CN117236999A

CN117236999A - Activity determination method and device, electronic equipment and storage medium

Info

Publication number: CN117236999A
Application number: CN202311212216.XA
Authority: CN
Inventors: 何锐明; 林志鹏; 赵金阳
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2023-09-19
Filing date: 2023-09-19
Publication date: 2023-12-15

Abstract

The application provides an activity determination method, an activity determination device, electronic equipment and a storage medium, relates to the technical field of data processing, and is used for improving accuracy of activity division. The method comprises the following steps: acquiring user behavior data and user attribute data of a target application in a first preset time period; clustering according to user behavior data and user attribute data of a target application to obtain an active frequency threshold N; n is an integer greater than or equal to 1; and dividing the liveness of the users of the target application according to the liveness frequency threshold value N and the user behavior data of the target application.

Description

Activity determination method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and apparatus for determining liveness, an electronic device, and a storage medium.

Background

Along with the development of computer and internet technology, various internet products are correspondingly produced, user portraits are the crucial problems faced by the products in the process of designing, developing and producing the internet products, and in the whole process, all the processes of generating the internet products are oriented to the same group. In the operation process of the Internet product, user portraits provide subdivision viewing angles for operation strategies, and targeted operation activities are deduced for different groups. The user liveness is an important feature in the user portrait, has the advantages of wide coverage, strong timeliness, high authenticity and the like, is an important user feature, and is an important index of internet products.

In the related art, when the user activity is measured, the user activity is generally judged through the access times, access time length, collection index and the like of the internet products, and the access times, the access time length, the collection index and the like are all based on the statistics of the product population, and the activity condition of each user is not concerned, so that the accuracy of the measured user activity is low, the measured user activity cannot be used as the guidance of manual intervention in the individual user level, and the practicability is poor.

Disclosure of Invention

The application provides an activity determination method, an activity determination device, electronic equipment and a storage medium, which are used for improving the accuracy of activity division.

In a first aspect, the present application provides a method for determining liveness, the method comprising: acquiring user behavior data and user attribute data of a target application in a first preset time period; clustering according to user behavior data and user attribute data of a target application to obtain an active frequency threshold N; n is an integer greater than or equal to 1; and dividing the liveness of the users of the target application according to the liveness frequency threshold value N and the user behavior data of the target application.

The technical scheme provided by the application has at least the following beneficial effects: firstly, clustering according to behavior data and attribute data of a user of a target application in a preset time period to obtain an active frequency threshold N; and then, dividing the liveness of the user according to the liveness frequency threshold value N and the user behavior data of the target application. It can be appreciated that compared with the method for dividing the liveness by adopting the preset fixed value in the related art, the method can cluster according to the user characteristics (including the behavior characteristics and the user attribute characteristics) of the target application to obtain the liveness frequency threshold, so that the determined liveness frequency threshold N is more fit with the use scene, and the accuracy of liveness division can be improved.

As a possible implementation manner, the performing activity classification on the user of the target application according to the activity frequency threshold N and the user behavior data of the target application includes: dividing a preset time period into a plurality of time units; according to user behavior data of the target application, determining the active conditions of a user of the target application in a plurality of time units; wherein the active condition includes active or inactive; and dividing the liveness of the user of the target application according to the liveness of the user of the target application in a plurality of time units and the liveness frequency threshold N.

As another possible implementation manner, the performing activity classification on the user of the target application according to the activity situation of the user of the target application in a plurality of time units and the activity frequency threshold N includes: dividing users meeting a first condition among users of the target application into users with first liveness; the first condition is that the user is in an active state in a first time unit, and N continuous time units including the first time unit are all in an active state; the first time unit is the time unit with the latest ending time in the plurality of time units; dividing users meeting a second condition among users of the target application into users with second liveness; the second condition is that the user is in an active state in the first time unit, but in the continuous N time units comprising the first time unit, the number of the time units in the active state is smaller than N; dividing users meeting a third condition among users of the target application into users with third liveness; the third condition is that the user is not in an active state in the first time unit, but the number of the active time units is less than N in the continuous N time units before the first time unit.

As another possible implementation manner, the dividing the activity of the user of the target application according to the activity situation of the user of the target application in a plurality of time units and the activity frequency threshold N, further includes: and analyzing potential users of the target application according to the user data of the first liveness user and the second liveness user.

As another possible implementation manner, the performing activity classification on the user of the target application according to the activity situation of the user of the target application in a plurality of time units and the activity frequency threshold N includes: dividing users meeting a fourth condition among users of the target application into reflow users; the fourth condition is that the user is in an active state in the first time unit, and the first time unit is separated from the time unit in the last active state by M time units; the first time unit is the time unit with the latest ending time in the plurality of time units; m is an integer greater than or equal to N; dividing users meeting a fifth condition among users of the target application into newly added users; the fifth condition is that the user is in an active state in the first time unit, but is not in an active state in a time unit before the first time unit; dividing users meeting a sixth condition among users of the target application into lost users; wherein the sixth condition is that none of the user's consecutive N time units including the first time unit are in an active state.

As another possible implementation manner, the clustering according to the user behavior data and the user attribute data of the target application to obtain the active frequency threshold N includes: according to user behavior data of the target application, determining the liveness of a user of the target application in k time units; wherein k is an integer greater than or equal to 1; forming a data object set by the liveness of a user of the target application in k time units and attribute data of the user in a first time unit; determining P cluster centers of the data object set; p is an integer greater than or equal to 1; respectively calculating the distance between each data object in the data object set and the P clustering centers; obtaining at least one cluster according to the distance between each data object in the data object set and the P cluster centers; wherein, a cluster corresponds to a value of the active frequency threshold N.

As another possible implementation manner, the activity determining method further includes: acquiring the liveness division condition of a user of the target application in a second preset time period; wherein the second preset time period is earlier than the first preset time period; and determining the fluctuation condition of the liveness of the user of the target application based on the liveness division condition of the user of the target application in the second preset time period and the liveness division condition of the user of the target application in the first preset time period.

In a second aspect, the present application provides an liveness determination apparatus, the apparatus comprising: the acquisition module is used for acquiring user behavior data and user attribute data of the target application in a first preset time period; the clustering module is used for clustering according to the user behavior data and the user attribute data of the target application to obtain an active frequency threshold N; n is an integer greater than or equal to 1; and the determining module is used for dividing the liveness of the users of the target application according to the liveness threshold value N and the user behavior data of the target application.

As a possible implementation manner, the determining module is specifically configured to divide the preset time period into a plurality of time units; according to user behavior data of the target application, determining the active conditions of a user of the target application in a plurality of time units; wherein the active condition includes active or inactive; and dividing the liveness of the user of the target application according to the liveness of the user of the target application in a plurality of time units and the liveness frequency threshold N.

As another possible implementation manner, the determining module is specifically configured to divide, among users of the target application, users that meet the first condition into users of a first activity level; the first condition is that the user is in an active state in a first time unit, and N continuous time units including the first time unit are all in an active state; the first time unit is the time unit with the latest ending time in the plurality of time units; dividing users meeting a second condition among users of the target application into users with second liveness; the second condition is that the user is in an active state in the first time unit, but the number of the time units in the active state is less than N in the continuous N time units including the first time unit; dividing users meeting a third condition among users of the target application into users with third liveness; the third condition is that the user is not in an active state in the first time unit, but the number of time units in the active state is less than N in the continuous N time units before the first time unit.

As another possible implementation manner, the determining module is further configured to analyze the potential users of the target application according to the user data of the first liveness user and the second liveness user.

As another possible implementation manner, the determining module is specifically configured to divide, among users of the target application, users that satisfy the fourth condition into reflow users; the fourth condition is that the user is in an active state in the first time unit, and the first time unit is separated from the time unit in the last active state by M time units; the first time unit is the time unit with the latest ending time in the plurality of time units; m is an integer greater than or equal to N; dividing users meeting a fifth condition among users of the target application into newly added users; the fifth condition is that the user is in an active state in the first time unit, but is not in an active state in a time unit before the first time unit; dividing users meeting a sixth condition among users of the target application into lost users; wherein the sixth condition is that none of the user's consecutive N time units including the first time unit are in an active state.

As another possible implementation manner, the clustering module is specifically configured to determine, according to user behavior data of the target application, an active situation of a user of the target application in k time units; wherein k is an integer greater than or equal to 1; forming a data object set by the active condition of a user of the target application in k time units and attribute data of the user in a first time unit; determining P cluster centers of the data object set; p is an integer greater than or equal to 1; respectively calculating the similarity between each data object in the data object set and the P clustering centers; obtaining at least one cluster according to the similarity between each data object in the data object set and the P cluster centers; wherein, a cluster corresponds to a value of the active frequency threshold N.

As another possible implementation manner, the obtaining module is further configured to obtain a user liveness division situation of the target application in a second preset time period; wherein the second preset time period is earlier than the first preset time period; the determining module is further configured to determine a fluctuation condition of the activity of the user of the target application based on the activity dividing condition of the user of the target application in the second preset time period and the activity dividing condition of the user of the target application in the first preset time period.

In a third aspect, the present application provides an electronic device comprising a processor and a memory, the processor being coupled to the memory; the memory is used to store computer instructions that are loaded and executed by the processor to cause the computer arrangement to implement the liveness determination method provided in the first aspect and any one of its possible implementations.

In a fourth aspect, the present application provides a computer readable storage medium comprising computer executable instructions which, when run on a computer, cause the computer to perform the activity determination method provided in the first aspect and any one of its possible implementations.

The description of the second to fourth aspects of the present application may refer to the detailed description of the first aspect; also, the advantageous effects described in the second aspect to the fourth aspect may refer to the advantageous effect analysis of the first aspect, and are not described herein.

Drawings

FIG. 1 is a schematic diagram of an liveness determination device system architecture in accordance with some embodiments;

FIG. 2 is a flowchart of a method for liveness determination in accordance with some embodiments;

FIG. 3 is a flow chart diagram II of a method of liveness determination in accordance with some embodiments;

FIG. 4 is a diagram of liveness division in accordance with some embodiments;

FIG. 5 is a schematic diagram of a wave analysis according to some embodiments;

FIG. 6 is a schematic diagram of an activity determining device according to some embodiments;

fig. 7 is a schematic diagram of a second configuration of an activity determining apparatus according to some embodiments.

Detailed Description

The following describes a detailed description of an activity determination method provided in the present application with reference to the accompanying drawings.

The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone.

The terms "first" and "second" and the like in the description and in the drawings are used for distinguishing between different objects or between different processes of the same object and not for describing a particular order of objects.

Furthermore, references to the terms "comprising" and "having" and any variations thereof in the description of the present application are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or apparatus.

It should be noted that, in the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

In the description of the present application, unless otherwise indicated, the meaning of "a plurality" means two or more.

As described in the background art, in the related art, when the user activity is measured, the user activity is generally judged by the access times, access duration, collection indexes and the like of the internet products, which are all based on statistics of the product population, and the activity condition of each user is not concerned, so that the accuracy of the measured user activity is low, the measured user activity cannot be used as a guide of manual intervention in the individual level of the user, and the practicability is poor.

Aiming at the technical problems, the embodiment of the application provides an activity determination method, which specifically comprises the following steps: firstly, clustering according to behavior data and attribute data of a user of a target application in a preset time period to obtain an active frequency threshold N; and then, dividing the liveness of the user according to the liveness frequency threshold value N and the user behavior data of the target application. It can be appreciated that, compared with the method of dividing the liveness by adopting the preset fixed value in the related art, the method of dividing the liveness by using the preset fixed value can cluster according to the user characteristics (including the behavior characteristics and the user attribute characteristics) of the target application to obtain the liveness frequency threshold, so that the determined liveness frequency threshold N is more fit with the use scene, and further, the accuracy of liveness division can be improved.

Referring to fig. 1, a schematic diagram of a system architecture of an activity determining device according to an embodiment of the present application is provided, where the system includes: server 100 and terminal device 200. The server and the terminal equipment can be connected in a wireless mode. For example, the processor and the terminal device are connected by a wireless local area network.

Wherein the server 100 is configured to provide services (e.g., computer services, management services, storage services, etc.) to the outside through a network.

In some embodiments, the server 100 may be configured to obtain user behavior data and user attribute data of the target application, and determine an activity of a user of the target application according to the user behavior data and the user attribute data.

The server may be a single server, or may be a server cluster formed by a plurality of servers. In some implementations, the server cluster may also be a distributed cluster.

The terminal device 200 is a device that performs man-machine interaction with a user, and the user generates user behavior data in the process of performing man-machine interaction with the terminal device.

By way of example, the terminal device may be a cell phone, tablet, desktop, laptop, handheld computer, notebook, ultra-mobile personal computer (UMPC), netbook, cell phone, personal digital assistant (personal digital assistant, PDA), augmented reality (augmented reality, AR) \virtual reality (VR) device, or the like. The embodiment of the present application is not particularly limited to the specific form of the terminal device 200. The system can perform man-machine interaction with a user through one or more modes of a keyboard, a touch pad, a touch screen, a remote controller, voice interaction or handwriting equipment and the like.

It should be noted that, the system architecture described in the embodiments of the present application is for more clearly describing the technical solution of the embodiments of the present application, and does not constitute a limitation on the technical solution provided by the embodiments of the present application, and those skilled in the art can know that, along with the evolution of the system architecture, the technical solution provided by the embodiments of the present application is equally applicable to similar technical problems.

The embodiments of the present application will be described in detail below with reference to the drawings attached to the specification.

As shown in fig. 2, an embodiment of the present application provides a flowchart one of an activity determining method, where the method is applied to the server shown in fig. 1, and the method includes:

s101, acquiring user behavior data and user attribute data of a target application in a first preset time period.

The first preset time period is a time period set by an analyst according to different service requirements. The first preset period may be, for example, one day, one week, one month, or the like, which is not limited by the embodiment of the present application.

The target application may be an Application (APP), a web page, an applet, or the like, for example, a WeChat, a QQ, a microblog, a beauty group, or the like, which is not limited by the embodiment of the present application.

It should be noted that, in the embodiment of the present application, "user behavior data of a target application" refers to user behavior data generated by a user using the target application, and "user attribute data of the target application" refers to user attribute data corresponding to a user using the target application.

It will be appreciated that, because the demands of users are constantly changing, and the acceptance of the target application by different users may not be high (users with lower acceptance may stop using the target application after a period of time, and the users may lose), the users of the target application may not be the same during different preset periods of time.

In some embodiments, the user behavior data is behavior data capable of reflecting an active condition of the user. By way of example, the behavior that can reflect the user's activity may include at least one of: logging in, page browsing, clicking actions, registering actions, focusing actions, collecting actions, etc.

By way of example, the user behavior data may be represented in the form shown in Table 1 below:

TABLE 1

Date of data	User id	Service	Date of last operation	Total number of operations
					2023-1-21	AE1256	Login	2023-1-21	1357
2023-1-21	AE1312	Login	2023-1-21	3145
					2023-1-21	AB1122	Browsing page A	2023-1-20	2478
2022-12-15	AB1122	Click control F	2022-5-10	123

As can be seen from table 1, the user behavior data may include time and number of times the user behavior occurs, so that the activity of the user for a certain period of time may be determined according to the user behavior data. It will be appreciated that all or part of the user behavior may be recorded according to table 1 above, updated and adjusted according to the user's needs.

In some embodiments, the user attribute data is data that can reflect user basic information. By way of example, the user attribute data may include at least one of: gender, age, cell phone model, province, industry, channel source, etc.

S102, clustering according to user behavior data and user attribute data of the target application to obtain an active frequency threshold N.

Wherein N is an integer greater than or equal to 1.

For example, step S102 may be implemented as a K-Means (K-Means clustering algorithm, K-Means) clustering algorithm, where the active frequency threshold N is clustered according to user behavior data and user attribute data of the target application. It will be appreciated that clustering is the division of a feature matrix of a set of N samples into K non-intersecting clusters (intuitively, clusters are a group of data that are clustered together), and the data in each cluster can be considered the same class of data. Clusters are the resultant manifestations of clustering. In the K-Means algorithm, the number K of clusters is a super parameter, and the core task of the K-Means is to find out K best centroids according to the set K.

In some embodiments, the step S102 is specifically implemented as follows:

and a1, determining the active condition of a user of the target application in each time unit of k time units according to the user behavior data of the target application.

Wherein k is an integer greater than or equal to 1.

The time units are set according to the service requirements, and the length of one time unit may be, for example, day, week, month, etc., which is not limited by the embodiment of the present application.

Exemplary, active conditions include: active and inactive.

For example, if the user of the target application generates behavior data in time unit 1 (e.g., the user has a login, browsing, praise, etc. behavior), then it is determined that the user of the target application is in an active state in time unit 1; if the user of the target application does not generate behavior data in the time unit 1, it is determined that the user of the target application is not in an active state, i.e. is not active, in the time unit 1.

Step a2, the data object set is formed by the activity condition of the user of the target application in each time unit and the user attribute data in each time unit.

In some embodiments, the target application may include a plurality of users, and the activity of a user in a time unit and the user attribute data of the user are taken as a data object. And the plurality of data objects obtained by the activity condition of a plurality of users in each time unit and the user attribute data of the plurality of users form a data object set.

Illustratively, the activity of user 1 at time unit 1 may be as a data object with user attribute data of user 1.

And a3, determining P clustering centers of the data object set.

Wherein P is an integer greater than or equal to 1.

As one possible implementation, the cluster center may be determined based on a random number seed (random_state) parameter in a machine learning tool (Scikit-Learn, sklearn) of the Python language. The random_state parameter can ensure that the initial centroid generated by each generation iteration is in the same position. By way of example, the optimal random_state parameter may be determined by plotting a learning curve.

As another possible implementation, the cluster center may also be determined based on a parameter n_init in Sklearn (n_init is used to characterize the number of runs corresponding to each random number seed) to determine the cluster center.

As another possible implementation, the cluster center may also be determined based on the k-means++ algorithm in Sklearn.

And a4, respectively calculating the similarity between each data object in the data object set and the P clustering centers.

Wherein the similarity calculation function includes at least one of: cosine distance, euclidean distance, markov distance, and manhattan distance.

Step a5, obtaining at least one cluster according to the similarity between each data object in the data object set and the P cluster centers; wherein, a cluster corresponds to a value of the active frequency threshold N.

Taking a cluster center 1 of the P cluster centers as an example, a cluster of the cluster center 1 is formed by data objects, of which the similarity with the cluster center 1 is greater than or equal to a preset threshold, in the data object set.

For example, a value of the activity frequency threshold N may be determined from each data object in the cluster.

S103, dividing the liveness of the user of the target application according to the liveness frequency threshold value N and the user behavior data of the target application.

In some embodiments, as shown in fig. 3, which is a flowchart of a method for determining the activity, the step S103 may be implemented as the following steps:

s1031, dividing the first preset time period into a plurality of time units.

Illustratively, a time unit may be daily, weekly, monthly, etc.

For example, assuming that the first preset time period is 1 month (31 days) and the length of the time unit is day, the first preset time period may be divided into 31 time units.

S1032, determining the active condition of the user of the target application in a plurality of time units according to the user behavior data of the target application.

Wherein the active condition includes active or inactive.

S1033, dividing the liveness of the user of the target application according to the liveness of the user of the target application in a plurality of time units and the liveness frequency threshold value N.

In some embodiments, the step S1033 may be implemented as the following steps:

and b1, determining the user meeting the first condition as a first liveness user from users of the target application. The first condition is that the user is in an active state in a first time unit, and N continuous time units including the first time unit are all in an active state; the first time unit is the time unit with the latest ending time in the plurality of time units.

And b2, determining the user meeting the second condition as a second liveness user from the users of the target application. The second condition is that the user is in an active state in the first time unit, but the number of the active time units is less than N in the continuous N time units including the first time unit.

And b3, determining the user meeting the third condition as a third liveness user from the users of the target application. The third condition is that the user is not in an active state in the first time unit, but the number of the active time units is less than N in the continuous N time units before the first time unit.

In some embodiments, potential users of the target application are analyzed based on user data of the first liveness user and the second liveness user.

Wherein potential users may be classified into high-value potential users and low-value potential users.

In particular, the high value potential user is a user that has not been active, but has properties similar to those of a heavily active user or a normally active user.

The low value potential users are users who have not been active, and the attribute of the low value potential users is widely separated from the heavy active users.

In some embodiments, the step S1033 may be further implemented as the following steps:

And c1, determining the user meeting the fourth condition as a reflow user from the users of the target application. The fourth condition is that the user is in an active state in the first time unit, and the first time unit is separated from the time unit in the last active state by M time units; the first time unit is the time unit with the latest ending time in the plurality of time units; m is an integer greater than or equal to N.

And c2, determining the user meeting the fifth condition as the newly added active user from the users of the target application. The fifth condition is that the user is in an active state for a first time unit, but is not in an active state for a time unit before the first time unit.

And c3, determining the user meeting the sixth condition as the lost user from the users of the target application. Wherein the sixth condition is that none of the user's consecutive N time units including the first time unit are in an active state.

For easy understanding, the method for determining the activity provided by the embodiment of the present application is described below in an exemplary manner.

For example, assuming that the length of the unit time is one week, the first preset period may be divided into 8 weeks, and the active frequency threshold N is 4. Then, as shown in fig. 4, the users of the target application may be classified into the following categories:

First liveness user: the current week is active and a continuous 4 week active user including the current week. The current week is the week with the latest ending time in the first preset time period.

Second liveness user: the current week is active, and the number of weeks in an active state is less than 4 in the consecutive 4 weeks including the current week.

Third liveness user: the current week is inactive, and the number of weeks in an active state is less than 4 for 4 consecutive weeks including the current week.

Newly added users: the current week is active, and none of the users in an active state in the week before the current week.

Reflow user: the current week is active and the user is inactive for 4 consecutive weeks, including the current week, but historically active.

Loss user: users that are not active for the current week and are not active for 4 consecutive weeks, including the current week.

Potential users: have not been lived and are attributed to users associated with the first liveness user and the second liveness user.

In some embodiments, the above method further comprises: and determining fluctuation conditions of the user liveness. By way of example, the following steps may be implemented:

step d1, acquiring the liveness division condition of a user of the target application in a second preset time period; wherein the second preset time period is earlier than the first preset time period.

Step d2, determining fluctuation conditions of the user liveness of the target application based on the liveness division conditions of the user of the target application in the second preset time period and the liveness division conditions of the user of the target application in the first preset time period.

The example assumes that the target application is WeChat, if the first activity user in the WeChat users in the second preset time period is 30 people, and the first activity user in the WeChat users in the first preset time period is 20 people, determining the category of fluctuation as the first activity user; the subject that fluctuated was 10 individuals lost from the first liveness user. Therefore, the method provided by the embodiment of the application can accurately determine the object with fluctuation, and then analyze the fluctuation reason aiming at the object with fluctuation, thereby accurately determining the next operation strategy.

In some embodiments, the above method further comprises: and analyzing the fluctuation condition of the user liveness of the target application, and determining the fluctuation reason. By way of example, firstly, by analyzing the fluctuation condition of the user liveness, users with larger fluctuation range are rapidly positioned, and then multidimensional analysis is carried out on factors influencing the fluctuation of the users. By way of example, these dimensions may include: user gender, age, mobile phone model, province, time festival holidays, industry, channel source, etc.

Illustratively, as shown in fig. 5, it is assumed that the user whose fluctuation amplitude is large includes: the method comprises the steps of a first-class liveness user, a newly added liveness user and a lost user. Wherein, the number of the first-class liveness users is reduced by 50%, one of reasons for the reduction is the service reduction of related industries, and the reasons account for 80% of the total reduction reasons. The number of newly added active users is reduced by 20%, and the advertisement is reduced by 10% and the advertisement is the heaviest. The loss user increases by 5%, and the loss of the user using the android mobile phone accounts for 3% of the total loss among the reasons for the increase.

It can be seen that the foregoing description of the solution provided by the embodiments of the present application has been presented mainly from a method perspective. To achieve the above-mentioned functions, embodiments of the present application provide corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The embodiment of the application can divide the functional modules of the network node according to the method example, for example, each functional module can be divided corresponding to each function, and two or more functions can be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules. Optionally, the division of the modules in the embodiment of the present application is schematic, which is merely a logic function division, and other division manners may be implemented in practice.

Fig. 6 is a schematic structural diagram of an activity determining device according to an embodiment of the present application. The modules in the device shown in fig. 6 have the functions of implementing the steps in fig. 2, and achieve the corresponding technical effects. As shown in fig. 6, the liveness determination apparatus 600 may include: an acquisition module 601, a clustering module 602 and a determination module 603.

The acquiring module 601 is configured to acquire user behavior data and user attribute data of a target application within a first preset period of time.

The clustering module 602 is configured to determine, according to user behavior data of the target application, an activity of a user of the target application in k time units. Wherein k is an integer greater than or equal to 1.

The determining module 603 is configured to divide the liveness of the user of the target application according to the liveness threshold N and the user behavior data of the target application.

In some embodiments, the determining module 603 is specifically configured to divide the preset time period into a plurality of time units; according to user behavior data of the target application, determining the active conditions of a user of the target application in a plurality of time units; wherein the active condition includes active or inactive; and dividing the liveness of the user of the target application according to the liveness of the user of the target application in a plurality of time units and the liveness frequency threshold N.

In some embodiments, the determining module 603 is specifically configured to divide, among the users of the target application, the users that meet the first condition into users of a first liveness; the first condition is that the user is in an active state in a first time unit, and N continuous time units including the first time unit are all in an active state; the first time unit is the time unit with the latest ending time in the plurality of time units; dividing users meeting a second condition among users of the target application into users with second liveness; the second condition is that the user is in an active state in the first time unit, but the number of the time units in the active state is less than N in the continuous N time units including the first time unit; dividing users meeting a third condition among users of the target application into users with third liveness; the third condition is that the user is not in an active state in the first time unit, but the number of time units in the active state is less than N in the continuous N time units before the first time unit.

In some embodiments, the determining module 603 is further configured to analyze the potential users of the target application according to the user data of the first liveness user and the second liveness user.

In some embodiments, the determining module 603 is specifically configured to divide, among the users of the target application, the user that satisfies the fourth condition into reflow users; the fourth condition is that the user is in an active state in the first time unit, and the first time unit is separated from the time unit in the last active state by M time units; the first time unit is the time unit with the latest ending time in the plurality of time units; m is an integer greater than or equal to N; dividing users meeting a fifth condition among users of the target application into newly added users; the fifth condition is that the user is in an active state in the first time unit, but is not in an active state in a time unit before the first time unit; dividing users meeting a sixth condition among users of the target application into lost users; wherein the sixth condition is that none of the user's consecutive N time units including the first time unit are in an active state.

In some embodiments, the clustering module 603 is specifically configured to determine, according to user behavior data of the target application, an activity condition of a user of the target application in k time units; wherein k is an integer greater than or equal to 1; forming a data object set by the active condition of a user of the target application in k time units and attribute data of the user in a first time unit; determining P cluster centers of the data object set; p is an integer greater than or equal to 1; respectively calculating the similarity between each data object in the data object set and the P clustering centers; obtaining at least one cluster according to the similarity between each data object in the data object set and the P cluster centers; wherein, a cluster corresponds to a value of the active frequency threshold N.

In some embodiments, the obtaining module 601 is further configured to obtain a user liveness division situation of the target application in a second preset period of time; wherein the second preset time period is earlier than the first preset time period; the determining module 603 is further configured to determine a fluctuation condition of the activity of the user of the target application based on the activity dividing condition of the user of the target application in the second preset time period and the activity dividing condition of the user of the target application in the first preset time period.

In the case of implementing the functions of the integrated modules in the form of hardware, the embodiment of the present application provides another possible structural schematic diagram of an activity determining apparatus related to the above embodiment. As shown in fig. 7, the liveness determination device 700 includes: a processor 702, a communication interface 703, and a bus 704. Optionally, the liveness determination device 700 may further comprise a memory 701.

The processor 702 may be any means for implementing or executing the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 702 may be a central processor, a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. The processor 702 may also be a combination of computing functions, e.g., including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

A communication interface 703 for connecting with other devices via a communication network. The communication network may be an ethernet, a radio access network, a wireless local area network (wireless local area networks, WLAN), etc.

The memory 701 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

As a possible implementation, the memory 701 may exist separately from the processor 702, and the memory 701 may be connected to the processor 702 through the bus 704 for storing instructions or program codes. The processor 702, when calling and executing instructions or program code stored in the memory 701, is capable of implementing the liveness determination method provided by the embodiments of the present invention.

In another possible implementation, the memory 701 may also be integrated with the processor 702.

Bus 704, which may be an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The bus 704 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus.

From the foregoing description of the embodiments, it will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the activity determining device is divided into different functional modules to perform all or part of the functions described above.

The embodiment of the application also provides a computer readable storage medium. All or part of the flow in the above method embodiments may be implemented by computer instructions to instruct related hardware, and the program may be stored in the above computer readable storage medium, and the program may include the flow in the above method embodiments when executed. The computer readable storage medium may be any of the foregoing embodiments or memory. The computer-readable storage medium may be an external storage device of the liveness determination device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card (flash card) or the like, which are provided in the liveness determination device. Further, the computer-readable storage medium may further include both an internal storage unit and an external storage device of the liveness determination apparatus. The computer-readable storage medium is used for storing the computer program and other programs and data required by the liveness determination device. The above-described computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

An embodiment of the present application also provides a computer program product comprising a computer program which, when run on a computer, causes the computer to perform any one of the activity determination methods provided in the above embodiments.

The foregoing is merely illustrative of specific embodiments of the present application, and the scope of the present application is not limited thereto, but any changes or substitutions within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining liveness, comprising:

acquiring user behavior data and user attribute data of a target application in a first preset time period;

clustering according to the user behavior data and the user attribute data of the target application to obtain an active frequency threshold N; the N is an integer greater than or equal to 1;

and dividing the liveness of the user of the target application according to the liveness frequency threshold value N and the user behavior data of the target application.

2. The method according to claim 1, wherein the performing liveness division on the user of the target application according to the liveness frequency threshold N and the user behavior data of the target application includes:

Dividing the preset time period into a plurality of time units;

according to the user behavior data of the target application, determining the active conditions of the user of the target application in the plurality of time units; wherein the active condition comprises active or inactive;

and dividing the liveness of the user of the target application according to the liveness of the user of the target application in the plurality of time units and the liveness frequency threshold N.

3. The method according to claim 2, wherein the classifying the activity of the user of the target application according to the activity of the user of the target application in the plurality of time units and the activity frequency threshold N includes:

dividing users meeting a first condition among users of the target application into users with first liveness; the first condition is that a user is in an active state in a first time unit, and continuous N time units including the first time unit are all in an active state; the first time unit is the time unit with the latest ending time in the plurality of time units;

dividing the users meeting the second condition among the users of the target application into users with second liveness; the second condition is that the user is in an active state in the first time unit, but in the continuous N time units comprising the first time unit, the number of the time units in the active state is smaller than N;

Dividing the users meeting the third condition among the users of the target application into users with third liveness; the third condition is that the user is not in an active state in the first time unit, but the number of the active time units is smaller than N in the continuous N time units before the first time unit.

4. A method according to claim 3, characterized in that the method further comprises: and analyzing potential users of the target application according to the user data of the first liveness user and the second liveness user.

5. The method according to claim 2, wherein the classifying the activity of the user of the target application according to the activity of the user of the target application in the plurality of time units and the activity frequency threshold N includes:

dividing the users meeting the fourth condition among the users of the target application into reflow users; the fourth condition is that the user is in an active state in a first time unit, and the first time unit is separated from a time unit in the last active state by M time units; the first time unit is the time unit with the latest ending time in the plurality of time units; m is an integer greater than or equal to N;

Dividing users meeting a fifth condition among the users of the target application into newly added users; wherein the fifth condition is that the user is in an active state in the first time unit, but is not in an active state in a time unit before the first time unit;

dividing users meeting a sixth condition among the users of the target application into loss users; wherein the sixth condition is that none of the user's consecutive N time units including the first time unit are in an active state.

6. The method according to claim 1, wherein the clustering the active frequency threshold N according to the user behavior data and the user attribute data of the target application comprises:

according to the user behavior data of the target application, determining the active conditions of the user of the target application in k time units; wherein k is an integer greater than or equal to 1;

forming a data object set by the active condition of the user of the target application in k time units and attribute data of the user in the first time unit;

determining P cluster centers of the data object set; the P is an integer greater than or equal to 1;

Respectively calculating the similarity between each data object in the data object set and the P clustering centers;

obtaining at least one cluster according to the similarity between each data object in the data object set and the P cluster centers; wherein one cluster corresponds to one value of the active frequency threshold N.

7. The method according to claim 1, wherein the method further comprises:

acquiring the user liveness division condition of the target application in a second preset time period; wherein the second preset time period is earlier than the first preset time period;

and determining the fluctuation condition of the activity of the user of the target application based on the activity dividing condition of the user of the target application in the second preset time period and the activity dividing condition of the user of the target application in the first preset time period.

8. An activity determination apparatus, the apparatus comprising:

the acquisition module is used for acquiring user behavior data and user attribute data of the target application in a first preset time period;

the clustering module is used for clustering according to the user behavior data and the user attribute data of the target application to obtain an active frequency threshold N; the N is an integer greater than or equal to 1;

And the determining module is used for dividing the liveness of the user of the target application according to the liveness threshold value N and the user behavior data of the target application.

9. An electronic device comprising a processor and a memory, the processor coupled to the memory; the memory is for storing computer instructions that are loaded and executed by the processor to cause a computer device to implement the liveness determination method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises computer-executable instructions which, when run on a computer, cause the computer to perform the liveness determination method of any one of claims 1 to 7.