Information processing method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to an information processing method and device, equipment and a storage medium. The method provided herein includes: generating a target graph based on activity data of at least one user, the target graph including a plurality of nodes and edges connecting the plurality of nodes, each node indicating a related entity corresponding to the activity data, each edge indicating a jump from one entity to another entity; determining at least one reference path associated with at least one user from the target map; and determining the importance of at least one target node in the target graph in executing the target activity at least based on the at least one reference path. In this way, the importance of the target node in executing the target activity can be evaluated more accurately and comprehensively so as to reasonably arrange various activities.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for information processing. Background Art

[0002] The Internet provides access to a wide variety of resources. For example, the Internet allows access to various applications, products, audio and video content, etc. As the number and types of resources grow rapidly, it is very difficult for the audience to find the resources they are interested in from a large number of resources. For resource suppliers, they also hope that their resources can attract the attention of the target audience. In view of this, recommendation systems are used to recommend resources that meet user needs to the audience. When providing recommended content related to a specific resource, it is usually expected to provide the content that the user needs in the appropriate scenario so that the recommended content is more in line with the user's needs. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for information processing is provided. The method comprises: generating a target graph based on activity data of at least one user, the target graph comprising a plurality of nodes and edges connecting the plurality of nodes, each node indicating a related entity corresponding to the activity data, and each edge indicating a jump from one entity to another entity; determining at least one reference path associated with at least one user from the target graph; and determining, based at least on the at least one reference path, the importance of at least one target node in the target graph in executing a target activity.

[0004] In a second aspect of the present disclosure, a device for information processing is provided. The device includes: a target graph generation module, configured to generate a target graph based on activity data of at least one user, the target graph including a plurality of nodes and edges connecting the plurality of nodes, each node indicating a related entity corresponding to the activity data, and each edge indicating a jump from one entity to another entity; a reference path determination module, configured to determine at least one reference path associated with at least one user from the target graph; and a node importance determination module, configured to determine the importance of at least one target node in the target graph in performing a target activity based at least on at least one reference path.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer executable instructions, which, when executed by a device, cause the device to perform the method of the first aspect.

[0008] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments according to the present disclosure may be implemented;

[0011] Figure 2 An interaction diagram illustrating an example process for information processing according to some embodiments of the present disclosure;

[0012] Figure 3 shows an example target graph according to some embodiments of the present disclosure;

[0013] Figure 4 An interaction diagram illustrating an example process for information processing according to some embodiments of the present disclosure;

[0014] Figure 5 A flowchart of an example process for information processing according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A schematic structural block diagram showing an example apparatus for information processing according to some embodiments of the present disclosure; and

[0016] Figure 7 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0019] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0020] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of executing a subsequent action executed in response to the event or condition is not necessarily strongly related to the time when the event occurs or the condition is satisfied. For example, in some cases, the subsequent action may be executed immediately when the event occurs or the condition is satisfied; while in other cases, the subsequent action may be executed some time after the event occurs or the condition is satisfied.

[0021] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects are subject to the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user knows and confirms. Accordingly, when implementing each embodiment of the present disclosure, the type, scope of use, usage scenario, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0022] The schemes in this specification and the embodiments, if involving the processing of personal information, will be processed on the premise of having a legal basis (for example, obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. The user's refusal to process personal information other than the necessary information required for basic functions will not affect the user's use of basic functions. As an optional but non-restrictive implementation method, in response to receiving the user's active request, a method of sending a prompt message to the user may be, for example, a pop-up window, in which the prompt message may be presented in text. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device. It is understandable that the above notification and the process of obtaining user authorization are only illustrative and do not constitute a limitation on the implementation method of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation method of the present disclosure.

[0023] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0024] A "neural network" is a machine learning network based on deep learning. A neural network is capable of processing inputs and providing corresponding outputs, and typically includes an input layer and an output layer and one or more hidden layers between the input layer and the output layer. Neural networks used in deep learning applications typically include many hidden layers, thereby increasing the depth of the network. The layers of a neural network are connected in sequence so that the output of the previous layer is provided as input to the next layer, where the input layer receives the input of the neural network and the output of the output layer serves as the final output of the neural network. Each layer of a neural network includes one or more nodes (also called processing nodes or neurons), each of which processes input from the previous layer.

[0025] Generally, machine learning can be roughly divided into three stages, namely the training stage, the testing stage, and the application stage (also called the inference stage). In the training stage, a given model can be trained using a large amount of training data, and the parameter values ​​are continuously updated iteratively until the model can obtain consistent inferences that meet the expected goals from the training data. Through training, the model can be considered to be able to learn the association between input and output (also called input-to-output mapping) from the training data. The parameter values ​​of the trained model are determined. In the testing stage, the test input is applied to the trained model to test whether the model can provide the correct output, thereby determining the performance of the model. The testing stage can sometimes be integrated into the training stage. In the application or inference stage, the trained model can be used to process the actual model input based on the parameter values ​​obtained through training to determine the corresponding model output.

[0026] As briefly discussed above, the Internet provides access to a wide variety of resources. For example, the Internet provides access to various applications, commodities, audio and video content, etc. As the number and types of resources grow rapidly, it is very difficult for the audience of resources to find the resources of interest from a large number of resources. For resource suppliers, they also hope that their resources can attract the attention of the target audience. In view of this, recommendation systems are used to recommend resources that meet user needs to the audience. When providing recommended content related to specific resources, it is usually expected to provide the content that users need in appropriate scenarios so that the recommended content is more in line with user needs. In some schemes, the effectiveness of information processing strategies is evaluated by using attribution algorithms. However, in real scenarios, which are complex and diverse, existing attribution algorithms cannot be applied to complex and diverse scenarios.

[0027] To better illustrate the above phenomenon, the Internet information delivery is used as an example scenario for further explanation. In operation, the platform can deliver information to each application and / or each page of the application. Users can trigger each application and switch freely between pages through their respective terminal devices. In the above process, users will obtain various types of information recommended by the platform. Taking application recommendation as an example, the download entrance of the application can be delivered to each application and / or each page of the application. The user may eventually trigger the download of the application. In order to better realize the information processing of information, the platform needs to analyze whether there is a correlation between the user's download behavior and the previous application recommendation strategy. Furthermore, if the application recommendation information is delivered to multiple applications and / or multiple pages, the platform further hopes to know the user's system behavior is attributed to which page or pages for browsing the recommended information.

[0028] In order to determine the above causal relationship, various schemes involving channel classification and user behavior analysis are proposed. In some schemes, a single touch attribution scheme is proposed, for example, the user's behavior is attributed to the channel of the first / last release. In other schemes, the contribution rate of each channel can be analyzed with the help of time decay model, UV (Ultra Virtual) model, etc. In some schemes, a multi-touch attribution scheme is proposed. In this scheme, the channel involved is regarded as a touch point, and the contribution of each touch point in multiple touch points is considered. Specifically, the user's touch points on each channel are tracked by various tracking technologies. The user's touch point data is aggregated and converted into system-recognizable data. Next, based on experience, a preset weight is assigned to each channel touch point and the contribution of each channel in executing the target activity is calculated based on the weight. In this multi-touch attribution scheme, a preset weight needs to be assigned to each channel touch point based on experience. In other words, the accuracy of its evaluation is greatly affected by subjective judgment, and it is impossible to capture the true correlation between users and various channels.

[0029] As briefly discussed above, real scenarios are complex and diverse. Specifically, the number of Internet users has increased rapidly, the number of platform applications has also increased dramatically, and the page content within the application has become increasingly rich, which has led to the user's behavior trajectory becoming very complicated. In this case, the existing attribution algorithm is not applicable to complex and diverse scenarios. In view of this, there is an urgent need to provide an efficient and accurate information processing solution.

[0030] The embodiment of the present disclosure proposes a user information processing scheme. In the scheme, a target graph is generated based on the activity data of at least one user, the target graph includes multiple nodes and edges connecting the multiple nodes, each node indicates a related entity corresponding to the activity data, and each edge indicates a jump from one entity to another entity; at least one reference path associated with at least one user is determined from the target graph; at least based on at least one reference path, the importance of at least one target node in the target graph in executing the target activity is determined.

[0031] In this way, according to the embodiments of the present disclosure, the importance of the target node in executing the target activity can be evaluated more accurately and comprehensively to reasonably arrange various activities.

[0032] Various example implementations of the solution are described in detail below in conjunction with the accompanying drawings.

[0033] Example Environment

[0034] Figure 1A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. One or more content providing entities 120-1, 120-2, 130-3 (collectively or individually referred to as content providing entity 120 for ease of discussion) can distribute the content provided by them via an internal server 110. The content providing entity 120 can be an individual entity or an organizational entity, which is not limited here. One or more terminal devices 130-1, 130-2, 130-3, etc. (collectively or individually referred to as terminal device 130 for ease of discussion) are associated with a content distribution platform 110, and can access various types of content provided on the content distribution platform 110, for example, based on requests from corresponding users 132-1, 132-2, 132-3, etc. (collectively or individually referred to as user 132 for ease of discussion). The content distribution platform 110 can also provide corresponding content to a target group based on corresponding policies.

[0035] The terminal device 130 can deploy applications. The application can provide the user 132 with an integration of multiple applications or components. These applications can be used as application modules in the application. In some embodiments, the application can be downloaded and installed on the terminal device 130 as an application. In some embodiments, the application 120 can also be accessed in other ways, such as through a web page.

[0036] Application 120 may be any appropriate type of application that can provide media content, examples of which may include but are not limited to: local life service applications, social applications, audio / video applications, media item playback applications, broadcast applications, etc. The embodiments of the present disclosure are not limited in this respect. Figure 1 In the environment 100, if the application is active, the terminal device 130 can present an interactive page through the application. The interactive page can be any appropriate type of page, which can support the user 132 to input any appropriate type of data and present media items of any media item type to the user 132. The interactive interface can include various types of interfaces that can be provided by the application.

[0037] The terminal device 130 can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable game terminals, VR / AR devices, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDA), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, game devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 130 can also support any type of interface for the user (such as "wearable" circuits, etc.).

[0038] The server 130 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms. The server 130 may include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like.

[0039] A communication connection may be established between the server 130 and the terminal device 125. The communication connection may be established in a wired manner or a wireless manner. The communication connection may include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, etc., and the embodiments of the present disclosure are not limited in this respect. In the embodiments of the present disclosure, the server 130 and the terminal device 125 may implement signaling interaction through a mutual communication connection.

[0040] It should be understood that the structure and function of each element in the environment 100 are described for exemplary purposes only, and do not imply any limitation on the scope of the present disclosure. Some exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0041] Example Interaction

[0042] As briefly discussed above, with the rapid development of computing technology, the number of Internet users has increased rapidly, the number of platform applications has also increased dramatically, and the page content within the application has become increasingly rich, which has caused the user's behavior trajectory to become very complex. Traditional methods have difficulty in handling the user's behavior trajectory on multiple channels and cannot achieve effective channel attribution. In addition, traditional solutions cannot provide a comprehensive analysis of the user's complex behavior on different devices and / or platforms, nor can they integrate the data content scattered across different channels for in-depth analysis. In this case, traditional solutions cannot accurately evaluate the contribution of different entities in executing target activities, thereby failing to achieve optimal resource allocation and timely adjust activity deployment strategies.

[0043] To solve at least some or all of the above problems, according to some embodiments of the present disclosure, an information processing solution is proposed. Compared with the traditional information processing solution, according to some embodiments of the present disclosure, a graph-based information processing method is proposed, and in particular, an attribution algorithm based on graph theory is disclosed. According to the solution of the present disclosure, the entities, users, behaviors, etc. involved in the user activity data are constructed into a complex network model, and the graph theory algorithm is used to deeply analyze and quantify the contribution (also called importance) of each link involved in the information transfer process, and the information processing strategy is optimized accordingly.

[0044] It should be understood that the user in the present disclosure refers to any user who can participate in various activities, such as individuals, organizations, enterprises, merchants, etc. In short, the present disclosure is not limited in terms of the specific type of users.

[0045] In various embodiments of the present disclosure, a target activity refers to any activity that a user can participate in, such as a promotion activity, a publicity activity, a sales promotion activity, etc. In short, the present disclosure is not limited in terms of the specific content of the target activity.

[0046] In various embodiments of the present disclosure, nodes may be various elements involved in user activity data, including but not limited to users, user behaviors, channels, deployed activities, etc. In some embodiments, various elements may be identified as nodes in a target graph, and the associations between nodes may be represented as edges between nodes. Further, in some embodiments, the target nodes discussed in the present disclosure may be channel nodes.

[0047] Just for a better understanding of the various embodiments of the present disclosure discussed below, some example scenarios involved in the present disclosure are briefly described as follows.

[0048] As an example scenario, the platform can promote various activities among various merchants, for example, Activity 1 and Activity 2. In operation, Activity 1 and Activity 2 can be deployed in various channels (examples of channels can be, for example, a specified platform, a specified homepage, a specified mall, a specified pop-up window, an activity plaza, etc.). As an example, Activity 1 can be deployed in Channels 1 and 2, and Activity 2 can be deployed in Channels 1 and 3. Merchants can conduct various Internet activities, including but not limited to conducting activities on various channels and non-channels. Furthermore, users can participate in activities on a certain channel. According to the information processing method disclosed in the present invention, the importance of each channel in the user's execution of the target activity can be evaluated.

[0049] As an example scenario, the platform can recommend content 1 and content 1 to the user, for example, content 1 and content 2. In operation, content 1 and content 2 can be deployed in various entities, for example, content 1 can be deployed in entities 1 and 2, and content 2 can be deployed in entities 1 and 3. The user can perform various Internet activities, including but not limited to performing activities on various entities and non-entities. Further, the user can view recommended content on a certain entity. According to the information processing method disclosed in the present invention, the importance of each entity in the user's activity of viewing recommended content can be evaluated.

[0050] In other embodiments, the activities may also include other types, such as application promotion, website promotion, etc. In this case, the conversion of information to desired actions may be registration, sign-up, click, download, browse, etc.

[0051] It should be understood that the above example scenarios are only for better understanding of various embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0052] Next, we will combine Figure 2-4 To describe the information processing scheme of each embodiment of the present disclosure. Figure 1 To describe Figure 2-4 First refer to Figure 2 , which shows an interaction diagram of an example process 200 for information processing according to some embodiments of the present disclosure. In operation, the process 200 may be implemented by an electronic device, which may include Figure 1 The server 110 and / or terminal device 130 in.

[0053] exist Figure 2 In the example embodiment of , a directed graph association relationship can be constructed based on the user's relevant data. Further, based on the shortest path algorithm in graph theory, the centrality index of the graph, and the node contribution distribution algorithm, the contribution of the node can be accurately evaluated.

[0054] In some embodiments, the electronic device may generate a target graph based on the activity data of at least one user. In some embodiments, the activity data indicates that each user of the at least one user performs a target activity via a corresponding access process. Specifically, the target graph may include a plurality of nodes and edges connecting the nodes, wherein each node indicates a related entity corresponding to the activity data (e.g., each node indicates an entity passed through during the access process), and each edge indicates a jump from one entity to another entity. Figure 2 As shown, in operation, the electronic device collects event data related to the user (action 1). Examples of events include, but are not limited to, activation of a control, browsing of specified media content, dwell time on a specified page, etc. Based on the collected activity data, the target graph discussed in the present disclosure can be constructed.

[0055] See also Figure 3 An example 300 of an example target graph according to some embodiments of the present disclosure is shown. Figure 3 In an example embodiment, the following five types of nodes may be included. The target graph may include a first type of node (also referred to as a user node). As briefly discussed above, users may include various entities such as individuals and merchants. In some embodiments, user nodes may also record user attributes. For example, when the user is a merchant, user attributes may include merchant name, merchant type (such as an e-commerce platform, offline physical store, etc.), merchant geographic location, merchant scale (small, medium, large), sales, sales channel distribution, sales cycle, etc. When the user is an individual, user attributes may include the user's historical behavior data and personal information, etc. The target graph may include a second type of node (also referred to as a channel node), for example, it may include online channels (such as social media, media platforms), offline channels (such as physical stores), etc. As briefly discussed above, channel nodes may include various channels that can display and promote information.

[0056] The target graph may also include a third type of node (also called a behavior node or a behavior embedding point). A behavior node may refer to a specified action of a user in performing a target activity, such as signing up, registering, browsing, downloading, and the like.

[0057] The target graph may also include a fourth type of node (also called an activity node). The activity node refers to various activities deployed on the channel node, wherein various activities can be expressed by information, and users can participate in the deployed various activities by activating information.

[0058] The target graph may also include a fifth type of node (also referred to as other nodes). Other nodes refer to other nodes involved in the user's activities. As an example, the platform may deploy activity A on channel A (e.g., home page). When browsing the Internet, users may operate on multiple other pages, such as a shopping page. At this point, the shopping page is part of the user's behavior data, but does not belong to the channel entity. In this case, the shopping page may be marked as other nodes. Furthermore, the nodes may be connected to each other through association relationships.

[0059] exist Figure 3 In the example, there are users AE, other nodes A and B, channel node AC, behavior nodes A and B, and activity nodes A and B. Figure 3 The target graph example is constructed based on the real behavior data of user AE. In order to better illustrate how to construct a target body based on the user's activity data, the following example will be used to illustrate.

[0060] In one example, the behavior data of user A is as follows: enter channel node A, enter other node A, enter other node B, enter channel node B, enter channel node A, perform behavior A at channel node A, participate in activity A. The above behavior data can be constructed in the target graph as: user A->channel A->other node A->other node B->channel node B->channel node A->behavior node A->activity node A (for ease of discussion, it is abbreviated as user A real path 1).

[0061] In another example, the behavior data of user B is as follows: enter channel node B, enter channel node A, perform behavior A at channel node A, and sign up for activity A. The above behavior data can be constructed in the target graph as: user B->channel node B->channel node A->behavior node A->activity node A (for ease of discussion, it is abbreviated as user B real path 1).

[0062] In another example, the behavior data of user C is as follows: enter other node B, enter channel node B, perform behavior A at channel node B, and sign up for activity A. The above behavior data can be constructed in the target graph as: user C->other node B->channel node B->behavior node A->activity node A (for ease of discussion, it is abbreviated as user C real path 1).

[0063] In another example, the behavior data of user C is as follows: enter other node B, enter channel node C, perform behavior B at channel node C, and sign up for activity B. The above behavior data can be constructed in the target graph as: user C->other node B->channel node C->behavior node B->activity node B (for ease of discussion, it is abbreviated as user C real path 2).

[0064] In some embodiments, user A may enter channel node A multiple times, or stay in channel node A for a long time. In this case, the association between user A and channel node A may be measured by adjusting the weight of the edge between user A and channel node A. In some other embodiments, one or more users may trigger behavior A in channel A. In this case, the weight of the edge between channel node A and behavior node A may increase with the number of times the triggering behavior is triggered. In other words, the edges between the nodes in the target graph may have importance, and the value of the importance is determined by the association relationship between the nodes.

[0065] In some embodiments, directed graph associations can be stored in the form of an adjacency matrix. Specifically, for a directed graph association with M nodes, it can be expressed by a matrix of M*M order. Each element in the matrix can be associated with two nodes out of the M nodes. When an element is 1, it indicates that there is an edge pointing from one node to another node. Conversely, when an element is 0, it indicates that there is no association between the two nodes. Alternatively, in some embodiments, directed graph associations can be stored in the form of an edge list. Specifically, the edge list is actually a table, and each row of the table corresponds to an edge in the directed graph association, for example, two corresponding node identifiers and optional edge weights.

[0066] Through the above process, complex operations in the real world can be converted into computer-processable data while maximizing the retention of operational information.

[0067] In some embodiments, the electronic device may determine, for each of the multiple users, a reference path for the user to perform the target activity from the target graph. In some embodiments, the length of the reference path may satisfy a predetermined condition, such as the shortest path. The shortest path may simplify complex user behaviors, thereby obtaining core data in the user activity data.

[0068] In some embodiments, determining a reference path for a user to perform a target activity from a target graph includes: for each of a plurality of users, marking a start node and an end node from the target graph, wherein the start node and the end node respectively indicate a starting point entity and an end entity of a user's access process. Further, the electronic device determines the shortest path for the user to perform the target activity from the target graph based on the start node and the end node using a shortest path algorithm as a reference path.

[0069] exist Figure 2In an example embodiment, the electronic device can apply a shortest path algorithm based on the constructed directed graph association relationship. The node and edge information of the constructed directed graph association relationship is provided to the shortest path algorithm (action 3). In some embodiments, the shortest path algorithm identifies each user access process and marks the starting point and the end point. Based on the marked starting point and the end point, the shortest path between the starting point and the end point is determined.

[0070] As an example, for user A's real path 1, that is, user A->channel A->other node A->other node B->channel node B->channel node A->behavior node A->sign up for activity A, its shortest path can be user A->channel A->behavior node A->activity node A. As an example, for user B's real path 1, that is, user B->channel node B->channel node A->behavior node A->activity node A, its shortest path can be user B->channel node B->channel node A->behavior node A->activity node A.

[0071] In some embodiments, the electronic device determines the node importance of each node in the target graph based on multiple reference paths determined for multiple users. Specifically, the electronic device determines the node importance of each node in the target graph based on the number of occurrences of each of the multiple nodes in the multiple reference paths (also called betweenness centrality). In some embodiments, the edges in the target graph are labeled with edge importance (i.e., edge weights), and the edge importance of each edge is determined based on at least the following: the number of jumps performed from the nodes connected by the edge during the access process indicated by the data; and wherein determining the node importance of each node in the target graph includes: for each node, also determining the node importance of the node based on the edge importance of at least one edge connected to the node. In the above manner, the importance of each node in the target graph can be evaluated. Next, in combination Figure 2 and Figure 3 The importance of nodes is described in more detail.

[0072] exist Figure 2 In an example embodiment, the output of the shortest path algorithm can be used as input data for determining the betweenness centrality of each node (action 4). In some embodiments, betweenness centrality can be used as an indicator to measure the importance of a node. In some embodiments, betweenness centrality is mainly used to measure the intermediary role of a node in a network. In some embodiments, betweenness centrality measures the importance of a node by calculating the frequency with which the node appears in all shortest paths in the graph. For example, if a node appears in multiple shortest paths, then its betweenness centrality is high, indicating that the node plays an important intermediary role in the network.

[0073] In some embodiments, the electronic device 110 calculates the betweenness centrality of each node in the target graph (action 5), and assigns weights to each node according to the betweenness centrality of each node to evaluate its importance in the information processing process. In some embodiments, the importance of each node is comprehensively evaluated by comprehensively considering the weight of each node and the weight of the edge connected to each node. In operation, the betweenness centrality index and / or the weight of each node and the edge can be used as input to the node contribution allocation algorithm (action 6).

[0074] For example, in Figure 3 In the example embodiment, there are 2 shortest paths involving channel node A, and channel node A is associated with multiple other nodes via multiple edges, and each edge has a different weight. Further, there are 3 shortest paths through channel node B, and channel node B is associated with multiple other nodes via multiple edges, and each edge has a different weight. Based on the above information, the importance of channel node A and channel node B can be evaluated. Similarly, the importance of other nodes in the target graph can also be evaluated.

[0075] Next, based on the importance of the nodes, the importance of each path can be further determined. In some embodiments, the electronic device determines, for each of the multiple users, the path importance corresponding to the multiple paths for the user to perform the target activity based on the node importance of each node in the target graph. Further, in some embodiments, the electronic device determines the importance of at least one target node in the target graph in the target activity based on the path importance of the multiple paths determined for the multiple users, each target node indicating an entity of a predetermined type, and the importance of each target node in performing the target activity indicates the degree of contribution of the entity indicated by the target node in the process of the user performing the target activity. In some embodiments, determining the path importance of each of the multiple paths for the user to perform the target activity includes: also determining the path importance of each of the multiple paths for the user to perform the target activity based on the path lengths of each of the multiple paths.

[0076] exist Figure 2 In an example embodiment, the electronic device 110 may assign attribution scores based on the model for each path according to the node contribution allocation algorithm (action 7). Additionally, in some embodiments, the electronic device 110 may assign scores to each channel node based on the position and interaction of each channel node in the path. By accumulating and summarizing the attribution scores of all users, an overall contribution evaluation of each channel may be formed. In some embodiments, the attribution scores may be recorded (action 8).

[0077] As an example only, an exemplary description is given for the real path 1 and the shortest path of user A. The real path 1 of user A is user A->channel A->other node A->other node B->channel node B->channel node A->behavior node A->active node A, and the shortest path of user A is user A->channel A->A->behavior node A->active node A. In operation, the path can be scored based on the length of the path and the importance of each node involved in the path. In some embodiments, the longer the path, the lower the score, and / or the lower the importance of the nodes involved in the path, the lower the path score. When scoring the path, different calculation weights can also be assigned to different determination factors to more reasonably determine the scores of each path. As an example, the score of user A's real path 1 can be 2, and the score of user A's shortest path can be 5.

[0078] In some embodiments, the importance of at least one target node in the target graph in the target activity is determined: for each path in a plurality of paths, the path importance corresponding to the path is assigned to one or more target nodes contained in the path; and for each target node, the importance of the target node in executing the target activity is determined by aggregating the path importances assigned to the target node.

[0079] In some embodiments, for each path in a plurality of paths, allocating the path importance corresponding to the path to one or more target nodes contained in the path includes: for each path in a plurality of paths, allocating the path importance corresponding to the path to one or more target nodes based at least on the positions of the one or more target nodes on the path.

[0080] As an example only, the score of user A's real path 1 may be 2. Further, user A's real path 1 involves two target nodes, channel node A and channel node B. In some implementations, channel node A and channel node B may each be assigned 1 point. Further, in some embodiments, the positions of channel node A and channel node B in the path may be considered, for example, if channel node A is closer to behavior node A, channel node A may be assigned 1.5 and channel node B may be assigned 0.5. The score of user A's shortest path may be 5, and user A's shortest path only involves channel node A. In this case, all 5 points may be assigned to channel node A.

[0081] After assigning the path score to each channel node, the sum of the scores of each channel node can be determined. In operation, the channel with the highest sum score can be considered the most important node in executing the target activity. For example, if channel node A has the highest score, the strategy can be adjusted to put more information on channel A. For example, the score of user A's real path 1 is 2, and channel node A can be assigned 1.5, and channel node B can be assigned 0.5. The score of user A's shortest path is 5, and all of them are assigned to channel node A. In this case, the sum score of channel node A is 6.5, while the sum score of channel node B is 0.5. It can be considered that channel node A contributes more in the process of executing the target activity.

[0082] In some embodiments, the contribution score (also referred to as the attribution score) can be used as the basis for real-time adjustment (action 9). In operation, the electronic device 110 collects activity and user behavior data in real time, uses machine learning algorithms to analyze and predict user behavior, dynamically adjusts the attribution score, and updates information strategies and resource allocations in real time based on the attribution score (action 10).

[0083] In some embodiments, the updated policy determined by the real-time adjustment mechanism may be sent to the policy distribution module for application (Act 11). Optionally, in some embodiments, the adjusted information processing policy may be provided to various objects of the system (Act 12).

[0084] According to the information processing process of the above embodiment of the present disclosure, a more accurate identification of the importance of each target node in executing the target activity can be achieved through the analysis of multi-channel attribution. In addition, the attribution calculation complexity caused by multiple touch points is simplified by using the shortest path algorithm and / or betweenness centrality algorithm.

[0085] Figure 4 An interactive diagram illustrating an example process of an information processing strategy according to some embodiments of the present disclosure is shown. Figure 4 In the example embodiment, real-time data streams can be collected. In operation, an administrator can design and deploy a data collection system (action 1). The data collection system can collect user behavior data and activity data from different channels, and use a stream processing framework to build a data pipeline to achieve real-time transmission and processing of data (actions 2 and 3).

[0086] In some embodiments, the collected data can be analyzed in real time. Figure 4 As shown, the administrator can instruct the application to implement complex event processing technology (action 4). The event processing engine can monitor key events and behavior patterns in real time (action 5).

[0087] In some embodiments, based on real-time monitoring of key events and behavior patterns, the electronic device 110 can apply an online machine learning model to dynamically adjust attribution model parameters (action 6).

[0088] In some embodiments, the electronic device 110 can obtain feedback information in real time and adjust the recommendation strategy. Figure 4 As shown, in response to the design feedback mechanism from the administrator (action 7), the electronic device 110 can feed back the analysis results to the decision-making layer in real time (action 8). The decision-making layer can provide adjustment guidance (action 9). Based on the feedback results, the electronic device 110 can dynamically adjust the strategy and resource configuration (action 10).

[0089] In some embodiments, different algorithms can be tested to determine the preferred algorithm. Figure 4 As shown, in response to the administrator's implementation of the optimization algorithm execution (action 11), the electronic device 110 can implement the online optimization algorithm to dynamically optimize resource configuration. Further, the electronic device 110 can implement a test (e.g., A / B test) (actions 12 and 13), and select the optimal strategy according to the test results (action 14). Based on the submitted test results, the decision layer can send the determined preferred strategy to the administrator (action 15).

[0090] In some embodiments, the administrator can visualize the recommendation strategy in multiple dimensions. In some embodiments, the attribution analysis results and recommendation effects can be displayed based on the interactive interface of the browser / application. Additionally, in some embodiments, customized display views based on different dimensions are supported.

[0091] In this way, users can intuitively view the execution results of the target activity through the interactive interface, improving convenience and interactivity. Furthermore, through multi-dimensional visualization technology, an intuitive view display method can be provided to help users quickly obtain the execution results of the target activity.

[0092] According to the above-described exemplary embodiments of the present disclosure, efficient and effective information processing may be achieved through accurate attribution analysis.

[0093] Example Method

[0094] Further references Figure 5 , which shows a flowchart 500 of a process for user information processing according to some embodiments of the present disclosure. For ease of discussion, reference will be made to Figure 1 The process 500 is described with reference to the environment 100. The process 500 may be performed by an electronic device, and the electronic device may include a server 110 and / or a terminal device 130.

[0095] In box 510, the electronic device generates a target graph based on activity data of at least one user, the target graph includes multiple nodes and edges connecting the multiple nodes, each node indicates a related entity corresponding to the activity data, and each edge indicates a jump from one entity to another entity.

[0096] At block 520 , the electronic device determines at least one reference path associated with at least one user from the destination graph.

[0097] In block 530, the electronic device determines the importance of at least one target node in the target graph in performing the target activity based at least on at least one reference path. In some embodiments, determining the importance of at least one target node in the target graph in performing the target activity includes: the electronic device determines the node importance of each node in the target graph based at least on at least one reference path; determines the path importance of multiple paths associated with at least one user based on the node importance of each node in the target graph; determines the importance of at least one target node in the target graph in performing the target activity based on the path importance of the multiple paths.

[0098] In some embodiments, in some embodiments, determining at least one reference path associated with at least one user includes: the electronic device marks a starting node and an ending node from a target graph for each of the at least one user; and using a shortest path algorithm, based on the starting node and the ending node, determining from the target graph the shortest path for the user to perform the target activity as a reference path.

[0099] In some embodiments, determining the node importance of each node in the target graph includes: determining the node importance of each node in the target graph based on the number of occurrences of each of the plurality of nodes in at least one reference path.

[0100] In some embodiments, the edges in the target graph are labeled with edge importance; and determining the node importance of each node in the target graph includes: for each node, determining the node importance of the node based on the edge importance of at least one edge connected to the node.

[0101] In some embodiments, determining the path importance of multiple paths associated with at least one user includes: determining the path importance of each of the multiple paths for the user to perform the target activity further based on the path length of each of the multiple paths.

[0102] In some embodiments, the importance of at least one target node in the target graph in the target activity is determined: for each path in a plurality of paths, the path importance corresponding to the path is assigned to one or more target nodes contained in the path; and for each target node, the importance of at least one target node in the target graph in the target activity is determined by aggregating the path importances assigned to the target nodes.

[0103] In some embodiments, for each path in a plurality of paths, allocating the path importance corresponding to the path to one or more target nodes contained in the path includes: for each path in a plurality of paths, allocating the path importance corresponding to the path to one or more target nodes based at least on the positions of the one or more target nodes on the path.

[0104] In some embodiments, the length of the reference path satisfies a predetermined condition.

[0105] Example devices and equipment

[0106] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 6 A schematic structural block diagram of an example apparatus 600 for data query according to some embodiments of the present disclosure is shown. The apparatus 600 may be implemented as or included in the terminal device 125 (or in the server 130, or in the terminal device 125 and the server 130). Each module / component in the apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0107] like Figure 6 As shown, the device 600 includes: a target graph generation module 610, configured to generate a target graph based on activity data of at least one user, the target graph including multiple nodes and edges connecting the multiple nodes, each node indicating a related entity corresponding to the activity data, and each edge indicating a jump from one entity to another entity; a reference path determination module 620, configured to determine at least one reference path associated with at least one user from the target graph; and a node importance determination module 630, configured to determine the importance of at least one target node in the target graph in performing the target activity based at least on at least one reference path.

[0108] In some embodiments, the node importance determination module 630 is further configured to: determine the node importance of each node in the target graph based at least on at least one reference path; determine the path importance of multiple paths associated with at least one user based on the node importance of each node in the target graph; and determine the importance of at least one target node in the target graph in executing the target activity based on the path importance of multiple paths.

[0109] In some embodiments, the node importance determination module 630 is further configured to: for each user among at least one user, mark the starting node and the ending node from the target graph; and utilize the shortest path algorithm to determine, based on the starting node and the ending node, the shortest path for the user to perform the target activity from the target graph as a reference path.

[0110] In some embodiments, the node importance determination module 630 is further configured to determine the node importance of each node in the target graph based on the number of occurrences of each of the multiple nodes in at least one reference path.

[0111] In some embodiments, the edges in the target graph are labeled with edge importances. The node importance determination module 630 is further configured to: for each node, determine the node importance of the node based on the edge importance of at least one edge connected to the node.

[0112] In some embodiments, the node importance determination module 630 is further configured to determine the path importance of each of the multiple paths for the user to perform the target activity based on the path lengths of each of the multiple paths.

[0113] In some embodiments, the node importance determination module 630 is further configured to: for each path in a plurality of paths, assign the path importance corresponding to the path to one or more target nodes contained in the path; and for each target node, determine the importance of at least one target node in the target graph in executing the target activity by aggregating the path importance assigned to the target node.

[0114] In some embodiments, the node importance determination module 630 is further configured to: for each path in the multiple paths, at least based on the position of the one or more target nodes on the path, assign the path importance corresponding to the path to one or more target nodes.

[0115] In some embodiments, the length of the reference path satisfies a predetermined condition.

[0116] like Figure 7 As shown, the electronic device 700 is in the form of a general electronic device. The components of the electronic device 700 may include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 770, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 700.

[0117] The electronic device 700 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 700.

[0118] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0119] The communication unit 740 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0120] The input device 750 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 760 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 may also communicate with one or more external devices (not shown) through the communication unit 740 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 700, or communicate with any device that allows the electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0121] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0122] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0123] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0124] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0125] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0126] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for information processing, comprising: generating a target graph based on the activity data of at least one user, the target graph comprising a plurality of nodes and edges connecting the plurality of nodes, each of the nodes indicating a related entity corresponding to the activity data, and each of the edges indicating a jump from one entity to another entity; determining at least one reference path associated with the at least one user from the target graph; as well as Based at least on the at least one reference path, an importance of at least one target node in the target graph in performing a target activity is determined.

2. The method according to claim 1, wherein determining the importance of at least one target node in the target graph in executing the target activity comprises: Determining a node importance of each node in the target graph based at least on the at least one reference path; determining path importances of a plurality of paths associated with the at least one user based on the node importances of the respective nodes in the target graph; as well as The importance of at least one target node in the target graph in executing the target activity is determined based on the path importances of the multiple paths.

3. The method of claim 1 , wherein determining at least one reference path associated with the at least one user comprises: For each of the at least one user, marking a start node and an end node from the target graph; as well as The shortest path algorithm is used to determine the shortest path for the user to perform the target activity from the target graph based on the start node and the end node, as the reference path.

4. The method according to claim 2, wherein determining the node importance of each node in the target graph comprises: The node importance of each node in the target graph is determined based on the number of occurrences of each of the multiple nodes in the at least one reference path.

5. The method of claim 2, wherein the edges in the target graph are labeled with edge importances; and wherein determining the node importances of the respective nodes in the target graph comprises: For each node, the node importance of the node is also determined based on the edge importance of at least one edge connected to the node.

6. The method of claim 2, wherein determining the path importance of the plurality of paths associated with the at least one user comprises: The path importance of each of the plurality of paths is also determined based on the path length of each of the plurality of paths.

7. The method according to claim 2, wherein determining the importance of at least one target node in the target graph in performing the target activity comprises: For each path in the plurality of paths, assigning a path importance corresponding to the path to one or more target nodes included in the path; as well as For each target node, the importance of the at least one target node in performing the target activity is determined by aggregating the path importances assigned to the target node.

8. The method according to claim 7, wherein for each of the plurality of paths, allocating the path importance corresponding to the path to one or more target nodes included in the path comprises: For each path in the plurality of paths, a path importance corresponding to the path is allocated to the one or more target nodes based at least on positions of the one or more target nodes on the path.

9. The method according to claim 1, wherein the length of the reference path satisfies a predetermined condition.

10. An apparatus for information processing, comprising: a target graph generation module, configured to generate a target graph based on activity data of at least one user, the target graph comprising a plurality of nodes and edges connecting the plurality of nodes, each of the nodes indicating a related entity corresponding to the activity data, and each of the edges indicating a jump from one entity to another entity; a reference path determination module configured to determine at least one reference path associated with the at least one user from the target graph; as well as The node importance determination module is configured to determine the importance of at least one target node in the target graph in executing the target activity based at least on the at least one reference path.

11. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 9 when executed by the at least one processing unit.

12. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 9.

13. A computer program product tangibly stored in a computer storage medium and comprising computer executable instructions which, when executed by a device, cause the device to perform the method according to any one of claims 1 to 9.

Images