dirty data and outliers, the accuracy of display data prediction under various bidding data is improved. According to statistics, the accuracy of exposure data with a mean squared error (MSE) < 0.2 determined by the exposure data determination method in this embodiment can be improved from 70% to 80% compared with the accuracy of exposure data with a mean squared error (MSE) < 0.2 determined without the exposure data determination method in this embodiment, achieving a better prediction effect.

[0166] 3) In this embodiment, by displaying the bid adjustment interface and the potential ad interface, an effective tool for suggesting bid increases is provided for the targeted advertising products. Statistics show that advertisers call the exposure prediction-related services an average of 100,000 times per day. Among them, 80% of advertisers who use the bid increase suggestions based on potential ad products receive satisfactory positive feedback.

[0167] The exposure data determination method provided in this application can be executed on a terminal, computer terminal, server, or similar computing device. Taking running on a server as an example... Figure 12This is a hardware structure block diagram of a server for an exposure data determination method according to an exemplary embodiment. For example... Figure 12 As shown, the server 300 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 310 (CPUs 310 may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory 330 for storing data, and one or more storage media 320 (e.g., one or more mass storage devices) for storing application programs 323 or data 322. The memory 330 and storage media 320 may be temporary or persistent storage. The program stored in the storage media 320 may include one or more modules, each module including a series of instruction operations on the server. Furthermore, the CPU 310 may be configured to communicate with the storage media 320 and execute a series of instruction operations stored in the storage media 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 Windows Server. TM Mac OS X TM Unix TM Linux TM FreeBSD TM etc.

[0168] The input / output interface 340 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 300. In one example, the input / output interface 340 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 340 may be a radio frequency (RF) module for wireless communication with the Internet.

[0169] Those skilled in the art will understand that Figure 12 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 300 may also include... Figure 12 The more or fewer components shown, or having the same Figure 12 The different configurations shown.

[0170] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0171] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and server embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0172] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0173] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining exposure data, characterized in that, The method includes: Obtain historical bid data, historical exposure data, multiple expected bid data, and historical exposure metric data of the target object corresponding to the historical bid data; Obtain multiple preset objects that will enter the object fine sorting stage, wherein the multiple preset objects include the target object; Estimate the exposure expenditure resources corresponding to each preset object, and select the preset object with the largest exposure expenditure resources under each expected bid data as the target object to be delivered for each of the multiple expected bid data; Determine the expected exposure metrics data for each of the multiple expected bid data corresponding to the target audience; the expected exposure metrics data is the ratio of the exposure volume of each target audience corresponding to the expected bid data within a preset time period to the number of times it participates in the ranking process during the fine-tuning stage; the preset time period is a time period of a preset duration after the current time; Based on the multiple expected bid data and the preset gamma function, a probability density function corresponding to the fitting parameters is constructed. Integrating the probability density function yields the probability distribution function; the probability distribution function is the cumulative distribution function of the chi-square distribution. The probability distribution function is expanded using Taylor to obtain a fitting function; the expected exposure index data and the multiple expected bid data are then substituted into the fitting function to determine the fitting parameters. Based on the fitting parameters, the expected exposure index data is fitted to obtain exposure index fitting data corresponding to different bid data, wherein the different bid data includes the multiple expected bid data. The ratio of the fitted exposure index data to the historical exposure index data is determined as the exposure change parameter corresponding to each of the different bid data; based on the exposure change parameter and the historical exposure data, the exposure data of the target object under the different bid data within a preset time period is determined.

2. The method for determining exposure data according to claim 1, characterized in that, The step of fitting the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bid data includes: Based on the fitting parameters, the expected exposure index data is fitted to obtain the fitted exposure index data corresponding to each of the different bid data. Connect the coordinate points formed by the different bid data and the corresponding fitted exposure index data to obtain the fitted exposure index data.

3. The method for determining exposure data according to any one of claims 1 to 2, characterized in that, The method further includes: The exposure expenditure resource represents the resources spent per thousand exposures of the preset object; Based on the exposure expenditure resources, the multiple preset objects are sorted to obtain the object sequence corresponding to each of the multiple expected bid data; The first object in the sequence of objects corresponding to each of the multiple expected bid data is taken as the target object to be deployed for each of the multiple expected bid data.

4. The method for determining exposure data according to claim 1, characterized in that, When the different bid data is equal to the historical bid data, the method further includes: The historical exposure data is used as the exposure data of the target object under different bid data within the preset time period.

5. An exposure data determining device, characterized in that, The device includes: The acquisition module is used to acquire historical bid data, historical exposure data, multiple expected bid data, and historical exposure metric data of the target object corresponding to the historical bid data; Multiple preset object acquisition units are used to acquire multiple preset objects that enter the object fine sorting stage, wherein the multiple preset objects include the target object; The target object determination unit is used to estimate the exposure expenditure resources corresponding to each preset object, and to take the preset object with the largest exposure expenditure resources under each expected bid data as the target object corresponding to each of the multiple expected bid data. The expected exposure metric data determination module is used to determine the expected exposure metric data of the target audience corresponding to each of the multiple expected bid data; the expected exposure metric data is the ratio of the exposure volume of the target audience corresponding to each expected bid data within a preset time period to the number of times it participates in the ranking in the fine ranking stage; the preset time period is a time period of preset duration after the current time; The probability density function construction unit is used to construct the probability density function corresponding to the fitting parameters based on the multiple expected bid data and the preset gamma function. The probability distribution function determination unit is used to perform an integral operation on the probability density function to obtain the probability distribution function; the probability distribution function is the cumulative distribution function of the chi-square distribution; The fitting function determination unit is used to perform a Taylor expansion on the probability distribution function to obtain the fitting function; The fitting parameter determination unit is used to input the expected exposure index data and the multiple expected bid data into the fitting function to determine the fitting parameters; The fitting module is used to fit the expected exposure index data based on the fitting parameters to obtain exposure index fitting data corresponding to different bid data, wherein the different bid data includes the multiple expected bid data. An exposure change parameter determination unit is used to determine the ratio of the exposure index fitting data and the historical exposure index data as the exposure change parameter corresponding to each of the different bid data. An exposure data determination unit is used to determine the exposure data of the target object under different bid data within a preset time period based on the exposure change parameters and the historical exposure data.

6. The apparatus according to claim 5, characterized in that, The fitting module includes: An exposure index data fitting unit is used to fit the expected exposure index data based on the fitting parameters to obtain the fitted exposure index data corresponding to each of the different bid data. The exposure index fitting data determination unit is used to connect the coordinate points formed by the different bid data and the corresponding fitted exposure index data to obtain the exposure index fitting data.

7. The apparatus according to claim 5, characterized in that, The device further includes: The object sequence acquisition unit is used to sort the multiple preset objects based on the exposure spending resources to obtain the object sequence corresponding to each of the multiple expected bid data. The target object determination unit is used to select the first object in the object sequence corresponding to each of the multiple expected bid data as the target object corresponding to each of the multiple expected bid data.

8. The apparatus according to claim 5, characterized in that, The device further includes: The second exposure data determination module is used to use the historical exposure data as the exposure data of the target object under different bid data within the preset time period.

9. An electronic device for determining exposure data, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by the processor to implement the exposure data determination method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the exposure data determination method as described in any one of claims 1 to 4.

Images