Multi-channel feature prediction method and device based on hierarchical mobility

Abstract

The invention relates to a hierarchical mobility-based multi-channel feature prediction method and device, electronic equipment, a computer readable medium and a computer program product. The method comprises the following steps: determining a current hierarchy of a user; obtaining a historical hierarchy of the user; determining the hierarchy migration degree of the user according to the hierarchy time sequence change conditions of the current hierarchy and the historical hierarchy; and when the change amplitude or the change rule of the hierarchical migration degree meets a preset strategy, determining that the user has a multi-channel feature. According to the hierarchical migration-based multi-channel feature prediction method and device, the electronic equipment, the computer readable medium and the computer program product, the hierarchy of the user can be more accurately mastered, and whether the user has interaction behaviors of other platforms or not is determined, so that the user monitoring effect and the service quality are improved, and the system security is improved.

Description

Technical Field

[0001] This application relates to the field of computer information processing, and more specifically, to a method, apparatus, electronic device, computer-readable medium, and computer program product for predicting multi-channel features based on hierarchical mobility. Background Technology

[0002] Multichannel characteristics typically refer to the behavior of users simultaneously participating, consuming, or communicating through multiple platforms, systems, or services. This phenomenon is widespread in various fields such as retail, e-commerce, social media, entertainment, and education.

[0003] In retail and e-commerce, multichannel characteristics refer to consumers making purchases simultaneously across multiple shopping channels, such as frequent interactions and purchases between physical stores, official websites, mobile apps, social media platforms, or third-party e-commerce platforms. In social media or content platforms, multichannel characteristics refer to users simultaneously publishing, consuming, or interacting with content across multiple platforms. For example, a user might consume and create content across multiple short video platforms. In education, multichannel characteristics refer to students switching between multiple learning platforms, courses, and devices to obtain a comprehensive learning experience.

[0004] Identifying users' multi-channel behavioral characteristics helps businesses better understand their users, provide personalized experiences, optimize marketing effectiveness, and improve customer loyalty. Integrating cross-channel data through technological means allows businesses to achieve more efficient operations, services, and decision-making, thereby gaining an advantage in a highly competitive market; however, there is currently no relevant technological research in this area.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] In view of this, this application provides a method, apparatus, electronic device, computer-readable medium, and computer program product for multi-channel feature prediction based on hierarchical mobility, which can more accurately grasp the user's hierarchy, determine whether the user has interactive behavior on other platforms, thereby improving the accuracy of monitoring and processing, the quality of user service, and the security of the system.

[0007] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0008] According to one aspect of this application, a multi-channel feature prediction method based on hierarchical mobility is proposed. The method includes: determining the user's current level; obtaining the user's historical level; determining the user's hierarchical mobility based on the hierarchical temporal changes of the current level and the historical level; and determining that the user has multi-channel features when the change magnitude or change pattern of the hierarchical mobility meets a preset strategy.

[0009] Optionally, determining the user's current level includes: obtaining the current overall information of all users; obtaining the current user information of the user; and determining the user's current level through the current user information and the current overall information.

[0010] Optionally, obtaining the current overall information of all users includes: obtaining user information of all users; and integrating the user information of all users to generate the current overall information.

[0011] Optionally, determining the user's current level using the current user information and the current overall information includes: determining a ranking index for the current level; generating user metrics by statistically analyzing the current user information based on the ranking index; generating overall metrics by statistically analyzing the current overall information based on the ranking index; and determining the user's current level based on the user metrics and the overall metrics.

[0012] Optionally, determining the user's current level based on the user metrics and the overall metrics includes: determining the number of levels; dividing the overall metrics according to the number of levels to generate multiple level intervals; and taking the level interval into which the user metrics fall as the user's current level.

[0013] Optionally, obtaining the user's historical level includes: determining multiple historical time points; obtaining the overall historical information of all historical users at the multiple historical time points; obtaining the historical user information of the user at the multiple historical time points; and determining the user's historical level through the historical user information at the multiple historical time points and the overall historical information.

[0014] Optionally, determining the user's historical level using the historical user information and the overall historical information at multiple historical time points includes: generating multiple historical time levels for the user using the historical user information and the overall historical information at multiple historical time points; and determining the user's historical level based on the average value of the multiple historical time levels.

[0015] Optionally, determining the user's historical level through the historical user information and the overall historical information at multiple historical time points includes: generating multiple historical time levels for the user through the historical user information and the overall historical information at multiple historical time points; arranging the multiple historical time levels according to time; and generating the user's historical level in a time series format through the sorted multiple historical time levels.

[0016] Optionally, determining the user's level migration degree based on the hierarchical temporal changes of the current level and the historical level includes: generating a level migration amplitude based on the current level and the historical level to determine the user's level migration degree; and / or generating a level migration function based on the current level and the historical level to determine the user's level migration degree.

[0017] According to one aspect of this application, a multi-channel feature prediction device based on hierarchical mobility is proposed. The device includes: a current module for determining the current level of a user; a history module for acquiring the historical levels of the user; a level module for determining the hierarchical mobility of the user based on the hierarchical temporal changes of the current level and the historical levels; and a strategy module for determining that the user has multi-channel features when the magnitude or pattern of the change in hierarchical mobility meets a preset strategy.

[0018] According to one aspect of this application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the method as described above.

[0019] According to one aspect of this application, a computer-readable medium is provided having a computer program stored thereon that, when executed by a processor, implements the method described above.

[0020] According to one aspect of this application, a computer program product is provided, comprising: a computer program / instructions that, when executed by a processor, implement the method as described above.

[0021] According to the multi-channel feature prediction method, apparatus, electronic device, computer-readable medium, and computer program product based on hierarchical mobility of this application, by determining the user's current level; obtaining the user's historical level; determining the user's hierarchical mobility based on the hierarchical temporal changes of the current level and the historical level; and determining the existence of multi-channel features of the user when the change amplitude or change pattern of the hierarchical mobility meets the preset strategy, the user's hierarchical level can be more accurately grasped, and it can be determined whether the user has interactive behavior on other platforms, thereby improving the monitoring and processing effect, improving the quality of user services, and enhancing system security.

[0022] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0023] The above and other objects, features, and advantages of this application will become more apparent from the detailed description of exemplary embodiments with reference to the accompanying drawings. The drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0024] Figure 1 This is a flowchart illustrating a multi-channel feature prediction method based on hierarchical mobility according to an exemplary embodiment.

[0025] Figure 2 This is a flowchart illustrating a multi-channel feature prediction method based on hierarchical mobility, according to another exemplary embodiment.

[0026] Figure 3 This is a flowchart illustrating a multi-channel feature prediction method based on hierarchical mobility, according to another exemplary embodiment.

[0027] Figure 4 This is a block diagram illustrating a multi-channel feature prediction device based on hierarchical mobility, according to an exemplary embodiment.

[0028] Figure 5 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0029] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this application will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0030] Figure 1 This is a flowchart illustrating a multi-channel feature prediction method based on hierarchical mobility according to an exemplary embodiment. The multi-channel feature prediction method 10 based on hierarchical mobility includes at least steps S102 to S108.

[0031] like Figure 1 As shown, in S102, the user's current level is determined. For example, this can be done by obtaining the current overall information of all users; obtaining the current user information of the user; and determining the user's current level using the current user information and the current overall information.

[0032] More specifically, it can obtain overall information about all users (such as the purchases and activity levels of the user group) as well as specific information about individual users (such as a user's current purchasing behavior or engagement). By comparing this information, users can be categorized into a specific tier, such as Top 10%, Top 30%, etc.

[0033] In specific application scenarios, on e-commerce platforms, users may be divided into different consumption tiers (such as "Gold Member" and "Silver Member"). By obtaining a user's recent purchase history, spending amount, and participation in activities, the user can be positioned at the current "Gold Member" tier.

[0034] In specific application scenarios, on short video platforms, users may be categorized into "regular users," "active users," and "creators" based on factors such as viewing time, interaction frequency, and the number of videos posted. Based on a user's recent viewing and interaction behavior, the platform can determine if they currently belong to the "active user" category.

[0035] In S104, the user's historical level is obtained. For example, multiple historical time points are determined; the overall historical information of all historical users at the multiple historical time points is obtained; the historical user information of the user at the multiple historical time points is obtained; and the user's historical level is determined by the historical user information at the multiple historical time points and the overall historical information.

[0036] For example, you can identify key historical time points (such as last month, last quarter, etc.) and obtain overall information about all users at that time (such as average spending or activity levels), while also obtaining personal information about target users at those time points (such as past purchase amounts or interaction data). By analyzing this data, you can determine which level the user belongs to at each historical time point.

[0037] More specifically, in real-world applications, a user's spending behavior may fluctuate significantly over the past few months; for example, two months ago they were a "Silver Member," and a month ago they were promoted to a "Gold Member." This tiered historical record allows for clear tracking of the user's past spending behavior.

[0038] More specifically, in real-world application scenarios, a user's activity level on a short video platform may also change. For example, two months ago he was a "regular user," but due to uploading a large number of videos or watching content recently, he was promoted to an "active user" a month ago.

[0039] In S106, the user's level migration degree is determined based on the time-series changes in the current level and the historical levels. For example, a level migration amplitude can be generated based on the current level and the historical levels to determine the user's level migration degree; alternatively, a level migration function can be generated based on the current level and the historical levels to determine the user's level migration degree.

[0040] More specifically, the migration magnitude can be calculated by comparing the current tier with the historical tier. For example, a user moving from the Top 30% to the Top 10% indicates a significant migration magnitude.

[0041] More specifically, a transfer function could be, for example, a hierarchical transfer function used to quantify the trend of a user's hierarchical changes over a period of time. This function can take into account factors such as the speed, frequency, and direction of hierarchical changes.

[0042] In step S108, when the magnitude or pattern of change in the hierarchical migration degree meets a preset strategy, it is determined that the user exhibits multi-channel characteristics. Enterprises can set certain strategic conditions (such as specific hierarchical migration degrees, user frequency across multiple channels, etc.). When these conditions are met, the system will identify that the user may have interacted across multiple channels. For example, a user's consumption level on an e-commerce platform may rapidly increase because they not only shop online but also through mobile applications and offline stores.

[0043] In real-world applications, users' spending on e-commerce platforms has increased frequently, with their membership level jumping from "Silver Member" to "Gold Member." By analyzing users' spending records across multiple channels, the system discovered that these users not only shopped online but also completed purchases through mobile applications and offline stores, indicating that they exhibit multi-channel behavioral characteristics.

[0044] In real-world applications, users are spending more time watching content on short video platforms and uploading videos more frequently, with their tier rapidly shifting from "ordinary user" to "creator." Further analysis reveals that this user not only frequently watches videos on mobile apps but also interacts on other devices (such as tablets and PCs), demonstrating multi-channel behavioral characteristics.

[0045] The steps described above calculate the user's tier migration degree by comparing their current tier with their historical tier, thereby determining whether the user exhibits multi-channel characteristic behavior. This method allows businesses to better identify users active across multiple channels and optimize their marketing or services based on these users' migration trends.

[0046] According to the multi-channel feature prediction method based on hierarchical mobility of this application, by determining the user's current level; obtaining the user's historical level; determining the user's hierarchical mobility based on the hierarchical temporal changes of the current level and the historical level; and determining the user's multi-channel features when the change magnitude or change pattern of the hierarchical mobility meets the preset strategy, the method can more accurately grasp the user's level, determine whether the user has interactive behavior on other platforms, thereby improving user service quality and enhancing system security.

[0047] It should be clearly understood that this application describes how specific examples are formed and used, but the principles of this application are not limited to any details of these examples. Rather, based on the teachings of the disclosure of this application, these principles can be applied to many other embodiments.

[0048] Figure 2 This is a flowchart illustrating a multi-channel feature prediction method based on hierarchical mobility, according to another exemplary embodiment. Figure 2 The process shown in step 20 is... Figure 1 The flowchart shown includes a detailed description of step S102, "Determine the user's current level." Each step will be explained in detail below, with examples from financial scenarios (such as multiple borrowing).

[0049] like Figure 2 As shown, in S202, the current overall information of all users is obtained. For example, the user information of all users is obtained; the user information of all users is integrated to generate the current overall information.

[0050] It can obtain relevant data from all users on the platform, typically including user account information, transactions, borrowing, repayments, and other related behaviors. By integrating this data, an information database reflecting the overall user status can be generated, known as "current overall information." This is similar to building a global benchmark for subsequent comparisons with individual users.

[0051] In S204, the system obtains the user's current user information. For each individual user, the system obtains their personal information, including borrowing behavior, repayment records, account activity, etc. This data will be used for subsequent hierarchical calculations; by comparing it with the overall information, the system determines the user's specific hierarchical level.

[0052] In S206, the user's current level is determined using the current user information and the current overall information. For example, a ranking metric for the current level can be determined; user metrics can be generated by statistically analyzing the current user information based on the ranking metric; overall metrics can be generated by statistically analyzing the current overall information based on the ranking metric; and the user's current level can be determined based on the user metrics and the overall metrics.

[0053] In one specific embodiment, key indicators for evaluating user tiers can be determined. These indicators may include the user's borrowing amount, repayment frequency, and number of borrowings in the financial sector. Based on these indicators, the user's information is statistically analyzed to generate "user indicators," and corresponding information for the entire user group is statistically analyzed to generate "overall indicators." Depending on the number of tiers, the overall indicators are divided into different intervals, such as Top 10%, Top 30%, etc. The tier interval in which a user belongs is their current tier.

[0054] More specifically, determining the user's current level based on the user metrics and the overall metrics includes: determining the number of levels; dividing the overall metrics according to the number of levels to generate multiple level intervals; and taking the level interval into which the user metrics fall as the user's current level.

[0055] In one specific implementation, the number of user tiers can be determined based on platform needs. For example, users can be divided into multiple tiers such as Top 10%, Top 30%, and Top 50%. Then, various metrics of the overall user base (such as total loan amount and credit score) are divided into multiple tier ranges. For instance, users in the top 10% of loan amounts are assigned to the highest tier, those in the 30%-50% tier are assigned to the middle tier, and those in the 50%-100% tier are assigned to the lowest tier. Finally, based on specific user metrics (such as loan amount and repayment history), users are assigned to the corresponding tier ranges.

[0056] In financial scenarios, multi-channel characteristics can manifest as multi-entity behavior, meaning that users simultaneously hold loans or credit accounts with multiple financial institutions. Using the methods described above, companies can identify user behavior patterns across multiple channels (such as banks, consumer finance companies, etc.).

[0057] The method described in this application can effectively acquire overall data for all users and specific data for individual users, and determine the user's current tier by comparison. In financial scenarios, based on these tier assessments, the platform can identify whether a user exhibits multi-channel characteristics such as multiple borrowing. This method not only helps financial institutions identify high-risk users with high security risks but also provides a foundation for multi-channel user behavior analysis, thereby enabling the development of corresponding risk control strategies.

[0058] Figure 3 This is a flowchart illustrating a multi-channel feature prediction method based on hierarchical mobility, according to another exemplary embodiment. Figure 3 The process shown in step 30 is... Figure 1 The flowchart shown provides a detailed description of step S104, "Obtain the user's historical level".

[0059] like Figure 3As shown in S302, multiple historical time points are defined. Important historical time points can be set, such as one month ago, three months ago, six months ago, or one year ago. These time points allow for the analysis of changes in user behavior over different time periods.

[0060] In step S304, the overall historical information of all historical users at the multiple historical time points is obtained. For each historical time point, overall information of all users is obtained, such as the total loan amount and delinquency rate of all users at that time. This overall historical information provides a global reference for subsequent hierarchical division.

[0061] In step S306, the historical user information of the user at the multiple historical time points is obtained. Specific data for the user at these historical time points is obtained, such as total loan amount and overdue payment status. This data helps to understand the user's financial situation at each past point in time.

[0062] In S308, the user's historical level is determined by the historical user information at multiple historical time points and the overall historical information.

[0063] In one embodiment, determining the user's historical level using historical user information and overall historical information at multiple historical time points includes: generating multiple historical time levels for the user using historical user information and overall historical information at multiple historical time points; and determining the user's historical level based on the average value of the multiple historical time levels.

[0064] More specifically, the system can obtain a user's specific tier at different points in time (such as monthly, quarterly, etc.). Each point in time generates a user's tier value, called the "historical time tier." These historical time tiers are statistically analyzed, and their average value is calculated to determine the user's historical tier. This average value reflects the user's overall tier performance over a certain period.

[0065] This method is more suitable for assessing a user's stability or long-term performance. For example, if a user has experienced significant fluctuations over a period of time, but their overall tier tends to be at the median, calculating the average of their tiers can help understand their overall historical performance.

[0066] In one embodiment, determining the user's historical level using historical user information and overall historical information at multiple historical time points includes: generating multiple historical time levels for the user using historical user information and overall historical information at multiple historical time points; arranging the multiple historical time levels according to time; and generating the user's historical level in a time series format using the sorted multiple historical time levels.

[0067] More specifically, the user's tier can be calculated at each historical point in time, generating multiple historical time tiers. These historical time tiers are then arranged chronologically to form a time series. Using the arranged tier data, the system can generate a historical tier record with time as the axis. This time series can intuitively reflect the changing trends of user tiers.

[0068] This method is more suitable for analyzing fluctuations in user tiers, especially changes in user tiers over time. Through this time series data, it's clear whether a user's tier gradually rises, falls, or experiences significant fluctuations.

[0069] Those skilled in the art will understand that all or part of the steps of the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, it performs the functions defined by the method provided in this application. The program can be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk, or an optical disk.

[0070] Furthermore, it should be noted that the above figures are merely illustrative representations of the processes included in the method according to exemplary embodiments of this application, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0071] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0072] Figure 4 This is a block diagram illustrating a multi-channel feature prediction device based on hierarchical mobility, according to an exemplary embodiment. Figure 4 As shown, the multi-channel feature prediction device 40 based on hierarchical mobility includes: a current module 402, a history module 404, a hierarchical module 406, and a strategy module 408.

[0073] The current module 402 is used to determine the user's current level; the current module 402 is also used to obtain the current overall information of all users; obtain the current user information of the user; and determine the user's current level through the current user information and the current overall information.

[0074] The history module 404 is used to obtain the user's historical level; the history module 404 is also used to determine multiple historical time points; obtain the overall historical information of all historical users at the multiple historical time points; obtain the historical user information of the user at the multiple historical time points; and determine the user's historical level through the historical user information at the multiple historical time points and the overall historical information.

[0075] The hierarchy module 406 is used to determine the user's hierarchy migration degree based on the hierarchical time sequence changes of the current hierarchy and the historical hierarchy; the hierarchy module 406 is also used to generate a hierarchy migration amplitude based on the current hierarchy and the historical hierarchy to determine the user's hierarchy migration degree; the hierarchy module 406 is also used to generate a hierarchy migration function based on the current hierarchy and the historical hierarchy to determine the user's hierarchy migration degree.

[0076] The strategy module 408 is used to determine that the user has multi-channel characteristics when the change range or change pattern of the hierarchical migration degree meets the preset strategy.

[0077] According to the multi-channel feature prediction device based on hierarchical mobility of this application, by determining the user's current level; obtaining the user's historical level; determining the user's hierarchical mobility based on the hierarchical temporal changes of the current level and the historical level; and determining that the user has multi-channel features when the change magnitude or change pattern of the hierarchical mobility meets the preset strategy, the device can more accurately grasp the user's level, determine whether the user has interactive behavior on other platforms, thereby improving user service quality and enhancing system security.

[0078] like Figure 5 As shown, this application provides an electronic device including a processor 510, a memory 520, and a bus, wherein the processor 510 and the memory 520 communicate with each other through the bus 540.

[0079] Memory 520 is used to store computer programs;

[0080] When the processor 510 executes the program stored in the memory 520, it implements the multi-channel feature prediction method based on hierarchical mobility of any of the above embodiments.

[0081] Communication interface 520 is used for communication between the above-mentioned electronic device and other devices.

[0082] The memory 520 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device 520. Optionally, the memory 520 may also be at least one storage device located remotely from the aforementioned processor 510.

[0083] If the methods described in this application are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms.

[0084] This application provides a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement the multi-channel feature prediction method based on hierarchical mobility of any of the above embodiments. For example, it may determine a user's current level; obtain the user's historical levels; determine the user's hierarchical mobility based on the temporal changes of the current level and the historical levels; and determine that the user possesses multi-channel features when the magnitude or pattern of the hierarchical mobility change meets a preset strategy.

[0085] Exemplary embodiments of this application have been specifically shown and described above. It should be understood that this application is not limited to the detailed structures, arrangements, or implementation methods described herein; rather, this application is intended to cover various modifications and equivalent arrangements contained within the spirit and scope of the appended claims.

Claims

1. A multi-channel feature prediction method based on hierarchical mobility, characterized in that, include: Determine the user's current level; Obtain the user's historical tier; The user's level migration degree is determined based on the time-series changes in the current level and the historical level; When the magnitude or pattern of change in hierarchical migration meets the preset strategy, it is determined that the user has multi-channel characteristics.

2. The method as described in claim 1, characterized in that, Determine the user's current level, including: Get the current overall information of all users; Obtain the current user information of the user; The user's current level is determined by the current user information and the current overall information.

3. The method as described in claim 2, characterized in that, Retrieve current overall information for all users, including: Get user information for all users; The user information of all users is integrated to generate the current overall information.

4. The method as described in claim 2, characterized in that, Determining the user's current level using the current user information and the current overall information includes: Determine the ranking criteria for the current level; User metrics are generated by statistically analyzing the current user information based on the ranking criteria. The overall index is generated by statistically analyzing the current overall information based on the ranking index. The user's current level is determined based on the user metrics and the overall metrics.

5. The method as described in claim 4, characterized in that, Determining the user's current level based on the user metrics and the overall metrics includes: Determine the number of levels; The overall indicator is divided according to the number of levels, generating multiple level intervals; The level range into which the user's metrics fall is taken as the user's current level.

6. The method as described in claim 1, characterized in that, Obtaining the user's historical hierarchy includes: Identify multiple historical time points; Obtain the overall historical information of all historical users at the multiple historical time points; Obtain the historical user information of the user at the multiple historical time points; The user's historical level is determined by combining the historical user information from multiple historical time points with the overall historical information.

7. The method as described in claim 6, characterized in that, The user's historical hierarchy is determined by combining historical user information from multiple historical time points with the overall historical information, including: Multiple historical time levels of the user are generated by combining the historical user information from multiple historical time points and the overall historical information. The user's historical tier is determined based on the average value of the multiple historical time tiers.

8. The method as described in claim 6, characterized in that, The user's historical hierarchy is determined by combining historical user information from multiple historical time points with the overall historical information, including: Multiple historical time levels of the user are generated by combining the historical user information from multiple historical time points and the overall historical information. Arrange the multiple historical time levels according to time; The user's historical hierarchy is generated in time series format by sorting the multiple historical time levels.

9. The method as described in claim 1, characterized in that, Determining a user's level migration degree based on the time-series changes in the current level and the historical levels includes: Generate a tier migration magnitude based on the current tier and the historical tier to determine the user's tier migration degree; and / or A hierarchy migration function is generated based on the temporal changes of the current hierarchy and the historical hierarchy to determine the user's hierarchy migration degree.

10. A multi-channel feature prediction device based on hierarchical mobility, characterized in that, include: The current module is used to determine the user's current level; The history module is used to obtain the user's historical hierarchy. The hierarchy module is used to determine the user's hierarchy migration degree based on the hierarchical changes of the current hierarchy and the historical hierarchy. The strategy module is used to determine that the user has multi-channel characteristics when the change range or change pattern of the hierarchical migration degree meets the preset strategy.

11. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 9.

12. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, Includes a computer program / instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 9.

Images