User value determination method and apparatus, electronic device, and storage medium
By acquiring user relationship networks and calculating feature matrices, core long-term users in the application can be accurately identified, solving the problem of the inability to accurately identify core long-term users in existing technologies and improving the effect of private domain traffic expansion.
Patent Information
- Application Number
- CN202211294504.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-10-21
- Publication Date
- 2026-02-17
- Estimated Expiration
- 2042-10-21
AI Technical Summary
Existing technologies cannot accurately identify core long-term users within an application, resulting in insufficient effectiveness in expanding private domain traffic.
By acquiring the user relationship network, determining the adjacency matrix and the first feature matrix, calculating the second feature matrix of the user relationship network, and using eigenvector centrality to determine user value, core long-term users can be accurately identified.
It enables accurate identification of user value and improves the expansion effect of private domain traffic.
Smart Images
Figure CN115587842B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of application development technology, and in particular to a method, apparatus, electronic device and storage medium for determining user value. Background Technology
[0002] With the rise of e-commerce, private domain traffic has become increasingly important. Many e-commerce companies expand their private domain traffic through their own applications (APPs). However, in the process of leveraging existing users to drive new users and expand private domain traffic, the inability to accurately identify core existing users and utilize their marketing power to attract more new users often results in insufficient private domain traffic expansion. Therefore, determining the user value of each user within an application and accurately identifying core existing users has become a pressing technical problem that needs to be solved. Summary of the Invention
[0003] This application provides a method, apparatus, electronic device, and storage medium for determining user value, in order to solve the problem that the existing technology cannot accurately identify core old users, resulting in insufficient effect of private domain traffic expansion.
[0004] Firstly, this application provides a method for determining user value, the method comprising:
[0005] Obtain a user relationship network, wherein the number of nodes in the user relationship network corresponds to the number of users in the target application, and the user relationship network is used to characterize the relationships between users in the target application;
[0006] Determine the adjacency matrix and the first feature matrix corresponding to the user relationship network. The adjacency matrix is used to characterize the adjacency relationship of each node in the user relationship network, and the first feature matrix is used to characterize the degree centrality of each node in the user relationship network.
[0007] Based on the adjacency matrix and the first feature matrix, a second feature matrix corresponding to the user relationship network is determined. The second feature matrix is used to characterize the eigenvector centrality of each node in the user relationship network.
[0008] Based on the eigenvector centrality, the user value of each user in the target application is determined.
[0009] Optionally, determining the second feature matrix corresponding to the user relationship network based on the adjacency matrix and the first feature matrix includes:
[0010] Iterative calculations are performed based on the adjacency matrix and the first feature matrix, and the calculation results corresponding to each iteration are recorded.
[0011] If the preset conditions are met, the iterative calculation is stopped, and the calculation result corresponding to the last iteration is determined as the second feature matrix.
[0012] The preset condition is that the number of iterations reaches a preset threshold, or the calculation results of two adjacent iterations are proportional.
[0013] Optionally, the iterative calculation based on the adjacency matrix and the first feature matrix includes:
[0014] S1, calculate the product of the adjacency matrix and the first feature matrix to obtain the intermediate matrix;
[0015] S2, calculate the product of the adjacency matrix and the intermediate matrix;
[0016] S3: After obtaining the product result of the adjacency matrix and the intermediate matrix each time, replace the intermediate matrix in S2 with the product result and repeat S2.
[0017] Optionally, obtaining the user relationship network includes:
[0018] Obtain user data corresponding to each user in the target application, the user data including usage records of entering the target application from links shared by other users;
[0019] Based on the user data, determine the correlation between users in the target application;
[0020] The user relationship network is determined based on the correlation between users in the target application.
[0021] Optionally, after determining the user value of each user in the target application based on the feature vector centrality, the method further includes:
[0022] Based on the user value of each user in the user relationship network, multiple user value ranges are determined;
[0023] Set corresponding incentive strategies for each of the user value ranges.
[0024] Secondly, this application also provides a user value determination device, the device comprising:
[0025] The acquisition module is used to acquire a user relationship network, wherein the number of nodes in the user relationship network corresponds to the number of users in the target application, and the user relationship network is used to characterize the relationship between users in the target application;
[0026] The first determining module is used to determine the adjacency matrix and the first feature matrix corresponding to the user relationship network. The adjacency matrix is used to characterize the adjacency relationship of each node in the user relationship network, and the first feature matrix is used to characterize the degree centrality of each node in the user relationship network.
[0027] The second determining module is used to determine the second feature matrix corresponding to the user relationship network based on the adjacency matrix and the first feature matrix. The second feature matrix is used to characterize the feature vector centrality of each node in the user relationship network.
[0028] The third determining module is used to determine the user value of each user in the target application based on the feature vector centrality.
[0029] Thirdly, this application also provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;
[0030] Memory, used to store computer programs;
[0031] When a processor executes a program stored in memory, it implements the steps of the user value determination method described in any embodiment of the first aspect.
[0032] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the user value determination method as described in any embodiment of the first aspect.
[0033] In this embodiment, a user relationship network is obtained, where the number of nodes in the network corresponds to the number of users in the target application. This network represents the correlation between users in the target application. An adjacency matrix and a first feature matrix are determined for the user relationship network. The adjacency matrix represents the adjacency relationships between nodes in the network, and the first feature matrix represents the degree centrality of each node. Based on the adjacency matrix and the first feature matrix, a second feature matrix is determined, representing the eigenvector centrality of each node. Based on the eigenvector centrality, the user value of each user in the target application is determined. Through this method, the second feature matrix corresponding to the user relationship network can be determined based on the adjacency matrix and the first feature matrix. Then, based on the eigenvector centrality of each element in the second feature matrix, the user value of each user in the network can be obtained. This allows for accurate identification of core existing users with high user value within the network, facilitating the subsequent use of the identified core existing users' marketing power to expand to more new users, thereby effectively improving the expansion effect of private domain traffic. Attached Figure Description
[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0035] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0036] Figure 1 A flowchart illustrating a user value determination method provided in an embodiment of this application;
[0037] Figure 2 A schematic diagram of a user relationship network provided for an embodiment of this application;
[0038] Figure 3 This is a schematic diagram of the structure of a user value determination device provided in an embodiment of this application;
[0039] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0040] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0041] See Figure 1 , Figure 1 This is a flowchart illustrating a method for determining user value provided in an embodiment of this application. Figure 1 As shown, the user value determination method may include the following steps:
[0042] Step 101: Obtain the user relationship network. The number of nodes in the user relationship network corresponds to the number of users in the target application. The user relationship network is used to represent the relationship between users in the target application.
[0043] Specifically, the target application can be configured according to actual needs. It can be any type of application, such as a shopping app, game app, social app, or video playback app; this application does not impose any specific limitations. The aforementioned user relationship network refers to an undirected network generated based on the relationships between users within the target application. In this user relationship network, different nodes represent different users. If two users are related, their nodes are connected by an edge; if two users are not related, their nodes are not connected by an edge. For example, suppose a target application includes 5 users. In this user relationship network, there are 5 nodes. Let V1 represent user 1, V2 represent user 2, V3 represent user 3, V4 represent user 4, and V5 represent user 5. If user 1 is associated with users 2, 3, and 4; user 2 is associated with users 1 and 3; user 3 is associated with users 1, 2, and 4; user 4 is associated with users 1 and 5; and user 5 is only associated with user 4, then the user relationship network is as follows: Figure 2 As shown.
[0044] It should be noted that since the user relationship network changes in real time, it needs to be retrieved periodically to analyze the user value of each user in the current target application. As an optional implementation, the user relationship network can be retrieved once a day.
[0045] Step 102: Determine the adjacency matrix and the first feature matrix corresponding to the user relationship network. The adjacency matrix is used to characterize the adjacency relationship of each node in the user relationship network, and the first feature matrix is used to characterize the degree centrality of each node in the user relationship network.
[0046] Specifically, the adjacency matrix described above is determined based on the associations between different users in the target application. This adjacency matrix can be used to characterize the adjacency relationships between nodes in the user relationship network. The adjacency matrix is a two-dimensional array, and since the user relationship network is undirected, the elements on the main diagonal of the adjacency matrix must be zero, and the elements in the adjacency matrix are symmetric along the main diagonal. The first characteristic matrix described above is used to characterize the degree centrality of each node in the user relationship network. This first characteristic matrix is a one-dimensional matrix, and each element in the first characteristic matrix represents the degree of each node in the user relationship network.
[0047] For example, suppose a user relationship network is like Figure 2 As shown, the adjacency matrix A and the first feature matrix X corresponding to this user relationship network can be obtained as follows:
[0048]
[0049]
[0050] Thus, the adjacency matrix A is a 5x5 matrix, where the element a ij Let a represent the element in the i-th row and j-th column. If the i-th node in the user relationship network is connected to the j-th node, then a ij The value of a is 1; if the i-th node and the j-th node in the user relationship network are not connected, then a ij The value is 0. The first feature matrix X is a 5*1 matrix, where each element represents the degree centrality of each node in the user relationship network, that is, the number of connections between that node and other nodes.
[0051] Step 103: Based on the adjacency matrix and the first feature matrix, determine the second feature matrix corresponding to the user relationship network. The second feature matrix is used to characterize the eigenvector centrality of each node in the user relationship network.
[0052] Specifically, the second characteristic matrix mentioned above is used to characterize the eigenvector centrality of each node in the user relationship network. Eigenvector centrality is another indicator for measuring node centrality. The basic idea of eigenvector centrality is that the centrality of a node is a function of the centrality of its neighboring nodes; that is, the more important the nodes connected to a node, the more important the node itself. The difference between eigenvector centrality and vertex degree centrality is that vertex degree centrality refers to the number of associated nodes (i.e., degree) of each node, while eigenvector centrality is obtained by spreading vertex degree centrality using an adjacency matrix.
[0053] In this step, the second characteristic matrix corresponding to the user relationship network can be determined based on the adjacency matrix and the first characteristic matrix. Specifically, the nodes in the user relationship network have a set of values. Multiplying the first characteristic matrix by the adjacency matrix A does not change the relative magnitudes of the elements in the first characteristic matrix. That is, the values of the elements in the first characteristic matrix will increase, but the multiplication factor is the same. Mathematically, this can be expressed as:
[0054] Ax=λx
[0055] x = cAx
[0056] The vectors that satisfy this property are the eigenvectors of matrix A. The elements of the eigenvectors represent the eigenvector centrality of each node in the user relationship network.
[0057] Let x be the number of times x is used. i If is the eigenvector centrality measure of node Vi, then:
[0058]
[0059] Where c is a proportionality constant, c = λ -1 ,x=[x1,x2,x3,...,x n ] T d ij Let x represent the element in the i-th row and j-th column of the adjacency matrix A. j This represents the element in the j-th column of the second characteristic matrix.
[0060] Therefore, by combining the above formula, the second characteristic matrix can be directly obtained based on the adjacency matrix A and the proportionality constant c; alternatively, the eigenvector centrality can be diffused multiple times based on the adjacency matrix and the first characteristic matrix (i.e., the initial vertex degree centrality), and after stabilization, a final eigenvector centrality, i.e., the second characteristic matrix, can be obtained. This application does not impose specific limitations on the embodiments.
[0061] Step 104: Determine the user value of each user in the target application based on the eigenvector centrality.
[0062] After obtaining the eigenvector centrality of each node in the user relationship network, the user value of each user in the target application can be determined based on the eigenvector centrality of each node. Generally speaking, the higher the eigenvector centrality of a node, the higher the user value of the user corresponding to that node; the lower the eigenvector centrality of a node, the lower the user value of the user corresponding to that node.
[0063] In this embodiment, the second feature matrix corresponding to the user relationship network can be determined based on the adjacency matrix and the first feature matrix. Then, based on the eigenvector centrality of each element in the second feature matrix, the user value of each user in the user relationship network can be obtained. This allows for the accurate identification of core old users with high user value in the user relationship network, facilitating the subsequent use of the marketing power of the identified core old users to expand more new users, thereby effectively improving the private domain traffic expansion effect.
[0064] Further, step 103 above, determining the second feature matrix corresponding to the user relationship network based on the adjacency matrix and the first feature matrix, includes:
[0065] Iterative calculations are performed based on the adjacency matrix and the first characteristic matrix, and the calculation results for each iteration are recorded.
[0066] If the preset conditions are met, the iterative calculation is stopped, and the calculation result corresponding to the last iteration is determined as the second feature matrix.
[0067] The preset conditions are that the number of iterations reaches a preset threshold, or the calculation results of two adjacent iterations are proportional.
[0068] In one embodiment, the second feature matrix can be calculated by iteratively calculating the adjacency matrix and the first feature matrix. Specifically, iterative calculations can be performed based on the adjacency matrix and the first feature matrix, and the calculation result corresponding to each iteration is recorded after each iteration. When the number of iterations reaches a preset threshold, or when the calculation results of two adjacent iterations are proportional, the iterative calculation is stopped, and the calculation result corresponding to the last iteration is determined as the second feature matrix.
[0069] It should be noted that the preset threshold here can be set according to actual needs, such as 10 times, 20 times, 30 times, etc. During the iterative calculation, the number of iterations can be recorded. When the number reaches the preset threshold, the iteration calculation ends. During the iterative calculation, the calculation result of each iteration can also be recorded, and the calculation result of the current iteration can be compared with the calculation result of the previous iteration. If the two are proportional (i.e., each element in the calculation result of the current iteration is each element in the calculation result of the previous iteration multiplied by the same factor), it means that the proportion of each node in the whole has remained stable. This result is the eigenvector centrality of each node.
[0070] In this embodiment, the second feature matrix is calculated by iteratively calculating the adjacency matrix and the first feature matrix, thereby obtaining the eigenvector centrality of each node. This allows for the determination of the value of each user by utilizing the magnitude of the eigenvector centrality of each node, defining user levels, and implementing different point systems to incentivize existing users to continuously attract new users.
[0071] Furthermore, the above steps, including iterative calculations based on the adjacency matrix and the first characteristic matrix, include:
[0072] S1, calculate the product of the adjacency matrix and the first characteristic matrix to obtain the intermediate matrix;
[0073] S2, calculate the product of the adjacency matrix and the intermediate matrix;
[0074] S3: After obtaining the product of the adjacency matrix and the intermediate matrix each time, replace the intermediate matrix in S2 with the product result and repeat S2.
[0075] In one embodiment, during the iterative calculation based on the adjacency matrix and the first feature matrix, an intermediate matrix can be obtained by calculating the product of the adjacency matrix and the first feature matrix. Then, the product of the adjacency matrix and the intermediate matrix can be calculated to obtain the product result. This product result is then used as a new intermediate matrix and multiplied with the adjacency matrix. This process is repeated until the above-mentioned preset condition is met, at which point the iterative calculation stops.
[0076] For example, when the adjacency matrix A corresponding to the user relationship network and the first feature matrix X corresponding to the user relationship network are respectively:
[0077]
[0078]
[0079] Therefore, when performing the product calculation based on the adjacency matrix A and the first characteristic matrix X, the intermediate matrix B can be obtained as follows:
[0080]
[0081] Then, by multiplying the adjacency matrix A and the intermediate matrix B, the product result can be obtained as follows:
[0082]
[0083] The product result D is used as the new intermediate matrix B, and then multiplied with the adjacency matrix A. This process is repeated iteratively until the aforementioned preset condition is met, at which point the iteration stops. Here, the adjacency matrix A redistributes the sum of neighboring nodes to each node, thus "diffusion" of the degree centrality of the nodes.
[0084] In this embodiment, the adjacency matrix and the first feature matrix can be iteratively calculated in the manner described above to obtain the second feature matrix.
[0085] Furthermore, step 101 above, obtaining the user relationship network, includes:
[0086] Obtain user data for each user in the target application. The user data includes usage records of users who accessed the target application through links shared by other users.
[0087] Based on user data, determine the relationships between users in the target application;
[0088] Determine the user relationship network based on the connections between users in the target application.
[0089] In one embodiment, when acquiring the user relationship network, user data corresponding to each user in the target application can be obtained. This user data may include, but is not limited to, usage records such as accessing the target application through links shared by other users. Usage records may include operation records such as searching, viewing, and purchasing. After acquiring the user relationship network, the correlation between users in the target application can be determined based on the user data. Users are then treated as nodes in the user relationship network, and the correlations between users are treated as edges, thus generating the user relationship network. This provides the user relationship network of the users in the target application, facilitating subsequent analysis of the user value of the users in the target application.
[0090] Furthermore, after determining the user value of each user in the target application based on eigenvector centrality in step 104 above, the method further includes:
[0091] Based on the user value of each user in the user relationship network, multiple user value ranges are determined;
[0092] Set corresponding incentive strategies for each user's value range.
[0093] In one embodiment, after determining the user value of each user in the target application, multiple user value ranges can be determined based on the user value of each user in the user relationship network. Each user's user value is then divided into different user value ranges, and incentives for user acquisition are applied based on the incentive strategy corresponding to each user value range. This allows for the development of better incentive strategies based on identified core existing users, actively encouraging them to recommend new users.
[0094] In practical applications, this scheme can be applied to e-commerce applications. During the process of existing users referring new users, existing users can recommend purchase links to new users. When a new user clicks the purchase link, their mobile phone number is registered as a platform user account, realizing the process of existing users referring new users. Furthermore, new users entering the application can also become existing users. If they participate in a distribution model, they can earn points. Existing users can also click on each other's links to make purchases, and the person who shared the link will receive corresponding points (which can be used for discounts or other benefits when purchasing goods). Therefore, by using user data from shared links between users, a graph database can be constructed, generating a relationship network (i.e., the user relationship network mentioned above). Then, using eigenvector centrality, the eigenvector centrality of each user in the network can be calculated. The magnitude of the eigenvector centrality determines the user value of each user, defining user levels and implementing different point systems, thereby incentivizing existing users to continuously recruit new users. In this way, within the user relationship network, people in the network can be stratified by user value, and different point systems can be adopted to incentivize users to continuously recruit new users. That is, those who share more receive higher point levels.
[0095] See Figure 3 , Figure 3 This is a schematic diagram of a user value determination device provided in an embodiment of this application. Figure 3 As shown, the user value determination device 300 includes:
[0096] The acquisition module 301 is used to acquire the user relationship network. The number of nodes in the user relationship network corresponds to the number of users in the target application. The user relationship network is used to represent the relationship between users in the target application.
[0097] The first determining module 302 is used to determine the adjacency matrix and the first feature matrix corresponding to the user relationship network. The adjacency matrix is used to characterize the adjacency relationship of each node in the user relationship network, and the first feature matrix is used to characterize the degree centrality of each node in the user relationship network.
[0098] The second determining module 303 is used to determine the second feature matrix corresponding to the user relationship network based on the adjacency matrix and the first feature matrix. The second feature matrix is used to characterize the eigenvector centrality of each node in the user relationship network.
[0099] The third determining module 304 is used to determine the user value of each user in the target application based on the eigenvector centrality.
[0100] Furthermore, the second determining module 303 includes:
[0101] The iterative calculation submodule is used to perform iterative calculations based on the adjacency matrix and the first characteristic matrix, and to record the calculation results corresponding to each iteration.
[0102] The first determining submodule is used to stop the iterative calculation when the preset conditions are met, and to determine the calculation result corresponding to the last iterative calculation as the second feature matrix;
[0103] The preset conditions are that the number of iterations reaches a preset threshold, or the calculation results of two adjacent iterations are proportional.
[0104] Furthermore, the iterative computation submodule includes:
[0105] The first calculation unit is used to execute step S1, calculate the product of the adjacency matrix and the first characteristic matrix, and obtain the intermediate matrix;
[0106] The second calculation unit is used to execute step S2, which calculates the product of the adjacency matrix and the intermediate matrix;
[0107] The third calculation unit is used to execute step S3. After obtaining the product result of the adjacency matrix and the intermediate matrix each time, the intermediate matrix in S2 is replaced with the product result and S2 is executed repeatedly.
[0108] Furthermore, the acquisition module 301 includes
[0109] The Get submodule is used to obtain user data corresponding to each user in the target application. The user data includes usage records of entering the target application through links shared by other users.
[0110] The second determination submodule is used to determine the correlation between users in the target application based on user data;
[0111] The third determination submodule is used to determine the user relationship network based on the correlation between users in the target application.
[0112] Furthermore, the user value determination device 300 also includes:
[0113] The fourth determination module is used to determine multiple user value ranges based on the user value of each user in the user relationship network;
[0114] The settings module is used to set corresponding incentive strategies for each user's value range.
[0115] It should be noted that the user value determination device 300 can implement the steps of the user value determination method provided in any of the aforementioned method embodiments and achieve the same technical effect, which will not be elaborated here.
[0116] like Figure 4As shown in the illustration, this application also provides an electronic device, including a processor 411, a communication interface 412, a memory 413, and a communication bus 414, wherein the processor 411, the communication interface 412, and the memory 413 communicate with each other via the communication bus 414.
[0117] Memory 413 is used to store computer programs;
[0118] In one embodiment of this application, when the processor 411 executes the program stored in the memory 413, it implements the user value determination method provided in any of the foregoing method embodiments, including:
[0119] Obtain the user relationship network. The number of nodes in the user relationship network corresponds to the number of users in the target application. The user relationship network is used to represent the relationship between users in the target application.
[0120] Determine the adjacency matrix and the first feature matrix corresponding to the user relationship network. The adjacency matrix is used to characterize the adjacency relationship of each node in the user relationship network, and the first feature matrix is used to characterize the degree centrality of each node in the user relationship network.
[0121] Based on the adjacency matrix and the first feature matrix, the second feature matrix corresponding to the user relationship network is determined. The second feature matrix is used to characterize the eigenvector centrality of each node in the user relationship network.
[0122] Based on eigenvector centrality, determine the user value of each user in the target application.
[0123] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the user value determination method provided in any of the foregoing method embodiments.
[0124] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0125] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A method for determining user value, characterized in that, The method includes: Obtain a user relationship network, wherein the number of nodes in the user relationship network corresponds to the number of users in the target application, and the user relationship network is used to characterize the relationships between users in the target application; Determine the adjacency matrix and the first feature matrix corresponding to the user relationship network. The adjacency matrix is used to characterize the adjacency relationship of each node in the user relationship network. The first feature matrix is used to characterize the degree centrality of each node in the user relationship network. Each element in the first feature matrix represents the degree of each node in the user relationship network. Based on the adjacency matrix and the first feature matrix, a second feature matrix corresponding to the user relationship network is determined. The second feature matrix is used to characterize the eigenvector centrality of each node in the user relationship network. The eigenvector centrality is obtained by spreading the degree centrality of the nodes using the adjacency matrix. Based on the eigenvector centrality, the user value of each user in the target application is determined; The step of determining the second feature matrix corresponding to the user relationship network based on the adjacency matrix and the first feature matrix includes: Iterative calculations are performed based on the adjacency matrix and the first feature matrix, and the calculation results corresponding to each iteration are recorded. If the preset conditions are met, the iterative calculation is stopped, and the calculation result corresponding to the last iteration is determined as the second feature matrix. The preset condition is that the number of iterations reaches a preset threshold, or the calculation results of two adjacent iterations are proportional. The iterative calculation based on the adjacency matrix and the first feature matrix includes: S1, calculate the product of the adjacency matrix and the first feature matrix to obtain the intermediate matrix; S2, calculate the product of the adjacency matrix and the intermediate matrix; S3: After obtaining the product result of the adjacency matrix and the intermediate matrix each time, replace the intermediate matrix in S2 with the product result and repeat S2.
2. The method according to claim 1, characterized in that, The acquisition of the user relationship network includes: Obtain user data corresponding to each user in the target application, the user data including usage records of entering the target application from links shared by other users; Based on the user data, determine the correlation between users in the target application; The user relationship network is determined based on the correlation between users in the target application.
3. The method according to claim 1, characterized in that, After determining the user value of each user in the target application based on the feature vector centrality, the method further includes: Based on the user value of each user in the user relationship network, multiple user value ranges are determined; Set corresponding incentive strategies for each of the user value ranges.
4. A user value determination device, characterized in that, The device includes: The acquisition module is used to acquire a user relationship network, wherein the number of nodes in the user relationship network corresponds to the number of users in the target application, and the user relationship network is used to characterize the relationship between users in the target application; The first determining module is used to determine the adjacency matrix and the first feature matrix corresponding to the user relationship network. The adjacency matrix is used to characterize the adjacency relationship of each node in the user relationship network. The first feature matrix is used to characterize the degree centrality of each node in the user relationship network. Each element in the first feature matrix represents the degree of each node in the user relationship network. The second determining module is used to determine the second feature matrix corresponding to the user relationship network based on the adjacency matrix and the first feature matrix. The second feature matrix is used to characterize the eigenvector centrality of each node in the user relationship network. The eigenvector centrality is obtained by spreading the degree centrality of the nodes using the adjacency matrix. The third determining module is used to determine the user value of each user in the target application based on the feature vector centrality. The second determining module includes: The iterative calculation submodule is used to perform iterative calculations based on the adjacency matrix and the first feature matrix, and record the calculation results corresponding to each iteration. The first determining submodule is used to stop the iterative calculation when the preset conditions are met, and to determine the calculation result corresponding to the last iterative calculation as the second feature matrix; The preset condition is that the number of iterations reaches a preset threshold, or the calculation results of two adjacent iterations are proportional. The iterative calculation submodule includes: The first calculation unit is used to execute step S1, which calculates the product of the adjacency matrix and the first feature matrix to obtain the intermediate matrix; The second calculation unit is used to execute step S2, which calculates the product of the adjacency matrix and the intermediate matrix; The third calculation unit is used to execute step S3. After obtaining the product result of the adjacency matrix and the intermediate matrix each time, the intermediate matrix in S2 is replaced with the product result and S2 is executed repeatedly.
5. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements the steps of the user value determination method according to any one of claims 1-3.
6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the user value determination method as described in any one of claims 1-3.