Method and apparatus for implementing ai / ML in a dual connection network

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. The present application generally relates to providing machine learning (ML) functionality within dual connectivity networks, including configuration and reporting as well as signaling processes. In addition, when the user equipment is not connected (i.e., in an INACTIVE or IDLE state), ML functionality is supported. There is a method for communicating data between a user equipment and a dual connectivity wireless communication network, the dual connectivity wireless communication network comprising a primary cell group (MCG) having a primary node and a secondary cell group (SCG) having a secondary node, the user equipment comprises a first receiver and a first transmitter connectable to the primary node and a second receiver and a second transmitter connectable to the secondary node. The method comprises: establishing a radio resource control (RRC) connection from a user equipment to a master node through a first channel; at least one configuration message is received at the user equipment, the at least one configuration message including at least one of primary measurement configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functionality within the primary cell group and secondary measurement configuration information for configuring the user equipment to collect and report AI / ML data within the secondary cell group. The auxiliary measurement configuration information is used for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions in the auxiliary cell group; and configuring the user equipment using the configuration information in the at least one configuration message.

Description

Technical Field

[0001] This application relates to providing machine learning (ML) capabilities within a 5G network. More specifically, this application relates to dual-connectivity networks. Additionally, ML capabilities are supported when a user equipment is not connected (i.e., in an INACTIVE or IDLE state). Background Art

[0002] 5G mobile communication technology defines wide frequency bands, enabling high transmission rates and new services, which can be achieved not only in the "Sub 6GHz" frequency band such as 3.5GHz, but also in the "Above 6GHz" frequency band called mmWave (including 28GHz and 39GHz). In addition, 6G mobile communication technology (referred to as the super 5G system) has been considered to be implemented in the terahertz (THz) frequency band (e.g., 95GHz to 3THz frequency band) in order to achieve a transmission rate 50 times faster than 5G mobile communication technology and an ultra-low latency one-tenth of 5G mobile communication technology.

[0003] At the beginning of the development of 5G mobile communication technology, in order to support services and meet the performance requirements related to enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), and massive machine-type communication (mMTC), standardization has been carried out on the following: beamforming and massive MIMO for reducing radio wave path loss in millimeter waves and increasing radio wave transmission distance, parameter sets (e.g., operating multiple subcarrier spacings) for supporting dynamic operations for effectively utilizing millimeter wave resources and time slot formats, initial access technologies for supporting multi-beam transmission and broadband, the definition and operation of BWP (bandwidth part), new channel coding methods (e.g., LDPC (low-density parity-check) codes for large data transmission and polarization codes for highly reliable transmission of control information), L2 preprocessing, and network slicing for providing dedicated networks dedicated to specific services.

[0004] Currently, in view of the services that 5G mobile communication technology is going to support, discussions on the improvement and performance enhancement of the initial 5G mobile communication technology are underway, and physical layer standardization already exists for the following technologies: such as V2X (vehicle-to-everything) for assisting in the driving determination of autonomous vehicles based on information about the position and state of the vehicle sent by the vehicle and for enhancing user convenience, NR-U (new radio unlicensed) targeting system operations that comply with various regulatory requirements in the unlicensed frequency band, NR UE energy saving, non-terrestrial networks (NTN) as UE satellite direct communication for providing coverage and positioning in areas where communication with the terrestrial network is unavailable.

[0005] In addition, standardization of the following technologies has been ongoing in the air interface architecture / protocol: industrial Internet of Things (IIoT) for supporting new services through interoperability and integration with other industries, integrated access and backhaul (IAB) for providing nodes for network service area expansion by supporting wireless backhaul links and access links in an integrated manner, mobility enhancements including conditional handover and dual active protocol stack (DAPS) handover, and two-step random access (two-step RACH for NR) for simplifying the random access process. Standardization of the following has also been ongoing in the system architecture / services: 5G baseline architecture for combining network function virtualization (NFV) and software-defined network (SDN) technologies (e.g., service-based architecture or service-based interface), and mobile edge computing (MEC) for receiving services based on UE location.

[0006] With the commercialization of 5G mobile communication systems, exponentially growing connected devices will be connected to the communication network, so enhanced functions and performance of 5G mobile communication systems and integrated operation of connected devices are expected to be necessary. For this purpose, new research has been arranged in combination with the following: extended reality (XR) for effectively supporting augmented reality (AR), virtual reality (VR), mixed reality (MR), etc., improving 5G performance and reducing complexity by leveraging artificial intelligence (AI) and machine learning (ML), AI service support, metaverse service support, and drone communication.

[0007] In addition, this development of 5G mobile communication systems will be used not only as a basis for developing: new waveforms for providing coverage in the terahertz band of 6G mobile communication technology, such as multi-antenna transmission technologies like full-dimensional MIMO (FD-MIMO), array antennas, and massive antennas, metamaterial-based lenses and antennas for improving the coverage of terahertz band signals, high-dimensional spatial multiplexing technology using orbital angular momentum (OAM), and reconfigurable intelligent surfaces (RIS); but also as a basis for developing: full-duplex technology for improving the frequency efficiency of 6G mobile communication technology and enhancing the system network, AI-based communication technology for achieving system optimization by leveraging satellites and AI (artificial intelligence) from the design stage and internalizing end-to-end AI support functions, and next-generation distributed computing technology for realizing services with a complexity level beyond the limitations of UE operation capabilities by leveraging ultra-high-performance communication and computing resources. Summary of the Invention

[0008] Technical Problem

[0009] Currently, there is a need to enhance the implementation of AI / ML in dual-connectivity networks.

[0010] Solution to the Problem

[0011] According to a first aspect of the present technology, there is provided a method for transmitting data between a user equipment and a dual-connectivity wireless communication network, the dual-connectivity wireless communication network including a master cell group (MCG) having a master node and a secondary cell group (SCG) having a secondary node, the user equipment including a first receiver and a first transmitter connectable to the master node and a second receiver and a second transmitter connectable to the secondary node. The method includes: establishing a radio resource control (RRC) connection from the user equipment to the master node on a first channel (e.g., on a first signaling radio bearer); receiving, at the first receiver of the user equipment, at least one configuration message on the first channel, wherein the at least one configuration message includes at least one of the following: primary measurement configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the master cell group; and secondary measurement configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the master cell group; and configuring the user equipment using the primary measurement configuration information and / or the secondary measurement configuration information in the at least one configuration message.

[0012] In this aspect, the network is a DC network including a master cell group (MCG) having a master node and a secondary cell group (SCG) having a secondary node. The user equipment is configured for dual connectivity and includes a first receiver and a first transmitter connectable to the master node and a second receiver and a second transmitter connectable to the secondary node.

[0013] The AI / ML functions in the network may include at least one AI / ML model located within the network and / or at the user equipment. For example, the AI / ML model may be used to perform network energy saving, load balancing, or mobility optimization within the network. The AI / ML functions in the network may include AI / ML model training, AI / ML model inference, and / or AI / ML model configuration. The AI / ML functions in the network may also include the transmission of AI / ML data around the network and / or between the network and the user equipment.

[0014] When the user equipment has been configured to collect and report AI / ML data to support AI / ML functions within the primary cell group, the method further includes performing collection of the AI / ML data (i.e., collecting the AI / ML data), and reporting the collected AI / ML data to the master node. Similarly, when the user equipment has been configured to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the secondary cell group, the method may include collecting the AI / ML data. In one example, the user equipment may report the collected AI / ML data to the master node for forwarding to the secondary node. In other words, the master node (and thus the MCG) may control the data flow to the SCG. Alternatively, the user equipment may report the collected AI / ML data directly to the secondary node.

[0015] When there is direct communication with the secondary node, the method may further include establishing a radio resource control (RRC) connection from a second receiver of the user equipment to the secondary node on a second channel. The second channel may be direct and thus may be different from the first channel. Both the first channel and the second channel may use the same radio signaling bearer, such as SRB1, and thus the term first radio signaling bearer may be interchangeable with the first channel and the second channel. The method may further include receiving, at the second receiver, at least one configuration message on the second channel, the at least one configuration message including information for configuring the user equipment to support AI / ML functions. The configuration message may be related to the AI / ML functions at the SCG, but may also include information about the AI / ML functions at the MCG.

[0016] Reporting of the AI / ML data may be done on the same signaling radio bearer as that used for the signaling radio bearers in the first and second channels. Alternatively, having a separate signaling radio bearer may be useful. The at least one configuration message (e.g., the at least one configuration message received at the first receiver or the at least one configuration message received at the second receiver or both) may further include bearer configuration information for configuring the user equipment to support AI / ML functions at the MCG and / or SCG by configuring at least one dedicated signaling radio bearer dedicated to transmitting data related to the AI / ML functions. The dedicated signaling radio bearer may be SRB3 or a newly defined bearer, such as SRBx. By establishing a connection using a separate radio bearer, messages sent via the first signaling radio bearer may be prioritized over messages sent via the dedicated signaling radio bearer. The signaling radio bearer or each signaling radio bearer may be referred to as a communication channel.

[0017] The method may further include configuring the user equipment by establishing a Radio Resource Control (RRC) connection between a first receiver of the user equipment and the master node by using a dedicated signaling radio bearer (e.g., SRBx), such that at least one RRC message can be sent from or received by the user equipment to / from the master node, the at least one RRC message including data related to AI / ML functionality. Once the dedicated signaling radio bearer has been configured, the collected AI / ML data for the MCG can be reported from the first transmitter to the master node in an RRC message via the dedicated signaling radio bearer. Similarly, when the master node controls the information flow within the network, the collected AI / ML data for the SCG can be reported from the first transmitter to the master node in an RRC message via the dedicated signaling radio bearer. Alternatively, the data for the SCG can be reported directly to the SCG. Accordingly, the method may further include: establishing a Radio Resource Control (RRC) connection between a second receiver of the user equipment and the secondary node by using a dedicated signaling radio bearer, using the bearer configuration information to configure the user equipment to support AI / ML functionality at the SCG, such that at least one RRC message can be sent from or received by the user equipment to / from the secondary node, the at least one RRC message including data related to AI / ML functionality. In this case, the dedicated signaling radio bearer can be a split bearer that connects the user equipment to both the master node (i.e., to the MCG) and the secondary node (i.e., to the SCG).

[0018] When the dedicated signaling radio bearer has been configured, the user equipment may receive an indicator from the network that indicates the user equipment to use the dedicated signaling radio bearer when reporting the collected AI / ML data to the master node and / or the secondary node. The indicator may be included when the dedicated signaling radio bearer is configured. For example, when the dedicated signaling radio bearer between the second receiver and the secondary node has been configured, the indicator may indicate that the user equipment should use the dedicated signaling radio bearer to report to the secondary node. When the dedicated signaling radio bearer has not been configured, the indicator may be received when the bearer configuration information is received, and the indicator may indicate that the user equipment reports the collected AI / ML data to the secondary node via the first signaling radio bearer.

[0019] When sending and / or receiving messages for AI / ML related information using a newly configured signaling radio bearer SBR5 and / or a newly configured data radio bearer, the network may configure the priority of these messages. The method may include receiving, at a user equipment, prioritization configuration information from the network, the prioritization configuration information defining a lower priority for messages including data related to AI / ML functions than for other messages transmitted between the user equipment and the network. The prioritization configuration information may be used to configure the user equipment, i.e., the user equipment may be configured to implement the prioritization configuration information. The prioritization configuration information may include logical channel prioritization parameters (i.e., the assignment of priorities and the prioritized bit rate (PBR)) to control the prioritization of data transmission. By prioritizing other messages, especially those related to establishing a connection within the network, the transmission of potentially large amounts of AI / ML data can be controlled, thus avoiding an impact on the control of the user equipment over the network.

[0020] Data security between the network and the user equipment is important. Thus, the method may include activating access stratum security. Once AS security is activated, all RRC messages on standard signaling radio bearers (e.g., SRB1, SRB2, SRB3, and SRB4) are typically subject to integrity protection and encryption, e.g., via PDCP (Packet Data Convergence Protocol). However, when using a new signaling radio bearer, the method may include receiving security configuration information that defines whether the user equipment will apply integrity protection and / or encryption to messages between the user equipment and the network, and configuring the user equipment according to the security configuration information. The security configuration information defines whether the message is neither integrity protected nor encrypted, not integrity protected but encrypted, integrity protected but not encrypted, or both integrity protected and encrypted. In other words, RRC integrity protection and encryption can be activated and deactivated based on the received configuration information. Using one of the options that does not include both integrity protection and encryption can reduce the processing burden at the user equipment and avoid over-security protection in the network.

[0021] Messages with measured data may be sent to and from the SCG via the master node. Similarly, configuration information may be sent to and from the SCG via the master node. For example, the method may further include receiving, at the user equipment, a first configuration message including primary measurement configuration information and a second configuration message including secondary measurement configuration information from the master node via a first channel, where the primary measurement configuration information is different from the secondary measurement configuration. In other words, two separate sets of configuration information may be maintained for the network: one set for the MCG and one set for the SCG. The separate sets of configuration information may be sent in separate messages or may be sent in the same configuration message.

[0022] Alternatively, a second channel between the user equipment and the network can be used to separately establish MCG and SCG configurations at the user equipment. For example, the method can further include receiving, at the user equipment via a first channel, a first configuration message including primary measurement configuration information from a primary node, and receiving, at the user equipment via a second channel, a second configuration message including secondary measurement configuration information from a secondary node, wherein the primary measurement configuration information is different from the secondary measurement configuration.

[0023] Alternatively, there can be a single set of configuration information for both MCG and SCG. Accordingly, the method can further include: receiving, at the user equipment via a first channel, a single configuration message from a primary node, the single configuration message including common measurement configuration information for collecting and reporting artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within both the primary cell group and the secondary cell group.

[0024] A second signaling radio bearer can be used to separately report data for SCG measurements and data for MCG measurements. The user equipment can perform collection of AI / ML data to support AI / ML functions within the primary cell group and report the collected AI / ML data to the primary node via a first signaling radio bearer. Separately, sequentially, or simultaneously, the user equipment can perform collection of AI / ML data to support AI / ML functions within the secondary cell group and report the collected AI / ML data to the secondary node via a second signaling radio bearer.

[0025] In any arrangement, the AI / ML data collected or measured can include at least one of the following: location information of the user equipment, one or more measurements from one or more nodes within the user equipment and / or the network. The one or more measurements can include one or more of wireless measurements, intra-frequency measurements, inter-frequency measurements, inter-RAT measurements, channel state information reference signal measurements, synchronization signal block measurements, synchronization signal or physical broadcast channel measurements. The measurement data can include location information of the user equipment, such as positioning, location measurement, and / or mobility measurement. For example, when the model is predicting an optimized network energy saving decision, configuring the user equipment can include configuring wireless measurements related to serving cells and neighboring cells associated with the user equipment (e.g., RSRP, RSRQ, and SINR) and cell-level and beam-level UE measurements. When the model is used for load balancing decisions, configuring the user equipment can include wireless measurements related to serving cells and neighboring cells associated with the user equipment (e.g., RSRP, RSRQ, and SINR) and measurements tracking the mobility history of the user equipment. When the model is used for mobility optimization, configuring the user equipment can include configuring measurements tracking the mobility history of the user equipment and wireless measurements related to serving cells and neighboring cells associated with the UE location information (e.g., RSRP, RSRQ, SINR).

[0026] The measurement configuration information may include some or all of the following parameters: a measurement object that defines the object to be measured, a reporting configuration, a measurement identity that links each reporting configuration to the measurement object, a quantity configuration that defines any filtering to be applied, and a measurement gap that defines the period during which the user equipment reports. Each measurement object may have one or more reporting configurations. The reporting configuration may include a reporting criterion, which is the criterion for triggering the user equipment to send a measurement report to the network. For example, it may point to an AI / ML model within the network or to different locations in the network specified in the reporting configuration. The criterion may be periodic or conditional, such as in response to an event such as receiving a message or in response to a condition satisfied by the user equipment. For example, the satisfaction of the condition may be determined by comparing a measurement with a threshold, and the measurement being compared may involve one or more of RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), or SINR (Signal-to-Interference-plus-Noise Ratio). By including the criterion for triggering a report, the frequency at which messages are sent can be controlled.

[0027] Another way to control the frequency at which messages are sent is to configure the message structure for reporting input data. The measurement configuration information may also define a message structure for reporting multiple pieces of data simultaneously in a single message sent from the user equipment to the network, where the message structure includes sequence information for each piece of data in the message, whereby the receiver can sort the multiple pieces of data in order (e.g., chronological order). The user equipment can avoid frequent reporting of multiple pieces of AI / ML data information in this newly proposed message structure. The sequence information may be a sequence number or timing information for each piece of AI / ML data. The number of AI / ML data that should be included in the report message may also be configured by an RRC message. Each piece of data may be for the same objective (measurement object) or for the same AI / ML model.

[0028] The at least one configuration message may further include prioritization configuration information and / or security configuration information. The prioritization configuration information is used to configure the user equipment to define a lower priority for messages including data related to AI / ML functions than for other messages transmitted between the user equipment and the network. The security configuration information is used to configure the user equipment to apply integrity protection and / or encryption to the messages between the user equipment and the network.

[0029] Once the user equipment has been configured, the user equipment can be reconfigured for one or both of the MCG and the SCG. The method may also include receiving, at the user equipment, at least one reconfiguration message, where the at least one reconfiguration message includes at least one of the following: primary measurement reconfiguration information for reconfiguring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the primary cell group; and secondary measurement reconfiguration information for reconfiguring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the primary cell group. The reconfiguration message can be received from the master node at a first receiver or from the secondary node at a second receiver. Before implementing the received configuration information, the user equipment can then determine whether the at least one reconfiguration message includes a release indicator from the network, the release indicator indicating to the user equipment to release any previous configuration of the user equipment to support AI / ML functions within the network. When it is determined that there is a release indicator, the user equipment can then be reconfigured using the reconfiguration information in the at least one reconfiguration message. The at least one reconfiguration message can be, for example, an RRC reconfiguration message.

[0030] A user equipment generally has three states. In a first state, the user equipment is connected to the network and the connection is active (i.e., messages are transmitted between the user equipment and the network). Once the user equipment has been connected to the network, the user equipment can transition to a second state where the connection is inactive. There is also a third state before a connection is established and where the user equipment is idle. These states can be referred to as RRC_Connected, RRC_INACTIVE, and RRC_IDLE. Appropriate RRC messages from the network to the user equipment will cause the user equipment to transition between these states. For example, a release message (e.g., RRC_release) received by the user equipment from the network will cause the user equipment to transition to the idle state (from a connected or inactive state).

[0031] When the user equipment is in a connected state, messages having AI / ML data to support AI / ML functions within the network can be transmitted between the user equipment and the rest of the network as described above. However, when the user equipment is in an inactive state or an idle state, it is also necessary to support AI / ML functions within the network. The method can include receiving, at the user equipment, a release message that indicates the user equipment changes to one of an inactive state and an idle state, and the release message includes mode change configuration information for configuring the user equipment to support AI / ML functions within the network when in the idle state or the inactive state, wherein in the inactive state, the user equipment remains connected to the network but does not send AI / ML data to the network, and wherein in the idle state, the user equipment disconnects from the network.

[0032] Thus, according to another aspect, there is provided a method of using a user equipment to support AI / ML functions within a wireless communication network, the method including: establishing a first radio resource control (RRC) connection from the user equipment to the network using a first signaling radio bearer; receiving, at the user equipment, via the first signaling radio bearer, at least one configuration message that includes configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the network; receiving, at the user equipment, configuring the user equipment using the configuration information; and subsequently receiving, at the user equipment, a release message that indicates the user equipment changes to one of an inactive state and an idle state and includes mode change configuration information for configuring the user equipment to support AI / ML functions within the network when in the idle state or the inactive state, wherein, in the inactive state, the user equipment remains connected to the network but does not send AI / ML data to the network, and wherein, in the idle state, the user equipment disconnects from the network.

[0033] The release message can be any suitable RRC message, including for example, RRCRelease that changes the user equipment from a connected state to an idle state and RRCRelease with suspendconfig that changes the user equipment from a connected state to an inactive state. The release message can be received by any suitable radio bearer, particularly the first signaling radio bearer, such as SRB1, which is typically preferred for messages establishing and releasing connections. The at least one configuration message can include any of the above types of configuration information. For example, the configuration message can include configuration information for configuring a second signaling radio bearer for the user equipment to convey data related to AI / ML functions, measurement configuration information, prioritization configuration information, and security configuration information between the user equipment and the network. When the network is a DC network, the configuration message can include primary measurement configuration and / or secondary configuration measurement and / or common measurement configuration.

[0034] A release message that can cause the user equipment to change to an inactive state or an idle state, and change the state of the user equipment as indicated in the release message. When the user equipment is in an inactive state or an idle state, the user equipment can perform collection of AI / ML data. The AI / ML data can be as described above and can include at least one of the following: location information of the user equipment, one or more measurements from the user equipment and / or one or more nodes within the network. It should be understood that the user equipment can change between the idle, inactive, and connected states when receiving an appropriate message.

[0035] The AI / ML data can be sent from the user equipment to the network in response to a report message requesting the AI / ML data from the network. The report message can be regarded as a request from the network for the results of measurements and / or data collection at the user equipment. In response to receiving the report message, the user equipment can send the collected AI / ML data to the network. The report message and the response message can be sent using any suitable radio bearer (e.g., SRB3 or a newly configured SRB), and / or can be sent via the MCG when there is dual connectivity or targeting the SCG. The report message can be triggered automatically by the network or can be in response to a data available message from the user equipment, which indicates that the collected AI / ML data is available.

[0036] The report message can be included in any suitable RRC message, such as an RRCSetup, RRCResume, or RRCReconfiguration message. The collected AI / ML data can be sent in any suitable RRC message as a response to the report message. For example, the user equipment can send an RRCSetupcomplete message in response to receiving an RRCSetup message and an RRCResumecomplete message in response to receiving an RRCResume message.

[0037] The RRC Setup message can be received when the user equipment is in the idle state and includes information for configuring the user equipment to transition from the idle state to the connected state. When the user equipment is in the inactive state, the RRC Resume message can be received, and the RRC Resume message includes information for configuring the user equipment to transition from the inactive state to the connected state. In other words, when the reporting message is included in such an RRC message, in addition to being instructed to report the collected AI / ML data, the user equipment also receives an instruction to change the state. Therefore, the method can include receiving, at the user equipment, a state change message (e.g., a resume or setup message), the state change message including configuration information for configuring a change in the state at the user equipment to the connected state to enable the user equipment to send AI / ML data.

[0038] The state change message can be received simultaneously with the reporting message. Alternatively, the reporting message can be received after the user equipment has changed to the connected state (i.e., after the state change has been achieved). When the user equipment is in the connected state, the user equipment can receive the reporting message in the form of a request for information (e.g., a UE Information Request message) and respond with a corresponding message (i.e., a UE Information Response message).

[0039] As described above, the reporting message can be triggered by a data available message sent from the user equipment. When in the idle or inactive state, the user equipment is not fully connected, and thus the data available message can be included in any suitable RRC message requesting a change in the state of the user equipment, such as an RRC Setup Request or an RRC Resume Request. For example, the user equipment can send an RRC Setup Request message that triggers an RRC Setup message from the network and an RRC Resume Request message that triggers an RRC Resume message from the network. The reporting message can be included together with the state change message or can occur after the state of the user equipment has changed.

[0040] When changing from the connected state to the idle or inactive state, especially to the inactive state, the user equipment can store the current configuration settings for the AI / ML function. In other words, the user equipment can store the configuration settings related to the secondary radio bearer, the measurement configuration settings, the prioritization configuration settings, and the security configuration settings. When the network is DC, the user equipment can also store the primary measurement configuration and / or the secondary configured measurement and / or the common measurement configuration. The configuration settings can be stored as a context for supporting the AI / ML function within the network. By storing the configuration settings, the configuration settings can be restored when the user equipment transitions back to the connected state.

[0041] A user equipment can be any suitable device that a user uses to connect to a network and is typically mobile, such as a mobile device or a terminal. A wireless communication network can also be referred to as a mobile communication network or a wireless communication network. Once the user equipment is connected to the network, the network can be considered to include the user equipment and other nodes, as described below.

[0042] The network can include multiple nodes (also referred to as base stations or cells) and a central server (e.g., an operation, administration, and management OAM server), and AI / ML models can be present at one or more of the nodes and / or in the central server. The network can be a next-generation dual-connectivity mobile communication system, hereinafter referred to as an NR-DC or EN-DC network. Data related to the AI / ML function can include the input and output data of the AI / ML models located within the network or at the user equipment. The input can include one or more of the following: data for training the AI / ML models, data to be used when inference is performed by the trained AI / ML models. The output data can include the output data from the AI / ML models at the time of inference and the feedback data from the AI / ML models.

[0043] At least one configuration message received at the user equipment can be any suitable RRC message, such as an RRCReconfiguration, RRCSetup, RRCResume, RRCRelease message, or a newly defined RRC message. The primary measurement configuration information, secondary measurement configuration information, bearer configuration information, prioritization configuration information, and security configuration information can be sent simultaneously in the same configuration message. Alternatively, separate messages can be used for some or each type of configuration information.

[0044] Each cell within the wireless communication network can broadcast system information that indicates whether the cell supports the AI / ML function, such as indicating whether the cell has an AI / ML that needs to be trained or can be used for inference. When the user equipment acquires the system information, the user equipment can establish an RRC connection and receive at least one configuration message. When the user equipment has previously connected to the network using a specific cell, the user equipment can select a cell that supports the AI / ML function and establish a new connection to the network via the selected cell. The user equipment can be configured to send capability information to the network (e.g., to the selected cell), where the capability information includes the user equipment's capability to support the AI / ML function of the cell (network).

[0045] Once the user equipment is configured, for example, using some or all of the master measurement configuration information, secondary measurement configuration information, bearer configuration information, prioritization configuration information, and security configuration information, a method is also provided for supporting AI / ML functions within the network by using the user equipment to send data related to AI / ML functions to the network (e.g., to a cell within the network having an AI / ML model). As described above, the user equipment may already be configured to measure the transmitted data before transmission. The user equipment may also receive messages from the network to support AI / ML functions, such as to trigger the measurement and reporting of AI / ML data and / or reconfigure the AI / ML functions at the user equipment.

[0046] The above methods focus on the steps performed by the user equipment, but it should be understood that the corresponding steps are also performed by the network, particularly by nodes within the network.

[0047] Once the user equipment is configured, according to another aspect of the present technology, a method for applying AI / ML functions within the network is described. For example, a node within the network having an AI / ML model may receive AI / ML data from the user equipment and may use the received AI / ML data to train the AI / ML model. Alternatively, a node within the network having an AI / ML model may receive AI / ML data from the user equipment and may infer an output from the AI / ML model.

[0048] The AI / ML model or each AI / ML model in the system may be a pre-trained general ML model that can be obtained from a data repository, and / or may be a general model that has been trained by a central server on data accessible to the central server with full precision. The AI / ML model in the form of a neural network includes multiple layers, each layer having a set of general weights. One or more local models may also exist within the system, and each local model may be a similar model, where each layer has a set of local weights. Each local model may be trained using a set of local data samples that can be stored in a database on the user equipment and / or measured by the user equipment.

[0049] In a related method of the present technology, a computer-readable storage medium including instructions is provided, which when executed by a processor causes the processor to perform any of the methods described herein.

[0050] As will be understood by those skilled in the art, the present technology may be embodied as a system, method, or computer program product. Accordingly, the present technology may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. All of the above methods may be considered computer-implemented methods.

[0051] In addition, the present technology may take the form of a computer program product embodied in a computer-readable medium having computer-readable program code embodied thereon. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable medium may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0052] The computer program code for performing the operations of the present technology may be written in any combination of one or more programming languages, including object-oriented programming languages and conventional procedural programming languages. The code components may be embodied as procedures, methods, etc., and may include sub-components that may take the form of instructions or sequences of instructions at any level of abstraction from direct machine instructions of a native instruction set to high-level compiled or interpreted language constructs.

[0053] Embodiments of the present technology also provide a non-transitory data carrier carrying code which, when implemented on a processor, causes the processor to perform any of the methods described herein.

[0054] These technologies also provide processor control code to implement the above methods, for example, on a general-purpose computer system or on a digital signal processor (DSP). These technologies also provide a carrier wave carrying the processor control code to implement any of the above methods at runtime, particularly on a non-transitory data carrier. The code may be provided on a carrier such as a disk, a microprocessor, a CD or DVD-ROM, on a programmable memory such as a non-volatile memory (e.g., flash memory) or a read-only memory (firmware), or on a data carrier such as an optical or electrical signal carrier. The code (and / or data) for implementing embodiments of the technologies described herein may include source, object, or executable code of a conventional programming language (such as Python, C, or assembly code), code for setting or controlling an ASIC (application-specific integrated circuit) or an FPGA (field-programmable gate array), or code for a hardware description language (such as Verilog(RTM) or VHDL (very high speed integrated circuit hardware description language)). As will be understood by those skilled in the art, such code and / or data may be distributed among multiple coupled components communicating with each other. The technology may include a controller that includes a microprocessor, a working memory, and a program memory coupled to one or more components of the system.

[0055] Those skilled in the art will also appreciate that all or part of the logical methods according to the embodiments of the present technology can be appropriately embodied in a logic device including logic elements for performing the steps of the above methods, and such logic elements can include components such as logic gates in, for example, a programmable logic array or an application specific integrated circuit. Such a logic arrangement can be further embodied in an enabling element for temporarily or permanently establishing a logic structure in such an array or circuit using, for example, a virtual hardware description language, which can be stored and transmitted using a fixed or transportable carrier medium.

[0056] In an embodiment, the present technology can be implemented in the form of a data carrier having functional data thereon, the functional data including functional computer data structures to enable the computer system to perform all steps of the above methods when loaded into and operated by the computer system or network.

[0057] The above methods can be performed in whole or in part on a device (i.e., a user equipment in the form of an electronic device).

[0058] According to another aspect of the present technology, there is provided a user equipment, which includes: a first receiver and a first transmitter, which can be connected to a master node of a master cell group in a dual-connectivity communication network; a second receiver and a second transmitter, which can be connected to a secondary node of a secondary cell group in the dual-connectivity communication network; and a processor, which is configured to: establish a radio resource control (RRC) connection from the first receiver and the first transmitter at the user equipment to the master node through a first signaling radio bearer; receive at least one configuration message at the user equipment through the first signaling radio bearer, where the at least one configuration message includes at least one of the following: primary measurement configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the master cell group; and secondary measurement configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the master cell group; and configure the user equipment using the configuration information in the at least one configuration message. When the user equipment has been configured to collect and report AI / ML data to support AI / ML functions within the master cell group, the user equipment can also perform the collection of the AI / ML data and report the collected AI / ML data to the master node via the first signaling radio bearer. The features described above with respect to the first aspect also apply to this aspect.

[0059] The model can be processed by an AI - specific processor designed in a hardware structure designated for AI - model processing. The AI model can be obtained through training. Here, "obtained through training" means that the predefined operation rules or AI model configured to perform the desired features (or purposes) are obtained by training a basic AI model with multiple training data using a training algorithm. The AI model can include multiple neural network layers. Each neural network layer among the multiple neural network layers includes multiple weight values and performs neural network calculations through the calculation between the calculation result of the previous layer and the multiple weight values.

[0060] As described above, the present technology can be implemented using an AI model. Functions associated with AI can be executed by a non - volatile memory, a volatile memory, and a processor. The processor can include one or more processors. At this time, the one or more processors can be a general - purpose processor (such as a central processing unit (CPU), an application processor (AP), etc.), a graphics - processing unit only (such as a graphics - processing unit (GPU)), a vision - processing unit (VPU), and / or an AI - specific processor (such as a neural - processing unit (NPU)). The one or more processors control the processing of input data according to predefined operation rules or an artificial - intelligence (AI) model stored in the non - volatile memory and the volatile memory. The predefined operation rules or AI model are provided through training or learning. Here, provided through a learning means, by applying a learning algorithm to multiple learning data, a predefined operation rule or AI model with desired characteristics is made. The learning can be performed in the device itself that executes the AI according to the embodiment, and / or can be implemented through a separate server / system.

[0061] The AI model can be composed of multiple neural network layers. Each layer has multiple weight values and performs layer operations through the operation of calculating the previous layer and the multiple weights. Examples of neural networks include, but are not limited to, convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), generative adversarial networks (GANs), and deep Q - networks.

[0062] A learning algorithm is a method for using multiple learning data to train a predetermined target device (e.g., a node) so as to enable, permit, or control the target device to make a determination or prediction. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi - supervised learning, or reinforcement learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Embodiments of the present technology will now be described by way of example only with reference to the accompanying drawings.

[0064] Figure 1It is a schematic diagram of an LTE system according to an embodiment disclosed herein.

[0065] Figure 2 It shows a radio protocol structure for an LTE system according to an embodiment disclosed herein.

[0066] Figure 3 It is a schematic diagram of a wireless communication system according to an embodiment disclosed herein.

[0067] Figure 4 It shows a radio protocol structure for a wireless communication system according to an embodiment disclosed herein.

[0068] Figure 5 It is a schematic block diagram of a functional framework 500 for implementing artificial intelligence or machine learning in a radio access network according to an embodiment disclosed herein.

[0069] Figure 6 It shows a state diagram of a user equipment according to an embodiment disclosed herein.

[0070] Figure 7 It shows a method by which a user equipment can obtain system information from a network according to an embodiment disclosed herein.

[0071] Figure 8 It is a flowchart showing the process of a UE switching from RRC idle mode to RRC connected mode according to an embodiment disclosed herein.

[0072] Figure 9 It is a flowchart showing an example use case according to an embodiment disclosed herein, where AI / ML model training is completed at a central server and AI / ML model inference is completed at one or more nodes of the network.

[0073] Figure 10 It is a flowchart showing another example use case according to an embodiment disclosed herein, where AI / ML model training is completed at a node and AI / ML model inference is completed at one or more nodes of the network.

[0074] Figure 11A It is a schematic diagram showing the communication between a user equipment, a master cell group (MCG) and a secondary cell group (SCG) according to an embodiment disclosed herein, where AI / ML configurations are maintained separately for the MCG and the SCG.

[0075] Figure 11B It shows Figure 11A a flowchart of the communication in the system of

[0076] Figure 11Cis a flowchart showing communication between a user equipment, a master cell group, and a secondary cell group according to embodiments disclosed herein, where a joint AI / ML configuration is maintained for the MCG and SCG.

[0077] Figure 11D is a flowchart showing simplified communication between a user equipment, a master cell group, and a secondary cell group according to embodiments disclosed herein.

[0078] Figure 11E is a schematic diagram showing an alternative arrangement of simplified communication between a user equipment, a master cell group, and a secondary cell group.

[0079] Figure 12A is a flowchart showing steps of a first aspect of the present technology related to a DC network.

[0080] Figure 12B is a flowchart showing steps of a second aspect of the present technology related to a user equipment when in an idle / inactive state.

[0081] Figure 13 is a block diagram of a system according to embodiments disclosed herein, the system including a node in a network and a user equipment connected to the node.

[0082] Figure 14 is a block diagram showing a terminal (or user equipment (UE)) according to embodiments disclosed herein.

[0083] Figure 15 is a block diagram showing a base station (BS) according to embodiments disclosed herein.

[0084] It can be noted that, to the extent possible, the same reference numerals are used in the drawings to denote the same elements. Further, those of ordinary skill in the art will understand that the elements in the drawings are shown for simplicity and may not necessarily be drawn to scale. For example, the dimensions of some elements in the drawings may be enlarged relative to other elements to help improve the understanding of aspects of the present invention. Additionally, one or more elements may be represented in the drawings by conventional symbols, and the drawings may show only the specific details relevant to understanding the embodiments of the present invention so as not to obscure the details of the drawings, which are clear to those of ordinary skill in the art who benefit from the description herein. Detailed Description

[0085] To meet the 5G network requirements for key performance and the ever-growing demands of mobile users, millions of base stations (BSs) are being deployed. This rapid growth brings problems of high energy consumption, CO2 emissions, and operating expenses (OPEX). Therefore, energy saving is an important use case that may involve different layers of the network, where mechanisms operate at different time scales.

[0086] Cell activation / deactivation is an energy-saving solution in the S124 spatial domain, which uses traffic offloading in a hierarchical structure to reduce the energy consumption of the entire radio access network (RAN). When the expected traffic volume is below a fixed threshold, the cell can be turned off, and the served UEs can be offloaded to a new target cell. Efficient energy consumption can also be achieved in other ways, such as reducing the load, modifying the coverage, or other RAN configuration adjustments. The optimal energy-saving decision depends on many factors, including the load conditions at different RAN nodes, the RAN node capabilities, the KPI / QoS (quality of service) requirements, the number of active UEs and UE mobility, the cell utilization rate, etc.

[0087] However, it is not easy to identify actions targeted at improving energy efficiency. Since the remaining active cells need to serve additional traffic, incorrect cell shutdown may seriously degrade the network performance. Incorrect traffic offloading actions may lead to deterioration rather than improvement of energy efficiency. Current energy-saving solutions are vulnerable to potential problems.

[0088] An example problem is inaccurate cell load prediction because current energy-saving decisions rely on the current traffic load without considering the future traffic load. Another example is the conflicting goals between system performance and energy efficiency. Maximizing the key performance indicators (KPIs) of the system is usually achieved at the expense of energy efficiency. Similarly, the most energy-efficient solution may affect the system performance. Therefore, it is necessary to balance and manage the trade-off between the two. Another example is the conventional energy-saving related parameter adjustment. Energy-saving related parameter configuration is set by traditional operations, for example, based on different thresholds of cell load for cell on / off, which is a somewhat rigid mechanism because it is difficult to set reasonable thresholds. Another example is an action that can produce local (e.g., limited to a single RAN node) improvement in energy efficiency while producing overall (e.g., involving multiple RAN nodes) deterioration in energy efficiency.

[0089] In addition to the need to save energy, the rapid traffic growth and multiple frequency bands used in commercial networks also pose challenges to the balanced distribution of traffic. To address this problem, load balancing has been proposed. The purpose of load balancing is to evenly distribute the load between cells and between cell areas, or to transfer part of the traffic from a congested cell or from a congested area of a cell, or to offload users from a cell, cell area, carrier, or RAT to improve the network performance. This can be done by optimizing handover parameters and handover actions. The automation of this optimization can provide a high-quality user experience while increasing the system capacity and also minimizing the human intervention in network management and optimization tasks.

[0090] However, the optimization of load balancing is not an easy task. Currently, load balancing decisions relying on the current / past state of cell load status are insufficient. The traffic load and resource status of the network change rapidly, especially in scenarios with high mobility and a large number of connections, which may lead to ping-pong handovers between different cells, cell overload, and deterioration of user service quality. It is difficult to guarantee the overall network and service performance when performing load balancing. For load balancing, user equipment (UE) in a congested cell can be offloaded to a target cell by means of a handover process or adapting the handover configuration. For example, if a UE with time-varying traffic load is offloaded to a target cell, the target cell may be overloaded due to the impact of a large amount of newly arrived traffic. It is difficult to determine whether the service performance after the offloading action meets the expected goals.

[0091] In addition to the need to save energy and perform load balancing, mobility management is a solution to ensure service continuity during mobility by minimizing call drops, RLFs, unnecessary handovers, and pings. For future high-frequency networks, as the coverage of a single node decreases, the frequency of UE handovers between nodes becomes higher, especially for high-mobility UEs. In addition, for applications characterized by strict quality of service (QoS) requirements such as reliability, latency, etc., QoE is sensitive to handover performance, making mobility management avoid unsuccessful handovers and reduce latency during the handover process. However, for traditional methods, it is challenging to achieve almost zero-fault handovers with a trial-and-error-based approach. Unsuccessful handover situations are the main cause of packet loss or additional latency during the mobile period, which is unexpected for applications intolerant of packet loss and low latency. In addition, due to the randomness and non-constancy of the transmission environment, the effectiveness of feedback-based adjustments may be weak. In addition to the baseline case of mobility, the optimization areas of mobility include dual connectivity, CHO, and DAPS, each of which has additional aspects to be addressed in mobility optimization.

[0092] There are various unexpected events associated with mobility. One example is a late intra-system handover. In this unexpected event, a radio link failure (RLF) occurs after the UE has stayed in a cell for a long period; the UE attempts to re-establish a radio link connection in a different cell. Another example is an early intra-system handover. In this unexpected event, an RLF occurs soon after a successful handover from a source cell to a target cell, or a handover failure occurs during the handover process; the UE attempts to re-establish a radio link connection in the source cell. Another example is an intra-system handover to the wrong cell. In this unexpected event, an RLF occurs soon after a successful handover from a source cell to a target cell, or a handover failure occurs during the handover process; the UE attempts to re-establish a radio link connection in a cell other than the source cell and the target cell. Another example is any potential problem that occurs during a successful handover process.

[0093] Accordingly, the present applicant has recognized the need to improve 5G networks, particularly for UEs configured for dual connectivity and / or when the UE is not in a connected state.

[0094] Broadly speaking, the present technology generally relates to supporting AI / ML capabilities for UEs configured with carrier aggregation (CA) or dual connectivity (DC) in the RRC connected state, which can allow the network to use separate radio resources for AI / ML capabilities, thereby improving implementation flexibility. To support dual connectivity, we describe the handling of multiple AI / ML configurations, secondary cell group (SCG) configurations for AI / ML, and delta configurations, handled by a specific single radio bearer (SRB3) or an RB configured for AI / ML capabilities (e.g., SRBx or DRB and / or split SRB handling).

[0095] If a UE not fully connected to the network supports AI / ML capabilities, such as a UE in the RRC inactive or RRC idle state rather than RRC connected, the network can obtain more information and more time to train AI / ML models. The network can also prepare the AI / ML model in advance to control the UE before it transitions into the RRC connected state. To support capabilities in the inactive state (RRC inactive), there may be system information enhancements, paging enhancements; considerations of how to measure (or collect) AI / ML data, how to configure AI / ML configurations, when to report and release, and when to stop measuring or collecting AI / ML data. There may also be UE inactive context handling and / or UE restrictions to avoid conflicts with SDT (Small Data transmission) handling.

[0096] More broadly, we describe supporting AI / ML capabilities in a 5G network. This includes AI / ML configuration / reporting, signaling notification procedures, and operations at the user equipment (UE). To reduce the UE processing burden, different from the mandatory security protection for signaling radio bearers (SRBs), new security protection (integrity protection or encryption) mechanisms are proposed. To avoid affecting network control of the UE, a new priority mechanism is introduced by defining rules for SRBs or introducing new SRBs or allocating separate data radio bearers (DRBs). To avoid frequent reporting, a new message structure is designed to report multiple data for the same target in chronological order in one message. To support UE mobility for AI / ML capabilities, radio resource control (RRC) procedures are proposed. To improve the reliability of AI / ML capabilities, a retransmission mechanism is proposed.

[0097] In summary, the present technology proposes technical enhancements to support AI / ML capabilities and extend them to the RRC inactive (or idle) state, carrier aggregation, and dual connectivity, as described below.

[0098] Definition of Terms, Symbols and Abbreviations, Acronyms

[0099]

[0100]

[0101]

[0102] Data Collection: Data collected from network nodes, management entities, or user equipment (UE) that serves as the basis for AI / ML model training, data analysis, and inference. Data collection is the function that provides input data to the model training and model inference functions. AI / ML algorithm-specific data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) is not performed in the data collection function. Examples of input data can include measurements (or responses or information or reports) from the UE or different network entities, feedback from an Actor, outputs from an AI / ML model.

[0103] Training Data: Data required as input to the AI / ML model training function.

[0104] Inference Data: Data required as input to the AI / ML model inference function.

[0105] AI / ML (Artificial Intelligence / Machine Learning) Model: A data-driven algorithm that applies machine learning techniques and generates a set of outputs consisting of prediction information and / or decision parameters based on a set of inputs. It also refers to AI / ML (model) training or inference or training data or prediction information or decision parameters or a set of inputs. AI / ML data refers to AI / ML (model) training or inference or training data or prediction information or decision parameters or a set of inputs for AI / ML or an AI / ML model. AI / ML configuration includes the type of AI / ML model, model inference, model training, algorithms, or how to construct an RRC (Radio Resource Control) message for a response (or report) that includes AI / ML data (e.g., what information should be included), or how to send the RRC message (e.g., period, timer-related information, etc.) from a transmitter (UE or gNB) to a receiver (gNB or UE). AI / ML data can refer to measurement reports (e.g., for beams or SSB (Synchronization Signal Block) or CSI (Channel State Information) or CRS (Cell-Specific Reference Signal)) and CSI reports. AI / ML configuration can include measurement configuration (e.g., for beams or SSB or CSI or CRS) and CSI measurement configuration (e.g., aperiodic CSI, periodic CSI, etc.). AI / ML functionality means all this information (e.g., AI / ML data and AI / ML configuration), measurement configuration and reports, requests / reports for training data, and the training and inference processes described below.

[0106] AI / ML Training: An online or offline process of training an AI / ML model by learning the features and patterns that best represent the data and obtaining a trained AI / ML model for inference. Model training is the function that performs AI / ML model training, validation, and testing, which can generate model performance metrics as part of the model testing process. If needed, the model training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered by the data collection function.

[0107] Model Deployment / Update: Used to initially deploy a trained, validated, and tested AI / ML model to the model inference function or deliver an updated model to the model inference function.

[0108] AI / ML Inference: The process of using a trained AI / ML model to make predictions or guide decisions based on the collected data and the AI / ML model. Model inference is the function that provides the AI / ML model inference output (e.g., prediction or decision). The model inference function can provide model performance feedback to the model training function when applicable. If needed, the model inference function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the inference data delivered by the data collection function.

[0109] Output: The inference output of the AI / ML model generated by the model inference function. The details of the inference output are use-case specific.

[0110] Model performance feedback: When available, it can be used to monitor the performance of the AI / ML model.

[0111] Actuator: This is the function that receives the output from the model inference function and triggers or executes corresponding actions. The actuator can trigger actions against other entities or against itself.

[0112] Feedback: Deriving training data, inference data, or information that may be required to monitor the performance of the AI / ML model and its impact on the network by updating KPIs (Key Performance Indicators) and performance counters.

[0113] Federated learning (also known as collaborative learning) is a machine learning technique that trains algorithms across multiple decentralized edge devices or servers that hold local data samples without exchanging them. This approach contrasts with traditional centralized machine learning techniques where all local datasets are uploaded to a single server and more classical decentralized methods that typically assume local data samples are identically distributed. Federated learning enables multiple actuators (or UEs) to build a common, robust machine learning model without sharing data, thus allowing critical issues such as data privacy, data security, data access rights, and access to heterogeneous data to be addressed. Its applications span multiple industries such as defense, telecommunications, Internet of Things, and pharmaceuticals.

[0114] Split learning is a newly developed technique that allows participating entities to train machine learning models without sharing any raw data. In principle, both federated learning and split learning have similar properties, with the benefit of data privacy effects.

[0115] The signaling radio bearer (SRB) is defined as a radio bearer (RB) that is used only for transmitting RRC (Radio Resource Control) and NAS (Non-Access Stratum) messages. More specifically, the following SRBs are defined:

[0116] SRB0 is used for RRC messages using the CCCH (Common Control Channel) logical channel.

[0117] SRB1 is used for the first RRC message (which may include the carried NAS message) and for NAS messages before the establishment of SRB2, all of which use the DCCH logical channel. It can be used for the second RRC message including AI / ML related information (e.g., AI / ML data, training data, update information, response, offset of AI / ML, etc.), but the second RRC message may have a lower priority than the first RRC message (e.g., the carried NAS message, NAS messages before the establishment of SRB2, RRC messages for establishing (re)connection and (re)configuration, i.e., RRCSetupRequest, RRCSetup, RRCSetupComplete, RRCResumeRequest, RRCResume, RRCResumeComplete, RRCReconfiguration, RRCReconfigurationComplete, RRCRestablishment, RRCRestablishmentRequest, etc.) because the first RRC message is more important than the second RRC message to support the connection management and mobility support of the UE. When the first message and the second message are generated together or coexist in the buffer, the first message may have priority over the second RRC message and may be submitted to the lower layer (e.g., PDCP layer) and sent first.

[0118] SRB2 is used for NAS messages and RRC messages, which include recorded measurement information or AI / ML related information (e.g., AI / ML data, training data, update information, response, offset of AI / ML, etc.), all using the DCCH logical channel. SRB2 has a lower priority than SRB1 and can be configured by the network after the activation of AS (access stratum) security;

[0119] SRB3 is used for specific RRC messages when the UE is in (NG)EN-DC or NR-DC or RRC messages including AI / ML related information (e.g., AI / ML data, training data, update information, response, offset of AI / ML, etc.), all using the DCCH logical channel;

[0120] SRB4 is used for RRC messages including application layer measurement report information or RRC messages including AI / ML related information (e.g., AI / ML data, training data, update information, response, offset of AI / ML, etc.), all using the DCCH logical channel. SRB4 can only be configured by the network after the activation of AS security.

[0121] SRBx (e.g., SRB5) is used for RRC messages including AI / ML related information (e.g., AI / ML data, training data, update information, responses, offsets of AI / ML, etc.), all using the DCCH logical channel. SRBx can be configured by the network after AS security activation. However, in cases where SRBx is not required to perform encryption and integrity protection on RRC messages, the network can configure SRBx before AS security activation. When SRBx is configured to send / receive RRC messages for AI / ML related information, the network can configure logical channel prioritization parameters (i.e., allocation of priorities and prioritized bit rate (PBR)) for the LCP process performed in the MAC entity (or layer) for SRBx to control the prioritization of data transmission. In the present invention, SRBx is a new SRB configured for AI / ML functions and can be named SRB5.

[0122] DRB (Data Radio Bearer): This is for AI / ML related information (e.g., AI / ML data, training data, update information, responses, offsets of AI / ML, etc.), all using the DCCH logical channel. This DRB can be configured by the network after AS security activation. However, in cases where the DRB is not required to perform encryption and integrity protection on AI / ML data, the network can configure the DRB before AS security activation. When the DRB is configured to send / receive AI / ML data, the network can configure logical channel prioritization (LCP) parameters (i.e., allocation of priorities and prioritized bit rate (PBR)) for the LCP process performed in the MAC entity (or layer) for the DRB to control the priority of data transmission.

[0123] NAS Messages: In the downlink, the carriage of NAS messages is only used for one subordinate (i.e., with joint success / failure) process: bearer establishment / modification / release. In the uplink, the carriage of NAS messages is only used for transmitting initial NAS messages during connection establishment and connection recovery. NAS messages transmitted via SRB2 are also included in RRC messages, however, they do not include any RRC protocol control information.

[0124] AS (Access Stratum) Security: Once AS security is activated, all RRC messages on SRB1, SRB2, SRB3, and SRB4 (including those RRC messages that contain NAS messages) are integrity protected and encrypted by PDCP (Packet Data Convergence Protocol). NAS by default independently applies integrity protection and encryption to NAS messages. However, even when AS security is activated, some RRC messages (e.g., RRC messages for AI / ML data) may not be integrity protected or encrypted by PDCP according to configuration (configured by RRC messages), or according to predefined rules (e.g., for specific RRC messages only, no integrity protection (integrity verification) or no encryption (decryption)), or according to an indication from RRC to PDCP regarding whether to perform encryption or integrity protection. This can allow RRC messages to be unprotected and unencrypted, RRC messages to be unprotected but encrypted, and RRC messages to be protected but unencrypted in order to reduce the processing burden on the UE and avoid over-security protection in the RAN.

[0125] For operations with shared spectrum channel access, SRB0, SRB1, and SRB3 are assigned the highest priority channel access priority category (CAPC) (i.e., CAPC = 1), while the CAPC of SRB2 is configurable.

[0126] System Architecture

[0127] Figure 1 Shows a Long-Term Evolution (LTE) system to which the AI / ML techniques described below can be applied. Refer to Figure 1 , the radio access network of the LTE system 10 includes next-generation base stations 16a, 16b, 16c, and 16d, a Mobility Management Entity (MME) 12, and a Serving Gateway (S-GW) 14. The User Equipment 18 (hereinafter referred to as UE or terminal) accesses the external network through eNBs 16a, 16b, 16c, and 16d and the S-GW 14. The next-generation base stations are also referred to as evolved Node Bs or cells, hereinafter referred to as eNBs, Node Bs, cells, or base stations.

[0128] In Figure 1In this, eNBs 16a, 16b, 16c, and 16d correspond to the existing Node Bs of UMTS (Universal Mobile Telecommunications System). The eNBs are connected to the UEs 18 via radio channels and perform more complex roles than the existing Node Bs. In the LTE system 10, since all user services related to real-time services (such as Voice over IP (VoIP)) via the Internet Protocol are provided through shared channels, a device that performs scheduling by collecting status information (such as buffer status, available transmit power status, and channel status of the UE) is required, and the eNBs 16a, 16b, 16c, and 16d are responsible for this function of the device. Generally speaking, one eNB controls multiple cells. For example, in order to achieve a transmission rate of 100 Mbps, the LTE system 10 uses Orthogonal Frequency Division Multiplexing (OFDM) as the radio access technology in a 20 MHz bandwidth. In addition, the LTE system 10 adopts an Adaptive Modulation and Coding Scheme (hereinafter referred to as AMC) to determine the modulation scheme and channel coding rate based on the channel status of the UE. The S-GW 14 is a device for providing data bearers and generating or removing data bearers under the control of the MME 12. In addition to the mobility management function of the UE, the MME 12 is also responsible for various control functions and is connected to multiple base stations.

[0129] Figure 2 shows the radio protocol structure in the Figure 1 LTE system as shown. Referring to Figure 2 , the radio protocol of the LTE system includes Packet Data Convergence Protocol (PDCP) 220 and 230, Radio Link Control (RLC) 222 and 232, and Medium Access Control (MAC) 224 and 234 in the UE 218 and eNB 216, respectively. The Packet Data Convergence Protocol (PDCP) 226 and 236 are used to perform operations such as IP header compression / recovery.

[0130] The main functions of PDCP are summarized as follows: Header compression and decompression only for Robust Header Compression (ROHC); Transmission of user data, and in-sequence transmission of upper layer protocol data units (PDUs) during the PDCP reconstruction process in RLC acknowledged mode (AM); Sequence reordering (for split bearers in DC (only RLC AM supported): Routing of PDCP PDUs for transmission and reordering of PDCP PDUs for reception); Duplicate detection of lower layer service data units (SDUs) during the PDCP reconstruction process in RLC AM; Retransmission of PDCP SDUs during handover, and for split bearers in DC, retransmission of PDCP PDUs during the PDCP data recovery process in RLC AM; Encryption and decryption; and Event-based SDU discard in the uplink.

[0131] The Radio Link Control (hereinafter referred to as RLC) 222 and 232 perform Automatic Repeat reQuest (ARQ) operations by reconfiguring the Packet Data Convergence Protocol (PDU) or the RLC Service Data Unit (SDU) to an appropriate size. The main functions of the RLC include the transfer of upper layer PDUs and RLC re-establishment. Only for AM data transfer, the main functions of the RLC include the ARQ function (error correction by ARQ), re-segmentation of RLC data PDUs, and protocol error detection. Only for Unacknowledged Mode (UM) and AM data transfer, the main functions of the RLC include concatenation, segmentation, and reassembly of RLC SDUs, reordering of RLC data PDUs, duplicate detection, and RLC SDU discard.

[0132] The Medium Access Control (MAC) 224, 234 is connected to multiple RLC layer devices configured in a User Equipment (UE) 218. The MAC 224, 234 can perform operations of multiplexing RLC PDUs into MAC PDUs and demultiplexing RLC PDUs from MAC PDUs. The main functions of the MAC are summarized as follows: mapping between logical channels and transport channels, multiplexing MAC SDUs belonging to one or different logical channels onto transport blocks (TBs) transmitted to the physical layer over the transport channel / demultiplexing transport blocks (TBs) from the physical layer over the transport channel into MAC SDUs belonging to one or different logical channels, scheduling information reporting, error correction by Hybrid Automatic Repeat reQuest (HARQ), priority handling between logical channels of a UE, priority handling between UEs by dynamic scheduling, Multimedia Broadcast Multicast Service (MBMS) identification, transport format selection, and padding.

[0133] The Physical Layer 226, 236 can perform the following operations: channel encoding and modulating upper layer data, shaping the upper layer data into Orthogonal Frequency Division Multiplexing (OFDM) symbols, transmitting the OFDM symbols over the radio channel, or demodulating the OFDM symbols received over the radio channel, performing channel decoding on the OFDM symbols, and sending the OFDM symbols to the upper layer.

[0134] Figure 3 The structure of a next-generation mobile communication system 300 to which the present disclosure can be applied is shown. Refer to Figure 3 The radio access network of a next-generation mobile communication system (hereinafter referred to as NR or 5G) includes a New Radio Node 326 and a New Radio Core Network 320 (NRCN). The user terminal 318 accesses an external network via the NR gNB 326 and the NR CN 320. The New Radio Node B is hereinafter referred to as the NR gNB or the NR base station, and the user terminal can be a New Radio User Equipment and is hereinafter referred to as the NR UE or the UE.

[0135] In Figure 3In it, the NR gNB 326 corresponds to the evolved Node B (eNB) of the existing LTE system (for example, as shown in Figure 1 ). The NR gNB 326 is connected to the NR UE 312 via a radio channel and can provide excellent services compared to the existing Node B. In the next-generation mobile communication system, since all types of user services are served through a shared channel, a device for performing scheduling by collecting status information (for example, the buffer status, available transmit power status, and channel status of the UE) is required. In addition, the NR gNB 326 is responsible for this function of the device. Generally speaking, one NR gNB 326 usually controls multiple cells. To achieve ultra-high-speed data transmission compared to the existing LTE, the NR gNB 326 can have the existing maximum bandwidth or a larger bandwidth, and can additionally adopt beamforming technology using orthogonal frequency division multiplexing (hereinafter referred to as OFDM) as a radio access technology. In addition, the NR gNB 326 adopts an adaptive modulation and coding (AMC) scheme, which determines the modulation scheme and channel coding rate based on the channel status of the UE.

[0136] The NR CN 320 performs functions such as mobility support, bearer configuration, QoS configuration, etc. The NR CN 320 is a device that is responsible for various control functions in addition to the mobility management function for the UE 318 and is connected to multiple base stations. In addition, the next-generation mobile communication system can also operate in combination with the existing LTE system 330, and the NR CN 320 can be connected to the MME 312 via a network interface. The MME 312 is connected to the eNB 316, that is, connected to the existing base station.

[0137] Figure 4 Shows such as Figure 3 The radio protocol structure of the next-generation mobile communication system shown. Referring to Figure 4 , the radio protocols of the next-generation mobile communication system respectively include the NR SDAP 420 and 430, NR PDCP 422 and 432, NR RLC 424 and 434, and NR MAC 426 and 436 in the UE 318 and the NR base station 326.

[0138] The main functions of NR SDAP 420 and 430 may include some of the following functions: transmission of user plane data; mapping between QoS flows and data radio bearers (DRBs) for both downlink (DL) and uplink (UL); marking QoS flow IDs in both DL and UL packets; and mapping reflected QoS flows to DRBs for UL SDAP PDUs. For the SDAP layer device, the UE 318 can be configured via RRC messages to use the header of the SDAP layer device (or new layer device) or the functions of the SDAP layer device (or new layer device) for each PDCP layer device, for each bearer, and for each logical channel. When the SDAP header is configured, the NAS reflected QoS reflection configuration 1-bit indicator (NAS reflected QoS) and the AS QoS reflection configuration 1-bit indicator (AS reflected QoS) of the SDAP header are used to indicate that the UE enables the update or reconfiguration of mapping information related to QoS flows of the uplink, downlink, and data bearers. The SDAP header may include QoS flow ID information indicating QoS. The QoS information can be used as data processing priority, scheduling information, etc. to support smooth services.

[0139] The main functions of NR PDCP 422 and 432 may include some of the following functions: header compression and decompression (only ROHC), transmission of user data, sequential delivery of upper layer PDUs, out-of-sequence delivery of upper layer PDUs, reordering of received PDCP PDUs for reception, duplicate detection of lower layer SDUs, retransmission of PDCP SDUs, encryption and decryption, and timer-based SDU discard in the uplink. The reordering function of the NR PDCP device refers to the function of reordering PDCP PDUs received from the lower layer in sequence based on the PDCP sequence number (SN). The reordering function may include the function of transmitting data to the upper layer in the reordered sequence, the function of directly transmitting data to the upper layer without considering the sequence, the function of reordering the sequence and recording lost PDCP PDUs, the function of providing a status report on lost PDCP PDUs to the transmission side, and the function of requesting retransmission of lost PDCP PDUs.

[0140] The main functions of NR RLC 424 and 434 may include some of the following functions: transmission of upper layer PDUs; sequential delivery of upper layer PDUs; out-of-sequence delivery of upper layer PDUs; error correction via ARQ; concatenation, segmentation, and reassembly of RLC SDUs; re-segmentation of RLC data PDUs; reordering of RLC data PDUs; duplicate detection; protocol error detection; RLC SDU discard and RLC reconstruction.

[0141] The in-sequence delivery function of the NR RLC device refers to the function of transmitting the RLC SDUs received from the lower layer to the upper layer in the received order. If an RLC SDU is initially segmented into multiple RLC SDUs and received, the in-sequence delivery function may include the function of reassembling and transmitting the multiple RLC SDUs. The in-sequence delivery function may include the following functions: reordering the received RLC PDUs based on the RLC SN or PDCPSN, reordering the sequence and recording the lost RLC PDUs, providing a status report on the lost RLC PDUs to the transmission side, and requesting retransmission of the lost RLC PDUs. Alternatively, the in-sequence delivery function of the NR RLC device may include the following functions: if an RLC SDU is lost, only the RLC SDUs before the lost RLC SDU are sent to the upper layer sequentially, or if even if there are lost RLC SDUs, if a timer expires, all the RLC SDUs received before the start of the timer are sent to the upper layer sequentially, or if even if there are lost RLC SDUs, if a predetermined timer expires, all the RLC SDUs received so far are sent to the upper layer sequentially. Additionally, the RLC PDUs may be processed in the order of receipt of the RLC PDUs (in the order of arrival, regardless of the sequence number or serial number) and may be sent to the PDCP device in an out-of-sequence delivery manner. The in-sequence delivery function may include the following functions: receiving the segments stored in the buffer or segments received later, reconfiguring the segments in a complete RLC PDU, processing the RLC PDU, and sending the RLC PDU to the PDCP device. The NR RLC layer may not include the concatenation function, and the concatenation function may be performed by the NR MAC layer, or may be replaced by the multiplexing function of the NR MAC layer.

[0142] The out-of-sequence delivery function of the NR RLC device refers to the function of directly sending the RLC SDUs received from the lower layer to the upper layer regardless of their order. If an RLC SDU is initially segmented into multiple RLC SDUs and received, the out-of-sequence delivery function may include the function of reassembling the multiple RLC SDUs and sending the multiple RLC SDUs, and the function of storing the RLC SN or PDCPSN of the received RLC PDUs, reordering the sequence and recording the lost RLC PDUs.

[0143] The NR MACs 426 and 436 can be connected to multiple NR RLC layer devices configured in a UE 318. The main functions of the NR MAC can include some of the following functions: mapping between logical channels and transport channels; multiplexing / demultiplexing of MAC SDUs; scheduling information reporting; error correction via HARQ; priority handling between logical channels of a UE; priority handling between UEs via dynamic scheduling; MBMS service identification; transport format selection; and padding.

[0144] The NR PHY layers 428 and 438 can perform the following operations: channel encoding and modulation of upper layer data, forming the upper layer data into OFDM symbols, transmitting the OFDM symbols via a radio channel, or demodulating and channel decoding the OFDM symbols received via the radio channel, and delivering the OFDM symbols to the upper layer.

[0145] Principle of security protection

[0146] As described above, in the two example networks, there is security protection from encryption or integrity protection. Encryption means not only the encryption operation but also the decryption operation, because if the data is encrypted at the transmitter, the decryption should be applied to the data at the receiver. Similarly, integrity protection means both the integrity verification operation and the integrity protection operation, because if the data is integrity protected at the transmitter, the integrity verification should be applied to the data at the receiver.

[0147] When implementing this technology, the following high-level principles can be applied. AS security includes integrity protection and encryption of RRC signaling (SRB) and user data (DRB). The RRC processes the configuration of AS security parameters as part of the AS configuration: integrity protection algorithms and encryption algorithms. If integrity protection and / or encryption are enabled for a DRB and two parameters, namely keySetChangeIndicator and nextHopChainingCount, which are used by the UE to determine the AS security key when performing a synchronized reconfiguration (with key change), connection reestablishment and / or connection recovery occur.

[0148] The integrity protection algorithm is common for SRB1, SRB2, SRB3 (if configured), SRB4 (if configured), SRBx (if configured), and DRBs with integrity protection configured, with the same keyToUse value. The encryption algorithm is common for SRB1, SRB2, SRB3 (if configured), SRB4 (if configured), SRBx (if configured), and DRBs with the same keyToUse value. Neither integrity protection nor encryption applies to SRB0. Note that all DRBs associated with the same PDU session have the same enable / disable settings for encryption and the same enable / disable settings for integrity protection.

[0149] RRC integrity protection and encryption are always activated together, i.e., in one message / process. RRC integrity protection and encryption for SRBs are never deactivated. However, it is possible to switch to the 'NULL' encryption algorithm (nea0). For SRBx (if configured), RRC integrity protection and encryption can be activated and deactivated based on configuration or indication via RRC messages (or MAC CE (control element) or PDCP control PDU (protocol data unit)) in order to reduce the UE processing burden. For SRBx (if configured), it is also possible to switch to the 'NULL' encryption algorithm (nea0), and the 'NULL' integrity protection algorithm (nia0) can be used.

[0150] The 'NULL' integrity protection algorithm (nia0) is only used for SRBs and UEs in limited service mode, and when used for SRBs, integrity protection is disabled for DRBs. In the case of using the 'NULL' integrity protection algorithm, the 'NULL' encryption algorithm is also used. Note that the lower layer discards RRC messages for which the integrity protection check fails and indicates to RRC that the integrity protection verification check has failed.

[0151] The AS applies four different security keys: one for the integrity protection of RRC signaling (K RRCint ), one for the encryption of RRC signaling (K RRCenc ), one for the integrity protection of user data (K UPint ), and one for the encryption of user data (K UPenc ). All four AS keys are derived from the K gNB key. The K gNB key is based on the K AMF key processed by the upper layer. The integrity protection and encryption algorithms can only be changed with a synchronized reconfiguration. The AS keys (K gNB , K RRCint , K RRCenc , K UPint and K UPenc) Changes when there is synchronized reconfiguration (if masterKeyUpdate is included) and during connection re - establishment and connection recovery.

[0152] For each radio bearer, an independent counter (COUNT used in the PDCP layer) is maintained for each direction. For each radio bearer, COUNT is used as an input for encryption and integrity protection. For a given security key, the same COUNT value is not allowed to be used multiple times. The network is responsible for avoiding the reuse of COUNT with the same RB identity and the same key, e.g., due to only a complete configuration of SN while the key stream inputs (i.e., bearer ID, security key) at the MN have not been updated, resulting in a large amount of data transmission, release and establishment of new RBs, and multiple termination point changes for RLC - UM bearers and multiple termination point changes for RLC - AM bearers with PDCP re - establishment (COUNT reset) having SN termination. To avoid such reuse, the network can, for example, use different RB identities for RB establishment, change the AS security key, or change from RRC_CONNECTED to RRC_IDLE / RRC_INACTIVE and then change back to RRC_CONNECTED transition.

[0153] To limit signaling overhead, each message / packet includes a short sequence number (PDCP SN (sequence number)). In addition, an overflow counter mechanism is used: hyper - frame number (HFN used in the PDCP layer). The HFN needs to be synchronized between the UE and the network.

[0154] For each SRB, the value of the 5 - bit BEARER parameter provided by RRC to the lower layer to derive the input for encryption and integrity protection is the value of the corresponding srb - Identity, with the MSB filled with zeros.

[0155] For a UE provided with sk - Counter, keyToUse indicates whether the UE uses the master key (K gNB ) or the secondary key (S - K eNB or S - K gNB ) for a specific DRB. The secondary key is derived from the master key and sk - Counter. Whenever it is necessary to refresh the secondary key, e.g., when the MN changes with the change of K gNB , or to avoid COUNT reuse, a security key update is used. When the UE is in NR - DC, even when no DRB is established using the secondary key (S - K gNB ), the network can provide sk - Counter to the UE configured with SCG to allow the configuration of SRB3. When using an MCG bearer with SN termination, the network can provide sk - Counter to the UE even if SCG is not configured.

[0156] General AI / ML Framework

[0157] Figure 5 is a schematic block diagram of a functional framework 500 for implementing artificial intelligence or machine learning in a radio access network (such as those shown in Figure 1 or Figure 3 ). Such a functional framework may be referred to as an AI-enabled radio access network intelligence. Figure 5 It includes a data collection module 502 that provides training data to a model training module 504 and inference data to a model inference module 506. As shown by the information flow, after the model has been trained in the model training module 504, an update of the model is deployed to the model inference module 506. Optionally, as shown by the dashed line, the model inference module 506 may provide model performance feedback to the model training module 504, which may be used to further update the model.

[0158] Figure 5 An actuator module 508 is also shown. The actuator module 508 receives the output from the model inference module 506 and is used to provide feedback to the data collection module 502. As described in the above definitions, the output from the model inference module 506 is the inference output of the AI / ML model. The feedback may include information required to derive training data, inference data, or monitor the performance of the AI / ML model.

[0159] The detailed AI / ML algorithms and models for use cases are implementation-specific. For example, considering the problems identified in the background section, ML techniques can be utilized to optimize energy-saving decisions by leveraging the data collected in the RAN network. The ML algorithm can predict the energy efficiency and load status for the next time period, which can be used to make better decisions on cell activation / deactivation to save energy. Based on the predicted load, the system can dynamically configure energy-saving policies (e.g., shutdown timing and granularity, offloading actions) to maintain the balance between system performance and energy efficiency and reduce energy consumption. Additionally or alternatively, an AI / ML model-based solution can be introduced to improve load balancing performance. Based on the collection of various measurements and feedback of UEs and network nodes, as well as historical data, etc., for example, the AI / ML model-based solution and predicted load can improve load balancing performance to provide a higher quality user experience and increase system capacity.

[0160] For further use, the mobility aspects of self-organizing networks (SON) that can be enhanced by using AI / ML include reducing the probability of unintentional events, UE location / mobility / performance prediction, and traffic steering. Predicting the location of the UE is a key part of mobility optimization because many RRM actions related to mobility (e.g., selecting a handover target cell) can benefit from the predicted UE location / trajectory. UE mobility prediction is also a key factor in optimizing early data forwarding (especially CHO). When the UE is served by certain cells, UE performance prediction is a key factor in determining which is the best mobility target for maximizing efficiency and performance. RAN intelligence can observe multiple handover events with associated parameters, use this information to train its ML model, and try to identify the set of parameters that lead to successful handovers and the set of parameters that lead to unexpected events.

[0161] Regarding traffic steering, effective resource handling can be achieved to adjust the handover trigger point and select the best combination of Pcell / PSCell / Scell to serve the user. Existing traffic steering can also be improved by providing the RAN node with information related to mobility or dual connectivity. For example, before initiating a handover, the source gNB can use the feedback on UE performance collected for past successful handovers and the feedback on UE performance received from neighboring gNBs. Similarly, for the case of dual connectivity, before triggering the addition of a secondary gNB or triggering an SN change, the eNB can use the information (feedback) received from the gNB in the past to successfully complete the SN addition or SN change process. In the two reported examples, the source RAN node of the mobility event or the RAN node acting as the master node (eNB for EN-DC, gNB for NR-DC) can use the feedback received from another RAN node as input to the AI / ML function for supporting traffic-related decisions (e.g., selecting a target cell in the case of mobility, selecting PSCell / Scell in other cases) so that future decisions can be optimized.

[0162] The location where the AI / ML function resides within the current RAN architecture depends on the deployment and specific use cases. For example, one solution that can be considered to support AI / ML-based network energy saving includes having the AI / ML model training located in the operation, administration, and maintenance (OAM) system, and the AI / ML model inference located in the gNB. In this example, it is also allowed for the gNB to continue model training based on the AI / ML model trained in the OAM. Alternatively, both the AI / ML model training and the AI / ML model inference are located in the gNB.

[0163] Detailed AI / ML algorithms and models (both training and inference) can be configured to the UE or gNB or network entity together with other relevant parameters and configuration information via RRC (Radio Resource Control) messages or newly defined network messages (e.g., X2 messages, inter-node messages for the interfaces between network entities). The configuration with messages allows various arrangements. For example, AI / ML model training can be located in the UE, and AI / ML model inference can be located in the gNB or OAM. Or, AI / ML model training can be located in the gNB or OAM, and AI / ML model inference can be located in the UE. Or, both AI / ML model training and AI / ML model inference are located in the UE. Training at the UE can implement federated learning or split learning as defined above.

[0164] The architecture can include a split of the Central Unit (CU) and Data Unit (DU) (in other words, a split CU / DU architecture can exist as one of the gNB implementations). In this example, one solution is that AI / ML model training is located in the OAM, and AI / ML model inference is located in the gNB-CU. Another solution is that both AI / ML model training and model inference are located in the gNB-CU. The configuration with messages (e.g., for federated or split learning) allows further solutions. For example, one solution is that AI / ML model training is located in the UE, and AI / ML model inference is located in the gNB-CU or OAM. Another solution is that AI / ML model training is located in the gNB-CU or OAM, and AI / ML model inference is located in the UE. Another solution is that both AI / ML model training and AI / ML model inference are located in the UE.

[0165] In all various arrangements, the general principle is that, if needed, the model training and model inference functions should be able to request specific information for training or executing AI / ML algorithms and avoid receiving unnecessary information from the UE or gNB or network entity by using signaling (i.e., sending request messages). The nature of this information depends on the use case and the AI / ML algorithm. The model inference function should only signal the output of the model to nodes that have explicitly requested them (e.g., via subscription or via configuration), or nodes that take actions based on the output from the model inference, such as by sending messages (e.g., RRC messages or inter-node messages or newly defined messages). The AI / ML model used in the model inference function must be initially trained, validated, and tested by the model training function before deployment to ensure performance and avoid excessive signaling and save radio resources. In some cases, it can also be trained after deployment. During AI / ML operations, user data privacy and anonymity can be respected.

[0166] As described in detail below, the proposed mechanism can operate in NG-RAN SA (Next Generation Network Standalone mode) and thus in the network arrangement of Figure 3 Those skilled in the art will readily understand that the proposed mechanism can be extended to other suitable networks, such as EN-DC (Evolved Universal Terrestrial Radio Access (E-UTRA)-New Radio Dual Connectivity, where E-UTRA is connected to the EPC (Evolved Packet Core)) and MR-DC (Multi-Radio Access Technology (RAT) Dual Connectivity).

[0167] User Equipment States and Transitions

[0168] As mentioned above, the AI / ML configuration information can be sent in RRC messages or other messages. Before considering in detail examples of implementations, we first consider the RRC procedures proposed to handle the AI / ML functions. Figure 6 An overview of the UE RRC state machine and state transitions in NR is shown. The UE has only one RRC state in NR at a time. As Figure 6 shown, when the RRC connection has been established, the UE is in the RRC_CONNECTED state or the RRC_INACTIVE state. If this is not the case, i.e., the RRC connection has not been established, the UE is in the RRC_IDLE state.

[0169] The RRC_IDLE state can be characterized by various features. For example, UE-specific DRX can be configured by the upper layer, and at the lower layer, the UE can be configured with discontinuous reception (DRX) for point-to-multipoint (PTM) transmissions for multicast and broadcast services (MBS) broadcasts. There can also be UE-controlled mobility based on network configuration. The UE can monitor short messages sent via Downlink Control Information (DCI) together with the Paging-Radio Network Temporary Identifier (P-RNTI), and can monitor the paging channel for core network (CN) paging using the 5G-S-TMSI, unless the UE acts as a Level 2 U2N Remote UE. When the UE is configured by the upper layer for MBS multicast reception, the UE can monitor the paging channel for CN paging using the TMGI. The UE can perform neighbor cell measurements and cell (re)selection; obtain System Information (SI) and can send an SI request (if configured); and record available measurements and record the location and time of the UE for the recorded measurement configuration. The UE can also perform idle / inactive measurements for the UE configured for idle / inactive measurements, and perform AI / ML functions (e.g., collect AI / ML data or measure AI / ML data or report AI / ML data) for the appropriately configured UE. When the UE is configured by the upper layer for MBS broadcast reception, the UE can obtain MCCH change notifications and MBS broadcast control information and data.

[0170] Similarly, the RRC_INACTIVE state can be characterized by various features. For example, UE-specific DRX can be configured by the upper layer or the RRC layer, and at the lower layer, the UE can be configured with DRX for PTM transmission for MBS broadcast. There can be UE-controlled mobility based on network configuration, and the UE can store the UE inactive AS context. The RAN-based notification area can be configured by the RRC layer, and the transmission of unicast data and / or signaling to / from the UE via a radio bearer can be configured for small data transmission (SDT). The UE can monitor short messages sent with the P-RNTI via DCI. During the SDT process, the UE can monitor the control channel associated with the shared data channel to determine whether data is scheduled for it, and when the SDT process is not in progress, the UE can monitor the paging channel for CN paging using the 5G-S-TMSI and RAN paging using the full-RNTI, unless the UE acts as an L2U2N remote UE. If the UE is configured by the upper layer for MBS multicast reception, then when the SDT process is not in progress, the UE can monitor the paging channel for paging using the TMGI. The UE can perform neighbor cell measurements and cell (re)selection; and perform RAN-based notification area updates periodically and when moving outside the configured RAN-based notification area. When the SDT process is not in progress, the UE can acquire system information and can send an SI request (if configured). When the SDT process is not in progress, the UE can perform the recording of available measurements and record the location and time of the UE for the recorded measurement configuration; and perform idle / inactive measurements for the UE with idle / inactive measurement configuration; and / or perform AI / ML functions for the configured UE (e.g., collect AI / ML data or measure AI / ML data or report AI / ML data). If the UE is configured by the upper layer for MBS broadcast reception, the UE acquires MCCH change notification and MBS broadcast control information and data. The UE can also send SRS for positioning.

[0171] Similarly, the RRC_CONNECTED state can be characterized by various features. For example, the UE stores the AS context. There is the transmission of unicast data to / from the UE and the transmission of MBS multicast data to the UE. At the lower layer, the UE can be configured with UE-specific DRX or DRX for PTM transmission for MBS broadcast and / or DRX for MBS multicast. For UEs that support carrier aggregation (CA), one or more SCell aggregated with the SPCell can be used to increase the bandwidth. For UEs that support DC, one SCG aggregated with the MCG can be used to increase the bandwidth. There can be network-controlled mobility to / from E-UTRA and to UTRA-FDD within NR. There can be network-controlled mobility (path switching) between the serving cell and the L2 U2N relay UE and vice versa. The UE can monitor short messages (if configured) sent with the P-RNTI via DCI. The UE can monitor the control channel associated with the shared data channel to determine whether data is scheduled for it. The UE can provide channel quality and feedback information. The UE can perform neighbor cell measurements and measurement reports and AI / ML functions (e.g., collect AI / ML data or measure AI / ML data or report AI / ML data) for the configured UE. The UE can obtain system information. The UE can perform immediate minimized drive test (MDT) measurements and available location reports. If the US is configured by the upper layer for MBS broadcast reception, the UE obtains MCCH change notifications and MBS broadcast control information and data.

[0172] Principles of RRC Control for AI / ML

[0173] The RRC protocol includes the following main functions: broadcast of system information, RRC connection control, and recovery from radio link failure. The broadcast of system information includes different types of information, including some or all of the following: NAS common information; information applicable to UEs in RRC_IDLE and RRC_INACTIVE (e.g., cell (re)selection parameters, neighbor cell information) and (also) information applicable to UEs in RRC_CONNECTED (e.g., common channel configuration information); earthquake and tsunami warning system (ETWS) notifications, commercial mobile alert service (CMAS) notifications; positioning assistance data and indication of whether the cell supports AI / ML functions. The system information can broadcast this indication. When the UE obtains the system information, the UE can perform cell (re)selection based on this, and if the system information broadcasts an indication of support for AI / ML functions, send UE capability information including the UE's capability to support AI / ML functions to the cell (or gNB or network).

[0174] RRC connection control may include paging. The paging message may be used to indicate whether the UE stops (deactivates) or starts (activates) reporting of AI / ML functions, or whether the UE stops (deactivates) or starts (activates) collection of AI / ML data, or whether to trigger reporting of AI / ML data, based on a newly defined indication included in the paging message when the UE is in the RRC idle or RRC inactive state. Using this indication, the identifier (full I-RNTI or short I-RNTI or ng-5G-S-TMSI) or the newly defined identifier in the paging message also indicates that the RRC inactive UE or UE group performs the above recommended actions.

[0175] RRC connection control may include establishment, modification, suspension, resume, and / or release of the RRC connection, including, for example, allocation / modification of UE identification (C-RNTI, full I-RNTI, etc.). RRC connection control may include establishment, modification, suspension, resume, and / or release of SRBs (except SRB0). RRC connection control may include establishment, modification, suspension, resume, and / or release of RBs (DRB / MRB) carrying user data;

[0176] RRC connection control may include access prohibition; the access prohibition mechanism may allow UEs with the purpose of AI / ML functions to access the cell based on a newly defined indication in the system information. The access prohibition mechanism may also not allow UEs with the purpose of AI / ML functions to access the cell based on the newly defined indication in the system information. RRC connection control may include initial AS security activation, i.e., initial configuration of AS integrity protection (SRB, DRB) and AS encryption (SRB, DRB). RRC connection mobility may include, for example, intra-frequency and inter-frequency handovers, path switching from the PCell to the target L2 U2N relay UE or from the L2 U2N relay UE to the target PCell, associated AS security processing (i.e., key / algorithm change), and specification of RRC context information transmitted between network nodes;

[0177] RRC connection control may include radio configuration control, including, for example, allocation and / or modification of ARQ configuration, HARQ configuration, and DRX configuration. In the case of DC, cell management may include, for example, addition, modification, and / or release of SCG cells or change of the PSCell. In the case of CA, cell management may include, for example, addition, modification, and / or release of SCell. RRC connection control may include QoS control, which includes allocation or modification of semi-persistent scheduling (SPS) configuration and configured grant configuration for downlink (DL) and uplink (UL) respectively, and allocation or modification of parameters for UL rate control in the UE, i.e., allocation of priority and prioritized bit rate (PBR) for each RB of the UE and the logical channel of the IAB-MT.

[0178] RRC connection control may include AI / ML function control, which includes the allocation or modification of semi-persistent scheduling (SPS) configurations and configured grant configurations for DL and UL respectively, the allocation / modification of parameters for UL rate control in the UE, i.e., the allocation of priorities and prioritized bit rates (PBRs) for each RB of the UE and the logical channels of the integrated access and backhaul mobile terminal (IAB-MT).

[0179] Recovery from radio link failure may include inter-RAT mobility, which includes, for example, AS security activation and the transmission of RRC context information. Recovery from radio link failure may include measurement configuration and reporting. For example, the configuration and reporting may include establishing, modifying, or releasing measurement configurations (e.g., intra-frequency, inter-frequency, and inter-RAT measurements, AI / ML function measurements; setting and releasing measurement gaps and measurement reports). Recovery from radio link failure may include AI / ML configuration as well as AI / ML functions and measurement reports. This may include establishing, modifying, or releasing AI / ML configurations, including measurement configurations (e.g., intra-frequency, inter-frequency, and inter-RAT measurements, time information (measurement duration or measurement timing) or sequence numbers or cell identities (or physical cell identities) for reordering), and including measurement configurations (e.g., for beams or single sidebands (SSBs) or channel state information (CSI) or cell reference signals (CRS)). The AI / ML configuration and reporting for AI / ML functions may include the establishment and release of AI / ML configurations containing measurement configurations; and the AI / ML reports include measurement reports (e.g., for frequencies or beams or SSBs or CSI or CRS or cell identities (or physical cell identities)).

[0180] Recovery from radio link failure may include configuring BAP entities and BH RLC channels for supporting IAB nodes. Recovery from radio link failure may include other functions, such as general protocol error handling, the transmission of dedicated NAS information, and the transmission of UE radio access capability information. Recovery from radio link failure may include support for self-configuration and self-optimization, support for measurement recording and reporting for network performance optimization support for the transmission of application layer measurement configurations and reports; and support for AI / ML configuration and reporting.

[0181] The establishment of the RRC connection involves the establishment of SRB1. The network completes the RRC connection establishment before the establishment of the NG connection is completed, that is, before receiving the UE context information from the 5GC. Therefore, AS security is not activated during the initial phase of the RRC connection. During this initial phase of the RRC connection, the network can configure the UE to perform measurement reporting or collect AI / ML data, but the UE only sends the corresponding measurement report or AI / ML data after successful AS security activation. However, when AS security has been activated, the UE only accepts reconfiguration with synchronization messages.

[0182] AI / ML data indicates a set of inputs for AI / ML (model) training or inference or training data or prediction information or decision parameters or AI / ML or the AI / ML model. For example, AI / ML data can indicate the UE's measurement reports (e.g., for beams or SSBs (synchronization signal blocks) or CSI or CRS (cell-specific reference signals)) and CSI (channel state information) reports or positioning information.

[0183] When receiving the UE context from the 5GC, the RAN uses the initial AS security activation procedure to activate AS security (both encryption and integrity protection). The RRC messages (commands and successful responses) used to activate AS security are integrity protected, while encryption only starts after the procedure is completed. That is, the response to the message used to activate AS security is not encrypted, while subsequent RRC messages (e.g., for establishing SRB2, DRB, and multicast MRB or new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB) or for sending / receiving AI / ML data (or AI / ML configuration)), such as RRCSetup or RRCResume or RRCReconfiguration messages, are both integrity protected and encrypted. In another embodiment, based on the security configuration, the RRC messages sent via the RB for sending / receiving AI / ML data (or AI / ML configuration) may not be integrity protected or encrypted, or not integrity protected and encrypted. After the initial AS security activation procedure has been initiated or SRB1 has been established, the network can initiate the establishment of SRB2, DRB, and / or multicast MRB or new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB), that is, the network can do so before receiving the confirmation of the initial AS security activation from the UE. In any case, the network will apply encryption and integrity protection to the RRC reconfiguration messages for establishing SRB2, DRB, and / or multicast MRB or new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB).

[0184] The network initiates the security mode command procedure for a UE in RRC_CONNECTED. In addition, when only SRB1 is established, i.e., before establishing SRB2, multicast MRB, and / or DRB or new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB), the network applies this procedure. The network can initiate an RRC reconfiguration procedure for a UE in RRC_CONNECTED to establish RBs (in addition to SRB1 established during RRC connection establishment), such as SRB2, DRB, and / or multicast MRB, or new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB), and it is executed only when AS security has been activated.

[0185] If the initial AS security activation and / or radio bearer establishment fails, the network shall release the RRC connection. Configurations with SRB2 without DRB or multicast MRB or new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB) or with DRB or multicast MRB without SRB2 are not supported (i.e., SRB2 and at least one DRB or multicast MRB or new RBs for supporting AL / ML functions (e.g., SRBx or SRB4 or DRB) must be configured in the same RRC reconfiguration message, and without releasing the RRC connection, it is not allowed to release all DRBs and multicast MRBs and new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB)). For IAB-MT, configurations with SRB2 without any DRB / MRB / or new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB) are supported.

[0186] To establish new RBs for supporting AI / ML functions (e.g., SRBx or SRB4 or DRB), the RRC message (e.g., RRCReconfiguration message) sent via SRB1 includes the AI / ML configuration and the configuration of the new SRB.

[0187] The AI / ML configuration includes the type of the AI / ML model (e.g., the identifier of the model or the model function), model inference, model training, algorithms, or how to construct the RRC message including AI / ML data for response (or reporting) (e.g., which information should be included), or how to send the RRC message from the transmitter (UE or gNB) to the receiver (gNB or UE) (e.g., period, timer-related information, etc.). The AI / ML configuration can include the measurement configuration of the UE (e.g., for beam or SSB (synchronization signal block) or CSI or CRS (cell-specific reference signal)) and the CSI measurement configuration (e.g., aperiodic CSI, periodic CSI, etc.) or the positioning configuration.

[0188] When AI / ML data or AI / ML configuration indicates an AI / ML model, this means that the AI / ML model is transmitted (or delivered) via an RRC message over SRB1 or a new RB (e.g., SRBx or SRB4 or DRB) for supporting AI / ML functions.

[0189] AI / ML model transmission (or delivery) can refer to delivering an AI / ML model over the air interface, or the parameters of a model structure known at the receiving end, or a new model with parameters or an identifier for a model or function. This function can indicate UE measurements (e.g., for beam or SSB (synchronization signal block) or CSI or CRS (cell-specific reference signal)) and CSI measurements (e.g., aperiodic CSI, periodic CSI, etc.) or positioning. Delivery can include the complete model or a partial model. It can be a general term referring to transferring an AI / ML model from one entity to another entity in any way. The entity can represent a network node / function (e.g., gNB, LMF (location management function), etc.), UE, a proprietary server, etc.

[0190] When a new RB (e.g., SRBx or SRB4 or DRB) for supporting AI / ML functions is established, the UE (or gNB) can send AI / ML data to the gNB (or UE) via the RB, and vice versa. If the RB is an SRB (e.g., SRBx or SRB4 or SRB5), RRC messages including AI / ML data can be sent and received in the UE or gNB, and RRC messages can be newly defined for AI / ML functions.

[0191] When sending AI / ML data (or AI / ML configuration) over SRB1 or a new RB, if RRC message segmentation is enabled based on the field rrc-SegAllowed received in the received RRC message, and the encoded RRC message (or AI / ML data) is larger than the maximum supported size of the PDCP SDU for uplink transmission or downlink transmission (e.g., 9 Kbytes), the RRC message (or AI / ML data) can be segmented. When the RRC message is segmented, each segment includes its own sequence number and an indicator (to indicate whether it is the last segment).

[0192] The same procedures proposed above for AI / ML configuration or RBs (for AI / ML functions such as SRBx or DRB) can be applied to UEs configured / to be configured for dual connectivity. For example, the establishment of SRB1 is completed during RRC connection establishment. To establish a new RB (e.g., SRBx or SRB4 or DRB) for supporting AI / ML functions, the RRC message (e.g., RRCRconfiguration message) sent via SRB1 includes the AI / ML configuration. When a new RB (e.g., SRBx or SRB4 or DRB) for supporting AI / ML functions is established, the UE (or gNB) can send AI / ML data to the gNB (or UE) via the RB, and vice versa. If the RB is an SRB (e.g., SRBx or SRB4 or SRB5), RRC messages including AI / ML data can be sent and received in the UE or gNB, and RRC messages can be newly defined for AI / ML functions via the SCG (or MCG). The RB (for AI / ML functions such as SRBx or DRB) can be configured for the SCG or MCG based on the configuration (e.g., based on an indicator or cell group identifier).

[0193] The AI / ML configuration can be configured, and the AI / ML data can be sent and received as part of SON (Self-Organizing Network) processes, MDT (Minimization of Drive Tests) processes, UE assistance information, early idle / inactive measurements, RRM (Radio Resource Management) measurement reports, CSI (Channel State Information) reporting frameworks, LPP (LTE Positioning Protocol) providing location information.

[0194] Returning to Figure 6 , as shown, when the RRC connection is released, the UE transitions from the RRC_CONNECTED state to the RRC_IDLE state. The release of the RRC connection is typically initiated by the network. This procedure can be used to redirect the UE to an NR frequency or an E-UTRA carrier frequency. The suspension of the RRC connection is initiated by the network. When the RRC connection is suspended, the UE stores the UE inactive AS context and any configuration received from the network and transitions to the RRC_INACTIVE state. The RRC message suspending the RRC connection is integrity protected and encrypted.

[0195] When the UE needs to transition from the RRC_INACTIVE state to the RRC_CONNECTED state, the recovery of the suspended RRC connection is initiated by the upper layer, or by the RRC layer to perform RAN Notification Area (RNA) update, or by RAN paging from the NG-RAN or for SDT. When the RRC connection is recovered, the network configures the UE according to the RRC connection recovery procedure based on the stored UE inactive AS context and any RRC configuration received from the network. The RRC connection recovery procedure reactivates the AS security and re-establishes the SRBs and DRBs and / or the multicast MRB or the new radio bearer RB (e.g., SRBx or SRB4 or DRB) for supporting AI / ML functions (if configured). When the new RB for supporting AI / ML functions is a DRB, the DRB can be an AM (Acknowledged Mode) DRB, which is configured with an AM RLC entity and uses the RLC AM mode to support lossless transmission and high reliability, where the AM mode supports the ARQ (Automatic Repeat reQuest) mechanism.

[0196] When initiating the recovery procedure for SDT, the AS security (both encryption and integrity protection) is reactivated for SRB2 (if configured for SDT) and SRB1. In addition, for all DRBs configured for SDT, the AS security is also reactivated (if security is configured). In addition, when the UE remains in the RRC_INACTIVE state, the PDCP entities of SRB1 and the PDCP entities of the radio bearers configured for SDT are re-established and recovered. When the UE is in the RRC_INACTIVE state and the SDT procedure is in progress, the transmission and reception of data and / or signaling messages via the radio bearers configured for SDT can occur.

[0197] In response to a request to resume the RRC connection or in response to a recovery procedure initiated for SDT, the network can resume the suspended RRC connection and inform the UE to RRC_CONNECTED, or reject the recovery request and inform the UE to RRC_INACTIVE (with a waiting timer), or directly re-suspend the RRC connection and inform the UE to RRC_INACTIVE, or directly release the RRC connection and inform the UE to RRC_IDLE, or instruct the UE to initiate a NAS-level recovery (in this case, the network sends an RRC establishment message).

[0198] System Information Acquisition

[0199] As described above, the UE applies the System Information (SI) acquisition procedure to obtain AS, NAS, and positioning assistance data information. This procedure applies to UEs in the RRC_IDLE, RRC_INACTIVE, and RRC_CONNECTED states.Figure 7 FIG. 0 shows a method by which the user equipment 718 may obtain system information from the network 700.

[0200] In a first step S720, the UE 718 in the RRC_IDLE or RRC_INACTIVE mode receives information from the Management Information Base (MIB) from the network 700. This ensures that the UE 718 has a valid version of the MIB. In a second step S722, the UE 718 receives system information block types including at least SIB1 to SIB4 from the network 700. If the UE supports E-UTRA, it also receives SIB5. If the UE is configured for idle / inactive measurement, it also receives SIB11. If the UE is capable of NR sidelink communication / discovery and is configured by the upper layer to receive or transmit NR sidelink communication / discovery, it also receives SIB 12. If the UE is capable of V2X sidelink communication and is configured by the upper layer to receive or transmit V2X sidelink communication, it receives SIB 13 and SIB 14. If the UE is configured by the upper layer to report disaster roaming related information, it receives SIB15. If the UE is capable of slice-based cell reselection and the UE receives NSAG information for cell reselection from the upper layer, it receives SIB 16. If the UE is accessing NR via NTN access, it receives SIB 19. Finally, if the US is capable of AI / ML functions (e.g., AI / ML model training and model inference), it receives a new system information block type SIBxx (e.g., SIB22). SIBxx may broadcast whether the cell supports AI / ML model training or model inference or AI / ML functions or information about AI / ML model training or model inference. A UE capable of AI / ML functions that is receiving or interested in receiving AI / ML functions via an SRB or DRB shall ensure that it has a valid version of SIBxx, regardless of the RRC state the UE is in.

[0201] Once the management information and system type block information have been shared, as shown in step S724, the UE 718 may send a message requesting system information (SystemInformationRequest). In the next step S726, the network 700 responds with one or more messages transmitting the requested system information (SystemInformationMessages).

[0202] Detailed process of an example state transition

[0203] Figure 8 FIG. 14 is a flowchart showing the process of the UE switching from the RRC idle mode to the RRC connected mode. This process may be performed in the RRC connected mode in a next-generation mobile communication system, for exampleFigure 1 or Figure 3 The example shown. The process includes a method for configuring the functions of a protocol layer device or UE 818. As shown, there is communication between the UE 818 and the first node gNB1 in the network and between the UE 818 and the second node gNB2 in the network. It should be understood that the two nodes are merely illustrative.

[0204] Each cell or node (e.g., gNB1 or gNB2) served by the base station can serve a very wide frequency band. First, the UE 818 can search the entire frequency band provided by the service provider (PLMN) in units of predetermined resource blocks (e.g., in units of 12 resource blocks (RBs)). That is, the UE 818 can start discovering the primary synchronization sequence (PSS) or the secondary synchronization sequence (SSS) in the entire system bandwidth in units of resource blocks. If the UE 818 discovers the PSS or SSS in units of resource blocks and then detects a signal, the UE can read the signal, analyze (decode) the signal, and identify the boundary between the subframe and the radio transmission resource frame (radio frame). If the UE 818 completes synchronization, the UE can read the system information of the cell where the UE is currently camped. That is, in operations S800 and S802, the UE can identify the information on the control resource set (CORESET) by identifying the master system information block (MIB) or the minimum system information (MSI), and identify the initial access bandwidth part (BWP) information by reading the system information. In the above, the CORESET information refers to the location of the time / frequency transmission resource through which the control signal is sent from the base station, and can be, for example, the location of the resource through which the PDCCH channel is sent. The system information and SIB acquisition can be as Figure 7 detailed in

[0205] As described above, if the UE 818 completes synchronization of the downlink signal with the base station (gNB1) and is able to receive control signals, the next stage is to configure the RRC connection. For example, this can be done by performing a random access procedure in the initial BWP, which includes sending a preamble message from the UE to the base station at step S804. Then, at step S806, the base station may send a random access response received at the UE 818. Then, the UE 818 sends an RRCConnectionRequest at step S808 to request configuration of the RRC connection and receives an RRCConnectionSetup message from the base station at step S810. The UE may be configured with one or more of the following by the RRCConnectionSetup message: bearer establishment information, cell group establishment information, cell establishment information, AI / ML configuration, per-layer device information (e.g., SDAP layer device (or new layer device), PDCP layer device, RLC layer device, MAC layer device, or PHY layer device). Once the RRC connection is configured or established at the UE 818, an RCConnectionSetupComplete message confirming the establishment completion is sent from the UE to the base station at step S812. The RRCConnectionSetup message may include configuration information for the PCell, Pscell, or multiple cells, and multiple partial bandwidths may be configured for each cell (PCell, Pscell, or Scell).

[0206] Steps S804 to S812 represent a procedure for establishing a basic RRC connection, for example, using SRB1. Once completed, at step S814, the base station (gNB1) may send an RRC message (UECapabilityEnquiry) to the UE to identify UE capabilities. The base station sends an RRC message to the UE to identify UE capabilities, for example, to identify how many frequency bands the UE can read, or whether the UE supports functions or frequency band regions that the UE can read.

[0207] When receiving an RRC message that enquires about UE capabilities, the UE performs a UE capability reporting procedure and may send an RRC message (UECapabilityInformation) including UE capability information related to functions supported by the UE to the base station at step S816. The RRC message for reporting UE capabilities (e.g., a non-access stratum (NAS) message or an access stratum (AS) message) may include some or multiple pieces of information for AI / ML functions. Additionally, after identifying UE capabilities, an appropriate partial bandwidth (BWP) or appropriate functions may be configured for the UE.

[0208] The base station can request UE capabilities from the UE. In another method, the base station can query the MME (Mobility Management Entity) or AMF (Access and Mobility Management Function) about the UE capabilities in order to identify the UE capabilities. This is because if the UE has previously accessed the MME or AMF, the MME or AMF may have UE capability information.

[0209] It may be necessary to reconfigure the UE, for example as a result of the received capability information, and thus the base station can send a reconfiguration message (e.g., an RRCConnectionReconfiguration message) to the UE in step S818. In response to the reconfiguration message, the UE can configure bearer establishment information, cell group establishment information, cell establishment information, AI / ML configuration, per-layer device information (e.g., SDAP layer device (or new layer device), PDCP layer device, RLC layer device, MAC layer device, or PHY layer device). The RRC message can include configuration information for the PCell, Pscell, or multiple cells, and multiple partial bandwidths can be configured for each cell (PCell, Pscell, or Scell). When receiving the RRCConnectionReconfiguration message in which the configuration information of the UE is received, the UE can apply the configuration information to the UE's bearer or layer device. Once the reconfiguration is complete, the UE sends a message confirming the completion of the configuration to the base station in step S820. This message can be an RRCConnectionReconfigurationComplete message. As shown in step S822, the configuration of the connection is thus completed.

[0210] In step S824, there are two-way arrows indicating that data can be transmitted from the UE to the base station and vice versa. Multiple data transmission steps can be performed. As indicated in step S826, it may be necessary to reconfigure the UE, and thus the base station can send an RRCConnectionReconfiguration message to the UE in step S826. In response to the reconfiguration message, the UE can apply the configuration information to the UE's bearer or layer device. Once the reconfiguration is complete, the UE sends a message confirming the completion of the configuration to the base station in step S828. As shown in step S830, the reconfiguration of the connection is thus completed. The reconfiguration information can cover the same parameters as the configuration information sent in step S810 and the reconfiguration information sent in step S818.

[0211] In addition, when the base station (gNB1) or the network instructs the UE to switch to another cell or frequency, the base station (gNB1) or the network may configure a handover message including configuration information of the target base station (gNB2) for the handover. In step S832, the handover message (RRCConnectionReconfiguration message) is sent to the UE. Then, the UE may perform a handover process according to the handover settings (e.g., a synchronization process or a random access process to the target base station gNB2 as shown in step S836). When the handover is successfully executed, the UE may configure an RRCConnectionReconfigurationComplete message and send it to the target base station in step S834. The configuration information of the target base station gNB2 may include bearer configuration information, cell group configuration information, cell configuration information, AI / ML configuration, per-layer device information (e.g., SDAP layer device (or new layer device) or PDCP layer device, or RLC layer device, MAC layer device or PHY layer device). Other configuration information as described above may also be included.

[0212] Figure 6 It shows that an RRC message for resuming a connection may be sent to move from an inactive state to a connected state. The resume message may include some or all of the configuration information described above for initial configuration or reconfiguration. Further details including pseudocode for RRC connection control are provided below.

[0213] Example use cases

[0214] AI / ML model training at the central server and AI / ML model inference at the nodes

[0215] Figure 9 is a flowchart showing the communication between the UE 918 and a network including a central server 930 (e.g., an operation, administration, and management (OAM) server) and multiple nodes (including a first node 926 and a second node 928). In this example, the AI / ML model training is completed at the OAM server 930, and the AI / ML model inference is completed at one or more nodes. In this solution, the nodes use the AI / ML model to make decisions for network energy saving, load balancing, mobility optimization, and other purposes. For UE configuration, the network may send an RRC message (e.g., RRCReconfiguration or RRCSetup or RRCResume or a newly defined RRC message) to the UE to configure the type of AI / ML configuration, such as an algorithm or a model, related timers, parameters for measurement (e.g., beam, CSI, SSB, frequency), conditions, or the type of report (or collection), etc.

[0216] In a first optional step S930, an AI / ML model may be provided to (or assumed to be available at) the second node 928 (NG-RAN node 2), which may provide input information to the first node 926 (NG-RAN node 1). In step S932 (step 1-1), UE capability information may be transferred from the UE 918 to the network (specifically, the first node 926) upon request. For a UE in the connected state, this may be done as described above in Figure 8 . For example, the network (or specifically, the first node 926) broadcasts system information including an indication of AI / ML function support, and the UE may report UE capabilities as described above. When the network requests the UE to report UE capability information by sending a UECapabilityEnquiry message, the UE may send a UEcapabilityInformation message including the capabilities of AI / ML function support.

[0217] Then in step S934 (step 1-2), configuration information is sent from the first node 926 to the UE 918, for example as described above. The NG-RAN node 1 configures the UE with AI / ML configuration (e.g., based on the received capability information) and sends a configuration message (e.g., RRCReconfiguration, RRCSetup, RRCResume, RRCRelease message or a newly defined message) to the UE to perform AI / ML functions (e.g., measurement procedures and reporting). The NG-RAN node 1 may also configure the UE to provide AI / ML data (e.g., measurement and / or location information, RRM measurements, MDT measurements, speed, location, time information for measurement, measurement duration, sequence number for reordering training data, or measurement results of CSI (e.g., aperiodic CSI or periodic CSI) or frequency (or cell identity or beam or SSB)).

[0218] The AI / ML configuration information may include configuring one of the signaling radio bearers (SRBs, particularly SRB1, SRB2, SRB3, SRB4, or SRBx) such that the UE reports AI / ML data to the network via the SRB by sending appropriate RRC messages. In another embodiment, the AI / ML configuration information may include, for example, configuring one of the data radio bearers (DRBs) with a special logical channel identifier or bearer identifier such that the UE reports AI / ML data to the network via the DRB by sending appropriate RRC messages. The AI / ML configuration information may include configuring radio resources (e.g., time and frequency resources for the PUCCH (Physical Uplink Control Channel) or PUSCH (Physical Uplink Shared Channel)) such that the UE reports AI / ML data via the configured resources (e.g., UL grant or SPS (Semi-Persistent Scheduling) grant (i.e., radio resources) or configured grant).

[0219] The configuration information for the SRB or DRB may include AS security configuration, i.e., whether encryption (or integrity protection) is performed. A large amount of AI / ML data may need to be reported to the network, i.e., frequent reporting may be required. To reduce the processing burden of the UE caused by encryption or integrity protection, one or both of the encryption function or integrity protection function may not be configured for the SRB or DRB. In other words, only encryption, or only integrity protection, or neither encryption nor integrity protection may be configured. In another alternative, the RRC layer may indicate to the PDCP layer via an indication whether each RRC message (or AI / ML data) needs to be integrity protected and whether each RRC message (or AI / ML data) needs to be encrypted. It can be applied to the SRB or DRB configured for AI / ML data. In another alternative, the AS security (encryption or integrity protection) for the configuration of the SRB (or DRB) for AI / ML data reporting can be activated or deactivated via an RRC message or MAC CE or PDCP control PDU or PDCCH DCI to control the UE processing burden.

[0220] As an alternative solution to the need to report a large amount of AI / ML data, the UE may avoid frequent reporting of including many pieces of AI / ML data information in the newly proposed message structure of an RRC message (e.g., measurement report message or RRC message for reporting). In other words, the UE may report a large amount of AI / ML data with a single message (e.g., RRC message or MAC CE). The proposed message may include a sequence number or timing information for each piece of AI / ML data such that the receiver sorts them in chronological order. The number of AI / ML data that should be included in the reporting message may be configured by an RRC message (e.g., in the AI / ML configuration). The detailed message structure is discussed below.

[0221] The configuration information may additionally or alternatively include prioritization information for AI / ML data. Given that it is very important to send / receive common RRC messages with low latency and high reliability due to the UE's connection management and mobility support, the AI / ML data may not be urgent, i.e., not time-sensitive. Therefore, a prioritization mechanism may be configured and used to prioritize other RRC messages over the reporting messages for AI / ML data.

[0222] The nature of the SRB (i.e., SRB1 or SRB2 or SRB3 or SRB4) may be configured and used for the sending / receiving of RRC messages including AI / ML data. These RRC messages may have a lower priority than the first RRC messages because the first RRC messages support the UE's connection management and mobility support and are thus more important than the RRC messages for AI / ML data. These first RRC messages may include carried NAS messages, NAS messages before the establishment of SRB2, RRC messages for the establishment (reconnection) and (re)configuration, including for example: RRCSetupRequest, RRCSetup, RRCSetupComplete, RRCResumeRequest, RRCResume, RRCResumeComplete, RRCReconfiguration, RRCReconfigurationComplete, RRCRestablishment, RRCRestablishmentRequest, etc.). When the first RRC messages and the RRC messages for AI / ML data are generated together or coexist in the buffer, the first RRC messages may be prioritized over the RRC messages for AI / ML data and may be submitted to the lower layer (e.g., the PDCP layer) and sent first.

[0223] Alternatively, the SRBx or DRB may be configured and used only for the sending / receiving of messages including AI / ML data. Alternatively, for the AI / ML data through the configured RB (SRB or DRB), the network may separately allocate / modify the semi-persistent scheduling (SPS) configuration and the configured grant configuration for DL and UL, allocate / modify parameters for UL rate control in the UE, i.e., assign priorities and PBR (LCP parameters for the LCP process in the MAC layer) for each RB and logical channel identifier of the UE, and allocate a separate SCell configuration or a separate BWP (bandwidth part) configuration to control the prioritization between the messages including AI / ML data and other messages (or data).

[0224] The configuration information may include the configuration of AI / ML data and the AI / ML configuration (e.g., the feature CSI-MeasConfig or MeasConfig specified below).

[0225] When the UE starts to collect AI / ML data (or perform measurements) via an appropriate RRC message (e.g., RRCReconfiguration or RRCRelease), the network may configure conditions (e.g., thresholds, explicit indications, timers, etc.). The conditions can be configured regardless of the UE's state (RRC connected or RRC idle or RRC inactive state). The network may send an RRCReconfiguration message including the configured conditions detailed below to the UE in the RRC connected state. When the UE is transferred to the RRC idle state or the RRC inactive state, the network may also send an RRCRelease message including the following configuration conditions.

[0226] As an example, the threshold can be configured such that when the UE starts to collect AI / ML data (or perform measurements), the UE knows the condition. When the condition is met, the UE starts to collect AI / ML data. For example, if a specific metric is greater than (or less than) a threshold and / or if another specific metric (e.g.) is greater than (or less than) another threshold, the UE may consider the condition to be satisfied. The specific metric can be RSRP (Reference Signal Received Power) or RSRQ (Reference Signal Received Quality) or SINR (Signal-to-Interference-plus-Noise Ratio) or time, etc. One or more thresholds can be used to generate conditions based on the configuration. The network may configure the period during which the UE should collect AI / ML data (or perform measurements).

[0227] As another example, the network may configure the conditions or type or size such that the UE knows which AI / ML data (or how much AI / ML data) the RRC message should collect. The network may send an explicit indication to the UE via an appropriate RRC message (e.g., RRCReconfiguration or RRCRelease message) or MAC CE (Control Element) or PDCCH (Physical Downlink Control Channel) or DCI (Downlink Control Information) indicating when to start (or activate) or stop (or deactivate) collecting AI / ML data (or performing measurements) or which measurement object should be measured (e.g., CSI, or beam, or SSB or frequency or cell identity) or change the target AI / ML data. When the UE receives the indication via the RRC message, the UE may start or stop collecting AI / ML data that meet the conditions configured by the network and store them.

[0228] As another example, the network may configure a timer (e.g., T3xx) for the UE via an RRC message (e.g., RRCReconfiguration or RRCRelease message). When the timer is configured, the UE may start the timer and may collect AI / ML data (or perform measurements) while the timer is running. After the timer expires, the UE may stop collecting AI / ML data. If the UE is in the RRC idle or RRC inactive state, the UE may stop the timer upon receiving an RRCSetup or RRCResume message to transition to the RRC connected state. The area information may be configured to cause the UE to collect AI / ML data (i.e., perform measurements) within the configured area. The configured area may be defined by a cell identifier (i.e., physical cell identifier or TAI (tracking area information)). When the UE leaves the area, the UE may stop collecting AI / ML data or may stop the timer.

[0229] When the UE (in the RRC connected or RRC idle or RRC inactive state) reports AI / ML data (e.g., reports measurement results) via an RRC message (e.g., RRCReconfiguration or RRCRelease) and the radio resources (e.g., time / frequency resources) on which the UE transmits the AI / ML data (or reports measurement results), the network may configure conditions (e.g., thresholds, explicit indications, timers, etc.), and the network may send an RRCReconfiguration message including the following configuration to the UE in the RRC connected state. When the network transitions the UE to the RRC idle or RRC inactive state, the network may also send an RRCRelease message including the following configuration.

[0230] For example, the network may configure the period during which the UE should report AI / ML data (or report measurement results). The UE may periodically send (or report) AI / ML data to the network via an RRC message or MAC CE or a configuration grant (i.e., radio resources) for PUCCH or PUSCH. As another example, upon receiving an explicit indication from the network, the UE may report AI / ML data (or report measurement results) via an RRC message or MAC CE or a configuration grant (i.e., time / frequency radio resources) for PUCCH or PUSCH. The network may send an explicit indication to the UE via an RRC message (e.g., an RRCReconfiguration or RRCRelease message) or MAC CE (control element) or PDCCH (physical downlink control channel) or DCI (downlink control information) indicating when, whether, or where (e.g., radio resources for reporting) to report AI / ML data (or perform measurements) or which measurement object (e.g., CSI, or beam, or SSB, or frequency, or cell identity) should be measured or the change of the target AI / ML data.

[0231] As another example, the network may configure a timer (e.g., T3xx) for the UE via an RRC message (e.g., an RRCReconfiguration or RRCRelease message). When the timer is configured, the UE may start the timer. Whenever the timer expires, the UE may report AI / ML data (or report measurement results) via an RRC message or MAC CE or a configuration grant (i.e., time / frequency radio resources) for PUCCH or PUSCH. After reporting (or sending AI / ML data), the UE may restart the timer.

[0232] As another example, a threshold may be configured to enable the UE to know the condition when the UE reports AI / ML data (or performs measurements). When the condition is met, the UE reports the AI / ML data. For example, if a specific metric is greater than (or less than) a threshold and / or if another specific metric (e.g.) is greater than (or less than) another threshold, the UE may consider the condition to be met. The specific metric may be RSRP (reference signal received power) or RSRQ (reference signal received quality) or SINR (signal-to-interference-plus-noise ratio) or time, etc. One or more thresholds may be utilized based on the configuration to generate the condition.

[0233] In step S926 (step 2), as described above, the UE collects AI / ML data or indicated measurements based on configured conditions or periodically (e.g., for configured radio resources) or upon receipt of an explicit indication or when a timer expires. Examples of UE measurements are related to the RSRP, RSRQ, and SINR of the serving cell and neighboring cells. As shown in step S938 (step 3-1), there is an optional request to report measurements from the first node to the UE. As described above, the UE sends the AI / ML data or measurement report message to the NG-RAN node 1 (in step S940 - step 3-2). Optionally, the network may send an RRC message (e.g., UEInformationRequest message) including an indication of an AI / ML data report, and the UE may report it via an RRC message (e.g., UEInformationResponse message). Alternatively, the UE may send based on configured conditions or periodically (e.g., for configured radio resources) or when a timer expires, not just upon receipt of an explicit indication. In this example, only one UE is shown, but it can be understood that the first node (NG-RAN) may collect AI / ML data from more UEs or other nodes (NG-RAN).

[0234] When the UE remains in the RRC connected state, the UE may perform AI / ML data collection and reporting based on configuration or a specific request. UEs in the RRC idle state and RRC inactive state may also report results corresponding to a configured request (e.g., AI / ML configuration). When the UE is in the RRC connected state, the configuration occurs, for example, via an RRCRelease message including an indication of a mode change from RRC connected to RRC idle / RRC inactive state or via an RRCReconfiguration message.

[0235] In one embodiment, a UE in the RRC idle or RRC inactive state may send the results (or an indication of result availability) via an appropriate RRC message (e.g., RRCSetupRequest or RRCSetupComplete or RRCResumeRequest or RRCResumeComplete) and may remain in the RRC idle or RRC inactive state. If the network wants the UE to request results, the network sends an RRC message including an indication for reporting (e.g., RRCSetup or RRCResume), and the UE may report it via an RRC message (e.g., RRCSetupComplete or RRCResumeComplete).

[0236] In another embodiment, a UE in the RRC idle or RRC inactive state can send the result after establishing an RRC connection with the network (i.e., by entering the RRC connected state) and then by sending an appropriate RRC message (e.g., RRC Setup Complete or RRC Resume Complete) while in the RRC connected state.

[0237] In step S942 (step 4), the first node (NG-RAN node 1) sends the AI / ML data or UE measurement report, together with other input data for model training, to the OAM 930. The AI / ML data can be included in the inter-node message between the NG-RAN node and the OAM. In step S944 (step 5), the second node (assuming NG-RAN node 2 with an optional AI / ML model) also sends AI / ML data or input data for model training to the OAM 930. NG-RAN node 2 sends the AI / ML data or input data for training, where the input data for training includes the required input information from NG-RAN node 2. If NG-RAN node 2 executes the AI / ML model, the sent AI / ML data or input data for training can include the corresponding inference result from NG-RAN node 2. The AI / ML data can be included in the inter-node message between the second node (NG-RAN node 2) and the OAM. In each of steps S942 and S944, the inter-node message can also include an indication of whether the AI / ML data is for model training or model inference or model performance feedback or model deployment or update. A new inter-node message can be defined for this purpose. In another embodiment, traditional inter-node messages can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameters in the message.

[0238] In step S946 (step 6), the model is trained at the OAM 930. The AI / ML data or the required measurements and input data from other nodes can also be utilized to train the AI / ML model for network energy saving / load balancing / mobility optimization.

[0239] In step S948 (step 7), the OAM 930 deploys or updates the AI / ML model into the NG-RAN node. For simplicity, only the deployment to the first node is shown. The NG-RAN node or each NG-RAN node can also continue model training based on the AI / ML model received from the OAM. The OAM 930 can send an AI / ML model deployment message to deploy the trained / updated AI / ML model into the NG-RAN node. Alternatively, the AI / ML model or update parameters can be included in the inter-node message between the NG-RAN node or each NG-RAN node and the OAM. The inter-node message can also include an indication of whether this is for model deployment or model update. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML model and the new indication / parameters in the message.

[0240] In step S950 (step 8), the second node (NG-RAN node 2) sends the AI / ML data or the required input data to the first node (NG-RAN node 1) for model inference. The NG-RAN node 1 receives the AI / ML data or the input information for model inference from the adjacent NG-RAN node 2. The AI / ML data can be included in the inter-node message between the NG-RAN nodes. The inter-node message can also include an indication of whether the AI / ML data is for model training or model inference or model performance feedback or model deployment or update. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameters in the message.

[0241] As shown in step S952 (step 9-1), there is an optional request to report measurements from the first node to the UE. As described above, the UE sends the AI / ML data or the measurement report message to the NG-RAN node 1 (in step S954 - step 392). The same process can be followed as explained with respect to steps S938 and S940.

[0242] In step S956 (step 10), the NG-RAN node 1 generates a model inference output (e.g., energy saving policy, load balancing, handover policy, mobility optimization, etc.). The inference can be based on the AI / ML data and / or the local input of the first node (NG-RAN node 1) and any AI / ML data or input received from the second node (NG-RAN node 2). The first node (NG-RAN node 1) performs model inference and generates a prediction or a decision. The AI / ML data or the required measurements are utilized in the model inference to output a prediction, e.g., UE trajectory prediction, target cell prediction, target NG-RAN node prediction, etc.

[0243] In step S958 (step 11), if applicable, there is an optional step for the first node (NG-RAN node 1) to send model performance feedback to the OAM. AI / ML data can be included in the inter-node message between the NG-RAN node and the OAM. The inter-node message can also include an indication of whether the AI / ML data is used for model training or model inference or model performance feedback or model deployment or update. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameter in the message.

[0244] In step S960 (step 12), although shown sequentially after the previous step, can also be performed simultaneously. The first node (NG-RAN node 1) performs any action according to the model inference output, such as network energy saving action, or load balancing action, or mobility optimization and / or handover process. If the output is a handover policy, the NG-RAN node 1 can select the most suitable target cell (e.g., another node) for each UE before it performs the handover. The NG-RAN node 1 can take a load balancing action, for example, a UE can move from its current node (NG-RAN node 1) to a different node (e.g., NG-RAN node 2). According to the prediction, recommended action or configuration, the NG-RAN node 1, the target NG-RAN node (represented by the NG-RAN node 2 in this step of the flowchart), and the UE perform mobility optimization and / or handover process to hand over the UE from the NG-RAN node 1 to the target NG-RAN node. AI / ML data (e.g., action) can be included in the inter-node message between the NG-RAN nodes (e.g., between the NG-RAN node 1 and the NG-RAN node 2). The inter-node message can also include an indication of whether the AI / ML data is used for transmitting the action or decision. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameter in the message.

[0245] In step S962 (step 13), the target node (e.g., NG-RAN node 2) can provide feedback to the OAM. Similarly, in step S964 (step 14), the first node (NG-RAN node 1) can provide feedback to the OAM. In both cases, the AI / ML data (e.g., feedback) can be included in the inter-node message between the NG-RAN nodes (e.g., between NG-RAN node 1 and NG-RAN node 2). The inter-node message can also include an indication of whether the AI / ML data is for model training or model inference or model performance feedback or model deployment or update. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameters in the message.

[0246] AI / ML model training at the first node and AI / ML model inference at the same or different nodes

[0247] Figure 10 is a flowchart showing the communication between UE 1018 and multiple nodes including the first node 1026 and the second node 1028. In this example, the AI / ML model training is completed at the first node 1026, and the AI / ML model inference is completed at one or more nodes. In this solution, the nodes use the AI / ML model to make decisions for network energy saving, load balancing, mobility optimization, and other purposes. For UE configuration, the network can send an RRC message (e.g., RRCReconfiguration or RRCSetup or RRCResume or a newly defined RRC message) to the UE to configure the type of AI / ML configuration, such as the algorithm or model, related timers, parameters for measurement (e.g., beam, CSI, SSB, frequency), conditions, or the type of report (or collection), etc.

[0248] In the first optional step S1030, the second node 1028 (NG-RAN node 2) can be provided with (or assumed to have) an AI / ML model, and the AI / ML model can provide input information to the first node 1026 (NG-RAN node 1). In step S1032 (step 1-1), the UE capability information can be transferred from UE 1018 to the network (specifically, the first node 1026) according to the request. For a UE in the connected state, this can be as described above in Figure 8be completed as described therein. For example, the network (or specifically, the first node 1026) broadcasts system information including an indication of AI / ML function support, and the UE may report UE capabilities as described above. When the network requests the UE to report UE capability information by sending a UECapabilityEnquiry message, the UE may send a UEcapabilityInformation message including the capability of AI / ML function support.

[0249] Then, in step S1034 (step 1-2), the configuration information is sent from the first node 1026 to the UE 1018, for example, as described above. The NG-RAN node 1 configures the UE with AI / ML configuration (e.g., based on the received capability information), and sends a configuration message (e.g., RRCReconfiguration, RRCSetup, RRCResume, RRCRelease message, or a newly defined message) to the UE to perform AI / ML functions (e.g., measurement procedures and reporting). The NG-RAN node 1 may also configure the UE to provide AI / ML data (e.g., measurement and / or location information, RRM measurements, MDT measurements, speed, location, time information for measurement, measurement duration, sequence number for reordering training data, or measurement results of CSI (e.g., aperiodic CSI or periodic CSI) or frequency (or cell identity, or beam, or SSB)). Details of the AI / ML configuration may be the same as those regarding Figure 9 described.

[0250] In step S1026 (step 2), as described above, the UE collects AI / ML data or indicated measurements based on configured conditions or periodically (e.g., for configured radio resources) or upon receipt of an explicit indication or when a timer expires. Examples of UE measurements are related to the RSRP, RSRQ, and SINR of the serving cell and neighboring cells. As shown in step S1038 (step 3-1), there is an optional request to report measurements from the first node to the UE. As proposed above, the UE sends the AI / ML data or measurement report message to the NG-RAN node 1 (in step S1040 - step 3-2). Optionally, the network may send an RRC message (e.g., UEInformationRequest message) including an indication for AI / ML data reporting, and the UE may report it via an RRC message (e.g., UEInformationResponse message). Or, the UE may send based on configured conditions or periodically (e.g., for configured radio resources) or when a timer expires, not just upon receipt of an explicit indication. In this example, only one UE is shown, but it should be understood that the first node (NG-RAN) may collect AI / ML data from more UEs or other nodes (NG-RAN).

[0251] When the UE is in the RRC connected state, the UE may perform AI / ML data collection and reporting based on configuration or a specific request. UEs in the RRC idle state and RRC inactive state may also report results corresponding to a configured request (e.g., AI / ML configuration). When the UE is in the RRC connected state, configuration occurs, for example, via an RRCRelease message including an indication of a mode change from RRC connected to RRC idle / inactive state or via an RRCReconfiguration message.

[0252] In one embodiment, a UE in the RRC idle or RRC inactive state may send the results (or an indication of result availability) via an appropriate RRC message (e.g., RRCSetupRequest or RRCSetupComplete or RRCResumeRequest or RRCResumeComplete) and may remain in the RRC idle or RRC inactive state. If the network wants the UE to request the results, the network sends an RRC message including an indication for reporting (e.g., RRCSetup or RRCResume), and the UE may report it via an RRC message (e.g., RRCSetupComplete or RRCResumeComplete).

[0253] In another embodiment, a UE in the RRC idle or RRC inactive state can send the result after establishing an RRC connection with the network (i.e., by entering the RRC connected state) and then by sending an appropriate RRC message (e.g., RRC Setup Complete or RRC Resume Complete) while in the RRC connected state.

[0254] In step S1042 (step 4), the second node (NG-RAN node 2) sends the AI / ML data or UE measurement report together with other input data for model training to the first node (NG-RAN node 1). If the NG-RAN node 2 executes the AI / ML model, the sent AI / ML data or input data for training can include the corresponding inference result from the NG-RAN node 2. The AI / ML data can be included in the inter-node message between the nodes. The inter-node message can also include an indication of whether the AI / ML data is for model training or model inference or model performance feedback or model deployment or update. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameter in the message.

[0255] In step S1044 (step 5), a model is trained at the first node (NG-RAN node 1) based on the collected data for configuration purposes. AI / ML data from other nodes or the required measurements and input data can also be utilized to train the AI / ML model for network energy saving / load balancing / mobility optimization.

[0256] In step S1046 (step 6), the second node (NG-RAN node 2) sends the AI / ML data (e.g., the required input data) to the first node (NG-RAN node 1) for model inference. The NG-RAN node 1 receives the AI / ML data (e.g., UE measurements and / or location information) from the adjacent NG-RAN node 2 for model inference. The AI / ML data can be included in the inter-node message between the NG-RAN nodes. The inter-node message can also include an indication of whether the AI / ML data is for model training or model inference or model performance feedback or model deployment or update. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameter in the message.

[0257] As shown in step S1048 (step 7), there is an optional request for reporting measurements from the first node to the UE. As proposed above, the UE sends AI / ML data or a measurement report message to the NG-RAN node 1 (in step S1050 - step 7-2). The same process can be followed as explained with respect to steps S1038 and S1040.

[0258] In step S1052 (step 8), the NG-RAN node 1 generates a model inference output (e.g., energy saving policy, load balancing, handover policy, mobility optimization, etc.). The inference can be based on AI / ML data and / or local inputs of the first node (NG-RAN node 1) and any AI / ML data or inputs received from the second node (NG-RAN node 2). The first node (NG-RAN node 1) performs model inference and generates a prediction or decision. AI / ML data or required measurements are utilized in the model inference to output predictions, e.g., UE trajectory prediction, target cell prediction, target NG-RAN node prediction, etc.

[0259] In step S1054 (step 9), the first node (NG-RAN node 1) performs any actions according to the model inference output, such as network energy saving actions or load balancing actions or mobility optimization and / or handover procedures. If the output is a handover policy, the NG-RAN node 1 can select the most suitable target cell (e.g., another node) for each UE before it performs the handover. The NG-RAN node 1 can take load balancing actions, e.g., the UE can be moved from its current node (NG-RAN node 1) to a different node (e.g., NG-RAN node 2). According to the prediction, recommended actions or configurations, the NG-RAN node 1, the target NG-RAN node (represented by the NG-RAN node 2 in this step of the flowchart), and the UE perform mobility optimization and / or handover procedures to hand over the UE from the NG-RAN node 1 to the target NG-RAN node. AI / ML data (e.g., actions) can be included in the inter-node messages between NG-RAN nodes (e.g., between NG-RAN node 1 and NG-RAN node 2). The inter-node message can also include an indication of whether the AI / ML data is used to convey actions or decisions. New inter-node messages can be defined for this purpose. In another embodiment, traditional inter-node messages can be used for this purpose by introducing new containers for AI / ML data and new indications / parameters in the message.

[0260] In step S1056 (step 10), a target node (e.g., NG-RAN node 2) can provide feedback to a first node (NG-RAN node 1). AI / ML data (e.g., feedback) can be included in an inter-node message between NG-RAN nodes (e.g., between NG-RAN node 1 and NG-RAN node 2). The inter-node message can also include an indication of whether the AI / ML data is for model training or model inference or model performance feedback or model deployment or update. An inter-node message can be newly defined for this purpose. In another embodiment, a traditional inter-node message can be used for this purpose by introducing a new container for the AI / ML data and the new indication / parameters in the message.

[0261] Other examples

[0262] In Figure 9 the arrangement, model training occurs in the central server 930, and model inference occurs in the node 926. In Figure 10 the arrangement, both model training and model inference occur in the node 1026. It should be understood that other arrangements are possible. For example, both model training and model inference can occur in the UE. In this case, the UE is configured with an AI / ML model (or AL / ML model functionality (e.g., training and inference)) via an appropriate RRC message or a newly defined message. Such an arrangement can be used for federated learning or split learning. As another example, model training occurs in the UE, and model inference occurs in a node or at a central server. As another example, model training occurs in a node or at a central server, and model inference occurs in the UE.

[0263] In any arrangement, the UE is configured as needed to collect AI / ML data and / or receive AI / ML data from the network (e.g., from a node (NG-RAN) or a central server (OAM)). Based on the received / collected AI / ML data, the UE can train (or update) an AI / ML model and / or generate model inference output or take an action. The UE can also send the trained AI / ML model or inference output or updated parameters to the network (e.g., a node (NG-RAN) or a central server (OAM)). For such delivery, the AI / ML model or updated parameters or AI / ML data can be included in an RRC message (or NAS message) between the NG-RAN node (or OAM) and the UE. The inter-node message can also include an indication of whether this is for model training or model inference (or inference output) or model performance feedback or model deployment or update. For this purpose, a new RRC message (or NAS (non-access stratum) message) can be newly defined. In another embodiment, a traditional RRC message (or NAS message) can be used for this purpose by introducing a new container for the AI / ML model and new indications / parameters in the message. In other words, the inter-node message can indicate an Xn message (i.e., a message via the Xn interface between gNBs) or a NAS message or an RRC message.

[0264] Inputs, Outputs, and Feedback

[0265] As mentioned in the above example, the UE, the node, and / or the central server with the updated model require various inputs during the inference phase. Similarly, there can be more than one output from the inference phase. The inputs and outputs will depend on the nature of the model, e.g., whether the model is for network energy saving, load balancing, or mobility optimization. The example also mentions that feedback can be provided by different parts of the network, and details of the feedback types are provided below.

[0266] For example, when the model is predicting optimized network energy saving decisions, the nodes (NG-RAN) that maintain the model, the central server, or the UE may require the following information as input data for AI / ML-based network energy saving. The model can use inputs from local nodes (i.e., any node within the network that is associated with the UE and is not the central server), and these inputs can include some or all of the following: UE mobility / trajectory prediction, current and / or predicted energy efficiency, and / or current and / or predicted resource status. The model can use inputs from the UE, and these inputs can include UE location information (e.g., coordinates, serving cell ID, movement speed) and UE measurement reports (e.g., UE RSRP, RSRQ, SINR measurements, etc.). When available, the UE location information can be interpreted by the gNB implementation. The UE measurement reports can include cell-level and beam-level UE measurements. The model can use inputs from adjacent nodes, and these inputs can include current and / or predicted energy efficiency, current and / or predicted resource status, and / or current energy state (e.g., active, high, low, inactive). If the model (e.g., at the gNB) requires existing UE measurements for AI / ML-based network energy saving, RAN3 will reuse the existing framework (including MDT and RRM measurements).

[0267] The outputs generated from the AI / ML-based network energy saving model can include: energy saving policies, such as recommended cell activation / deactivation; handover policies, including recommended candidate cells for taking over traffic; predicted energy efficiency; predicted energy state (e.g., active, high, low, inactive), and / or the model output validity time. To optimize the performance of the AI / ML-based network energy saving model, feedback can be collected from the NG-RAN nodes, including the resource status, energy efficiency, and UE performance (e.g., handovered UEs) affected by the energy saving actions of adjacent NG-RAN nodes, including bit rate, packet loss, latency, and system KPIs (e.g., throughput, latency, RLF of the current and adjacent NG-RAN nodes).

[0268] As another example, when the model is used for load balancing decision-making, the nodes (NG-RAN) that hold the model, the central server, or the UE may require the following information as input data for AI / ML-based network energy saving. The model can use inputs from local nodes, and these inputs can include UE mobility / trajectory prediction as in the previous example, as well as the current and / or predicted resource status. The model can also use the current and predicted UE traffic and predicted resource status information from adjacent NG-RAN nodes of the local node. The model can use inputs from the UE, and these inputs can include UE location information (e.g., coordinates, serving cell ID, moving speed) and UE measurement reports (e.g., UERSRP, RSRQ, SINR measurements, etc.) as in the previous example. The model can also use the following input from the UE: UE mobility history information. The model can use inputs from adjacent nodes, and these inputs can include the current and / or predicted resource status as in the previous example. The model can also use UE performance measurements at traffic offloading adjacent cells.

[0269] The outputs generated from the AI / ML-based load balancing model can include some or all of the following: selection of the target cell for load balancing, predicted own resource status information, predicted resource status information of adjacent NG-RAN nodes, model output validity time, and predicted UEs selected to be switched to the target NG-RAN node (to be used internally by the RAN node). To optimize the performance of the AI / ML-based load balancing model, feedback can be collected from the NG-RAN nodes, including some or all of the UE performance information from the target NG-RAN (for those UEs switched from the source NG-RAN node), updated resource status information from the target NG-RAN, and system KPIs (e.g., current and adjacent throughput, latency, RLF).

[0270] As another example, when the model is used for mobility optimization, the nodes (NG-RAN) that hold the model, the central server, or the UE may require the following information as input data for AI / ML-based network energy saving. The model can use inputs from local nodes, and these inputs can include UE mobility / trajectory prediction, current and / or predicted resource status, and predicted UE traffic, as in the previous example. The model can use inputs from the UE, and these inputs can include UE location information (e.g., coordinates, serving cell ID, moving speed) and UE mobility history information, as in the previous example. The model can also use the following inputs from the UE: radio measurements related to the serving cell and neighboring cells associated with the UE location information, e.g., RSRP, RSRQ, SINR. The model can use inputs from neighboring nodes, and these inputs can include current and / or predicted resource status as in the previous example. Based on the existing SON / RLF reporting mechanism, the model can also use historical information, location, QoS parameters of UEs from neighbors, and performance information of historical UEs that have been handed over (e.g., packet loss rate, latency, etc.), as well as past successful and unsuccessful UE handovers, including premature, late, or handover to the wrong (sub-optimal) cell.

[0271] Outputs generated from the AI / ML-based mobility optimization model can include some or all of the following: UE trajectory prediction (latitude, longitude, altitude, cell ID of the UE within a future time period), estimated arrival probability and associated confidence interval in CHO, predicted handover target node, candidate cells in CHO, priority, handover execution timing, predicted resource reservation time window for CHO, UE traffic prediction, and model output validity time. The predicted handover target node can be output together with the predicted confidence. It should also be noted that whether the UE trajectory prediction is an external output of the node hosting the model inference function should be discussed during the specification working phase. The UE traffic prediction will be used internally by the RAN node, and the details are left to the specification working phase. To optimize the performance of the AI / ML-based mobility optimization model, feedback can be collected from the NG-RAN nodes, including some or all QoS parameters, such as throughput, packet delay, etc. of the handovered UE; resource status information update from the target NG-RAN; and performance information from the target NG-RAN.

[0272] Measurement

[0273] Measurements include (or indicate) a set of AI / ML data, measurement configurations include (or indicate) AI / ML configurations, measurement results include (or indicate) AI / ML data, events triggered by measurements include (or indicate) events collected by AI / ML, and measurement reports include (or indicate) AI / ML data reports.

[0274] The network may configure UEs in the RRC_CONNECTED state to perform measurements. The network may configure the UEs to report them according to a measurement configuration, or to perform conditional reconfiguration evaluations according to conditional reconfigurations. The measurement configuration is provided by means of dedicated signaling, i.e., using appropriate RRC messages such as the RRCReconfiguration or RRCResume messages.

[0275] The network may configure the UEs to perform some or all of the following types of measurements: NR measurements; inter-RAT measurements on E-UTRA frequencies; inter-RAT measurements on UTRA-FDD frequencies; and NR side-link measurements for L2 U2N relay UEs.

[0276] The network may configure the UEs to report some or all of the following measurement information based on SS / PBCH blocks: measurement results per SS / PBCH block; measurement results per cell based on SS / PBCH blocks; and SS / PBCH block indices. The network may configure the UEs to report some or all of the following measurement information based on CSI-RS resources: measurement results per CSI-RS resource; measurement results per cell based on CSI-RS resources; and CSI-RS resource measurement identifiers.

[0277] The network may configure the UEs to perform the following types of measurements for NR side-links and V2X side-links: CBR measurements. The network may configure the UEs to report the following CLI measurement information based on SRS resources: measurement results per SRS resource; and SRS resource indices. The network may configure the UEs to report the following CLI measurement information based on CLI-RSSI resources: measurement results per CLI-RSSI resource; and CLI-RSSI resource indices. The network may configure the UEs to report the following Rx-Tx time difference measurement information based on CSI-RS or PRS for tracking: UE Rx-Tx time difference measurement results.

[0278] The measurement configuration includes some or all of the following parameters: measurement objects, reporting configurations, measurement identities, quantity configurations, and measurement gaps, which will be described in more detail below.

[0279] The Measurement Object (MO) is a list of objects on which the UE shall perform measurements. For intra-frequency and inter-frequency measurements, the measurement object indicates the frequency / time location and subcarrier spacing of the reference signal to be measured. Associated with this measurement object, the network can configure a list of cell-specific offsets, a list of 'excluded' cells, and a list of 'allowed' cells. Excluded cells are not applicable for event evaluation or measurement reporting. Some of the allowed cells are the only cells applicable in event evaluation or measurement reporting. The measObjectId of the measurement object corresponding to each serving cell is indicated by servingCellMO within the serving cell configuration.

[0280] For inter-RAT E-UTRA measurements, the measurement object is a single E-UTRA carrier frequency. Associated with this E-UTRA carrier frequency, the network can configure a list of cell-specific offsets and a list of 'excluded' cells. Excluded cells are not applicable for event evaluation or measurement reporting. For inter-RAT UTRA-FDD measurements, the measurement object is a set of cells on a single UTRA-FDD carrier frequency. For NR sidelink measurements of L2 U2N relay UEs, the measurement object is a single NR sidelink frequency to be measured. For CBR measurements of NR sidelink communication, the measurement object is a set of transmission resource pools on a single carrier frequency for NR sidelink communication. For CBR measurements of NR sidelink discovery, the measurement object is a set of discovery-specific resource pools or transmission resource pools for NR sidelink discovery on a single carrier frequency that is also used for NR sidelink discovery. For CLI measurements, the measurement object indicates the frequency / time location of the SRS resource and / or the CLI-RSSI resource, and the subcarrier spacing of the SRS resource to be measured.

[0281] The report configuration is a list of report configurations, where each measurement object can have one or more report configurations. Each measurement report configuration includes some or all of the following information. The configuration can include a reporting criterion, which is the criterion that triggers the UE to send a measurement report. This can be periodic or a single event description. The configuration can include the RS type to indicate the RS (SS / PBCH block or CSI-RS) that the UE uses for beam and cell measurement results. The configuration can include the report format, e.g., the number of per-cell and per-beam that the UE includes in the measurement report (e.g., RSRP), and other associated information, such as the maximum number of cells to be reported and the maximum number of beams per cell.

[0282] In the case of conditional reconfiguration, it includes some or all of the following information. The configuration may include an execution criterion, which is the criterion used by the UE for conditional reconfiguration execution. The configuration may include an RS type to indicate the RS that the UE uses to obtain beam and cell measurement results (based on SS / PBCH block or based on CSI-RS) for evaluating the conditional reconfiguration execution condition.

[0283] For a measurement report, there may be a list of measurement identities, where each measurement identity links a measurement object to a reporting configuration. By configuring multiple measurement identities, more than one measurement object can be linked to the same reporting configuration, and more than one reporting configuration can be linked to the same measurement object. The measurement identity is also included in the measurement report that triggers the report and is used as a reference to the network. For conditional reconfiguration triggering, one measurement identity exactly links to one conditional reconfiguration triggering configuration. Up to two measurement identities can be linked to one conditional reconfiguration execution condition.

[0284] The quantity configuration defines the measurement filter configuration for all event evaluations and related reports and for the periodic report of this measurement. For NR measurements, the network can configure up to two quantity configurations, where the reference in the NR measurement object is for the configuration to be used. In each configuration, different filter coefficients can be configured for different measurement quantities, different RS types, and the measurements of each cell and each beam.

[0285] A measurement gap is a period during which the UE can perform measurements.

[0286] A UE in the RRC_CONNECTED state maintains a list of measurement objects, a list of reporting configurations, and a list of measurement identities according to the signaling and procedures in this specification. The list of measurement objects may include NR measurement objects, CLI measurement objects, inter-RAT objects, and L2 U2N relay objects. Similarly, the list of reporting configurations includes NR, inter-RAT, and L2 U2N relay reporting configurations. Any measurement object can be linked to any reporting configuration of the same RAT type. Some reporting configurations may not be linked to measurement objects. Similarly, some measurement objects may not be linked to reporting configurations.

[0287] The measurement process differentiates the following types of cells: NR serving cells, listed cells, and detected cells. An NR serving cell is a SpCell and one or more SCell. A listed cell is a cell listed in the measurement object. A detected cell is a cell that is not listed in the measurement object but is detected by the UE at the SSB frequency and subcarrier spacing indicated by the measurement object.

[0288] For NR measurement objects, the UE measures and reports the serving cell / serving relay UE (for L2 U2N remote UEs), the listed cells, and / or the detected cells. For inter-RAT measurement objects for E-UTRA, the UE measures and reports the listed cells and the detected cells, and for RSSI and channel occupancy measurements, the UE measures and reports the configured resources on the indicated frequencies. For inter-RAT measurement objects for UTRA-FDD, the UE measures and reports on the listed cells. For CLI measurement objects, the UE measures and reports the configured measurement resources (i.e., SRS resources and / or CLI-RSSI resources). For L2 U2N relay objects, the UE measures and reports the serving NR cell and the discovered L2 U2N relay UEs.

[0289] RRC message structure

[0290] As described above, a large amount of AI / ML data needs to be reported to the network. One solution to avoid frequent reporting as described above is to create a messaging structure that allows the UE to include many pieces of AI / ML data information in one RRC message (e.g., a measurement report message for reporting or an RRC message). The proposed message may include a sequence number or timing information for each piece of AI / ML data to enable the receiver to sort them in chronological order. The number of AI / ML data that should be included in the report message can be configured by the RRC message (e.g., in the AI / ML configuration). The detailed message structure is described below.

[0291] RRC messages may contain one or more of the following information elements: MeasConfig, ReportConfigNR, MeasResults, CSI-MeasConfig, CSI-ReportConfig, and MeasurementReport. These provide configuration information for measurements. For AI / ML implementation, the message structure and parameters can be extended to configure AI / ML configuration: MeasConfigAIML, ReportConfigNRAIML, MeasResultsAIML, CSI-MeasConfigAIML, CSI-ReportConfigAIML, MeasurementReportAIML. For example, hereafter, when the network configures AI / ML configuration for a UE (or network entity), MeasConfig, ReportConfigNR, MeasResults, CSI-MeasConfig, CSI-ReportConfig, and MeasurementReport can be regarded as MeasConfigAIML, ReportConfigNRAIML, MeasResultsAIML, CSI-MeasConfigAIML, CSI-ReportConfigAIML, and MeasurementReportAIML.

[0292] Whenever the proposed procedure involves fields, it involves the fields included in VarMeasConfig, unless otherwise explicitly stated, i.e., only the measurement configuration procedure covers the direct UE actions related to the received measConfig.

[0293] Some of these key information elements are used in sequence: The message structure may include a measurement configuration information element (MeasConfig) that specifies measurements to be performed by the UE. This information element may include fields covering intra-frequency, inter-frequency, and inter-RAT mobility, as well as measurement gap configurations. For example, when the field "interFrequencyConfig-NoGap-r16" is set to true, the UE may be configured to perform inter-frequency measurements based on SSBs without a measurement gap when the inter-frequency SSB is fully contained within the UE's active DL BWP. There may also be fields within the information element that are lists of measurement identities for removal, addition, and / or modification (e.g., MeasIdToAddModList and MeasIdToRemoveList). There may also be fields within the information element that are lists of measurement objects for removal, addition, and / or modification (e.g., MeasObjectToAddModList and MeasObjectToRemoveList). There may also be fields within the information element that are lists of measurement report configurations for removal, addition, and / or modification (e.g., ReportConfigToAddModList and ReportConfigToRemoveList). There may also be one or more thresholds, such as a threshold for controlling when the UE is required to perform measurements on non-serving cells. These fields may also be referred to as information elements.

[0294] The message structure may include a measurement configuration identity information element to identify the measurement configuration (MeasId), which is the link between the measurement object and the report configuration. The MeasID in the MeasConfig information element indicates the type of measurement or the identifier for a separate measurement. When the network configures an AI / ML configuration for the UE (or a network entity), the measID in MeasConfigAIML may indicate the type of AI / ML data to be collected (e.g., it can be used as an AI / ML data identifier to configure an AI / ML configuration for multiple types of AI / ML data) or the AI / ML model (e.g., it can be used as an AI / ML model identifier to configure an AI / ML configuration for multiple AI / ML models) or the same information for the measurement.

[0295] The MeasConfig information element includes a field that is a list of measurement objects to be removed, added, and / or modified. The MeasObject information element within the MeasConfig information element includes details of the target frequency (e.g., time / frequency radio resources). The MeasObjectID can be used to indicate each measurement object MeasObject. When the network configures an AI / ML configuration for a UE (or network entity), the measurement object information element measObject in the configuration information element MeasConfigAIML can indicate an AI / ML model (e.g., an AI / ML model identifier can be used to configure the AI / ML configuration for multiple AI / ML models) or the same information used for measurement. Similarly, there can be an information element (MeasObjectIDAIML) that can be used to indicate each measurement object in the AI / ML configuration (MeasObjectAIML). The MeasObject information element can also include fields for indicating the individual offset (cellIndividualOffset) applicable to a specific cell and the cell identity (physCellId) of the cells in the cell list.

[0296] The MeasurementReport message can include measurement results (MeasResults) for an identified measurement configuration (measID). When an AI / ML configuration is configured, the MeasurementReportAIML can include AI / ML data for measIDAIML. The MeasurementReport message is used for the indication of measurement results. The signaling radio bearer can be SRB1 and / or SRB3, and a data radio bearer DRB (if configured) can be used. The RLC-SAP can be AM, the logical channel can be DCCH, and the direction of the message is from the UE to the network.

[0297] The measurement result information element (MeasResults) includes detailed information to be reported for each identified measurement configuration (measID) (e.g., physical cell identifier, cell list, frequency list, beam, beam list, RSRP, RSRQ, SINR, etc.). The measurement result information element (MeasResults) can cover measurement results for intra-frequency, inter-frequency, and inter-RAT mobility and measurement results for NR sidelink communication / discovery. When the network configures an AI / ML configuration for a UE (or network entity), for each identified measurement configuration including AI / ML (measIDAIML), MeasResultsAIML includes an AI / ML data set, the type of AI / ML data, the quantity of AI / ML data, time information, sequence number, etc. MeasResultsAIML can include the same measurement information as the measurement result information element (MeasResults).

[0298] For AI / ML data, a sequence number or time information can be included to report multiple data of the same target in chronological order (i.e., time series) (e.g., the configured MeasObject, AI / ML data, or AI / ML model as described above). For example, Option 1 is to introduce a sequence number (or time information) for each measurement result and include it. Option 2 is to introduce a list with a sequence number (or time information), i.e., each measured quantity of the measurement result can include a sequence number (or time information). These two options are shown in the code in the detailed section below. In another embodiment, rules can be defined that do not require a sequence number (or time information) for each result (or quantity), e.g., the first result in the report message is the first in the time series and the second result is the second. The rule can also be defined in the opposite way, i.e., the first result in the report message is the most recent result in the time series and the second result is the second most recent result. Rules can be defined in various ways to report multiple data of the same target.

[0299] The field description of the Measurement Results information element (MeasResults) includes some or all of the following fields: a field indicating the coarse location information (coarseLocationInfo) reported by the UE, a field indicating the ratio of packets exceeding a configured delay threshold (exProcessDelay), and a field having the measurement results of the measured cells with reference signals indicated in the serving cell measurement object (measResultServingMOList). The results of these measurements can include the measurement results of the SpCell, the configured SCell, and the best neighboring cells within the measured cells with reference signals indicated on each serving cell measurement object. The measurement results can include SFTD measurements (i.e., the timing difference between the PCell of the LTE network and the PSCell of the 5G NR network), such as measResultSFTD-EUTRA and measResultSFTD-NR. There can also be sidelink measurements, e.g., measResultsSL, sl-MeasResultsCandRelay, and sl-MeasResultsServingRelay.

[0300] The field description of the Measurement Results information element (MeasResults) includes some or all of the following fields depending on the network type: the measurement results of UTRA-FDD cells (measResultUTRA-FDD), the physical cell identity of the E-UTRA cell or UTRA-FDD cell on which the reporting is being performed (measResultUTRA-FDD or physcellID). There can also be a field description of the results of measurements related to the NR (New Radio) network.

[0301] Measurements can also be performed in the RRC_IDLE and RRC_INACTIVE states. These measurements can be described by the information element (MeasResultIdleNR), in which case MeasResultIdleNR covers the NR (New Radio) network. The field description can include fields for indicating the following: NR carrier frequency (carrierFreq), idle / inactive measurement results for NR cells (measIdleResultNR), measurement results of the serving cell (measResultServingCell), a list of idle / inactive measurement results of the best cells reported for a given NR carrier (measResultsPerCellListIdleNR), and / or beam-level measurements (resultsSSB-Indexes).

[0302] There is also an information element (ReportConfigNR) that includes details for reporting (e.g., what type of results should be reported, or periodic or time / frequency resources, or when to trigger reporting, i.e., events, etc.). There is an identification information element (ReportConfigID) that can be used to indicate each reporting information element ReportConfigNR. When the network configures AI / ML configuration for a UE (or network entity), the reporting information element can be marked as ReportConfigNRAIML and can include details for reporting (e.g., what type of results should be reported, or periodic or time / frequency resources, or when to trigger reporting, i.e., events, etc.). There is also an identification information element ReportConfigIDAIML that can be used to indicate each AIL / ML reporting configuration ReportConfigNRAIML.

[0303] The reporting information element ReportConfigNR specifies criteria for triggering one or more of the following: NR measurement report events, CHO (conditional handover), conditional PSCell addition (CPA), or conditional PSCell change (CPC) events, or L2 U2N relay measurement report events. For events labeled AN where N equals 1, 2, etc., the measurement report events and CHO, CPA, or CPC events are based on cell measurement results, which can be derived based on SS / PBCH blocks or CSI-RS. The following table gives some examples of events that can trigger reporting:

[0304]

[0305]

[0306] Therefore, the reporting can be conditional, and there can be field descriptions for offsets or thresholds, including, for example, the offset value (a3-offset) to be used for triggering event A3, and / or the thresholds (a4-Threshold and a5-Threshold) associated with the selected trigger quantity for each RS type used to trigger event A4 or A5.

[0307] The message structure may also include an information element (ReportConfigToAddModList) that involves a list of report configurations for addition or modification. The message structure may also include an information element (ServingCellConfig) for configuring (adding or modifying) serving cells for the UE. The serving cell may be the SpCell or SCell of the MCG or SCG. The parameters in this article are mainly UE-specific, but some are also cell-specific (e.g., in the bandwidth part of the additional configuration). Only SCell release and addition are used to support reconfiguration between PUCCH and PUCCHless SCell.

[0308] The message structure may also include an information element (CSI-MeasConfig) that is used to configure CSI-RS (Channel State Information Reference Signal) belonging to the serving cell including CSI-MeasConfig. On the serving cell including this information element (CSI-MeasConfig), the information element may also be used to configure the channel state information report to be sent on the PUCCH and the channel state information report on the PUSCH triggered by DCI received on the serving cell. There are various field descriptions for this information element, including a list (aperiodicTriggerStateList) for dynamically selecting one or more aperiodic and semi-persistent report configuration trigger states. There are also various lists for adding or modifying elements, including CSI-IM-Resource, CSI report settings, CSI resource settings, CSI-SSB resource, and CSI-RS-Resource.

[0309] The message structure may also include an information element (CSI-ReportConfig) that is used to configure periodic or semi-persistent reports sent on the PUCCH in the cell including the information element CSI-ReportConfig. Alternatively, this information element may be used to configure semi-persistent or aperiodic reports sent on the PUSCH triggered by DCI received in the cell including CSI-ReportConfig. In this case, the cell on which the report is sent is determined by the received DCI.

[0310] The identifier of the measurement configuration (measID), the identifier of the measurement object (measObjectID), and the identifier of the reporting configuration (ReportConfigID) can be mapped in the identifier of the measurement configuration to be added or modified (MeasIdToAddMod). In this way, the measurement target, how to perform measurements on the target, how to report the results, which results should be reported, etc. can be defined. Similarly, the identifier of the AI / ML measurement configuration (measIDAIML), the identifier of the AI / ML measurement object (measObjectIDAIML), and the identifier of the AI / ML reporting configuration (ReportConfigIDAIML) can be mapped in the identifier of the AI / ML measurement configuration to be added or modified (MeasIdToAddModAIML). By mapping measIDAIML, measObjectIDAIML, and ReportConfigIDAIML in MeasIdToAddMod, the target data to be collected, how to perform measurements (or collect it) on the target, how to report the results, which results should be reported, etc. can be defined.

[0311] Extension to dual connectivity

[0312] There exists an alternative network known as Multi-Radio Dual Connectivity (MR-DC) and schematically shown in Figure 11A and Figure 11B This is a generalization of dual connectivity (DC). A UE 1118 with multiple receivers and transmitters (Rx / Tx) can be configured to utilize resources provided by two different nodes connected via a non-ideal backhaul connection. For simplicity, a single receiver 1102 and a single transmitter 1104 within the UE 1100 are shown. The first node provides New Radio (NR) access, while the other node provides E-UTRA (Evolved UMTS Terrestrial Radio Access) or NR access. One node 1120 acts as the master node (MN) and is part of the MCG (Master Cell Group). The other node 1122 acts as the secondary node (SN) and is part of the SCG (Secondary Cell Group). The MN or MCG and the SN or SCG are connected via a network interface, and at least the MN is connected to the core network. The MN and / or the SN can operate using shared spectrum channel access.

[0313] Unless otherwise specified, all functions specified for a UE can be used for an integrated access and backhaul mobile terminal (IAB-MT). Similar to those specified for a UE, an IAB-MT can access the network using one network node or using two different nodes with an E-UTRA NR dual-connectivity (EN-DC) and an NR dual-connectivity NR-DC architecture. In EN-DC, backhaul traffic on the E-UTRA radio interface is not supported. Multi-RAT dual-connectivity (MR-DC) is a general term for a series of different dual-connectivity configuration options. In the present invention, the AI / ML configurations and their functions proposed above can be extended and applied to the MR-DC scenario as follows:

[0314] In a first arrangement, the E-UTRAN supports MR-DC via EN-DC. The E-UTRAN is a combination of E-UTRA, a user equipment (UE), and a Node B (E-UTRAN Node B or evolved Node B, eNodeB). The UE is connected to one eNB (LTE base station) acting as the MN and one en-gNB (5G E-UTRA base station or NR base station) acting as the SN. The eNB is connected to the evolved packet core (EPC) via the S1 interface and to the en-gNB via the X2 interface. The en-gNB can also be connected to the EPC via the S1-U interface and to other en-gNBs via the X2-U interface.

[0315] In another arrangement, the NG-RAN supports an NG-RAN E-UTRA-NR dual-connectivity (NGEN-DC). The NG-RAN is the next-generation radio access network. The UE is connected to one ng-eNB (next-generation evolved Node B) acting as the MN and one gNB (5G base station) acting as the SN.

[0316] In another arrangement, the NG-RAN supports an NR-E-UTRA dual-connectivity (NE-DC). The UE is connected to one gNB (5G Node B) acting as the MN and one ng-eNB acting as the SN.

[0317] In another arrangement, the NG-RAN supports an NR-NR dual-connectivity (NR-DC). The UE is connected to one gNB (5G Node B) acting as the MN and another gNB (5G Node B) acting as the SN. Additionally, when the UE is connected to a single gNB, NR-DC can also be used, acting as both the MN and the SN, and configuring the MCG and SCG.

[0318] For example, it will be difficult to support AI / ML functions in LTE as it is the state of the art, while NR is likely to support it. To support AI / ML functions in LTE, when a UE is connected to an eNB (or E-UTRAN or ng-eNB), the network can configure MR-DC for the UE. For the UE, SRB3 or an RB (configured for AI / ML functions, such as SRBx or DBR) can be configured and used for AI / ML (re)configuration and reporting (such as AI / ML data) to support the AI / ML function, which can be configured and used for the UE's SCG (NR gNB). In other words, NR can support AI / ML functions via the SCG (e.g., gNB) of the UE configured with MR-DC. To achieve this, the MCG (eNB or E-UTRAN or ng-eNB) should negotiate the configuration or capabilities of the AI / ML function with the candidate of the SCG (e.g., gNB) by exchanging messages including such information before configuring MR-DC for the UE.

[0319] In (NG)EN-DC and NR-DC, SRB3 or an RB (configured for AI / ML functions, such as SRBx or DRB) can be used for multiple tasks. These tasks can include measurement configuration and reporting, UE-assisted (re)configuration and reporting for power saving, and AI / ML (re)configuration and reporting (such as AI / ML data) for AI / ML function support. These tasks can also include IP address (re)configuration and reporting for IAB nodes, (re)configuring MAC, RLC, BAP, physical layer, and RLF timers, and constants for SCG configuration, and reconfiguring PDCP for the DRB associated with S-K gNB or SRB3 or an RB (configured for AI / ML functions, such as SRBx or DRB). These tasks can include for S-K in NGEN-DC and NR-DC gNBThe associated DRB reconfigures SDAP, and the PSCell change configuration for the add / modify / release conditions, provided that the (re)configuration does not require any MN participation. These tasks may include: sending RRC messages between the MN and the UE during fast MCG link recovery. In (NG)EN-DC and NR-DC, only the following information elements: measConfig, radioBearerConfig, conditionalReconfiguration, bap-Config, iab-IP-AdddressConfigurationList, otherConfig, and secondaryCellGroup, and / or the AI / ML (re)configuration and reporting (e.g., AI / ML data) for AI / ML function support are included in the RRCReconfiguration message received via SRB3 or RB (configured for AI / ML functions, e.g., SRBx or DRB), unless the RRCReconfiguration is received within DLInformationTransferMRDC.

[0320] For measurement configuration, the network applies some or all of the following features. Whenever the UE has a measConfig associated with a CG, it includes the SpCell of the CG to be measured and the measObject for each NR SCell. Configure at most one measurement identity (or AI / ML identity) across all CG configurations using a report configuration with reportType set to reportCGI. Configure at most one measurement identity (or AI / ML identity) per node hosting a PDCP entity using a report configuration with ul-DelayValueConfig. Configure at most one measurement identity (or AI / ML identity) per node hosting a PDCP entity using a report configuration with ul-ExcessDelayConfig.

[0321] In addition, in the measConfig associated with the CG, it is ensured that for all SSB-based measurements, there is at most one measurement object with the same ssbFrequency. It is also ensured that smtc1 included in any measurement object with the same ssbFrequency has the same value, and smtc2 included in any measurement object with the same ssbFrequency has the same value, and smtc3list included in any measurement object with the same ssbFrequency has the same value, and smtc4list included in any measurement object with the same ssbFrequency has the same value. It is further ensured that all measurement objects configured in this specification and having the same ssbFrequency have the same ssbSubcarrierSpacing.

[0322] It is also ensured that if the measurement object associated with the MCG and the measurement object associated with the SCG have the same ssbFrequency, then for that ssbFrequency, the measurement window of smtc1 configured by the MCG includes the measurement window of smtc1 configured by the SCG, and vice versa, where the accuracy of the maximum received timing difference is specified. If both measurement objects are used for RSSI measurement, the bits in measurementSlots in the two objects corresponding to the same time slot are set to the same value. In addition, the endSymbol is the same in the two objects.

[0323] It is also ensured that if a measurement object has the same ssbFrequency as the configured measurement object, then for that ssbFrequency, the measurement window of the configured smtc includes the measurement window of the configured smtc1, and vice versa, where the accuracy of the maximum received timing difference is specified. If both measurement objects are used for RSSI measurement, the bits in measurementSlots in the two objects corresponding to the same time slot are set to the same value. In addition, the endSymbol is the same in the two objects.

[0324] When the UE is in NE-DC, NR-DC, or NR standalone, it is ensured that a reporting configuration with reportType set to reportSFTD is used to configure at most one measurement identity across all CGs.

[0325] For CSI-RS resources, the network applies the following process. It is ensured that all CSI-RS resources configured in each measurement object have the same center frequency (startPRB + floor(nrofPRB / 2)). It is also ensured that the total number of CSI-RS resources configured in each measurement object does not exceed the specified maximum number.

[0326] In NR-DC, a UE can receive two AI / ML configurations, one from the MCG (Master Cell Group) and the other from the SCG (Secondary Cell Group). To simplify UE operation and network configuration, we propose several options for handling AI / ML configurations and AI / ML data reporting when the UE is configured with dual connectivity (i.e., configured with an MCG and an SCG). The following options can also be applied to UEs configured with single connectivity (e.g., only the MCG).

[0327] Figure 11A and Figure 11B The first option is shown, where the UE 1118 can maintain AI / ML configurations (or reports) for the MCG 1120 and the SCG 1122 separately. Given that the network can configure multiple AI / ML models (or AI / ML configurations) for the UE with the corresponding identifiers proposed above, this option provides greater flexibility for the network. In other words, the network can run AI / ML models (e.g., with separate configurations or with separate cell group identifiers) for each cell group (MCG or SCG) as follows.

[0328] In this arrangement, the UE 1118 is configured with AI / ML capabilities per cell group, e.g., two AI / ML capabilities (one for the MCG 1130 and another for the SCG 1132). The UE 1118 is connected to the first node 1120 via the first SRB 1131. The UE 1118 is directly connected to the second node 1122 via the second SRB 1135 (e.g., SRBx). The UE 1118 is also indirectly connected to the second node 1122 via the first node 1120 using the signaling flow 1133, which includes SRB1 to the first node and SRB3 from the first node to the third node. The network may configure the UE with the AI / ML capabilities of each cell group with a cell group identity such that the UE can establish and manage them separately. For example, the AI / ML capabilities of the MCG 1130 may be configured to the UE directly via SRB1 or via split SRB1 (or SRBx). Then, the AI / ML capabilities are stored at the UE as the AI / ML capabilities of the MCG 1130'. The AI / ML capabilities for the SCG 1132 may be configured at the UE directly from the SCG to the UE via SRB3 (or SRBx) or split SRB3 or indirectly via the MCG, e.g., using SRB3 (or SRBx) and SRB1. Then, the AI / ML capabilities are stored at the UE as the AI / ML capabilities of the SCG 1132'.

[0329] Consider Figure 11B , in the first step S1132, the AI / ML configuration message AIMLConfigMCG associated with the MCG is included in the reconfiguration message RRCReconfiguration (e.g., generated by the MCG). These messages may be received at the UE 1118 from the MCG 1120, e.g., via SRB1. In another step S1134, shown sequentially but which may be completed simultaneously, the AI / ML configuration message AIMLConfigSCG associated with the SCG is included in the RRCReconfiguration message (e.g., generated by the SCG). As Figure 11B shown, these messages may be received at the UE 1118 from the SCG 1122, e.g., via SRB3 or RB (configured for AI / ML capabilities, e.g., SRBx or DRB). Alternatively, as shown by the dashed line, the SCG AI / ML configuration message may be included in the RRCReconfiguration message (e.g., generated by the SCG) that is sent to the MCG in step S1136 and then embedded in the reconfiguration message RRCReconfiguration generated by the MCG. Then, in step S1138, the message with the embedded message is received at the UE 1118 from the MCG 1120, e.g., via SRB1.

[0330] In this arrangement of NR-DC, the UE can receive two independent information elements related to the measurement configuration measConfig. There is a measConfig associated with the MCG. This can be included, for example, in the RRCReconfiguration message received at the UE from the MCG via SRB1. There can also be a measConfig associated with the SCG. This can be included, for example, in the RRCReconfiguration message received directly from the SCG via SRB3 or an RB (configured for AI / ML functions, such as SRBx or DRB). Alternatively, this can be within the RRCReconfiguration message embedded in the RRCReconfiguration message received via SRB1. In this case, the UE maintains two independent VarMeasConfig and VarMeasReportList, one associated with each measConfig, and all the processes in the present invention are performed independently for each measConfig and the associated VarMeasConfig and VarMeasReportList, unless otherwise explicitly stated.

[0331] For AI / ML data reporting, the AI / ML data (or the AI / ML configuration for the MCG) associated with the MCG can be reported to the MCG via SRB1, as shown in step S1140. As shown in step S1142, the AI / ML data (or the AI / ML configuration for the SCG) associated with the SCG can be reported. This reporting can be via SRB3 or an RB (configured for AI / ML functions, such as SRBx or DRB) or SRB1. For the AI / ML data (or the AI / ML configuration for the SCG) associated with the SCG, if SRB3 or an RB (configured for AI / ML functions, such as SRBx or DRB) is configured, then when the UE reports the AI / ML data, the UE gives priority to SRB3 or an RB (configured for AI / ML functions, such as SRBx or DRB) over SRB1.

[0332] In another embodiment, the network may introduce an indicator to indicate which SRB the UE uses for AI / ML data reporting for the SCG, i.e., SRB1 or SRB3 or RB (configured for AI / ML functions, e.g., SRBx or DRB). In another example, if the SRB3 or RB indicator is included in the RRC reconfiguration message, the UE reports the AI / ML data for the SCG via SRB3 or RB (configured for AI / ML functions, e.g., SRBx or DRB). If the SRB3 or RB indicator is not included, the UE reports the AI / ML data for the SCG via SRB1. In this case, as shown by the dashed line in Figure 11B , at step S1144, the AI / ML data for the SCG is included in the RRC message from the UE to the MCG, and then at step S1146, it is embedded in the RRC message forwarded by the MCG to the SCG. In another example, if the SRB1 indicator is included in the RRC message, the UE reports the AI / ML data for the SCG via SRB1. In this case, as shown by the dashed line, the AI / ML data for the SCG is included in the RRC message that is embedded in the RRC message forwarded by the MCG to the SCG. If the SRB1 indicator is not included, the UE reports the AI / ML data for the SCG to the SCG via SRB3 or RB (configured for AI / ML functions, e.g., SRBx or DRB).

[0333] Figure 11C Figure 6 shows a second option, where the UE 1118 may maintain a joint / single / common AI / ML configuration 1140 for the MCG and the SCG. In other words, the network may operate an AI / ML configuration for the MCG and the SCG, i.e., only one AI / ML configuration is possible, and a common AI / ML configuration (or AI / ML model) for the MCG and the SCG may be configured. For example, when the UE receives a new AI / ML configuration from the MCG or the SCG, the UE replaces (or overwrites) the old AI / ML configuration with the new AI / ML configuration. As shown in Figure 11CAs shown, in step S1152, the AI / ML configuration message AIMLConfig can be included in the RRCReconfiguration message generated by the MCG 1120 and received at the UE 1118, for example, via SRB1. Alternatively, as shown in step S1154, the AI / ML configuration message AIMLConfig can be included in the RRCReconfiguration message generated by the SCG 1122 and received at the UE 1118 via SRB3 or an RB (configured for AI / ML functions, e.g., SRBx or DRB). Alternatively, as shown by the dashed line, in step S1156, the AI / ML configuration message AIMLConfig can be included in the RRCReconfiguration message generated by the SCG 1122 and sent to the MCG. The AI / ML configuration message AIMLConfig is then embedded in the RRCReconfiguration message generated by the MCG 1120 and received at the UE 1118 via SRB1.

[0334] In an arrangement embodiment in NR-DC, the UE may receive a common measConfig. The measConfig can be included in the RRCReconfiguration message received from the MCG via SRB1. The measConfig can be included in the RRCReconfiguration message received from the SCG via SRB3 or an RB (configured for AI / ML functions, e.g., SRBx or DRB). Alternatively, it can be included in the RRCReconfiguration message from the SCG, which is embedded in the RRCReconfiguration message received from the MCG via SRB1.

[0335] In this case, unless otherwise explicitly stated, the UE maintains the common VarMeasConfig and VarMeasReportList, one associated with the measConfig, and performs all the processes in the present invention for the measConfig and the associated VarMeasConfig and VarMeasReportList. The configuration related to CBR measurement is only included in the measConfig associated with the MCG. The configuration related to Rx-Tx time difference measurement is only included in the measConfig associated with the MCG.

[0336] The AI / ML data report can be related to Figure 11BThe same as described. Therefore, the AI / ML data can be reported to the MCG via SRB1 as shown in step S1160, or reported to the SCG via SRB3 or RB (configured for AI / ML functions, such as SRBx or DRB) as shown in step S1162. The report from the SCG to the MCG can be forwarded from the MCG to the SCG via an Xn message. If SRB3 or RB is configured, when the UE reports AI / ML data, the UE gives priority to SRB3 or RB (configured for AI / ML functions, such as SRBx or DRB) over SRB1. As described above, the network can introduce an indicator to indicate which SRB the UE uses for AI / ML data reporting, i.e., SRB1 or SRB3 or RB (configured for AI / ML functions, such as SRBx or DRB). For example, if the indicator is included in the RRC message, the UE reports the AI / ML data via SRB3 or RB; otherwise, SRB1 is used. In another example, if the indicator is included in the RRC message, the UE reports the AI / ML data via SRB1; otherwise, SRB3 or RB is used.

[0337] Figure 11D shows a third option compatible with the Figure 11A or Figure 11C arrangement. In Figure 11D , to simplify the implementation of the UE, this arrangement restricts the network implementation such that the AI / ML configuration is only configured by the MCG 1120. For example, the AI / ML configuration can be included in the RRCReconfiguration message generated by the MCG and received at the UE 1118 via, for example, SRB1, as shown in step S1172. When implementing Figure 11C example, the RRCReconfiguration message can include a common AIML configuration AIMLConfig, or when implementing in Figure 11A example, it can include an MCG-specific AIML configuration AIMLConfigMCG. Alternatively, in step S1176, the AI / ML configuration can be included in the RRCReconfiguration message generated by the SCG 1122 and sent to the MCG 1120. Then, in step S1174, this message is embedded in the RRCReconfiguration message generated by the MCG 1120 and received at the UE1118 via, for example, SRB1. In this example, when implementing Figure 11C example, the RRCReconfiguration message from the SCG to the MCG can include a common AIML configuration AIMLConfig, or when implementing in Figure 11A example, it can include an SCG-specific AIML configuration AIMLConfigSCG.

[0338] In the third option, the UE / network implementation can also be restricted such that AI / ML data is only reported to the MCG (i.e., SRB1). For example, when the data is intended for the MCG, the data can be reported in an RRC message via SRB1, as shown in step S1180. Alternatively, when the data is intended for the SCG, the data can be reported within an RRC message from the UE to the MCG, as shown in step S1182, and then embedded in an RRC message forwarded by the MCG to the SCG in step S1184.

[0339] Figure 11E shows a fourth option compatible with the Figure 11B or Figure 11C arrangement. In Figure 11E , to simplify the UE implementation, this arrangement restricts the network implementation such that the AI / ML configuration 1142 is only configured by the SCG 1122. By configuring only the AI / ML functions for the SCG in the UE, data interruption and data processing burden regarding the MCG 1120 can be avoided, which will be beneficial in terms of load balancing. The AI / ML functions of the SCG 1142 can be configured at the UE 1118 via signaling 1135 directly from the SCG to the UE (e.g., SRB3 (or SRBx) or split SRB3), or indirectly configured via the MCG via signaling 1133, e.g., using SRB3 (or SRBx) and SRB1. Then, the AI / ML functions are stored at the UE as the AI / ML functions of the SCG 1142'.

[0340] In Figures 11A to 11E any or all of the options shown, incremental configuration is supported. For example, the MCG or SCG can reconfigure a part of a previous (or current) AI / ML configuration via an RRC message. In another embodiment, we can introduce an indicator to indicate whether to completely release a previous (or current) AI / ML configuration. In other words, if the indicator is included in the RRC message together with the new AI / ML configuration, the UE releases the current AI / ML configuration and configures the received configuration. Otherwise, if the new AI / ML configuration is included without the indicator, the UE can reconfigure a part of the current AI / ML configuration with the received AI / ML configuration.

[0341] When the UE is configured with AI / ML capabilities for both the MCG and SCG (or either the MCG or the SCG), an indication (or cell group identity) can be used to indicate one of the AI / ML capabilities for (re)configuration or AI / ML data reporting. For example, when the network requests AI / ML data reporting for the MCG by sending a request RRC message via SRBx (or SRB1 or split SRB1), the UE can report it using a response RRC message via SRBx (or SRB1 or split SRB1). When the network requests AI / ML data reporting for the SCG by sending a request RRC message via SRBx (or SRB1 or split SRB1), the UE can report it using a response RRC message via SRBx (or SRB1 or split SRB1 or SRB3). In another embodiment, when the network requests AI / ML data reporting for the SCG by sending a request RRC message via SRB1 (or split SRB1), if SRB3 is not configured or if the SCG is deactivated, the UE can report it using a response RRC message via SRB1 (or split SRB1), while if SRB3 is configured or if the SCG is not deactivated, the UE can report it using a response RRC message via SRB3. When the network requests AI / ML data reporting for the SCG by sending a request RRC message via SRB3, the UE can report it using a response RRC message via SRB3.

[0342] Split SRB handling

[0343] SRB4 is used for RRC messages including application layer measurement report information, all of which use the DCCH logical channel. SRB4 can only be configured by the network after AS security is activated. The main purpose of SRB4 is for QoE (Quality of Experience) measurement. QoE is related to but different from Quality of Service (QoS), and QoS embodies the concept that can measure, improve, and possibly guarantee hardware and software characteristics. For SRB4, split SRB can be used to enhance reliability, while it can complicate the UE's implementation for all multi-RAT dual connection (MR-DC) options. Note that MR-DC is a general term given to a series of dual connection configurations.

[0344] Regarding SRB4, we propose the following options for handling split SRBs. In the first option, split SRBs are supported for all MR-DC options in both SRB1 and SRB2 (split SRBs are not supported for SRB0, SRB3, and SRB4). The benefit of split SRBs is to reduce latency and improve the reliability of data transmission at the cost of UE implementation complexity. For SRB4, considering that SRB4 is mainly used for QoE (Quality of Experience) enhancement, it may be more preferable to reduce UE implementation complexity rather than the benefit of split SRBs. Therefore, it is better to restrict the network configuration, i.e., not allow the network to configure SRB4 with split SRBs for the UE. When the network configures SRB4 with split SRBs for the UE, the UE treats it as an error condition or declares an error (e.g., misconfiguration or configuration failure).

[0345] As a second alternative option, split SRBs are supported for all MR-DC options in SRB1, SRB2, and SRB4 (split SRBs are not supported for SRB0 and SRB3). The benefit of split SRBs is to reduce latency and improve the reliability of data transmission at the cost of UE implementation complexity. It can be extended to the configuration of SRB4 to provide more flexible configuration for the network.

[0346] As explained in the previous example, there may be RBs specifically configured for AI / ML functions, such as SRBx. This RB is used for RRC messages including AI / ML function or configuration-related information, all of which use the DCCH logical channel. SRBx can only be configured by the network after AS security activation. The main purpose of SRBx is for AI / ML functions. For SRBx, split SRBs can be used to enhance reliability, while it can complicate the UE implementation for all MR-DC options.

[0347] Regarding SRBx, we propose the following options for handling split SRBs. In the first option, split SRBs are supported for all MR-DC options in both SRB1 and SRB2 (split SRBs are not supported for SRB0, SRB3, SRB4, and SRBx). The benefit of split SRBs is to reduce latency and improve the reliability of data transmission at the cost of UE implementation complexity. For SRBx, given that SRBx is mainly used for AI / ML functions, reducing UE implementation complexity may be more preferable than the benefit of split SRBs. Therefore, it would be better to restrict the network configuration, i.e., not allow the network to configure SRBx with split SRBs for the UE. When the network configures SRBx with split SRBs for the UE, the UE treats it as an error condition or declares an error (e.g., misconfiguration or configuration failure).

[0348] In a second alternative option, split SRB is supported for all MR-DC options in SRB1, SRB2, and SRBx (split SRB is not supported for SRB0, SRB3, and SRB4). The benefit of split SRB is to reduce latency and improve the reliability of data transmission at the cost of UE implementation complexity. It can be extended to the configuration of SRBx to provide more flexible configuration for the network.

[0349] General method

[0350] Figure 12A is a flowchart showing an overview of the steps of the method described in detail above, particularly with respect to Figures 11A to 11D . The method configures a user equipment (UE) to support artificial intelligence / machine learning (AI / ML) functions in a wireless dual-connectivity communication network. In a first step S1200, a radio resource control (RRC) connection is established from the user equipment 1118 to the master node 1120 of the MCG. The RRC connection can be established on a first channel using a first signaling radio bearer (e.g., SRB1). Optionally, in step S1205, a first RRC connection can also be established from the user equipment 1118 to the master node 1122 of the SCG. The RRC connection can be established on a second channel using the same signaling radio bearer (e.g., SRB1). Messages can be relayed from the SCG to the MCG and vice versa, so it may not be necessary to establish a direct second channel between the UE and the SCG.

[0351] In step S1210, the master node of the MCG 1120 sends a configuration message to the user equipment 1118 via the first channel. The configuration message can include primary measurement configuration information and / or secondary measurement configuration information. The primary measurement configuration information is used to configure the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support the AI / ML function within the MCG, and the secondary measurement configuration information is used to configure the user equipment to collect and report AI / ML data to support the AI / ML function within the SCG. Optionally, in the case where direct communication has been established, in step S1215, the secondary node of the SCG 1122 sends configuration information to the user equipment 1118. This message can receive secondary measurement configuration information.

[0352] In step S1220, the user equipment 1118 receives the message, and in step S1225, the user equipment 1118 uses the primary measurement configuration information and / or secondary measurement configuration information in the received at least one configuration message to configure the user equipment 1118 to collect and report AI / ML data to support the AI / ML function within the MCG and / or the SCG.

[0353] As an optional step of S1230, a second RRC connection using a dedicated radio signal bearer may be established from the user equipment to the master node of the MCG. A second RRC connection using a dedicated radio signal bearer may also be established from the user equipment to the secondary node of the SCG.

[0354] When the user equipment has been configured to collect and report AI / ML data to support AI / ML functions within the MCG and / or SCG, as shown in step S1235, the AI / ML data is collected. Then in step S1240, the collected data that supports the AI / ML function within the MCG is reported from the user equipment to the master node of the MCG. As shown in step S1245, the data is received at the master node. In step S1240, the AI / ML data that supports the AI / ML function within the SCG is also sent to the secondary node of the SCG and is received at the secondary node in step S1250. As shown, the collected AI / ML data that supports the AI / ML function within the SCG may be received directly from the user equipment or via the MCG.

[0355] Figure 12B is a flowchart showing an overview of the steps of the method described in detail above, particularly regarding supporting AI / ML functions for a UE that is not fully connected to the network (e.g., a UE in the RRC inactive or RRC idle state rather than in the RRC connected state). In a first step S1260, a first Radio Resource Control (RRC) connection is established from the user equipment to the network using a first channel. As described above, the connection may be established via a first Signaling Radio Bearer (e.g., SRB1). Then in step S1262, at least one configuration message is sent from the network to the user equipment. In step S1264, the configuration message is received at the user equipment using the first channel via the first Signaling Radio Bearer. The configuration information explains how to configure the user equipment to collect and report AI / ML data to support AI / ML functions within the network. When the network is a dual-connectivity network, the configuration information may include at least one of the following: primary measurement configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the primary cell group; and secondary measurement configuration information for configuring the user equipment to collect and report artificial intelligence / machine learning (AI / ML) data to support AI / ML functions within the secondary cell group. The configuration message may include bearer configuration information for a second Signaling Radio Bearer to support AI / ML functions in the network. The transmission of data related to the AI / ML function may be completed via the second Signaling Radio Bearer.

[0356] In the next step S1268, the information in the configuration message can be used to configure the user equipment. Optionally, the configuration can include: Establishing a second radio resource control (RRC) connection from the user equipment to the network via a second signaling radio bearer is part of configuring the user equipment. The second signaling radio bearer can be a standard signaling radio bearer (e.g., SRB2), a newly configured signaling radio bearer (e.g., SBR5 or other appropriate SRB number), or can be a data radio bearer.

[0357] In step S1272, a release message is sent from the network and received at the user equipment in step S1274. The release message instructs the user equipment to change to one of the inactive state and the idle state, and includes mode change configuration information for configuring the user equipment to support AI / ML functions within the network when in the idle state or the inactive state. For example, the user equipment can be configured to continue measuring data related to the AI / ML function, as shown in step S1278. However, even when the user equipment remains in the inactive state connected to the network, the measured data is not transmitted to the network. In the idle state, the user equipment is disconnected from the network and cannot transmit data.

[0358] As shown in step S1280, a report message is sent from the network and received at the user equipment in step S1282. The report message instructs the user equipment to report the collected AI / ML data to the network. Then, as shown in step S1284, data related to the AI / ML function is sent from the user equipment. As shown in step S1286, the data is received at the network. If a second RRC connection has been established, an RRC message including data related to the AI / ML function can be sent from the user equipment using, for example, a dedicated radio signaling bearer.

[0359] General system

[0360] Figure 13 is a system block diagram including node 1300 in the network and user equipment 1350 connected to node 1300. It should be understood that the system can include multiple local devices, which can also be referred to as client devices or user devices or user equipment, and the system can include multiple nodes or cells and OAM as described above.

[0361] The user device 1350 can be any one of the following: a smart phone, a tablet computer, a laptop computer, a computer or computing device, a virtual assistant device, a vehicle, a drone, an autonomous vehicle, a robot or robotic device, a robotic assistant, an image capture system or device, an augmented reality system or device, a virtual reality system or device, a gaming system, an Internet of Things device or a smart consumer device (such as a smart refrigerator). It should be understood that this is a non-exhaustive and non-limiting list of example devices. The device 1350 includes standard components, such as at least one processor 1352 coupled to a memory 1354. There may also be a microphone 1356 for capturing speech and a user interface 1358 for capturing other user inputs. There may be other sensors 1360 to capture other data including the above-mentioned AI / ML data. It should be understood that there may be other standard components not shown for simplicity, such as the above-mentioned transmitter or receiver. The device 1350 may include one or more modules for collecting user data 1364 stored in a storage device 1362, and such a storage device may be an encrypted storage device. By way of example only, the modules may include the microphone 1356, the user interface 1358, and the sensors 1360.

[0362] The at least one processor 1352 may include one or more of the following: a microprocessor, a microcontroller, and an integrated circuit. The memory 1354 may include volatile memory, such as random access memory (RAM), used as temporary memory, and / or non-volatile memory, such as flash memory, read-only memory (ROM), or electrically erasable programmable ROM (EEPROM) for storing, for example, data, programs, or instructions.

[0363] A training module 1390 may be present on the user device to train the ML model 1306 to generate a local ML model 1380 stored on the user device. The local model parameters 1368 of the local ML model may be stored in the storage device 1362. Alternatively, the user device 1350 may not train the ML model but instead only use the stored local ML model 1380 for inference.

[0364] The system can incorporate federated learning, and thus node 1300 (or OAM) is arranged to perform any pre-training steps required to generate an initial trained ML model 1306. For example, node 1300 receives reference training data (input x and output / label y) from database 1302. Node 1300 includes a training module 1304 that receives the reference data from database 1302 as input and outputs basic or full-precision model parameters (i.e., a set of weights or parameters that have been learned during the training process). As an alternative to federated learning with training module 1390 on the user device, when using training module 1304 on the node, local data can be received from user device 1350 to train the local ML model of user device 1350 in a manner similar to that described for training on the user device. Then the personalized ML model generated on the node is sent to the user device for storage as local ML model 1380. This can be referred to as distributed learning.

[0365] It should be understood that there are other components within node 1300 that are not shown for ease of reference. Node 1300 can also use the trained ML model 1306 for inference, for example, to infer an output based on an input received from device 1350 (e.g., an input such as a measurement from a sensor).

[0366] Figure 14 is a block diagram showing a terminal (or user equipment (UE)) according to an embodiment disclosed herein.

[0367] As Figure 14 shown, a terminal according to an embodiment can include a transceiver 1410, a memory 1420, and a processor (or controller) 1430. The transceiver 1410, memory 1420, and processor (or controller) 1430 of the terminal can operate according to the communication method of the terminal described above. However, the components of the terminal are not limited thereto. For example, the terminal can include more or fewer components than those Figure 14 described. Additionally, the processor (or controller) 1430, transceiver 1410, and memory 1420 can be implemented as a single chip. Furthermore, the processor (or controller) 1430 can include at least one processor. Additionally, Figure 14 the UE of Figures 1 to 1 2 corresponds to UE 18, UE 218, NR UE, UE 318, UE 718, UE 818, UE 918, UE 1018, UE 1118, or device 1450.

[0368] The transceiver 1410 is collectively referred to as a terminal receiver and a terminal transmitter and can transmit / receive signals to / from a base station or another terminal. The signals transmitted to or received from the terminal may include control information and data. The transceiver 1410 may include an RF transmitter for up-converting and amplifying the frequency of the transmission signal and an RF receiver for amplifying the low noise and down-converting the frequency of the received signal. However, this is only an example of the transceiver 1410, and the components of the transceiver 1410 are not limited to the RF transmitter and the RF receiver.

[0369] In addition, the transceiver 1410 may receive signals through a wireless channel and output them to the processor (or controller) 1430, and transmit the signals output from the processor (or controller) 1430 through the wireless channel.

[0370] The memory 1420 may store programs and data required for the operation of the terminal. In addition, the memory 1420 may store control information or data included in the signals obtained by the terminal. The memory 1420 may be a storage medium such as a read-only memory (ROM), a random access memory (RAM), a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0371] The processor (or controller) 1430 may control a series of processes such that the terminal operates as described above. For example, the processor (or controller) 1430 may receive data signals and / or control signals, and the processor (or controller) 1430 may determine the result of receiving signals transmitted by the base station and / or another terminal.

[0372] Figure 15 is a block diagram showing a base station (BS) according to an embodiment disclosed herein.

[0373] As Figure 15 shown, the base station of the present disclosure may include a transceiver 1510, a memory 1520, and a processor (or controller) 1530. The transceiver 1510, the memory 1520, and the processor (or controller) 1530 of the base station may operate according to the communication method of the base station described above. However, the components of the base station are not limited thereto. For example, the base station may include more or fewer components than those Figure 15 described in the above. In addition, the processor (or controller) 1530, the transceiver 1510, and the memory 1520 may be implemented as a single chip. In addition, the processor (or controller) 1530 may include at least one processor. In addition, Figure 15 the base station of Figures 1 to 1ENBs 16a - 16d of 2, LTE eNB 216, eNB 316, NR gNB 326, gNB1, NG-RAN Node 1 (926), NG-RAN Node 2 (928), NG-RAN Node 1 (1026), NG-RAN Node 2 (1026), MCG 1120, SCG 1122, or Node 1200.

[0374] The transceiver 1510 is collectively referred to as a base station receiver and a base station transmitter and can send / receive signals to / from a terminal, another base station, and / or a core network function (or entity). Signals sent to or received from a base station can include control information and data. The transceiver 1510 can include an RF transmitter for up-converting and amplifying the frequency of a transmitted signal and an RF receiver for amplifying the frequency of a received signal with low noise and down-converting it. However, this is only an example of the transceiver 1510, and the components of the transceiver 1510 are not limited to an RF transmitter and an RF receiver.

[0375] In addition, the transceiver 1510 can receive a signal through a wireless channel and output it to the processor (or controller) 1530, and send a signal output from the processor (or controller) 1530 through the wireless channel.

[0376] The memory 1520 can store programs and data required for the operation of the base station. In addition, the memory 1520 can store control information or data included in the signals obtained by the base station. The memory 1520 can be a storage medium such as ROM, RAM, hard disk, CD-ROM, and DVD, or a combination of storage media.

[0377] The processor (or controller) 1530 can control a series of processes so that the base station operates as described above. For example, the processor (or controller) 1530 can receive data signals and / or control signals, and the processor (or controller) 1530 can determine the result of receiving signals sent by the terminal and / or the core network function.

[0378] Detailed process of RRC connection control

[0379] RRCSetup received by the UE

[0380] Figure 8 Outlines how to establish an RRC connection. The following pseudocode gives the details of the steps performed by the UE when receiving RRCSetup:

[0381]

[0382]

[0383]

[0384] The UE receives RRCReconfiguration

[0385] Figure 8 It also outlines how to perform RRC reconfiguration. The following pseudocode gives details of the steps executed by the UE upon receiving an RRCReconfiguration message. These steps can also be executed based on conditional reconfiguration (CHO, CPA or CPC). As described above, when an RRC message (RRCReconfiguration or RRCResume) includes configuration information, the UE can apply AI / ML configuration. If the UE receives an AI / ML configuration in otherConfig of the RRCReconfguration, the UE can include AI / ML data in subsequent RRC messages to enable the network to utilize this information for network management. When the UE receives a handover command message (i.e., an RRCReconfiguration including reconfigurationWithSync) from the network (or gNB or source gNB), the UE can send a handover complete message (i.e., RRCReconfigurationComplete) to the network (or gNB or target gNB). The UE can include an indication of the availability of the AI / ML data to be reported or the AI / ML data itself in the response message (RRCReconfigurationComplete) to notify the network. In addition to this, the UE can support retransmission of RRC messages including AI / ML data, i.e., the UE can retransmit it before its successful delivery has been acknowledged (e.g., from the source gNB).

[0386]

[0387]

[0388]

[0389] AI / ML configuration

[0390] Figure 9 and Figure 10 are examples of how AI / ML data is used in a network including the UE. The following pseudocode gives details of the steps executed by the UE when configuring the AI / ML configuration:

[0391]

[0392]

[0393] The UE receives RRCRelease

[0394] Figure 9 and Figure 10 is an example of how AI / ML data is used in a network including a UE. As described above, when the UE is in the RRC inactive state, AI / ML capabilities can be supported. The following pseudocode gives details of the steps performed by the UE when receiving an RRCRelease. As described below, when receiving an RRCRelease message, there is a process of storing the AI / ML configuration in the UE inactive AS context. When the UE enters the RRC connected state upon receiving an RRCResume (or RRCReconfiguration) that indicates the AI / ML configuration, the UE can resume the AI / ML configuration.

[0395]

[0396]

[0397] Received by UE: RRCResume

[0398] The following pseudocode gives details of the steps performed by the UE when receiving an RRCResume that indicates the AI / ML configuration to be resumed when the UE enters the RRC connected state. If the indication is not included in the RRCResume, the UE can release the stored AI / ML configuration from the UE inactive AS context.

[0399]

[0400]

[0401]

[0402]

[0403] UE Actions upon Entering RRC_IDLE

[0404] If a UE in the RRC idle state does not support AI / ML capabilities, there is a process of discarding AI / ML data or releasing the AI / ML configuration when the UE moves from the RRC connected (or RRC inactive) mode to the RRC idle state. The following pseudocode gives the actions of the UE when entering RRC_IDLE:

[0405]

[0406]

[0407] Received by UE: RRCReject

[0408] The following pseudocode shows the actions of the UE when it receives an RRCReject message:

[0409]

[0410]

[0411] Note that if timer T331 is running, the UE continues with idle / inactive measurements. It should also be noted that if timer Txxx (a timer configured for AI / ML operations) is running, the UE continues with AI / ML operations (e.g., collecting AI / ML data or performing measurements) according to the AI / ML configuration even if the UE receives an RRCReject message from the network.

[0412] UE Quantity Configuration

[0413] The following pseudocode shows the actions of the UE for quantity configuration. The UE shall:

[0414]

[0415] UE Measurement Reporting

[0416] The following pseudocode shows the actions of the UE for the identified measurement (measId) that triggers the measurement reporting procedure. The UE shall set the measResults within the MeasurementReport message as follows:

[0417]

[0418]

[0419]

[0420]

[0421]

[0422]

[0423]

[0424]

[0425]

[0426]

[0427]

[0428]

[0429]

[0430]

[0431]

[0432] Details of various information elements

[0433] As described above, there are various information elements in the RRC message structure. The codes for these elements are provided below:

[0434]

[0435]

[0436]

[0437]

[0438]

[0439]

[0440]

[0441]

[0442]

[0443]

[0444]

[0445]

[0446]

[0447]

[0448]

[0449]

[0450]

[0451]

[0452]

[0453]

[0454]

[0455]

[0456]

[0457]

[0458]

[0459]

[0460]

[0461]

[0462]

[0463]

[0464]

[0465]

[0466]

[0467]

[0468]

[0469]

[0470]

[0471]

[0472]

[0473]

[0474]

[0475]

[0476]

[0477]

[0478]

[0479]

[0480]

[0481]

[0482]

[0483]

[0484]

[0485]

[0486]

[0487]

[0488]

[0489]

[0490]

[0491]

[0492] Those skilled in the art will understand that although the best mode and other suitable modes of carrying out the technology have been described above, the technology should not be limited to the specific configurations and methods disclosed in the description of the preferred embodiments. Those skilled in the art will recognize that the technology has a wide range of applications and that the embodiments can be widely modified without departing from any inventive concept defined in the appended claims.

[0493] Various combinations of alternative features have been described herein, and it should be understood that the described features can be combined in any suitable combination. In particular, the features of any one exemplary embodiment can be appropriately combined with the features of any other embodiment, unless such a combination is mutually exclusive. Throughout the specification, the term "comprising" or "including" means including the specified components but not excluding the presence of other components.

[0494] Attention is directed to all papers and documents filed concurrently with this specification or filed in connection with this application prior to this specification, and such papers and documents are open to public inspection with this specification, and the contents of all such papers and documents are incorporated herein by reference. All features disclosed in this specification (including any accompanying claims, abstract and drawings) and / or all steps of any method or process so disclosed may be combined in any combination, except combinations in which at least some of such features and / or steps are mutually exclusive.

[0495] Unless expressly stated otherwise, each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by an alternative feature serving the same, equivalent or similar purpose. Therefore, unless expressly stated otherwise, each feature disclosed is only one example of a series of generally equivalent or similar features. The invention is not limited to the details of the foregoing embodiments. The invention extends to any novel one or any novel combination of the features disclosed in this specification (including any accompanying claims, abstract and drawings), or to any novel one or any novel combination of the steps of any method or process so disclosed.

Claims

1. A method performed by a user equipment (UE) for transmitting data between the UE and a dual-connectivity wireless communication network including a master cell group (MCG) and a secondary cell group (SCG), the method comprising: Establishing a radio resource control (RRC) connection between the UE and a master node of the MCG on a first channel; Receiving, on the first channel by using a first receiver of the UE, at least one configuration message including at least one of master measurement configuration information and secondary measurement configuration information from the master node of the MCG; Collecting and reporting artificial intelligence / machine learning (AI / ML) data to the master node of the MCG based on the master measurement configuration information to support the AI / ML function within the MCG, or Collecting and reporting the AI / ML data to a secondary node of the SCG based on the secondary measurement configuration information to support the AI / ML function within the SCG.

2. The method according to claim 1, the method further comprising: Establishing a radio resource control (RRC) connection between a second receiver of the UE and the secondary node on a second channel, and Receiving, on the second channel by using the second receiver, the at least one configuration message from the secondary node, the at least one configuration message including information for supporting the AI / ML function in the SCG.

3. The method according to claim 1, Among them, The at least one configuration message further includes bearer configuration information for configuring at least one dedicated signaling radio bearer (SRB) dedicated to transmitting data related to the AI / ML function.

4. The method according to claim 3, the method further comprising: Receiving an indicator indicating the use of the dedicated SRB from the master node of the MCG in case of reporting the collected AI / ML data to the master node or the secondary node.

5. A user equipment (UE) in a dual-connectivity communication network, the UE comprising: A first receiver and a first transmitter connectable to a master node of a master cell group (MCG), A second receiver and a second transmitter connectable to a secondary node of a secondary cell group (SCG); And At least one processor configured to: Establish a radio resource control (RRC) connection between the first receiver and the first transmitter at the UE and the master node on a first channel; Receiving, on the first channel by using the first receiver of the UE, at least one configuration message including at least one of master measurement configuration information and secondary measurement configuration information from the master node of the MCG; And Collecting and reporting artificial intelligence / machine learning (AI / ML) data to the master node of the MCG based on the master measurement configuration information to support the AI / ML function within the MCG, or Collecting and reporting the AI / ML data to a secondary node of the SCG based on the secondary measurement configuration information to support the AI / ML function within the SCG.

6. The UE according to claim 5, wherein, The at least one processor is further configured to: Establish a Radio Resource Control (RRC) connection between a second receiver of the UE and a secondary node on a second channel, and Receive, by using the second receiver on the second channel, the at least one configuration message from the secondary node, the at least one configuration message including information for supporting AI / ML functions in the SCG.

7. The UE according to claim 5, wherein, The at least one processor is further configured to: Wherein, the at least one configuration message further includes bearer configuration information for configuring at least one dedicated signaling radio bearer (SRB) dedicated to transmitting data related to the AI / ML function.

8. The UE according to claim 5, wherein The at least one processor is further configured to: In the case of reporting the collected AI / ML data to the primary node or the secondary node, receive an indicator indicating the use of the dedicated SRB from the primary node of the MCG.

9. A method performed by a primary node of a Master Cell Group (MCG) for transmitting data between a User Equipment (UE) and a dual-connectivity communication network including the MCG and a Secondary Cell Group (SCG), the method comprising: Establish a Radio Resource Control (RRC) connection between the primary node of the MCG and the UE on a first channel; Send, via the first channel, at least one configuration message including at least one of primary measurement configuration information and secondary measurement configuration information to a first receiver of the UE; Receive artificial intelligence / machine learning (AI / ML) data from the UE to support AI / ML functions within the MCG, wherein the AI / ML data is based on the primary measurement configuration information.

10. The method according to claim 9, Among them, The at least one configuration message further includes bearer configuration information for configuring at least one dedicated signaling radio bearer (SRB) dedicated to transmitting data related to the AI / ML function.

11. The method according to claim 10, the method further comprising: In the case of reporting the collected AI / ML data to the primary node or the secondary node, send an indicator indicating the use of the dedicated SRB to the UE.

12. A primary node of an MCG for transmitting data between a User Equipment (UE) and a dual-connectivity communication network including a Master Cell Group (MCG) and a Secondary Cell Group (SCG), the method comprising: A transceiver; At least one processor, the at least one processor being connected to the transceiver and configured to: Establish a Radio Resource Control (RRC) connection between the primary node and a first receiver and a first transmitter of the UE on a first channel; Send, via the first channel, at least one configuration message including at least one of primary measurement configuration information and secondary measurement configuration information to the first receiver of the UE; And Receive artificial intelligence / machine learning (AI / ML) data from the UE to support AI / ML functions within the MCG, wherein the AI / ML data is based on the primary measurement configuration information.

13. The primary node according to claim 12, Among them, The at least one configuration message further includes bearer configuration information for configuring at least one dedicated signaling radio bearer (SRB) dedicated to transmitting data related to the AI / ML function.

14. The master node according to claim 13, wherein, The at least one processor is further configured to: In the case of reporting the collected AI / ML data to the master node or the secondary node, send an indicator to the UE indicating the use of the dedicated SRB.

15. The master node according to claim 13, wherein, The at least one processor is further configured to: Establish the RRC connection between the master node and the first receiver and the first transmitter by using the bearer configuration information, Send at least one RRC message including data related to the AI / ML function to the UE by using the dedicated SRB.

Images