Data processing method and device, electronic equipment and readable storage medium

Abstract

The invention provides a data processing method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of computers and Internet. The data processing method is applied to a server and comprises the steps that product activation information uploaded by a client side is obtained, and the product activation information is collected by the client side; generating an activation vector according to the product activation information; a plurality of advertisement click vectors are obtained, the advertisement click vectors are generated according to advertisement click information, and the advertisement click information is collected by the webpage; determining the similarity between the activation vector and each advertisement click vector; determining a target advertisement click vector with the highest similarity with the activation vector in the plurality of advertisement click vectors; and determining that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector. According to the embodiment of the invention, the activation reason of the client product can be accurately attributed.

Description

Technical Field

[0001] The present disclosure relates to the field of computer and Internet technology, and in particular to a data processing method and device, an electronic device, and a computer-readable storage medium. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] In the scenario of off-site delivery on the client (such as application (APP)), in order to better measure the delivery effect, it is necessary to attribute the off-site delivery scenario. At present, the attribution methods in the industry are mainly divided into two types: precise attribution and fuzzy attribution. Precise attribution mainly uses device identifiers such as Identifier for Advertising (IDFA), International Mobile Equipment Identity (IMEI), OpenAnonymousDeviceIdentifier (oaid), etc. as the basis for attribution, and can also be attributed in the form of shared clipboard data; when it is impossible to attribute through a consistent attribution parameter such as device identification number (ID), the method of matching through other parameters is called fuzzy attribution, such as Internet Protocol Address (IP) + User-Agent (UA) and other methods. There is also a method of attribution using device fingerprints. Usually, when advertising is delivered in the client (such as APP), information such as device ID can be obtained, but in the scenario of web page (HTML5, H5) delivery, since the device ID cannot be obtained, advertising attribution is usually not possible.

[0004] Therefore, the technical problem to be solved by this application is how to attribute client activation to advertisements in a web page delivery scenario. Summary of the invention

[0005] The purpose of the present disclosure is to provide a data processing method, device, electronic device and computer-readable storage medium, which can accurately attribute advertisements placed on web pages.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] The disclosed embodiment provides a data processing method, including: obtaining product activation information uploaded by a client, wherein the product activation information is collected by the client; generating an activation vector according to the product activation information; obtaining multiple advertisement click vectors, wherein the advertisement click vector is generated according to advertisement click information, wherein the advertisement click information is collected by a web page; determining the similarity between the activation vector and each advertisement click vector; determining a target advertisement click vector having the highest similarity to the activation vector among the multiple advertisement click vectors; and determining that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0008] In some embodiments, the multiple ad click vectors include a first ad click vector, a second ad click vector, and a third ad click vector; wherein, obtaining multiple ad click vectors includes: obtaining a device graph, the device graph includes multiple nodes, each node corresponds to an ad click vector, the edge between two nodes in the device graph is used to indicate the similarity between the two nodes, the device graph includes a first node, a second node, and a third node, the first node is connected to the second node and the third node, the first node corresponds to the first ad click vector, the second node corresponds to the second ad click vector, and the third node corresponds to the third ad click vector; wherein , determine the similarity between the activation vector and the first node vector; determine the first vector similarity between the activation vector and the first ad click vector; determine the second vector similarity between the activation vector and the second ad click vector; determine the third vector similarity between the activation vector and the third ad click vector; determine the second node similarity between the first node and the second node; determine the third node similarity between the first node and the third node; weight the first vector similarity, the second vector similarity and the third vector similarity by the second node similarity and the third node similarity to determine the similarity between the activation vector and the first node vector.

[0009] In some embodiments, the first vector similarity, the second vector similarity and the third vector similarity are weighted by the second node similarity and the third node similarity to determine the similarity between the activation vector and the first node vector, including: determining the first node similarity between the first node and the first node; normalizing the first node similarity, the second node similarity and the third node similarity to obtain a first normalized similarity, a second normalized similarity and a third normalized similarity; weighting the first vector similarity, the second vector similarity and the third vector similarity by the first normalized similarity, the second normalized similarity and the third normalized similarity to determine the similarity between the activation vector and the first node vector.

[0010] In some embodiments, the product activation information includes both the device information, network information and environment information corresponding to the client when the activation action occurs, which are collected by the client through the client information collection interface, and the device information, network information and web page environment information corresponding to the web page when the activation action occurs, which are collected by the client through the built-in web page information collection interface.

[0011] In some embodiments, the product activation information includes both the device information, network information and environment information corresponding to the client when the activation action occurs, which are collected by the client through the client information collection interface, and the device information, network information and web page environment information corresponding to the web page when the activation action occurs, which are collected by the client through the built-in web page information collection interface.

[0012] The present disclosure provides a data processing method, which is applied to a web page, and the method also includes: determining that an advertisement click behavior occurs; collecting device information, network information and web page environment information corresponding to the web page when the advertisement click behavior occurs through the web page information collection interface of the web page; generating advertisement click information according to the device information corresponding to the web page, the network information and web page environment information corresponding to the web page when the advertisement click behavior occurs; uploading the advertisement click information to a server, so that when the server receives product activation information, it matches the activation vector corresponding to the product activation information with the advertisement click vector corresponding to the advertisement click information, so as to determine whether the activation operation corresponding to the product activation information is caused by the advertisement click behavior.

[0013] The disclosed embodiment provides a data processing method, which is applied to a client, and the method includes: determining that an activation action occurs on the client; collecting, through a client information collection interface of the client, device information corresponding to the client, network information corresponding to the client, and client environment information when the activation action occurs; generating product activation information through the device information corresponding to the client, the network information and environment information corresponding to the client when the activation action occurs; uploading the product activation information to a server so that the server matches a product activation vector corresponding to the product activation information with an advertisement click vector corresponding to multiple advertisement click information received by the server, so as to determine a target advertisement click vector having the highest similarity to the activation vector among the multiple advertisement click vectors, and determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0014] In some embodiments, the data processing method also includes: the client implicitly loads a built-in web page and calls a web page information collection interface corresponding to the web page to collect device information corresponding to the web page, network information corresponding to the web page when the activation action occurs, and web page environment information; wherein, the product activation information is generated through the device information corresponding to the client, the network information and environment information corresponding to the client when the activation action occurs, including: the product activation information is generated through the device information corresponding to the client, the network information and environment information corresponding to the client when the activation action occurs, the device information corresponding to the web page, and the network information and web page environment information corresponding to the web page when the activation action occurs.

[0015] The embodiment of the present disclosure provides a data processing device, including: an activation information acquisition module, an activation vector generation module, an advertisement click vector acquisition module, a similarity determination module, a target advertisement click vector determination module, and an attribution module.

[0016] Among them, the activation information acquisition module is used to obtain product activation information uploaded by the client, and the product activation information is collected by the client; the activation vector generation module can be used to generate an activation vector based on the product activation information; the advertisement click vector acquisition module can be used to obtain multiple advertisement click vectors, wherein the advertisement click vector is generated based on advertisement click information, and the advertisement click information is collected from the web page; the similarity determination module can be used to determine the similarity between the activation vector and each advertisement click vector; the target advertisement click vector determination module can be used to determine the target advertisement click vector with the highest similarity to the activation vector among the multiple advertisement click vectors; the attribution module can be used to determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0017] An embodiment of the present disclosure provides an electronic device, which includes: a memory and a processor; the memory is used to store computer program instructions; the processor calls the computer program instructions stored in the memory to implement any of the data processing methods described above.

[0018] The embodiment of the present disclosure provides a computer-readable storage medium on which computer program instructions are stored to implement any of the data processing methods described above.

[0019] The embodiment of the present disclosure provides a computer program product or a computer program, which includes computer program instructions stored in a computer-readable storage medium. The computer program instructions are read from the computer-readable storage medium, and a processor executes the computer program instructions to implement the above data processing method.

[0020] The data processing method, device, electronic device and computer-readable storage medium provided by the embodiments of the present disclosure can accurately determine the advertisement click behavior that caused the client activation by performing similarity matching between the product activation vector corresponding to the product activation information uploaded by the client and the advertisement click vector uploaded by the web page.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0023] Figure 1 A schematic diagram of a scenario that can be applied to a data processing method or a data processing device in an embodiment of the present disclosure is shown.

[0024] Figure 2 The invention is a flowchart of a data processing method according to an exemplary embodiment.

[0025] Figure 3 The figure is a flow chart of a method for determining similarity according to an exemplary embodiment.

[0026] Figure 4 The figure is a flow chart of a method for determining similarity according to an exemplary embodiment.

[0027] Figure 5The invention is a flowchart of a data processing method according to an exemplary embodiment.

[0028] Figure 6 The present invention is a flowchart of a delivery attribution method according to an exemplary embodiment.

[0029] Figure 7 The present invention is a flowchart of a delivery attribution method according to an exemplary embodiment.

[0030] Figure 8 The figure is a structural diagram of an advertising attribution method according to an exemplary embodiment.

[0031] Fig. 9 It is a block diagram of a data processing device according to an exemplary embodiment.

[0032] Fig.10 is a block diagram of a data processing device according to an exemplary embodiment. The above data processing device can be applied to web pages.

[0033] Fig.11 It is a block diagram of a data processing device according to an exemplary embodiment.

[0034] Fig.12 A schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0035] 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 disclosure 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.

[0036] Those skilled in the art will appreciate that the embodiments of the present disclosure may be a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0037] The features, structures or characteristics described in the present disclosure 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 disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0038] The accompanying drawings are only schematic diagrams of the present disclosure, and the same reference numerals in the drawings represent the same or similar parts, so their repeated description will be omitted. Some block diagrams shown in the accompanying drawings do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0039] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and steps, nor must they be executed in the order described. For example, some steps can be decomposed, and some steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0040] In the description of the present disclosure, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a kind of association relationship describing the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different; the terms "comprising", "including" and "having" are used to express the meaning of open inclusion and mean that in addition to the listed elements / components / etc., there may be other elements / components / etc.

[0041] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0042] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0043] First, some terms involved in the embodiments of the present disclosure are explained below to facilitate understanding by those skilled in the art.

[0044] Device fingerprint: refers to the device characteristics or unique device identifier that can be used to uniquely identify the device.

[0045] RSA encryption: is an asymmetric encryption algorithm that uses different keys for encryption or decryption.

[0046] Software Development Kit: Software Development Kit, SDK. Generally, some independent functions are packaged together and provided to the outside as an SDK.

[0047] WebSDK: SDK for front-end pages, usually implemented in javascript.

[0048] Client SDK: SDK used by the application APP, embedded in the APP.

[0049] Device vector: A set of vectors used to characterize device characteristics.

[0050] Off-site traffic: In simple terms, it means that the buyer sees the product information on other websites or other apps, then develops a desire to buy or use the product, and clicks on the product ad or link to return to the product website to place an order. In this process, the buyer learns about the general information of the product through other traffic channels. The buyer may want to click on the ad or link to learn about the product information. This process is to learn about the product through off-site traffic.

[0051] The foregoing introduces some terms and concepts involved in the embodiments of the present disclosure. The following introduces the technical features involved in the embodiments of the present disclosure.

[0052] In order to achieve rapid user growth, online advertising aimed at promoting clients (such as apps) is an important way for many platforms to acquire new users. With the development of mobile Internet, there are more and more channels for app promotion. In addition to third-party apps, HyperText Markup Language 5 (HTML5) has become another main battlefield for app promotion. Among them, HTML is used to form web documents.

[0053] Then, how to attribute and match the client activation with the ad click behavior on the web page is a pain point that the industry needs to solve.

[0054] In response to the above problems, this application provides the following technical solutions.

[0055] The exemplary embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0056] Figure 1 A schematic diagram of a scenario that can be applied to a data processing method or a data processing device in an embodiment of the present disclosure is shown.

[0057] Please refer to Figure 1 , which shows a schematic diagram of an implementation environment provided by an exemplary embodiment of the present disclosure.

[0058] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0059] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, virtual reality devices, smart homes, etc.

[0060] The server 105 may be a server that provides various services, such as a background management server that provides support for devices operated by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received request data, and feed back the processing results to the terminal device.

[0061] The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as basic cloud computing services such as big data and artificial intelligence platforms, etc. The present disclosure does not impose any restrictions on this.

[0062] Server 105 may, for example, obtain product activation information uploaded by the client, where the product activation information is collected by the client; server 105 may, for example, generate an activation vector based on the product activation information; server 105 may, for example, obtain multiple advertisement click vectors, where the advertisement click vector is generated based on advertisement click information, where the advertisement click information is collected from the web page; server 105 may, for example, determine the similarity between the activation vector and each advertisement click vector; server 105 may, for example, determine a target advertisement click vector having the highest similarity to the activation vector among multiple advertisement click vectors; server 105 may, for example, determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0063] It should be understood that Figure 1 The number of terminal devices, networks and servers in the figure is only for illustration. The server 105 may be a physical server or may be composed of multiple servers. According to actual needs, it may have any number of terminal devices, networks and servers.

[0064] Figure 2 is a flow chart of a data processing method according to an exemplary embodiment. The method provided by the embodiment of the present disclosure can be executed by any electronic device with computing and processing capabilities. For example, the method can be executed by the above Figure 1 The server or terminal device in the embodiment may be executed, or the server and the terminal device may be executed together. In the following embodiments, the server is used as the execution subject for example, but the present disclosure is not limited to this.

[0065] Reference Figure 2 The data processing method provided by the embodiment of the present disclosure may include the following steps.

[0066] Step S202: Acquire product activation information uploaded by the client, where the product activation information is collected by the client.

[0067] In some embodiments, after some clients (such as application programs APP) are activated, the clients may upload product activation information to the server.

[0068] In some embodiments, the activation information may be information collected by the client through a client information collection interface (such as an information collection interface corresponding to a client SDK). The collected information may be, for example, device information, network information, and environmental information corresponding to the client when the activation action occurs (the information collected by the client information collection interface may refer to Table 1).

[0069] In some embodiments, the product activation information may include the device information, network information, and environment information corresponding to the client when the activation action occurs, which are collected by the client through the client information collection interface. The product activation information may also include the device information, network information, and web page environment information corresponding to the web page when the activation action occurs, which are collected by the client through the built-in web page information collection interface (the information collected by the web page information collection interface can be referred to in Table 2).

[0070] Among them, as shown in Table 1, the device information collected by the client information collection interface may include the screen size, device ID, CPU information and memory information of the device where the client is located when the activation action occurs; the network information collected by the client information collection interface may include the SIM information, network type, network strength and operator name corresponding to the activation action when the activation action occurs; the environmental information collected by the client information collection interface may include the system version, platform information, language used and power information.

[0071] Table 1

[0072]

[0073] Step S204: Generate an activation vector according to the product activation information.

[0074] In some embodiments, the product activation information may be first vectorized to obtain an initial vector, and then feature extraction may be performed on the initial vector using a neural network model to obtain the activation vector.

[0075] In some embodiments, the product activation information may be arranged according to preset positions to generate an array, and then the array is used as the activation vector.

[0076] In some embodiments, the product activation information may be arranged at preset positions to generate a product activation array, and then the product activation array may be vectorized, and finally the vectorized data may be normalized to obtain the activation vector.

[0077] In short, this application does not limit the generation process of the above activation vector.

[0078] Step S206, obtaining multiple advertisement click vectors, wherein the advertisement click vectors are generated according to advertisement click information, wherein the advertisement click information is collected from the web page.

[0079] In some embodiments, the above-mentioned advertisement click information may be information collected by a web page information collection interface (or a browser information collection interface) corresponding to the network element when an advertisement click action occurs.

[0080] In some embodiments, the above-mentioned advertisement click information may include information as shown in Table 2. For example, when the advertisement click action occurs, the device information collected by the web page information collection interface may include the screen resolution, device brand or device model shown in Table 2; for another example, when the advertisement click action occurs, the network information collected by the web page information collection interface may include the IP or network type shown in Table 2; for example, when the advertisement click action occurs, the environment information collected by the web page information collection interface may include the system font, system language and color gamut shown in Table 2.

[0081] Table 2

[0082]

[0083] It should be noted that the type of information collected by the web page information collection interface (or browser information collection interface) is different from the type of information collected by the client information collection interface.

[0084] Step S208: determining the similarity between the activation vector and each advertisement click vector.

[0085] In some embodiments, if the activation vector and the ad click vector are feature vectors output by a neural network model, a cosine value or the like between the activation vector and the ad click vector may be determined as the similarity.

[0086] In some embodiments, if the activation vector and the ad click vector are arrays, the activation vector can be segmented according to the position corresponding to the data type (such as the position of the data corresponding to the device information), and then each segmented part can be compared for similarity separately to determine the similarity of the entire vector.

[0087] Step S210: determining a target advertisement click vector having the highest similarity to the activation vector among multiple advertisement click vectors.

[0088] Step S212, determining whether the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0089] Through the above method, the product activation information collected by the client information collection interface and the advertisement click data collected by the web page information collection interface can be accurately matched to accurately determine which advertisement click caused the client product activation.

[0090] Figure 3 The figure is a flow chart of a method for determining similarity according to an exemplary embodiment.

[0091] In some embodiments, obtaining multiple advertisement click vectors may include: obtaining a device graph.

[0092] The device graph obtained above may include multiple nodes (such as Figure 8 The device graph shown in the upper part may include multiple nodes such as id1, id2, id3, etc.), where each node corresponds to an ad click vector, and the edge between two nodes in the device graph is used to indicate the similarity between the ad click vectors corresponding to the two nodes (such as Figure 8 ), the device map includes the first node (as shown in the upper part of Figure 8 id3 in), the second node (such as Figure 8 id1 in ) and the third node (such as Figure 8 id4), the first node is connected to the second node and the third node, the first node corresponds to the first advertisement click vector, the second node corresponds to the second advertisement click vector, and the third node corresponds to the third advertisement click vector.

[0093] In some embodiments, the multiple advertisement click vectors obtained may include a first advertisement click vector (eg, Figure 8 The ad click vector corresponding to id3 in ), the second ad click vector (such as Figure 8 The ad click vector corresponding to id1 in ) and the third ad click vector (such as Figure 8 The ad click vector corresponding to id4 in ).

[0094] In the following embodiments, the similarity determination process may be explained by taking the similarity between the product activation vector and the first advertisement click vector as an example, but those skilled in the art may determine the similarity between the product activation vector and other advertisement click vectors according to the following embodiments.

[0095] Reference Figure 3 The similarity method provided by the embodiment of the present disclosure may include the following steps.

[0096] Step S302: determine a first vector similarity between the activation vector and the first advertisement click vector.

[0097] For example, we can determine the activation vector and Figure 8 The first vector similarity between the advertisement click vectors corresponding to the id3 node in .

[0098] Step S304: determine the second vector similarity between the activation vector and the second advertisement click vector.

[0099] For example, we can determine the activation vector and Figure 8 The second vector similarity between the advertisement click vectors corresponding to the id1 node in .

[0100] Step S306: determine a third vector similarity between the activation vector and the third advertisement click vector.

[0101] For example, we can determine the activation vector and Figure 8 The third vector similarity between the ad click vectors corresponding to the id4 node in .

[0102] Step S308: determining the second node similarity between the first node and the second node.

[0103] In some embodiments, it may be assumed that the second node similarity between the first node and the second node is res2.

[0104] Step S310, determining a third node similarity between the first node and the third node.

[0105] In some embodiments, it may be assumed that the second node similarity between the first node and the second node is res3.

[0106] Step S312: weighting the first vector similarity, the second vector similarity and the third vector similarity by the second node similarity and the third node similarity to determine the similarity between the activation vector and the first node vector.

[0107] The weighted processing of the first vector similarity, the second vector similarity and the third vector similarity by the second node similarity and the third node similarity to determine the similarity between the activation vector and the first node vector may specifically be the following steps.

[0108] Figure 4 The figure is a flow chart of a method for determining similarity according to an exemplary embodiment.

[0109] refer to Figure 4 , the above similarity determination method may include the following steps.

[0110] Step S402: determining the first node similarity between the first nodes.

[0111] In some embodiments, the first node similarity may be 1.

[0112] Step S404 , normalizing the first node similarity, the second node similarity, and the third node similarity to obtain a first normalized similarity, a second normalized similarity, and a third normalized similarity.

[0113] In some embodiments, similarity processing may be performed between the first node similarity 1, the second node similarity res2 and the third node similarity res3 so that the sum of the first node similarity, the second node similarity and the third node similarity is 1, and the normalized value can represent the proportion of their similarity.

[0114] Step S406 , weighting the first vector similarity, the second vector similarity and the third vector similarity by using the first normalized similarity, the second normalized similarity and the third normalized similarity to determine the similarity between the activation vector and the first node vector.

[0115] It can be understood that the second node vector (or the third node vector) and the first node vector are related vectors with a similarity greater than a certain threshold. If the activation vector is related to the second node vector, then the correlation between the activation vector and the second node vector can be superimposed on the correlation between the activation vector and the first node vector to determine the similarity between the activation vector and the first node vector.

[0116] Through the above method, the similarity between the activation vector and the first node vector can be combined with the similarity between the activation vector and the correlation vector of the first node vector to supplement and enhance the similarity between the activation vector and the first node vector to more accurately determine the similarity between the activation vector and the first node vector.

[0117] Figure 5 is a flow chart of a data processing method according to an exemplary embodiment. The method provided by the embodiment of the present disclosure can be executed by any electronic device with computing and processing capabilities. For example, the method can be executed by the above Figure 1 The server or terminal device in the embodiment may be executed, or the server and the terminal device may be executed together. In the following embodiments, the terminal device is taken as an example for illustration, but the present disclosure is not limited to this.

[0118] In some embodiments, the following embodiments may be applied to a web page.

[0119] Reference Figure 5 The data processing method provided by the embodiment of the present disclosure may include the following steps.

[0120] Step S502: Determine whether an advertisement click occurs.

[0121] In some embodiments, when an advertisement behavior occurs on a terminal device, it can be determined that an advertisement click behavior has occurred on the terminal device. For example, the advertisement click behavior may occur in a client, or advertisement click information may occur in a web page, and this application does not limit this.

[0122] Step S504, collecting device information, network information and web page environment information corresponding to the web page when the advertisement click behavior occurs through the web page information collection interface of the web page.

[0123] In some embodiments, when an advertisement click occurs in a client or on a web page, it may be necessary to collect and upload the advertisement click information through the web page.

[0124] In some embodiments, the web page may collect device information, network information, and web page environment information corresponding to the web page when the advertisement click behavior occurs through the web page information collection interface of the web page.

[0125] Step S506, generating advertisement click information according to the device information corresponding to the web page, the network information corresponding to the web page when the advertisement click behavior occurs, and the web page environment information.

[0126] In some embodiments, the advertisement click information may be generated based on the device information corresponding to the webpage, the network information corresponding to the webpage when the advertisement click behavior occurs, and the webpage environment information.

[0127] Step S508, uploading the advertisement click information to the server, so that when the server receives the product activation information, it matches the activation vector corresponding to the product activation information with the advertisement click vector corresponding to the advertisement click information to determine whether the activation operation corresponding to the product activation information is caused by the advertisement click behavior.

[0128] In some embodiments, the web page will upload advertisement click information to the server once when different click behaviors occur.

[0129] In some embodiments, when the server receives the ad click information sent by the web page, it generates an ad click vector based on the ad click information, and then calculates the similarity between the ad click vector corresponding to the ad click information received this time and the ad click vector corresponding to each node in the device graph, and then determines in the device graph a target ad click vector whose similarity with the ad click vector uploaded this time is greater than a certain threshold, and finally adds the ad click vector uploaded this time to the device graph, and connects the ad click vector uploaded this time with the target ad click vector.

[0130] Figure 6 is a flowchart of a delivery attribution method according to an exemplary embodiment. The method provided by the embodiment of the present disclosure can be executed by any electronic device with computing and processing capabilities. For example, the method can be executed by the above Figure 1 The server or terminal device in the embodiment may be executed, or the server and the terminal device may be executed together. In the following embodiments, the terminal device is taken as an example for illustration, but the present disclosure is not limited to this.

[0131] In some embodiments, the following embodiments may be applied to a client.

[0132] Reference Figure 6 The delivery attribution method provided by the embodiment of the present disclosure may include the following steps.

[0133] Step S602: Determine whether the client has activated the action.

[0134] In some embodiments, an activation action is considered to have occurred when the client product is activated.

[0135] Step S604: collecting device information corresponding to the client, network information corresponding to the client, and client environment information when the activation action occurs through the client information collection interface of the client.

[0136] In some embodiments, when the client is activated, the client can collect the device information corresponding to the client, the network information corresponding to the client and the client environment information when the activation action occurs through the client information collection interface (for example, refer to the corresponding information in Table 1).

[0137] Step S606: Generate product activation information through the device information corresponding to the client, the network information and environment information corresponding to the client when the activation action occurs.

[0138] Step S608, upload the product activation information to the server so that the server can match the product activation vector corresponding to the product activation information with the advertisement click vectors corresponding to the multiple advertisement click information received by the server, so as to determine the target advertisement click vector with the highest similarity to the activation vector among the multiple advertisement click vectors, and determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0139] In some embodiments, after the client uploads the product activation information to the server, the server performs the following operations: obtain the product activation information uploaded by the client, where the product activation information is collected by the client; generate an activation vector based on the product activation information; obtain multiple advertisement click vectors, where the advertisement click vector is generated based on the advertisement click information, where the advertisement click information is collected from the web page; determine the similarity between the activation vector and each advertisement click vector; determine a target advertisement click vector with the highest similarity to the activation vector among multiple advertisement click vectors; and determine that the client's activation is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0140] Figure 7 is a flowchart of a delivery attribution method according to an exemplary embodiment. The method provided by the embodiment of the present disclosure can be executed by any electronic device with computing and processing capabilities. For example, the method can be executed by the above Figure 1 The server or terminal device in the embodiment may be executed, or the server and the terminal device may be executed together. In the following embodiments, the terminal device is taken as an example for illustration, but the present disclosure is not limited to this.

[0141] In some embodiments, the following embodiments may be applied to a client.

[0142] Reference Figure 7 The delivery attribution method provided by the embodiment of the present disclosure may include the following steps.

[0143] Step S702: Determine whether the client has activated the action.

[0144] Step S704: collecting device information corresponding to the client, network information corresponding to the client, and client environment information when the activation action occurs through the client information collection interface of the client.

[0145] In some embodiments, when the client is activated, the client can collect the device information corresponding to the client, the network information corresponding to the client and the client environment information when the activation action occurs through the client information collection interface (for example, refer to the corresponding information in Table 1).

[0146] Step S706, the client implicitly loads the built-in web page and calls the web page information collection interface corresponding to the web page to collect the device information corresponding to the web page, the network information corresponding to the web page when the activation action occurs, and the web page environment information.

[0147] In some embodiments, when the client is activated, the client will also implicitly load the built-in web page (or browser) and call the web page (browser) information collection interface corresponding to the web page (or browser) to collect the device information corresponding to the web page, the network information corresponding to the web page when the activation action occurs, and the web page environment information (for example, refer to the information shown in Table 2).

[0148] Step S708, generating product activation information through the device information corresponding to the client, the network information and environment information corresponding to the client when the activation action occurs, the device information corresponding to the webpage, and the network information and webpage environment information corresponding to the webpage when the activation action occurs.

[0149] Step S710, upload the product activation information to the server so that the server can match the product activation vector corresponding to the product activation information with the advertisement click vectors corresponding to the multiple advertisement click information received by the server, so as to determine the target advertisement click vector with the highest similarity to the activation vector among the multiple advertisement click vectors, and determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0150] Figure 8 The figure is a structural diagram of an advertising attribution method according to an exemplary embodiment.

[0151] In some embodiments, advertisers can place advertisements corresponding to the clients on some web pages (such as web pages of browsers) or clients, and then when the advertisements are clicked, the advertisement click information can be collected and uploaded through the web page information collection interface on the device where the web page (or client) is located; then when the client is activated, the client can collect product activation information through the client information collection interface and upload it to the server so as to perform advertising attribution on the product activation information.

[0152] In the above embodiment, the type of information collected through the web page information collection interface is different from the type of information collected through the client information collection interface (for details, please refer to the difference between Table 1 and Table 2).

[0153] For the specific process above, please refer to Figure 8 The embodiment shown.

[0154] The corresponding solution of this embodiment can be implemented by seven modules: browser SDK (such as web page information collection interface), client SDK (such as client information collection interface), cloud service, device fingerprint generation module, device vector generation module, device fingerprint-device vector mapping module and device fingerprint map.

[0155] In some embodiments, when an advertisement is clicked on a device (for example, it can be clicked in a client on the device or on a web page), the browser SDK on the device can collect device information, network information, and environmental information corresponding to the device where the browser is located when the advertisement click action occurs through JS (Java Dcript, a scripting language) (for details, please refer to the data types in Table 2), and report it to the cloud service for storage through encryption.

[0156] In some embodiments, when the APP is activated for the first time, the client SDK built into the APP will implicitly load a client-built-in browser, and collect the browser environment information when the activation action occurs through the browser (WEB) SDK (specifically, please refer to the data types in Table 2) and report it to the cloud. At the same time, the device information, network information, and client environment information are collected through the client SDK and reported to the cloud (specifically, please refer to the data types in Table 1).

[0157] It should be noted that the data type collected by the browser (web page) SDK may be different from the data type collected by the client SDK.

[0158] refer to Figure 8When the product advertising click information collected by the browser Web SDK is reported to the cloud, the encrypted data can be decrypted and a device fingerprint can be generated through the device fingerprint generation algorithm. At the same time, the advertising click information is processed using a deep model to generate a device vector, and a mapping relationship between the device fingerprint and the device vector is established. By calculating the similarity between the device vectors, the corresponding device fingerprint is added to the device graph, and the similarity relationship of the device graph is improved. When attributing, the device fingerprint and device vector are used to query the device fingerprint with the highest similarity in the device graph for attribution.

[0159] refer to Figure 8 When the product activation information collected by the client SDK is uploaded to the cloud, the encrypted data can be decrypted and processed using a deep model to generate a device vector corresponding to the product activation information; then the device vector corresponding to the product activation information is calculated similarly with the vector in the device graph to query the device fingerprint with the highest similarity in the device graph for attribution.

[0160] In the above embodiment, on the one hand, the client SDK implicitly loads the built-in browser and calls the Web SDK to collect and report the same browser information. On the other hand, the reported information is used to generate a device vector through a deep model, and a mapping relationship between the device fingerprint and the device vector is established; in addition, a device map is established based on the historical device and other device-related IDs, and similarity calculations are performed on the newly reported devices through the device vector, and the device fingerprint is added to the device map based on the similarity, and queries are performed through the device fingerprint.

[0161] It should be particularly pointed out that each step in each embodiment of the above data processing method can be mutually crossed, replaced, added, or deleted. Therefore, these reasonable permutations, combinations, and transformations of the data processing method should also fall within the protection scope of the present disclosure, and the protection scope of the present disclosure should not be limited to the embodiments.

[0162] Based on the same inventive concept, the present disclosure also provides a data processing device in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0163] Fig. 9 is a block diagram of a data processing device according to an exemplary embodiment. The above data processing device can be applied to a server. Fig. 9 The data processing device 900 provided in the embodiment of the present disclosure may include: an activation information acquisition module 901, an activation vector generation module 902, an advertisement click vector acquisition module 903, a similarity determination module 904, a target advertisement click vector determination module 905 and an attribution module 906.

[0164] Among them, the activation information acquisition module 901 can be used to obtain product activation information uploaded by the client, and the product activation information is collected by the client; the activation vector generation module 902 can be used to generate an activation vector based on the product activation information; the advertisement click vector acquisition module 903 can be used to obtain multiple advertisement click vectors, wherein the advertisement click vector is generated based on advertisement click information, wherein the advertisement click information is collected from the web page; the similarity determination module 904 can be used to determine the similarity between the activation vector and each advertisement click vector; the target advertisement click vector determination module 905 can be used to determine the target advertisement click vector with the highest similarity to the activation vector among multiple advertisement click vectors; the attribution module 906 can be used to determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0165] It should be noted that the activation information acquisition module 901, the activation vector generation module 902, the advertisement click vector acquisition module 903, the similarity determination module 904, the target advertisement click vector determination module 905, and the attribution module 906 correspond to S202 to S212 in the method embodiment, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above method embodiment. It should be noted that the above modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0166] In some embodiments, the multiple advertisement click vectors include a first advertisement click vector, a second advertisement click vector, and a third advertisement click vector; wherein the advertisement click vector acquisition module 903 may include: a device graph determination submodule.

[0167] Among them, the device graph determination submodule can be used to obtain a device graph, the device graph includes multiple nodes, each node corresponds to an advertisement click vector, the edge between two nodes in the device graph is used to indicate the similarity between the two nodes, the device graph includes a first node, a second node and a third node, the first node is connected to the second node and the third node, the first node corresponds to the first advertisement click vector, the second node corresponds to the second advertisement click vector, and the third node corresponds to the third advertisement click vector;

[0168] The similarity determination module 904 may include: a first vector similarity determination submodule, a second vector similarity determination submodule, a third vector similarity determination submodule, a second node similarity determination submodule, a third node similarity determination submodule and a first weighted processing submodule.

[0169] Among them, the first vector similarity determination submodule can be used to determine the first vector similarity between the activation vector and the first advertisement click vector; the second vector similarity determination submodule can be used to determine the second vector similarity between the activation vector and the second advertisement click vector; the third vector similarity determination submodule can be used to determine the third vector similarity between the activation vector and the third advertisement click vector; the second node similarity determination submodule can be used to determine the second node similarity between the first node and the second node; the third node similarity determination submodule can be used to determine the third node similarity between the first node and the third node; the first weighted processing submodule can be used to perform weighted processing on the first vector similarity, the second vector similarity and the third vector similarity through the second node similarity and the third node similarity to determine the similarity between the activation vector and the first node vector.

[0170] In some embodiments, the first weighted processing submodule includes: a first node similarity unit normalization processing unit and a second weighted processing unit.

[0171] Among them, the first node similarity unit can be used to determine the first node similarity between the first node and the first node; the normalization processing unit can be used to normalize the first node similarity, the second node similarity and the third node similarity to obtain the first normalized similarity, the second normalized similarity and the third normalized similarity; the second weighted processing unit can be used to weight the first vector similarity, the second vector similarity and the third vector similarity through the first normalized similarity, the second normalized similarity and the third normalized similarity to determine the similarity between the activation vector and the first node vector.

[0172] In some embodiments, the product activation information includes both the device information, network information, and environment information corresponding to the client when the activation action occurs, which are collected by the client through the client information collection interface, and the device information, network information, and web page environment information corresponding to the web page when the activation action occurs, which are collected by the client through the built-in web page information collection interface.

[0173] Since the functions of the device 900 have been described in detail in the corresponding method embodiments, the present disclosure will not elaborate on them here.

[0174] Fig.10 is a block diagram of a data processing device according to an exemplary embodiment. The data processing device can be applied to web pages. Fig.10 The data processing device 1000 provided in the embodiment of the present disclosure may include: a click behavior determination module 1001, a web page information collection module 1002, an advertisement click information generation module 1003 and an advertisement click information upload module 1004.

[0175] Among them, the click behavior determination module 1001 can be used to determine the occurrence of advertisement click behavior; the web page information collection module 1002 can be used to collect the device information, network information and web page environment information corresponding to the web page when the advertisement click behavior occurs through the web page information collection interface of the web page; the advertisement click information generation module 1003 can be used to generate advertisement click information according to the device information corresponding to the web page, the network information and web page environment information corresponding to the web page when the advertisement click behavior occurs; the advertisement click information upload module 1004 can be used to upload the advertisement click information to the server, so that when the server receives the product activation information, it matches the activation vector corresponding to the product activation information with the advertisement click vector corresponding to the advertisement click information, so as to determine whether the activation operation corresponding to the product activation information is caused by the advertisement click behavior.

[0176] Since the functions of the device 1000 have been described in detail in the corresponding method embodiments, the present disclosure will not elaborate on them here.

[0177] Fig.11 is a block diagram of a data processing device according to an exemplary embodiment. The above data processing device can be applied to a client. Fig.11 The data processing device 1100 provided in the embodiment of the present disclosure may include: an activation action determination module 1101 , a client information collection module 1102 , a product activation information collection module 1103 and a product activation information upload module 1104 .

[0178] Among them, the activation action determination module 1101 can be used to determine whether an activation action occurs on the client; the client information collection module 1102 can be used to collect the device information corresponding to the client, the network information corresponding to the client and the client environment information when the activation action occurs through the client information collection interface of the client; the product activation information collection module 1103 can be used to generate product activation information through the device information corresponding to the client, the network information and the environment information corresponding to the client when the activation action occurs; the product activation information upload module 1104 can be used to upload the product activation information to the server, so that the server matches the product activation vector corresponding to the product activation information with the advertisement click vectors corresponding to the multiple advertisement click information received by the server, so as to determine the target advertisement click vector with the highest similarity to the activation vector among the multiple advertisement click vectors, and determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0179] In some embodiments, the data processing device 1100 may further include: an implicit collection module.

[0180] Among them, the implicit collection module can be used for the client to implicitly load the built-in web page and call the web page information collection interface corresponding to the web page to collect the device information corresponding to the web page, the network information corresponding to the web page when the activation action occurs, and the web page environment information.

[0181] In some embodiments, the product activation information collection module 1103 may include: a product activation information generation module.

[0182] Among them, the product activation information generation module can be used to generate product activation information through the device information corresponding to the client, the network information and environment information corresponding to the client when the activation action occurs, the device information corresponding to the webpage, and the network information and webpage environment information corresponding to the webpage when the activation action occurs.

[0183] Since the functions of the device 1100 have been described in detail in the corresponding method embodiments, the present disclosure will not elaborate on them here.

[0184] The modules and / or submodules and / or units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The modules and / or submodules and / or units described may also be arranged in a processor. The names of these modules and / or submodules and / or units do not, in certain circumstances, constitute limitations on the modules and / or submodules and / or units themselves.

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a part of a module or program segment, and a part of the above-mentioned module or program segment contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer program instructions.

[0186] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0187] Fig.12The structure diagram of the electronic device suitable for implementing the embodiment of the present disclosure is shown. It should be noted that: Fig.12 The electronic device 1200 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0188] like Fig.12 As shown, the electronic device 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1202 or a program loaded from a storage part 1208 into a random access memory (RAM) 1203. In the RAM 1203, various programs and data required for the operation of the electronic device 1200 are also stored. The CPU 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0189] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, etc.; an output section 1207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN card, a modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as needed, so that a computer program read therefrom is installed into the storage section 1208 as needed.

[0190] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains computer program instructions for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1209, and / or installed from a removable medium 1211. When the computer program is executed by the central processing unit (CPU) 1201, the above-mentioned functions defined in the system of the present disclosure are executed.

[0191] It should be noted that the computer-readable storage medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable computer program instructions. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The computer program instructions contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0192] As another aspect, the present disclosure also provides a computer-readable storage medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed by a device, the device can implement functions including: obtaining product activation information uploaded by the client, which is collected by the client; generating an activation vector based on the product activation information; obtaining multiple advertisement click vectors, wherein the advertisement click vector is generated based on the advertisement click information, wherein the advertisement click information is collected by the web page; determining the similarity between the activation vector and each advertisement click vector; determining the target advertisement click vector with the highest similarity to the activation vector among multiple advertisement click vectors; and determining that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

[0193] According to one aspect of the present disclosure, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer program instructions, the computer program instructions being stored in a computer-readable storage medium. The computer program instructions are read from the computer-readable storage medium, and a processor executes the computer program instructions to implement the methods provided in various optional implementations of the above embodiments.

[0194] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution of the embodiment of the present disclosure 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.), including a number of computer program instructions for enabling an electronic device (which can be a server or a terminal device, etc.) to execute the method according to the embodiment of the present disclosure.

[0195] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0196] It should be understood that the present disclosure is not limited to the detailed structures, drawings or implementations shown herein, but rather the present disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A data processing method, characterized in that: Applicable to servers, including: Acquire product activation information uploaded by a client, where the product activation information is collected by the client; generating an activation vector according to the product activation information; Acquire multiple advertisement click vectors, wherein the advertisement click vectors are generated according to advertisement click information, wherein the advertisement click information is collected from a web page; Determining the similarity between the activation vector and each advertisement click vector; Determine, among the multiple advertisement click vectors, a target advertisement click vector having the highest similarity to the activation vector; It is determined that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

2. The method according to claim 1, characterized in that: The multiple advertisement click vectors include a first advertisement click vector, a second advertisement click vector, and a third advertisement click vector; wherein obtaining the multiple advertisement click vectors includes: Acquire a device graph, the device graph comprising a plurality of nodes, wherein each node corresponds to an advertisement click vector, an edge between two nodes in the device graph is used to indicate a similarity between the two nodes, the device graph comprising a first node, a second node, and a third node, the first node is connected to the second node and the third node, the first node corresponds to the first advertisement click vector, the second node corresponds to the second advertisement click vector, and the third node corresponds to the third advertisement click vector; Wherein, determining the similarity between the activation vector and the first node vector includes: determining a first vector similarity between the activation vector and the first advertisement click vector; determining a second vector similarity between the activation vector and the second advertisement click vector; determining a third vector similarity between the activation vector and the third advertisement click vector; determining a second node similarity between the first node and the second node; Determining a third node similarity between the first node and the third node; The first vector similarity, the second vector similarity and the third vector similarity are weighted by the second node similarity and the third node similarity to determine the similarity between the activation vector and the first node vector.

3. The method according to claim 2, characterized in that: The first vector similarity, the second vector similarity and the third vector similarity are weighted by the second node similarity and the third node similarity to determine the similarity between the activation vector and the first node vector, including: determining a first node similarity between the first node and the first node; Normalizing the first node similarity, the second node similarity, and the third node similarity to obtain a first normalized similarity, a second normalized similarity, and a third normalized similarity; The first vector similarity, the second vector similarity and the third vector similarity are weighted by the first normalized similarity, the second normalized similarity and the third normalized similarity to determine the similarity between the activation vector and the first node vector.

4. The method according to claim 1, characterized in that: The product activation information includes the device information, network information and environment information corresponding to the client when the activation action occurs, which are collected by the client through the client information collection interface; the product activation information also includes the device information, network information and web page environment information corresponding to the web page when the activation action occurs, which are collected by the client through the built-in web page information collection interface.

5. A data processing method, characterized in that: Applied to a web page, the method further comprises: Determine that an ad click has occurred; Collecting device information, network information and web page environment information corresponding to the web page when the advertisement click behavior occurs through the web page information collection interface of the web page; Generate advertisement click information according to device information corresponding to the webpage, network information corresponding to the webpage when the advertisement click behavior occurs, and webpage environment information; The advertisement click information is uploaded to a server so that when the server receives the product activation information, it matches the activation vector corresponding to the product activation information with the advertisement click vector corresponding to the advertisement click information to determine whether the activation operation corresponding to the product activation information is caused by the advertisement click behavior.

6. A data processing method, characterized in that: Applied to a client, the method comprises: Determining that an activation action occurs on the client; Collecting device information, network information and client environment information corresponding to the client when the activation action occurs through the client information collection interface of the client; Generate product activation information through the device information corresponding to the client, the network information corresponding to the client, and the client environment information when the activation action occurs; The product activation information is uploaded to a server so that the server can match a product activation vector corresponding to the product activation information with an advertisement click vector corresponding to multiple advertisement click information received by the server, so as to determine a target advertisement click vector having the highest similarity to the activation vector among multiple advertisement click vectors, and determine that the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

7. The method according to claim 6, characterized in that: The method further comprises: The client implicitly loads the built-in web page and calls the web page information collection interface corresponding to the web page to collect the device information corresponding to the web page, the network information corresponding to the web page when the activation action occurs, and the web page environment information; The product activation information is generated by using the device information corresponding to the client, the network information and the environment information corresponding to the client when the activation action occurs, including: The product activation information is generated by the device information corresponding to the client, the network information and environment information corresponding to the client when the activation action occurs, the device information corresponding to the webpage, and the network information and webpage environment information corresponding to the webpage when the activation action occurs.

8. A data processing device, characterized in that: Applicable to servers, including: An activation information acquisition module, used to acquire product activation information uploaded by a client, wherein the product activation information is collected by the client; An activation vector generation module, used to generate an activation vector according to the product activation information; An advertisement click vector acquisition module, used to acquire a plurality of advertisement click vectors, wherein the advertisement click vectors are generated according to advertisement click information, wherein the advertisement click information is collected from a web page; A similarity determination module, used to determine the similarity between the activation vector and each advertisement click vector; a target advertisement click vector determination module, configured to determine, among the plurality of advertisement click vectors, a target advertisement click vector having the highest similarity to the activation vector; The attribution module is used to determine whether the activation of the client is converted from the advertisement click behavior corresponding to the target advertisement click vector.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer program instructions; the processor calls the computer program instructions stored in the memory to implement the data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the data processing method according to any one of claims 1 to 7 is implemented.

Images