Device and Method for Network Configuration

Abstract

The present disclosure relates to a communication method and system for converging a fifth generation (5G) communication system for supporting higher data rates beyond a fourth generation (4G) system with Internet of Things (IoT) technology. The present disclosure may be applied to intelligent services based on 5G communication technology and IoT-related technologies, such as smart home, smart building, smart city, smart car, connected car, healthcare, digital education, smart retail, safety and security services. A method of controlling, preferably configuring and / or reconfiguring a fifth generation (5G) network including a set of user equipment (UE), the set of UE including a first UE, is provided. The method includes configuring the set of UE (e.g., the first UE) to collect data therefrom, collecting data from the set of UE, mapping the collected data to user intent, and controlling, preferably configuring and / or reconfiguring the network at least in part based on the mapped user intent.

Description

Technical Field

[0001] The present disclosure relates to control. More specifically, the present disclosure relates to configuring and / or reconfiguring a fifth generation (5G) network. Background Art

[0002] To meet the demand for increased wireless data traffic since the deployment of 4G communication systems, efforts have been made to develop improved 5G or pre-5G communication systems. Therefore, 5G or pre-5G communication systems are also referred to as "beyond 4G networks" or "post-LTE systems". The 5G communication system is considered to be implemented in a higher frequency (millimeter wave) band (e.g., 60 GHz band) in order to achieve higher data rates. To reduce the propagation loss of radio waves and increase the transmission distance, beamforming, massive multiple-input multiple-output (MIMO), full-dimensional MIMO (FD-MIMO), array antennas, analog beamforming, and massive antenna technologies are discussed in the 5G communication system. In addition, in the 5G communication system, development of system network improvements is underway based on advanced small cells, cloud radio access network (RAN), ultra-dense network, device-to-device (D2D) communication, wireless backhaul, mobile network, cooperative communication, coordinated multi-point (CoMP), receiver-side interference cancellation, etc. In the 5G system, hybrid FSK and QAM modulation (FQAM) and sliding window superimposed coding (SWSC) as advanced coding modulation (ACM), and filter bank multi-carrier (FBMC), non-orthogonal multiple access (NOMA), and sparse code multiple access (SCMA) as advanced access technologies have been developed.

[0003] The Internet, as a human-centric connected network in which people generate and consume information, is now evolving into the Internet of Things (IoT), in which distributed entities (such as things) exchange and process information without human intervention. The Internet of Everything (IoE), in which IoT technology is combined with big data processing technology through connection to a cloud server, has emerged. Since implementing IoT requires technical elements such as "sensing technology", "wired / wireless communication and network infrastructure", "service interface technology", and "security technology", sensor networks, machine-to-machine (M2M) communication, machine type communication (MTC), etc. have been studied recently. Such an IoT environment can provide intelligent Internet technology services, which create new value for human life by collecting and analyzing data generated between interconnected things. IoT can be applied to various fields, including smart home, smart building, smart city, smart car or connected car, smart grid, healthcare, smart appliances, and advanced medical services, through the convergence and combination of existing information technology (IT) and various industrial applications.

[0004] Consistently, various attempts have been made to apply 5G communication systems to IoT networks. For example, technologies such as sensor networks, machine type communication (MTC), and machine-to-machine (M2M) communication can be implemented through beamforming, MIMO, and array antennas. Cloud radio access network (RAN), as an application of the above big data processing technology, can also be considered an example of the convergence between 5G technology and IoT technology.

[0005] The above information is presented only as background information to help understand the present disclosure. Neither determination nor assertion is made as to whether any of the above can be applied as prior art to the present disclosure. Summary of the Invention

[0006] Technical Problem

[0007] There is a need to provide control, such as configuring and / or reconfiguring a 5G network, for example, based on data obtained from a user equipment (UE).

[0008] Solution to the Problem

[0009] Aspects of the present disclosure at least solve the above problems and / or disadvantages and at least provide the following advantages.

[0010] According to one aspect of the present disclosure, there is provided a method for controlling, preferably configuring and / or reconfiguring a 5G network including a set of UEs, the set of UEs including a first UE. The method includes configuring the set of UEs (e.g., the first UE) to collect data therefrom, collecting data from the set of UEs, mapping the collected data to user intentions, and controlling, preferably configuring and / or reconfiguring the network at least partially based on the mapped user intentions.

[0011] According to another aspect of the present disclosure, there is provided a 5G network including a set of UEs, the set of UEs including a first UE. The network is configured to configure the set of UEs (e.g., the first UE) to collect data therefrom, collect data from the set of UEs, map the collected data to user intentions, and control, preferably configure and / or reconfigure the network at least partially based on the mapped user intentions.

[0012] According to another aspect of the present disclosure, there is provided a computer including a processor and a memory, which is configured to at least partially implement the method according to the first aspect.

[0013] According to another aspect of the present disclosure, there is provided a computer program including instructions, which when executed by a computer including a processor and a memory, cause the computer to at least partially execute the method according to the first aspect.

[0014] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium including instructions that, when executed by a computer including a processor and a memory, cause the computer to at least partially perform the method according to the first aspect.

[0015] The specific implementation manners of various embodiments of the present disclosure are disclosed below in conjunction with the accompanying drawings. Other aspects, advantages, and significant features of the present disclosure will become clear to those skilled in the art.

[0016] Advantages of the invention

[0017] Therefore, one aspect of the present disclosure is to provide a network and a method for controlling the network that at least partially eliminate or mitigate at least some of the disadvantages of the prior art, whether pointed out herein or elsewhere.

[0018] Another aspect of the present disclosure is to provide a method for controlling a 5G network that uses data collected from a user equipment (UE) to improve network performance.

[0019] Another aspect of the present disclosure is to provide a 5G network that can be self-configured and / or reconfigured based on data collected from the UE.

[0020] Additional aspects will be partially elaborated in the following description, and partially, will become clear from the description, or can be learned through the practice of the presented embodiments. Brief description of the drawings

[0021] From the following description in conjunction with the accompanying drawings, the above and other aspects, features, and advantages of certain embodiments of the present disclosure will become clearer, where:

[0022] Figure 1 The method or a part thereof according to an embodiment of the present disclosure is schematically depicted;

[0023] Figure 2 The method or a part thereof according to an embodiment of the present disclosure is schematically depicted;

[0024] Figure 3 The method or a part thereof according to an embodiment of the present disclosure is schematically depicted;

[0025] Figure 4 The method or a part thereof according to an embodiment of the present disclosure is schematically depicted; and

[0026] Figure 5 The method according to an embodiment of the present disclosure is schematically depicted.

[0027] In all the drawings, like reference numerals will be understood to refer to like parts, components, and structures. Detailed Implementation Modes

[0028] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of various embodiments of the present disclosure defined by the claims and their equivalents. The following description includes various specific details to facilitate understanding, but these are only considered exemplary. Therefore, those of ordinary skill in the art will recognize that various changes and modifications can be made to the various embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and structures may be omitted for clarity and conciseness.

[0029] The terms and words used in the following description and claims are not limited to the literal meanings, but are used only by the inventor to enable a clear and consistent understanding of the present disclosure. Therefore, it will be apparent to those skilled in the art that the following description of the various embodiments of the present disclosure is provided for illustrative purposes only and not for the purpose of limiting the present disclosure defined by the appended claims and their equivalents.

[0030] It should be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, a reference to "a component surface" includes a reference to one or more of such surfaces.

[0031] According to the present disclosure, a method as set forth in the appended claims is provided. A network is also provided. Other features of the present disclosure will become apparent from the dependent claims and the following description.

[0032] Network

[0033] The 3rd Generation Partnership Project (3GPP) is currently standardizing the service-based architecture (SBA) of the 5G core [1][2] as part of the system architecture of the 5G system, which started in Release 15 and will continue to be developed in Release 16 and later releases. In the SBA, different network functions and associated services can communicate directly with each other as service initiators or consumers via a common bus called the Service-Based Interface (SBI).

[0034] A key function envisioned in the SBA is the network data analytics function (NWDAF) [3], which enables network functions to access analytics for different purposes, including intelligent automated network configuration and deployment.

[0035] The UE is a natural data collection point for gathering more localized analytics. The UE can have on-device capabilities to generate analytics, and the network can configure the UE to collect data for generating analytics through in-network intelligence.

[0036] When it comes to social behavior and social gatherings (such as sports events, concerts, opera festivals, etc.), several UEs can exhibit closely related behaviors (referred to herein as "collective behavior") without any explicit group designation. For example, these UEs can adopt similar routes, speeds, orientations, and / or movement patterns as collective behavior in a joint event or a common event (e.g., arriving at a destination). Another type of collective behavior can be monitored based on social protocols that UEs must comply with at specific locations (such as public settings, e.g., inside trains, buses, shopping malls, restaurants, factories, etc.), where the combination of relative proximity, orientation, and / or time intervals spent in these locations becomes valuable information based on public health and safety regulations. Therefore, collecting input data from UEs that reflects user intent or indicates possible actions that such UEs may take (or have taken) can be useful for generating analytics data at the NWDAF within the 5G Core (5GC). It should be understood that a UE is generally associated with a corresponding user, e.g., being in very close proximity to the UE held or carried by the corresponding user. Thus, the associated UE of a specific user can accordingly track the behavior or intent of that specific user.

[0037] Collective behavior patterns can be inferred based on a large amount of UE input data (i.e., from a single or multiple UEs), where the UE input data includes sensor information, device-to-device signaling, a new generation of on-device personal assistant platforms relying on advanced natural language processing (NLP) techniques, or any enhancements via more general natural body language gestures and expressions.

[0038] The user intent and user collective behavior obtained therefrom are input data that the UE and / or the network can use to generate analytics for, e.g., automated network configuration, deployment, or any associated public safety actions and responses.

[0039] This document describes novel methods, processes, service flows, and triggers regarding how UE input data on the device (including, e.g., NLP, sensor data, proximity information) coordinates with network data analytics functions within the 5G Core (5GC) to provide powerful tools for communication service providers (CSPs) to autonomously (re)configure network functions and parameters, e.g., to optimize system performance and / or facilitate public safety actions and responses based on end-user collective behavior.

[0040] The NLP used in this disclosure covers both natural language processing and any enhancements through more general natural body language postures and expressions.

[0041] A first aspect provides a method for controlling, preferably configuring and / or reconfiguring a 5G network including a set of UEs including a first UE, the method including configuring the set of UEs (such as the first UE) to collect data from it, collecting data from the set of UEs, mapping the collected data to user intents, and controlling, preferably configuring and / or reconfiguring the network at least in part based on the mapped user intents.

[0042] In this way, the data collected from the set of UEs can be used to improve network performance.

[0043] The method includes configuring the set of UEs (such as the first UE) to collect data from it. In one example, configuring the set of UEs to collect data from it includes defining what data to collect and / or defining how to collect the data. For example, the set of UEs (such as its applications) can be configured based on operator preferences, such as setting appropriate tags and / or characterizations to configure data collection from the control plane (CP), user plane (UP), or via a trace collection element (TCE) controlled by operation, administration and management (OAM), and / or setting privacy parameters.

[0044] In one example, configuring the set of UEs includes setting its configuration parameters at the application function (AF) level, for example, via an operator-driven application server or assisted by the NWDAF.

[0045] In one example, configuring the set of UEs to collect data from it includes setting the path for collecting data from the set of UEs, for example, via a policy control function (PCF).

[0046] In one example, the method includes subscribing, by an access mobility management function (AMF), to unified data management (UDM) notifications regarding user profile updates, for example.

[0047] In one example, the method includes the PCF subscribing to the AF for UE policies and / or privacy parameters, such as for configuring data collection (CP, UP, or via TCE / OAM) for each UE. If the parameters are related to data collection paths, privacy, or anonymization configurations, the PCF (instead of the UDM) may initiate a UE configuration update triggered by an AF request in operation 4, as described below.

[0048] In one example, setting configuration parameters for a UE set at the AF level with NWDAF assistance includes the AF optionally subscribing to the NWDAF via a network exposure function (NEF) to obtain UE analytics, such as UE mobility and / or communication analytics for a first UE and / or UE set. In one example, the AF receives a notification of the UE analytics.

[0049] In one example, setting configuration parameters for a UE set includes: if setting configuration parameters at the AF level via an operator-driven application server, the AF determines the configuration parameters based on operator preferences; or if setting configuration parameters with NWDAF assistance, the AF determines the configuration parameters based on the UE analytics received from the NWDAF.

[0050] In one example, setting configuration parameters for a UE set includes the UDM creating and / or updating the configuration parameters in response to a request received, for example, from the AF via the NEF. Optionally, the request (i.e., the payload) includes an identifier of the first UE, such as a GPSI, a transaction reference identifier, application-level parameters such as NLP token parameters, parameters related to data collection paths and / or privacy, and / or anonymization configuration parameters, as described below. In one example, the method includes the UDM notifying the AMF of the configuration parameters in response to the request.

[0051] In one example, setting configuration parameters for a UE set includes the AMF initiating an update to the UE set (e.g., the first UE) to, for example, update user profile information.

[0052] In one example, setting configuration parameters for a UE set includes the PCF initiating an update to the UE set (e.g., the first UE) to, for example, update user policy information. If the parameters are related to data collection paths, privacy, or anonymization configurations, the PCF (instead of the UDM) may initiate a UE configuration update triggered by an AF request in operation 4, as described below.

[0053] In one example, collecting data from a UE set includes anonymizing the data. In this way, the data and / or the privacy of individual subscribers (i.e., users) can be protected.

[0054] In one example, anonymizing data includes anonymizing data when configuring the UE set, for example, by defining an anonymization strategy when setting configuration parameters, such as by defining a unique pseudonym for the payload. In this way, personally identifiable information (PII) can be decoupled from the data.

[0055] In one example, anonymizing data includes anonymizing data when collecting data from the UE set. For example, PII can be decoupled from the data based on the anonymization strategy defined above. In one example, for CP data collection, anonymizing data includes the AMF using the 5G globally unique temporary identifier (5G-GUTI) of each UE in the UE set. In one example, for UP data collection, anonymizing data includes the user plane function (UPF) and / or the session management function (SMF) replacing the corresponding identifier with a pseudonym (e.g., a temporarily assigned pseudonym) for each UE in the UE set. The corresponding identifier can be replaced periodically or via a triggering mechanism. Additionally and / or alternatively, the UPF and / or SMF can aggregate data and / or mask individual subscription permanent identifiers (SUPI), such as when exposing the analysis payload to the NWDAF. In one example, for OAM data collection, anonymizing data includes the management system replacing the corresponding identifier with a pseudonym (e.g., a temporarily assigned pseudonym) for each UE in the UE set. The corresponding identifier can be replaced periodically or via a triggering mechanism.

[0056] In one example, the path for collecting data (CP, UP, and / or management plane) from the UE set is set via the PCF.

[0057] In one example, collecting data from a set of UEs via the CP includes the NWDAF subscribing to the AMF event exposure service for the first UE or the set of UEs. In one example, the subscription defines a minimum subset of the set of UEs, for example, to maintain anonymity. In one example, the subscription defines a data collection timer as the minimum time for the AMF to collect data (unless the minimum subset is reached) before aggregating and / or anonymizing the analysis. In one example, the subscription includes the set of UEs (e.g., the first UE) providing data to the AMF in one or more UL NAS TRANSPORT messages (optionally using 5G-GUTI) via UL N1. In one example, the subscription includes the AMF identifying the data and aggregating the analysis, for example, according to the individual 5G-GUTI corresponding to the individual target SUPI (uncovered case) or according to the 5G-GUTI group corresponding to the target group of the SUPI (anonymized case).

[0058] In one example, collecting data from a set of UEs via the UP includes the NWDAF subscribing to the SMF for updates from the first UE or the set of UEs. In one example, the subscription includes the first UE indicating to the network that the UP message or the header message (e.g., of the corresponding packet data unit (PDU) message) will include UE data. In one example, the subscription includes the AMF invoking PDU session establishment or the AMF invoking the update SM context service from the SMF, enabling the SMF to configure the UPF on which to extract the header of the UP message or the UP PDU message. In one example, the subscription includes the SMF updating the UPF, for example, via an N4 session modification, and optionally, indicating the analysis extraction from the established PDU session or from the header of the UP message or the UP PDU message. In one example, the subscription includes the set of UEs (e.g., the first UE) providing data on the relevant headers of the established PDU session or the UP PDU message to the UPF via single or multiple UL messages. In one example, the subscription includes the UPF extracting the data provided by the set of UEs (e.g., the first UE). In one example, the subscription includes aggregating the analysis, for example, for the set of UEs and / or multiple messages, and notifying the NWDAF of the aggregated analysis, optionally including masking the individual SUPI for anonymization. In one example, collecting data from a set of UEs via the UP includes the NWDAF subscribing to the UPF for updates from the first UE or the set of UEs, as described with reference to the SMF with necessary modifications.

[0059] In one example, collecting data from a set of UEs via the UP includes the NWDAF subscribing to the management system / OAM for updates from a first UE or set of UEs. In one example, the subscription includes the management system / OAM initiating a trace session activation via the NG-RAN. In one example, the subscription includes the management system / OAM aggregating the analysis from the trace record reports and notifying the NWDAF of the aggregated analysis, optionally including masking individual SUPIs for anonymization. In other words, collecting data from a set of UEs may include aggregating the data.

[0060] In one example, controlling the network at least in part based on the mapped user intent includes the consumer NF requesting an analysis from the NWDAF, such as requesting an NF load analysis (optionally, for a specific NF instance). In one example, the request includes setting a time window for receiving the analysis. In one example, controlling the network at least in part based on the mapped user intent includes the NWDAF subscribing to one or more (e.g., all) specified analysis data collection parts of one or more SUPIs within an area of interest (i.e., a geographical area of interest), optionally including retrieving the NF load analysis from a specific and / or each NF instance. In one example, controlling the network at least in part based on the mapped user intent includes the NWDAF processing an analysis, such as regarding collective movement patterns and / or collective behavior patterns, optionally in combination with the current NF load analysis. In one example, controlling the network at least in part based on the mapped user intent includes the NWDAF predicting a load change, such as a load change pattern across one or more tracking areas (TAs) and / or one or more AMF regions, and periodically providing the predicted load change to the consumer NF, for example. In one example, controlling the network at least in part based on the mapped user intent includes, for example, the consumer NF configuring and / or reconfiguring the network at least in part based on the predicted load change, such as the consumer NF. In one example, the consumer NF is a single instance, such as an AMF instance. In one example, the consumer NF is a primary NF instance, such as the primary AMF instance in its set, which is arranged to configure and / or reconfigure the remaining AMF instances in the set. In one example, the consumer NF is the OAM, which is arranged to configure and / or reconfigure one or more (e.g., all) NF instances, for example, via a corresponding management service.

[0061] In one example, controlling the network at least in part based on the mapped user intent includes preemptive control plane load balancing and / or rebalancing, for example, by adjusting the weight factor of an AMF instance.

[0062] In one example, mapping the collected data to user intent includes at least partially identifying, interpreting, and learning user intent based on one or more of speech, expression, gesture, sensor, and proximity data obtained by a first UE.

[0063] In one example, mapping the collected data to user intent includes at least partially learning the user intent common to a set of UEs. For example, as described above, this learning is based on the collective user behavior from a set of users.

[0064] In one example, mapping the collected data to user intent includes using natural language programming (NLP) to map the data and / or the collected data to user intent.

[0065] In one example, mapping the collected data to user intent includes receiving an instruction from a set of users including a first user, the instruction including audio data such as speech and / or an expression such as a vocal expression and / or image data such as a gesture and / or an expression such as a body expression; transcribing the received instruction; using natural language programming (NLP) to map the transcribed instruction to user intent.

[0066] In one example, the method is to control, preferably configure and / or reconfigure a 5G network including a set of UEs (including a first UE), the method including receiving an instruction from a set of users including a first user, the instruction including audio data such as speech and / or an expression such as a vocal expression and / or image data such as a gesture and / or an expression such as a body expression, transcribing the received instruction, using natural language programming (NLP) to map the transcribed instruction to user intent, and controlling, preferably configuring and / or reconfiguring the network at least partially based on the mapped user intent.

[0067] In one example, using NLP to map the transcribed instruction to user intent is at least partially based on, for example, the NLP configuration provided by an NLP server within the network.

[0068] In one example, the NLP configuration includes an anonymization policy.

[0069] In one example, the method includes decoupling the user intent from the personally identifiable information (PII) of the first user.

[0070] In one example, the set of users includes N users, where N is a natural number greater than or equal to 1, such as a user group, such as 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 50, 100, 500, 1000, 5000, 10000 or more users.

[0071] In one example, the method includes learning collective user behavior from a set of users and, optionally, providing recommendations for controlling the network, such as statistical or predictive.

[0072] In one example, the method includes, for example, providing a recommendation to a first UE.

[0073] In one example, the method includes configuring the first UE by the network, for example, based on operator settings such as preferences.

[0074] In one example, configuring the first UE by the network includes setting UE configuration parameters at the Application Function (AF) level.

[0075] In one example, setting UE configuration parameters at the AF level is performed with the assistance of a Network Data Analytics Function (NWDAF).

[0076] In one example, receiving instructions from a set of users including a first user includes collecting instructions by the network, for example, via a control plane (CP), a user plane (UP), and / or a management plane.

[0077] In one example, the method includes, for example, a consumer network function (NF) requesting an analysis of the NF load (e.g., for a specific NF instance), optionally, where the consumer NF is a single NF instance, a primary NF instance, or an Operations, Administration, and Management (OAM) NF.

[0078] In one example, the method includes applying a weight factor to an Access and Mobility Management Function (AMF) and / or load balancing the network.

[0079] In one example, the network includes an AMF, an NWDAF, a unified data repository (UDR), a UDM, a NEF, an AF, a (R)AN, an SMF, a UPF, an OAM TCE, a consumer network function (NF), and / or a network repository function (NRF).

[0080] Network

[0081] A second aspect provides a 5G network including a set of UEs including a first UE, where the network is arranged to configure the set of UEs (e.g., the first UE) to collect data from it, collect data from the set of UEs, map the collected data to user intents, and control, preferably configure and / or reconfigure the network at least in part based on the mapped user intents.

[0082] The network, UE set, first UE, collection, data, mapping, collected data, user intent, control, configuration, reconfiguration, and / or mapped user intent may be as described with reference to the first aspect.

[0083] Computer

[0084] A third aspect provides a computer including a processor and a memory, the computer being configured to at least partially implement the method according to the first aspect.

[0085] Computer program

[0086] A fourth aspect provides a computer program including instructions that, when executed by a computer including a processor and a memory, cause the computer to at least partially execute the method according to the first aspect.

[0087] Non-transitory computer-readable storage medium

[0088] A fifth aspect provides a non-transitory computer-readable storage medium including instructions that, when executed by a computer including a processor and a memory, cause the computer to at least partially execute the method according to the first aspect.

[0089] Define

[0090] Throughout the specification, the term "comprising" or "including" means including the specified components, but does not exclude the presence of other components. The term "consisting essentially of" or "consisting essentially of" means including the specified components and excluding other components, except for materials present as impurities, inevitable materials present as a result of the process for providing the components, and components added for purposes other than achieving the technical effects of the present disclosure, such as colorants, etc.

[0091] The term "consisting of" or "consisting of" means including the specified components and excluding other components.

[0092] When appropriate, depending on the context, the use of the term "comprising" or "including" may also be understood to include the meaning of "consisting essentially of" or "consisting essentially of", and may also be understood to include the meaning of "consisting of" or "consisting of".

[0093] When appropriate, and especially in the combinations set forth in the appended claims, the optional features set forth herein may be used alone or in combination with each other. As described herein, when appropriate, the optional features of each aspect or embodiment of the present disclosure are also applicable to all other aspects or embodiments of the present disclosure. In other words, those skilled in the art reading this specification should consider that the optional features of each aspect or embodiment of the present disclosure are interchangeable and combinable between different aspects and embodiments.

[0094] Figure 1 Schematically depicts a method or a part thereof according to an embodiment of the present disclosure. More specifically, Figure 1 Schematically depicts different stages of network configuration based on UE data.

[0095] Referring to Figure 1 , different stages of network configuration based on UE input data on a device are shown. As shown, UE input data on the device can first be used to identify subscriber (also referred to as user) voice, expression, gesture, sensor, and / or proximity data (or any other UE-driven data). Next, a data interpretation engine on the UE maps the input data to user intent based on UE configuration parameters provided by an application server within the network. The UE configuration parameters may also include an anonymization policy, as described below, which applies to one or more stages of user configuration update and / or user data collection.

[0096] (After data collection) Collective user behavior can be learned from the in-network individual user group intents, that is, collective user behavior can be learned from the in-network intents of an individual user group. Based on the collective user behavior, for example, in response thereto, the NWDAF can provide recommendations (such as in the form of statistics or predictions) for other NFs within the 5GC for autonomous network (re)configuration.

[0097] Figures 2 to 4 Includes various known network functions / entities, whose known functions and definitions are described at least in 3GPP TS23.501, 3GPP TS 23.502, and 3GPP TS 23.503. As described herein, according to the method of the first aspect, various known functions of these network functions / entities are changed / enhanced.

[0098] For completeness, Figures 2 to 4 The various functions / entities shown in

[0099] User Equipment: UE

[0100] (Radio) Access Network: (R)AN

[0101] Access and Mobility Management Function: AMF

[0102] Session Management Function: SMF

[0103] User Plane Function: UPF

[0104] User Data Management: UDM

[0105] Unified Data Repository: UDR

[0106] Network Exposure Function: NEF

[0107] Application Function: AF

[0108] Network Repository Function: NRF

[0109] Operation, Administration and Maintenance: OAM

[0110] Policy Control Function: PCF

[0111] A. UE Configuration Update for Collection and Analysis

[0112] Figure 2 Schematically depicts a method or a part thereof according to an embodiment of the present disclosure.

[0113] Reference Figure 2 , which schematically depicts the call flow for UCU to collect UE data analysis.

[0114] As described above, for autonomous network configuration, it may be necessary to configure the applications on the device (i.e., UE) based on operator preferences (e.g., to set the correct tagging / classification or other application-level parameters, configure the analysis data collection path from the control plane, user plane, or a trace collection element (TCE) controlled via OAM; or set privacy parameters). The service flows described below consider two related variants of UE configuration:

[0115] A.1. Variant 1 (AF-driven): In this variant, UE configuration parameters are set at the AF level (e.g., via an operator-driven application server).

[0116] A.2. Variant 2 (AF-driven, NWDAF-assisted): In this variant, UE configuration parameters are set at the AF level via NWDAF assistance.

[0117] Figure 2 Schematically depicts the operation of this service flow.

[0118] 0. The AMF subscribes to UDM notifications regarding user profile updates by sending a Nudm_SDM_Subscribe message [Subscription data type = UE data configuration] to the UDM.

[0119] 1. [Conditional on NWDAF assistance - Variant 2] The AF may (i.e., optionally) subscribe to the NWDAF via the NEF to obtain UE behavior analysis of a UE or UE group (e.g., UE mobility or communication analysis) in order to set (see operation 2) the configuration parameters of the UE or UE group based on these analyses. In response, the AF receives notifications of UE analysis.

[0120] 2. Determine configuration parameters (also referred to as settings) based on AF or operator preference (variant 1) or based on analysis (operation 1 - variant 2) extracted via NWDAF (i.e., received from NWDAF).

[0121] 3. AF provides the configuration parameters to be created (updated) on UDM / UDR by sending a Nudm_SDM_Update message to UDM via NEF (using input parameters: GPSI as the UE identifier (or any other external UE identifier) and transaction reference ID). The payload of operation 3 may include application-level parameters (e.g., NLP tagging parameters) (or any other relevant IE). Additionally, the payload may include parameters related to the data collection path, i.e., UE access selection and PDU session selection related policy information (e.g., from CP, UP, or OAM) or privacy and anonymization configuration parameters, as detailed in section 3.3.B (Analysis anonymization).

[0122] 4. UDM notifies the relevant AMF of the update (i.e., configuration parameters) by invoking the Nudm_SDM_Notify service operation [subscription data type = UE data configuration].

[0123] Note 1: If the configuration parameters are related to the data collection path, privacy, or anonymization configuration, the PCF (instead of UDM) may initiate a UE configuration update triggered by the AF request in operation 4.

[0124] 5. AMF (via N1) initiates a UE configuration update for the UE to update the user profile information related to the configuration parameters received from AF via UDM.

[0125] B. Analysis anonymization

[0126] To ensure data protection and individual subscriber privacy, analysis anonymization can be performed in various ways, as described below with reference to Figure 1 as mentioned.

[0127] B.1. During the UE configuration phase:

[0128] The operator-driven application server (at the AF level) can define a specific anonymization / tagging strategy, for example, by defining a unique pseudonym (e.g., container ID) for the payload of 3.3.A - operation 3 (user configuration update) (either AF-driven (variant 1) or assisted by NWDAF (variant 2)), which ensures that any interpreted application-related data (such as user intent data) derived from a large amount of UE input data is completely decoupled from personally identifiable information (PII). This is to avoid singling out individuals based on the collected data through association or inference.

[0129] B.2. During the data collection phase:

[0130] During the data collection phase, based on the anonymization policy set during the UE configuration phase (as described in Section 3.3.B.1 above), PII is decoupled from (and removed) the exported UE input data or analysis. Additionally, ensure that the UE ID (and similar user identifiers) are pseudonymized or masked via aggregation during this phase.

[0131] In one example, for CP data collection, the AMF uses the 5G-GUTI temporary allocation value for each UE that has been standardized in 3GPP to pseudonymize the UE ID. Additionally, when exposing the analysis payload to the NWDAF, the AMF can aggregate the analysis data or mask the individual SUPI (e.g., using a pseudonym similar to that in Section 3.3.B.1).

[0132] In one example, for UP data collection, the UPF / SMF either periodically (based on the anonymization period) or via a trigger mechanism from the UE / network operator replaces the UE identifier with a temporarily allocated pseudonym for each UE. Additionally, when exposing the analysis payload to the NWDAF, the UPF / SMF can aggregate the analysis data or mask the individual SUPI (e.g., using a pseudonym similar to that in Section 3.3.B.1).

[0133] In one example, for OAM data collection, the management system either periodically (based on the anonymization period) or via a trigger mechanism from the UE / network operator replaces the UE identifier with a temporarily allocated pseudonym for each UE. Additionally, when exposing the analysis payload to the NWDAF, the OAM can aggregate the analysis data or mask the individual SUPI (e.g., using a pseudonym similar to that in Section 3.3.B.1).

[0134] C. Data collection from the UE

[0135] Figure 3 Schematically depicts a method or a part thereof according to an embodiment of the present disclosure.

[0136] Reference Figure 3 , which schematically depicts the call flow of the UE input data collection process.

[0137] As described in Operation 4 of Section 3.3.A, the data collection path for analysis can be set via the PCF based on the configuration via the CP, UP, or management plane.

[0138] The following references Figure 3 to describe the call flows of three examples of data collection from the UE.

[0139] C.1. Control Plane (CP) Process

[0140] 1. In this example, assuming that the configuration parameters are configured by the operator, the NWDAF can subscribe to the AMF event exposure service based on the event ID specified for the UE input data to be informed of all occurrences of the event. In the case of a non-covered UE with consent, the subscription can be set for an individual SUPI (i.e., via a mapping similar to the pseudonym to UE ID in 3.3.B.1), or in the case of an anonymized UE, the subscription can be set for the SUPI group together. In response to the request, the AMF also provides a subscription-related ID.

[0141] Note: The subscription request can define the minimum group size for data collection to ensure sufficient anonymization. The subscription request can also define the collection window timer as the minimum time the AMF needs to wait (unless it receives analysis data of the minimum group size) before aggregating / anonymizing the analysis.

[0142] 2. The UE provides terminal analysis (i.e., UE input data) to the AMF via UL N1. Depending on the NG-RAN settings and the parameters set during the user configuration operation, each UE can provide terminal analysis via a single or multiple UL NAS TRANSPORT messages. The 5G globally unique temporary identifier (5G-GUTI) can be used to keep the International Mobile Subscriber Identity (IMSI) of the subscriber confidential.

[0143] 3. The AMF identifies UE input data events and aggregates the analysis either according to the individual 5G-GUTI corresponding to the individual target SUPI (non-covered case) or according to the 5G-GUTI group corresponding to the target group of the SUPI (anonymized case). In the anonymized case, aggregation occurs when the minimum group size is reached or the collection window timer expires. The AMF uses the notification target address (+ notification-related ID) to notify the subscribed NWDAF of the event and the analysis payload, optionally masking the individual SUPI of each entry of the analysis payload in the anonymized case, using the Namf_EventExposure_Notify message.

[0144] C.2. User Plane (UP) Procedures

[0145] 1. In this example, assuming that the configuration parameters are configured by the operator, the NWDAF can subscribe to the UE input data updates from the SMF.

[0146] 2. Based on the user configuration update, the UE (via invoking PDU session establishment or modification) indicates to the network that the UP message or the header message of the (corresponding PDU message) will be filled with the UE input data.

[0147] 3. In response, the AMF invokes the PDU session establishment procedure or updates the SM context service from the SMF, enabling the SMF to configure the UPF on which the headers of the UP message or UP PDU message will be extracted.

[0148] 4. The SMF updates the UPF accordingly (via N4 session modification) and indicates the analysis extraction from the established PDU session or related headers based on the newly proposed attributes within the packet detection rules (as part of the N4 session context), as described in TS23.501 for example.

[0149] 5. Depending on the NG-RAN settings and the parameters set during the user configuration update operation, the UE provides the terminal analysis (i.e., UE input data) to the UPF via a single or multiple UL messages, via the related headers of the established PDU session or UP PDU message. Pseudonyms can be used as described herein.

[0150] 6. The UPF extracts the UE input data from the related headers of the established PDU session and / or UP PDU message and delivers the (buffered) data to the SMF.

[0151] 7. The SMF aggregates the analysis across multiple messages and / or multiple UEs. The SMF notifies the subscribed NWDAF of the terminal analysis (i.e., UE input data) in the CP, optionally masking the individual SUPI of each entry in the analysis payload in case of anonymization.

[0152] Note: As an alternative to the example C.2 procedure, in operation 1, the NWDAF can subscribe to (or send a request for) UE input data updates from the UPF (instead of the SMF). Thus, in operations 6 and 7, the UPF itself can continue to aggregate the analysis extracted from the related headers of the established PDU session or UP PDU message and directly notify the subscribed NWDAF of the analysis (in operation 4, according to the SMF instructions).

[0153] C.3. Management System Procedures

[0154] 1. In this example, assuming the configuration parameters are configured by the operator, the NWDAF subscribes to (or sends a request to) the management system (trace event subscription). In the case of non-overriding UEs with consent, the request can include the individual SUPI (i.e., via a mapping of pseudonym to UE ID similar to that in 3.3.B.1), or in the case of anonymized UEs, the request can include a SUPI group.

[0155] 2. The management system / OAM initiates a trace session activation via the NG-RAN according to a request received from the NWDAF, and collects trace record reports whenever the target UE provides terminal analysis (i.e., UE input data). Pseudonyms can be used as described herein.

[0156] 3. The management system / OAM aggregates the terminal analysis (i.e., UE input data) from the trace record reports and notifies the NWDAF of the analysis. In the case of anonymization, the individual SUPI of each entry in the analysis payload is optionally masked.

[0157] D. Network Structure

[0158] Figure 4 Schematically depicts a method or a part thereof according to an embodiment of the present disclosure.

[0159] Reference Figure 4 , which schematically depicts the service flow of network (re)configuration.

[0160] In this example, other NFs within the 5GC combine the analysis generated based on the UE input data (or any resulting suggestions) aggregated by the NWDAF to autonomously (re)configure network parameters and / or optimize system performance.

[0161] The following references Figure 4 to describe the service flow of the above process.

[0162] 1. The consumer NF uses the Nnwdaf_AnalyticsInfo or Nnwdaf_AnalyticsSubscription service to send a request for the analysis of the NF load of a specific NF instance to the NWDAF. The analysis ID is set to "NF load information", the target of the analysis is set to the NF id and the newly proposed analysis filter information based on the area of interest (e.g., a specific TA or AMF area). The consumer NF can set a future time window to obtain a prediction of the load change pattern for that window.

[0163] 2. The NWDAF (by setting the analysis filter information to the specific TA or AMF area requested by the consumer NF in operation 1 as shown Figure 3 and accordingly collecting UE input data) subscribes to the specified analysis data collection paths for all SUPIs within the area of interest.

[0164] 3. The NWDAF can optionally use the Nnrf_NFManagement_NFStatusSubscribe service operation of each NF instance to retrieve NF load and NF status information from the NRF.

[0165] 4. The NWDAF processes the analyzed data collected on the collective mobility patterns or any other collective behavior patterns and (optionally) combines it with the current NF load analysis retrieved from the NRF (for each AMF instance).

[0166] 5. The NWDAF provides the consumer NF with the predicted load change patterns across multiple TAs or AMF areas.

[0167] 6 - 8. If, in operation 1, the consumer NF has subscribed to receive continuous reports of NF load analysis, the NWDAF may generate new analysis and provide the new analysis to the NF upon receiving a notification of new analyzed data.

[0168] Multiple network configuration variants for load balancing:

[0169] In one variant of the present disclosure, the consumer NF may be a single NF instance (e.g., an AMF instance) that configures itself individually based on the analysis information provided by the NWDAF.

[0170] In another variant of the present disclosure, the consumer NF may be a master NF instance (e.g., an AMF master instance) designated for each NF set and jointly adjusting the configurations of all instances within that set.

[0171] In another variant of the present disclosure, the consumer NF may be an OAM that collects the analysis information provided by the NWDAF and adjusts the configurations of all NF instances accordingly via the corresponding management service.

[0172] Below, we provide some examples of network (re)configuration based on the Figure 4 service procedure.

[0173] Preemptive control plane load balancing / rebalancing

[0174] In the case of social events such as sports games, concerts, operas, festivals, etc., multiple subscribers may adopt similar routes to reach a combined or common destination, which helps predict the load change patterns across multiple TAs or AMF areas. The NWDAF can process the aggregated data on device analysis to identify the expected load changes in each tracking area (TA) or AMF area by recognizing the correlation of the mobility patterns of UE groups.

[0175] As an embodiment of the present disclosure, the weight factors of each AMF instance within the AMF set can be preemptively adjusted (under the operator's policy) based on the above - mentioned collective mobility pattern information (within a given AMF area or TA defined by TS23.502) to avoid future overload / congestion. The 5G - (R)AN nodes can adjust their load balancing parameters accordingly.

[0176] A similar approach can be adopted for load rebalancing, where for AMF instances within an AMF set, their loads can be actively rebalanced among each other before reaching overload, i.e., preventing overload situations.

[0177] NF Selection and Reselection

[0178] The SMF selection function is supported by the AMF (and SCP) and is used to allocate the SMF that will manage the PDU session. If the AMF performs the discovery, the AMF will utilize the NRF to discover SMF instances, unless the SMF information is available in other ways, e.g., locally configured on the AMF. When attempting to discover SMF instances, the AMF provides the UE location information to the NRF. The NRF provides the NF profile of the SMF instance to the AMF. In addition, the NRF also provides the SMF service area of the SMF instance to the AMF. The SMF selection function in the AMF selects the SMF instance and the SMF service instance based on the available SMF instances obtained from the NRF or based on the SMF information configured in the AMF.

[0179] In one example, in addition to the NF profile or deployment scenario, the AMF also utilizes the exported collective user behavior information to select an appropriate target NF (i.e., the SMF).

[0180] Given a centralized or distributed UPF deployment scenario, the SMF can adopt a similar approach to select and reselect the UPF.

[0181] Figure 5 A method according to an embodiment of the present disclosure is schematically depicted.

[0182] Reference Figure 5 , the method controls, preferably configures and / or reconfigures a 5G network including a set of UEs, the set of UEs including a first UE.

[0183] In operation S501, the method includes configuring the set of UEs (e.g., the first UE) to collect data from it.

[0184] In operation S502, the method includes collecting data from the set of UEs.

[0185] In operation S503, the method includes mapping the collected data to user intentions.

[0186] In operation S504, the method includes controlling, preferably configuring and / or reconfiguring the network at least partially based on the mapped user intentions.

[0187] The method may include any operation as described herein with reference to the first aspect.

[0188] Although the preferred embodiments have been shown and described, those skilled in the art will understand that various changes and modifications can be made without departing from the scope of the present disclosure as defined in the appended claims and as described above.

[0189] Abbreviations

[0190] The abbreviations used herein have their ordinary meanings, and the following definitions are provided for convenience only.

[0191]

Table 1

[0192]

[0193]

[0194] References

[0195] [1] System Architecture for the 5G System, 3GPP SA2 TS 23.501, Release 15 (5G system's system architecture, 3GPP SA2 TS 23.501, version 15)

[0196] [2] Procedures for the 5G System, 3GPP SA2 TS 23.502, Release 15 (5G system's procedures, 3GPP SA2 TS 23.502, version 15)

[0197] [3] Architecture enhancements for 5G System (5GS) to support network data analytics services, 3GPP SA2 TS23.288, Release 16 (5G system (5GS)'s architecture enhancements to support network data analytics services, 3GPP SA2 TS23.288, version 16)

[0198] [1]-[3]'s subject matter is incorporated herein by reference.

[0199] Note

[0200] Pay attention to all papers and documents submitted simultaneously with or prior to this specification related to this application, and these papers and documents are publicly available for inspection together with this specification. The content of all these papers and documents is incorporated herein by reference.

[0201] All features disclosed in this specification (including any accompanying claims and drawings), and / or all operations of any method or process so disclosed, may be combined in any combination, except combinations in which at most some of such features and / or operations are mutually exclusive.

[0202] Each feature disclosed in this specification (including any accompanying claims and drawings) may be replaced by an alternative feature serving the same, equivalent, or similar purpose, unless expressly stated otherwise. Thus, each feature disclosed is only an example of a series of equivalent or similar features, unless expressly stated otherwise.

[0203] Although the present disclosure has been shown and described with reference to various embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made therein without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents.

Claims

1. A method performed by a Network Data Analytics Function (NWDAF) entity in a wireless communication system for network configuration, the method comprising: Receiving an analysis information request from a Network Function (NF), the analysis information request including an analysis identity ID set to NF load information and analysis filter information; Setting the analysis filter information to a specific Tracking Area (TA) or an Access and Mobility Management Function (AMF) area; Collecting User Equipment (UE) input data including at least one of route, speed, orientation, and destination; Processing the collected UE input data; And Sending an analysis information response to the NF, the analysis information response including a predicted load change pattern based on the processed UE input data.

2. The method according to claim 1, wherein, The at least one UE is within a predetermined area.

3. The method according to claim 1, further comprising: Obtaining NF load and NF status information of the NF from a Network Repository Function (NRF) entity; And Combining the processed UE input data with the NF load and NF status information to generate a predicted load change pattern.

4. The method according to claim 1, further comprising: Updating the predicted load change pattern by processing newly obtained UE input data in case of NF subscription to receive continuous reports; And Sending an additional analysis information response including the updated predicted load change pattern.

5. The method according to claim 1, wherein The UE input data is anonymized based on a policy.

6. The method according to claim 1, further comprising: Generating an analysis to identify the expected load change for each TA or AMF area, so that Operations, Administration, and Maintenance (OAM) or other NFs adjust the weight factor of each AMF.

7. A Network Data Analytics Function (NWDAF) entity for network configuration in a wireless communication system, the NWDAF comprising: A transceiver; And At least one processor coupled to the transceiver and configured to: Receive an analysis information request from a Network Function (NF), the analysis information request including an analysis identity ID set to NF load information and analysis filter information, Set the analysis filter information to a specific Tracking Area (TA) or an Access and Mobility Management Function (AMF) area, Obtain UE input data of at least one User Equipment (UE), Collect the collected UE input data including route, speed, orientation, and destination, and Send an analysis information response to the NF, the analysis information response including a predicted load change pattern based on the processed UE input data.

8. The NWDAF entity according to claim 7, wherein, The at least one UE is within a predetermined area.

9. The NWDAF entity according to claim 7, wherein, The at least one processor is further configured to: Obtain NF load and NF status information of the NF from a Network Repository Function (NRF) entity, and Combine the processed UE input data with the NF load and NF status information to generate a predicted load change pattern.

10. The NWDAF entity according to claim 7, wherein, The at least one processor is further configured to: Update the predicted load change pattern by processing newly obtained UE input data in case of NF subscription to receive continuous reports, and Send an additional analysis information response including the updated predicted load change pattern.

11. The NWDAF entity according to claim 7, wherein, The UE input data is anonymized based on a policy.

12. The NWDAF entity according to claim 7, wherein, The at least one processor is further configured to: Generate an analysis to identify an expected load change for each tracking area TA or AMF area, so that operations, administration, and maintenance OAM or other NFs adjust the weight factor of each AMF.

Images