Target user determination method and apparatus, terminal device, and storage medium

Abstract

The application discloses a target user determination method and device, terminal equipment and a storage medium. The target user determination method comprises the following steps: obtaining a plurality of candidate user information and historical activity information, wherein the candidate user information comprises consumption characteristics; determining the similarity between each candidate user according to the plurality of candidate user information and the historical activity information, wherein the similarity is used to represent the similarity degree of the consumption characteristics between the candidate users; determining a plurality of user sets according to the similarity between each candidate user; obtaining a sample user and determining the user set where the sample user is located to obtain a plurality of target users. The above technical scheme can accurately determine the target user.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method and apparatus for determining a target user, a terminal device, and a storage medium. Background Technology

[0002] To improve business efficiency in different application scenarios, enterprises typically screen the users targeted by each application scenario before launching business operations, and then proceed with business based on the screened target users. Existing technologies often identify target users based on a single dimension, such as only based on a user's spending amount, which can lead to the omission of truly needed target users and an inaccurate identification of the target audience.

[0003] Therefore, accurately identifying target users is a problem that urgently needs to be solved. Summary of the Invention

[0004] The technical problem solved by this invention is how to accurately identify target users.

[0005] To address the aforementioned technical problems, this invention provides a method for determining target users. The method includes: acquiring multiple candidate user information and historical activity information, wherein the historical activity information includes merchant information and activity time, and the candidate user information includes consumption characteristics; determining the similarity between each candidate user based on the multiple candidate user information and the historical activity information, wherein the similarity is used to characterize the degree of similarity in consumption characteristics between candidate users; determining multiple user sets based on the similarity between each candidate user, each user set including multiple candidate users, wherein the similarity between any two candidate users within the same user set reaches a first similarity threshold; acquiring sample users and determining the user set to which the sample users belong, thereby obtaining multiple target users, wherein the sample users possess target consumption characteristics.

[0006] Optionally, the candidate user information includes consumption time, consumption amount, and consumption preferences. Determining the similarity between candidate users based on the multiple candidate user information and the historical activity information includes: constructing multiple consumption feature databases based on the activity time and the merchant information, each representing a different consumption feature; determining whether the candidate user's consumption time, consumption amount, and consumption preferences match the consumption features in the consumption feature databases; if a candidate user's information matches the consumption feature database, adding the candidate user to the consumption feature database; and determining the proportion of times each pair of candidate users appears in the same consumption feature database relative to the total number of users in the consumption feature database, using this proportion as the similarity between candidate users.

[0007] Optionally, determining the user set to which the sample user belongs includes: determining an initial user set to which the sample user belongs; determining associated users, wherein the associated users are outside the initial user set and have a similarity to at least one candidate user in the initial user set that reaches a first similarity threshold; calculating the direction of change of the set fitness before and after the associated users are added to the initial user set, wherein the set fitness of the user set is used to characterize the degree of association between the users in the user set; if the direction of change of the set fitness indicates that the degree of association between the users in the user set remains unchanged or increases, then the associated users are added to the initial user set to obtain a final target user set, wherein the final target user set includes multiple target users.

[0008] Optionally, calculating the change direction of the set fitness before and after the associated user is added to the initial user set includes: calculating the first fitness of the associated user before being added to the initial user set, and calculating the second fitness of the associated user after being added to the initial user set, wherein when the difference between the second fitness and the first fitness reaches a preset fitness, it indicates that the degree of association between users in the user set remains unchanged or increases.

[0009] Optionally, the target user determination method further includes: if the difference between the second fitness and the first fitness does not reach a preset fitness, stopping the addition of the associated user to the initial user set, and / or, if the number of target users in the target user set reaches a preset number, stopping the addition of the associated user to the initial user set.

[0010] Optionally, the set fitness of the user set can be calculated using the following formula: Where F represents the set fitness of the user set, kin represents the sum of similarities among the users in the user set, kout represents the sum of similarities between the users in the user set and the associated users, and α represents the preset multiplier.

[0011] Optionally, the target user determination method further includes: generating a user report for the user set, the user report including the total number of target users in the user set where the sample user is located, the identifier of each target user, and consumption characteristics.

[0012] This invention also discloses a target user determination device, comprising: an acquisition module for acquiring multiple candidate user information and historical activity information, wherein the historical activity information includes merchant information and activity time, and the candidate user information includes consumption characteristics; a similarity calculation module for determining the similarity between each candidate user based on the multiple candidate user information and the historical activity information, wherein the similarity is used to characterize the degree of similarity of consumption characteristics between candidate users; a first determination module for determining multiple user sets based on the similarity between each candidate user, wherein each user set includes multiple candidate users, and the similarity between any two candidate users within the same user set reaches a first similarity threshold; and a second determination module for acquiring sample users and determining the user set to which the sample users belong, thereby obtaining multiple target users, wherein the sample users have target consumption characteristics.

[0013] The present invention also discloses a terminal device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the computer program, when run by the processor, performs the steps of any of the target user determination methods described above.

[0014] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium is a non-volatile storage medium or a non-transient storage medium, and the computer program, when executed by a processor, performs the steps of any of the target user determination methods described above.

[0015] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0016] This invention proposes a method for determining target users. It obtains merchant information, activity time, and consumption characteristics of candidate users by acquiring information from multiple candidate users and historical activity information. The similarity between each candidate user is determined based on this information and historical activity information. Multiple user sets are then determined based on the similarity between candidate users. Sample users are then acquired, and the user sets to which these sample users belong are determined, thus obtaining multiple target users. This invention utilizes candidate user information to determine the consumption characteristics of each candidate user, and then determines the similarity of consumption characteristics between candidate users based on merchant information and activity time from historical activity information. Multiple user sets are determined, where the similarity between any two candidate users in a user set reaches a first similarity threshold. Each candidate user in each user set has similar consumption characteristics, allowing for the rapid identification of multiple candidate users with similar consumption characteristics based on the user sets. After acquiring sample users with target consumption characteristics, the user sets to which these sample users belong can be determined, allowing multiple candidate users with similar target consumption characteristics to be selected as target users. By only determining suitable sample users, target users with similar target consumption characteristics can be identified from multiple candidate users, significantly improving the efficiency and accuracy of target user search.

[0017] Furthermore, by calculating the set fitness of the initial user set before and after adding associated users, the degree of association between users in the user set can be determined. Adding associated users whose set fitness meets the condition to the initial user set can expand the number of target users, thereby meeting the needs of different application scenarios for different numbers of target users. Attached Figure Description

[0018] Figure 1 This is an overall flowchart of a target user determination method provided by an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of the structure of a target user determination device provided in an embodiment of the present invention. Detailed Implementation

[0020] As described in the background section, to improve business efficiency in different application scenarios, enterprises typically screen the users targeted by each application scenario before launching their business operations. Existing technologies often identify target users based on a single dimension, such as solely relying on a user's spending amount. This leads to the omission of truly needed target users and an inability to accurately identify them. Therefore, accurately identifying target users is a pressing issue that needs to be addressed.

[0021] In this invention, merchant information, activity time, and consumption characteristics of candidate users are obtained by acquiring multiple candidate user information and historical activity information. The similarity between each candidate user is determined based on the candidate user information and historical activity information. Multiple user sets are then determined based on the similarity between candidate users. Sample users are then acquired, and the user set to which the sample users belong is determined, thus obtaining multiple target users. The technical solution of this invention utilizes candidate user information to determine the consumption characteristics of each candidate user, and then determines the degree of similarity of consumption characteristics between candidate users based on merchant information and activity time in historical activity information. Multiple user sets are determined, and the similarity between any two candidate users in a user set reaches a first similarity threshold. Each candidate user in each user set has similar consumption characteristics, allowing for the rapid identification of multiple candidate users with similar consumption characteristics based on the user sets. After acquiring sample users with target consumption characteristics, the user set to which the sample users belong can be determined, allowing multiple candidate users with similar target consumption characteristics to be used as target users. By only determining suitable sample users, target users with similar target consumption characteristics can be identified from multiple candidate users, greatly improving the efficiency and accuracy of target user search.

[0022] Furthermore, by calculating the set fitness of the initial user set before and after adding associated users, the degree of association between users in the user set can be determined. Adding associated users whose set fitness meets the condition to the initial user set can expand the number of target users, thereby meeting the needs of different application scenarios for different numbers of target users.

[0023] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Figure 1 This is an overall flowchart of a target user determination method provided by an embodiment of the present invention.

[0025] In specific implementation, the target user determination method described in steps 101 to 104 below can be used in a terminal device. These steps can be executed by the terminal device itself, by a chip with data processing capabilities within the terminal device, or by a chip module within the terminal device that includes a chip with data processing capabilities. In one specific embodiment, the server can execute each step of the target user determination method.

[0026] Specifically, such as Figure 1As shown, the method for determining the target user may include the following steps:

[0027] In step 101, multiple candidate user information and historical activity information are obtained;

[0028] In step 102, the similarity between each candidate user is determined based on the multiple candidate user information and the historical activity information;

[0029] In step 103, multiple user sets are determined based on the similarity between the candidate users;

[0030] In step 104, sample users are obtained, and the user set to which the sample users belong is determined, so as to obtain multiple target users.

[0031] In a specific implementation of step 101, the server obtains information on multiple candidate users, including their consumption characteristics, and acquires historical activity information, including merchant information and activity time. Specifically, the consumption characteristics of a candidate user can refer to the pattern of their consumption; merchant information can include the merchant's industry type and average spending; and activity time can include the activity period of the last time the activity took place. For example, consumption characteristics can include the time, amount, and preferences of the candidate user's consumption.

[0032] It should be noted that the candidate user information generated during the user's consumption is used with the user's authorization.

[0033] In a specific implementation of step 102, the server constructs multiple consumption feature databases based on historical activity information and merchant information, with each database representing different consumption features. Candidate users are added to these databases based on their information, and the similarity between candidates is calculated based on the number of times each pair of candidates resides in the same database. Specifically, the similarity is used to characterize the degree of similarity in consumption features between candidate users.

[0034] In a non-limiting embodiment, candidate user information includes consumption time, consumption amount, and consumption preferences. It can be determined whether the candidate user information, including consumption time, consumption amount, and consumption preferences, matches the consumption features corresponding to the consumption feature database. If the candidate user information matches the consumption feature database, the candidate user is added to the consumption feature database. After all candidate users are classified, the proportion of each pair of candidate users belonging to the same consumption feature database is calculated to represent the total number of users in the consumption feature database, which is used as the similarity between candidate users.

[0035] In one specific embodiment, the historical activity information includes the activity date of the last activity, October 1st, and the merchant information of Merchant 1 and Merchant 2 who participated in the last activity. The merchant information for each merchant is shown in Table 1:

[0036] Merchant 1 Merchant 2 Industry type apparel fresh Average consumption 1500 yuan 100 yuan

[0037] Table 1

[0038] Based on historical activity information, multiple consumer characteristic databases can be identified. Specifically, the obtained consumer characteristic databases are shown in Table 2:

[0039]

[0040] Table 2

[0041] We have candidate user information for candidate user 1, candidate user 2, and candidate user 3. Candidate user 1 made a purchase of 1000 yuan at merchant 1 on October 1st, so candidate user 1 can be added to consumption feature database 1, consumption feature database 2, and consumption feature database 5. Candidate user 2 made a purchase of 200 yuan at merchant 2 on October 2nd, so candidate user 2 can be added to consumption feature database 3 and consumption feature database 4. Candidate user 3 made a purchase of 100 yuan at merchant 2 on October 1st, so candidate user 3 can be added to consumption feature database 1, consumption feature database 3, and consumption feature database 4. The similarity between candidate users can be calculated by calculating the proportion of times each candidate user appears in the same consumption feature database relative to the total number of users in the database. Specifically, the similarity between candidate user 1 and candidate user 2 is 0; the similarity between candidate user 1 and candidate user 3 is 1 / 5; and the similarity between candidate user 2 and candidate user 3 is 2 / 5.

[0042] It should be noted that the content in the candidate user information and historical activity information can be selected according to the actual situation in order to build a consumer feature database representing different consumption characteristics according to the needs. This application does not impose any restrictions on this.

[0043] In a non-limiting embodiment, multiple candidate user information and historical activity information can be input into a similarity calculation model to obtain the similarity between any two candidate users. Specifically, the similarity calculation model can be a neural network model, trained using multiple candidate user information, historical activity information, and a preset similarity between candidate users. The similarity calculation model can determine the consumption features corresponding to different consumption feature databases, and add candidate users to different consumption feature databases based on the candidate user information, thereby obtaining the similarity between two candidate users.

[0044] In a specific implementation of step 103, the server can iterate through the similarity between every two candidate users, and establish an association between the two candidate users when the similarity between them reaches a first similarity threshold, thus obtaining an association network. The association network includes all candidate users and the associations between them.

[0045] Furthermore, multiple user sets are determined based on the association network, each user set including multiple candidate users. The similarity between any two candidate users within the same user set reaches a first similarity threshold. By segmenting the candidate users in the association network, multiple candidate users with similar consumption characteristics can be accurately identified. Each candidate user belongs to only one user set. Specifically, each user set includes identifiers for multiple candidate users, such as identity information or card number information that uniquely identifies the user.

[0046] In a specific implementation of step 104, sample users can be acquired, and these sample users possess target consumption characteristics. Specifically, the consumption characteristics of the sample users meet the needs of the activity. For example, sample user A's consumption amount reaches 2000 yuan, and the sample user's consumption time falls within the activity period of previous activities. Therefore, the sample user has a high probability of promoting the business.

[0047] In a specific implementation, the identifier of the sample user is obtained, and the user set to which the sample user belongs is determined. All candidate users within this user set are then selected as target users. By using candidate users who are in the same user set as the sample user as target users, the efficiency of identifying target users can be greatly improved. Furthermore, target users and sample users have similar consumption characteristics, which can effectively improve business efficiency.

[0048] In a non-limiting embodiment, after obtaining sample users, the set of users containing the sample users is used as the initial user set. Associated users of each candidate user in the initial user set are determined. These associated users are located outside the initial user set and have a similarity threshold of at least one candidate user within the initial user set. For example, the initial user set includes candidate user A and candidate user B. Candidate user C, outside the initial user set, has a similarity threshold of the first similarity threshold with candidate user A, while the similarity between candidate user C and candidate user B does not reach the first similarity threshold. Since candidate user C has a similarity threshold with candidate user A, candidate user C can be considered an associated user of candidate user A.

[0049] Furthermore, the direction of change in the set fitness of associated users before and after adding them to the initial user set is calculated. The set fitness of a user set characterizes the degree of association between users in that set; the higher the set fitness, the greater the degree of association between users in the set. If the direction of change in set fitness indicates that the degree of association between users in the user set remains unchanged or increases, then the associated users can be added to the initial user set to expand it. After traversing all associated users in the initial user set, associated users that conform to the direction of change in set fitness are added to the initial user set to obtain the final target user set, which includes multiple target users.

[0050] In a specific implementation, the first fitness of the associated user before being added to the initial user set is calculated, and the second fitness of the associated user after being added to the initial user set is calculated. When the difference between the second fitness and the first fitness reaches a preset fitness, it indicates that the degree of association between the users in the user set remains unchanged or increases. For example, if the first fitness of associated user A before being added to the initial user set is F1, and the second fitness of associated user A after being added to the initial user set is F2, if F2-F1 reaches the preset fitness, it indicates that the degree of association between the users after associated user A is added to the initial user set remains unchanged or increases, and associated user A can be added to the initial user set. After calculating the first fitness and second fitness of each associated user before and after being added to the initial user set, the addition of associated users whose difference between the second fitness and the first fitness does not reach the preset fitness can be stopped, and / or, if the number of target users in the target user set reaches a preset number, the addition of associated users to the initial user set can be stopped, and the final target user set is obtained.

[0051] Specifically, the set fitness of a user set can be calculated using the following formula:

[0052]

[0053] Where F represents the set fitness of the user set, k in k represents the sum of similarities among all users in the user set. out This represents the sum of similarities between each user in the user set and its associated users, with α representing a preset multiplier. This embodiment determines whether to add associated users to the initial user set by calculating the direction of change in the set fitness before and after the associated users are added. If the degree of association between users in the user set remains unchanged or increases, it means that adding associated users will not adversely affect the degree of association between users in the user set, and the associated users can be added to the initial user set.

[0054] In a non-limiting embodiment, a user report can be generated after determining the user set to which the sample users belong. The user report includes the total number of target users in the user set, the identifier of each target user, and consumption characteristics. Business can be precisely advanced based on the user report.

[0055] Furthermore, a user report for the final target user set can be generated after obtaining the final target user set. This user report includes the total number of target users in the final target user set, the identifier of each target user, and their consumption characteristics.

[0056] In this embodiment, by calculating the similarity between candidate users, multiple user sets can be identified, with each set containing multiple candidate users exhibiting similar consumption characteristics. Then, by determining sample users, multiple candidate users with similar consumption characteristics to the sample users can be selected as target users. Expanding the initial user set increases the number of target users, and the set fitness ensures the correlation between associated users and the candidate users in the initial user set, thereby guaranteeing the efficiency of business promotion targeting associated users.

[0057] like Figure 2 As shown, this embodiment of the invention also discloses a target user determination device. The target user determination device 20 includes:

[0058] The acquisition module 201 is used to acquire multiple candidate user information and historical activity information, wherein the historical activity information includes merchant information and activity time, and the candidate user information includes consumption characteristics.

[0059] The similarity calculation module 202 is used to determine the similarity between each candidate user based on the multiple candidate user information and the historical activity information, wherein the similarity is used to characterize the degree of similarity of consumption characteristics between candidate users;

[0060] The first determining module 203 is used to determine multiple user sets based on the similarity between the candidate users, each user set including multiple candidate users, and the similarity between any two candidate users in the same user set reaches a first similarity threshold.

[0061] The second determining module 204 is used to acquire sample users and determine the user set to which the sample users belong, so as to obtain multiple target users, wherein the sample users have target consumption characteristics.

[0062] In specific implementation, the aforementioned target user determination device may correspond to a chip with data processing function in a terminal device, such as a SOC (System-On-a-Chip), a baseband chip, etc.; or correspond to a chip module in a terminal device that includes a chip with data processing function; or correspond to a chip module with a chip having data processing function; or correspond to a terminal device.

[0063] For more information on the working principle and operation mode of the target user determination device 20, please refer to [link / reference needed]. Figure 1 The relevant descriptions in the text will not be repeated here.

[0064] Regarding the modules / units included in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or a combination of both. For example, for various devices and products applied to or integrated into a chip, all of their modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits; for various devices and products applied to or integrated into a chip module, all of their modules / units can be implemented using hardware methods such as circuits, and different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The components can be implemented using software programs that run on the processor integrated within the chip module. The remaining (if any) modules / units can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into the terminal, each of its components / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or in different components within the terminal. Alternatively, at least some modules / units can be implemented using software programs that run on the processor integrated within the terminal, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits.

[0065] This invention also discloses a storage medium, which is a computer-readable storage medium, specifically a non-volatile or non-transient storage medium. The storage medium stores a computer program thereon, which can be executed during runtime. Figure 1 The steps of the method shown are as follows.

[0066] This invention also discloses a terminal device, which may include a memory and a processor. The memory stores a computer program that can run on the processor, and the processor can execute the computer program. Figure 1 The steps of the method shown are as follows.

[0067] In the embodiments of this application, "multiple" refers to two or more.

[0068] The descriptions of "first," "second," etc., appearing in the embodiments of this application are for illustrative purposes and to distinguish the objects being described. They have no order and do not indicate any special limitation on the number of devices in the embodiments of this application, nor do they constitute any limitation on the embodiments of this application.

[0069] It should be understood that in the embodiments of this application, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0070] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0071] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive. The storage medium can also include non-volatile memory or non-transitory memory, etc.

[0072] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and other division methods may exist in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0074] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0076] The integrated unit implemented as a software functional unit described above can be stored in a computer-readable storage medium. This software functional unit, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute some steps of the methods described in the various embodiments of the present invention.

[0077] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can make various modifications and alterations without departing from the spirit and scope of the invention; therefore, the scope of protection of the present invention should be determined by the scope defined in the claims.

Claims

1. A method for determining target users, characterized in that, include: Acquire multiple candidate user information and historical activity information, wherein the historical activity information includes merchant information and activity time, and the candidate user information includes consumption characteristics; The similarity between each candidate user is determined based on the multiple candidate user information and the historical activity information, and the similarity is used to characterize the degree of similarity in consumption characteristics between candidate users; Multiple user sets are determined based on the similarity between the candidate users. Each user set includes multiple candidate users, and the similarity between any two candidate users in the same user set reaches a first similarity threshold. Obtain sample users and determine the user set to which the sample users belong in order to obtain multiple target users, wherein the sample users have target consumption characteristics; Wherein, determining the user set to which the sample user belongs includes: Determine the initial user set to which the sample users belong; Identify associated users, wherein the associated users are outside the initial user set and have a similarity to at least one candidate user within the initial user set that reaches a first similarity threshold; Calculate the direction of change in set fitness before and after the associated user is added to the initial user set. The set fitness of the user set is used to characterize the degree of association between the users in the user set. If the change in the fitness of the set indicates that the degree of association between users in the user set remains unchanged or increases, then the associated users are added to the initial user set to obtain the final target user set, which includes multiple target users. The fitness of the user set is calculated using the following formula: in, This represents the set fitness of the user set. This represents the sum of similarities among all users in the user set. This represents the sum of similarities between each user in the user set and the associated user. This indicates the preset multiplier.

2. The target user determination method according to claim 1, characterized in that, The candidate user information includes consumption time, consumption amount, and consumption preferences. Determining the similarity between each candidate user based on the multiple candidate user information and the historical activity information includes: Multiple consumption feature databases are constructed based on the activity time and the merchant information, with each consumption feature database representing different consumption features; Determine whether the candidate user's consumption time, consumption amount, and consumption preferences match the consumption characteristics in the consumption characteristic database; If a candidate user's information matches the consumption feature database, then the candidate user is added to the consumption feature database. The similarity between candidate users is determined by the proportion of times each pair of candidate users appears in the same consumption feature database relative to the total number of users in the database.

3. The target user determination method according to claim 1, characterized in that, The calculation of the change in set fitness before and after the associated user is added to the initial user set includes: Calculate the first fitness of the associated user before it is added to the initial user set, and calculate the second fitness of the associated user after it is added to the initial user set. When the difference between the second fitness and the first fitness reaches a preset fitness, it indicates that the degree of association between users in the user set remains unchanged or increases.

4. The target user determination method according to claim 3, characterized in that, Also includes: If the difference between the second fitness and the first fitness does not reach the preset fitness, stop adding the associated user to the initial user set, and / or, if the number of target users in the target user set reaches the preset number, stop adding the associated user to the initial user set.

5. The target user determination method according to claim 1, characterized in that, Also includes: Generate a user report for the user set, the user report including the total number of target users in the user set where the sample users are located, the identifier of each target user, and consumption characteristics.

6. A target user determination device, characterized in that, include: The acquisition module is used to acquire multiple candidate user information and historical activity information. The historical activity information includes merchant information and activity time, and the candidate user information includes consumption characteristics. A similarity calculation module is used to determine the similarity between each candidate user based on the multiple candidate user information and the historical activity information, wherein the similarity is used to characterize the degree of similarity in consumption characteristics between candidate users; The first determining module is used to determine multiple user sets based on the similarity between the candidate users, each user set including multiple candidate users, and the similarity between any two candidate users in the same user set reaches a first similarity threshold. The second determining module is used to acquire sample users and determine the user set to which the sample users belong, so as to obtain multiple target users, wherein the sample users have target consumption characteristics; The second determining module is further configured to: determine the initial user set to which the sample user belongs; Identify associated users, wherein the associated users are outside the initial user set and have a similarity to at least one candidate user within the initial user set that reaches a first similarity threshold; Calculate the direction of change in set fitness before and after the associated user is added to the initial user set. The set fitness of the user set is used to characterize the degree of association between the users in the user set. If the change in the fitness of the set indicates that the degree of association between users in the user set remains unchanged or increases, then the associated users are added to the initial user set to obtain the final target user set, which includes multiple target users. The second determining module is further configured to calculate the set fitness of the user set using the following formula: in, This represents the set fitness of the user set. This represents the sum of similarities among all users in the user set. This represents the sum of similarities between each user in the user set and the associated user. This indicates the preset multiplier.

7. A terminal device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor runs the computer program, it performs the steps of the target user determination method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer-readable storage medium is a non-volatile or non-transient storage medium, and the computer program, when executed by a processor, performs the steps of the target user determination method according to any one of claims 1 to 5.

Images