Data processing method and device, medium, equipment and computer program product

Abstract

The invention provides a data processing method and device, a medium, equipment and a computer program product, and the method comprises the steps: obtaining activation data and conversion data of a target application, the activation data represents a first event of starting the target application for the first time, and the conversion data represents a second event of starting the target application for the first time; the conversion data represents a second event of which advertisement display meets a target condition in the target application; performing first attribution analysis on the basis of the conversion data, and determining a conversion activation user associated with the conversion data; performing second attribution analysis on the basis of the activation data, and determining a click event and a click advertisement corresponding to an activation user in the activation data; and determining an attribution result corresponding to the conversion data based on the conversion activation user, the click event and the click advertisement. Therefore, attribution analysis can be carried out based on the actual conversion data and activation data in the target application, different user behaviors are represented based on the attribution result, and the accuracy of the attribution result is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular, to a data processing method, apparatus, medium, device, and computer program product. Background Art

[0002] In an advertising placement system, app download placement is an advertising form for promoting mobile apps, enabling users to click on the placed ads to download the corresponding apps. The IAA (In App Advertisement) model, i.e., the in-app advertisement model, is a monetization method for obtaining corresponding revenues through ads displayed within an app. For example, a developer displays various ads within the app developed by the developer. Users of the app can unlock permissions or functions within the app by watching the ads, and at the same time, the developer can obtain revenues through the ads displayed within the app.

[0003] In the related art, in the IAA model, apps mainly focus on key behaviors. For example, the key behaviors of high-value users are defined by combining IPU (Impression Per User, average number of impressions per user) and ECPM (Effective Cost Per Mille, revenue per thousand impressions), and then the attribution of the placement effect of app download placement ads is based on the key behaviors. However, the combination of IPU and ECPM is difficult to distinguish the behaviors of high-value users, resulting in a deviation in the attribution results. Summary of the Invention

[0004] This Summary of the Invention section is provided to introduce concepts in a concise form, which will be described in detail in the subsequent Detailed Description section. This Summary of the Invention section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a data processing method, the method including: Obtaining activation data and conversion data of a target app, where the activation data represents a first event of the first startup of the target app, and the conversion data represents a second event that an ad display in the target app meets a target condition; Performing a first attribution analysis based on the conversion data to determine conversion activation users associated with the conversion data; Performing a second attribution analysis based on the activation data to determine a click event and a clicked ad corresponding to an activation user in the activation data; Determining an attribution result corresponding to the conversion data based on the conversion activation users, the click event, and the clicked ad.

[0006] Second aspect, the present disclosure provides a data processing device, the device comprising: A first acquisition module, configured to acquire activation data and conversion data of a target application, wherein the activation data represents a first event of the first startup of the target application, and the conversion data represents a second event that an advertisement display in the target application meets a target condition; A first determination module, configured to perform a first attribution analysis based on the conversion data to determine a conversion activation user associated with the conversion data; A second determination module, configured to perform a second attribution analysis based on the activation data to determine a click event and a clicked advertisement corresponding to an activation user in the activation data; A third determination module, configured to determine an attribution result corresponding to the conversion data based on the conversion activation user, the click event, and the clicked advertisement.

[0007] Third aspect, the present disclosure provides a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processing device, the steps of the method described in the first aspect are implemented.

[0008] Fourth aspect, the present disclosure provides an electronic device, comprising: A storage device, on which a computer program is stored; A processing device, configured to execute the computer program in the storage device to implement the steps of the method described in the first aspect.

[0009] Fifth aspect, the present disclosure provides a computer program product, comprising a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In the above technical solution, it is possible to analyze each conversion data corresponding to a second event that an advertisement display occurring in a target application meets a target condition, so that it is possible to perform attribution analysis on the conversion behavior in the target application to determine the behavior performance of different users in the target application. Through the above technical solution, it is possible to perform attribution analysis based on actual conversion data and activation data in the target application, so as to realize the attribution from the conversion behavior to the activation behavior, and from the activation behavior to the specific advertisement of the click behavior, ensure that the attribution path is clear, improve the accuracy of the attribution result, and at the same time, in this process, it is possible to perform attribution based on the original conversion event collected in the target application. Compared with the attribution based on the abstractly defined key behavior in the related art, it is possible to characterize different user behaviors based on the attribution result, thereby improving the effectiveness and accuracy of the attribution result to provide accurate data support in the subsequent processing process based on the attribution result.

[0011] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation part. Brief Description of the Drawings

[0012] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and that the original and elements are not necessarily drawn to scale. In the drawings: Figure 1 is a flowchart of a data processing method provided according to an embodiment of the present disclosure.

[0013] Figure 2 is an interaction diagram of a data processing method provided based on an embodiment of the present disclosure.

[0014] Figure 3 is a block diagram of a data processing apparatus provided according to an embodiment of the present disclosure.

[0015] Figure 4 It shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. Detailed Description of the Embodiments

[0016] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0017] It should be understood that the various steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0018] As used herein, the term "including" and its variants are open-ended, i.e., "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of the functions executed by these devices, modules or units or their interdependent relationships.

[0020] It should be noted that the modifiers "a" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly specified in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] It can be understood that, before using the technical solutions disclosed in the embodiments of this disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0023] For example, when responding to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that performs the operations of the technical solutions of this disclosure according to the prompt message.

[0024] As an optional but non-limiting implementation manner, the manner of sending a prompt message to the user in response to receiving an active request from the user can be, for example, in the form of a pop-up window, and the prompt message can be presented in text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0025] It can be understood that the above process of notifying and obtaining the user's authorization is only illustrative and does not limit the implementation manners of this disclosure. Other manners that meet relevant laws and regulations can also be applied to the implementation manners of this disclosure.

[0026] At the same time, it can be understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and related provisions.

[0027] As described in the background art, currently, applications in the IAA mode are usually attributed and delivered based on the definition of key behaviors. In this scenario, if the key behaviors defined are those with high IPU and low ECPM, then when advertising is delivered to users with low IPU and high ECPM, the bid price will be relatively low, resulting in limited ad exposure times.

[0028] Figure 1 As shown, it is a flowchart of a data processing method provided according to an embodiment of this disclosure. As Figure 1 shown, the method may include: In step 11, activation data and conversion data of the target application are obtained, where the activation data represents a first event of the first launch of the target application, and the conversion data represents a second event where an advertisement display in the target application meets a target condition.

[0029] As an example, the target application can be an application in the IAA mode. The target application can be an application for which application downloads are promoted. That is, after promoting an advertisement of the target application, a user can download the target application by clicking on the advertisement. After that, when the user first launches the target application after downloading it, the first event is triggered to obtain the activation data. When an advertisement displayed in the target application viewed by the user meets the target condition, the second event is triggered to obtain the conversion data. Among them, the target condition can be set based on the actual application scenario. For example, it can be that the advertisement viewing duration exceeds a preset duration. An example scenario can be the display advertisement A1 in the target application. When the user's viewing duration of the advertisement A1 exceeds the preset duration, it can be considered that the second event is triggered, and then the conversion data can be generated and reported. The conversion data can include user information, advertisement information viewed, and viewing duration, etc.

[0030] In some embodiments, the activation data and the conversion data are reported based on an SDK (Software Development Kit). The SDK is used to report the activation data when the first event occurs in the target application, and report the conversion data when the second event occurs in the target application. The SDK is integrated into the target application. Thus, by integrating the SDK into the target application, corresponding data can be reported in real time when the first event and the second event occur in the target application, enabling the attribution middle platform to perceive the events occurring in the target application in real time, obtain the activation data and the full amount of conversion data of the target application, so as to perform attribution analysis on the full amount of conversion data. Compared with the related art where users who meet the key behaviors are regarded as equivalent users, in the present disclosure, by performing attribution analysis on each conversion data, the behaviors of each user can be distinguished, providing data support for subsequent different treatments for different user behaviors.

[0031] In step 12, a first attribution analysis is performed based on the conversion data to determine the conversion-activated users associated with the conversion data.

[0032] As an example, the conversion-activated users can be determined based on the user information in the conversion data, that is, the association between the conversion event in the target application and the application activation is determined, so as to clarify which activated users have performed monetization conversion behaviors. Thus, through this step, the conversion data can be attributed to the activated users.

[0033] In step 13, a second attribution analysis is performed based on the activation data to determine the click events and clicked ads corresponding to the activated users in the activation data.

[0034] As an example, an ad of the target application is shown to a user. If the user is interested, the user can click on the ad. The server can generate a clickid for this click behavior and record the click, which includes the ad clicked in this click behavior.

[0035] Correspondingly, the performing a second attribution analysis based on the activation data to determine the click events and clicked ads corresponding to the activated users in the activation data may include: Based on the time information of the activation data, determine the click events corresponding to the activation data.

[0036] Among them, a click behavior that occurs before the activation behavior may trigger the activation behavior. In this step, the click event attributed to the activation data can be determined from the click events whose time information is earlier than the time information of the activation data. For example, the event indicated by the clickid that is earlier than the time information in the activation data and closest to the time information in the activation data can be used as the click event, so that the activation behavior can be associated and attributed with the behavior of clicking on an ad.

[0037] After that, based on the click record indicated by the click event, determine the ad in the click record as the clicked ad. For example, the click record indicated by the clickid of the click event can be obtained, and the ad indicated by the ad identifier in the click record can be used as the clicked ad. As an example, ad information can be further obtained based on the clicked ad. For example, the ID of the clicked ad is XX1, the ad creative content is XX2, the delivery channel is XX3, and the delivery time period is XX4.

[0038] In step 14, based on the converted activated users, click events, and clicked ads, determine the attribution result corresponding to the conversion data.

[0039] As an example, the converted activated users attributed to the conversion data can be compared with the activated users in the activation data, so that the click events and clicked ads attributed to the activated users with consistent comparison are used as the attribution result corresponding to the conversion data. For example, the converted activated user attributed to the conversion data is U1. Through the above attribution process, the attribution result corresponding to the conversion data can be obtained as user U1 viewed ad A1, clicked on it, and activated. In the above technical solution, each piece of conversion data corresponding to a second event in which an advertisement display in a target application meets a target condition can be analyzed, so that attribution analysis can be performed on the conversion behavior in the target application to determine the behavior performance of different users in the target application. Through the above technical solution, attribution analysis can be performed based on the actual conversion data and activation data in the target application, so as to achieve attribution from the conversion behavior to the activation behavior and from the activation behavior to the specific advertisement of the click behavior, ensure that the attribution path is clear, improve the accuracy of the attribution result, and at the same time, during this process, attribution can be performed based on the original conversion events collected in the target application. Compared with the attribution based on the key behaviors defined abstractly in the related technology, different user behaviors can be characterized based on the attribution result, so as to improve the effectiveness and accuracy of the attribution result, and provide accurate data support in the subsequent processing process based on the attribution result.

[0040] Figure 2 As shown, it is an interaction schematic diagram of a data processing method provided based on an embodiment of the present disclosure. As Figure 2 described, the user clicks on an advertisement of a target application and downloads and installs the target application on their client, and starts the target application for the first time. After that, the SDK integrated in the target application can report the activation data of the activation event. Then the activation data is reported to the attribution middle platform for second attribution analysis based on the activation data. When the user watches an advertisement in the target application and meets the target condition, the SDK reports the conversion data of the conversion event. Then the conversion data is reported to the attribution middle platform for first attribution analysis based on the conversion data, and the attribution result of the conversion data is determined by combining the result of the second attribution analysis. The first attribution analysis and the second attribution analysis can be provided in one attribution service.

[0041] In some embodiments, the method may further include: Determining training data based on the activation data, the conversion data, the conversion activation user, the click event, and the click advertisement; Performing model training based on the training data to obtain a value prediction model, where the value prediction model is used to determine the predicted value of the user to download the advertisement application associated with the displayed advertisement based on the displayed advertisement and perform conversion in the advertisement application.

[0042] As an example, through the above-described method, attribution analysis can be performed on the activation data and the conversion data, so that attribution can be performed on each conversion behavior in the target application. Then, in this embodiment, training data can be generated based on the original data and the attribution result to implement the training of the value prediction model.

[0043] In an application scenario, after presenting an advertisement to a user, the user can click on the advertisement and download the advertisement-associated advertisement application. Subsequently, the user can choose to launch the advertisement application for activation. Further, the user can watch the advertisement within the advertisement application for conversion. Based on the analysis of this process, in some embodiments, the value prediction model may include a click-through rate sub-model, an activation rate sub-model, a conversion rate sub-model, and a value sub-model. Among them, the click-through rate sub-model is used to predict the probability that a user clicks on the presented advertisement; the activation rate sub-model is used to predict the probability that a user activates the advertisement application after clicking on the presented advertisement; the conversion rate sub-model is used to predict the probability that a user converts after activating the advertisement application; and the value sub-model is used to predict the predicted value of a user's conversion within the advertisement application.

[0044] Correspondingly, based on the activation data, the conversion data, the conversion-activated users, the click event, and the clicked advertisement, the steps for determining the training data may include: Based on the click event and the advertisement information and display information of the clicked advertisement, determine the first training data for the click-through rate sub-model.

[0045] For example, based on the display information of the clicked advertisement, the display users corresponding to the clicked advertisement can be determined, that is, to which users the clicked advertisement was presented. Based on the click event, the click users who clicked on the clicked advertisement can be determined. Then, the first positive sample can be determined based on the advertisement information and the click users among the display users, and the first negative sample can be generated based on the advertisement information and the non-click users among the display users to obtain the first training data. The click-through rate sub-model is trained based on the first training data.

[0046] Based on the advertisement information of the clicked advertisement, the click event, and the activation data, determine the second training data for the activation rate sub-model.

[0047] For example, based on the click event, the click users who clicked on the clicked advertisement can be determined, and based on the activation data, the activation users of the target application can be determined. Then, the second positive sample can be determined based on the advertisement information and the activation users among the click users, and the second negative sample can be determined based on the advertisement information and the non-activation users among the click users to obtain the second training data. The activation rate sub-model is trained based on the second training data.

[0048] Based on the advertisement information of the clicked advertisement, the conversion-activated users, and the activation data, determine the third training data for the conversion rate sub-model.

[0049] Based on the activation data, the activated users of the target application can be determined. Then, the third positive samples can be determined based on the advertisement information and the converted activated users among the activated users, and the third negative samples can be determined based on the advertisement information and the non-converted activated users among the activated users, so as to obtain the third training data. The conversion rate sub-model is trained based on this third training data.

[0050] Among them, the training methods of the above click-through rate sub-model, activation rate sub-model and conversion rate sub-model can be trained based on the machine learning methods of positive and negative samples common in this field, and the present disclosure does not limit this.

[0051] Based on the advertisement information of the clicked advertisement, the conversion data and the converted activated users, the fourth training data of the value sub-model is determined. The training data includes the first training data, the second training data, the third training data and the fourth training data.

[0052] As an example, a conversion time window can be set in advance to determine the conversion value of the converted activated user within this conversion time window based on the conversion data and the converted activated users. For example, if the conversion time window is 24 hours, the conversion data of the converted activated user within 24 hours after activation can be aggregated to determine the advertisements viewed by the converted activated user in the target application within 24 hours and the revenue corresponding to each advertisement, and then the number of advertisement views and the average advertisement revenue of the converted activated user within 24 hours can be determined. Then, the fourth training data can be obtained based on the converted activated users, the advertisement information, and the number of advertisement views and the average advertisement revenue of the user within the conversion time window. Then, the value sub-model is trained based on this fourth training data, so that the trained value sub-model can determine the estimated conversion value of the user corresponding to the user information within the conversion time window of the advertisement application corresponding to the advertisement information based on the input user information and advertisement information.

[0053] Thus, through the above technical solutions, corresponding training data can be generated based on the collected original data, such as activation data and conversion data, and the attribution results of the original data, so as to realize the training of the value prediction model, predict the placement effect of advertisements, improve the accuracy of the prediction results of the value prediction model, and provide data support for the subsequent advertisement placement process.

[0054] In an actual application scenario, when placing an advertisement for an application under an IAA model, in related technologies, the bid is usually based on key behaviors. That is, when it is considered that a user meets the key behaviors, a bid of M1 can be made for placing the advertisement to this user; when it is considered that the user does not meet the key behaviors, a bid of M2 can be made for placing the advertisement to this user. Then, the bids for multiple users who can meet the key behaviors are the same. This may result in a lower bid for users with higher value among them, leading to a failed auction and making it difficult to place advertisements to such users, thereby reducing the advertisement promotion effect. Based on this, the present disclosure also provides the following embodiments.

[0055] In some embodiments, the method may further include: Obtain the advertisement information of the auction advertisement. Among them, the auction advertisement may be an advertisement that needs to be auctioned and placed currently. Then, the advertisement information can be obtained based on the identifier of the auction advertisement. The advertisement information may include information such as advertisement ID, creative content, placement channel, placement time period, etc., and can be configured based on the actual application scenario, which is not limited here.

[0056] Based on the advertisement information and the value prediction model, determine the predicted value of the target user's conversion based on the advertisement information. Among them, the value prediction model is trained based on the training data determined by the activation data, the conversion data, the conversion-activated users, the click events, and the clicked advertisements. The process of determining the training data and training has been described above and will not be repeated here.

[0057] Among them, the target user may be a user who needs to have an advertisement placed currently. After obtaining the corresponding authorization of the user, the user information can be obtained. Then, in this step, the advertisement information and the user information of the target user can be input into the value prediction model, and the predicted value of the target user downloading the advertisement application associated with the auction advertisement based on the auction advertisement and performing conversion in the advertisement application can be obtained.

[0058] As an example, this step may include: Input the advertisement information and the user information of the target user into the value prediction model, and obtain the predicted click-through rate, predicted activation rate, predicted conversion rate of the target user based on the advertisement information, and the predicted number of advertisement views and predicted average advertisement revenue of the target user in the application indicated by the advertisement information.

[0059] For example, the advertisement information and the user information can be input into each sub-model in the value prediction model. Then, the predicted click-through rate can be obtained based on the click-through rate sub-model, the predicted activation rate can be obtained based on the activation rate sub-model, the predicted conversion rate can be obtained based on the conversion rate sub-model, and the predicted number of advertisement views and predicted average advertisement revenue can be obtained based on the value sub-model.

[0060] After that, based on the predicted click-through rate, the predicted activation rate, the predicted conversion rate, the predicted number of ad views, and the average predicted ad revenue, the predicted value is determined. As an example, the product of the above-mentioned predicted click-through rate, the predicted activation rate, the predicted conversion rate, the predicted number of ad views, and the average predicted ad revenue can be used as the predicted value.

[0061] Thus, before the advertising information is delivered to the target user, the value that the target user may convert can be predicted based on the value prediction model, so as to predict the delivery effect of the competitive ad, provide data reference for subsequent bidding on the competitive ad, and be able to dynamically bid on the competitive ad in combination with user information to increase the number of exposures of the competitive ad.

[0062] After the predicted value is determined, the target bid for the competitive ad can be determined based on the predicted value, and bidding is carried out in the ad group with the target bid, where the ad group contains the competitive ad, and the ads in the ad group are candidate ads for recommending to the target user.

[0063] For example, in the process of delivering ads to a target user, the candidate ads to be recommended can be formed into an ad group, and then one of the ads can be selected through bidding based on the bids of the ads in the ad group and pushed to the user.

[0064] As an example, the determining the target bid for the competitive ad based on the predicted value may include: Obtain the set revenue coefficient. Among them, this revenue system can be pre-configured by the advertiser of the competitive ad. To ensure the stability of the bid, this revenue coefficient can be based on the coefficient within the conversion time window, such as 24 hours as mentioned above. For example, the revenue coefficient within 24 hours after activation can be set to 30% in advance, and it can be configured through the configuration interface. The length of this conversion time window is the same as the length of the conversion time window when determining the training data of the value determination sub-model mentioned above.

[0065] After that, based on the predicted value and the revenue coefficient, the target bid is determined. For example, the ratio of the predicted value to the revenue coefficient can be used as the target bid.

[0066] Accordingly, the bid price of the competitive advertisement can be adjusted from bidding on key behaviors to bidding based on the estimated value and the revenue coefficient, so that the bid price of the competitive advertisement can match the ROI (Return On Investment) required by the customer, enabling dynamic bidding for advertising delivery to users with different values, ensuring the delivery cost while improving the effectiveness of the bid price, thereby enhancing the competitive ability of the competitive advertisement and expanding the applicable scope of the disclosed method.

[0067] Based on the same inventive concept, the present disclosure also provides a data processing device, as Figure 3 shown. The device 10 may include: A first acquisition module 100, configured to acquire activation data and conversion data of a target application, where the activation data represents a first event of the first startup of the target application, and the conversion data represents a second event in which an advertisement display in the target application meets a target condition; A first determination module 200, configured to perform a first attribution analysis based on the conversion data to determine conversion-activated users associated with the conversion data; A second determination module 300, configured to perform a second attribution analysis based on the activation data to determine a click event and a clicked advertisement corresponding to an activated user in the activation data; A third determination module 400, configured to determine an attribution result corresponding to the conversion data based on the conversion-activated users, the click event, and the clicked advertisement.

[0068] Optionally, the activation data and the conversion data are reported based on an SDK, and the SDK is used to report the activation data when the first event occurs in the target application and report the conversion data when the second event occurs in the target application, and the SDK is integrated in the target application.

[0069] Optionally, the second determination module includes: A first determination sub-module, configured to determine the click event corresponding to the activation data based on the time information of the activation data; A second determination sub-module, configured to determine the advertisement in the click record as the clicked advertisement based on the click record indicated by the click event.

[0070] Optionally, the device further includes: A fourth determination module, configured to determine training data based on the activation data, the conversion data, the conversion-activated users, the click event, and the clicked advertisement; A training module for training a model based on the training data to obtain a value prediction model, where the value prediction model is used to determine the predicted value of a user downloading an advertising application associated with the displayed advertisement based on the displayed advertisement and making a conversion in the advertising application.

[0071] Optionally, the device further includes: A second acquisition module for acquiring advertisement information of a competitive advertisement; A fifth determination module for determining the predicted value of a target user making a conversion based on the advertisement information and the value prediction model, where the value prediction model is trained based on the training data determined by the activation data, the conversion data, the conversion-activated users, the click events, and the clicked advertisements; A processing module for determining a target bid for the competitive advertisement based on the predicted value and making a bid in an advertisement group at the target bid, where the advertisement group includes the competitive advertisement, and the advertisements in the advertisement group are candidate advertisements for recommending to the target user.

[0072] Optionally, the processing module includes: An acquisition sub-module for acquiring a set revenue coefficient; A third determination sub-module for determining the target bid based on the predicted value and the revenue coefficient.

[0073] Optionally, the value prediction model includes a click-through rate sub-model, an activation rate sub-model, a conversion rate sub-model, and a value sub-model, and the fifth determination module includes: A fourth determination sub-module for inputting the advertisement information and the user information of the target user into each sub-model of the value prediction model to obtain the predicted click-through rate, predicted activation rate, predicted conversion rate of the target user based on the advertisement information, and the predicted number of advertisement views and predicted average advertisement revenue of the target user in the application indicated by the advertisement information; A fifth determination sub-module for determining the predicted value based on the predicted click-through rate, the predicted activation rate, the predicted conversion rate, the predicted number of advertisement views, and the predicted average advertisement revenue.

[0074] Optionally, the target application is an application in an in-app advertising mode.

[0075] Next, refer to Figure 4, which shows a schematic structural diagram of an electronic device (such as a terminal device or a server) 600 suitable for implementing the embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0076] As Figure 4 shown, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may perform various appropriate actions and processes according to the programs stored in the read-only memory (ROM) 602 or the programs loaded from the storage device 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0077] Generally, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 4 the electronic device 600 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices may be alternatively implemented or had.

[0078] Particularly, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

[0079] It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0080] In some embodiments, the client and the server may communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed network.

[0081] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist separately and not be assembled into the electronic device.

[0082] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: obtain activation data and conversion data of a target application, wherein the activation data represents a first event of the first startup of the target application, and the conversion data represents a second event that an advertisement display in the target application meets a target condition; perform a first attribution analysis based on the conversion data to determine conversion activation users associated with the conversion data; perform a second attribution analysis based on the activation data to determine click events and clicked advertisements corresponding to the activation users in the activation data; and determine an attribution result corresponding to the conversion data based on the conversion activation users, the click events, and the clicked advertisements.

[0083] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0084] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that, in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0085] The modules involved in the embodiments of the present disclosure can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation to the module itself in some cases. For example, the first acquisition module can also be described as "the module for acquiring the activation data and conversion data of the target application".

[0086] The functions described above in this article can be performed at least in part by one or more hardware logic components. For example, without limitation, the exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0087] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM or Flash Memory), optical fibers, portable compact disc read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0088] According to one or more embodiments of the present disclosure, Example 1 provides a data processing method, the method comprising: Acquiring activation data and conversion data of a target application, wherein the activation data represents a first event of the first start of the target application, and the conversion data represents a second event that an advertisement display in the target application meets a target condition; Performing a first attribution analysis based on the conversion data to determine the conversion activation users associated with the conversion data; Performing a second attribution analysis based on the activation data to determine the click event and the clicked advertisement corresponding to the activated users in the activation data; Based on the conversion activation users, the click event, and the clicked advertisement, determining an attribution result corresponding to the conversion data.

[0089] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, where the activation data and the conversion data are reported based on an SDK. The SDK is used to report the activation data when the first event occurs in the target application, and report the conversion data when the second event occurs in the target application. The SDK is integrated in the target application.

[0090] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 1. The second attribution analysis based on the activation data to determine the click event and the clicked advertisement corresponding to the activated user in the activation data includes: Based on the time information of the activation data, determine the click event corresponding to the activation data; Based on the click record indicated by the click event, determine the advertisement in the click record as the clicked advertisement.

[0091] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 1. The method further includes: Based on the activation data, the conversion data, the conversion-activated user, the click event, and the clicked advertisement, determine training data; Based on the training data, perform model training to obtain a value prediction model, where the value prediction model is used to determine the predicted value of a user downloading an advertisement application associated with the displayed advertisement based on the displayed advertisement and performing a conversion in the advertisement application.

[0092] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 1. The method further includes: Obtain the advertisement information of the auction advertisement; Based on the advertisement information and the value prediction model, determine the predicted value of the target user performing a conversion based on the advertisement information, where the value prediction model is trained based on the training data determined by the activation data, the conversion data, the conversion-activated user, the click event, and the clicked advertisement; Based on the predicted value, determine the target bid of the auction advertisement, and perform an auction in the advertisement group with the target bid, where the advertisement group includes the auction advertisement, and the advertisements in the advertisement group are candidate advertisements for recommending to the target user.

[0093] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 5. The determining the target bid of the auction advertisement based on the predicted value includes: Obtain the set revenue coefficient; Based on the predicted value and the revenue coefficient, determine the target bid.

[0094] According to one or more embodiments of the present disclosure, Example 7 provides the method of Example 5. The value prediction model includes a click-through rate sub-model, an activation rate sub-model, a conversion rate sub-model, and a value sub-model. Based on the advertisement information and the value prediction model, determining the predicted value of a target user's conversion based on the advertisement information includes: Inputting the advertisement information and the user information of the target user into each sub-model of the value prediction model to obtain the predicted click-through rate, predicted activation rate, predicted conversion rate of the target user based on the advertisement information, and the predicted number of advertisement views and the average predicted advertisement revenue of the target user in the application indicated by the advertisement information; Determining the predicted value based on the predicted click-through rate, the predicted activation rate, the predicted conversion rate, the predicted number of advertisement views, and the average predicted advertisement revenue.

[0095] According to one or more embodiments of the present disclosure, Example 8 provides the method of any one of Examples 1-7, where the target application is an application in the in-app advertisement mode.

[0096] According to one or more embodiments of the present disclosure, Example 9 provides a data processing device, which includes: A first acquisition module, configured to acquire activation data and conversion data of a target application, where the activation data represents a first event of the first startup of the target application, and the conversion data represents a second event where an advertisement display in the target application meets a target condition; A first determination module, configured to perform a first attribution analysis based on the conversion data to determine the conversion-activated users associated with the conversion data; A second determination module, configured to perform a second attribution analysis based on the activation data to determine the click events and clicked advertisements corresponding to the activated users in the activation data; A third determination module, configured to determine the attribution result corresponding to the conversion data based on the conversion-activated users, the click events, and the clicked advertisements.

[0097] According to one or more embodiments of the present disclosure, Example 10 provides a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processing device, the steps of the method according to any one of Examples 1-8 are implemented.

[0098] According to one or more embodiments of the present disclosure, Example 11 provides an electronic device, including: A storage device, on which a computer program is stored; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of Examples 1-8.

[0099] According to one or more embodiments of the present disclosure, Example 12 provides a computer program product including a computer program which, when executed by a processor, implements the steps of the method described in any one of Examples 1-8.

[0100] The above description is only for the preferred embodiments of the present disclosure and the illustration of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0101] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although a number of specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0102] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated herein.

Claims

1. A data processing method, characterized in that, The method includes: Obtaining activation data and conversion data of a target application, where the activation data represents a first event of the first startup of the target application, and the conversion data represents a second event where an advertisement display in the target application meets a target condition; Performing a first attribution analysis based on the conversion data to determine conversion-activated users associated with the conversion data; Performing a second attribution analysis based on the activation data to determine a click event and a clicked advertisement corresponding to an activated user in the activation data; Determining an attribution result corresponding to the conversion data based on the conversion-activated users, the click event, and the clicked advertisement.

2. The method according to claim 1, wherein The activation data and the conversion data are reported based on an SDK. The SDK is used to report the activation data when the first event occurs in the target application, and to report the conversion data when the second event occurs in the target application. The SDK is integrated in the target application.

3. The method according to claim 1, wherein The performing a second attribution analysis based on the activation data to determine a click event and a clicked advertisement corresponding to an activated user in the activation data includes: Determining the click event corresponding to the activation data based on the time information of the activation data; Determining the advertisement in the click record as the clicked advertisement based on the click record indicated by the click event.

4. The method according to claim 1, wherein The method further includes: Determining training data based on the activation data, the conversion data, the conversion-activated users, the click event, and the clicked advertisement; Performing model training based on the training data to obtain a value prediction model, where the value prediction model is used to determine the predicted value of a user to download an advertisement application associated with a displayed advertisement based on the displayed advertisement and perform a conversion in the advertisement application.

5. The method according to claim 1, wherein The method further includes: Obtaining advertisement information of a competitive advertisement; Determining the predicted value of a target user to perform a conversion based on the advertisement information based on the advertisement information and the value prediction model, where the value prediction model is trained based on training data determined based on the activation data, the conversion data, the conversion-activated users, the click event, and the clicked advertisement; Determining a target bid for the competitive advertisement based on the predicted value and performing a bid in an advertisement group at the target bid, where the advertisement group includes the competitive advertisement, and the advertisements in the advertisement group are candidate advertisements for recommending to the target user.

6. The method according to claim 5, wherein The determining a target bid for the competitive advertisement based on the predicted value includes: Obtaining a set revenue coefficient; Determining the target bid based on the predicted value and the revenue coefficient.

7. The method according to claim 5, characterized in that The value prediction model includes a click-through rate sub-model, an activation rate sub-model, a conversion rate sub-model, and a value sub-model. The determining the predicted value of a target user to perform a conversion based on the advertisement information based on the advertisement information and the value prediction model includes: Input the advertisement information and the user information of the target user into each sub-model of the value prediction model to obtain the predicted click-through rate, predicted activation rate, predicted conversion rate of the target user based on the advertisement information, and the predicted number of ad views and the average predicted ad revenue of the target user in the application indicated by the advertisement information; Determine the predicted value based on the predicted click-through rate, the predicted activation rate, the predicted conversion rate, the predicted number of ad views, and the average predicted ad revenue.

8. The method according to any one of claims 1-7, characterized in that, The target application is an application in the in-app advertising mode.

9. A data processing device, characterized in that, The device includes: A first acquisition module, configured to acquire activation data and conversion data of a target application, where the activation data represents a first event of the first startup of the target application, and the conversion data represents a second event that an ad display in the target application meets a target condition; A first determination module, configured to perform a first attribution analysis based on the conversion data to determine the conversion-activated users associated with the conversion data; A second determination module, configured to perform a second attribution analysis based on the activation data to determine the click events and clicked ads corresponding to the activated users in the activation data; A third determination module, configured to determine the attribution result corresponding to the conversion data based on the conversion-activated users, the click events, and the clicked ads.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processing device, it implements the steps of the method according to any one of claims 1-8.

11. An electronic device, characterized in that, Including: A storage device, on which a computer program is stored; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1-8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-8.

Images