User behavior simulation method and electronic device

Abstract

The embodiment of the invention provides a user behavior simulation method and an electronic device. The method comprises the following steps: generating a target user instance according to a constructed user behavior model; the user behavior is simulated in the target network through the target user instance, and the target user instance is a simulation entity of the real user behavior in the mobile network. Therefore, through the embodiment of the invention, the problems that the user behavior coverage is not comprehensive and the real user behavior cannot be effectively reflected due to the fact that the traditional simulation environment mainly depends on the manually pre-written test script when simulating the user behavior can be solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communications, and more specifically, to a user behavior simulation method and an electronic device. Background Art

[0002] With the evolution of mobile network technology, the number of users and data traffic carried by networks has increased dramatically, making the collection and analysis of user behavior data increasingly important. To improve network stability and security and accelerate the verification and deployment of new features, the industry has shown strong interest in digital twin technologies, which can efficiently and accurately simulate user behavior. By replicating real-world network environments, digital twin networks provide powerful support for network planning, function verification, fault prediction, and optimization.

[0003] However, related technologies for user behavior data collection and simulation have significant shortcomings in terms of performance, cost, security, and implementation complexity. Traditional data collection and simulation methods are particularly insufficient for modeling the massive amounts of user behavior data required for future sixth-generation mobile communication systems (6G). Therefore, there is an urgent need for a solution that can efficiently collect and process large-scale user behavior data, thereby building a more accurate and realistic digital twin network environment to support network function verification, performance optimization, and fault prediction.

[0004] In summary, no effective solution has been proposed in the related art. Summary of the Invention

[0005] The embodiments of the present application provide a user behavior simulation method and electronic device to at least solve the problem that traditional simulation environments mainly rely on manually pre-written test scripts to simulate user behavior, resulting in incomplete user behavior coverage and inability to effectively reflect real user behavior.

[0006] According to one embodiment of the present application, a user behavior simulation method is provided, comprising: generating a target user instance based on a constructed user behavior model; and simulating user behavior in a target network through the target user instance, wherein the target user instance is a simulation entity of real user behavior in a mobile network.

[0007] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.

[0008] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in the above method embodiment.

[0009] According to another embodiment of the present application, a computer program product is provided, including a computer program, which implements the steps in the above method embodiment when executed by a processor.

[0010] Through the above-mentioned embodiments of the present application, a user behavior simulation method is provided, which generates a target user instance based on the constructed user behavior model, and simulates user behavior in the target network through the target user instance, wherein the target user instance is a simulation entity of the real user behavior in the mobile network, that is, through the constructed user behavior model, a specific user object is instantiated. Compared with pre-written scripts, the user behavior model of the embodiment of the present application can cover a wider range of scenarios and user behavior types, so that the user behavior simulation in the target network can be more adaptable to and reflect the real environment, and improve the authenticity and flexibility of the simulation environment. Therefore, the embodiment of the present application can solve the problem that the traditional simulation environment mainly relies on manually pre-written test scripts when simulating user behavior, resulting in incomplete user behavior coverage and inability to effectively reflect real user behavior, thereby achieving the effect of improving the efficiency of user behavior simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 1 is a hardware structure block diagram of a computer terminal according to a user behavior simulation method according to an embodiment of the present application;

[0012] Figure 2 This is a network architecture diagram of a method for running user behavior simulation according to an embodiment of the present application;

[0013] Figure 3 is a flow chart of a user behavior simulation method according to an embodiment of the present application;

[0014] Figure 4 This is a schematic diagram of the process of collecting user service data according to an embodiment of the present application;

[0015] Figure 5 This is a schematic diagram of the process of collecting user signaling data according to an embodiment of the present application;

[0016] Figure 6 This is a flow chart of collecting user service data and user signaling data according to an embodiment of the present application;

[0017] Figure 7 This is a flow chart of simulating user behavior based on a test instrument according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0019] It should be noted that the terms "first", "second", etc. in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0020] The user behavior model constructed in the embodiment of the present application includes but is not limited to applying the following networks: a digital twin network and a test network.

[0021] The digital twin network of the embodiments of the present application includes but is not limited to applications in 5G twin networks and future 6G twin networks.

[0022] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 : is a hardware structure block diagram of a computer terminal according to the user behavior simulation method of an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data. The computer terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0023] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the user behavior simulation method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0024] The transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a communications provider of a computer terminal. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0025] In traditional simulation environments, user behavior simulation mainly relies on manually written test scripts. These test scripts are usually based on fixed assumptions and expected behavior patterns, which have the following limitations:

[0026] Incomplete coverage: Because pre-written test scripts are often based on specific scenarios or limited user behavior data, they may not fully cover all potential user behaviors and scenarios. This is especially true for atypical or edge cases, which may result in a low match between simulation results and the actual network environment.

[0027] Inability to reflect real user behavior: User behavior on the real web is dynamic and changeable, influenced by numerous factors such as time, location, and personal preferences. Pre-written scripts struggle to capture the complexity and randomness of user behavior, resulting in simulations that often lack realism and fail to reflect the diversity and complexity of user behavior.

[0028] In view of the above problems, the embodiments of the present application propose a modeling method based on large-scale user behavior data. By collecting large-scale user behavior data and constructing a user behavior model based on multi-dimensional cluster analysis, and then combining it with test instruments to generate user equipment (UE) with real user behavior characteristics of the live network, the accuracy and comprehensiveness of user behavior simulation in the simulation environment are significantly improved. Specifically, the modeling method based on large-scale user behavior data includes the following three parts:

[0029] 1. Collecting large-scale user behavior data based on the data plane

[0030] The embodiments of the present application are based on the data plane or data service to collect large-scale user behavior data in real time and efficiently; further, for user signaling data, real-time collection is performed through the Access and Mobility Management Function (AMF) in the production network; for user service data, real-time collection is performed through the User Plane Function (UPF).

[0031] 2. Build a user behavior model based on the collected large-scale user behavior data

[0032] After collecting large amounts of user behavior data, clustering algorithms are used to cluster the user behavior data according to clustering dimensions, thereby building a user behavior model. Clustering dimensions include but are not limited to the following:

[0033] (1) Time dimension: Grouping users with similar time patterns together;

[0034] (2) Tracking Area (TA): Also known as the location dimension, it groups users with the same location together;

[0035] (3) Slice dimension: grouping users with the same slice together;

[0036] (4) Access Point Name (APN): Also known as the network type dimension, it groups users with the same network type together.

[0037] Furthermore, when clustering user behavior data according to clustering dimensions, the clustering dimensions can be superimposed to cluster the user behavior data. For example, according to the time dimension and the slice dimension, users with similar time patterns and the same slices are clustered together.

[0038] 3. Instantiate specific UE objects in conjunction with test instruments

[0039] Based on the user behavior model constructed above and combined with test instrumentation, a UE with the behavioral characteristics of real users in the live network is generated. This UE can dynamically adjust its signaling interaction and service flow behavior to more accurately replicate user behavior. Compared to traditional test instruments that rely on pre-written static test scripts, the signaling interaction and service flow behavior of the embodiments of the present application are more flexible.

[0040] Through the above embodiment, large-scale user behavior data is collected in real time through AMF and UPF, and a user behavior model is constructed based on multi-dimensional clustering analysis. Then, combined with test instruments, a UE with real user behavior characteristics of the existing network is generated, and the UE object is connected to the digital twin network or test network to simulate real user behavior in the field, thereby building a highly realistic twin environment to support scenarios such as new function verification, upgrade verification, and configuration change verification of network elements.

[0041] Figure 2 is a network architecture diagram of a method for running user behavior simulation according to an embodiment of the present application, such as Figure 2 As shown in FIG, the network architecture of the user behavior simulation method includes the following network components:

[0042] 1. Twin Network

[0043] User Equipment Management (UEM): collects user behavior data for cluster analysis, builds user behavior models, and integrates with test instruments to simulate UE behavior in the digital twin network.

[0044] Testing Instrument: Based on the user behavior model provided by the UEM, it simulates UE behavior, generates user signaling data and user service data, and interacts with other network elements in the digital twin network to test network performance and functions.

[0045] Access and Mobility Management Function (AMF): Handles UE registration, authentication, security context management, and mobility management. It interacts with instruments in the twin network, simulates UE access and mobility behavior, and supports user behavior simulation.

[0046] Session Management Function (SMF): This function manages sessions, including session establishment, modification, and release, and collaborates with the UPF and PCF to ensure data transmission. In a twin network, it processes UE session requests simulated by the instrument to ensure accurate session management.

[0047] Unified Data Management (UDM): This is used to store and manage user subscription and authentication data, such as user IDs, subscription information, and authentication credentials. In a twin network, this ensures the consistency and authenticity of user data and supports behavioral verification of simulated UEs.

[0048] User Plane Function (UPF): Responsible for forwarding user data packets, implementing packet encapsulation, decapsulation, routing, and forwarding. It forwards service data generated by instruments in the twin network, simulating user data flows in a real network.

[0049] Policy Control Function (PCF): Provides policy rule information to guide the SMF and UPF on how to implement traffic control, network access policies, etc. This ensures that data processing in the production network and the twin network follows established policies, supports policy consistency in user behavior simulation, and thus improves the accuracy and effectiveness of the simulation.

[0050] 2. Production Network

[0051] User Equipment (UE): For example, mobile phones and smart terminals are the end users of network services, initiating signaling interactions and exchanging service data. The behavioral data of real users in production networks is the foundation for building user behavior models.

[0052] Radio Access Network (RAN): provides wireless connectivity between UE and the core network, including signal transmission and access control.

[0053] Access and Mobility Management Function (AMF): Handles UE registration, authentication, security context management, and mobility management. It monitors UE mobility and access status in production networks and collects user signaling data.

[0054] Session Management Function (SMF): This function manages sessions, including session establishment, modification, and release, and collaborates with the UPF and PCF to ensure data transmission. In production networks, it tracks UE session activity and provides data transmission strategies to the UPF.

[0055] Unified Data Management (UDM): This is used to store and manage user subscription and authentication data, such as user IDs, subscription information, and authentication credentials. It provides user data query services for AMF and SMF in production networks, supporting user authentication and service activation.

[0056] User Plane Function (UPF): Responsible for forwarding user data packets, implementing packet encapsulation, decapsulation, routing, and forwarding. It collects UE service data flows in production networks and provides a foundation for user service behavior analysis for the UEM.

[0057] Policy Control Function (PCF): Provides policy rule information to guide the SMF and UPF on how to implement traffic control, network access policies, etc. This ensures that data processing in the production network and the twin network follows established policies, supports policy consistency in user behavior simulation, and thus improves the accuracy and effectiveness of the simulation.

[0058] The AMF / SMF / UDM / UPF / PCF mentioned above are similar to the components of the same name in the twin network, but in the production network, these components are used to process real user requests and control and manage real-time network services.

[0059] Data Control Function (DCF): Responsible for the control and coordination of data services, including the issuance of data collection and storage tasks.

[0060] Data Repository Function (DRF): Responsible for storing collected user behavior data, including user signaling data and user business data, and persistently storing it for use in UEM analysis.

[0061] Through the network architecture of the user behavior simulation method of the embodiment of the present application, UEM generates and manages user behavior models in the twin network through user behavior data collected from the production network, and simulates real user behavior in combination with instruments, and interacts with other components in the twin network (AMF, SMF, UDM, UPF and PCF) to perform new function verification, network performance upgrade verification, configuration change verification, etc. Therefore, the user behavior simulation method under this network architecture can not only avoid the impact on real user services in the production network, but also provide accurate simulation of large-scale user behavior in the twin environment.

[0062] like Figure 2 As shown, based on the network architecture of the user behavior simulation method, the overall process of the user behavior simulation method of the embodiment of the present application includes the following steps:

[0063] 1. Based on the data plane or data service, collect large-scale user behavior data in the production network in real time;

[0064] 2. Based on the collected large-scale user behavior data, a user behavior model is constructed using clustering algorithms;

[0065] 3. Based on the constructed user behavior model and combined with test instruments, a UE with the real user behavior characteristics of the existing network is generated.

[0066] Figure 3 is a flow chart of a user behavior simulation method according to an embodiment of the present application. Figure 3 As shown, the user behavior simulation process includes the following steps:

[0067] Step S302: Generate a target user instance based on the constructed user behavior model;

[0068] In this embodiment, the user behavior model can be combined with the test instrument to generate a UE with the real user behavior characteristics of the existing network, that is, the target user instance. The UE instance of this embodiment is not generated according to a fixed script or preset logic, but is generated dynamically in real time according to the user behavior model, thereby constructing a highly realistic user behavior simulation environment.

[0069] In some embodiments, before generating the target user instance according to the constructed user behavior model, the method further includes: acquiring user data, wherein the user data includes at least one of the following: user service data, user signaling data.

[0070] In this embodiment, the user service data is obtained from the production network through at least one user plane functional device, and the user signaling data is obtained from the production network through at least one access and mobility management functional device.

[0071] In this embodiment, user data (user behavior data) must be obtained before constructing a user behavior model, where the user behavior data includes user service data and user signaling data. The user signaling data can be used to analyze the user's mobility behavior (for example, location changes, switching, etc.), and the user service data can be used to analyze the type of service accessed by the user (for example, video streaming, web browsing, instant messaging, etc.).

[0072] In some embodiments, the traditional user data collection method is mainly based on: collection based on the network management platform, collection based on the optical division method, or collection based on the real user traffic of the existing network, and the user service data collection of the embodiment of the present application is usually processed by at least one UPF, for example, user service data is collected by UPF1 and UPF2. After UPF1 receives the user service data collection task, it extracts 0.1% of users for service data collection according to the collection rules. Specifically, when the extracted 0.1% users initiate a service operation (for example: video streaming, web browsing, instant messaging), UPF1 collects service data according to the collection rules. User business messages are saved in units of flows, and UPF1 extracts summary data or complete data, user address, timestamp, etc. from user business messages and reports them for storage; similarly, after UPF2 receives the user business data collection task, it extracts 0.1% of users for business data collection according to the collection rules. Specifically, when the extracted 0.1% users initiate a business operation (for example: video streaming, web browsing, instant messaging), UPF2 saves user business messages in units of flows, and UPF2 extracts summary data or complete data, user address, timestamp, etc. from user business messages and reports them for storage.

[0073] In some embodiments, user signaling data collection is typically processed through at least one AMF. For example, user signaling data is collected through AMF1 and AMF2. After receiving a user signaling data collection task, AMF1 selects 0.1% of users for signaling data collection based on collection rules. Specifically, when the 0.1% of users selected initiate a signaling operation (e.g., registration, location update, handover, session establishment, etc.), AMF1 extracts key information from the user signaling data, including but not limited to the signaling type, timestamp, and user ID. Similarly, after receiving a user signaling data collection task, AMF2 selects 0.1% of users for signaling data collection based on collection rules. Specifically, when the 0.1% of users selected initiate a signaling operation (e.g., registration, location update, handover, session establishment, etc.), AMF2 extracts key information from the user signaling data, including but not limited to the signaling type, timestamp, and user ID. Through at least one AMF, user signaling data can be collected in real time or on a scheduled basis, providing time series information on user network behavior.

[0074] In some embodiments, obtaining user data includes: sending a user data acquisition request to a production network; wherein the user data acquisition request includes at least one of the following parameters: user data collection type, user data collection range, user data collection rules, user data collection start time, user data collection end time, and user data storage location, wherein the user data storage location is a storage location queried from the production network or a storage location allocated from the production network; in response to the user data acquisition request, obtaining user data from the production network.

[0075] In this embodiment, after receiving the user data acquisition request sent by the twin network, the production network performs the user behavior data collection task according to the user data acquisition request, wherein the user data acquisition request carries the following parameters: user data collection type, user data collection range, user data collection rules, user data collection start time, user data collection end time and user data storage location.

[0076] In this embodiment, if a user data service query request sent by the twin network is received before a user data acquisition request sent by the twin network is received, the user data storage location is determined to be the storage location queried from the production network in response to the user data service query request; if a user data service query request sent by the twin network is not received before a user data acquisition request sent by the twin network is received, the user data storage location is determined to be the storage location allocated from the production network.

[0077] In some embodiments, Figure 4 FIG. 1 is a flow chart of collecting user service data according to an embodiment of the present application. Figure 4As shown, user service data is collected from the production network through at least one UPF device. The user service data collection process includes the following steps:

[0078] S401a. DRF initiates a data service registration request to DCF, where the registration type is data storage service registration, indicating that DRF can provide user behavior data storage service.

[0079] S401b. UPF1 initiates a data service registration request to DCF, where the registration type is user business data collection service registration, indicating that UPF1 provides user business data collection services.

[0080] S401c. UPF2 initiates a data service registration request to DCF, where the registration type is user business data collection service registration, indicating that UPF2 provides user business data collection services.

[0081] S402 (optional): The UEM of the twin network initiates a data service query request to the DCF. The data service query request carries the following parameters:

[0082] a. Query type: User business data collection service and data storage service.

[0083] S403 (optional): DCF returns the data service query request result to UEM. The data service query request result is as follows:

[0084] a. User business data collection service: UPF1, UPF2.

[0085] b. Data storage service: DRF.

[0086] S404: UEM initiates a data request to DCF. The data request includes the following parameters:

[0087] (1) Data collection type: indicates whether the collected data is user signaling data or user service data, or both user signaling data and user service data.

[0088] (2) Data collection scope: Indicates on which UPFs user service data collection is performed. The indication content can be a network element identifier or a wildcard rule.

[0089] (3) Data collection rules: Indicates which users’ business data are collected. The indication content can be user identification (such as IMSI / IMEI), or filtering rules (such as by APN / slice, etc.) or sampling rules (such as proportional sampling).

[0090] (4) Data collection start time: Indicates when the user's business data collection task needs to start collecting data.

[0091] (5) Data collection end time: Indicates when the user's business data collection task needs to end.

[0092] (6) Data storage location: Indicates on which DRF the user's business data is stored.

[0093] For example, the parameters carried in the data request are as follows:

[0094] (1) Data collection type: user business data.

[0095] (2) Data collection scope: UPF1 (can be determined based on the results of the S403 data service query request).

[0096] (3) Data collection rules: Sampling is conducted at a rate of 0.1%.

[0097] (4) Data collection start time: 2025.3.10 00:00:00.

[0098] (5) Data collection end time: 2025.3.15 00:00:00.

[0099] (6) Data storage location: DRF (can be determined based on the result of the S403 data service query request).

[0100] S405a: After receiving the data request, DCF sends a data storage task to DRF.

[0101] S405b. After receiving the data request, DCF sends a user service data collection task to UPF1, carrying data collection parameters.

[0102] S405c: After receiving the data request, DCF sends a user service data collection task to UPF2, carrying data collection parameters.

[0103] S406. The DCF returns the determined DRF data storage address to the UEM, so that the UEM can communicate directly with the DRF.

[0104] After S407a / S407b and UPF1 / UPF2 receive the user business collection task, they extract 0.1% of users for business data collection according to the collection rules. Specifically, when the extracted 0.1% users initiate a business operation (for example: video streaming, web browsing, instant messaging), UPF1 / UPF2 saves the user business message in units of streams, and UPF1 extracts the summary data or complete data, user address, timestamp, etc. in the user business message, and reports it to DRF for storage. The reporting method can be immediate reporting or cached timed reporting.

[0105] Among them, the format of user service data is shown in Table 1:

[0106] Table 1

[0107]

[0108] S408. UEM directly initiates a data acquisition request to DRF through the DRF data storage address obtained in S406 (it can be a one-time acquisition after the user business data collection is completed, or it can be acquired in a subscription manner during the user business data collection).

[0109] In this embodiment, Figure 5 FIG. 1 is a flow chart of collecting user signaling data according to an embodiment of the present application. Figure 5 As shown, user signaling data is collected from the production network through at least one AMF device. The process of collecting user signaling data includes the following steps:

[0110] S501a. DRF initiates a data service registration request to DCF, where the registration type is data storage service registration, indicating that DRF can provide user behavior data storage service.

[0111] S501b. AMF1 initiates a data service registration request to DCF, where the registration type is user signaling data collection service registration, indicating that AMF 1 provides user signaling data collection service.

[0112] S501c, AMF 2 initiates a data service registration request to DCF, where the registration type is user signaling data collection service registration, indicating that AMF 2 provides user signaling data collection service.

[0113] S502 (optional): The UEM of the twin network initiates a data service query request to the DCF. The data service query request carries the following parameters:

[0114] a. Query type: user signaling data collection service and data storage service.

[0115] S503 (optional): DCF returns the data service query request result to the UEM. The data service query request result is as follows:

[0116] a. User signaling data collection service: AMF1, AMF2.

[0117] b. Data storage service: DRF.

[0118] S504: UEM initiates a data request to DCF. The data request includes the following parameters:

[0119] (1) Data collection type: indicates whether the collected data is user signaling data or user service data, or both user signaling data and user service data.

[0120] (2) Data collection scope: Indicates on which AMFs user signaling data collection is performed. The indication content can be a network element identifier or a wildcard rule.

[0121] (3) Data collection rules: Indicates which users’ signaling data are collected. The indication content can be user identification (such as IMSI / IMEI), or filtering rules (such as by APN / slice, etc.) or sampling rules (such as proportional sampling).

[0122] (4) Data collection start time: Indicates when the user signaling data collection task needs to start collecting data.

[0123] (5) Data collection end time: Indicates the time when the user signaling data collection task needs to end.

[0124] (6) Data storage location: Indicates on which DRF the user signaling data is stored.

[0125] For example, the parameters carried in the data request are as follows:

[0126] (1) Data collection type: user signaling data.

[0127] (2) Data collection scope: AMF1 (can be determined based on the results of the S503 data service query request).

[0128] (3) Data collection rules: Sampling is conducted at a rate of 0.1%.

[0129] (4) Data collection start time: 2025.3.10 00:00:00.

[0130] (5) Data collection end time: 2025.3.15 00:00:00.

[0131] (6) Data storage location: DRF (can be determined based on the result of the S503 data service query request).

[0132] S505a: After receiving the data request, DCF sends a data storage task to DRF.

[0133] S505b. After receiving the data request, DCF sends a user signaling data collection task to AMF1, carrying data collection parameters.

[0134] S505c. After receiving the data request, DCF sends a user signaling data collection task to AMF2, carrying data collection parameters.

[0135] S506. The DCF returns the determined DRF data storage address to the UEM, so that the UEM can communicate directly with the DRF.

[0136] After S507a / S507b and AMF1 / AMF2 receive the user signaling collection task, they extract 0.1% of users for signaling data collection according to the collection rules. Specifically, when the extracted 0.1% users initiate a signaling operation (for example, registration, location update, switching, session establishment, etc.), AMF1 / AMF2 extracts key information from the user signaling data, including but not limited to signaling type, timestamp, user ID, etc., and reports it to DRF for storage. The reporting method can be immediate reporting or cached timed reporting.

[0137] Among them, the user signaling data format is shown in Table 2:

[0138] Table 2

[0139]

[0140] S508. UEM directly initiates a data acquisition request to DRF through the DRF data storage address obtained in S506 (it can be acquired once after the user signaling data collection is completed, or it can be acquired by subscription during the user signaling data collection).

[0141] In some embodiments, Figure 6 FIG. 1 is a flow chart of collecting user service data and user signaling data according to an embodiment of the present application. Figure 6 As shown, user service data and user signaling data are collected from the production network through at least one user plane function device UPF device and AMF device. The process of collecting user service data and user signaling data includes the following steps:

[0142] S601a. ​​DRF initiates a data service registration request to DCF, where the registration type is data storage service registration, indicating that DRF can provide user behavior data storage service.

[0143] S601b. AMF1 initiates a data service registration request to DCF, where the registration type is user signaling data collection service registration, indicating that AMF 1 provides user signaling data collection service.

[0144] S601c. UPF1 initiates a data service registration request to DCF, where the registration type is user business data collection service registration, indicating that UPF1 provides user business data collection services.

[0145] S602 (optional): The UEM of the twin network initiates a data service query request to the DCF. The data service query request carries the following parameters:

[0146] a. Query type: user signaling data collection service, user business data collection service and data storage service.

[0147] S603 (optional): DCF returns the data service query request result to UEM. The data service query request result is as follows:

[0148] a. User signaling data collection service: AMF1.

[0149] b. User business data collection service: UPF1.

[0150] c. Data storage service: DRF.

[0151] S604: The UEM initiates a data request to the DCF. The data request includes the following parameters:

[0152] (1) Data collection type: indicates whether the collected data is user signaling data or user service data, or both user signaling data and user service data.

[0153] (2) Data collection scope: Indicates on which AMFs user signaling data collection is performed, and indicates on which UPFs user service data collection is performed. The indication content can be a network element identifier or a wildcard rule.

[0154] (3) Data collection rules: Indicates which users’ signaling data are collected and which users’ service data are collected. The indication content can be user identification (such as IMSI / IMEI), or filtering rules (such as according to APN / slice, etc.) or sampling rules (such as proportional sampling).

[0155] (4) Data collection start time: Indicates when the user signaling data / user service data collection task needs to start collecting.

[0156] (5) Data collection end time: indicates when the user signaling data / user service data collection task needs to end.

[0157] (6) Data storage location: Indicates on which DRF the user signaling data / user service data is stored.

[0158] For example, the parameters carried in the data request are as follows:

[0159] (1) Data collection type: user signaling data, user service data.

[0160] (2) Data collection scope: empty (if empty, the collection scope is all registered user data collection services).

[0161] (3) Data collection rules: IMSI:1101245123, IMSI:1101245124, IMSI:1101245125 (specified IMSI collection).

[0162] (4) Data collection start time: 2025.3.10 00:00:00.

[0163] (5) Data collection end time: 2025.3.15 00:00:00.

[0164] (6) Data storage location: empty (if empty, it is determined by DCF).

[0165] S605a: After receiving the data request, the DCF sends a data storage task to the DRF.

[0166] S605b. After receiving the data request, DCF sends a user signaling data collection task to AMF1, carrying data collection parameters.

[0167] S605c: After receiving the data request, DCF sends a user service data collection task to UPF1, carrying data collection parameters.

[0168] S606. The DCF returns the determined DRF data storage address to the UEM, so that the UEM can communicate directly with the DRF.

[0169] S607a. After AMF1 receives the user signaling collection task, it selects the user for signaling data collection according to the collection rules. Specifically, when the selected user initiates a signaling operation (for example, registration, location update, switching, session establishment, etc.), AMF1 extracts key information from the user signaling data, including but not limited to signaling type, timestamp, user ID, etc., and reports it to DRF for storage. The reporting method can be immediate reporting or cached timed reporting.

[0170] S607b, after UPF1 receives the user business collection task, it selects a user for business data collection according to the collection rules. Specifically, when the selected user initiates a business operation (for example: video streaming, web browsing, instant messaging), UPF1 saves the user business message in units of streams. UPF1 extracts the summary data or complete data, user address, timestamp, etc. in the user business message and reports it to DRF for storage. The reporting method can be immediate reporting or cached timed reporting.

[0171] S608. UEM directly initiates a data acquisition request to DRF through the DRF data storage address obtained in S606 (it can be a one-time acquisition after the user business data collection is completed, or it can be acquired in a subscription manner during the user business data collection).

[0172] In some embodiments, after obtaining the user data, the method further includes: performing data processing on the user service data to construct the user behavior model; or, clustering the user signaling data according to the clustering dimension to construct the user behavior model; or, performing data processing on the user service data and clustering the user signaling data according to the clustering dimension to construct the user behavior model.

[0173] In this embodiment, different user behavior models can be constructed according to different business requirements and network environments. For example, if the focus is on the impact of different types of business data (such as video, voice, and text messages) on network performance and resources, the user behavior model can be constructed by processing the user business data; if the focus is on the user's mobility and network access characteristics, the user signaling data can be clustered to construct a user behavior model; or both the user business data and the signaling data can be clustered to construct a comprehensive user behavior model that includes user business preferences and mobile behaviors. Furthermore, after obtaining the user business data, the user business data is cleaned, deduplicated, and stored in a database; after obtaining the user signaling data, the user signaling data is clustered according to the clustering dimensions and the user signaling data is clustered into different classes; after obtaining the user business data and user signaling data, the user business data is cleaned, deduplicated, and stored in a database, and the user signaling data is clustered according to the clustering dimensions.

[0174] In this embodiment, different user data may be obtained to construct different user behavior models according to different application scenarios.

[0175] In this embodiment, the clustering dimension includes at least one of the following: a time dimension, a slice dimension, a location dimension, and a network type dimension.

[0176] Step S304: Simulate user behavior in the target network through the target user instance, wherein the target user instance is a simulation entity of real user behavior in the mobile network.

[0177] In this embodiment, the target network includes but is not limited to a digital twin network and a test network.

[0178] In this embodiment, simulating user behavior in the target network through the target user instance includes: extracting a user behavior chain from the user behavior model, wherein the user behavior chain is obtained by integrating at least one of the clustered user signaling data or the data-processed user service data; converting the user behavior chain into a user behavior process through a test instrument, and generating a user behavior message based on the user behavior process, wherein the user behavior process includes a user signaling process or a user service process, and the user behavior message includes a user signaling message or a user service message; generating a target user instance based on the user behavior message to simulate user behavior in the target network through the target user instance.

[0179] In this embodiment, different user behavior models can be constructed according to different business requirements and network environments, and different user behavior chains can be extracted from different user behavior models. Figure 7 This is a flow chart of simulating user behavior based on a test instrument according to an embodiment of the present application, such as Figure 7 As shown, taking a comprehensive user behavior model constructed based on user service data and user signaling data as an example, the process of simulating user behavior by using the constructed comprehensive user behavior model in combination with test instruments includes the following steps:

[0180] S701, sending a user behavior indication to a test instrument;

[0181] The UEM obtains clustered user signaling data and processed user service data, and can integrate the user signaling data with the user service data to form a complete user behavior chain. The UEM sends a user behavior indication to the test instrument based on the timestamp of the user behavior. The user behavior indication includes the following specific user behaviors:

[0182] If it is a signaling behavior, the user behavior indication carries the signaling type and signaling parameters.

[0183] If it is a business behavior, the user behavior indication includes the business type and message data.

[0184] S702: Construct a user behavior message;

[0185] After receiving the user behavior indication, the test instrument converts the user behavior in the user behavior indication into a user signaling process or a user business process, and constructs or modifies the corresponding user behavior message and sends it to the twin network.

[0186] S703, signaling / service processing flow;

[0187] When the twin network element receives the user behavior message sent by the test instrument, it processes or responds according to the normal signaling / service processing flow.

[0188] S704, user behavior feedback;

[0189] When the signaling / business process execution is completed, the test instrument sends user behavior feedback to the UEM, where the user behavior feedback message includes the user behavior execution result and related parameters.

[0190] In some embodiments, after generating the target user instance according to the user behavior message, the method further includes: extracting a new user behavior chain from the user behavior model when a new user behavior occurs.

[0191] In this embodiment, when new service types continue to emerge or users' network usage habits change in different time periods, it may directly affect user behavior. Based on the extracted new user behavior chain, user behavior messages are generated or updated to update UE behavior parameters, including but not limited to the frequency of signaling interaction, selection of service type, and adjustment of traffic size. By continuously generating new user behavior chains and messages, and then continuously updating the user behavior model, the accuracy and effectiveness of user behavior simulation in the twin network are ensured.

[0192] Through the above-mentioned embodiments of the present application, a user behavior simulation method is provided, which generates a target user instance based on the constructed user behavior model, and simulates user behavior in the target network through the target user instance, wherein the target user instance is a simulation entity of the real user behavior in the mobile network, that is, through the constructed user behavior model, a specific user object is instantiated. Compared with pre-written scripts, the user behavior model of the embodiment of the present application can cover a wider range of scenarios and user behavior types, so that the user behavior simulation in the target network can be more adaptable to and reflect the real environment, and improve the authenticity and flexibility of the simulation environment. Therefore, the embodiment of the present application can solve the problem that the traditional simulation environment mainly relies on manually pre-written test scripts when simulating user behavior, resulting in incomplete user behavior coverage and inability to effectively reflect real user behavior, thereby achieving the effect of improving the efficiency of user behavior simulation.

[0193] The highly realistic user behavior model constructed in the embodiment of the present application can be combined with a digital twin network or a test network to build a highly realistic simulation environment in the twin network, which can be applied to a variety of verification scenarios, such as new function verification of network elements, upgrade verification, configuration change verification, etc.

[0194] The embodiments of the present application can form a system for centrally storing user behavior data, build a user behavior library, and test network robustness based on a twin network environment.

[0195] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0196] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0197] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any of the above method embodiments when run.

[0198] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0199] An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0200] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0201] According to yet another embodiment of the present disclosure, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of the method described in each embodiment of the present disclosure are implemented.

[0202] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0203] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices, they can be implemented using program code executable by the computing device, and thus, they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0204] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A user behavior simulation method, characterized in that: include: Generate target user instances based on the constructed user behavior model; The user behavior is simulated in the target network through the target user instance, wherein the target user instance is a simulation entity of the real user behavior in the mobile network.

2. The method according to claim 1, characterized in that Before generating the target user instance according to the constructed user behavior model, the method further includes: Acquire user data, wherein the user data includes at least one of the following: user service data and user signaling data.

3. The method according to claim 2, characterized in that in, The user service data is obtained from the production network through at least one user plane functional device, and the user signaling data is obtained from the production network through at least one access and mobility management functional device.

4. The method according to claim 2, characterized in that After obtaining the user data, the method further includes: Processing the user service data to construct the user behavior model; or Clustering the user signaling data according to clustering dimensions to construct the user behavior model; or, The user service data is processed, and the user signaling data is clustered according to clustering dimensions to construct the user behavior model.

5. The method according to claim 4, characterized in that in, The clustering dimension includes at least one of the following: time dimension, slice dimension, location dimension, and network type dimension.

6. The method according to claim 2, characterized in that The obtaining of user data includes: Sending a user data acquisition request to the production network; wherein the user data acquisition request includes at least one of the following parameters: user data collection type, user data collection scope, user data collection rule, user data collection start time, user data collection end time, and user data storage location, where the user data storage location is a storage location queried from the production network or a storage location allocated from the production network; In response to the user data acquisition request, user data is acquired from the production network.

7. The method according to claim 1, characterized in that The simulating user behavior in the target network through the target user instance includes: Extracting a user behavior chain from the user behavior model, wherein the user behavior chain is obtained by integrating at least one of the clustered user signaling data or the processed user service data; Converting the user behavior chain into a user behavior process through a test instrument, and generating a user behavior message according to the user behavior process, wherein the user behavior process includes a user signaling process or a user service process, and the user behavior message includes a user signaling message or a user service message; A target user instance is generated according to the user behavior message, so as to simulate the user behavior in the target network through the target user instance.

8. The method according to claim 7, characterized in that After generating the target user instance according to the user behavior message, the method further includes: When a new user behavior occurs, a new user behavior chain is extracted from the user behavior model.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images