Network data analysis method and network data analysis functional entity
The NWDAF entity retrieves the network information of user behavior and parameters, dynamically determines and adjusts the analysis parameters, solving the problem that user equipment mobility analysis relies on fixed parameters in the prior art, and improving the flexibility and accuracy of the analysis.
Patent Information
- Application Number
- CN202011052662.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-09-29
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2040-09-29
AI Technical Summary
The existing network data analysis function (NWDAF) relies on pre-configured fixed parameters when analyzing user equipment mobility, resulting in inflexible and accurate task analysis and ineffective collection of other parameters closely related to user equipment mobility, such as paths. and speed, affecting the flexibility and accuracy of the analysis.
NWDAF entities dynamically determine the relevant parameters of behavior analysis tasks by recalling the relationship network information of user behavior and parameters, subscribe to the corresponding data to relevant network elements, and update the relationship network information based on the analysis results, adjust the parameter weight and association relationship to improve the Flexibility and accuracy of analysis.
By dynamically determining and adjusting analysis parameters, the flexibility and accuracy of user equipment mobility analysis are improved, and the adaptability and accuracy of task analysis are enhanced.
Smart Images

Figure CN114338392B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of communications, and in particular to a network data analysis method and a network data analysis functional entity. Background Art
[0002] The network data analysis function (NWDAF, Network Data Analytics Function) is mainly used for the analysis of network slicing related data.
[0003] The NWDAF entity pre-configures the data to be collected according to the type of analysis task. For example, for the analysis task of User Equipment (UE) mobility type, several fixed parameters such as UE ID, UE location, TAC (Tracking area code), Timestamp, Application, etc. are pre-configured.
[0004] If the user equipment mobility is to be analyzed, the NWDAF entity will retrieve fixed parameters such as UE ID, UElocation, TAC, Timestamp, Application, etc. according to the configuration information, and collect data related to these fixed parameters to perform user equipment mobility analysis.
[0005] In this way, even if NWDAF finds new strongly associated data, it cannot increase the collection of other parameters (such as path, speed, etc.) that are closely related to the content that needs to be judged (such as UE Mobility). Summary of the invention
[0006] The inventors found that the NWDAF entity performs task analysis based on the configured fixed parameters, and the task analysis results depend on the accuracy of the configured fixed parameters, resulting in inflexible and inaccurate task analysis. For example, in addition to the above-mentioned configured fixed parameters, parameters such as path and speed also have a strong correlation with the mobility of the user equipment. If these parameters are not pre-configured, the flexibility and accuracy of the mobility analysis of the user equipment will be adversely affected.
[0007] In the disclosed embodiment, the NWDAF entity retrieves the relationship network information between user behavior and parameters, determines the relevant parameters of the behavior analysis task according to the relationship network information, subscribes to the corresponding relevant parameter data from the relevant network element according to the relevant parameters of the behavior analysis task, and performs behavior analysis on the behavior analysis task according to the relevant parameter data. Thus, the relevant parameters of the behavior analysis task are dynamically determined, and the flexibility and accuracy of the task analysis are improved.
[0008] Some embodiments of the present disclosure provide a network data analysis method, including:
[0009] The network data analysis function NWDAF entity retrieves the relationship network information between user behavior and parameters;
[0010] The NWDAF entity determines relevant parameters of the behavior analysis task according to the relationship network information;
[0011] The NWDAF entity subscribes to corresponding relevant parameter data from relevant network elements according to relevant parameters of the behavior analysis task;
[0012] The NWDAF entity performs behavior analysis on the behavior analysis task according to the relevant parameter data.
[0013] In some embodiments, the method further includes: the NWDAF entity updating the relationship network information according to the behavior analysis result of the behavior analysis task.
[0014] In some embodiments, the NWDAF entity updates the relationship network information including:
[0015] When the behavior analysis result shows that different behaviors of a user have a temporal succession relationship, the NWDAF entity adds the association relationship between the different behaviors of the user in the relationship network information; or
[0016] When the behavior analysis result shows that different users have the same behavior at the same time, the NWDAF entity adds the association relationship between the different users in the relationship network information;
[0017] When the behavior analysis result shows that different behaviors of different users have a preset association relationship, the NWDAF entity adds the association relationship between the different behaviors of the different users to the relationship network information.
[0018] In some embodiments, the NWDAF entity updates the relationship network information including: when the analysis accuracy of the behavior analysis result is lower than a preset value, the NWDAF entity modifies the weight of the parameters associated with the user behavior in the relationship network information, or / and adjusts the parameters associated with the user behavior.
[0019] In some embodiments, the NWDAF entity adjusting the parameters associated with the user behavior includes: the NWDAF entity determining a derived parameter according to at least one initial parameter associated with the user behavior, and adding the derived parameter to the parameters associated with the user behavior.
[0020] In some embodiments, the NWDAF entity determines, based on the relationship network information, relevant parameters of the behavior analysis task including:
[0021] The NWDAF entity determines the target behavior of the behavior analysis task and the corresponding parameters of the target user according to the relationship network information;
[0022] The NWDAF entity selects relevant parameters for the behavior analysis task from the corresponding parameters of the target behavior and the target user.
[0023] In some embodiments, the NWDAF entity determines the relevant parameters of the behavior analysis task according to the relationship network information, further comprising:
[0024] The NWDAF entity determines the related behaviors of the target behavior of the behavior analysis task based on the relationship network information;
[0025] The NWDAF entity determines corresponding parameters of the relevant behavior according to the relationship network information;
[0026] The NWDAF entity selects relevant parameters of the behavior analysis task from the parameters corresponding to the target behavior and the target user and the parameters corresponding to the relevant behaviors.
[0027] In some embodiments, the NWDAF entity determines the relevant parameters of the behavior analysis task according to the relationship network information, further comprising:
[0028] The NWDAF entity determines the related users of the target user of the behavior analysis task according to the relationship network information;
[0029] The NWDAF entity determines corresponding parameters of the relevant users according to the relationship network information;
[0030] The NWDAF entity selects relevant parameters of the behavior analysis task from the parameters corresponding to the target behavior and the target user and the parameters corresponding to the relevant users.
[0031] In some embodiments, the relevant network elements include one or more of a radio access network RAN, an access and mobility management function AMF entity, a user plane function UPF entity, a policy control function PCF entity, a user data module UDM, and a session management function SMF entity.
[0032] Some embodiments of the present disclosure provide a network data analysis functional entity, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute a network data analysis method based on instructions stored in the memory.
[0033] Some embodiments of the present disclosure provide a non-transitory computer-readable storage medium having a computer program stored thereon, which implements the steps of a network data analysis method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. The present disclosure can be more clearly understood according to the following detailed description with reference to the drawings.
[0035] Obviously, the drawings described below are only some embodiments of the present disclosure, and a person skilled in the art can obtain other drawings based on these drawings without creative work.
[0036] Figure 1 A schematic diagram showing a communication network according to some embodiments of the present disclosure.
[0037] Figure 2 A flowchart illustrating a network data analysis method according to some embodiments of the present disclosure is shown.
[0038] Figure 3 A flowchart illustrating a network data analysis method according to some embodiments of the present disclosure is shown. DETAILED DESCRIPTION
[0039] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure.
[0040] Figure 1 A schematic diagram showing a communication network according to some embodiments of the present disclosure.
[0041] like Figure 1 As shown in FIG, in the communication network, there are network elements including: NWDAF entity, Radio Access Network (RAN) equipment, Access and Mobility Management Function (AMF) entity, User Plane Function (UPF) entity, Policy Control Function (PCF) entity, User Data Module (UDM), Session Management Function (SMF) entity, etc. The connection relationship between each network element is as follows: Figure 1 As shown in the figure, the NWDAF entity stores the relationship network information between user behaviors and parameters based on the knowledge graph technology.
[0042] The NWDAF entity can obtain task analysis-related data from other network elements that are connected to it. For example, the terminal location information (such as Tracking Area Identity (TAI)) and the number of users in the base station collected from the RAN can be used to confirm the user's location information and movement trajectory, and the number of users in the base station and adjacent base stations can be understood; the terminal connection status information, switching event reporting and other information collected from the AMF can be used to confirm the user's connection status and other information; the user's mobility policy and session policy related information collected from the PCF can be used to confirm the user's related mobility policy and session policy; the user contract information, user trajectory information, etc. collected from the UDM can be used to confirm the user type and other user contract-related information; the user session information collected from the SMF can be used to confirm the user session status, including the number of sessions, session type, etc.; the user session data routing information, billing information, etc. collected from the UPF can be used to confirm the routing status of the user data plane, that is, whether the user data is routed to the edge computing network or the backbone network. But it is not limited to the examples given.
[0043] After the NWDAF entity obtains data related to task analysis, it can perform various network data analyses. The following uses (1)-(4) as examples to illustrate.
[0044] (1) Mobility management customization or optimization based on terminal mobility prediction
[0045] Terminals in diverse 5G scenarios have different mobility behaviors. When the 5G network is expected to customize the mobility management of the terminal or optimize the mobility support, the network needs to be able to predict the mobility model of the terminal. Artificial intelligence technology provides a method for predicting terminal mobility behavior. By abstracting the terminal location prediction problem into a classification problem or regression problem in machine learning, the relevant machine learning algorithms can be used to predict the terminal location or trajectory.
[0046] The network data analysis function first needs to collect the location information of the terminal, including historical movement trajectory and real-time terminal location information. The collected information can be used as training data to adjust or correct the prediction model. Then, using a reliable prediction model, the terminal location or mobility trajectory can be predicted, including the distribution characteristics of group terminals and the location information of a single terminal. This prediction information is an important basis for 5G network mobility management customization or optimization.
[0047] Based on the prediction of the terminal mobility model, the network can perform dynamic network optimization, including the customization and optimization of mobility management, such as mobility management mechanism customization, registration area management, and handover management optimization.
[0048] (2) Network Slicing Optimization
[0049] Network slicing is an important technology introduced by 5G networks. It divides multiple virtual logical end-to-end networks on demand on the same hardware infrastructure. Each network slice is logically isolated to adapt to the different network requirements of various types of services. Logically, a network slice is a collection of network functions used to serve a class of services, but physically, multiple network slices still share network resources. Considering the limited network resources and the network status in different network slices, operators need to reuse the underlying network resources as much as possible while ensuring the service level agreement SLA (Service Level Agreement). Therefore, in order to operate efficiently, operators need to optimize the resource division of network slices.
[0050] The NWDAF entity collects information such as resource usage, business volume, and user business experience of network slices, and uses reliable analysis and prediction models to achieve statistics and prediction of network slice business volume, resource requirements, and user business experience of network slices, build network slice portraits, and optimize network slice resource allocation and network slice selection strategies.
[0051] Artificial intelligence technology can help operators optimize the management of network slice resources. The NWDAF entity uses machine learning algorithms to create a model of the network slice's business volume and resource usage by collecting the actual operation of the network slice, the business volume data in the slice, and the execution of the SLA. Then, using this model, it can accurately predict the business volume and resource requirements of the network slice, thereby optimizing the resource allocation strategy between network slices. The network management system will dynamically adjust the network slice resources according to the resource allocation, such as dynamic expansion and contraction. The network operation status after using the optimized resource allocation strategy can be iterated into the prediction model again to complete the closed-loop feedback and approach the optimal solution.
[0052] (3) Business (path) optimization
[0053] The NWDAF entity collects information such as network performance, service load in a specific area, and user service experience, and uses reliable network performance analysis and prediction models to evaluate and analyze different types of services, build service portraits, and determine the inherent relationships between the service quality of experience (Quality of Experience, QoE) and service paths, QoS (Quality of Service), and optimize service paths (such as optimizing UPF selection), service routing (such as optimizing UE routing selection strategies), edge computing, and QoS corresponding to services.
[0054] (4) Optimization of business parameters
[0055] Application layer adjustment assisted by network performance prediction. In order to help the application layer make correct parameter adjustments, the 5G network should provide accurate network performance prediction information to the application layer. Therefore, in addition to predicting the mobility of the terminal, the 5G network also needs to establish an analysis model for network performance. The network can collect and analyze the operating status information of each base station to create a model. After receiving a subscription request for network performance prediction information from the application layer, the network performance analysis model and the location of the terminal are used to predict the network conditions that the terminal will face in the future for the relevant terminal.
[0056] The Internet of Vehicles is an important technology of 5G networks. In the scenario of autonomous driving in the Internet of Vehicles, the prediction of the network performance (such as QoS information and business load) of the base station that the vehicle is about to pass plays an important role in improving the service quality of the Internet of Vehicles. For example, the Internet of Vehicles server can determine whether to continue the unmanned driving mode based on the predicted information of network performance. The NWDAF entity collects information such as network performance and business load in a specific area, and uses reliable network performance analysis and prediction models to realize the statistics and prediction of network performance, and assist in optimizing application parameters.
[0057] Figure 2 A flowchart illustrating a network data analysis method according to some embodiments of the present disclosure is shown.
[0058] like Figure 2 As shown, the network data analysis method of this embodiment includes: steps 210-240, and may also include step 250.
[0059] In step 210, the NWDAF entity retrieves the relationship network information between user behaviors and parameters.
[0060] The relationship network information records various user behaviors and the associations of parameters related to each user behavior. It can also record the associations between different behaviors, the associations between different users, and the like.
[0061] The relationship network information between user behavior and parameters can be constructed using knowledge graph technology.
[0062] For example, when the network is initially deployed, the initial pre-configuration method can be used to configure associations between behaviors and between behaviors and parameters based on behavior-related information, forming an initial knowledge graph between behaviors. Subsequently, the NWDAF entity collects relevant information based on the initially configured knowledge graph, makes user behavior judgments, and feeds back the results of each judgment to the knowledge graph. Based on the judgment results, the associations between behaviors are strengthened or weakened. Based on the judgment results, the types of parameters that are strongly related to user behaviors can be increased, and the types of parameters that are irrelevant or weakly related can be reduced. As the number of user behavior judgments increases and the knowledge graph continues to improve, the NWDAF entity continuously adjusts the types of parameters collected for each user behavior, gradually reaching the optimal state of parameter collection.
[0063] In some application cases, for large-scale contract-signed dedicated terminals or IoT devices, the terminal types are similar and the contract information is similar. When NWDAF determines the behavior of this type of terminal, it has little to do with which terminal the behavior comes from. For example, the terminals equipped by mine workers have a set of behavioral specifications for mine operations, and the behavioral differences between terminals are not large. Therefore, it is only necessary to build a knowledge graph based on a certain behavior as the granularity, which can simplify the complexity of the knowledge graph and facilitate rapid behavior recognition without taking into account the behavioral differences of each user.
[0064] For another example, when the network is initially deployed, the parameters related to the behavior of a single user can be preconfigured according to the contract information in the UDM and other known information of the network through the initial preconfiguration method, and the relationship between different behaviors of a single user, the same behavior of multiple users, and different behaviors of multiple users can be configured to form an initial knowledge graph. The NWDAF entity will subsequently collect relevant information based on the initially configured knowledge graph, make behavioral judgments on a single user, and feed back the results of each judgment to the knowledge graph. The association between behaviors will be enhanced or weakened based on the judgment results. The types of parameters that are strongly related to user behaviors can also be increased based on the judgment results, and the types of parameters that are irrelevant or weakly related can be reduced. As the number of judgments on user behaviors continues to increase and the knowledge graph continues to improve, the types of parameters collected by the NWDAF entity for each user behavior are also continuously adjusted, gradually reaching the optimal state of parameter collection.
[0065] In some application examples, for personalized terminals (such as mobile phones), the behavioral habits of each person have certain regularities. For example, each user's commuting time, route, and speed (walking, driving, or subway) have certain regularities. Constructing the knowledge graph according to the granularity of users and behaviors is conducive to the accuracy of user behavior judgment.
[0066] In step 220, the NWDAF entity determines relevant parameters of the behavior analysis task according to the relationship network information.
[0067] In some embodiments, the NWDAF entity determines the relevant parameters of the behavior analysis task including: the NWDAF entity determines the target behavior and target user corresponding parameters of the behavior analysis task according to the relationship network information, that is, according to the various user behaviors and various parameters recorded in the relationship network information and their associations, using the target behavior and target user specified by the behavior analysis task, and searching and determining the corresponding parameters of the target behavior and target user from the relationship network information; the NWDAF entity selects the relevant parameters of the behavior analysis task from the corresponding parameters of the target behavior and target user. Among them, all or part of the parameters are selected from the corresponding parameters of the target behavior and target user as the relevant parameters of the behavior analysis task. Among them, if some parameters are selected, the parameters with larger weights can be selected according to the weights of each parameter (the size of the weight indicates the size of the influence on the behavior analysis task).
[0068] In some embodiments, the NWDAF entity determines the relevant parameters of the behavior analysis task, including: the NWDAF entity determines the target behavior and the corresponding parameters of the target user of the behavior analysis task according to the relationship network information; the NWDAF entity determines the relevant behaviors of the target behavior of the behavior analysis task according to the relationship network information, as described above, the relationship network information records the correlation between different behaviors, and the relevant behaviors of the target behavior can be determined based on this; the NWDAF entity determines the corresponding parameters of the relevant behaviors according to the relationship network information, as described above, the relationship network information records the parameters related to each behavior, and the corresponding parameters of the relevant behaviors can be determined based on this; the NWDAF entity selects the relevant parameters of the behavior analysis task from the parameters corresponding to the target behavior and the target user and the parameters corresponding to the relevant behaviors. Among them, all or part of the parameters are selected from the parameters corresponding to the target behavior and the target user and the parameters corresponding to the relevant behaviors as the relevant parameters of the behavior analysis task. Among them, if some parameters are selected, the parameters with larger weights can be selected according to the weights of each parameter (the size of the weight indicates the size of the influence on the behavior analysis task).
[0069] In some embodiments, the NWDAF entity determines the relevant parameters of the behavior analysis task, including: the NWDAF entity determines the target behavior and the corresponding parameters of the target user of the behavior analysis task according to the relationship network information; the NWDAF entity determines the relevant users of the target user of the behavior analysis task according to the relationship network information. As mentioned above, the relationship network information records the correlation between different users, and the relevant users of the target user can be determined based on this; the NWDAF entity determines the corresponding parameters of the relevant users according to the relationship network information, for example, the basic information of the relevant users, or the corresponding parameters of a certain behavior of the relevant users (such as the target behavior or the relevant behavior of the target behavior), etc.; the NWDAF entity selects the relevant parameters of the behavior analysis task from the corresponding parameters of the target behavior and the target user and the corresponding parameters of the relevant users. Among them, all or part of the parameters are selected from the corresponding parameters of the target behavior and the target user and the corresponding parameters of the relevant users as the relevant parameters of the behavior analysis task. Among them, if some parameters are selected, the parameters with larger weights can be selected according to the weights of each parameter (the size of the weight indicates the size of the influence on the behavior analysis task).
[0070] Those skilled in the art can understand that the NWDAF entity can also select relevant parameters of the behavior analysis task from parameters corresponding to the target behavior and the target user, parameters corresponding to the relevant behavior, and parameters corresponding to the relevant user.
[0071] In step 230, the NWDAF entity subscribes to corresponding relevant parameter data from relevant network elements according to relevant parameters of the behavior analysis task.
[0072] The NWDAF entity can obtain data related to task analysis from related network elements with which it is connected. As mentioned above, the related network elements include one or more of the RAN, AMF entity, UPF entity, PCF entity, UDM, and SMF entity. The data that can be obtained from the related gateway is referred to above and will not be repeated here.
[0073] In step 240, the NWDAF entity performs behavior analysis on the behavior analysis task according to the relevant parameter data.
[0074] After the NWDAF entity obtains the data related to the task analysis, it can perform various network data analyses. The analysis content and analysis methods are described above and will not be repeated here.
[0075] In step 250, the NWDAF entity updates the relationship network information according to the behavior analysis result of the behavior analysis task.
[0076] In some embodiments, the NWDAF entity updating the relationship network information includes: when the behavior analysis result shows that different behaviors of a user have a temporal succession relationship, the NWDAF entity adding the association relationship between the different behaviors of the user in the relationship network information.
[0077] For example, if a user goes to the gym to exercise after getting off work, we can establish an association between the different behaviors of the single user, "getting off work" and "exercise", and make a behavioral judgment.
[0078] In some embodiments, the NWDAF entity updating the relationship network information includes: when the behavior analysis result shows that different users have the same behavior at the same time, the NWDAF entity adding the association relationship between the different users in the relationship network information.
[0079] For example, after one employee leaves work, it is likely that other employees will leave work as well. We can establish a connection between the same "off-duty behavior" of different employees and make behavioral judgments.
[0080] In some embodiments, the NWDAF entity updates the relationship network information including: when the behavior analysis results show that different behaviors of different users have a preset correlation relationship (for example, a strong correlation relationship such as cause and effect, progression, etc.), the NWDAF entity adds the correlation relationship between the different behaviors of the different users in the relationship network information.
[0081] For example, after a parent sends his child to school, the child will usually attend class. We can establish associations between the different behaviors of different users "parents" and "children", such as "sending children to school" and "attending class", and make behavioral judgments.
[0082] For example, after get off work every day, half an hour after the husband picks up the child, the wife starts cooking so that the family can have dinner together after returning home. We can establish the association between the different behaviors of different users "husband" and "wife", such as "picking up the child" and "cooking", and make behavioral judgments. In other words, the time, place and people of these two behaviors are different, but there is a correlation between the two behaviors. When analyzing the wife's cooking behavior, we introduce the parameter of the time when the husband picks up the child based on previous data analysis experience.
[0083] In some embodiments, the NWDAF entity updates the relationship network information including: when the analysis accuracy of the behavior analysis result is lower than a preset value, the NWDAF entity modifies the weight of the parameters associated with the user behavior in the relationship network information, or / and adjusts (increases or decreases) the parameters associated with the user behavior.
[0084] In some embodiments, the NWDAF entity adjusting the parameters associated with the user behavior includes: the NWDAF entity determining a derived parameter according to at least one initial parameter associated with the user behavior, and adding the derived parameter to the parameters associated with the user behavior.
[0085] For example, in user mobility analysis, initial parameters such as user location and timestamp are associated with user mobility behavior, and derived parameters such as user speed or path are determined based on each user location and the corresponding timestamp.
[0086] In the above embodiment, the NWDAF entity retrieves the relationship network information between user behavior and parameters, determines the relevant parameters of the behavior analysis task based on the relationship network information, subscribes to the corresponding relevant parameter data from the relevant network element based on the relevant parameters of the behavior analysis task, and performs behavior analysis on the behavior analysis task based on the relevant parameter data. Thus, the relevant parameters of the behavior analysis task are dynamically determined and adjusted, improving the flexibility and accuracy of task analysis.
[0087] Figure 3 A flowchart illustrating a network data analysis method according to some embodiments of the present disclosure is shown.
[0088] like Figure 3 As shown, the network data analysis functional entity 300 of this embodiment includes: a memory 310 and a processor 320 coupled to the memory 310 , and the processor 320 is configured to execute the network data analysis method in any of the aforementioned embodiments based on instructions stored in the memory 310 .
[0089] The memory 310 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.
[0090] The network data analysis functional entity 300 may also include an input / output interface 330, a network interface 340, a storage interface 350, etc. These interfaces 330, 340, 350 and the memory 310 and the processor 320 may be connected, for example, via a bus 330. The input / output interface 330 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 340 provides a connection interface for various networked devices. The storage interface 350 provides a connection interface for external storage devices such as SD cards and USB flash drives.
[0091] Some embodiments of the present disclosure provide a non-transitory computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the network data analysis method in any of the aforementioned embodiments is implemented.
[0092] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more non-transient computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer program code.
[0093] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0096] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.
Claims
1. A network data analysis method, It is characterized in that include: The network data analysis function NWDAF entity retrieves the relationship network information between user behaviors and parameters. The relationship network information records the association between various user behaviors and the parameters related to each user behavior. The NWDAF entity determines the relevant parameters of the behavior analysis task according to the relationship network information, including: the NWDAF entity determines the target behavior and the corresponding parameters of the target user of the behavior analysis task according to the relationship network information; the NWDAF entity selects the relevant parameters of the behavior analysis task from the corresponding parameters of the target behavior and the target user; The NWDAF entity subscribes to corresponding relevant parameter data from relevant network elements according to relevant parameters of the behavior analysis task; The NWDAF entity performs behavior analysis on the behavior analysis task according to the relevant parameter data.
2. The method according to claim 1, It is characterized in that Also includes: The NWDAF entity updates the relationship network information according to the behavior analysis result of the behavior analysis task.
3. The method according to claim 2, It is characterized in that The NWDAF entity updates the relationship network information including: When the behavior analysis result shows that different behaviors of a user have a temporal succession relationship, the NWDAF entity adds the association relationship between the different behaviors of the user in the relationship network information; or When the behavior analysis result shows that different users have the same behavior at the same time, the NWDAF entity adds the association relationship between the different users in the relationship network information; When the behavior analysis result shows that different behaviors of different users have a preset association relationship, the NWDAF entity adds the association relationship between the different behaviors of the different users to the relationship network information.
4. The method according to claim 2, It is characterized in that The NWDAF entity updates the relationship network information including: When the analysis accuracy of the behavior analysis result is lower than a preset value, the NWDAF entity modifies the weight of the parameter associated with the user behavior in the relationship network information, or / and adjusts the parameter associated with the user behavior.
5. The method according to claim 4, It is characterized in that The parameters associated with user behavior adjusted by the NWDAF entity include: The NWDAF entity determines a derived parameter based on at least one initial parameter associated with the user behavior, and adds the derived parameter to the parameter associated with the user behavior.
6. The method according to claim 1, It is characterized in that The NWDAF entity determines, based on the relationship network information, the relevant parameters of the behavior analysis task, further comprising: The NWDAF entity determines the related behaviors of the target behavior of the behavior analysis task based on the relationship network information; The NWDAF entity determines corresponding parameters of the relevant behavior according to the relationship network information; The NWDAF entity selects relevant parameters of the behavior analysis task from the parameters corresponding to the target behavior and the target user and the parameters corresponding to the relevant behaviors.
7. The method according to claim 1, It is characterized in that The NWDAF entity determines, based on the relationship network information, the relevant parameters of the behavior analysis task, further comprising: The NWDAF entity determines the related users of the target user of the behavior analysis task according to the relationship network information; The NWDAF entity determines corresponding parameters of the relevant users according to the relationship network information; The NWDAF entity selects relevant parameters of the behavior analysis task from the parameters corresponding to the target behavior and the target user and the parameters corresponding to the relevant users.
8. The method according to any one of claims 1 to 7, It is characterized in that The relevant network elements include one or more of a radio access network RAN, an access and mobility management function AMF entity, a user plane function UPF entity, a policy control function PCF entity, a user data module UDM, and a session management function SMF entity.
9. A network data analysis functional entity, include: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the network data analysis method according to any one of claims 1 to 8 based on instructions stored in the memory.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the network data analysis method according to any one of claims 1 to 8.
