Active cycle preference determination method and device, electronic equipment and storage medium

Abstract

The invention relates to an active cycle preference determination method and device, electronic equipment and a storage medium. The method comprises the steps of determining a first active concentration degree corresponding to a first time period and a second active concentration degree corresponding to a second time period based on active degree data generated by a target object in the first time period based on an interactive application; obtaining target object data of interaction between the target object and the interaction application in a third time period; predicting the active preference of the target object in the interactive application according to the target object data to obtain the corresponding active preference degree of the target object in the interactive application; determining active period preference information corresponding to the target object based on the first active concentration degree, the second active concentration degree and the active preference degree; the active period preference information is used for indicating the active time period of the target object in periodic preference in the interactive application. According to the technical scheme provided by the invention, the accuracy of determining the active period preference can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device, and storage medium for determining an active period preference. Background Art

[0002] With the widespread use of the internet, interactions within various applications are becoming increasingly diverse, such as playing games and participating in in-game activities. To enhance these interactions, related technologies typically consider factors such as weekly and monthly active days to effectively allocate resources. However, existing allocation strategies often consider a single, fixed set of factors and fail to effectively characterize players' active preferences. This leads to inaccurate determination of active habits, resulting in inaccurate resource allocation and disruption to players. Summary of the Invention

[0003] This application provides a method, device, electronic device, and storage medium for determining an active period preference to improve the accuracy of the active period preference. The technical solution of this application is as follows:

[0004] According to a first aspect of an embodiment of the present application, a method for determining an active period preference is provided, comprising:

[0005] Acquiring activity data generated by a target object based on an interactive application within a first time period, wherein the first time period is composed of a periodically occurring second time period;

[0006] Determining, based on the activity data, a first activity concentration corresponding to the first time period and a second activity concentration corresponding to the second time period; the first activity concentration being used to characterize the distribution and concentration of activity in the second time period within the first time period; and the second activity concentration being used to characterize the distribution and concentration of a single activity in the first time period within the second time period;

[0007] Acquire target object data of the target object interacting with the interactive application within a third time period; the first time period belongs to the third time period;

[0008] predicting the activity preference of the target object in the interactive application based on the target object data to obtain the corresponding activity preference level of the target object in the interactive application;

[0009] Based on the first activity concentration, the second activity concentration, and the activity preference degree, activity period preference information corresponding to the target object is determined; the activity period preference information is used to indicate a periodic preferred activity period of the target object in the interactive application.

[0010] According to a second aspect of an embodiment of the present application, a device for determining an active period preference is provided, including:

[0011] A first acquisition module is configured to acquire activity data generated by a target object based on an interactive application within a first time period; the first time period is composed of a periodically occurring second time period;

[0012] a concentration determination module, configured to determine, based on the activity data, a first activity concentration corresponding to the first time period and a second activity concentration corresponding to the second time period; the first activity concentration being used to characterize the distribution and concentration of activity in the second time period within the first time period; and the second activity concentration being used to characterize the distribution and concentration of a single activity in the first time period within the second time period;

[0013] A second acquisition module is configured to acquire target object data of the target object interacting with the interactive application within a third time period; the first time period belongs to the third time period;

[0014] an activity preference degree prediction module, configured to predict the activity preference of the target object in the interactive application based on the target object data, and obtain the activity preference degree corresponding to the target object in the interactive application;

[0015] An activity period preference determination module is configured to determine activity period preference information corresponding to the target object based on the first activity concentration, the second activity concentration, and the activity preference degree; the activity period preference information is configured to indicate a period of activity during which the target object has a periodic preference in the interactive application.

[0016] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method as described in any one of the first aspects above.

[0017] According to the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of an electronic device, the electronic device can execute any method described in the first aspect of the embodiments of the present application.

[0018] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, comprising computer instructions, which, when executed by a processor, enable a computer to execute any one of the methods according to the first aspect of the embodiment of the present application.

[0019] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0020] By determining the first activity concentration of the target object within a first time period consisting of a periodic second time period and the corresponding second activity concentration of the target object in the second time period, the target object's activity concentration distribution habits can be effectively characterized, so that the first activity concentration and the second activity concentration can accurately reflect the target object's activity habits. Furthermore, by combining target object data of the target object interacting with an interactive application within a third time period that spans a longer time span than the first time period, the target object's activity preference level is predicted. Based on the first activity concentration, the second activity concentration, and the activity preference level, activity period preference information corresponding to the target object is determined. This activity period preference information indicates the target object's periodic preferred activity period in the interactive application. Operations, such as resource allocation, can thus be performed on the target object based on this periodic preferred activity period, making resource allocation and other operations more accurate and effectively reducing repeated interference with the target object.

[0021] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0023] Figure 1 It is a schematic diagram showing an application environment according to an exemplary embodiment.

[0024] Figure 2 The figure is a flowchart of a method for determining an active period preference according to an exemplary embodiment.

[0025] Figure 3 The figure is a schematic diagram showing hierarchical statistics of first activity concentrations corresponding to a large number of objects according to an exemplary embodiment.

[0026] Figure 4 The figure is a schematic diagram showing hierarchical statistics of second activity concentrations corresponding to a large number of objects according to an exemplary embodiment.

[0027] Figure 5 The figure is a flowchart of a method for determining an active period preference according to an exemplary embodiment.

[0028] Figure 6 The figure is a block diagram of a device for determining an active period preference according to an exemplary embodiment.

[0029] Figure 7It is a block diagram of an electronic device for determining an active period preference according to an exemplary embodiment. DETAILED DESCRIPTION

[0030] Various exemplary embodiments, features, and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0031] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0032] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0033] In addition, numerous specific details are provided in the detailed description below to better illustrate the present application. Those skilled in the art will appreciate that the present application can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present application.

[0034] Artificial Intelligence (AI) is the theory, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. AI software technologies primarily encompass computer vision, speech processing, natural language processing, computer data processing, and machine learning / deep learning.

[0035] In recent years, with the research and progress of artificial intelligence technology, artificial intelligence technology has been widely used in many fields. The solution provided in the embodiment of this application involves computer data processing technology, which is specifically illustrated by the following embodiment.

[0036] See also Figure 1 , Figure 1 A schematic diagram of an application system provided according to an embodiment of the present application is shown. The application system can be used in the method for determining the active period preference of the present application. Figure 1 As shown, the application system may at least include a server 01 and a terminal 02.

[0037] In an embodiment of the present application, the server 01 can be used to determine and process the active period preference. The server 01 may include an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0038] In the embodiment of the present application, the terminal 02 can be used to trigger the active period preference processing, or receive and display delivered resources, etc. The terminal 02 may include a physical device such as a smartphone, a desktop computer, a tablet computer, a laptop computer, a smart speaker, a digital assistant, an augmented reality (AR) / virtual reality (VR) device, a smart wearable device, etc. The physical device may also include software running on the physical device, such as an application. The operating system running on the terminal 02 in the embodiment of the present application may include, but is not limited to, Android, iOS, Linux, Windows, etc.

[0039] In addition, it should be noted that Figure 1 The example shown is only one application environment of the method for determining the active period preference provided by the present application. For example, the active period preference determination process may also be triggered by the server 01, which is not limited in the present application.

[0040] In the embodiments of this specification, the terminal 02 and the server 01 may be connected directly or indirectly via wired or wireless communication, which is not limited in this application.

[0041] In a specific embodiment, when server 02 is a distributed system, the distributed system may be a blockchain system. Blockchain is a novel application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (to prevent counterfeiting) and generate the next block. Blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0042] The underlying blockchain platform can include processing modules such as user management, basic services, smart contracts, and operation monitoring. Among them, the user management module is responsible for the identity information management of all blockchain participants, including maintaining public and private key generation (account management), key management, and maintaining the corresponding relationship between the user's real identity and the blockchain address (authority management), etc., and under authorization, it supervises and audits the transactions of certain real identities and provides risk control rule configuration (risk control audit); the basic service module is deployed on all blockchain node devices to verify the validity of business requests, and records the valid requests to the storage after consensus is reached. For a new business request, the basic service first adapts the interface to parse and authenticate the request (interface adaptation), and then encrypts the business information through the consensus algorithm (consensus management). The smart contract module is responsible for the registration, issuance, triggering and execution of contracts. Developers can define the contract logic in a programming language and publish it to the blockchain (contract registration). According to the logic of the contract terms, the contract logic is triggered by calling keys or other events to trigger execution. The contract logic is completed, and the contract upgrade and cancellation functions are also provided. The operation monitoring module is mainly responsible for the deployment, configuration modification, contract setting, cloud adaptation and real-time status visualization output of the product during the product release process, such as alarms, network status monitoring, and node equipment health status monitoring.

[0043] The platform's product service layer provides the basic capabilities and implementation framework for typical applications. Developers can build on these basic capabilities, overlay business features, and complete the blockchain implementation of business logic. The application service layer provides application services based on blockchain solutions for business participants to use.

[0044] It should be noted that in the specific implementation of this application, user-related data is involved. When the following embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0045] Figure 2 FIG. 1 is a flow chart showing a method for determining an active period preference according to an exemplary embodiment. Figure 2 As shown, the following steps may be included.

[0046] In step S201 , activity data generated by a target object based on an interactive application within a first time period is obtained; the first time period is composed of periodically occurring second time periods.

[0047] In the embodiments of this specification, the target object can be any object in an interactive application, and the object can refer to a user. An interactive application can refer to an application that provides object interaction, such as a game, short video, and the like, and this application does not limit this. For example, the interactive application can be any application in an application group service, and the application group service can be used to manage different applications in the application group service. For example, a company's game manager service can be used to manage different games of the company, and the determined active cycle preference information can refer to the active habits reflected by the target object's interactions with different games in the game manager service.

[0048] The first time period may be composed of a second time period that occurs periodically, i.e., the second time period occurs periodically within the first time period. For example, the first time period is a single week, i.e., one week; correspondingly, the second time period may be a day, so that the first time period may include 7 recurring days. Alternatively, the first time period is a month, and correspondingly, the second time period may be a week, which is not limited in this application. In one example, the first time period may also occur periodically over a longer time span, for example, the first time period is a single week, and the single week may occur periodically over a longer time span, such as a month or year, which is not limited in this application.

[0049] In an embodiment of the present specification, the activity data generated by the target object based on the interactive application within the first time period can be obtained. For example, the recorded data of the target object interacting with the interactive application can be obtained, such as the recorded data of the target object logging into the interactive application. Furthermore, the target recorded data within the first time period can be extracted from the recorded data, so that the data that can characterize the activity of the object in the target recorded data can be filtered as the activity data. Among them, the activity data may include but is not limited to the online time and login frequency of logging into the interactive application, etc., and this application is not limited to this. The recorded data can record the relevant data of each login, for example, the recorded data may include but is not limited to the login time of each login to the interactive application, the online time continued after login (such as the time between the login time and the logout time corresponding to a login to the interactive application), the time to log out of the interactive application, the operations in the interactive application, etc., and this application is not limited to this, as long as the interaction events (such as login events) between the target object and the interactive application can be effectively recorded.

[0050] In step S203 , a first activity concentration corresponding to the first time period and a second activity concentration corresponding to the second time period are determined based on the activity data.

[0051] In the embodiments of this specification, the first activity concentration can be used to characterize the distribution and concentration of the activity in the second time period within the first time period. That is, the first activity concentration can be used to know the distribution and concentration of the proportion of the activity in the second time period in the entire activity in the first time period, such as the proportion of the activity in the second time period to the entire activity in the first time period, so that it can be known what proportion the distribution is concentrated in, etc., or the first activity concentration can be used to know the activity level represented by the activity in the second time period in the entire activity in the first time period. For example, the higher the above ratio, the higher the activity level represented by the activity in the second time period in the entire activity in the first time period. Exemplarily, the first activity concentration can be the ratio of the statistical information of the activity in the second time period to the statistical information of the activity of the target object in the first time period.

[0052] The second activity concentration can be used to characterize the distribution and concentration of single activity within the first time period within the second time period, wherein single activity can refer to the activity between the target object's single login to the interactive application and the time it exits the interactive application, such as the single activity duration, that is, the duration between the time it logs into the interactive application and the time it exits the interactive application. Based on this, it can be understood that the single activity within the first time period corresponds to a single login to the interactive application. There may be one or more login operations within the first time period, which may correspond to one or more single activity levels, that is, one or more single activity durations. Based on the second activity, the distribution and concentration of single activity within the first time period in the activity within the second time period can be determined, such as the proportion of single activity within the first time period to the activity within the second time period, so as to determine the proportion of the single activity within the second time period. In other words, the second activity concentration can be used to determine the degree of activity represented by the activity within the first time period in the overall activity within the second time period. For example, the higher the above ratio, the higher the degree of activity represented by the single activity within the overall activity within the second time period. For example, the second activity concentration may be a ratio of statistical information of a single activity in the first time period to statistical information of the activity of the target object in the second time period.

[0053] Statistical information may refer to information obtained by performing preset statistical processing on activity. The preset statistical processing may include but is not limited to averaging, cumulative summing, extracting the highest value, extracting the lowest value, etc., which is not limited in this application. Activity may include but is not limited to active duration, active frequency, etc. For example, active duration may be the duration of logging into an interactive application, such as the duration between the login time of logging into the interactive application and the logout time of logging out of the interactive application. Active frequency may be the frequency of logging into the interactive application within a time period.

[0054] In one possible implementation, determining the first activity concentration corresponding to the first time period based on the activity data may include:

[0055] A first cumulative active duration of the target object's login to the interactive application during the first time period can be calculated based on the activity data, for example, the cumulative sum of the duration of each login of the target object to the interactive application during the first time period, i.e., the cumulative sum of the single active durations during the first time period. Furthermore, a second cumulative active duration of the target object's login to the interactive application during each second time period can be calculated based on the activity data, for example, the cumulative sum of the duration of each login of the target object to the interactive application during the second time period, i.e., the cumulative sum of the single active durations during the second time period.

[0056] Furthermore, the highest second cumulative active duration can be selected from the second cumulative active durations corresponding to each second time period and used as the target cumulative duration. For example, if the first time period is a week and the corresponding second time period is a day, there can be seven second time periods, corresponding to seven second cumulative active durations. Based on this, the second cumulative active duration with the highest duration can be selected from these seven second cumulative active durations and used as the target cumulative duration. That is, the target cumulative duration is the second cumulative active duration that belongs to one of the seven second cumulative active durations and is higher than the other second cumulative active durations. The other second cumulative active durations are the second cumulative active durations among the seven second cumulative active durations excluding the target cumulative duration. For example, if the seven second cumulative active durations are, from Monday to Sunday, 1 hour, 2 hours, 1.5 hours, 1 hour, 1 hour, 0.5 hour, and 3 hours, the second cumulative active duration with the highest duration can be selected as 3 hours, i.e., the target cumulative duration is 3 hours. This shows that Sunday is the most active day for the target subject, i.e., the target subject is most active on Sunday.

[0057] Finally, the ratio of the target cumulative duration to the first cumulative active duration can be used as the first active concentration. Specifically, the first active concentration d can be obtained by the following formula.

[0058]

[0059] By using the proportion of the target cumulative duration corresponding to the most active second time period in the first cumulative active duration, we can characterize the active distribution concentration of the periodic second time period in the first time period, which can effectively and accurately characterize the activity of the target object in the periodic time period.

[0060] Reference Figure 3 Assuming the first time period is one week and the second time period is one day, if the first active concentration is calculated according to the level of the target object in the application group (assuming 7 levels: Level 1 to Level 7), the following can be obtained: Figure 3 As shown, Figure 3 This may be a case of the first activity concentration of a large number of objects. Here, the first activity concentration may refer to the proportion of the cumulative active time on the most active day in the cumulative active time in a week, where each small circle may represent an object.

[0061] In one possible implementation, the single activity level may be a single activity duration corresponding to a single login, for example, the duration between the login time and the logout time of a single login to an interactive application. Based on this, the second activity concentration level corresponding to the second time period may be obtained by the following steps, including:

[0062] The second cumulative active duration of the target object's login to the interactive application in each second time period can be calculated based on the activity data. For example, the number of logins in each second time period can be calculated based on the activity data, so that the single active duration of each login to the interactive application can be determined, such as the duration between the login time and the logout time of each login to the interactive application. For example, the single active duration can be obtained by subtracting the login time from the logout time corresponding to a login. The single active duration can then be summed up to obtain the second cumulative active duration of the target object's login to the interactive application in the second time period. Furthermore, the second cumulative active duration corresponding to each second time period can be statistically processed to obtain the statistical active duration corresponding to the second time period. The statistical processing can include averaging processing, summing processing, etc., which is not limited in this application. In one example, the second cumulative active duration corresponding to each second time period can be averaged to obtain the statistical active duration corresponding to the second time period, that is, the statistical active duration corresponding to the second time period is the average of the second cumulative active durations corresponding to each second time period.

[0063] Furthermore, the highest single active duration within the first time period can be selected as the target single active duration. For example, the single active duration corresponding to each login to an interactive application can be counted based on activity data, and the sizes of the individual single active durations can be compared to select the highest single active duration within the first time period as the target single active duration.

[0064] Finally, the ratio of the target single active duration to the statistical active duration can be used as the second active concentration. Specifically, the second active concentration t can be obtained by the following formula.

[0065]

[0066] Reference Figure 4 Assuming the first time period is one week and the second time period is one day, if the second active concentration is calculated according to the level of the target object in the application group (assuming 7 levels: Level 1 to Level 7), the following can be obtained: Figure 4As shown, Figure 4 This may be the case of the second active concentration of a large number of objects. The second active concentration here may refer to the proportion of the online time corresponding to the login with the longest online time among multiple logins within a week in the statistical active time, where each small circle may represent an object.

[0067] In an optional embodiment, before determining the first activity concentration and the second activity concentration, it is possible to first determine whether the activity data indicates that the target object has the characteristics of active concentration. If so, the determination is made, and if not, the determination process may not be performed. For example, for the first activity concentration, it is possible to determine whether there is a most active day. For example, if there is a day within a week where the second cumulative active duration is higher than that of other days, or if the difference between the second cumulative active duration of a day and the second cumulative active duration of other days is greater than a preset duration threshold, then the most active day can be determined and stored, so that it can be determined whether there are characteristics of active concentration within a week, and the first activity concentration can be determined based on the activity data; if it does not exist, that is, the second cumulative active duration corresponding to each second time period is relatively evenly distributed, then the determination process of the first activity concentration may not be performed. For the second activity concentration, it can be determined whether there is a most active period, that is, whether there is a single active duration in the first time period whose difference between the duration and other single active durations is greater than a specified duration threshold. The specified duration threshold can be less than the preset duration threshold. If it exists, the determination process of the second activity concentration can be determined; if it does not exist, that is, the single active duration in the first time period is relatively evenly distributed, then the determination process of the second activity concentration can be omitted.

[0068] In step S205, target object data of the target object interacting with the interactive application within the third time period is acquired.

[0069] In the embodiment of this specification, the above-mentioned first time period may belong to the third time period. For example, the third time period may be the past three months. Accordingly, the first time period may be any week in the past three months. For example, the first time period may be the week from Monday to Sunday closest to the current time. This application does not limit this.

[0070] In actual applications, recorded data of the interactive application can be obtained, so that target object data of the interaction between the target object and the interactive application in the third time period, such as operation data, can be filtered out from the recorded data. This application does not limit this.

[0071] In a possible implementation, the interactive application may be any application in an application group service (or simply referred to as an application group). Accordingly, obtaining target object data of the target object interacting with the interactive application during the third time period may include the following steps:

[0072] Obtain object attribute information related to the target object logging into the interactive application during the third time period, activity-related data related to the target object logging into the interactive application during the third time period, and activity-related data related to the target object's participation in activities based on the interactive application during the third time period. In one example, recorded data of the interactive application can be obtained, and target recorded data corresponding to the target object during the third time period can be filtered from the recorded data. Based on this, the aforementioned object attribute information, activity-related data, and activity-related data corresponding to the target object during the third time period can be filtered and statistically analyzed from the target recorded data.

[0073] Furthermore, the object attribute information, the activity-related data, and the activity-related data may be used as the target object data.

[0074] Exemplarily, object attribute information may include but is not limited to the target object's virtual character, held virtual props, login terminal, level, registration time, etc. Taking the third time period as the past three months as an example, activity-related data may include but is not limited to the monthly game login days corresponding to the target object in the past three months, the monthly login days' growth rate compared to the previous month, the monthly online time in the past three months (for example, the game online time), the monthly online time's growth rate compared to the previous month, the number of interactive applications in the monthly login application group in the past three months (for example, the number of games), the monthly interactive application group's growth rate compared to the previous month, the average daily login days on weekends compared to the average daily login days on weekdays in the past three months, the proportion of login time in each time period of each month in the past three months (for example, working hours, noon, after get off work, early morning), etc. This application does not impose any restrictions on this, as long as it can effectively represent the activity. Activity-related data may include, but is not limited to, the number of activity participations in the past three months, the duration of activity stays, the number of activity product collections, the number of product clicks, the number of product purchases, the number of gift packs received at each level, the number of coupons received at each level, the number of tasks completed, the number of gifts given away, the number of return logins after the activity, the number of return purchases, etc. Activity may refer to interactive activities in interactive applications.

[0075] In step S207 , the activity preference of the target object in the interactive application is predicted based on the target object data to obtain the corresponding activity preference degree of the target object in the interactive application.

[0076] In one possible implementation, the target object data of the target object can be input into an active preference prediction model to perform active preference prediction, and the target object's corresponding active preference level in the interactive application can be output, such as an active preference level value, which can represent the probability of active preference. The active preference prediction model can be obtained by supervised training a preset machine learning model based on a large amount of sample interaction association data, and this application is not limited to this. The method for obtaining the sample interaction association data here can refer to the method for obtaining the target object data, but it can be targeted at a large number of objects. For example, object attribute information of different objects logging into the interactive application within a preset time period, activity-related data of different objects logging into the interactive application within a preset time period, and activity-related data of different objects participating in activities based on the interactive application within a preset time period can be obtained. Thus, the object attribute information, activity-related data, and activity-related data of the above-mentioned different objects can be used as a large amount of sample interaction association data. The specific process can be referred to the above-mentioned target object data acquisition content, and will not be repeated here. The length of the preset time period here can be aligned with the length of the third time period to be suitable for predicting the target object data within the third time period. For example, it can be a three-month time period, and this application is not limited to this.

[0077] In another possible implementation, the step of predicting the target object's activity preference in the interactive application based on the target object data to obtain the corresponding activity preference level of the target object in the interactive application may include:

[0078] The target object data is sequentially processed with missing value repair, discretization and normalization to obtain the target interactive correlation data;

[0079] Furthermore, the target interaction correlation data can be input into a logistic regression model to predict the active preference of the target object in the interactive application, and obtain the corresponding active preference degree of the target object in the interactive application.

[0080] In the embodiments of this specification, to provide more accurate data for active preference prediction of the target object data, missing value repair is performed on the target object data. For example, missing value repair may include, but is not limited to, deleting missing value records or filling them with specified values. Optionally, considering data integrity, missing values ​​may be filled with the average value of the data.

[0081] Furthermore, feature engineering processing can be performed on the target object data after missing value repair, such as discretization and normalization processing, to obtain target interactive correlation data. In the learning stage, the purpose of discretization can be to increase the nonlinearity of the model and improve the generalization ability of the model, and the purpose of normalization can be to speed up the gradient descent to quickly solve the problem; in the prediction stage, feature engineering processing can improve prediction accuracy and prediction efficiency. For example, for discretization processing, features such as levels can be discretized using an equidistant interval method. For example, features can be grouped according to the same principle of each grouping interval. For example, the level value range can be 1 to 10. If the equidistant interval discretization takes 2 as the interval interval, the levels can be divided into (1, 2), (3, 4), ..., (9, 10) in sequence.

[0082] For the normalization process, the normalization process can be performed using the following normalization calculation formula.

[0083] x′=(x-X_min) / (X_max-X_min)

[0084] Among them, x ′ It can represent the target interactive correlation data; x can represent the original data, that is, the target object data after missing values ​​are repaired; X_min can represent the minimum value in the original data, and X_max can represent the maximum value in the original data.

[0085] After obtaining the target interaction correlation data, the target interaction correlation data can be input into a logistic regression model (Logit model) to predict the active preference of the target object in the interactive application and obtain the corresponding active preference degree of the target object in the interactive application. For example, the Logit model calculation formula can be as follows:

[0086]

[0087] Where P is the degree of active preference; x′ can represent the target interaction correlation data; w represents the weight of the Logit model; and e is a natural constant. The Logit model can be obtained by setting the initial value of w and learning based on sample data. This application does not limit this learning process.

[0088] In step S209 , based on the first activity concentration, the second activity concentration, and the activity preference level, activity period preference information corresponding to the target object is determined; the activity period preference information is used to indicate the periodic preferred activity period of the target object in the interactive application.

[0089] In the embodiments of this specification, the specific method for determining the active period preference information is not limited. In one example, the correspondence between the first activity concentration, the second activity concentration, and the activity preference degree and the active period can be obtained, so that the correspondence can be searched to obtain the corresponding active period as the active period preference information. In another example, the activity preference probability can be obtained based on the first activity concentration, the second activity concentration, and the activity preference degree. The activity preference probability can be positively correlated with the first activity concentration, the second activity concentration, and the activity preference degree, respectively. This application does not limit the specific method for obtaining the activity preference probability. For example, the sum of the first activity concentration, the second activity concentration, and the activity preference degree can be used as the activity preference probability. Alternatively, the weighted sum of the first activity concentration, the second activity concentration, and the activity preference degree can be used as the activity preference probability, where the weights corresponding to the first activity concentration, the second activity concentration, and the activity preference degree are not limited. Based on this, further, the correspondence between the activity preference probability and the active period can be obtained, so that the correspondence can be searched to obtain the corresponding active period as the active period preference information.

[0090] Optionally, after determining the target object's corresponding active period preference information, resources can be effectively delivered based on the target object's periodic preferred active periods in the interactive application, as indicated by the active period preference information. This improves resource conversion rates while also reducing information interference with the target object. For example, if the target object's corresponding active period preference information is every Wednesday at noon, resources can be delivered to the target object every Wednesday at noon.

[0091] In a possible implementation, determining the activity period preference information corresponding to the target object based on the first activity concentration, the second activity concentration, and the activity preference degree may include:

[0092] An activity preference probability is obtained based on the first activity concentration, the second activity concentration, and the activity preference level. For example, the activity preference probability can be obtained by multiplying the first activity concentration, the second activity concentration, and the activity preference level. For example, the activity preference probability L can be calculated using the following formula.

[0093] L=t*d*P

[0094] Among them, t is the second active concentration corresponding to the target object; d is the first active concentration corresponding to the target object; P is the active preference level corresponding to the target object.

[0095] Optionally, a weighted product of the first activity concentration, the second activity concentration, and the activity preference degree may be used as the activity preference probability.

[0096] Furthermore, the correspondence between the active preference probability range and the active preference time period can be obtained; the periodic interval of the active preference time period is the first time period mentioned above. Therefore, based on this correspondence, the active preference time period corresponding to the active preference probability range where the active preference probability is located can be determined as the active period preference information. For example, the first time period is a single week, and the correspondence between the active preference probability range and the active preference time period is: 0-0.1 corresponds to Monday morning, 0.1-0.2 corresponds to Tuesday afternoon, 0.2-0.3 corresponds to Wednesday morning, and so on. If the active preference probability of the target object is 0.26, the corresponding active preference probability range can be determined to be 0.2-0.3, so that the active period preference information can be determined to be Wednesday morning of each week. In this way, periodic precise operations with weekly periodic intervals can be achieved, such as allocating resources to the target object on Wednesday morning of each week.

[0097] By determining the first activity concentration of the target object within a first time period consisting of a periodic second time period and the corresponding second activity concentration of the target object in the second time period, the target object's activity concentration distribution habits can be effectively characterized, so that the first activity concentration and the second activity concentration can accurately reflect the target object's activity habits. Furthermore, by combining target object data of the target object interacting with an interactive application within a third time period that spans a longer time span than the first time period, the target object's activity preference level is predicted. Based on the first activity concentration, the second activity concentration, and the activity preference level, activity period preference information corresponding to the target object is determined. This activity period preference information indicates the target object's periodic preferred activity period in the interactive application. Operations, such as resource allocation, can thus be performed on the target object based on this periodic preferred activity period, making resource allocation and other operations more accurate and effectively reducing repeated interference with the target object.

[0098] Reference Figure 5In one application example, activity data generated by a target object based on an interactive application within a first time period can be obtained; the first time period is composed of periodically occurring second time periods, which can also occur periodically. Furthermore, activity concentration and activity preference can be processed based on the activity data. For example, the first cumulative active duration of the target object logging into the interactive application within the first time period and the second cumulative active duration of the target object logging into the interactive application within each second time period can be calculated based on the activity data; the highest second cumulative active duration corresponding to each second time period can be selected as the target cumulative duration; and the proportion of the target cumulative duration in the first cumulative active duration can be used as the first activity concentration. Furthermore, the second cumulative active duration of the target object logging into the interactive application within each second time period can be calculated based on the activity data; the second cumulative active duration corresponding to each second time period can be statistically processed to obtain the statistical active duration corresponding to the second time period; the highest single active duration within the first time period can be selected as the target single active duration; and the proportion of the target single active duration in the statistical active duration can be used as the second activity concentration. Furthermore, object attribute information of the target object logging into the interactive application during the third time period, activity-related data of the target object logging into the interactive application during the third time period, and activity-related data of the target object participating in activities based on the interactive application during the third time period can be obtained; the object attribute information, activity-related data, and activity-related data can be used as target object data; and the target object data can be sequentially repaired for missing values, discretized, and normalized to obtain target interaction-related data. The target interaction-related data can then be input into a logistic regression model to predict the target object's activity preference in the interactive application and obtain the target object's corresponding activity preference level in the interactive application. Furthermore, the product of the first activity concentration, the second activity concentration, and the activity preference level can be used as the activity preference probability to obtain the corresponding relationship between the activity preference probability range and the activity preference period. Based on this corresponding relationship, the activity preference period corresponding to the activity preference probability range within which the activity preference probability lies can be determined as the activity cycle preference information, thereby obtaining the target object's activity cycle preference habits.

[0099] The embodiments of this specification characterize the active cycle habits of an object by setting an active cycle preference, which takes into account the active concentration of the object in the interactive application and the active preference degree predicted based on the target object data, so that the active cycle preference can better measure the active distribution habits of the object and can effectively improve the retention of the object in the interactive application. In this way, in active retention and anti-churn activities, the active cycle habits can be used to differentiate operations, thereby reducing the input of activity resources and reducing the probability of repeated disturbances to the object. For example, the promotion of operational activities based on historical active days is compared with the promotion of operational activities based on active cycle preferences. Tests are conducted in the interactive application of the game. In the game activities, under the goal of attracting the same number of players to be active, the resources invested in the promotion of operational activities based on active cycle preferences can be reduced by 21% compared to the promotion of operational activities based on historical active days, and the number of repeated disturbances to the object can be reduced by 54%.

[0100] Figure 6 FIG. 1 is a block diagram of a device for determining an active cycle preference according to an exemplary embodiment. Figure 6 , the apparatus may include:

[0101] A first acquisition module 601 is configured to acquire activity data generated by a target object based on an interactive application within a first time period; the first time period is composed of periodically occurring second time periods;

[0102] Concentration determination module 603 is configured to determine, based on the activity data, a first activity concentration corresponding to the first time period and a second activity concentration corresponding to the second time period; the first activity concentration being used to represent the distribution and concentration of activity within the second time period within the first time period; and the second activity concentration being used to represent the distribution and concentration of a single activity within the first time period within the second time period;

[0103] The second acquisition module 605 is configured to acquire target object data of the target object interacting with the interactive application within a third time period; the first time period belongs to the third time period;

[0104] An activity preference degree prediction module 607 is configured to predict the activity preference of the target object in the interactive application based on the target object data, and obtain the activity preference degree corresponding to the target object in the interactive application;

[0105] The activity period preference determination module 609 is configured to determine the activity period preference information corresponding to the target object based on the first activity concentration, the second activity concentration, and the activity preference degree; the activity period preference information is configured to indicate the period of activity during which the target object has a periodic preference in the interactive application.

[0106] By determining the first activity concentration of the target object within a first time period consisting of a periodic second time period and the corresponding second activity concentration of the target object in the second time period, the target object's activity concentration distribution habits can be effectively characterized, so that the first activity concentration and the second activity concentration can accurately reflect the target object's activity habits. Furthermore, by combining target object data of the target object interacting with an interactive application within a third time period that spans a longer time span than the first time period, the target object's activity preference level is predicted. Based on the first activity concentration, the second activity concentration, and the activity preference level, activity period preference information corresponding to the target object is determined. This activity period preference information indicates the target object's periodic preferred activity period in the interactive application. Operations, such as resource allocation, can thus be performed on the target object based on this periodic preferred activity period, making resource allocation and other operations more accurate and effectively reducing repeated interference with the target object.

[0107] In a possible implementation, the concentration determination module 603 may include:

[0108] a first active duration counting unit, configured to count, based on the activity data, a first cumulative active duration of the target object logging into the interactive application in the first time period, and a second cumulative active duration of the target object logging into the interactive application in each second time period;

[0109] a target cumulative duration acquisition unit, configured to select the highest second cumulative active duration from the second cumulative active durations corresponding to the second time periods as the target cumulative duration;

[0110] The first activity concentration acquiring unit is configured to use a ratio of the target cumulative duration to the first cumulative activity duration as the first activity concentration.

[0111] In a possible implementation, the single activity is a single activity duration corresponding to a single login; the concentration determination module 603 may further include:

[0112] a second active duration counting unit, configured to count, based on the activity data, a second cumulative active duration of the target object logging into the interactive application in each second time period;

[0113] a statistical activity duration acquisition unit, configured to perform statistical processing on the second accumulated activity duration corresponding to each second time period to obtain a statistical activity duration corresponding to the second time period;

[0114] a target single active duration acquisition unit, configured to select the highest single active duration in the first time period as the target single active duration;

[0115] The second activity concentration obtaining unit is configured to use a ratio of the target single activity duration to the statistical activity duration as the second activity concentration.

[0116] In a possible implementation, the interactive application is any application in an application group; the second acquisition module 605 may include:

[0117] An acquisition unit is used to obtain object attribute information of the target object logging into the interactive application within the third time period, activity-related data of the target object logging into the interactive application within the third time period, and activity-related data of the target object participating in activities based on the interactive application within the third time period; and to use the object attribute information, the activity-related data and the activity-related data as the target object data.

[0118] In a possible implementation, the activity preference level prediction module 607 may include:

[0119] A data processing unit, configured to sequentially perform missing value repair, discretization, and normalization on the target object data to obtain target interactive correlation data;

[0120] The activity preference degree acquisition unit is used to input the target interaction association data into a logistic regression model, predict the activity preference of the target object in the interactive application, and obtain the corresponding activity preference degree of the target object in the interactive application.

[0121] In a possible implementation, the active period preference determination module 609 may include:

[0122] an activity preference probability obtaining unit, configured to obtain an activity preference probability based on the first activity concentration, the second activity concentration, and the activity preference degree;

[0123] a corresponding relationship acquisition unit, configured to acquire a corresponding relationship between an active preference probability range and an active preference period; wherein the period interval of the active preference period is the first time period;

[0124] The active period preference information determining unit is configured to determine, according to the corresponding relationship, an active preference time period corresponding to an active preference probability range within which the active preference probability lies, as the active period preference information.

[0125] In a possible implementation, the activity preference probability acquisition unit may include:

[0126] The activity preference probability acquisition subunit is configured to take the product of the first activity concentration, the second activity concentration, and the activity preference degree as the activity preference probability.

[0127] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0128] Figure 7 is a block diagram of an electronic device for determining an active period preference according to an exemplary embodiment. The electronic device may be a server, and its internal structure may be as shown in FIG. Figure 7 As shown. The electronic device includes a processor, a memory, and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for determining an active cycle preference.

[0129] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0130] In an exemplary embodiment, an electronic device is further provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the method for determining the active cycle preference as in the embodiment of the present application.

[0131] In an exemplary embodiment, a computer-readable storage medium is also provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method for determining the active period preference in the embodiment of the present application. The computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0132] In an exemplary embodiment, a computer program product containing instructions is further provided. When the computer program product is executed on a computer, the computer is caused to perform the method for determining the active period preference in the embodiment of the present application.

[0133] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, which can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0134] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0135] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining an active period preference, characterized in that: include: Obtaining activity data generated by the target object based on the interactive application within a first time period; The first time period is composed of a second time period that occurs periodically; determining, based on the activity data, a first activity concentration corresponding to the first time period and a second activity concentration corresponding to the second time period; The first activity concentration is used to represent the distribution and concentration of activity in the second time period within the first time period, and the second activity concentration is used to represent the distribution and concentration of a single activity in the first time period within the second time period; Acquire target object data of the target object interacting with the interactive application within a third time period; The first time period belongs to the third time period; predicting the activity preference of the target object in the interactive application based on the target object data to obtain the corresponding activity preference level of the target object in the interactive application; determining, based on the first activity concentration, the second activity concentration, and the activity preference degree, activity period preference information corresponding to the target object; The active period preference information is used to indicate a periodic preferred active period of the target object in the interactive application.

2. The method according to claim 1, characterized in that The determining, based on the activity data, a first activity concentration corresponding to the first time period includes: Calculating, based on the activity data, a first cumulative active duration of the target object logging into the interactive application in the first time period, and a second cumulative active duration of the target object logging into the interactive application in each second time period; Filtering the highest second cumulative active duration from the second cumulative active durations corresponding to the second time periods as the target cumulative duration; The proportion of the target cumulative duration in the first cumulative activity duration is used as the first activity concentration.

3. The method according to claim 1, characterized in that The single activity is a single activity duration corresponding to a single login; and the second activity concentration corresponding to the second time period is obtained by the following steps, including: Calculating, based on the activity data, a second cumulative active duration of the target object logging into the interactive application in each second time period; Performing statistical processing on the second accumulated active duration corresponding to each second time period to obtain a statistical active duration corresponding to the second time period; Filter out the highest single active duration in the first time period as the target single active duration; The ratio of the target single active duration to the statistical active duration is used as the second activity concentration.

4. The method according to claim 1, wherein The interactive application is any application in the application group; and obtaining target object data of the target object interacting with the interactive application within the third time period includes: Obtaining object attribute information of the target object logging into the interactive application within the third time period, activity-related data of the target object logging into the interactive application within the third time period, and activity-related data of the target object participating in an activity based on the interactive application within the third time period; The object attribute information, the activity-related data, and the activity-related data are used as the target object data.

5. The method according to any one of claims 1 to 4, characterized in that The predicting the activity preference of the target object in the interactive application based on the target object data to obtain the corresponding activity preference level of the target object in the interactive application includes: Performing missing value repair, discretization, and normalization processing on the target object data in sequence to obtain target interactive correlation data; The target interaction association data is input into a logistic regression model to predict the active preference of the target object in the interactive application, and obtain the corresponding active preference degree of the target object in the interactive application.

6. The method according to claim 1, characterized in that The determining, based on the first activity concentration, the second activity concentration, and the activity preference level, the activity period preference information corresponding to the target object includes: Obtaining an activity preference probability based on the first activity concentration, the second activity concentration, and the activity preference degree; Obtaining a correspondence between an active preference probability range and an active preference period; the periodic interval of the active preference period is the first time period; According to the corresponding relationship, an active preference time period corresponding to the active preference probability range within which the active preference probability lies is determined as the active period preference information.

7. The method according to claim 6, characterized in that Obtaining an activity preference probability based on the first activity concentration, the second activity concentration, and the activity preference degree includes: The product of the first activity concentration, the second activity concentration, and the activity preference degree is used as the activity preference probability.

8. A device for determining an active period preference, characterized in that: include: A first acquisition module is used to acquire activity data generated by the target object based on the interactive application within a first time period; The first time period is composed of a second time period that occurs periodically; a concentration determination module, configured to determine a first activity concentration corresponding to the first time period and a second activity concentration corresponding to the second time period based on the activity data; The first activity concentration is used to represent the distribution and concentration of activity in the second time period within the first time period, and the second activity concentration is used to represent the distribution and concentration of a single activity in the first time period within the second time period; A second acquisition module is configured to acquire target object data of the target object interacting with the interactive application within a third time period; The first time period belongs to the third time period; an activity preference degree prediction module, configured to predict the activity preference of the target object in the interactive application based on the target object data, and obtain the activity preference degree corresponding to the target object in the interactive application; an activity period preference determining module, configured to determine activity period preference information corresponding to the target object based on the first activity concentration, the second activity concentration, and the activity preference degree; The active period preference information is used to indicate a periodic preferred active period of the target object in the interactive application.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining the active period preference according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method for determining an active period preference according to any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, cause the computer to perform the method for determining the active period preference according to any one of claims 1 to 7.

Images