Regulation and control method and device for attribution data return in intelligent delivery mode

Abstract

The invention provides a regulation and control method and device for attribution data return in an intelligent delivery mode, and relates to the technical field of platform data return. The invention discloses a regulation and control method for attribution data return in an intelligent delivery mode. The regulation and control method comprises the following steps: acquiring real-time attribution data of a platform; calculating an estimated life cycle value of the platform user, and calculating an advertisement conversion rate under a preset time window; calculating a return threshold value corresponding to the estimated life cycle value under the preset time window through the advertisement conversion rate; and controlling the return of the real-time attribution data based on the estimated life cycle value and the return threshold. According to the embodiment of the invention, the data returned to the media release end can be dynamically regulated and controlled by estimating the advertisement conversion rate, the estimated life cycle value of the user and the corresponding return threshold value.

Description

Technical Field

[0001] The present application relates to the technical field of platform data feedback, and more specifically, to a method and device for regulating the feedback of attribution data in an intelligent delivery mode. Background Art

[0002] At present, platforms usually use oCPX (i.e., intelligent delivery mode) to attribute the click data of external advertising to the platform user behavior, and transmit the attributed target user behavior data back to the media publishing end to help the corresponding media model accurately acquire effective users.

[0003] Due to the complexity of the oCPX attributed data link and the instability of the latency of the upstream and downstream data flows, the flow of data returned by the platform through oCPX often fluctuates, resulting in high-amplitude fluctuations in the flow, such as Figure 1 The high fluctuation of traffic leads to the accumulation of a large amount of data to be transmitted back to the media publishing end, which interferes with the accuracy of data acquisition by the media model and causes the cost of acquiring effective users by the media model to soar. Summary of the invention

[0004] According to one aspect of the present application, a method for regulating the feedback of attribution data in an intelligent delivery mode is provided, including: obtaining real-time attribution data of a platform; calculating an estimated lifetime value of platform users, and calculating an advertising conversion rate in a preset time window; calculating a feedback threshold corresponding to the estimated lifetime value in a preset time window through the advertising conversion rate; and controlling the feedback of real-time attribution data based on the estimated lifetime value and the feedback threshold.

[0005] According to some embodiments, obtaining real-time attribution data of a platform includes: obtaining conversion behavior data of platform users through data embedding points; attributing the conversion behavior data to the corresponding media publishing end to obtain real-time attribution data.

[0006] According to some embodiments, calculating the estimated lifetime value of platform users includes: obtaining parameters of an estimated lifetime value model; and calculating the estimated lifetime value through the estimated lifetime value model based on the parameters and conversion behavior data.

[0007] According to some embodiments, obtaining parameters of an estimated lifetime value model includes: obtaining historical conversion behavior data of platform users through data embedding; obtaining the lifetime value generated by platform users; training the estimated lifetime value model based on the historical conversion behavior data and the lifetime value generated; and obtaining parameters of the trained estimated lifetime value model.

[0008] According to some embodiments, calculating the advertising conversion rate in a preset time window includes: obtaining the real-time number of target conversion users and the number of platform logged-in users; and calculating the advertising conversion rate in the preset time window based on the number of target conversion users and the number of platform logged-in users.

[0009] According to some embodiments, a feedback threshold corresponding to an estimated lifetime value in a preset time window is calculated through an advertising conversion rate, including: obtaining a corresponding distribution relationship between the advertising conversion rate and the feedback threshold; fitting a functional relationship between the advertising conversion rate and the feedback threshold according to the corresponding distribution relationship to obtain a fitting coefficient; and calculating the feedback threshold based on the fitting coefficient and the advertising conversion rate.

[0010] According to some embodiments, calculating the return threshold corresponding to the estimated lifetime value in a preset time window through the advertising conversion rate also includes: constraining the return threshold according to the estimated advertising conversion rate in the preset time window.

[0011] According to some embodiments, based on the estimated lifetime value and the feedback threshold, the feedback of real-time attribution data is controlled, including: obtaining the feedback threshold corresponding to the estimated lifetime value in a preset time window calculated based on the fitting coefficient and the advertising conversion rate; when the estimated lifetime value is greater than or equal to the feedback threshold, the real-time attribution data is fed back; when the estimated lifetime value is less than the feedback threshold, the real-time attribution data is not fed back.

[0012] According to some embodiments, when the estimated lifetime value is greater than or equal to the feedback threshold, real-time attribution data is fed back, including: calculating the advertising conversion rate fluctuation value for a preset time period before a preset time window; and dynamically adjusting the amount of data fed back of the real-time attribution data based on the calculated advertising conversion rate fluctuation value.

[0013] According to one aspect of the present application, a control device for the feedback of attribution data in an intelligent delivery mode is provided, including: a data acquisition module, used to obtain real-time attribution data of a platform; a first calculation module, used to calculate the estimated lifetime value of platform users, and calculate the advertising conversion rate in a preset time window; a second calculation module, used to calculate the feedback threshold corresponding to the estimated lifetime value in a preset time window through the advertising conversion rate; a data control module, used to control the feedback of real-time attribution data based on the estimated lifetime value and the feedback threshold.

[0014] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the aforementioned method.

[0015] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the aforementioned method is implemented.

[0016] According to the embodiments of the present application, the estimated advertising conversion rate, the estimated lifetime value of the user and the corresponding feedback threshold can be calculated in real time through a sliding window, and the user behavior data transmitted back to the media publishing end can be dynamically adjusted to ensure the accuracy and cost stability of the media model in acquiring users, thereby promoting high-quality growth of platform users.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application.

[0019] Figure 1 A schematic diagram showing fluctuations in oCPX return data traffic in the prior art is shown.

[0020] Figure 2 A flow chart of a method for regulating attribution data feedback in a smart delivery mode according to an example embodiment of the present application is shown.

[0021] Figure 3 A schematic diagram showing the distribution of advertiser accounts corresponding to the advertising conversion rate when the feedback threshold corresponding to the estimated lifetime value according to an example embodiment of the present application is a fixed value.

[0022] Figure 4 A schematic diagram showing the distribution of advertiser accounts corresponding to the advertising conversion rate when the feedback threshold corresponding to the estimated lifetime value according to an exemplary embodiment of the present application is another fixed value.

[0023] Figure 5 A schematic diagram showing the functional relationship fitting between the fluctuation of the advertisement conversion rate and the fluctuation of the return threshold corresponding to the estimated lifetime value according to an exemplary embodiment of the present application is shown.

[0024] Figure 6 A block diagram of a control device for attribution data feedback in a smart delivery mode according to an example embodiment of the present application is shown.

[0025] Figure 7 A block diagram of an electronic device according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0028] The described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application may be put into practice without one or more of these specific details, or other modes, components, materials, devices or operations may be adopted. In these cases, known structures, methods, devices, realizations, materials or operations will not be shown or described in detail.

[0029] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0030] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0031] The present application provides a method and device for regulating the return of attribution data in an intelligent delivery mode, which can dynamically regulate the user behavior data returned to the media publishing end.

[0032] A method and device for regulating attribution data feedback in an intelligent delivery mode according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0033] This application includes the following terms:

[0034] oCPX (Optimized Cost Per X): By transmitting the expected target user behavior back to the media end, the optimization of the settlement model in different ways is a bidding method based on target optimization, also known as the smart delivery model.

[0035] Life Time Value (LTV): The sum of all economic benefits obtained from all user interactions.

[0036] Ad conversion rate (CVR): The proportion of users who click on an ad and complete a conversion within a certain period of time. Conversion goals include user registration, download, online consultation, purchase, etc. It is an important indicator for measuring the effectiveness of advertising.

[0037] Figure 2 A flow chart of a method for regulating attribution data feedback in a smart delivery mode according to an example embodiment of the present application is shown.

[0038] like Figure 2 As shown, in step S100, the control device obtains real-time attribution data of the platform.

[0039] For example, in step S100, the control device obtains the real-time attribution data of the platform through the conversion behavior data of the platform users.

[0040] The control device obtains the conversion behavior data of platform users through data embedding.

[0041] According to some embodiments, the conversion behavior data of platform users includes real-time conversion behavior data. The control device obtains the real-time conversion behavior data of platform users through data embedding points set on the platform end, and stores it in the form of real-time data streams and log tables. Among them, the real-time conversion behavior data includes real-time user click data. The control device obtains the real-time user click data of advertisements from the media publishing end and stores it in the data table.

[0042] According to some embodiments, the conversion behavior data of the platform users also includes offline conversion behavior data. The control device obtains the offline conversion behavior data by reading the conversion behavior log of the platform end and the advertisement click log of the media publishing end.

[0043] According to the conversion and advertisement click-related data in the conversion behavior data of the platform users, the control device attributes the conversion behavior data to the corresponding media publishing end that publishes the advertisement to obtain real-time attribution data of the platform.

[0044] In step S200, the control device calculates the estimated lifetime value of platform users and calculates the advertising conversion rate within a preset time window.

[0045] For example, in step S200, the control device calculates the estimated lifetime value of platform users and the advertising conversion rate in a preset time window respectively.

[0046] The control device obtains a preset estimated life cycle value model.

[0047] The control device obtains the historical conversion behavior data of platform users through data embedding as sample data for estimating the life cycle value model.

[0048] The control device obtains the actual lifetime value of platform users from historical data, and uses it as a label for the estimated lifetime value model to supervise the training results of the estimated lifetime value model.

[0049] According to some embodiments, the control device obtains historical conversion behavior data, marked as vector x. The control device sets the parameters of the estimated lifetime value model as vector W, and sets the estimated lifetime value function as y=Wx. The control device obtains the lifetime value generated by the platform user, marked as the model supervision training label y'.

[0050] The control device trains the estimated life cycle value model through the historical conversion behavior data of platform users and the generated life cycle value, and obtains and stores the parameters of the estimated life cycle value model after training.

[0051] According to some embodiments, the control device uses a conventional logistic regression function to train the parameters W of the estimated lifetime value model, and uses a conventional gradient descent method to reduce the error between the predicted result y and the true label y' (such as an error less than 0.01%) to obtain the trained model parameters W, and stores the model parameters W in a data table.

[0052] According to the parameters of the estimated life cycle value model and the conversion behavior data of the platform users, the control device calculates and obtains the estimated life cycle value through the estimated life cycle value model.

[0053] According to some embodiments, the control device obtains the parameters W of the trained estimated life cycle value model and the real-time platform user conversion behavior data sample x. The control device calculates and obtains the estimated life cycle value y=Wx through the trained estimated life cycle value model.

[0054] Furthermore, the control device obtains the real-time number of target conversion users and the number of platform login users, and uses this to calculate the advertising conversion rate within a preset time window.

[0055] According to some embodiments, in the process of transmitting data back to the media publishing end through oCPX, the platform records the number of target converted users and the number of platform logged-in users each time the media publishing end is successfully transmitted back in real time into a data table. The control device can obtain the number of target converted users and the number of platform logged-in users in real time through the data table.

[0056] According to some embodiments, the control device may calculate the advertisement conversion rate within a preset time window by using the following formula.

[0057]

[0058] Among them, f cvr (t) represents the estimated advertising conversion rate calculated from the preset time window t0 to t, x convert Indicates the number of target conversion users on the media publishing end, x login Indicates the number of users logged into the platform on the media publishing end.

[0059] In step S300, the control device calculates the return threshold corresponding to the estimated life cycle value in a preset time window through the advertisement conversion rate.

[0060] For example, in step S300, the control device calculates the feedback threshold corresponding to the estimated life cycle value in a preset time window through the calculated advertising conversion rate and the fitting coefficient of the advertising conversion rate and the feedback threshold corresponding to the estimated life cycle value.

[0061] The control device obtains the corresponding distribution relationship between the advertisement conversion rate and the return threshold value corresponding to the estimated life cycle value in a preset time window through the previous experimental data.

[0062] According to some embodiments, in the early experimental data, under the condition of a fixed return threshold corresponding to the estimated life cycle value, the advertising conversion rate obtained by the corresponding advertising of the advertiser account with a given proportion can reach the target advertising conversion rate. Under different return thresholds corresponding to the estimated life cycle value, the fluctuation of the advertiser account scale and the advertising conversion rate conforms to the normal distribution, that is, the advertiser account with the same proportion scale can obtain the expected target advertising conversion rate by adjusting the return threshold corresponding to the estimated life cycle value.

[0063] like Figure 3 The figure shows the distribution of advertiser accounts corresponding to the advertising conversion rate when the feedback threshold corresponding to the estimated lifetime value is 0.63.

[0064] like Figure 4 The figure shows the distribution of advertiser accounts corresponding to the advertising conversion rate when the feedback threshold corresponding to the estimated lifetime value is 0.68.

[0065] According to the corresponding distribution relationship between the advertisement conversion rate and the feedback threshold corresponding to the estimated lifetime value in a preset time window, the control device performs functional fitting on the advertisement conversion rate and the feedback threshold corresponding to the estimated lifetime value to obtain a fitting coefficient.

[0066] According to some embodiments, the control device may perform an approximate linear fitting on the relationship between the fluctuation of the advertisement conversion rate and the fluctuation of the return threshold corresponding to the estimated lifetime value, such as Figure 5 As shown, the fitting coefficient coef i .Depend on Figure 5 From the slope in, we can see that the fitting coefficient coef i Is a negative number.

[0067] The control device calculates the return threshold corresponding to the estimated life cycle value in a preset time window according to the fitting coefficient and the advertisement conversion rate.

[0068] According to some embodiments, the return threshold corresponding to the estimated life cycle value in a preset time window can be expressed by the following formula.

[0069] i t =i t-1 -(cvr diff ×X dummy ×coef i ), (2)

[0070]

[0071] Among them, i t represents the return threshold corresponding to the estimated lifetime value of the time window from t to t+1, i t-1 Indicates the return threshold corresponding to the estimated lifetime value of the time window from t-1 to t, cvr diff Indicates the difference between the actual advertising conversion rate of the return media publisher and the target advertising conversion rate in the preset period (e.g., 24 hours) before stage t, X dummy Represents cvr diff Whether it is within the preset fluctuation range (for example, ±0.01).

[0072] According to some embodiments, the control device constrains the return threshold corresponding to the estimated lifetime value by the estimated advertisement conversion rate in a preset time window to avoid the return of low-value user data and the loss of high-value users. t The constraint can be expressed by the following formula.

[0073] i min ≤i t ≤i max , (4)

[0074] Among them, i min represents the estimated lifetime value of low-value users, i max represents the estimated lifetime value of high-value users. Assuming that the estimated advertising conversion rate in the current time window is cvr0, and the estimated error range of the advertising conversion rate is Δcvr (e.g. 5%), then i max is calculated when cvr0-Δcvr is used as the estimated advertising conversion rate, i min It is calculated when cvr0+Δcvr is used as the estimated advertising conversion rate.

[0075] In step S400, based on the estimated lifetime value and its corresponding feedback threshold, the control device controls the feedback of real-time attribution data.

[0076] For example, in step S400, based on the comparison result between the estimated lifetime value and its corresponding feedback threshold, the control device controls the feedback of real-time attribution data.

[0077] The control device obtains the calculated estimated life cycle value under the preset time window and its corresponding feedback threshold, and performs data comparison.

[0078] When the estimated life cycle value is greater than or equal to the corresponding feedback threshold, the control device returns real-time attribution data to the corresponding media publishing end.

[0079] When the estimated lifetime value is less than the corresponding feedback threshold, the control device does not return the real-time attribution data to the corresponding media publishing end.

[0080] For example, during the cold start period of the advertiser account, that is, when the advertiser account starts advertising and the number of platform users logged in is less than x login (e.g., 20), the feedback threshold corresponding to the initial estimated lifetime value is set to i0, which can be an empirical value associated with the target advertising conversion rate.

[0081] In the time series data stream, the step size of the fixed time window is l (for example, 15 minutes), and the current time window is set from time t1 to time t1+1. The control device calculates the advertising conversion rate fluctuation range of the preset period (for example, 24 hours) before time t1.

[0082] The control device obtains the feedback threshold corresponding to the estimated life cycle value at time t1-1 of the time window of the previous stage, and calculates the feedback threshold i1 corresponding to the estimated life cycle value of the time window from time t1 to time t1+1 according to formula (2).

[0083] In the time window from time t1 to time t1+1, the control device controls the return of oCPX real-time attribution data according to the return threshold i1 corresponding to the estimated lifetime value. If the estimated lifetime value of the current user is less than i1, the control device does not return the real-time attribution data. Otherwise, the control device returns the real-time attribution data.

[0084] According to some embodiments, when the control device returns real-time attribution data to the corresponding media publishing end, the control device calculates the advertising conversion rate fluctuation value in a preset time period before the preset time window, and dynamically adjusts the return data volume of the real-time attribution data based on this.

[0085] For example, it can be seen from formula (2) that when the actual advertising conversion rate of the return media publishing end in the preset time period before the preset time window is higher than the target advertising conversion rate, that is, the advertising conversion rate fluctuation value is greater than 0, the return threshold of the next sliding window of the preset sliding window increases, and the control device reduces the corresponding amount of return data of the real-time attribution data.

[0086] Similarly, when the actual return advertising conversion rate of the media publishing end in the preset time period before the preset time window is lower than the target advertising conversion rate, that is, the advertising conversion rate fluctuation value is less than 0, the return threshold of the next sliding window of the preset sliding window is reduced, and the control device increases the return data volume of the corresponding real-time attribution data.

[0087] According to the embodiments of the present application, the estimated advertising conversion rate, the estimated lifetime value of the user and the corresponding feedback threshold can be calculated in real time, and the user behavior data transmitted back to the media publishing end can be dynamically adjusted to ensure the accuracy of the media model in acquiring users.

[0088] Figure 6 A block diagram of a control device for attribution data feedback in a smart delivery mode according to an example embodiment of the present application is shown.

[0089] like Figure 6 As shown, the control device 500 includes a data acquisition module 510 , a first calculation module 520 , a second calculation module 530 and a data control module 540 .

[0090] The data acquisition module 510 acquires the conversion behavior data of platform users through data embedding.

[0091] According to the conversion and advertisement click related data in the conversion behavior data of the platform users, the data acquisition module 510 attributes the conversion behavior data to the corresponding media publishing end that publishes the advertisement to obtain the real-time attribution data of the platform.

[0092] The first calculation module 520 obtains a preset estimated life cycle value model.

[0093] The first calculation module 520 obtains the historical conversion behavior data of platform users through data embedding to serve as sample data for estimating the life cycle value model.

[0094] The first calculation module 520 obtains the actual lifetime value of platform users from historical data, and uses it as a label of the estimated lifetime value model to supervise the training results of the estimated lifetime value model.

[0095] The first calculation module 520 trains the estimated lifetime value model through the historical conversion behavior data of platform users and the generated lifetime value, and obtains and stores the parameters of the estimated lifetime value model after training.

[0096] According to the parameters of the estimated life cycle value model and the conversion behavior data of the platform users, the first calculation module 520 calculates and obtains the estimated life cycle value through the estimated life cycle value model.

[0097] The first calculation module 520 obtains the real-time number of target conversion users and the number of platform login users, and uses them to calculate the advertisement conversion rate in a preset time window.

[0098] The second calculation module 530 obtains the corresponding distribution relationship between the advertisement conversion rate and the return threshold corresponding to the estimated lifetime value in a preset time window through the previous experimental data.

[0099] According to the corresponding distribution relationship between the advertisement conversion rate and the feedback threshold corresponding to the estimated lifetime value in a preset time window, the second calculation module 530 performs functional fitting on the advertisement conversion rate and the feedback threshold corresponding to the estimated lifetime value to obtain a fitting coefficient.

[0100] The second calculation module 530 calculates a return threshold corresponding to the estimated lifetime value in a preset time window according to the fitting coefficient and the advertisement conversion rate.

[0101] The data control module 540 obtains the calculated estimated life cycle value under the preset time window and its corresponding return threshold, and performs data comparison.

[0102] When the estimated lifetime value is greater than or equal to the corresponding feedback threshold, the data control module 540 returns the real-time attribution data to the corresponding media publishing terminal.

[0103] When the estimated lifetime value is less than the corresponding feedback threshold, the data regulation module 540 does not return the real-time attribution data to the corresponding media publishing end.

[0104] When returning the real-time attribution data to the corresponding media publishing end, the data regulation module 540 calculates the advertising conversion rate fluctuation value in the preset time period before the preset time window, and dynamically adjusts the return data volume of the real-time attribution data accordingly.

[0105] Figure 7 A block diagram of an electronic device according to an exemplary embodiment of the present application is shown.

[0106] like Figure 7 As shown, the electronic device 600 is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0107] like Figure 7 As shown, the electronic device 600 is in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc. The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the methods described in this specification according to various exemplary embodiments of the present application. For example, the processing unit 610 may execute the following: Figure 2 The method shown in .

[0108] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0109] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0110] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0111] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0112] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by combining software with necessary hardware. The technical solution according to the embodiment of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal or a network device, etc.) to execute the method according to the embodiment of the present application.

[0113] The software product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0114] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0115] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0116] The computer-readable medium carries one or more programs. When the one or more programs are executed by a device, the computer-readable medium implements the aforementioned functions.

[0117] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0118] The embodiments of the present application are described in detail above, and the description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, changes or deformations made by those skilled in the art based on the idea of ​​the present application, the specific implementation method and the scope of application of the present application, all belong to the scope of protection of the present application. In summary, the content of this specification should not be construed as limiting the present application.

Claims

1. A method for regulating the attribution data return of an intelligent delivery model, characterized in that: include: Get real-time attribution data from the platform; Calculate the estimated lifetime value of platform users and calculate the advertising conversion rate within a preset time window; Calculating the return threshold corresponding to the estimated life cycle value in the preset time window through the advertisement conversion rate; Based on the estimated lifetime value and the feedback threshold, the feedback of the real-time attribution data is controlled.

2. The method according to claim 1, characterized in that Get real-time attribution data from the platform, including: Acquire conversion behavior data of platform users through data embedding; The conversion behavior data is attributed to the corresponding media publishing end to obtain the real-time attribution data.

3. The method according to claim 2, characterized in that Calculate the estimated lifetime value of platform users, including: Obtain parameters of the estimated lifetime value model; The estimated life cycle value is calculated according to the parameters and the conversion behavior data by using the estimated life cycle value model.

4. The method according to claim 3, characterized in that Get the parameters of the estimated lifetime value model, including: Acquire historical conversion behavior data of the platform users through the data embedding points; Obtain the lifetime value generated by the platform users; Training the estimated lifetime value model based on the historical conversion behavior data and the generated lifetime value; Get the parameters of the trained estimated lifetime value model.

5. The method according to claim 1, characterized in that: Calculate the ad conversion rate within a preset time window, including: Obtain real-time target conversion user numbers and platform login user numbers; The advertisement conversion rate in the preset time window is calculated according to the target conversion user number and the platform login user number.

6. The method according to claim 1, characterized in that Calculating the return threshold corresponding to the estimated life cycle value in the preset time window by the advertisement conversion rate includes: Obtaining a corresponding distribution relationship between the advertisement conversion rate and the feedback threshold; According to the corresponding distribution relationship, fitting the functional relationship between the advertisement conversion rate and the feedback threshold is performed to obtain a fitting coefficient; The feedback threshold is calculated based on the fitting coefficient and the advertisement conversion rate.

7. The method according to claim 6, characterized in that Calculating the return threshold corresponding to the estimated life cycle value in the preset time window by the advertisement conversion rate also includes: The feedback threshold is constrained according to the estimated advertisement conversion rate in the preset time window.

8. The method according to claim 6, characterized in that Based on the estimated lifetime value and the feedback threshold, controlling the feedback of the real-time attribution data includes: Obtaining a return threshold corresponding to the estimated lifetime value in the preset time window calculated based on the fitting coefficient and the advertisement conversion rate; When the estimated lifetime value is greater than or equal to the feedback threshold, feedback the real-time attribution data; When the estimated lifetime value is less than the feedback threshold, the real-time attribution data is not fed back.

9. The method according to claim 8, characterized in that When the estimated lifetime value is greater than or equal to the feedback threshold, the real-time attribution data is fed back, including: Calculating the advertising conversion rate fluctuation value in a preset period before the preset time window; According to the calculated advertising conversion rate fluctuation value, the amount of returned data of the real-time attribution data is dynamically adjusted.

10. A control device for attribution data return in intelligent delivery mode, characterized in that: include: Data acquisition module, used to obtain real-time attribution data of the platform; The first calculation module is used to calculate the estimated lifetime value of platform users and calculate the advertising conversion rate within a preset time window; A second calculation module is used to calculate the return threshold corresponding to the estimated life cycle value in the preset time window according to the advertisement conversion rate; A data control module is used to control the return of the real-time attribution data based on the estimated life cycle value and the return threshold.

11. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images