Target user identification method and device

Abstract

The invention provides a target user identification method and device, and the method comprises the steps: constructing a relation graph between candidate users; each node in the relation graph represents a candidate user; the edge weight in the relation graph is obtained by calculating the lifting degree; performing community division by using the improvement degree to obtain at least one sub-community; and determining the active degree of the nodes in each sub-community by using the support degree and the improvement degree corresponding to each node so as to determine a first target user in each sub-community. According to the embodiment, the recognition efficiency of the target user can be improved, and the marketing cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a target user identification method and device. Background Art

[0002] In today's business environment, it is crucial to identify target users for marketing. However, in the prior art, marketing is often carried out by randomly distributing advertisements, coupons, etc. to users, which has the problems of high marketing costs and low efficiency. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure at least provide a target user identification method, device, electronic device and storage medium, which can improve the efficiency and accuracy of target user identification.

[0004] In a first aspect, an embodiment of the present disclosure provides a target user identification method, including:

[0005] Construct a relationship graph between candidate users; each node in the relationship graph represents a candidate user; the edge weights in the relationship graph are obtained by calculating the lift;

[0006] Dividing the community by using the lifting degree to obtain at least one sub-community;

[0007] The node activity levels in each of the sub-communities are determined by using the support and promotion corresponding to each of the nodes, so as to determine the first target user in each of the sub-communities.

[0008] Optionally, after determining the first target user in each sub-community, the method further includes:

[0009] Determine whether the reach of information reached based on the first target user meets the preset requirements; if not, determine the second target user in each of the sub-communities based on the lift degree associated with the first target user, so as to reach the second target user with information.

[0010] Optionally, determining the second target user in each of the sub-communities according to the promotion degree associated with the first target user includes:

[0011] Unreached users in each of the sub-communities are determined, and second target users are determined from the unreached users in each of the sub-communities according to the support and promotion of each of the unreached users.

[0012] Optionally, using the support and promotion corresponding to each of the nodes to determine the activity level of the nodes in each of the sub-communities includes:

[0013] Generate a community classification graph according to the support and lift corresponding to each of the nodes; the size of each of the nodes in the community classification graph is determined by the support, and the size of the connection line between the nodes in the community classification graph is determined by the lift;

[0014] According to the community classification diagram, the activity level of nodes in each of the sub-communities is determined.

[0015] Optionally, after determining the first target user in each sub-community, the method further includes:

[0016] The candidate users corresponding to the nodes in each of the sub-communities whose promotion degree with the first target user is less than a preset threshold are taken as third target users, so as to reach the third target users with information based on the first target user.

[0017] Optionally, after determining the first target user in each sub-community, the method further includes:

[0018] Record the reach range of information reached by each of the first target users, and update the promotion degree of the node corresponding to the first target user in the relationship graph based on the reach range.

[0019] Optionally, before constructing the relationship graph between candidate users, the following steps are also included:

[0020] The data used to construct the relationship map are standardized and desensitized.

[0021] In a second aspect, an embodiment of the present disclosure provides a target user identification device, including:

[0022] A construction module is used to construct a relationship graph between candidate users; each node in the relationship graph represents a candidate user; and the edge weights in the relationship graph are obtained by calculating the lifting degree;

[0023] A division module, used to divide the community by using the lifting degree to obtain at least one sub-community;

[0024] The determination module is used to determine the node activity level in each of the sub-communities by using the support level and the promotion level corresponding to each of the nodes, so as to determine the first target user in each of the sub-communities.

[0025] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps in the above-mentioned first aspect, or any optional implementation of the first aspect are performed.

[0026] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect, or any optional implementation of the first aspect are executed.

[0027] Any of the above aspects or any implementation of any of the aspects, by constructing a relationship graph between candidate users; each node in the relationship graph represents a candidate user; the edge weight in the relationship graph is obtained by calculating the lift; the community is divided using the lift to obtain at least one sub-community; the node activity level in each sub-community is determined using the support and lift corresponding to each node, so as to determine the first target user in each sub-community. Thus, using the lift as the edge weight in the relationship graph and dividing the community can more accurately discover the correlation and influence between users, thereby improving the accuracy and efficiency of target user identification.

[0028] In a further embodiment of the present disclosure, after determining the first target user in each sub-community, it further includes: judging whether the reach range of information reach based on the first target user meets the preset requirements; if not, determining the second target user in each sub-community according to the promotion degree associated with the first target user, so as to reach the second target user with information. In this way, users can be reached in batches, the efficiency of target user identification is improved, and the cost of marketing based on target users is saved.

[0029] The effects of the above-mentioned target user identification device, electronic device and storage medium refer to the description of the above-mentioned target user identification method, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0031] Figure 1 A flow chart of a target user identification method provided by an embodiment of the present disclosure is shown;

[0032] Figure 2 A schematic diagram of a relationship map in a target user identification method provided by an embodiment of the present disclosure is shown;

[0033] Figure 3 A schematic diagram of a community classification diagram in a target user identification method provided by an embodiment of the present disclosure is shown;

[0034] Figure 4 A schematic diagram of a target user identification device provided by an embodiment of the present disclosure is shown;

[0035] Figure 5 An exemplary system architecture is shown in which embodiments of the present disclosure may be applied;

[0036] Figure 6 A schematic diagram of the structure of a computer system of a terminal device or a server used to implement an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0038] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0039] The raising of the above problems and the solutions are the results obtained by the inventor after practice and careful research. The discovery process of the above problems and the solutions proposed for the above problems should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0040] The technical solutions in the present disclosure will be clearly and completely described below in conjunction with the drawings in the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure claimed for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0041] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0042] To facilitate understanding of the present embodiment, a target user identification method disclosed in the present embodiment is first introduced in detail. The execution subject of the target user identification method provided in the present embodiment is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device. The terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the target user identification method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0043] See also Figure 1 FIG. 1 is a flow chart of a target user identification method provided by an embodiment of the present disclosure, wherein the method includes S101 to S103, wherein:

[0044] S101: Construct a relationship graph between candidate users; each node in the relationship graph represents a candidate user; and the edge weights in the relationship graph are obtained by calculating the lift.

[0045] A relationship graph is a graphical data representation method used to show the relationship between data entities. A relationship graph is usually composed of nodes and edges, where nodes represent entities and edges represent the relationship between entities. In a relationship graph, the meaning of an edge can be customized according to the actual application scenario. For example, in a relationship graph of social attributes, an edge can represent a family relationship; in a relationship graph of knowledge attributes, an edge can represent a hierarchical relationship, etc. Furthermore, by assigning weights to the edges in the relationship graph, the edges can not only represent the relationship between entities, but also describe the strength of the relationship.

[0046] In the disclosed embodiment, before constructing the relationship map between the candidate users, the process further includes: standardizing and desensitizing the data used to construct the relationship map. Desensitizing the data can protect the privacy of sensitive data and reduce the risk of data leakage; since the data used to construct the relationship map may have data from different sources and formats, standardizing the data can ensure the consistency and accuracy of the data.

[0047] Exemplarily, the historical data used to construct the relationship graph can be shown in the following table:

[0048]

[0049] In the specific implementation, the relationship graph can be constructed based on the above sample data and using association rules. Specifically, each user in the above personnel set can be used as a node in the relationship graph, and the relationship between users can be used as an edge in the relationship graph. Then, the concepts of support, confidence and lift in the association rules can be used to assign weights to the relationship graph. Among them, support refers to the ratio of the number of times one or several users appear to the total number of times. As shown in Table 1, user A appears in every order, so the support of user A is 1; or the combination of user A + user B appears 21 times in 39 orders, so the support of "user A + user B" is 0.54. Confidence refers to the probability of another user appearing when one user appears. As shown in Table 1, when user A appears, user B appears 21 times, so the confidence (AB) is 0.54. Lift can represent the degree to which the probability of another user appearing when one user appears, as shown in Table 1. If you want to calculate the degree to which the probability of user B appearing when user A appears, you can use the formula "Lift (AB) = Confidence (AB) / Support (B)" to calculate; when the lift calculation result is greater than 1, it means there is an improvement, otherwise it means there is a decrease.

[0050] In the disclosed embodiment, the edges in the relationship graph can be constructed according to the relationships between the users in Table 1, and the concept of lift can be used to assign weights to the edges in the relationship graph to represent the lift between the users. Figure 2 This is a relationship graph constructed based on the sample data in Table 1, such as Figure 2 As shown in the figure, the edge weight between every two nodes is the lift between them. It should be noted that the lift can be bidirectional, and the lift of user A to user B can be calculated, and the lift of user B to user A can also be calculated. In order to facilitate the display in the relationship graph and ensure the availability of data, in the specific implementation, only the lift of the node with higher support to the node with lower support can be calculated and displayed as the edge weight between every two nodes. Figure 2 As shown, it can be seen that the nodes connected to the user A node have a larger edge weight, and the outer weight decreases, thus emphasizing the importance of user A.

[0051] S102: Divide the community by using the promotion degree to obtain at least one sub-community.

[0052] In this step, based on the above relationship graph, the community can be divided to obtain at least one sub-community.

[0053] Community partitioning refers to the process of dividing the nodes in a network or relationship graph into several subgroups. In network analysis, nodes usually represent entities, while edges represent the relationships between them. The goal of community partitioning is to divide nodes into several groups so that the connections between nodes in the same group are close and the connections between groups are sparse. An important concept in community partitioning is modularity, which is an indicator of the quality of community partitioning. The higher the modularity, the better the community partitioning.

[0054] In specific implementations, the Louvain algorithm, Walktrap algorithm, Infomap algorithm and other algorithms can be used for community division, and the present invention does not make specific limitations on this. In existing community division algorithms, the difference between the number of connections of the actual edges and the number of connections of the expected edges is usually compared, and the difference values ​​of all communities are added to obtain the modularity. In the embodiment of the present disclosure, the lift degree described above can be used as the basis for calculating the modularity, and the weight of the edge within the community minus the weight of all edges connected to the community nodes is taken as the modularity. The calculation of the lift degree in this way can more comprehensively evaluate the tightness of the community structure, and take into account the influence between nodes, which has high value in the scenario of identifying target users.

[0055] In a specific implementation, the calculation formula of modularity can be as follows:

[0056]

[0057] in, represents the weight within community c, It represents the weight of the edges connected to the nodes inside community c, including the edges inside the community and the edges outside the community. m is the sum of the weights of all edges in the network.

[0058] In the specific implementation, taking the Louvain algorithm as an example, each node is first assigned to a unique subcommunity, and then the nodes are moved between these subcommunities in sequence. Specifically, suppose there is a node i, which has three neighboring nodes , and , we can try to move node i to , and The subcommunity where the node is located is selected and the corresponding modularity change value is calculated. The node i can be moved to the corresponding subcommunity with the largest change value. Repeat this method until the movement of any node in the network can no longer increase the total modularity value. The modularity change value here can be calculated using the following formula:

[0059]

[0060] in, The weights within the sub-community c represented by It represents the weight sum of the edges connected to the nodes inside the subcommunity c, including the edges inside the subcommunity and the edges outside the subcommunity. represents the weight sum of the edges connected to node i, represents the sum of the edge weights connecting node i to nodes in subcommunity c, and m is the sum of the weights of all edges in the network.

[0061] In specific implementation, each sub-community obtained above can be used as a new "big node" to reconstruct the relationship graph. In the new relationship graph, the sum of the edge weights of all the connections between any two "big nodes" can be used as the weight of the connection between the two "big nodes". This can obtain a clearer community structure and a more comprehensive relationship between communities, thereby improving the accuracy and efficiency of target user identification.

[0062] S103: Determine the activity level of the nodes in each of the sub-communities by using the support level and the promotion level corresponding to each of the nodes, so as to determine the first target user in each of the sub-communities.

[0063] In this step, the first target user in each sub-community can be determined according to the sub-communities obtained by the above community division.

[0064] In an embodiment of the present disclosure, the activity level of nodes in each of the sub-communities is determined using the support and lift corresponding to each of the nodes, including: generating a community classification graph based on the support and lift corresponding to each of the nodes; the size of each of the nodes in the community classification graph is determined by the support, and the size of the connection line between the nodes in the community classification graph is determined by the lift; and determining the activity level of nodes in each of the sub-communities based on the community classification graph.

[0065] In the specific implementation, Figure 3 is a schematic diagram of a community classification diagram. Figure 3 As shown, the size of each node can represent the activity of the node in the large community composed of various sub-communities. For example, if node A is the largest, then in the entire large community, node A is the most active. The node activity here can be obtained by the support degree; in addition, the shape of the node, color depth, etc. can also be used to indicate the activity of each node. The color of the line between nodes can indicate the degree of interaction between the two nodes. A darker line color indicates that the interaction between the two nodes is more active. For example, node A and node B interact the most in this community, so the color of the line between node A and node B is the darkest among all the lines. The node interaction here can be determined by the degree of promotion between the two nodes; in addition, the thickness, reality, etc. of the line can also be used to indicate the degree of interaction between the nodes. As Figure 3 As shown, the grayscale of the nodes in each subcommunity is consistent, while the grayscale of the nodes belonging to different subcommunities is different, which can more intuitively show the activity level of the nodes in each subcommunity and the degree of interaction between the nodes.

[0066] In the disclosed embodiment, the support of each node in each sub-community and the promotion of other nodes can be combined to determine the node corresponding to the first target user in each sub-community. In specific implementation, different reference weights can be set for support and promotion in combination with actual application scenarios. For example, in a scenario that focuses more on marketing effects, the weight of promotion can be set higher, thereby finding the first target user who is more able to use the self-propagation effect to achieve marketing goals; or in a scenario that focuses more on the target user identification effect, the weight of support can be set higher, thereby finding a more accurate first target user.

[0067] In the embodiment of the present disclosure, after determining the first target user in each sub-community, it also includes: judging whether the reach of information reach based on the first target user meets the preset requirements; if not, determining the second target user in each of the sub-community according to the lift degree associated with the first target user, so as to reach the information based on the second target user.

[0068] In specific implementation, for example, if user A is determined as the first target user in the corresponding sub-community, an advertisement can be sent to user A first. Since the promotion degree is taken into account when determining the first target user, the self-propagation effect of user A can be used to make it spontaneously spread the relevant advertisement content to other users in the corresponding sub-community. After a period of time, the reach of user A as the first target user can be obtained through various methods such as questionnaires and actual feedback effects, such as Figure 3 As shown, the sub-community where user A is located contains 12 users in addition to user A himself, so it can be set to reach all 12 users to meet the preset requirements. Of course, the setting of the preset requirements here can be made according to actual conditions, and the present invention does not make specific limitations on this. Assuming that the reach of information reach using the self-propagation effect of user A does not meet the preset requirements, a second target user can be selected from the sub-community where user A is located to conduct a new round of information reach to users in the sub-community.

[0069] In an embodiment of the present disclosure, after determining the first target user in each sub-community, it also includes: recording the reach range of information reach based on each of the first target users, and updating the promotion degree of the node corresponding to the first target user in the relationship graph based on the reach range.

[0070] In a specific implementation, after determining the reach range of information reaching the first target user, the degree of promotion of the node corresponding to the first target user in the relationship graph can be updated based on the reach range. For example, assuming that after the first target user reaches the other 12 users in the sub-community with information, 9 of them have completed the information reach through the self-propagation effect of user A, then the reach range of user A can be determined as 75%. At this time, the calculated 75% can be used as the total promotion attribute parameter of the first target user, and the promotion of user A to the above 9 reached users can be updated to 1, so that when the sub-community is subsequently reached with information, a more accurate target user can be identified based on the updated promotion.

[0071] In one possible implementation, in the sub-community to which user A belongs, the user corresponding to the node with the highest promotion degree among the nodes other than user A can be selected as the second target user, and information can be reached to the second target user, and the self-propagation effect of the second target user can be used again to achieve full reach of information within the sub-community.

[0072] In another possible implementation, the second target user in each of the sub-communities is determined based on the promotion degree associated with the first target user, including: determining the unreached users in each of the sub-communities, and determining the second target user from the unreached users in each of the sub-communities based on the support degree and promotion degree of each of the unreached users.

[0073] In a specific implementation, unreached users who have not been reached by the first target user can be identified from each sub-community. For example, in the sub-community to which user A belongs, 9 users are reached by utilizing the self-propagation effect of user A, while users E, Z, and M are not reached. At this time, the user corresponding to the node with higher support and the highest improvement for the other two nodes can be selected from users E, Z, and M as the second target user for a new round of information reach.

[0074] Through the method described above, the self-propagation effect of target users can be utilized to achieve layered information reach within each sub-community, which not only improves the accuracy of target user identification, but also improves marketing efficiency and saves marketing costs.

[0075] In a possible implementation, after determining the first target user in each sub-community, it also includes: taking the candidate users corresponding to the nodes in each of the sub-communities whose promotion degree with the first target user is less than a preset threshold as the third target users, so as to reach the third target users with information based on the first target user.

[0076] In a specific implementation, the third target user can be determined before information is reached based on the first target user. The third target user here refers to those users who may not be reached by using the self-propagation utility of the first target user. For example, assuming that the promotion threshold is 50%, and in the sub-community where user A is located, the promotion of user A to user E, user Z and user M is less than 50%, then user E, user Z and user M can be used as the third target user. When information is reached to the target user, user A and user E, user Z and user M can be reached at the same time, thereby achieving layered reach and ensuring the comprehensiveness of the reach to a great extent.

[0077] In another possible implementation, before information is reached based on the first target user, the user corresponding to the node with the highest degree of improvement for other candidate user nodes can be selected from the candidate users whose improvement is less than a preset threshold as the third target user. For example, assume that the improvement of user A for user E, user Z, and user M is 20%, 25%, and 35% respectively; the improvement of user E for user Z and user M is 10% and 15% respectively; the improvement of user Z for user E and user M is 60% and 80% respectively; the improvement of user M for user E and user Z is 45% and 50% respectively. Since user Z has the highest improvement for user E and user M, user E can be selected as the third target user and information is reached together with user A.

[0078] According to a second aspect of the embodiment of the present disclosure, Figure 4As shown, a target user identification device 400 is provided, comprising:

[0079] Construction module 401 is used to construct a relationship graph between candidate users; each node in the relationship graph represents a candidate user; the edge weights in the relationship graph are obtained by calculating the lifting degree;

[0080] A division module 402 is used to divide the community by using the lifting degree to obtain at least one sub-community;

[0081] The determination module 403 is used to determine the node activity level in each of the sub-communities by using the support level and the promotion level corresponding to each of the nodes, so as to determine the first target user in each of the sub-communities.

[0082] Optionally, the determination module 403 is further configured to:

[0083] Determine whether the reach of information reached based on the first target user meets the preset requirements; if not, determine the second target user in each of the sub-communities based on the lift degree associated with the first target user, so as to reach the second target user with information.

[0084] Optionally, the determination module 403 is further configured to:

[0085] Unreached users in each of the sub-communities are determined, and second target users are determined from the unreached users in each of the sub-communities according to the support and promotion of each of the unreached users.

[0086] Optionally, the determination module 403 is specifically configured to:

[0087] Generate a community classification graph according to the support and lift corresponding to each of the nodes; the size of each of the nodes in the community classification graph is determined by the support, and the size of the connection line between the nodes in the community classification graph is determined by the lift;

[0088] According to the community classification diagram, the activity level of nodes in each of the sub-communities is determined.

[0089] Optionally, the determination module 403 is further configured to:

[0090] The candidate users corresponding to the nodes in each of the sub-communities whose promotion degree with the first target user is less than a preset threshold are taken as third target users, so as to reach the third target users with information based on the first target user.

[0091] Optionally, the determination module 403 is further configured to:

[0092] Record the reach range of information reached by each of the first target users, and update the promotion degree of the node corresponding to the first target user in the relationship graph based on the reach range.

[0093] Optionally, the construction module 401 is further used for:

[0094] The data used to construct the relationship map are standardized and desensitized.

[0095] According to the third aspect of an embodiment of the present disclosure, an electronic device for target user identification is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present invention.

[0096] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present disclosure is implemented.

[0097] Figure 5 An exemplary system architecture 500 to which the target user identification method or target user identification apparatus implemented by the present disclosure can be applied is shown.

[0098] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0099] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0100] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0101] The server 505 may be a server that provides various services, such as a background management server (only as an example) that provides support for shopping websites browsed by users using the terminal devices 501, 502, and 503. The background management server may process the received target user identification request and feed back the processing result (only as an example) to the terminal device.

[0102] It should be noted that the target user identification method provided in the embodiment of the present invention is generally executed by the server 505, and accordingly, the target user identification device is generally set in the server 505. The target user identification method provided in the embodiment of the present invention can also be executed by the terminal devices 501, 502, and 503, and accordingly, the target user identification device can be set in the terminal devices 501, 502, and 503.

[0103] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0104] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0105] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0106] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0107] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0108] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0109] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, a processor includes a construction module, a division module, and a determination module. The names of these modules do not constitute a limitation on the modules themselves in some cases. For example, the construction module may also be described as a "module for constructing a relationship graph between candidate users."

[0111] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements the following method:

[0112] Construct a relationship graph between candidate users; each node in the relationship graph represents a candidate user; the edge weights in the relationship graph are obtained by calculating the lift;

[0113] Dividing the community by using the lifting degree to obtain at least one sub-community;

[0114] The node activity levels in each of the sub-communities are determined by using the support and promotion corresponding to each of the nodes, so as to determine the first target user in each of the sub-communities.

[0115] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be based on the protection scope of the claims.

Claims

1. A target user identification method, characterized in that: include: Build a relationship graph between candidate users; Each node in the relationship graph represents a candidate user; The edge weights in the relationship graph are obtained by calculating the lifting degree; Dividing the community by using the lifting degree to obtain at least one sub-community; The node activity levels in each of the sub-communities are determined by using the support and promotion corresponding to each of the nodes, so as to determine the first target user in each of the sub-communities.

2. The method according to claim 1, characterized in that After determining the first target user in each sub-community, it also includes: Determine whether the reach of information reached based on the first target user meets the preset requirements; if not, determine the second target user in each of the sub-communities based on the lift degree associated with the first target user, so as to reach the second target user with information.

3. The method according to claim 2, characterized in that Determining a second target user in each of the sub-communities according to the lift degree associated with the first target user includes: Unreached users in each of the sub-communities are determined, and second target users are determined from the unreached users in each of the sub-communities according to the support and promotion of each of the unreached users.

4. The method according to claim 1, characterized in that Using the support and promotion corresponding to each of the nodes, determining the activity of the nodes in each of the sub-communities, including: Generate a community classification graph according to the support and lift corresponding to each of the nodes; the size of each of the nodes in the community classification graph is determined by the support, and the size of the connection line between the nodes in the community classification graph is determined by the lift; According to the community classification diagram, the activity level of nodes in each of the sub-communities is determined.

5. The method according to claim 1, characterized in that After determining the first target user in each sub-community, it also includes: The candidate users corresponding to the nodes in each of the sub-communities whose promotion degree with the first target user is less than a preset threshold are taken as third target users, so as to reach the third target users with information based on the first target user.

6. The method according to claim 1, characterized in that After determining the first target user in each sub-community, it also includes: Record the reach range of information reached by each of the first target users, and update the promotion degree of the node corresponding to the first target user in the relationship graph based on the reach range.

7. The method according to claim 1, characterized in that Before building the relationship graph between candidate users, it also includes: The data used to construct the relationship map are standardized and desensitized.

8. A target user identification device, characterized in that: include: A construction module is used to construct a relationship graph between candidate users; Each node in the relationship graph represents a candidate user; The edge weights in the relationship graph are obtained by calculating the lifting degree; A division module, used to divide the community by using the lifting degree to obtain at least one sub-community; The determination module is used to determine the node activity level in each of the sub-communities by using the support level and the promotion level corresponding to each of the nodes, so as to determine the first target user in each of the sub-communities.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

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

Images