Method and apparatus for attribution

Abstract

Provided are a method and apparatus for attribution, wherein the method comprises: determining target conversion data from a plurality of conversion data, wherein each conversion data records a conversion event occurring on a user terminal and an operation performed on a target object and a type of the conversion event; selecting at least one target type from a plurality of types of conversion events recorded in the plurality of conversion data according to input data; determining at least one process conversion data from the plurality of conversion data, wherein at least one process conversion data and the target conversion data come from the same user terminal and the type of the recorded conversion event belongs to at least one target type; and determining at least one target promotion data matching the conversion link data from a plurality of promotion data according to an attribution rule, so as to determine that at least one promotion event recorded by the at least one target promotion data caused the conversion event recorded by the target conversion data.

Description

Technical Field

[0001] The present disclosure relates to data processing, and more particularly to a method and apparatus for attribution. Background Art

[0002] Attribution analysis is a data analysis solution that is often used by companies to analyze user conversion behaviors. By setting product embedding points, establishing analysis dimensions, and user portrait tags, the relationship between conversion events such as product purchases or other key performance indicators of user groups and the delivered ads can be visualized, thereby prompting companies to make promotion decisions that meet user preferences to increase business growth. However, in existing attribution analysis solutions, the attribution rules used are relatively simple, so the accuracy of the analysis results is low. Summary of the invention

[0003] It would be advantageous to provide a mechanism that alleviates, mitigates, or even eliminates one or more of the above-mentioned problems.

[0004] According to one aspect of the present disclosure, a method for attribution is provided, comprising: determining target conversion data from a plurality of conversion data, wherein each conversion data records a conversion event occurring on a user terminal and an operation performed on a target object and a type of the conversion event; selecting at least one target type from a plurality of types of conversion events recorded in the plurality of conversion data according to input data; determining at least one process conversion data from the plurality of conversion data, wherein at least one process conversion data and the target conversion data come from the same user terminal and the type of the recorded conversion event belongs to at least one target type; and determining at least one target promotion data matching the conversion link data from a plurality of promotion data according to an attribution rule, so as to determine that at least one promotion event recorded by at least one target promotion data caused the conversion event recorded by the target conversion data, wherein each promotion data records a promotion event occurring on a user terminal and that has been touched by the user, and the conversion link data comprises the target conversion data and at least one process conversion data.

[0005] According to another aspect of the present disclosure, a method for calculating attribution contribution is provided, comprising: executing the above-mentioned method for attribution multiple times for multiple different target conversion data to generate multiple conversion link data containing different target conversion data; and generating a total conversion contribution of each promotion event to the multiple conversion link data, wherein the total conversion contribution corresponding to each promotion event is the ratio of the sum of the conversion contributions of the promotion event to each conversion link data to the sum of all conversion contributions.

[0006] According to another aspect of the present disclosure, a device for attribution is provided, comprising: a first determination unit, configured to determine target conversion data from a plurality of conversion data, wherein each conversion data records a conversion event occurring on a user terminal and an operation performed on a target object and a type of the conversion event; a selection unit, configured to select at least one target type from a plurality of conversion event types recorded in the plurality of conversion data according to input data; a second determination unit, configured to determine at least one process conversion data from the plurality of conversion data, wherein at least one process conversion data and the target conversion data come from the same user terminal and the type of the recorded conversion event belongs to at least one target type; and a third determination unit, configured to determine at least one target promotion data matching the conversion link data from a plurality of promotion data according to an attribution rule, so as to determine that at least one promotion event recorded by at least one target promotion data caused the conversion event recorded by the target conversion data, wherein each promotion data records a promotion event occurring on a user terminal and that the user has been exposed to, and the conversion link data comprises the target conversion data and at least one process conversion data.

[0007] According to yet another aspect of the present disclosure, a computer device is provided, comprising: at least one processor; and at least one memory on which a computer program is stored, wherein when the computer program is executed by the at least one processor, the at least one processor executes the above method.

[0008] According to yet another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the above method.

[0009] According to yet another aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the processor is caused to execute the above method.

[0010] In the method of the embodiment of the present application, before performing attribution analysis, the process conversion data that records the conversion events that really need to be attributed is first found based on the target conversion data. Subsequently, attribution analysis is performed on the conversion events that really need to be attributed, avoiding the influence of non-critical target conversion data and improving the accuracy of attribution. In addition, the target type of the above-mentioned conversion events that really need to be attributed can be determined by the attribution data administrator according to the actual application scenario, thereby improving the flexibility of the attribution analysis, so that the method can be applied to attribution analysis in different scenarios.

[0011] These and other aspects of the disclosure will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Further details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0013] Figure 1 is a schematic diagram illustrating an example system in which the various methods described herein may be implemented according to an exemplary embodiment;

[0014] Figure 2 is a flow chart illustrating a method for attribution according to an exemplary embodiment;

[0015] Figure 3 is a schematic diagram illustrating a comparison between an attribution method according to an exemplary embodiment and an attribution method in a related art;

[0016] Figure 4 is a flow chart illustrating a method for attribution according to another exemplary embodiment;

[0017] Figure 5 is a flow chart illustrating a method for determining the contribution of each related promotion event according to another exemplary embodiment;

[0018] Figure 6 is a schematic block diagram illustrating an apparatus for attribution according to an exemplary embodiment;

[0019] Figure 7 is a block diagram illustrating an exemplary computer device that can be applied to the exemplary embodiments. DETAILED DESCRIPTION

[0020] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0021] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. As used herein, the term "plurality" means two or more, and the term "based on" should be interpreted as "based at least in part on". In addition, the terms "and / or" and "at least one of..." cover any one of the listed items and all possible combinations.

[0022] Exemplary embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0023] Figure 1 is a schematic diagram illustrating an example system 100 in which the various methods described herein may be implemented according to an exemplary embodiment. Figure 1 The system 100 includes a client device 110 , a server 120 , and a network 130 that communicatively couples the client device 110 and the server 120 .

[0024] The client device 110 includes a display 114 and a client application (APP) 112 that can be displayed via the display 114. The client application 112 can be an application that needs to be downloaded and installed before running or a small program (liteapp) as a lightweight application. It can also include an H5 page or a QR code for offline promotion, etc. In the case where the client application 112 is an application that needs to be downloaded and installed before running, the client application 112 can be pre-installed on the client device 110 and activated. In some embodiments, the above-mentioned client application 112 is an application that can operate a related attribution engine, and the attribution engine is used to perform attribution analysis on the conversion events recorded by the conversion data. The above-mentioned attribution engine will be described in detail below. In some embodiments, the client device 110 can be any type of mobile computer device, including a mobile computer, a mobile phone, a wearable computer device (such as a smart watch, a head-mounted device, including smart glasses, etc.) or other types of mobile devices. In some embodiments, the client device 110 can be a fixed computer device, such as a desktop, a server computer or other types of fixed computer devices.

[0025] The server 120 is typically a server deployed by an Internet Service Provider (ISP) or an Internet Content Provider (ICP). The server 120 may represent a single server, a cluster of multiple servers, a distributed system, or a cloud server that provides basic cloud services (such as cloud databases, cloud computing, cloud storage, and cloud communications). It will be understood that although Figure 1 The server 120 is shown in FIG. 1 in communicating with only one client device 110 , but the server 120 may provide background services for multiple client devices simultaneously.

[0026] Examples of network 130 include a local area network (LAN), a wide area network (WAN), a personal area network (PAN), and / or a combination of communication networks such as the Internet. Network 130 can be a wired or wireless network. In some embodiments, the data exchanged through network 130 is processed using technologies and / or formats including hypertext markup language (HTML), extensible markup language (XML), etc. In addition, encryption technologies such as secure socket layer (SSL), transport layer security (TLS), virtual private network (VPN), Internet protocol security (IPsec) can also be used to encrypt all or some links. In some embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0027] Figure 2 2 is a flow chart illustrating a method 200 for attribution according to an exemplary embodiment. The method 200 is performed by a related attribution engine, which may be installed on a client device (e.g., Figure 1 , that is, the execution subject of each step of method 200 may be Figure 1 In some embodiments, the attribution engine may also be installed on a server (e.g., Figure 1 In some embodiments, the attribution engine may be partially installed on a client device and the rest installed on a server, that is, the method 200 may be performed by a client device (e.g., the client device 110) and a server (e.g., the server 120) in combination. Hereinafter, the steps of the method 200 are described in detail by taking the server 120 as an example. Figure 2 As shown, the method 200 includes:

[0028] Step 210, determining target conversion data from a plurality of conversion data, wherein each conversion data records a conversion event occurring on a user terminal and operating on a target object and a type of the conversion event;

[0029] Step 220, selecting at least one target type from a plurality of types of conversion events recorded in a plurality of conversion data according to the input data;

[0030] Step 230, determining at least one process conversion data from the plurality of conversion data, wherein the at least one process conversion data and the target conversion data are from the same user terminal and the type of the recorded conversion event belongs to at least one target type; and

[0031] Step 240: According to the attribution rules, at least one target promotion data matching the conversion link data is determined from the multiple promotion data to determine that at least one promotion event recorded by the at least one target promotion data caused the conversion event recorded by the target conversion data, wherein each promotion data records a promotion event that occurred on the user terminal and has been exposed to by the user, and the conversion link data includes the target conversion data and at least one process conversion data.

[0032] It should be understood that the term "reach" as used herein refers to the user's perception of a promotional event occurring on a user terminal, such as browsing or playing via the user terminal.

[0033] In the method of the embodiment of the present application, when performing attribution analysis, first, the process conversion data that occurred in the same user terminal device before the target conversion event is found based on the target conversion data. Subsequently, the attribution analysis is performed with reference to the process conversion data, and not only the target conversion data is analyzed, so that the promotion events that contribute to the overall conversion link can be analyzed, thereby improving the accuracy of attribution. In addition, the target type of the above-mentioned process conversion event can be determined by the attribution data administrator according to the actual application scenario, thereby improving the flexibility of the attribution analysis, so that the method can be applied to attribution analysis in different scenarios.

[0034] As described above, the attribution engine may be installed on a related server 120, and an interface is also provided on the server 120 for the client device 110 to access the attribution engine. The client device 110 may be operated by a related attribution data manager 102, and the attribution data manager 102 may use the attribution engine via the client device 110 to complete attribution analysis of target conversion data.

[0035] like Figure 1 The system 100 shown also includes a database 140, which is connected to the server 120 and the client device 110 via the network 130. The database 140 is used to store a large amount of various target conversion data and a large amount of promotion data. The attribution data manager 102 can obtain the conversion data stored in the database 140 via the client device 110 to perform attribution analysis using the attribution engine in the server 12. In addition, the attribution data manager 102 can also upload newly obtained various target conversion data and / or promotion data through the client device 110 to update the database 140. In addition, the server 120 can also receive the conversion data and promotion data uploaded by the application that sets the promotion event, and send it to the database 140.

[0036] The generation process of conversion data and promotion data will be described in detail below. Conversion data and promotion data can be generated by certain applications that can execute promotion events, including but not limited to shopping platform apps, social media apps, etc. During the use of these applications by users, the application will place advertisements of the target object on the user terminal where the application is installed, such as: advertisements of certain products or advertisements of other apps, etc. At this time, the application will generate promotion data, which records the promotion events that occurred on the user terminal. The above-mentioned promotion data can also record some additional information, such as: the contact time of the promotion event, the type of promotion event, the specific content of the advertisement, etc. If a conversion event occurs after this, that is, the user registers the promoted App or the user orders the target object's goods, the application will also generate conversion data, which records the conversion events and the types of conversion events that occurred on the user terminal. The types of conversion events include, for example, operation types such as user registration of a new account or ordering of goods. The above-mentioned applications can upload these data to the database 140 in real time when generating promotion data or conversion data to update the database 140. Therefore, based on the above, there are two ways to update the promotion data or conversion data in the database 140. One is that the attribution data administrator 102 uploads the newly acquired data through the client device 110. These data may be acquired from other channels (for example, data from other databases). The other is that the relevant application directly generates and uploads the data.

[0037] In some related technologies, conversion data and promotion data are mainly generated by different applications, including the media end (i.e., the application that exposes the advertisement) and the conversion end (i.e., the application that is promoted). The above-mentioned application uploads the conversion data and promotion data to the server 120 in real time. The server 120 immediately performs attribution analysis after receiving the conversion data. That is to say, the server 120 only receives and processes a single conversion data, and does not store the conversion data. In an embodiment of the present application, the above-mentioned conversion data and promotion data obtained can be stored in the database 140, and the attribution data administrator 102 can call the conversion data in the database 140 for the database 140 to perform attribution analysis. Therefore, the server 120 in the embodiment of the present application can simultaneously perform attribution analysis on multiple conversion data selected by the attribution data administrator 102, thereby improving the efficiency of the attribution analysis. In addition, the attribution data administrator 102 can upload data by itself. For example, the conversion data from other databases 140 can be uploaded to the database 140, thereby realizing the sharing and common use of conversion data.

[0038] In step 210, the target conversion data that needs to be subjected to attribution analysis is determined from the multiple conversion data pre-stored in the database 140. The attribution data administrator 102 can complete the determination of the above-mentioned target conversion data by operating the interactive interface of the attribution engine via the client device 110. It can be understood that a large amount of conversion data is pre-stored in the database 140, and these data include conversion events that occurred on multiple users' respective user terminals in different time periods. In order to make it easy for the attribution data administrator 102 to find the target conversion data, the attribution engine can pre-prepare a data label table for the conversion data stored in the database 140, and each data is represented by a specific label. The above-mentioned specific label can be, for example, information such as the time when the conversion event occurred, the code of the conversion event, or a brief description of the conversion event. The attribution data administrator 102 can determine the target conversion data by checking, clicking, and selecting on the relevant interactive interface of the attribution engine.

[0039] In related technologies, attribution analysis mostly uses fixed analysis models, such as the last touch attribution model, which uses the last touch promotion event before the conversion event as the attribution result of the conversion event. The disadvantage of this attribution is that it may not be able to achieve accurate attribution in some application scenarios. Figure 3 A schematic diagram 300 is shown comparing the attribution method according to an embodiment of the present application and the attribution method in the related art. Figure 3 Four time nodes that occur in sequence are shown, and the arrows in the figure show the time sequence. At time node a, promotion event A occurs on the user terminal, and the promotion event is about an advertisement for a shopping app; at time node b, the user clicks, downloads, and installs the advertisement for the shopping app, that is, conversion event A' occurs; at time node c, promotion event B occurs on the user terminal, and the promotion event is still about an advertisement for a shopping app; at time node d, the user uses the shopping app and pays, that is, conversion event B' occurs. At this time, if the conversion event B' (that is, the user's payment operation) is attributed, according to the last-touch attribution model in the relevant technology, it can be determined that promotion event B caused conversion event B'. However, for shopping apps, download events are more critical than payment events. Therefore, it may actually be that promotion event A indirectly caused conversion event B'. In this case, the attribution result obtained using the attribution method of the relevant technology is inaccurate. In addition, the attribution method of the relevant technology only supports the attribution of activation events (i.e., the first time a user opens the APP after downloading it). At this time, if you want to analyze the contributing role of the shopping event, the attribution method of the relevant technology cannot support it and cannot provide the positive effect of promoting event B.

[0040] In step 220, the attribution engine allows the attribution data administrator 102 to set the target type of the target conversion event according to the specific situation. In the subsequent steps, the attribution engine first searches for the process conversion data associated with the target conversion data according to the target type. The above process conversion data and the target conversion data come from the same user terminal device, and record the conversion events that occurred before the target conversion event. Then, attribution analysis is performed based on the target conversion data and the newly determined process conversion data. A conversion link data can be created, which includes the target conversion data and at least one process conversion data. In one example, the conversion events to be attributed contained in the target conversion data and the process conversion events contained in the process conversion data can be combined into a list (list), which sorts multiple conversion events in chronological order and has the following format:

[0041] User terminal device ID Process conversion event 1 Process conversion event 2 To be attributed conversion event

[0042] For example, Figure 3 Taking the scenario shown as an example, the conversion event type recorded by the target conversion data is a payment event (i.e., conversion event B'). However, the payment event is not the only key conversion event. There may be other key conversion events, such as the download event before the payment event (i.e., conversion event A'). Therefore, when attributing the payment event, the attribution data administrator 102 can set it so that the attribution engine includes the download event as a process conversion event in the subsequent attribution analysis. The above setting process can still be completed by the attribution data administrator 102 by operating the interactive interface of the attribution engine. For example: the interactive interface can be pre-set to include multiple conversion event types, and the attribution data administrator 102 can select the target type of the conversion event on the interactive interface by checking, clicking, etc.

[0043] It should be noted that the number of target types set can be multiple, that is, the number of process conversion data can be multiple. When multiple process conversion data are selected, it is equivalent to setting different attribution schemes. At this time, the attribution engine will perform attribution according to different attribution schemes, thereby obtaining different attribution analysis results generated for different attribution schemes.

[0044] In step 230, the attribution engine finds the process conversion data associated with the target conversion data from the database 140. The above process conversion data needs to meet two conditions: 1. The process conversion data and the target conversion data come from the same user terminal, because only the data from the same user terminal is the data at different time points on the same link, and the data from different user terminals cannot be associated; 2. The type of conversion event recorded by the process conversion data needs to meet the target type set by the attribution data administrator 102. For example, if the target type is set to order, then the conversion event recorded by the process conversion data must belong to the order event. The attribution engine searches for at least one process conversion data according to the two restrictions mentioned above.

[0045] In step 240, attribution analysis is performed on the entire conversion link data (i.e., the target conversion data and the at least one process conversion data determined in step 230) according to the attribution rule. In one example, the conversion events to be attributed contained in the target conversion data and the process conversion events contained in the process conversion data can be combined into a list to form the conversion link data. The list sorts the multiple conversion events in chronological order and has the following format:

[0046] User terminal device ID Process conversion event 1 Process conversion event 2 To be attributed conversion event

[0047] The above list is merely exemplary, and in other embodiments, the list may include only process transformation event 1, or may include more than two process transformation events.

[0048] The attribution engine searches for target promotion data that matches the target conversion data and at least one process conversion data in the multiple promotion data in the database 140 according to the set attribution rules, so that the promotion events and conversion events recorded by the target promotion data establish an attribution relationship. The subsequent clustering operation based on the attribution relationship can produce a report as an analysis result. For example, taking the simplest last-touch attribution rule as an example, only the promotion events that the user touches before the earliest process conversion event are used as attribution analysis results. For another example, for the linear attribution model, the promotion events that are touched before each process conversion event and the promotion events that are touched before the target conversion event are all used as attribution analysis results, and these promotion events have the same contribution.

[0049] Figure 4 4 is a flow chart illustrating a method 400 for attribution according to another exemplary embodiment. The method 400 may be performed on a server (e.g., Figure 1 , that is, the execution body of each step of method 400 may be Figure 1In some embodiments, the method 400 may be performed on a client device (e.g., Figure 1 110) as shown in FIG. 111. In the following, the steps of method 400 are described in detail by taking the execution subject as server 120 as an example. Figure 4 , the method 400 comprises:

[0050] Step 410, determining target conversion data from multiple conversion data;

[0051] Step 420 , selecting at least one target type from a plurality of types of conversion events recorded in a plurality of conversion data according to the input data;

[0052] Step 430, identifying a unique identification code of the target conversion data;

[0053] Step 440 , selecting a plurality of conversion data having a unique identity code identical to the unique identity code of the conversion data to be attributed from the plurality of conversion data as process conversion data;

[0054] Step 450, determining the attribution field based on the input data;

[0055] Step 460, determining at least one promotion data having an attribution field identical to the attribution field of the target conversion data from the plurality of promotion data, as the target promotion data matched with the process conversion data;

[0056] Step 470, sorting the multiple target promotion data according to the reach time of the promotion events recorded in the target promotion data;

[0057] Step 480, selecting target promotion data that meets the time condition from the sorted plurality of target promotion data according to the selection rule; and

[0058] Step 490: Determine the conversion contribution of multiple promotional events to the conversion events recorded in the conversion link data according to the attribution rules.

[0059] The above steps 410 and 420 are substantially the same as steps 210 and 220 in method 200 and are not described in detail here.

[0060] Each conversion data may also record the unique identity code of the user terminal where the conversion event occurred. When the relevant application generates the conversion data, the unique identity code of the user terminal may be encoded into the conversion data. The above unique identity code may be, for example, the ID of the device. In the case where the user terminal is a mobile phone, the ID of the device may be the mobile phone serial number (IMEI code), which is used to identify each independent mobile phone in the communication network.

[0061] As described above, the process conversion data and the target conversion data come from the same user terminal. In steps 430 to 440, when reading the conversion data, the attribution engine can obtain the unique identity code of the relevant user terminal, and then can determine which conversion data and the target conversion data come from the same user terminal by comparing the unique identity code of the target conversion data record with the unique identity codes of other conversion data records in the database, and take the conversion data of the target type recorded in these conversion data as multiple process conversion data.

[0062] In some other embodiments, steps 430 to 440 may also determine multiple process conversion data in other ways. For example, step 430 may also be to identify multiple operating parameter codes of the target conversion data; step 440 may be to select at least one conversion data from the multiple conversion data whose multiple operating parameter codes are respectively the same as the multiple operating parameter codes of the target conversion data, as multiple process conversion data. The operating parameters may be parameters related to the operating status of the relevant user terminal, such as the power-on time, the power-off time, or whether it is in flight mode. Since a single operating parameter cannot uniquely identify a user terminal, in step 430, multiple operating parameter codes of the target conversion data may be identified, and only when the multiple operating parameter codes of the target conversion data and other conversion data are respectively the same, the conversion data is identified as process conversion data.

[0063] In step 450 to step 460, target promotion data that matches the conversion link data is determined from the multiple promotion data in the database 140. The above matching is achieved by comparing whether the attribution field of the promotion data and the attribution field of the conversion link data are the same. In some embodiments, the above attribution field can be information that records the attributes of the user terminal, such as the unique identity code of the user terminal mentioned above. In other embodiments, the above attribution field can also be information related to the target object of the promotion, such as the target field can be a code that records the information of the promoted product. The promotion event recorded in the target promotion data obtained by comparing the attribution fields is the attribution result of the conversion event recorded in the target conversion data.

[0064] In step 450, the attribution data administrator 102 can independently select the type of attribution field according to the actual application scenario, thereby further improving the degree of freedom of attribution analysis. In addition, in some embodiments, in order to improve the accuracy of attribution analysis, the attribution data administrator 102 can also select multiple attribution fields. The attribution engine will try to match through a variety of attribution methods to achieve a more comprehensive attribution analysis. In the case where the attribution field is a device ID, such as idfa information, after the privacy protocol architecture of Apple system 14.5 is launched, it must be explicitly authorized by the user to obtain it, and the acquisition rate is extremely low. In this scenario, if the device fingerprint or multi-dimensional characteristic parameter is selected as the attribution field, the system will try to perform attribution matching through the corresponding information in order from high to low priority of matching accuracy.

[0065] In steps 470 to 480, at least one process conversion data can be selected from multiple process conversion data according to the occurrence time of the conversion event. In step 470, the target promotion data can be sorted first, and then in step 480, at least one target promotion data that meets the time condition can be selected from the sorted multiple target promotion data. Because the criticality of the promotion event is also related to the order of contact, the target promotion data can be selected according to the order of promotion events. For example: only the promotion data within a preset time period (for example, a 7-day attribution lookback period range) before the conversion event recorded by the target conversion data is selected as the target promotion data, because the promotion event that is contacted after the conversion event recorded by the conversion link data has less impact on the occurrence of the actual conversion. Through the secondary selection of the above steps 470 to 480, promotion events with less criticality can be further excluded, and more critical promotion events can be obtained, thereby further improving the accuracy of the final attribution analysis.

[0066] It should be noted that, in some other embodiments, the secondary selection process such as step 470 and step 480 may not exist, and the target promotion data obtained in step 460 may be directly used for the subsequent attribution analysis step.

[0067] Since there may be multiple target promotion data in step 470, that is, there may be multiple promotion events related to the conversion event recorded by the conversion link data, therefore, in step 480, the conversion contribution of each related promotion event can be further determined to facilitate subsequent in-depth data analysis.

[0068] In step 490, different calculation methods of conversion contribution can be set for different attribution rules. For example, linear attribution means that within the attribution lookback period, all promotional events before the conversion share the conversion contribution equally.

[0069] In some embodiments, in order to visualize the conversion contribution of each promotion event to the conversion event recorded by the conversion link data, the conversion contribution of the promotion event can also be tabulated. Specifically, the attributes of the promotion event can be used as the dimension of the conversion contribution statistics, and these attributes include: media channels, brands, categories, products, projects, advertising positions, advertising creativity, advertising campaign groups, advertising plans, regions, etc. In the case of analyzing multiple different target conversion data, there will be multiple different conversion link data to be attributed. The total conversion contribution of the promotion event recorded by each target promotion data to the conversion events recorded in multiple conversion link data is the proportion of the sum of the conversion contribution of the promotion event to each conversion link data to the sum of all conversion contributions. The dimension of the final calculation of the conversion contribution can be selected by configuring the attributes of the promotion event. For example, taking the attribute of the promotion event as the media channel as an example to calculate the conversion contribution: before the activation behavior of user 1 occurs, it is sequentially reached by four media channels A, B, C, and D. Before the activation behavior of user 2 occurs, it is sequentially reached by two media channels A and E. According to the linear model attribution:

[0070] The activation of user 1 is contributed by 25% each from the four media channels A, B, C, and D, and the activation of user 2 is contributed by 50% each from the two media channels A and E. The conversion contribution of each media channel is:

[0071] Channel A clicks 2 conversions 2 conversion contribution 37.5%;

[0072] Channel B clicks 1 conversion 1 conversion contribution 12.5%;

[0073] C channel clicks 1 conversion 1 conversion contribution 12.5%;

[0074] D channel clicks 1 conversion 1 conversion contribution 12.5%;

[0075] E channel clicks 1 conversion 1 conversion contribution 25.0%.

[0076] It can be understood that the above examples only use the attribute of the promotion event as the media channel to calculate the conversion contribution. In other examples, the conversion contribution can also be calculated based on other attributes of the promotion event.

[0077] Figure 5 FIG. 5 is a flow chart showing a method 500 for determining the contribution of each related promotion event according to an embodiment of the present disclosure, wherein the method calculates the contribution based on a time decay attribution model. Figure 5 As shown, the method 500 includes:

[0078] Step 510, determining a time difference between a reach time of a promotion event recorded in each target promotion data in at least one target promotion data and an occurrence time of a conversion event recorded in the target conversion data; and

[0079] Step 520, determining the conversion contribution of the media channel to which the promotion event recorded in each target promotion data belongs based on the time difference, wherein the conversion contribution of the promotion event with a larger time difference is smaller than the conversion contribution of the promotion event with a smaller time difference.

[0080] In method 500, the contribution of each promotion event may be determined based on attribution rules. The attribution rules may include, for example, time decay attribution. For promotion events on the timeline, promotion events with a shorter time from a conversion event may have a greater conversion contribution, indicating that the promotion event has a greater influence on the conversion event.

[0081] In the method of this embodiment, each conversion data also records the occurrence time of the conversion event, and each promotion data also records the reach time of the promotion event. In step 510, the attribution engine can read the process conversion data and the target promotion data respectively to determine the time difference between the occurrence time of the conversion event and the reach time of the promotion event recorded by them. In step 510, a larger conversion contribution can be assigned to the promotion event with a smaller time difference, and a smaller conversion contribution can be assigned to the promotion event with a larger time difference. Exemplarily, the above conversion contribution can decay exponentially according to the time difference. In one example, the conversion contribution formula is 2^(-t / halflife), where t is the time interval between the reach time of the promotion event and the occurrence time of the conversion event, and halflife is an exponential decay parameter.

[0082] It should be noted that method 500 is only used for the contribution calculation of the time decay attribution model. In other embodiments, methods such as first touch attribution, last touch attribution, linear attribution, etc. can also be used to calculate the conversion contribution of the promotion event. First touch attribution means that within the attribution lookback period, the first touch contributes 100% to the conversion, and the conversion contribution of the remaining touches is 0. Last touch attribution means that within the attribution lookback period, the last touch before the conversion contributes 100% to the conversion, and the conversion contribution of the remaining touches is 0.

[0083] In some other embodiments, the attribution rule may also include linear attribution, that is, all promotion events are assumed to have the same conversion contribution. In this case, the promotion events recorded in each target promotion data in the at least one target promotion data may be determined to have the same conversion contribution.

[0084] According to the embodiments of the present disclosure, the conversion contribution of each promotion event can be determined according to the attribution rules, so as to further analyze the impact of each promotion event on the conversion event recorded by the conversion link data. The conversion contribution can enable relevant data analysts to more intuitively feel the effects of some attribute information of the promotion event, such as the promotion media, promotion creativity, and the portrait information of the conversion user (such as region), which attributes of these dimensions have better conversion effects, so as to purposefully increase specific types of promotion events in subsequent advertising delivery.

[0085] In the method of the above embodiment, although each operation is depicted in the drawings as being in a specific order, this should not be understood as requiring that these operations must be performed in the specific order shown or in sequential order, nor should it be understood as requiring that all the shown operations must be performed to obtain the desired results.

[0086] Figure 6 is a schematic block diagram illustrating an apparatus 600 for attribution according to an exemplary embodiment. Figure 6 As shown, the device 600 includes: a first determination unit 610, configured to determine target conversion data from multiple conversion data, wherein each conversion data records a conversion event that operates on a target object and the type of the conversion event that occurs on a user terminal; a selection unit 620, configured to select at least one target type from the types of multiple conversion events recorded in the multiple conversion data according to input data; a second determination unit 630, configured to determine at least one process conversion data from the multiple conversion data, at least one process conversion data and the target conversion data come from the same user terminal and the type of the recorded conversion event belongs to at least one target type; and a third determination unit 640, configured to determine at least one target promotion data that matches the conversion link data from multiple promotion data according to attribution rules, so as to determine that at least one promotion event recorded by at least one target promotion data causes the conversion event recorded by the target conversion data, wherein each promotion data records a promotion event that has occurred on the user terminal and has been touched by the user, and the conversion link data includes the target conversion data and at least one process conversion data.

[0087] It should be understood that Figure 6 The various modules of the apparatus 600 shown in FIG. 6 can be used in conjunction with the reference Figure 2 The steps in the method 200 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 200 are also applicable to the apparatus 600 and the modules included therein. For the sake of brevity, some operations, features and advantages are not described in detail here.

[0088] Although specific functions are discussed above with reference to specific units, it should be noted that the functions of the various units discussed herein may be divided into multiple units, and / or at least some of the functions of multiple units may be combined into a single unit. The specific unit discussed herein performing an action includes the specific unit itself performing the action, or alternatively the specific unit calling or otherwise accessing another component or unit that performs the action (or performs the action in conjunction with the specific unit). Therefore, the specific unit performing an action may include the specific unit itself that performs the action and / or another unit that the specific unit calls or otherwise accesses to perform the action. As used herein, the phrase "entity A initiates action B" may mean that entity A issues an instruction to perform action B, but entity A itself does not necessarily perform the action B.

[0089] It should also be understood that various techniques may be described herein in the general context of software hardware elements or program units. Figure 6 The various units described can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these units can be implemented as computer program codes / instructions, which are configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these units can be implemented as hardware logic / circuits. For example, in some embodiments, one or more of the first determining unit 610, the selecting unit 620, the second determining unit 630, and the third determining unit 640 can be implemented together in a system on chip (System on Chip, SoC). SoC may include an integrated circuit chip (which includes a processor (e.g., a central processing unit (CPU), a microcontroller, a microprocessor, a digital signal processor (DSP), etc.), a memory, one or more communication interfaces, and / or one or more components in other circuits), and may optionally execute the received program code and / or include embedded firmware to perform functions.

[0090] According to one aspect of the present disclosure, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory. The processor is configured to execute the computer program to implement the steps of any method embodiment described above.

[0091] According to one aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method embodiment described above are implemented.

[0092] According to one aspect of the present disclosure, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the steps of any method embodiment described above are implemented.

[0093] In the following, combined Figure 7 Illustrative examples of such a computer device, non-transitory computer-readable storage medium, and computer program product are described.

[0094] Figure 7 An example configuration of a computer device 700 that can be used to implement the methods described herein is shown. For example, Figure 1 The server 120 and / or the client device 110 shown in FIG. 1 may include an architecture similar to the computer device 700. The above-mentioned user terminal may also be implemented in whole or at least in part by the computer device 700 or a similar device or system.

[0095] Computer device 700 can be a variety of different types of devices. Examples of computer device 700 include, but are not limited to, desktop computers, server computers, laptop or netbook computers, mobile devices (e.g., tablet computers, cellular or other wireless phones (e.g., smart phones), notepad computers, mobile stations), wearable devices (e.g., glasses, watches), entertainment devices (e.g., entertainment appliances, set-top boxes communicatively coupled to display devices, game consoles), televisions or other display devices, automotive computers, and the like.

[0096] The computer device 700 may include at least one processor 702, memory 704, communication interface(s) 706, a display device 708, other input / output (I / O) devices 710, and one or more mass storage devices 712 that can communicate with each other, such as via a system bus 714 or other appropriate connection.

[0097] The processor 702 may be a single processing unit or multiple processing units, all of which may include a single or multiple computing units or multiple cores. The processor 702 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operating instructions. Among other capabilities, the processor 702 may be configured to obtain and execute computer-readable instructions stored in the memory 704, mass storage device 712, or other computer-readable media, such as program codes of an operating system 716, program codes of an application program 718, program codes of other programs 720, and the like.

[0098] The memory 704 and the mass storage device 712 are examples of computer-readable storage media for storing instructions that are executed by the processor 702 to implement the various functions described above. For example, the memory 704 may generally include both volatile memory and non-volatile memory (e.g., RAM, ROM, etc.). In addition, the mass storage device 712 may generally include a hard drive, a solid-state drive, a removable medium, including external and removable drives, a memory card, a flash memory, a floppy disk, an optical disk (e.g., a CD, a DVD), a storage array, a network attached storage, a storage area network, etc. The memory 704 and the mass storage device 712 may all be collectively referred to herein as memory or computer-readable storage media, and may be a non-transitory medium capable of storing computer-readable, processor-executable program instructions as computer program code, which may be executed by the processor 702 as a specific machine configured to implement the operations and functions described in the examples herein.

[0099] A plurality of programs may be stored on the mass storage device 712. These programs include an operating system 716, one or more application programs 718, other programs 720, and program data 722, and they may be loaded into the memory 704 for execution. Examples of such applications or program modules may include, for example, computer program logic (e.g., computer program code or instructions) for implementing the following components / functions: the client application 112 (including the first determination unit 610, the selection unit 620, the second determination unit 630, and the third determination unit 640), the method 200 and / or the method 400, 500 (including any suitable steps of the method 200, 400, 500), and / or other embodiments described herein.

[0100] Although in Figure 7 700, but modules 716, 718, 720, and 722, or portions thereof, may be implemented using any form of computer-readable media accessible by computer device 700. As used herein, "computer-readable media" includes at least two types of computer-readable media, namely, computer-readable storage media and communication media.

[0101] Computer-readable storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information, such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media include but are not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD), or other optical storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device, or any other non-transmission medium that can be used to store information for access by a computer device. In contrast, communication media can embody computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism. Computer-readable storage media defined herein do not include communication media.

[0102] One or more communication interfaces 706 are used to exchange data with other devices, such as through a network, a direct connection, etc. Such communication interfaces can be one or more of the following: any type of network interface (e.g., a network interface card (NIC)), a wired or wireless (such as IEEE 802.11 wireless LAN (WLAN)) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a cellular network ... TM The communication interface 706 may facilitate communication within a variety of network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, etc. The communication interface 706 may also provide for communication with external storage devices (not shown) such as in a storage array, network attached storage, storage area network, etc.

[0103] In some examples, a display device 708 such as a monitor may be included for displaying information and images to the user. Other I / O devices 710 may be devices that receive various inputs from the user and provide various outputs to the user, and may include a touch input device, a gesture input device, a camera, a keyboard, a remote control, a mouse, a printer, an audio input / output device, and the like.

[0104] The technology described herein can be supported by these various configurations of the computer device 700, and is not limited to the specific examples of the technology described herein. For example, the function can also be implemented in whole or in part on the "cloud" by using a distributed system. The cloud includes and / or represents a platform for resources. The platform abstracts the underlying functions of the hardware (e.g., server) and software resources of the cloud. Resources can include applications and / or data that can be used when performing computing processing on a server away from the computer device 700. Resources can also include services provided through the Internet and / or through a subscriber network such as a cellular or Wi-Fi network. The platform can abstract resources and functions to connect the computer device 700 to other computer devices. Therefore, the implementation of the functions described herein can be distributed throughout the cloud. For example, the functions can be implemented partially on the computer device 700 and partially through a platform that abstracts the functions of the cloud.

[0105] Although the present disclosure has been illustrated and described in detail in the drawings and the foregoing description, such illustration and description should be considered illustrative and schematic, not restrictive; the present disclosure is not limited to the disclosed embodiments. By studying the drawings, the disclosure and the appended claims, those skilled in the art will be able to understand and implement variations to the disclosed embodiments when practicing the claimed subject matter. In the claims, the word "comprising" does not exclude other elements or steps that are not listed, the indefinite article "a" or "an" does not exclude a plurality, the term "plurality" means two or more, and the term "based on" should be interpreted as "based at least in part on". The mere fact that certain measures are recorded in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Claims

1. A method for attribution, comprising: Determining target conversion data from a plurality of conversion data, wherein each conversion data in the plurality of conversion data records a conversion event occurring on a user terminal and operating on a target object and a type of the conversion event; According to the input data, selecting at least one target type from a plurality of types of conversion events recorded in the plurality of conversion data; Determine at least one process conversion data from the plurality of conversion data, wherein the at least one process conversion data and the target conversion data are from the same user terminal and a type of the recorded conversion event belongs to the at least one target type; and According to the attribution rule, at least one target promotion data matching the conversion link data is determined from the multiple promotion data to determine that at least one promotion event recorded by the at least one target promotion data caused the conversion event recorded by the target conversion data, wherein each promotion data records a promotion event that occurred on the user terminal and has been touched by the user, and the conversion link data includes the target conversion data and the at least one process conversion data, After determining at least one target promotion data matching the conversion link data from the plurality of promotion data, the method further includes: sorting the at least one target promotion data according to the reaching time of the promotion event recorded in the at least one target promotion data; and According to the selection rule, at least one target promotion data that meets the time requirement is selected from the at least one sorted target promotion data, thereby excluding promotion events with low criticality.

2. The method according to claim 1, wherein: Each conversion data also records a unique identity code of the user terminal, wherein determining at least one process conversion data from the plurality of conversion data comprises: A unique identification code that identifies the target conversion data; and At least one conversion data having a unique identification code identical to the unique identification code of the target conversion data is selected from the plurality of conversion data as the at least one process conversion data.

3. The method according to claim 1, wherein: Each of the conversion data further records a plurality of operating parameter codes of the user terminal, wherein determining at least one process conversion data from the plurality of conversion data further comprises: identifying a plurality of operation parameter codes of the target conversion data; and At least one conversion data having a plurality of operation parameter codes which are respectively the same as the plurality of operation parameter codes of the target conversion data is selected from the plurality of conversion data as the at least one process conversion data.

4. The method according to claim 1, wherein: According to the attribution rule, determining at least one target promotion data that matches the at least one process conversion data respectively from the plurality of promotion data includes: Determining an attribution field based on the input data; For each process transformation data of the at least one process transformation data: At least one promotion data having an attribution field identical to the attribution field of the process conversion data is determined from the plurality of promotion data as target promotion data matched with the process conversion data.

5. The method according to claim 1, further comprising: After determining at least one target promotion data matching the conversion link data from the multiple promotion data according to the attribution rules: According to the attribution rule, the conversion contribution of the promotion event recorded in the at least one target promotion data to the conversion event recorded in the conversion link data is determined.

6. The method according to claim 5, wherein: The attribution rule includes linear attribution, wherein, according to the attribution rule, determining the conversion contribution of the promotion event recorded in the at least one target promotion data to the conversion event recorded in the conversion link data includes: The promotion events recorded in the at least one target promotion data are determined to have the same conversion contribution.

7. The method according to claim 5, wherein: The attribution rule includes time decay attribution, each conversion data further records the occurrence time of the conversion event, and each promotion data further records the reach time of the promotion event, wherein, according to the attribution rule, determining the conversion contribution of the promotion event recorded in the at least one target promotion data to the conversion event recorded in the conversion link data further includes: Determine a time difference between a reach time of a promotion event recorded in each target promotion data in the at least one target promotion data and an occurrence time of a conversion event recorded in the target conversion data; and Based on the time difference, determine the conversion contribution of the promotion event recorded in the at least one target promotion data to the conversion event recorded in the conversion link data, wherein the conversion contribution of the promotion event with a larger time difference is smaller than the conversion contribution of the promotion event with a smaller time difference.

8. A method for calculating attribution contribution, comprising: For a plurality of different target conversion data, executing the method for attribution according to any one of claims 5 to 7 multiple times to generate a plurality of conversion link data respectively containing different target conversion data; and Generate the total conversion contribution of the promotion event recorded in each target promotion data to the multiple conversion link data, wherein the total conversion contribution corresponding to the promotion event recorded in each target promotion data is the ratio of the sum of the conversion contribution of the promotion event to each conversion link data to the sum of all conversion contributions.

9. An apparatus for attribution, comprising: A first determining unit is configured to determine target conversion data from a plurality of conversion data, wherein each conversion data in the plurality of conversion data records a conversion event occurring on a user terminal and operating on a target object and a type of the conversion event; A selection unit configured to select at least one target type from a plurality of types of conversion events recorded in the plurality of conversion data according to input data; A second determining unit is configured to determine at least one process conversion data from the plurality of conversion data, wherein the at least one process conversion data and the target conversion data are from the same user terminal and a type of the recorded conversion event belongs to the at least one target type; and a third determination unit configured to determine, according to the attribution rule, at least one target promotion data matching the conversion link data from the plurality of promotion data, so as to determine that at least one promotion event recorded by the at least one target promotion data caused a conversion event recorded by the target conversion data, wherein each promotion data records a promotion event that occurred on a user terminal and has been touched by the user, and the conversion link data includes the target conversion data and the at least one process conversion data, After determining at least one target promotion data matching the conversion link data from the plurality of promotion data, the method further includes: sorting the at least one target promotion data according to the reaching time of the promotion event recorded in the at least one target promotion data; and According to the selection rule, at least one target promotion data that meets the time requirement is selected from the at least one sorted target promotion data, thereby excluding promotion events with low criticality.

10. A computer device comprising: at least one processor; as well as at least one memory having a computer program stored thereon, Wherein, when the computer program is executed by the at least one processor, the at least one processor is caused to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 8.

Images