Activity attribution method, live broadcast activity attribution method and its device, equipment, and medium
By drawing and merging the node paths of online activities, overlapping nodes and pre-paths are determined, and based on conversion rate attribution, the problem of inefficient online activity conversion rate statistics in the existing technology is solved, and efficient online activity attribution and deployment are achieved. optimization.
Patent Information
- Application Number
- CN202211739302.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-31
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-12-31
AI Technical Summary
Existing online platforms need to pass complex data collection or AB testing when stating online activity conversion rates, resulting in high cost and inefficiency, making it difficult to effectively attribute the conversion of online activities.
By drawing the active node path of online activities, combining the path map to determine overlapping nodes, and determining the pre-path based on user historical activity participation information and node conversion rate to realize the attribution of online activities.
It improves the efficiency of online activity attribution, saves development and labor costs, realizes real-time attribution and activity effect prediction, and optimizes online activity deployment.
Smart Images

Figure CN116112701B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet online activities and live broadcasts, and in particular to an activity attribution method and a live broadcast activity attribution method. In addition, the present application also relates to corresponding devices, equipment and computer-readable storage media for each method. Background Art
[0002] Existing network platforms usually provide various types of online activities to platform users to attract users to participate in online activities and use corresponding platform services. For example, for online live broadcast platforms, when it is necessary to attract users to pay attention to the live broadcast room, online activities such as live broadcast room interface control activities or live broadcast room rendering window activities can be used to attract users to pay attention to the corresponding anchor users in the platform through live broadcast room interface controls or live broadcast room rendering windows. However, when the network platform attributes activities to count the conversion rate of activities, it is usually necessary to attribute online activities through complex data collection or AB testing. In order to count the conversion rate of online activities, the network platform needs to consume a lot of opening costs and manpower costs, and it is also difficult to pay attention to a certain platform business for attribution conversion statistics. Therefore, how to improve the efficiency of online activity attribution statistics is a problem existing in the network platform. The applicant has made corresponding explorations in order to solve this problem. Summary of the invention
[0003] The purpose of this application is to provide an activity attribution method and a live activity attribution method to meet user needs. In addition, it also relates to corresponding devices, equipment, computer-readable storage media and computer program products of the method.
[0004] In order to achieve the purpose of this application, a method for attributing an activity is provided, which adopts the following technical solution:
[0005] Based on the activity tracking data of multiple online activities in the platform, draw the activity node path corresponding to each of the online activities;
[0006] Merging the activity node paths to generate an activity merged node path graph, and determining one or more overlapping nodes between the activity node paths from the activity merged node path graph;
[0007] In response to a node attention event of any of the overlapping nodes, according to the user historical activity participation information corresponding to the node attention event, multiple predecessor nodes corresponding to the overlapping nodes are determined from the activity merge node path graph, and one or more predecessor node paths of each of the predecessor nodes are drawn;
[0008] Based on the attention path determination rule, the attention path in each of the predecessor node paths is determined according to the node length corresponding to each of the predecessor node paths and the historical node conversion rate of the user end, and the online activity corresponding to the attention path is used as the attributed online activity of the overlapping node.
[0009] In a further embodiment, the step of drawing the activity node path corresponding to each online activity according to the activity tracking data of multiple online activities in the platform includes the following steps:
[0010] Acquire the activity tracking data corresponding to each of the multiple online activities in the platform, wherein the activity tracking data includes activity feature information corresponding to each of the multiple activity events;
[0011] According to the activity event name and activity event triggering sequence contained in the activity feature information of each activity event in the activity tracking data, an activity node path corresponding to each online activity is drawn. Each activity event in the activity node path represents its activity feature information in the form of an activity node, and each activity node is connected according to its event triggering sequence.
[0012] In a further embodiment, the step of merging the active node paths to generate an active merged node path graph, and determining one or more overlapping nodes between the active node paths from the active merged node path graph, comprises the following steps:
[0013] Merging a plurality of said activity node paths to draw an activity merged node path graph;
[0014] The activity merge node path graph is traversed to determine the activity nodes intersecting between the activity node paths, and the activity nodes are used as overlapping nodes.
[0015] In a further embodiment, the step of responding to a node attention event of any of the overlapping nodes, determining a plurality of predecessor nodes corresponding to the overlapping nodes from the activity merge node path graph according to the user historical activity participation information corresponding to the node attention event, and drawing one or more predecessor node paths of each of the predecessor nodes, includes the following steps:
[0016] In response to an online activity triggering event acting on a user terminal, determining an activity event corresponding to the online activity triggering event;
[0017] Determine the target overlapping node corresponding to the activity event, and determine the activity merge node path graph where the target overlapping node is located;
[0018] Taking the target overlapping node as the end point, querying the activity path composed of the predecessor nodes of the target overlapping node from the activity merge node path graph according to the user's historical activity participation information, and taking each of the activity paths as the predecessor activity path of the target overlapping node;
[0019] Invalid duplicate nodes are removed from each of the preceding active paths.
[0020] In a further embodiment, the step of determining the attention path in each of the preceding node paths based on the attention path determination rule according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user terminal, and taking the online activity corresponding to the attention path as the attribution online activity of the overlapping node, includes the following steps:
[0021] Comparing the path lengths of the plurality of the preceding node paths, determining the preceding node path with the longest path length among the preceding node paths as the focus path;
[0022] When there are multiple predecessor node paths with the longest path lengths, obtaining the historical node conversion rate of each active node in each predecessor node path acted on by the user end, and calculating the total historical node conversion rate of each predecessor node path;
[0023] A target preceding node path having the highest total historical node conversion rate among the preceding node paths is determined, and the target preceding node is used as the focus path.
[0024] In a further embodiment, the method comprises the following steps after the step of determining the attention path in each of the preceding node paths based on the attention path determination rule according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user terminal, and taking the online activity corresponding to the attention path as the attribution online activity of the overlapping node:
[0025] Counting the number of attribution determinations of the plurality of online activities corresponding to the target overlapping node, wherein the number of attribution determinations is determined according to the number of times each of the online activities acts on its associated overlapping node and is determined as an attribution online activity;
[0026] Determine a target online activity in which the attribution determination number exceeds a preset number among the online activities, and increase the number of activity delivery times of the target online activity on the platform.
[0027] An activity attribution device proposed for the purpose of this application includes:
[0028] A node path drawing module is used to draw the activity node path corresponding to each online activity according to the activity tracking data of multiple online activities in the platform;
[0029] An overlapping node determination module, used for merging the active node paths to generate an active merged node path graph, and determining one or more overlapping nodes between the active node paths from the active merged node path graph;
[0030] A predecessor path drawing module, for responding to a node attention event of any of the overlapping nodes, determining a plurality of predecessor nodes corresponding to the overlapping nodes from the activity merge node path graph according to the user historical activity participation information corresponding to the node attention event, and drawing one or more predecessor node paths of each of the predecessor nodes;
[0031] The attribution activity determination module is used to determine the attention path in each of the predecessor node paths based on the attention path determination rule, according to the node length corresponding to each of the predecessor node paths and the historical node conversion rate of the user end, and use the online activity corresponding to the attention path as the attribution online activity of the overlapping node.
[0032] In a further embodiment, the node path drawing module includes:
[0033] An activity tracking data acquisition submodule is used to acquire the activity tracking data corresponding to each of a plurality of online activities in the platform, wherein the activity tracking data includes activity feature information corresponding to each of a plurality of activity events;
[0034] The activity path drawing submodule is used to draw the activity node path corresponding to each online activity based on the activity event name and the activity event triggering sequence contained in the activity feature information of each activity event in the activity tracking data. Each activity event in the activity node path represents its activity feature information in the form of an activity node, and each activity node is connected according to its event triggering sequence.
[0035] In a further embodiment, the overlapping node determination module includes:
[0036] A merged node path drawing submodule is used to merge a plurality of said activity node paths and draw an activity merged node path graph;
[0037] The overlapping node determination submodule is used to traverse the activity merge node path graph, determine the activity nodes intersecting between the activity node paths, and use the activity nodes as overlapping nodes.
[0038] In a further embodiment, the front path drawing module includes:
[0039] An activity event determination submodule, for responding to an online activity triggering event acting on a user terminal, and determining an activity event corresponding to the online activity triggering event;
[0040] A target overlapping node processing submodule is used to determine the target overlapping node corresponding to the activity event and determine the activity merge node path graph where the target overlapping node is located;
[0041] A predecessor path drawing submodule is used to query the activity path composed of the predecessor nodes of the target overlapping node from the activity merge node path graph based on the user's historical activity participation information, taking the target overlapping node as the end point, and using each of the activity paths as the predecessor activity path of the target overlapping node;
[0042] The preceding path processing submodule is used to remove invalid duplicate nodes from each preceding active path.
[0043] In a further embodiment, the attribution activity determination module includes:
[0044] A path length comparison submodule, used to compare the path lengths of the plurality of the preceding node paths, and determine the preceding node path with the longest path length among the preceding node paths as the focus path;
[0045] A node conversion rate calculation submodule is used to obtain the historical node conversion rate of each active node in each of the preceding node paths by the user end when there are multiple preceding node paths with the longest path length, and calculate the total historical node conversion rate of each of the preceding node paths;
[0046] The focus path determination submodule is used to determine the target preceding node path with the highest total historical node conversion rate among the preceding node paths, and use the target preceding node as the focus path.
[0047] To achieve another purpose of the present application, a live broadcast activity attribution method is provided, which adopts the following technical solution:
[0048] In response to the anchor attention event acting on the audience end, determining the overlapping node corresponding to the anchor attention event;
[0049] Obtaining a merged node path graph where the overlapping node is located, and determining one or more preceding node paths of the overlapping node from the merged node path graph according to the historical activity participation information of the user at the viewer end;
[0050] Based on the attention path determination rule, the attention path in each of the preceding node paths is determined according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user end, and the online activity corresponding to the attention path is used as the attributed online activity of the host's attention event.
[0051] A live broadcast activity attribution device proposed for the purpose of this application includes:
[0052] An overlapping node determination module, used to respond to the anchor attention event acting on the audience end and determine the overlapping nodes corresponding to the anchor attention event;
[0053] A preceding path determination module is used to obtain a merged node path graph where the overlapping node is located, and determine one or more preceding node paths of the overlapping node from the merged node path graph according to the historical activity participation information of the user at the audience end;
[0054] The attribution activity determination module is used to determine the attention path in each of the preceding node paths based on the attention path determination rules, according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user end, and use the online activity corresponding to the attention path as the attribution online activity of the host's attention event.
[0055] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the above-mentioned activity attribution method or the live broadcast activity attribution method.
[0056] In order to solve the above technical problems, an embodiment of the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the above-mentioned activity attribution method or the live broadcast activity attribution method.
[0057] In order to solve the above technical problems, an embodiment of the present application also provides a computer program product, including a computer program and computer instructions. When the computer program and computer instructions are executed by a processor, the processor executes the steps of the above-mentioned activity attribution method or the live broadcast activity attribution method.
[0058] Compared with the prior art, the advantages of this application are as follows:
[0059] The present application can draw out the activity node paths of each online activity in the platform and merge them, determine the overlapping nodes of each activity node path to identify the overlapping activity events of each online activity, and when the overlapping activity event of any overlapping node in the platform is triggered by the user end, according to the activity events that the user end in the platform has participated in before the overlapping activity event is triggered, determine one or more corresponding preceding activity paths that act on the overlapping nodes from the activity merged node path graph generated by merging the activity node paths, and then based on the attention path determination rule, compare the path length and node conversion rate of each preceding activity path to determine the attributed online activity corresponding to the triggered overlapping activity event. For example, for a live broadcast platform, when the platform needs to count the attributed online activities of users following the anchor in the platform, by counting the overlapping nodes associated with the users following the anchor, the preceding activity paths that are pre-merged and related to the users following the anchor are determined. In the activity merged node path graph generated by the activity node path of the connected online activities, the preceding path corresponding to the overlapping node is determined, and the online activities of the users who follow the anchor are attributed for statistics. It can be seen that by drawing the activity node path and the overlapping node determination, the activity events that are the same as the online activities in the platform are determined in advance, and the online activities of each activity event are attributed in real time. Compared with the traditional online activity attribution through complex data collection or AB testing to count the conversion rate of online activities, the present application not only saves development and labor costs, but also does not need to intrude into the activity flow of online activities. It attributes the online activities of each activity event in the platform in a bypass manner to count the conversion rate of online activities, and also predicts the activity effects between online activities with the same activity events, and then determines the optimal online activity acting on the activity event for activity optimization, so that the platform can carry out online activity deployment planning. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0061] Figure 1 A schematic diagram of a typical network deployment architecture related to implementing the technical solution of this application;
[0062] Figure 2 A flowchart of a typical embodiment of the activity attribution method of the present application;
[0063] Figure 3 A schematic diagram of an activity node path for a live broadcast control to follow an online activity of a host in this application;
[0064] Figure 4 A schematic diagram of an activity merged node path diagram generated by merging the activity node path of the live broadcast control following the anchor's online activity with the activity node path of the live broadcast room promotion window online activity in the online activity in this application;
[0065] Figure 5 A flowchart formed by a specific implementation method of drawing a corresponding activity node path based on activity tracking data of an online activity in this application;
[0066] Figure 6 A flowchart diagram of a specific implementation method for merging activity node paths of multiple online activities to generate an activity merged node path graph in this application;
[0067] Figure 7 A flowchart diagram of a specific implementation method of determining a preceding path corresponding to an overlapping node from an active merge node path graph in the present application;
[0068] Figure 8 A flowchart diagram of a specific implementation method of determining a focus path from multiple preceding paths based on a focus path determination rule in this application;
[0069] Fig. 9 A flowchart formed by a specific implementation method of selecting online activities whose attribution determination times exceed a preset number from multiple online activities corresponding to target overlapping nodes in this application to increase the number of activity delivery times;
[0070] Fig.10 This is a principle block diagram of a typical embodiment of the activity attribution device of the present application;
[0071] Fig.11 This is a flowchart of a typical embodiment of the live broadcast activity attribution method of the present application;
[0072] Fig.12 This is a basic structural block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION
[0073] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.
[0074] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.
[0075] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.
[0076] It will be understood by those skilled in the art that the "client", "terminal" and "terminal device" used herein include both devices with wireless signal receivers, which are devices with only wireless signal receivers without transmission capabilities, and devices with receiving and transmitting hardware, which are devices with receiving and transmitting hardware capable of two-way communication on a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers, tablet computers, which have single-line displays or multi-line displays or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service, personal communication system), which can combine voice, data processing, fax and / or data communication capabilities; PDA (Personal Digital Assistant, personal digital assistant), which may include a radio frequency receiver, pager, Internet / intranet access, web browser, notepad, calendar and / or GPS (Global Positioning System, global positioning system) receiver; traditional laptop and / or palmtop computers or other devices, which have and / or include radio frequency receivers. The "client", "terminal" and "terminal device" used herein may be portable, transportable, installed in a vehicle (air, sea and / or land), or suitable and / or configured to run locally, and / or in a distributed form, at any other location on the earth and / or in space. The "client", "terminal" and "terminal device" used herein may also be a communication terminal, an Internet terminal, a music / video playback terminal, such as a PDA, a MID (Mobile Internet Device) and / or a mobile phone with a music / video playback function, or a smart TV, a set-top box and other devices.
[0077] The hardware referred to by the names such as "server", "client", and "working node" in this application is essentially an electronic device with capabilities equivalent to those of a personal computer. It is a hardware device that has the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. Computer programs are stored in its memory, and the central processing unit calls the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.
[0078] It should be pointed out that the concept of "server" referred to in this application can also be extended to the case of server clusters. According to the network deployment principle understood by those skilled in the art, the servers should be logically divided. In physical space, these servers can be independent of each other but can be called through interfaces, or integrated into a physical computer or a set of computer clusters. Those skilled in the art should understand this flexibility, and should not use it to restrict the implementation of the network deployment method of this application.
[0079] See also Figure 1 , the hardware foundation required for the implementation of the relevant technical solutions of this application can be deployed according to the architecture shown in the figure. The server 80 referred to in this application is deployed in the cloud. As an online server, it can be responsible for further connecting relevant data servers and other servers that provide relevant support, etc., so as to form a logically related service cluster to provide services for relevant terminal devices such as the smartphone 81 and personal computer 82 shown in the figure or a third-party server (not shown). The smartphone and personal computer can access the Internet through a well-known network access method and establish a data communication link with the server 80 in the cloud to run terminal applications related to the services provided by the server.
[0080] For the server, the application is usually constructed as a service process, opening the corresponding program interface for remote calls by applications running on various terminal devices. The relevant technical solutions suitable for running on the server in this application can be implemented in the server in this way.
[0081] The application described herein refers to an application running on a server or terminal device. This application implements the relevant technical solutions of the present application in a programming manner. Its program code can be stored in a computer-readable storage medium recognizable by a computer in the form of computer-executable instructions, and can be loaded into the memory by the central processing unit for execution. The relevant device of the present application is constructed by the operation of the application on the computer.
[0082] For the server, the application is usually constructed as a service process, opening the corresponding program interface for remote calls by applications running on various terminal devices. The relevant technical solutions suitable for running on the server in this application can be implemented in the server in this way.
[0083] Those skilled in the art should be aware that, although the various methods of the present application are described based on the same concept and thus present commonality to each other, unless otherwise specified, these methods can be independently executed. Similarly, for each embodiment disclosed in the present application, they are all proposed based on the same inventive concept, therefore, concepts with the same expression, and concepts that are appropriately changed for convenience despite different expressions, should be understood as equivalent.
[0084] See also Figure 2 , an activity attribution method of the present application, in its typical embodiment, comprises the following steps:
[0085] Step S11, based on the activity tracking data of multiple online activities in the platform, draw the activity node path corresponding to each of the online activities:
[0086] The activity tracking data generally refers to the activity feature information set by the platform for multiple activity events in online activities. For example, when the online activity is a live broadcast room control following the anchor's online activity, the live broadcast control following the anchor's activity generally includes the live broadcast room control click activity event, the follow-up anchor activity window pop-up activity event, the participation activity control click activity event, the activity page display activity event and the follow-up anchor user activity event. Each of the activity events in the live broadcast control following the anchor's online activity has corresponding activity feature information to characterize the activity event name and activity event triggering order of the activity event, and the activity feature information corresponding to each of the activity events constitutes the activity tracking data corresponding to the live broadcast control following the anchor's online activity.
[0087] After the server obtains the activity tracking data corresponding to any online activity in the platform, it will draw the activity node path corresponding to the online activity according to the activity tracking data. The activity node path represents the triggering order of multiple activity events of the online activity. Specifically, according to the activity event name and activity event triggering order contained in the activity feature information of each activity event in the activity tracking data, the activity events are sorted and the activity event name of each activity event is determined to draw the activity node path corresponding to the online activity. Each activity event in the activity node path represents its activity feature information in the form of an activity node, and each activity node is connected according to its event triggering order.
[0088] Please refer to Figure 3 , Figure 3 The activity node path shown is the activity node path of the live broadcast control following the host's online activities. The activity nodes in the activity node path shown are used to represent the activity events included in the live broadcast control following the host's online activities.
[0089] Step S12: merging the activity node paths to generate an activity merged node path graph, and determining one or more overlapping nodes between the activity node paths from the activity merged node path graph:
[0090] After drawing the activity node paths corresponding to each of the online activities, the activity node paths are merged to generate the activity merged node path graph having the activity node paths. The merged activity node paths generally have overlapping nodes, and each overlapping node is the same activity node between the activity node paths, that is, the same activity event in each of the online activities.
[0091] The server merges multiple active node paths, draws the active merged node path graph corresponding to each active node path, and then traverses the active merged node path graph to determine the active nodes that intersect between the active node paths and treats the active nodes as overlapping nodes.
[0092] Please refer to Figure 4 , Figure 4 The activity node path 401 is the activity node path for the live broadcast room control to follow the host's online activities, the activity node path 402 is the activity node path for the online activities of the live broadcast room promotion window, and the activity merged node path diagram 403 is the activity merged node path diagram of the activity node path 401 and the activity node path 402, wherein the activity node 404 is the overlapping node between the activity node path 401 and the activity node path 402.
[0093] Step S13, responding to a node attention event of any of the overlapping nodes, determining multiple predecessor nodes corresponding to the overlapping nodes from the activity merge node path graph according to the user historical activity participation information corresponding to the node attention event, and drawing one or more predecessor node paths of each of the predecessor nodes:
[0094] The node attention event generally refers to an event triggered by an activity event corresponding to any overlapping node triggered by a user terminal in the platform. For example, when the activity event corresponding to the overlapping node to which the node attention event responded by the server acts is to follow the anchor user, the node attention event is an event triggered by an activity event triggered by a user terminal in the platform to follow the anchor user.
[0095] The user's historical activity participation information includes activity events triggered by the user before the preset time window when the node attention event is triggered. For example, when the activity event corresponding to the overlapping node acted upon by the node attention event is to follow the anchor user, the user's historical activity participation information includes multiple activity events participated in by the user before triggering the activity event of following the anchor user, such as live broadcast room control click activity event, follow anchor activity window pop-up activity event, participation activity control click activity event and activity page display activity event, live broadcast room promotion window click activity event or live broadcast room promotion pop-up display activity event, etc.; the time range of the time window is generally set within the time range of 15 to 20. Of course, designers in this field can flexibly design the time window.
[0096] In response to the node attention event, the target overlapping node corresponding to the node attention event will be determined, and the activity merge node path graph corresponding to the target overlapping node will be determined, so as to take the target overlapping node as the end point, and based on the user's historical activity participation information, the activity path composed of one or more predecessor nodes of the end point is queried from the activity merge node path graph, and each of the activity paths is used as the predecessor activity path of the target overlapping node.
[0097] Please refer to Figure 4 When the overlapping node affected by the node attention event responded by the server is the overlapping node 404 shown, the server will determine the preceding activity paths of the overlapping node 404 shown, and the preceding activity paths are the activity node path 401 shown and the activity node path 402 shown.
[0098] There may be invalid or duplicate active nodes in the predecessor active path determined by the server. Therefore, the server needs to perform invalid duplicate node removal processing on each of the predecessor active paths it determines to remove the invalid or duplicate active nodes in the predecessor active path and prevent invalid or duplicate active nodes from interfering with the subsequent focus path determination processing.
[0099] Step S14, based on the attention path determination rule, according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user end, the attention path in each of the preceding node paths is determined, and the online activity corresponding to the attention path is used as the attributed online activity of the overlapping node:
[0100] The focus path determination rule refers to a rule for determining the focus path in each of the predecessor node paths. The focus path determination rule generally determines the focus path in each of the predecessor node paths based on the path length of each of the predecessor node paths or the total historical node conversion rate of each of the predecessor node paths.
[0101] After the server determines the predecessor node path of the overlapping node corresponding to the node attention event, when there is only one predecessor node path, the predecessor node path will be directly determined as the attention path corresponding to the overlapping node; when there are multiple predecessor node paths, the server will compare the path lengths of each of the predecessor node paths and determine the predecessor node path with the longest path length among the predecessor node paths as the attention path.
[0102] When the server compares the path lengths of multiple predecessor node paths and determines that there are multiple predecessor node paths with the longest node paths, the server will obtain the historical node conversion rate of each active node in each predecessor node path acted on by the user end, and then calculate the total historical node conversion rate of each predecessor node path, so as to take the target predecessor node path with the highest total historical node conversion rate as the focus path.
[0103] The historical node conversion rate generally refers to the trigger rate of the active event corresponding to the active node. For example, when the active event of the active node is a live broadcast room control display event, and the next active event of the live broadcast room control event is a live broadcast room control click event, then the historical node conversion rate of the active node is the ratio between the trigger times of the live broadcast room control click event and the live broadcast room control display event.
[0104] After determining the attention path corresponding to the overlapping node, the online activity corresponding to the attention path will be determined, and the online activity will be used as the attributed online activity of the overlapping node, that is, the online activity that triggers the activity event corresponding to the overlapping node is tracked, and the online activity is the attributed online activity corresponding to the activity event.
[0105] It can be known from the typical implementation of the method that the method can draw out the activity node paths of each online activity in the platform and merge them, determine the overlapping nodes of each activity node path to identify the overlapping activity events of each online activity, when the overlapping activity event of any overlapping node in the platform is triggered by the user end, according to the activity events that the user end in the platform has participated in before the overlapping activity event is triggered, determine the corresponding one or more preceding activity paths acting on the overlapping nodes from the activity merged node path graph generated by merging the activity node paths, and then based on the attention path determination rule, compare the path length and node conversion rate of each preceding activity path to determine the attributed online activity corresponding to the triggered overlapping activity event. For example, for a live broadcast platform, when the platform needs to count the attributed online activities of users following the anchor in the platform, by counting the overlapping nodes associated with the users following the anchor, the attributed online activities corresponding to the triggered overlapping activity events are determined. First, the activity node paths of the online activities associated with the users who follow the anchor are merged to generate an activity merge node path graph, and the preceding path corresponding to the overlapping nodes is determined. The online activities of the users who follow the anchor are attributed and counted. It can be seen that by drawing the activity node paths and the overlapping nodes, the activity events that are the same as the online activities in the platform are determined in advance, and the online activities of each activity event are attributed in real time. Compared with the traditional method of attributing online activities through complex data collection or AB testing to count the conversion rate of online activities, this method not only saves development and labor costs, but also does not need to intrude into the activity flow of online activities. It attributes the online activities of each activity event in the platform in a bypass manner to count the conversion rate of online activities, and also predicts the activity effects between online activities with the same activity events, thereby determining the optimal online activities acting on the activity events, so that the platform can carry out online activity deployment planning.
[0106] The above typical embodiments and their variations fully disclose the implementation scheme of the activity attribution method of the present application. However, various variations of the method can still be derived by changing and amplifying some technical means. Other embodiments are briefly described as follows:
[0107] In one embodiment, please refer to Figure 3 and Figure 5 The step of drawing the activity node paths corresponding to each online activity according to the activity tracking data of multiple online activities in the platform includes the following steps:
[0108] Step S111, obtaining the activity tracking data corresponding to each of the multiple online activities in the platform, wherein the activity tracking data includes activity feature information corresponding to each of the multiple activity events:
[0109] The activity tracking data generally refers to the activity feature information set by the platform for multiple activity events in online activities. Each of the activity feature information includes the activity event name corresponding to the activity event and the activity event triggering sequence.
[0110] Step S112, according to the activity event name and activity event triggering sequence contained in the activity feature information of each activity event in each activity tracking data, draw the activity node path corresponding to each online activity, each activity event in the activity node path represents its activity feature information in the form of an activity node, and each activity node is connected according to its event triggering sequence:
[0111] Please refer to Figure 3 , Figure 3 The activity node path shown is the activity node path of the live broadcast control following the anchor's online activities. The live broadcast control following the anchor's activities includes the live broadcast room control click activity event, the anchor activity window pop-up activity event, the participation activity control click activity event, the activity page display activity event and the anchor user activity event. The activity node path shown is represented by the activity node. The activity events included in the live broadcast control following the anchor's online activities.
[0112] In this embodiment, based on the activity feature information corresponding to multiple activity events contained in the activity tracking data of the online activity, an activity node path representing each activity event in the online activity is drawn.
[0113] In one embodiment, please refer to Figure 4 and Figure 6 The step of merging the activity node paths to generate an activity merged node path graph, and determining one or more overlapping nodes between the activity node paths from the activity merged node path graph, comprises the following steps:
[0114] Step S121, merging multiple activity node paths to draw an activity merged node path graph:
[0115] Please refer to Figure 4 , Figure 4 The activity node path 401 is the activity node path for the live broadcast room control to follow the host's online activities, the activity node path 402 is the activity node path for the online activities of the live broadcast room promotion window, and the activity merged node path diagram 403 is the activity merged node path diagram of the activity node path 401 and the activity node path 402.
[0116] Step S122, traverse the activity merge node path graph, determine the activity nodes that intersect between the activity node paths, and use the activity nodes as overlapping nodes:
[0117] Please refer to Figure 4 , Figure 4 The active node 404 shown is an overlapping node between the active node path 401 shown and the active node path 402 shown.
[0118] In this embodiment, the activity node paths of multiple online activities are merged to generate an activity merge node path graph, so as to determine the overlapping nodes of each online activity from the activity merge node path graph.
[0119] In one embodiment, please refer to Figure 4 and Figure 7 , the step of responding to a node attention event of any of the overlapping nodes, determining a plurality of predecessor nodes corresponding to the overlapping nodes from the activity merge node path graph according to the user historical activity participation information corresponding to the node attention event, and drawing one or more predecessor node paths of each of the predecessor nodes, comprises the following steps:
[0120] Step S131, responding to an online activity triggering event acting on a user terminal, determining an activity event corresponding to the online activity triggering event:
[0121] The online activity triggering event refers to an event triggered by a user terminal triggering an activity event in a corresponding online activity on the platform.
[0122] Step S132, determining the target overlapping node corresponding to the activity event, and determining the activity merge node path graph where the target overlapping node is located:
[0123] Because there may be activity node paths without overlapping nodes in different activity node paths, there are generally multiple activity merge node path graphs in the server, each of which has a corresponding activity type identifier, and the overlapping nodes determined from each of the activity merge node path graphs generally also have a corresponding activity type identifier, so that after the server determines the target overlapping node, it can determine the activity merge node path graph with the target overlapping node through the activity type identifier corresponding to the target overlapping node.
[0124] Step S133, taking the target overlapping node as the end point, querying the activity path composed of the preceding nodes of the target overlapping node from the activity merge node path graph according to the user's historical activity participation information, and taking each of the activity paths as the preceding activity path of the target overlapping node:
[0125] Please refer to Figure 4When the overlapping node affected by the node attention event responded by the server is the overlapping node 404 shown, the server will determine the preceding activity paths of the overlapping node 404 shown, and the preceding activity paths are the activity node path 401 shown and the activity node path 402 shown.
[0126] Step S134, performing invalid duplicate node removal processing on each of the preceding active paths:
[0127] There may be invalid or duplicate active nodes in the predecessor active path determined by the server. Therefore, the server needs to perform invalid duplicate node removal processing on each of the predecessor active paths it determines to remove the invalid or duplicate active nodes in the predecessor active path and prevent invalid or duplicate active nodes from interfering with the subsequent focus path determination processing.
[0128] In this embodiment, by determining the preceding activity path of the overlapping node in its activity merge node path graph, the attention path corresponding to the overlapping node is determined based on the attention path determination rule to perform online activity attribution.
[0129] In one embodiment, please refer to Figure 8 The step of determining the attention path in each of the preceding node paths based on the attention path determination rule and according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user terminal, and taking the online activity corresponding to the attention path as the attribution online activity of the overlapping node, comprises the following steps:
[0130] Step S141, comparing the path lengths of the plurality of the preceding node paths, and determining the preceding node path with the longest path length among the preceding node paths as the concerned path:
[0131] The focus path determination rule refers to a rule for determining the focus path in each of the predecessor node paths. The focus path determination rule generally determines the focus path in each of the predecessor node paths based on the path length of each of the predecessor node paths or the total historical node conversion rate of each of the predecessor node paths.
[0132] Step S142, when there are multiple predecessor node paths with the longest path length, obtain the historical node conversion rate of each active node in each predecessor node path acted on by the user end, and calculate the total historical node conversion rate of each predecessor node path:
[0133] The historical node conversion rate generally refers to the trigger rate of the active event corresponding to the active node. For example, when the active event of the active node is a live broadcast room control display event, and the next active event of the live broadcast room control event is a live broadcast room control click event, then the historical node conversion rate of the active node is the ratio between the trigger times of the live broadcast room control click event and the live broadcast room control display event.
[0134] The total historical node conversion rate is the sum of the historical node conversion rates of each active node in the preceding node path.
[0135] Step S143, determining the target preceding node path with the highest total historical node conversion rate among the preceding node paths, and taking the target preceding node as the focus path:
[0136] After calculating the total historical node conversion rate corresponding to each of the predecessor node paths, the target predecessor node path with the highest total historical node conversion rate is determined, and then the target predecessor node is used as the focus path of the overlapping nodes corresponding to each of the predecessor node paths.
[0137] In this embodiment, the attention path corresponding to the overlapping node is determined, and the online activity corresponding to the attention path is attributed to the overlapping node, so as to track the online activity of the activity event corresponding to the overlapping node.
[0138] In one embodiment, please refer to Fig. 9 , after the step of determining the attention path in each of the preceding node paths based on the attention path determination rule and according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user terminal, and taking the online activity corresponding to the attention path as the attribution online activity of the overlapping node, the following steps are included:
[0139] Step S15, counting the attribution determination times of the multiple online activities corresponding to the target overlapping node, wherein the attribution determination times are determined according to the times each online activity acts on its associated overlapping node and is determined as an attribution online activity:
[0140] The attribution determination times refers to the number of times an online activity is determined as an attribution online activity, that is, the number of times a preceding path corresponding to an activity node path corresponding to the online activity is determined as a focus path.
[0141] Step S16, determining the target online activity whose attribution determination times exceeds the preset times in each of the online activities, and increasing the activity delivery times of the target online activity on the platform:
[0142] After counting the number of attribution determinations corresponding to the online activities, one or more online activities whose number of attribution determinations exceeds a preset number are determined as the target online activities, thereby increasing the number of activity delivery times of each target online activity on the platform, so as to increase the number of delivery times of the target online activities on the platform.
[0143] In this embodiment, by counting the attribution determination times of each online activity, online activities whose attribution determination times meet the preset times are screened out, and then the activity delivery times of these online activities are increased to improve the exposure rate of these online activities in the platform.
[0144] Furthermore, by functionalizing each step in the method disclosed in the above embodiments, an activity attribution device of the present application can be constructed. According to this idea, please refer to Fig.10 In a typical embodiment, the device includes: a node path drawing module 11, which is used to draw the activity node path corresponding to each online activity according to the activity embedding data of multiple online activities in the platform; an overlapping node determination module 12, which is used to merge the activity node paths to generate an activity merged node path graph, and determine one or more overlapping nodes between the activity node paths from the activity merged node path graph; a predecessor path drawing module 13, which is used to respond to the node attention event of any of the overlapping nodes, determine the multiple predecessor nodes corresponding to the overlapping nodes from the activity merged node path graph according to the user historical activity participation information corresponding to the node attention event, and draw one or more predecessor node paths of each of the predecessor nodes; an attribution activity determination module 14, which is used to determine the attention path in each of the predecessor node paths based on the attention path determination rule, according to the node length corresponding to each of the predecessor node paths and the historical node conversion rate of the user end, and use the online activity corresponding to the attention path as the attribution online activity of the overlapping node.
[0145] In one embodiment, the node path drawing module 11 includes: an activity tracking data acquisition submodule, used to obtain the activity tracking data corresponding to each of the multiple online activities in the platform, wherein the activity tracking data contains activity feature information corresponding to each of the multiple activity events; an activity path drawing submodule, used to draw the activity node path corresponding to each online activity according to the activity event name and activity event triggering sequence contained in the activity feature information of each activity event in each of the activity tracking data, wherein each activity event in the activity node path represents its activity feature information in the form of an activity node, and each of the activity nodes is connected according to its event triggering sequence.
[0146] In one embodiment, the overlapping node determination module 12 includes: a merged node path drawing submodule, which is used to merge multiple active node paths and draw an active merged node path graph; an overlapping node determination submodule, which is used to traverse the active merged node path graph, determine the active nodes that intersect between each of the active node paths, and use the active nodes as overlapping nodes.
[0147] In one embodiment, the preceding path drawing module 13 includes: an activity event determination submodule, which is used to respond to an online activity triggering event acting on a user terminal and determine the activity event corresponding to the online activity triggering event; a target overlapping node processing submodule, which is used to determine the target overlapping node corresponding to the activity event and determine the activity merge node path graph where the target overlapping node is located; a preceding path drawing submodule, which is used to take the target overlapping node as the end point and, based on the user's historical activity participation information, query the activity path composed of the preceding nodes of the target overlapping node from the activity merge node path graph and use each of the activity paths as the preceding activity path of the target overlapping node; and a preceding path processing submodule, which is used to remove invalid duplicate nodes from each of the preceding activity paths.
[0148] In one embodiment, the attribution activity determination module 14 includes: a path length comparison submodule, which is used to compare the path lengths of multiple predecessor node paths, and determine the predecessor node path with the longest path length among the predecessor node paths as the focus path; a node conversion rate calculation submodule, which is used to obtain the historical node conversion rate of each active node in each of the predecessor node paths acted on by the user end when there are multiple predecessor node paths with the longest path length, and calculate the total historical node conversion rate of each of the predecessor node paths; a focus path determination submodule, which is used to determine the target predecessor node path with the highest total historical node conversion rate among the predecessor node paths, and use the target predecessor node as the focus path.
[0149] See also Fig.11 A live broadcast activity attribution method of the present application, in its typical embodiment, comprises the following steps:
[0150] Step S21, in response to the anchor attention event acting on the audience end, determining the overlapping nodes corresponding to the anchor attention event:
[0151] The anchor attention event refers to an event triggered by the anchor user in the audience end attention platform. After the server responds to the anchor attention event, it will determine that the active event is an overlapping node of the anchor user attention event.
[0152] Step S22, obtaining a merged node path graph where the overlapping node is located, and determining one or more preceding node paths of the overlapping node from the merged node path graph according to the historical activity participation information of the user at the viewer end:
[0153] After the overlapping nodes are determined, the merged node path graph with the overlapping nodes is obtained, and then one or more preceding node paths of the overlapping nodes are determined from the merged node path graph based on the historical activity participation information of the user at the audience end.
[0154] The user's historical activity participation information generally includes live broadcast-related activity events such as live broadcast room control click activity events, follow-up anchor activity window pop-up activity events, participation activity control click activity events and activity page display activity events, live broadcast room promotion window click activity events or live broadcast room promotion pop-up display activity events.
[0155] Step S23, based on the attention path determination rule, according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user end, the attention path in each of the preceding node paths is determined, and the online activity corresponding to the attention path is used as the attributed online activity of the anchor's attention event:
[0156] When multiple predecessor node paths are determined, the path lengths of the predecessor node paths are compared, and the predecessor node path with the longest path length among the predecessor node paths is determined as the focus path. If there are multiple predecessor node paths with the longest path lengths, the historical node conversion rates of the user end acting on each active node in each predecessor node path are obtained, and the total historical node conversion rate of each predecessor node path is calculated, and then the target predecessor node path with the highest total historical node conversion rate among the predecessor node paths is determined, and the target predecessor node is taken as the focus path.
[0157] After determining the attention path corresponding to the overlapping node, the online activity corresponding to the attention path is determined, and the online activity is used as the attributed online activity of the anchor's attention event.
[0158] It can be seen from the typical implementation of the method that by responding in real time to the event of the audience following the anchor user in the live broadcast platform, one or more preceding paths are determined in a pre-drawn merged node path diagram according to the overlapping nodes corresponding to the event of following the anchor activity, and then the online activities of the anchor user are attributed based on the determined attention path of the anchor user, so that the live broadcast platform can optimize the online activities associated with following the anchor.
[0159] To solve the above technical problems, the present application also provides a computer device for running a computer program implemented according to the activity attribution method or the live broadcast activity attribution method. Fig.12 , Fig.12 This is a basic structural block diagram of the computer device in this embodiment.
[0160] like Fig.12 As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement an activity attribution method or a live activity attribution method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute an activity attribution method or a live activity attribution method. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0161] In this embodiment, the processor is used to execute the specific functions of each module / submodule in the activity attribution device or live activity attribution device of the present application, and the memory stores the program code and various data required to execute the above modules. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules / submodules in the activity attribution device or live activity attribution device, and the server can call the program code and data of the server to execute the functions of all submodules.
[0162] The present application also provides a computer-readable storage medium, wherein the activity attribution method or live broadcast activity attribution method is written into a computer program and stored in the storage medium in the form of computer-readable instructions. When the computer-readable instructions are executed by one or more processors, it means that the program is run in the computer, thereby enabling one or more processors to execute the steps of the activity attribution method of any of the above-mentioned embodiments.
[0163] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a computer-readable storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
[0164] In summary, the present application attributes online activity events through the path overlap nodes of each online activity in the platform, and then efficiently calculates the conversion rate of each online service.
[0165] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0166] Those skilled in the art will appreciate that the various operations, methods, steps, measures, and schemes in the processes discussed in this application may be alternated, altered, combined, or deleted. Further, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and schemes in the prior art that are similar to those disclosed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted.
[0167] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. An activity attribution method, characterized in that: The steps include: Based on the activity tracking data of multiple online activities in the platform, draw the activity node path corresponding to each of the online activities; Merging the activity node paths to generate an activity merged node path graph, and determining one or more overlapping nodes between the activity node paths from the activity merged node path graph; In response to a node attention event of any of the overlapping nodes, according to the user historical activity participation information corresponding to the node attention event, multiple predecessor nodes corresponding to the overlapping nodes are determined from the activity merge node path graph, and one or more predecessor node paths of each of the predecessor nodes are drawn; Based on the attention path determination rule, the attention path in each of the predecessor node paths is determined according to the node length corresponding to each of the predecessor node paths and the historical node conversion rate of the user end, and the online activity corresponding to the attention path is used as the attributed online activity of the overlapping node.
2. The method according to claim 1, characterized in that The step of drawing the activity node paths corresponding to each of the online activities according to the activity tracking data of the multiple online activities in the platform includes the following steps: Acquire the activity tracking data corresponding to each of the multiple online activities in the platform, wherein the activity tracking data includes activity feature information corresponding to each of the multiple activity events; According to the activity event name and activity event triggering sequence contained in the activity feature information of each activity event in the activity tracking data, an activity node path corresponding to each online activity is drawn. Each activity event in the activity node path represents its activity feature information in the form of an activity node, and each activity node is connected according to its event triggering sequence.
3. The method according to claim 1, characterized in that The step of merging the active node paths to generate an active merged node path graph, and determining one or more overlapping nodes between the active node paths from the active merged node path graph, comprises the following steps: Merging a plurality of said activity node paths to draw an activity merged node path graph; The activity merge node path graph is traversed to determine the activity nodes intersecting between the activity node paths, and the activity nodes are used as overlapping nodes.
4. The method according to claim 1, characterized in that The step of responding to a node attention event of any of the overlapping nodes, determining a plurality of predecessor nodes corresponding to the overlapping nodes from the activity merge node path graph according to the user historical activity participation information corresponding to the node attention event, and drawing one or more predecessor node paths of each of the predecessor nodes, comprises the following steps: In response to an online activity triggering event acting on a user terminal, determining an activity event corresponding to the online activity triggering event; Determine the target overlapping node corresponding to the activity event, and determine the activity merge node path graph where the target overlapping node is located; Taking the target overlapping node as the end point, querying the activity path composed of the predecessor nodes of the target overlapping node from the activity merge node path graph according to the user's historical activity participation information, and taking each of the activity paths as the predecessor activity path of the target overlapping node; Invalid duplicate nodes are removed from each of the preceding active paths.
5. The method according to claim 1, characterized in that The step of determining the attention path in each of the preceding node paths based on the attention path determination rule according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user terminal, and taking the online activity corresponding to the attention path as the attribution online activity of the overlapping node, comprises the following steps: Comparing the path lengths of the plurality of the preceding node paths, determining the preceding node path with the longest path length among the preceding node paths as the focus path; When there are multiple predecessor node paths with the longest path lengths, obtaining the historical node conversion rate of each active node in each predecessor node path acted on by the user end, and calculating the total historical node conversion rate of each predecessor node path; A target preceding node path having the highest total historical node conversion rate among the preceding node paths is determined, and the target preceding node is used as the focus path.
6. The method according to claim 1, characterized in that After the step of determining the attention path based on the attention path determination rule, according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user terminal, determining the attention path in each of the preceding node paths, and using the online activity corresponding to the attention path as the attributed online activity of the overlapping node, the following steps are included: Counting the number of attribution determinations of the plurality of online activities corresponding to the target overlapping node, wherein the number of attribution determinations is determined according to the number of times each of the online activities acts on its associated overlapping node and is determined as an attribution online activity; Determine a target online activity in which the attribution determination number exceeds a preset number among the online activities, and increase the number of activity delivery times of the target online activity on the platform.
7. A live broadcast activity attribution method, characterized in that: The steps include: In response to the anchor attention event acting on the audience end, determining the overlapping node corresponding to the anchor attention event; Obtaining a merged node path graph where the overlapping node is located, and determining one or more preceding node paths of the overlapping node from the merged node path graph according to the historical activity participation information of the user at the viewer end; Based on the attention path determination rule, according to the node length corresponding to each of the preceding node paths and the historical node conversion rate of the user end, the attention path in each of the preceding node paths is determined, and the online activity corresponding to the attention path is used as the attributed online activity of the anchor's attention event; The step of responding to the anchor attention event on the audience end and determining the overlapping nodes corresponding to the anchor attention event includes the following steps: Based on the activity tracking data of multiple online activities in the platform, draw the activity node path corresponding to each of the online activities; The active node paths are merged to generate an active merged node path graph, and one or more overlapping nodes between the active node paths are determined from the active merged node path graph.
8. An activity attribution device, characterized in that: include: A node path drawing module is used to draw the activity node path corresponding to each online activity according to the activity tracking data of multiple online activities in the platform; An overlapping node determination module, used for merging the active node paths to generate an active merged node path graph, and determining one or more overlapping nodes between the active node paths from the active merged node path graph; A predecessor path drawing module, for responding to a node attention event of any of the overlapping nodes, determining a plurality of predecessor nodes corresponding to the overlapping nodes from the activity merge node path graph according to the user historical activity participation information corresponding to the node attention event, and drawing one or more predecessor node paths of each of the predecessor nodes; The attribution activity determination module is used to determine the attention path in each of the predecessor node paths based on the attention path determination rule, according to the node length corresponding to each of the predecessor node paths and the historical node conversion rate of the user end, and use the online activity corresponding to the attention path as the attribution online activity of the overlapping node.
9. An electronic device, comprising a central processing unit and a memory, characterized in that: The central processing unit is used to call and run a computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the method are executed.
Citation Information
Patent Citations
Channel attribution method and device
CN110189152A
User determination method and device
CN113362097A
User behavior analysis method and device based on clustering algorithm, equipment and medium
CN113434745A
Business event attribution analysis method and device, electronic equipment and storage medium
CN113469519A
Attribution analysis method and device, computer equipment and storage medium
CN115409544A
