Communication equipment and communication methods

Abstract

A communication device, which communicates with another communication device in a mobile communication system that uses machine learning technology, comprises: a control unit that executes at least one machine learning process out of a learning process for deriving a trained model using learning data and an inference process for inferring inference result data from inference data using the trained model; and a transmission unit that transmits to the communication device, a message containing information elements relating to the processing capacity and / or storage capacity available to the communication device for a machine learning process.

Description

Technical Field

[0001] The present disclosure relates to a communication device and a communication method used in a mobile communication system.

Background Art

[0002] In recent years, in 3GPP (Third Generation Partnership Project) (registered trademark; the same shall apply hereinafter), which is a standardization project for mobile communication systems, studies have been conducted on applying artificial intelligence (AI) technology, particularly machine learning (ML) technology, to the wireless communication (air interface) of mobile communication systems.

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

[0004] A communication device according to a first aspect is a device that communicates with another communication device in a mobile communication system using machine learning technology. The communication device includes a control unit that executes at least one of machine learning processes, namely, a learning process for deriving a learned model using learning data and an inference process for inferring inference result data from inference data using the learned model, and a transmission unit that transmits a message including an information element regarding the processing capacity and / or storage capacity that the communication device can use for the machine learning process to the other communication device.

[0005] A second communication method is a method performed by a communication device that communicates with another communication device in a mobile communication system using machine learning technology. The communication method includes the steps of: performing at least one of a machine learning process, which is a learning process that derives a trained model using training data, and an inference process that infers inference result data from inference data using the trained model; and transmitting a message to the other communication device that includes information elements regarding the processing capacity and / or memory capacity available for the machine learning process. [Brief explanation of the drawing]

[0006] [Figure 1] This diagram shows the configuration of a mobile communication system according to an embodiment. [Figure 2] This diagram shows the configuration of the UE (User Equipment) according to the embodiment. [Figure 3] This diagram shows the configuration of the gNB (base station) according to the embodiment. [Figure 4] This diagram shows the protocol stack configuration of the user plane wireless interface that handles data. [Figure 5] This diagram shows the protocol stack configuration of the wireless interface of the control plane that handles signaling (control signals). [Figure 6] This figure shows the functional block configuration of AI / ML technology in a mobile communication system according to this embodiment. [Figure 7] This diagram shows an overview of the operation for each operation scenario according to the embodiment. [Figure 8] This is a diagram showing the first operation scenario according to the embodiment. [Figure 9] This figure shows a first example of reducing CSI-RS according to the embodiment. [Figure 10] This figure shows a second example of reducing CSI-RS according to the embodiment. [Figure 11] This is an operation flowchart showing a first operation example related to the first operation scenario according to the embodiment. [Figure 12]This is an operation flow diagram showing a second operation example related to the first operation scenario according to the embodiment. [Figure 13] This is an operation flow diagram showing a third operation example related to the first operation scenario according to the embodiment. [Figure 14] This figure shows a second operation scenario according to the embodiment. [Figure 15] This is an operation flowchart showing an example of operation related to the second operation scenario according to the embodiment. [Figure 16] This figure shows a third operation scenario according to the embodiment. [Figure 17] This is an operation flowchart showing an example of operation related to the third operation scenario according to the embodiment. [Figure 18] This is a diagram illustrating the notification of capacity information or load status information according to the embodiment. [Figure 19] This is a diagram illustrating the configuration of the model according to the embodiment. [Figure 20] This figure shows a first example of operation related to model transfer according to the embodiment. [Figure 21] This figure shows an example of a configuration message including a model and additional information according to the embodiment. [Figure 22] This figure shows a second example of operation related to model transfer according to the embodiment. [Figure 23] This figure shows an example of the operation related to the split transmission of a configuration message according to the embodiment. [Figure 24] This figure shows a third example of operation related to model transfer according to the embodiment. [Modes for carrying out the invention]

[0007] When attempting to apply machine learning technology to mobile communication systems, the specific techniques for how to utilize machine learning processing have not yet been established.

[0008] Therefore, this disclosure aims to enable the use of machine learning processing in mobile communication systems.

[0009] Referring to the drawings, a mobile communication system according to an embodiment will be described. In the description of the drawings, the same or similar parts are denoted by the same or similar reference numerals.

[0010] (Configuration of Mobile Communication System) First, the configuration of the mobile communication system according to the embodiment will be described. FIG. 1 is a diagram showing the configuration of a mobile communication system 1 according to the embodiment. The mobile communication system 1 complies with the 5th generation system (5GS) of the 3GPP standard. Hereinafter, the 5GS will be described as an example, but the LTE (Long Term Evolution) system may be at least partially applied to the mobile communication system. Alternatively, the 6th generation (6G) system may be at least partially applied to the mobile communication system.

[0011] The mobile communication system 1 includes a user equipment (UE: User Equipment) 100, a 5G radio access network (NG-RAN: Next Generation Radio Access Network) 10, and a 5G core network (5GC: 5G Core Network) 20. Hereinafter, the NG-RAN 10 may be simply referred to as the RAN 10. Also, the 5GC 20 may be simply referred to as the core network (CN) 20.

[0012] The UE 100 is a movable wireless communication device. The UE 100 may be any device as long as it is a device used by a user. For example, the UE 100 is a mobile phone terminal (including a smartphone), a tablet terminal, a notebook PC, a communication module (including a communication card or a chipset), a sensor or a device provided in the sensor, a vehicle or a device provided in the vehicle (Vehicle UE), an aircraft or a device provided in the aircraft (Aerial UE).

[0013] NG-RAN10 includes base stations (referred to as "gNBs" in 5G systems) 200. The gNBs 200 are interconnected via the Xn interface, which is an inter-base station interface. Each gNB 200 manages one or more cells. The gNB 200 performs wireless communication with UEs 100 that have established a connection with its own cell. The gNB 200 has radio resource management (RRM) functions, user data routing functions (hereinafter simply referred to as "data"), measurement and control functions for mobility control and scheduling, etc. "Cell" is used as a term to indicate the smallest unit of a wireless communication area. "Cell" is also used as a term to indicate a function or resource that performs wireless communication with the UE 100. One cell belongs to one carrier frequency (hereinafter simply referred to as "frequency").

[0014] Furthermore, gNBs can also connect to the EPC (Evolved Packet Core), which is the core network of LTE. LTE base stations can also connect to 5GCs. LTE base stations and gNBs can also be connected via an inter-base station interface.

[0015] The 5GC20 includes the AMF (Access and Mobility Management Function) and the UPF (User Plane Function) 300. The AMF performs various mobility controls for the UE100. The AMF manages the mobility of the UE100 by communicating with it using NAS (Non-Access Stratum) signaling. The UPF controls data transfer. The AMF and UPF are connected to the gNB200 via the NG interface, which is the base station-core network interface.

[0016] Figure 2 shows the configuration of UE100 (user device) according to an embodiment. UE100 comprises a receiving unit 110, a transmitting unit 120, and a control unit 130. The receiving unit 110 and the transmitting unit 120 constitute a communication unit that performs wireless communication with gNB200. UE100 is an example of a communication device.

[0017] The receiving unit 110 performs various types of reception under the control of the control unit 130. The receiving unit 110 includes an antenna and a receiver. The receiver converts the radio signal received by the antenna into a baseband signal (received signal) and outputs it to the control unit 130.

[0018] The transmitting unit 120 performs various types of transmissions under the control of the control unit 130. The transmitting unit 120 includes an antenna and a transmitter. The transmitter converts the baseband signal (transmission signal) output by the control unit 130 into a wireless signal and transmits it from the antenna.

[0019] The control unit 130 performs various control and processing operations in the UE 100. Such processing includes processing in each layer described later. The control unit 130 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used for processing by the processor. The processor may include a baseband processor and a CPU (Central Processing Unit). The baseband processor performs modulation, demodulation, encoding, and decoding of baseband signals. The CPU executes programs stored in memory and performs various processing operations.

[0020] Figure 3 shows the configuration of a gNB200 (base station) according to an embodiment. The gNB200 comprises a transmitter 210, a receiver 220, a control unit 230, and a backhaul communication unit 240. The transmitter 210 and receiver 220 constitute a communication unit that performs wireless communication with the UE100. The backhaul communication unit 240 constitutes a network communication unit that communicates with the CN20. The gNB200 is another example of a communication device.

[0021] The transmitting unit 210 performs various types of transmissions under the control of the control unit 230. The transmitting unit 210 includes an antenna and a transmitter. The transmitter converts the baseband signal (transmission signal) output by the control unit 230 into a radio signal and transmits it from the antenna.

[0022] The receiving unit 220 performs various types of reception under the control of the control unit 230. The receiving unit 220 includes an antenna and a receiver. The receiver converts the radio signal received by the antenna into a baseband signal (received signal) and outputs it to the control unit 230.

[0023] The control unit 230 performs various control and processing in the gNB200. Such processing includes processing in each layer described later. The control unit 230 includes at least one processor and at least one memory. The memory stores programs executed by the processor and information used for processing by the processor. The processor may include a baseband processor and a CPU. The baseband processor performs modulation, demodulation, encoding, and decoding of baseband signals. The CPU executes programs stored in memory and performs various processing.

[0024] The backhaul communication unit 240 is connected to an adjacent base station via the Xn interface, which is an inter-base station interface. The backhaul communication unit 240 is connected to the AMF / UPF300 via the NG interface, which is an inter-base station-core network interface. The gNB200 may consist of a central unit (CU) and distributed units (DU) (i.e., functionally separated), and the two units may be connected by the F1 interface, which is a fronthaul interface.

[0025] Figure 4 shows the configuration of the protocol stack for the user plane's wireless interface that handles data.

[0026] The user plane radio interface protocol comprises a physical (PHY) layer, a media access control (MAC) layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, and a service data adaptation protocol (SDAP) layer.

[0027] The PHY layer performs encoding / decoding, modulation / demodulation, antenna mapping / demapping, and resource mapping / demapping. Data and control information are transmitted between the UE100's PHY layer and the gNB200's PHY layer via a physical channel. The UE100's PHY layer receives downlink control information (DCI) transmitted from the gNB200 over the physical downlink control channel (PDCCH). Specifically, the UE100 performs blind decoding of the PDCCH using a Radio Network Temporary Identifier (RNTI) and acquires the successfully decoded DCI as the DCI addressed to its own UE. The DCI transmitted from the gNB200 has a CRC parity bit added, which is scrambled by the RNTI.

[0028] In NR, UE100 can use a bandwidth narrower than the system bandwidth (i.e., the cell bandwidth). The gNB200 configures a bandwidth portion (BWP) consisting of consecutive PRBs for UE100. UE100 sends and receives data and control signals in the active BWP. For example, up to four BWPs may be configured for UE100. Each BWP may have a different subcarrier spacing, or the frequencies of each BWP may overlap. If multiple BWPs are configured for UE100, the gNB200 can specify which BWP to apply by controlling the downlink. This allows the gNB200 to dynamically adjust the UE bandwidth according to the amount of data traffic on UE100, thereby reducing UE power consumption.

[0029] The gNB200 can, for example, configure up to three control resource sets (CORESETs) for each of up to four BWPs on a serving cell. A CORESET is a radio resource for control information that the UE100 should receive. The UE100 may have up to 12 or more CORESETs configured on a serving cell. Each CORESET may have an index from 0 to 11 or more. A CORESET may consist of six resource blocks (PRBs) and one, two, or three consecutive OFDM symbols in the time domain.

[0030] The MAC layer performs data priority control, retransmission processing using Hybrid Automatic Repeat request (HARQ), and random access procedures. Data and control information are transmitted between the MAC layer of the UE100 and the MAC layer of the gNB200 via the transport channel. The MAC layer of the gNB200 includes a scheduler. The scheduler determines the transport format for the up and down links (transport block size, modulation and coding scheme (MCS)) and the resource blocks to be allocated to the UE100.

[0031] The RLC layer transmits data to the receiving RLC layer using the functions of the MAC layer and PHY layer. Data and control information are transmitted between the UE100's RLC layer and the gNB200's RLC layer via a logical channel.

[0032] The PDCP layer performs header compression / decompression, encryption / decryption, etc.

[0033] The SDAP layer maps IP flows, which are the units under which the core network performs QoS (Quality of Service) control, to wireless bearers, which are the units under which the access layer (AS: Access Stratum) performs QoS control. Note that if the RAN is connected to the EPC, the SDAP layer may not be necessary.

[0034] Figure 5 shows the configuration of the protocol stack of the wireless interface of the control plane that handles signaling (control signals).

[0035] The protocol stack of the control plane's wireless interface includes a Radio Resource Control (RRC) layer and a Non-Access Stratum (NAS) layer, instead of the SDAP layer shown in Figure 4.

[0036] RRC signaling for various settings is transmitted between the RRC layer of the UE100 and the RRC layer of the gNB200. The RRC layer controls the logical channel, transport channel, and physical channel in response to the establishment, re-establishment, and release of the radio bearer. If there is a connection (RRC connection) between the RRC of the UE100 and the RRC of the gNB200, the UE100 is in the RRC connected state. If there is no connection (RRC connection) between the RRC of the UE100 and the RRC of the gNB200, the UE100 is in the RRC idle state. If the connection between the RRC of the UE100 and the RRC of the gNB200 is suspended, the UE100 is in the RRC inactive state.

[0037] The NAS, located above the RRC layer, handles session management and mobility management, among other things. NAS signaling is transmitted between the UE100's NAS and the AMF300A's NAS. The UE100 also has application layers in addition to the wireless interface protocol. Layers below the NAS are called AS (Access Stratum).

[0038] (Overview of AI / ML technology) Next, the AI / ML technology according to the embodiment will be described. Figure 6 is a diagram showing the functional block configuration of the AI / ML technology in the mobile communication system 1 according to the embodiment.

[0039] The functional block configuration shown in Figure 6 includes a data acquisition unit A1, a model learning unit A2, a model inference unit A3, and a data processing unit A4.

[0040] The data collection unit A1 collects input data, specifically training data and inference data, outputs the training data to the model training unit A2, and outputs the inference data to the model inference unit A3. The data collection unit A1 may acquire data from its own device as input data. Alternatively, the data collection unit A1 may acquire data from another device as input data.

[0041] The model learning unit A2 performs model learning. Specifically, the model learning unit A2 optimizes the parameters of the learning model using machine learning with training data, derives (generates, updates) a trained model, and outputs the trained model to the model inference unit A3. For example, considering y=ax+b, a (slope) and b (intercept) are parameters, and optimizing these corresponds to machine learning. Generally, there are three types of machine learning: supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a method that uses correct answer data as training data. Unsupervised learning is a method that does not use correct answer data as training data. For example, in unsupervised learning, feature points are memorized from a large amount of training data, and correct answers are judged (range estimation) is performed. Reinforcement learning is a method that assigns a score to the output result and learns how to maximize the score.

[0042] The model inference unit A3 performs model inference. Specifically, the model inference unit A3 uses a trained model to infer an output from the inference data and outputs the inference result data to the data processing unit A4. For example, in the equation y=ax+b, x corresponds to the inference data and y corresponds to the inference result data. Note that "y=ax+b" is the model. A model with optimized slope and intercept, such as "y=5x+3", is a trained model. Here, there are various modeling methods (approaches), including linear regression analysis, neural networks, and decision tree analysis. The above "y=ax+b" can be considered a type of linear regression analysis. The model inference unit A3 may also provide model performance feedback to the model learning unit A2.

[0043] Data processing unit A4 receives the inference result data and performs processing that utilizes the inference result data.

[0044] When applying machine learning technology to wireless communication in a mobile communication system, the arrangement of the functional block configuration shown in Figure 6 becomes a problem. In the description of each embodiment, wireless communication between UE100 and gNB200 is primarily assumed. In this case, the arrangement of each functional block in Figure 6 on UE100 and gNB200 becomes a problem. Furthermore, once the arrangement of each functional block is determined, the question arises of how to control and configure each functional block from gNB200 to UE100.

[0045] Figure 7 is a diagram showing an overview of the operation for each operation scenario according to the embodiment. In Figure 7, one of UE100 and gNB200 corresponds to the first communication device, and the other corresponds to the second communication device.

[0046] In step S1, UE100 transmits or receives control data related to model learning to or from gNB200. The control data may be an RRC message, which is signaling for the RRC layer (i.e., Layer 3). Alternatively, the control data may be a MAC CE (Control Element), which is signaling for the MAC layer (i.e., Layer 2). Alternatively, the control data may be downlink control information (DCI), which is signaling for the PHY layer (i.e., Layer 1). The downlink signaling may be UE-specific signaling. Alternatively, the downlink signaling may be broadcast signaling. The control data may also be a control message in a control layer specialized for artificial intelligence or machine learning (e.g., an AI / ML layer).

[0047] (First action scenario) Figure 8 shows a first operation scenario according to the embodiment. In the first operation scenario, the data acquisition unit A1, the model learning unit A2, and the model inference unit A3 are located in the UE100 (for example, the control unit 130), and the data processing unit A4 is located in the gNB200 (for example, the control unit 230). In other words, model learning and model inference are performed on the UE100 side.

[0048] In the first operational scenario, machine learning techniques are introduced to the channel status information (CSI) feedback from UE100 to gNB200. The CSI sent (feeded back) from UE100 to gNB200 is information indicating the channel status of the downlink between UE100 and gNB200. The CSI includes at least one of the following: channel quality indicator (CQI), precoding matrix indicator (PMI), and rank indicator (RI). Based on the CSI feedback from UE100, gNB200 performs, for example, downlink scheduling.

[0049] The gNB200 transmits a reference signal for the UE100 to estimate the channel state of the downlink. Such a reference signal may be, for example, a CSI reference signal (CSI-RS) or a demodulation reference signal (DMRS). In the description of the first operating scenario, we assume that the reference signal is CSI-RS.

[0050] Firstly, during model training, UE100 (receiver 110) receives a first reference signal from gNB200 using a first resource. Then, UE100 (model training unit A2) uses training data, including the first reference signal, to derive a trained model for inferring CSI from the reference signal. In the description of the first operating scenario, such a first reference signal is sometimes referred to as full CSI-RS.

[0051] For example, UE100 (CSI generation unit 131) performs channel estimation using the received signal (CSI-RS) received by the receiver unit 110 from gNB200 and generates a CSI. UE100 (transmitter unit 120) transmits the generated CSI to gNB200. Model learning unit A2 uses multiple sets of received signals (CSI-RS) and CSIs as training data to perform model learning and derives a trained model for inferring CSI from received signals (CSI-RS).

[0052] Secondly, in model inference, UE100 (receiver 110) receives a second reference signal from gNB200 using a second resource which is less resource than the first resource. Then, UE100 (model inference unit A3) uses a trained model to infer the CSI as inference result data from the inference data including the second reference signal. In the description of the first operation scenario, such a second reference signal may be referred to as a partial CSI-RS or a punctured CSI-RS.

[0053] For example, UE100 (model inference unit A3) uses the received signal (CSI-RS) received by the receiver unit 110 from gNB200 as inference data, and uses a trained model to infer the CSI from the received signal (CSI-RS). UE100 (transmitter unit 120) transmits the inferred CSI to gNB200.

[0054] This allows the UE100 to feed back the accurate (complete) CSI to the gNB200 from the small amount of CSI-RS (partial CSI-RS) received from the gNB200. For example, the gNB200 can intentionally reduce (puncture) the CSI-RS to reduce overhead. It also allows the UE100 to cope with situations where wireless conditions deteriorate and some CSI-RS cannot be received properly.

[0055] Figure 9 shows a first example of reducing CSI-RS according to the embodiment. In the first example, the gNB200 reduces the number of antenna ports that transmit CSI-RS. For example, in the mode in which the UE100 performs model learning, the gNB200 transmits CSI-RS from all antenna ports on the antenna panel. On the other hand, in the mode in which the UE100 performs model inference, the gNB200 reduces the number of antenna ports that transmit CSI-RS and transmits CSI-RS from half of the antenna ports on the antenna panel. Note that antenna ports are an example of resources. This reduces overhead, improves the utilization efficiency of antenna ports, and reduces power consumption.

[0056] Figure 10 shows a second example of reducing CSI-RS according to the embodiment. In the second example, the gNB200 reduces the number of radio resources, specifically time-frequency resources, used to transmit CSI-RS. For example, in the mode in which the UE100 performs model learning, the gNB200 transmits CSI-RS using a predetermined amount of time-frequency resources. On the other hand, in the mode in which the UE100 performs model inference, the gNB200 transmits CSI-RS using a smaller amount of time-frequency resources than the predetermined amount. This reduces overhead, improves the efficiency of radio resource utilization, and reduces power consumption.

[0057] Next, a first example of operation related to the first operation scenario will be described. In this first example of operation, the gNB200 sends a switching notification to the UE100 as control data to notify it of a mode switch between a mode for performing model learning (hereinafter also referred to as "learning mode") and a mode for performing model inference (hereinafter also referred to as "inference mode"). The UE100 receives the switching notification and performs a mode switch between the learning mode and the inference mode. This makes it possible to perform a mode switch between the learning mode and the inference mode appropriately. The switching notification may be setting information that sets the mode for the UE100. Alternatively, the switching notification may be a switching command that instructs the UE100 to switch modes.

[0058] In this first operational example, when model training is complete, UE100 sends a completion notification to gNB200 as control data indicating that model training is complete. gNB200 receives the completion notification. This allows gNB200 to understand that model training has been completed on the UE100 side.

[0059] Figure 11 is an operation flow diagram showing a first example of operation according to the first operation scenario of the embodiment. This flow may be performed after UE100 has established an RRC connection with the gNB200 cell. In the following operation flow diagram, optional steps are indicated by dashed lines.

[0060] In step S101, the gNB200 may notify or set the input data pattern in inference mode, for example, the CSI-RS transmission pattern (puncture pattern) in inference mode, to the UE100 as control data. For example, the gNB200 notifies the UE100 of the antenna ports and / or time-frequency resources that transmit or do not transmit CSI-RS in inference mode.

[0061] In step S102, the gNB200 may send a switch notification to the UE100 to initiate learning mode.

[0062] In step S103, UE100 enters learning mode.

[0063] In step S104, gNB200 transmits a full CSI-RS. UE100 receives the full CSI-RS and generates a CSI based on the received CSI-RS. In learning mode, UE100 can perform supervised learning using the received CSI-RS and its corresponding CSI. UE100 may derive and manage learning results (trained models) for each of its communication environments, for example, for each reception quality (RSRP, RSRQ, SINR) and / or mobile speed.

[0064] In step S105, UE100 sends (feeds back) the generated CSI to gNB200.

[0065] Subsequently, in step S106, when model training is complete, UE100 sends a completion notification to gNB200 indicating that model training is complete. UE100 may also send a completion notification to gNB200 when the derivation (generation, update) of the trained model is complete. Here, UE100 may also send a notification indicating the completion of training for each of its communication environments (e.g., mobile speed, reception quality). In this case, UE100 includes information in the notification indicating which communication environment the completion notification pertains to.

[0066] In step S107, the gNB200 sends a switch notification to the UE100 to switch from learning mode to inference mode.

[0067] In step S108, UE100 switches from learning mode to inference mode in response to receiving the switch notification in step S107.

[0068] In step S109, gNB200 transmits a partial CSI-RS. Upon receiving the partial CSI-RS, UE100 uses a trained model to infer the CSI from the received CSI-RS. UE100 may also select a trained model corresponding to its own communication environment from among the trained models managed for each communication environment, and use the selected trained model to perform CSI inference.

[0069] In step S110, UE100 sends (feeds back) the inferred CSI to gNB200.

[0070] In step S111, if UE100 determines that model training is necessary, it may send a notification to gNB200 as control data indicating that model training is necessary. For example, UE100 may send such a notification to gNB200 if it determines that the accuracy of the inference results can no longer be guaranteed when it moves, when its movement speed changes, when the reception quality at its location changes, when the cell it is located in changes, or when the bandwidth portion (BWP) it uses for communication changes.

[0071] Next, a second example of operation related to the first operation scenario will be described. This second example of operation may be used in conjunction with the above example of operation. In this second example of operation, gNB200 sends a completion condition notification, indicating the completion conditions for model learning, to UE100 as control data. UE100 receives the completion condition notification and determines the completion of model learning based on the completion condition notification. This allows UE100 to appropriately determine the completion of model learning. The completion condition notification may also be configuration information that sets the completion conditions for model learning in UE100. The completion condition notification may also be included in a switching notification that notifies (instructs) the switching to learning mode.

[0072] Figure 12 is an operation flow diagram showing a second operation example related to the first operation scenario according to the embodiment.

[0073] In step S201, the gNB200 sends a completion condition notification, indicating the completion conditions for model training, to the UE100 as control data. The completion condition notification may include at least one of the following completion condition information.

[0074] • Tolerance for error relative to the correct data: For example, this refers to the acceptable range of error between the CSI generated using a standard CSI feedback calculation method and the CSI inferred by model inference. Once a certain level of training has been completed, UE100 can infer the CSI using the trained model at that point, compare it to the correct CSI, and determine that training is complete based on whether the error is within an acceptable range.

[0075] • Number of training data points: This refers to the number of data points used for training; for example, the number of CSI-RS signals received corresponds to the number of training data points. The UE100 can determine that training is complete when the number of CSI-RS signals received in training mode reaches the notified (configured) number of training data points.

[0076] • Number of training trials: This is the number of times the model has been trained using the training data. The UE100 can determine that training is complete when the number of training sessions in training mode reaches the notified (configured) number.

[0077] • Output score threshold: For example, consider a score in reinforcement learning. UE100 can determine that learning is complete based on whether the score reaches the notified (set) score.

[0078] UE100 continues learning based on full CSI-RS until it determines that learning is complete (steps S203, S204).

[0079] In step S205, when UE100 determines that model training is complete, it may send a completion notification to gNB200 indicating that model training is complete.

[0080] Next, a third operational example related to the first operational scenario will be described. This third operational example may be used in conjunction with the operational example described above. When it is desired to improve the accuracy of CSI feedback, other types of data, such as the reception characteristics of a physical downlink shared channel (PDSCH), can be used as training data and inference data, in addition to CSI-RS. In this third operational example, the gNB200 transmits data type information, which specifies at least the type of data to be used as training data, to the UE100 as control data. That is, the gNB200 specifies to the UE100 what the training data and inference data should be (type of input data). The UE100 receives the data type information and performs model training using the specified type of data. This enables the UE100 to perform appropriate model training.

[0081] Figure 13 is an operation flow diagram showing a third operation example related to the first operation scenario according to the embodiment.

[0082] In step S301, UE100 may send capability information to gNB200 as control data indicating what types of input data UE100 can handle using machine learning. Here, UE100 may also provide additional information, such as the accuracy of the input data.

[0083] In step S302, gNB200 transmits data type information to UE100. The data type information may be setting information that sets the type of input data to UE100. Here, the input data type may be the reception quality and / or UE moving speed for CSI feedback. The reception quality may be the reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-interference noise ratio (SINR), bit error rate (BER), block error rate (BLER), analog / digital converter output waveform, etc.

[0084] Furthermore, assuming the UE positioning described later, the input data may include GNSS (Global Navigation Satellite System) location information (latitude, longitude, altitude), RF fingerprint (cell ID and its reception quality, etc.), angle of arrival (AoA) of the received signal, reception level, reception phase, and reception time difference (OTDOA) for each antenna, round-trip time, and reception information for short-range wireless networks such as Wi-Fi (Local Area Network).

[0085] Furthermore, the gNB200 may specify the input data type independently for training data and inference data. The gNB200 may also specify the input data type independently for CSI feedback and UE positioning.

[0086] (Second action scenario) Next, we will explain the second operation scenario, focusing primarily on the differences from the first operation scenario. In the first operation scenario, we mainly explained the downlink reference signal (i.e., downlink CSI estimation). In the second operation scenario, we will explain the uplink reference signal (i.e., uplink CSI estimation). In the explanation of the second operation scenario, we will assume that the uplink reference signal is the sounding reference signal (SRS), but it may also be the uplink DMRS, etc.

[0087] Figure 14 shows a second operation scenario according to the embodiment. In the second operation scenario, the data acquisition unit A1, model learning unit A2, model inference unit A3, and data processing unit A4 are arranged in the gNB200 (for example, the control unit 230). That is, model learning and model inference are performed on the gNB200 side.

[0088] In the second operating scenario, machine learning techniques are introduced to the CSI estimation performed by the gNB200 based on the SRS from the UE100. Therefore, the gNB200 (e.g., the control unit 230) has a CSI generation unit 231 that generates CSI based on the SRS received by the receiver unit 220 from the UE100. This CSI is information indicating the channel state of the uplink between the UE100 and the gNB200. The gNB200 (e.g., the data processing unit A4) performs, for example, uplink scheduling based on the CSI generated from the SRS.

[0089] Firstly, during model training, the gNB200 (receiver 220) receives a first reference signal from the UE100 using a first resource. Then, the gNB200 (model training unit A2) uses training data, including the first reference signal, to derive a trained model for inferring the CSI from the reference signal (SRS). In the description of the second operating scenario, such a first reference signal may be referred to as the full SRS.

[0090] For example, the gNB200 (CSI generation unit 231) performs channel estimation using the received signal (SRS) received by the receiver unit 220 from the UE100 and generates a CSI. The model learning unit A2 uses multiple sets of received signals (SRS) and CSIs as training data to train the model and derives a trained model for inferring the CSI from the received signal (SRS).

[0091] Secondly, in model inference, the gNB200 (receiver 220) receives the second reference signal from the UE100 using a second resource that is less resource-intensive than the first resource. The UE100 (model inference unit A3) then uses a trained model to infer the CSI from the inference data, including the second reference signal, as inference result data. In the description of the second operating scenario, such a second reference signal may be referred to as a partial SRS or a punctured SRS. The same puncture patterns as in the first operating scenario can be used for the SRS (see Figures 9 and 10).

[0092] For example, the gNB200 (model inference unit A3) uses the received signal (SRS) received by the receiver unit 220 from the UE100 as inference data, and uses a trained model to infer the CSI from the received signal (SRS).

[0093] This allows the gNB200 to generate an accurate (complete) CSI from the small amount of SRS (partial SRS) received from the UE100. For example, the UE100 can intentionally reduce (puncture) the SRS to reduce overhead. It also allows the gNB200 to handle situations where wireless conditions deteriorate and some SRS cannot be received properly.

[0094] In this type of operation scenario, it is possible to substitute "CSI-RS" with "SRS", "gNB200" with "UE100", and "UE100" with "gNB200" in the operation of the first operation scenario described above.

[0095] In the second operating scenario, the gNB200 transmits reference signal type information as control data to the UE100, specifying which type of reference signal (either a first reference signal (full SRS) or a second reference signal (partial SRS)) to transmit to the UE100. The UE100 receives the reference signal type information and transmits the specified SRS to the gNB200. This ensures that the appropriate SRS is transmitted to the UE100.

[0096] Figure 15 is an operation flowchart showing an example of operation related to the second operation scenario according to the embodiment.

[0097] In step S501, gNB200 configures UE100 for SRS transmission.

[0098] In step S502, the gNB200 starts learning mode.

[0099] In step S503, UE100 sends the full SRS to gNB200 according to the settings in step S501. gNB200 receives the full SRS and performs model training for channel estimation.

[0100] In step S504, the gNB200 identifies the SRS transmission pattern (puncture pattern) to be input as inference data to the trained model, and sets the identified SRS transmission pattern in the UE100.

[0101] In step S505, the gNB200 transitions to inference mode and starts model inference using the trained model.

[0102] In step S506, UE100 transmits a partial SRS according to the SRS transmission settings in step S504. gNB200 inputs this SRS as inference data into the trained model to obtain channel estimation results, and then uses these channel estimation results to perform uplink scheduling for UE100 (for example, controlling uplink transmission weights). Note that gNB200 may reconfigure UE100 to transmit a full SRS if the inference accuracy of the trained model deteriorates.

[0103] (Third action scenario) Next, the third operation scenario will be explained, primarily focusing on its differences from the first and second operation scenarios. The third operation scenario is an embodiment in which the position estimation of UE100 (so-called UE positioning) is performed using federated learning. Figure 16 shows the third operation scenario according to this embodiment. In this example of applying federated learning, the following procedure is performed.

[0104] Firstly, the location server 400 sends the model to the UE100.

[0105] Secondly, UE100 performs model learning on the UE100 (model learning unit A2) side using the data present in UE100. The data present in UE100 includes, for example, the positioning reference signal (PRS) received by UE100 from gNB200 and / or the output data of the GNSS receiver 140. The data present in UE100 may also include position information (including latitude and longitude) generated by the position information generation unit 132 based on the PRS reception result and / or the output data of the GNSS receiver 140.

[0106] Thirdly, UE100 applies the trained model, which is the learning result, to UE100 (model inference unit A3), and also sends the variable parameters included in the trained model (hereinafter also referred to as "trained parameters") to the location server 400. In the example above, the optimized a (slope) and b (intercept) correspond to the trained parameters.

[0107] Fourth, the location server 400 (federated learning unit A5) collects trained parameters from multiple UE100s and integrates them. The location server 400 may also send the trained model obtained through integration to the UE100s. Based on the trained model obtained through integration and the measurement reports from the UE100s, the location server 400 can estimate the position of the UE100s.

[0108] In the third operation scenario, gNB200 sends trigger setting information as control data to UE100, which sets the transmission trigger conditions for UE100 to send the learned parameters. UE100 receives the trigger setting information and sends the learned parameters to gNB200 (location server 400) when the set transmission trigger conditions are met. This allows UE100 to send the learned parameters at the appropriate time.

[0109] Figure 17 is an operation flowchart showing an example of operation related to the third operation scenario according to the embodiment.

[0110] In step S601, gNB200 may notify UE100 of the base model to be trained. Here, the base model may be a model that has been trained in the past. As described above, gNB200 may also send data type information to UE100 indicating what the input data should be.

[0111] In step S602, gNB200 instructs UE100 to train the model and sets the timing (trigger condition) for reporting trained parameters. The set reporting timing may be periodic. Alternatively, the reporting timing may be triggered (i.e., event triggered) when the training proficiency meets a condition.

[0112] In the case of periodic timing, gNB200 sets a timer value to UE100, for example. UE100 starts the timer when learning begins (step S603), and reports the learned parameters to gNB200 (location server 400) when it expires (step S604). Alternatively, gNB200 may specify to UE100 the radio frame or time to be reported. The radio frame may be specified as an absolute value, for example, SFN=512. The radio frame may be calculated by modulo operation. For example, gNB200 sets N as the set value and reports the learned parameters to UE100 in an SFN such that "SFN mod N=0" (step S604).

[0113] In the event trigger, gNB200 sets the completion conditions described above in UE100. When these completion conditions are met, UE100 reports the trained parameters to gNB200 (location server 400) (step S604). UE100 may also trigger the reporting of trained parameters, for example, when the accuracy of the model inference is better than the previously sent model. Here, UE100 may introduce an offset and trigger when "current accuracy > previous accuracy + offset". UE100 may also trigger the reporting of trained parameters, for example, when training data has been input (trained) N or more times. Such an offset and / or value of N may be set by gNB200 to UE100.

[0114] In step S604, when the reporting timing conditions are met, UE100 reports the learned parameters at that point to the network (gNB200).

[0115] In step S605, the network (location server 400) integrates the learned parameters reported from multiple UE100s.

[0116] (Other operation scenarios) Although the above operation scenarios primarily describe communication between UE100 and gNB200, the above operation scenarios may also be applied to communication between gNB200 and AMF300A (i.e., communication between base stations and core networks). The above control data may be transmitted from gNB200 to AMF300A via the NG interface. Alternatively, the above control data may be transmitted from AMF300A to gNB200 via the NG interface. Federated learning execution requests and / or federated learning results may be exchanged between AMF300A and gNB200. The above operation scenarios may also be applied to communication between gNB200 and another gNB200 (i.e., communication between base stations). The above control data may be transmitted from gNB200 to another gNB200 via the Xn interface. Federated learning execution requests and / or federated learning results may be exchanged between gNB200 and another gNB200. Each of the above-described operation scenarios may be applied to communication between UE100 and another UE100 (i.e., communication between user devices). The above-described control data may be transmitted from UE100 to another UE100 over the sidelink. Requests for federated learning and / or learning results of federated learning may be exchanged between UE100 and another UE100. The same applies to the following embodiments.

[0117] (Overview of model transfer operation) Next, the operation of model transfer according to the embodiment will be described. In the following description of the embodiment, it is assumed that model transfer (model setting) is performed from one communication device to another communication device.

[0118] (1) Notification of capacity information or load status information Figure 18 is a diagram illustrating the notification of capacity information or load status information according to the embodiment.

[0119] (1.1) In a mobile communication system 1 using machine learning technology, the communication device 501 that communicates with the communication device 502 includes a control unit 530 that performs at least one of the following machine learning processes (also referred to as "AI / ML processing"): a learning process that derives a trained model using training data (i.e., model learning), and an inference process that infers inference result data from inference data using the trained model (i.e., model inference); and a transmission unit 520 that sends a message to the communication device 502 that includes information elements regarding the processing capacity and / or storage capacity (memory capacity) available to the communication device 501 for machine learning processing.

[0120] As a result, the communication device 502 can appropriately configure and / or change the settings of the model for the communication device 501 based on a message containing informational elements regarding the processing capacity and / or storage capacity available to the communication device 501 for machine learning processing.

[0121] (1.2) In (1.1) above, the information element may be an information element indicating the execution capability of the communication device 501 for machine learning processing.

[0122] (1.3) In (1.2) above, the communication device 501 may further include a receiving unit 510 that receives a transmission request from the communication device 502 requesting the transmission of a message containing the above-mentioned information elements. The transmitting unit 520 may, upon receiving the transmission request, transmit a message containing the above-mentioned information elements to the communication device 502.

[0123] (1.4) In (1.2) or (1.3) above, the control unit 530 includes a processor 531 and / or memory 532 for performing machine learning processing, and the information elements may include information indicating the capabilities of the processor 531 and / or memory 532.

[0124] (1.5) In any of (1.2) to (1.4) above, the information element may include information indicating the ability to perform inference processing.

[0125] (1.6) In any of (1.2) to (1.5) above, the information element may include information indicating the ability to perform the learning process.

[0126] (1.7) In (1.1) above, the information element may be an information element indicating the load status related to machine learning processing in the communication device 501.

[0127] (1.8) In (1.7) above, the communication device 501 may further include a receiving unit 510 that receives information from the communication device 502 requesting or setting the transmission of a message containing the above information elements. The transmitting unit 520 may transmit a message containing the above information elements to the communication device 502 in response to the receiving unit 510 receiving the information.

[0128] (1.9) In (1.7) or (1.8) above, the transmitting unit 520 may transmit a message containing the above information elements to the communication device 502 in response to the value indicating the load status meeting the threshold condition, or periodically.

[0129] (1.10) In any of (1.7) to (1.9) above, the control unit 530 includes a processor 531 and / or memory 532 for executing machine learning processing, and the information element may include information indicating the load status of the processor 531 and / or the load status of the memory 532.

[0130] (1.11) In any of (1.1) to (1.10) above, the transmitting unit 520 transmits a message to the communication device 502 that includes the information element and a model identifier associated with the information element, and the model identifier may be an identifier that identifies a model in machine learning.

[0131] (1.12) In any of the above (1.1) to (1.11), the communication device 501 may further include a receiving unit 510 that receives a model to be used for machine learning processing from another communication device 502 after the transmission of a message.

[0132] (1.13) In any of the above (1.1) to (1.12), the communication device 502 may be a base station (gNB200) or a core network device (e.g., AMF300A), and the communication device 501 may be a user device (UE100).

[0133] (1.14) In (1.13) above, the communication device 502 may be a base station and the message may be an RRC message.

[0134] (1.15) In (1.13) above, the communication device 502 may be a core network device and the message may be a NAS message.

[0135] (1.16) In any of the above (1.1) to (1.12), the communication device 502 may be a core network device and the communication device 501 may be a base station.

[0136] (1.17) In any of the above (1.1) to (1.12), the communication device 502 may be the first base station and the communication device 501 may be the second base station.

[0137] (1.18) In a mobile communication system 1 using machine learning technology, a communication method performed by a communication device 501 that communicates with a communication device 502 includes the steps of: performing at least one of the following machine learning processes: a learning process that derives a trained model using training data, and an inference process that infers inference result data from inference data using the trained model; and sending a message to the communication device 502 that includes information elements regarding the processing capacity and / or memory capacity available for machine learning processing by the communication device 501.

[0138] (2) Model settings Figure 19 is a diagram illustrating the settings of the model according to the embodiment.

[0139] (2.1) In a mobile communication system 1 using machine learning technology, the communication device 501 that communicates with the communication device 502 includes a receiving unit 510 that receives a setting message from the communication device 502 that includes a model used in at least one of the machine learning processes of learning and inference, and additional information about the model, and a control unit 530 that executes a machine learning process using the model based on the additional information.

[0140] This makes it possible to appropriately set the model from communication device 502 to communication device 501.

[0141] (2.2) In (2.1) above, the model may be a pre-trained model used in the inference process.

[0142] (2.3) In (2.1) above, the model may be an untrained model used in the training process.

[0143] (2.4) In any of the above paragraphs (2.1) to (2.3), the message may include a plurality of models, including the above model, and additional information that is individually or commonly associated with each of the plurality of models.

[0144] (2.5) In any of the above (2.1) to (2.4), the additional information may include the index of the above model.

[0145] (2.6) In any of the above (2.1) to (2.5), the additional information may include at least one of the following: information indicating the use of the model, and information indicating the type of input data to the model.

[0146] (2.7) In any of the above (2.1) to (2.6), the additional information may include information indicating the performance required to apply the above model.

[0147] (2.8) In any of the above paragraphs (2.1) through (2.7), the additional information may include information indicating the criteria for which the above model is applied.

[0148] (2.9) In any of the above (2.1) to (2.8), the additional information may include at least one of the following: information indicating whether the model needs to be trained or retrained, and information indicating whether the model can be trained or retrained.

[0149] (2.10) In any of the above (2.1) to (2.9), the control unit 530 deploys the model in response to the receipt of a message, and the communication device 501 may further include a transmitting unit 520 that transmits a response message to the communication device 502 indicating that the deployment of the model has been completed.

[0150] (2.11) If the deployment of the above model fails in (2.10) above, the transmitting unit 520 may send an error message to the communication device 502.

[0151] (2.12) In any of (2.1) to (2.11) above, the message is a message that sets the model on the user device, the receiving unit 510 may further receive an activation command from the communication device 502 to apply the set model, and the control unit 530 may deploy the model in response to the receipt of the message and activate the deployed model in response to the receipt of the activation command.

[0152] (2.13) In (2.12) above, the activation command may include an index indicating the model to which it applies.

[0153] (2.14) In any of the above (2.1) to (2.13), the receiving unit 510 may further receive a delete message instructing the deletion of the model set by the setting message, and the control unit 530 may delete the model set by the setting message in response to the receipt of the delete message.

[0154] (2.15) In any of the above (2.1) to (2.14), if a set message is divided and multiple divided messages are transmitted from the communication device 502, the receiving unit 510 may receive information from the communication device 502 indicating how to transmit the multiple divided messages.

[0155] (2.16) In any of the above (2.1) to (2.15), the communication device 502 may be a base station or core network device, and the communication device 501 may be a user device.

[0156] (2.17) In (2.16) above, the communication device 502 may be a base station and the message may be an RRC message.

[0157] (2.18) In (2.16) above, the communication device 502 may be a core network device and the message may be a NAS message.

[0158] (2.19) In any of the above (2.1) to (2.15), the communication device 502 may be a core network device and the communication device 501 may be a base station, or the communication device 502 may be a first base station and the communication device 501 may be a second base station.

[0159] (2.20) In a mobile communication system 1 using machine learning technology, a communication method performed by a communication device 501 that communicates with a communication device 502 includes the steps of receiving a configuration message from the communication device 502 that includes a model to be used in at least one of the machine learning processes of learning and inference, and additional information relating to the model, and performing a machine learning process using the model based on the additional information.

[0160] (First example of model transfer operation) Figure 20 is a diagram showing a first example of model transfer according to the embodiment. In the diagrams referenced in the following first to third example of operation, non-essential processes are shown with dashed lines. In the following first to third example of operation, the communication device 501 is assumed to be UE100, but the communication device 501 may be gNB200 or AMF300A. In the following first to third example of operation, the communication device 502 is assumed to be gNB200, but the communication device 502 may be UE100 or AMF300A.

[0161] As shown in Figure 20, in step S701, gNB200 sends a capability query message to UE100 requesting the transmission of a message containing information elements indicating the ability to perform machine learning processing. The capability query message is an example of a transmission request that requests the transmission of a message containing information elements indicating the ability to perform machine learning processing. UE100 receives the capability query message. However, gNB200 may also send the capability query message when it decides to perform machine learning processing (i.e., when it decides to perform it).

[0162] In step S702, UE100 sends a message to gNB200 containing informational elements indicating the execution capability for machine learning processing (or, from another perspective, the execution environment for machine learning processing). gNB200 receives the message. The message may be an RRC message, for example, a "UE Capability" message as defined in the RRC technical specifications, or a newly defined message (for example, a "UE AI Capability" message). Alternatively, if the communication device 502 is an AMF300A, the message may be a NAS message. Alternatively, if a new layer for executing or controlling machine learning processing (AI / ML processing) is defined, the message may be a message for that new layer. The new layer will be appropriately referred to as the "AI / ML layer".

[0163] An information element indicating the ability to perform machine learning processing is at least one of the following information elements (A1) to (A3).

[0164] • Information element (A1) Information element (A1) is an information element that indicates the processor's capacity for performing machine learning processing and / or the memory's capacity for performing machine learning processing.

[0165] The information element indicating the processor's capabilities for executing machine learning processing may also indicate whether or not UE100 has an AI processor. If UE100 has such a processor, the information element may include the AI ​​processor part number (model number). The information element may also indicate whether or not UE100 can utilize a GPU (Graphics Processing Unit). Alternatively, the information element may indicate whether or not machine learning processing must be performed on a CPU. By transmitting the information element indicating the processor's capabilities for executing machine learning processing from UE100 to gNB200, the network can determine, for example, whether or not UE100 can utilize a neural network model as a model. The information element indicating the processor's capabilities for executing machine learning processing may also indicate the processor's clock frequency and / or the number of parallel executions possible.

[0166] The information element indicating the memory capacity for executing machine learning processing may be an information element indicating the memory capacity of volatile memory (e.g., RAM: Random Access Memory) within the UE100's memory. Alternatively, the information element may be an information element indicating the memory capacity of non-volatile memory (e.g., ROM: Read Only Memory) within the UE100's memory. The information element may also be both. The information element indicating the memory capacity for executing machine learning processing may be defined for each type, such as model storage memory, AI processor memory, and GPU memory.

[0167] Information element (A1) may be defined as an information element for inference processing (model inference). Alternatively, information element (A1) may be defined as an information element for learning processing (model learning). Alternatively, information element (A1) may be defined as both an information element for inference processing and an information element for learning processing.

[0168] ·Information element (A2) Information element (A2) is an information element that indicates the ability to perform inference processing. Information element (A2) may also be an information element that indicates the models supported by the inference processing. This information element may also be an information element that indicates whether or not a deep neural network model is supported. In that case, this information element may include at least one of the following: information indicating the number of layers (stages) of the neural network that can be supported, information indicating the number of neurons that can be supported (which may be the number of neurons per layer), and information indicating the number of synapses that can be supported (which may be the number of input or output synapses per layer or per neuron).

[0169] Information element (A2) may also be an information element indicating the execution time (response time) required to execute the inference process. Alternatively, information element (A2) may be an information element indicating the number of concurrent inference processes (for example, how many inference processes can be executed in parallel). Alternatively, information element (A2) may be an information element indicating the processing capacity of the inference process. For example, if the processing load of a certain standard model (standard task) is fixed at 1 point, the information element indicating the processing capacity of the inference process may be information indicating how many points its own processing capacity is.

[0170] • Information element (A3) Information element (A3) is an information element that indicates the ability to perform the learning process. Information element (A3) may also be an information element that indicates the learning algorithm supported by the learning process. The learning algorithms indicated by this information element include supervised learning (e.g., linear regression, decision trees, logistic regression, k-nearest neighbors, support vector machines, etc.), unsupervised learning (e.g., clustering, k-means algorithm, principal component analysis, etc.), reinforcement learning, and deep learning. If UE100 supports deep learning, this information element may include at least one of the following: information indicating the number of layers (stages) of the neural network that can be supported, information indicating the number of neurons that can be supported (which may be the number of neurons per layer), and information indicating the number of synapses that can be supported (which may be the number of input or output synapses per layer or per neuron).

[0171] Information element (A3) may also be an information element indicating the execution time (response time) required to execute the learning process. Alternatively, information element (A3) may be an information element indicating the number of simultaneous executions of the learning process (for example, how many learning processes can be executed in parallel). Alternatively, information element (A3) may be an information element indicating the processing capacity of the learning process. For example, if the processing load of a certain standard model (standard task) is fixed at 1 point, the information element indicating the processing capacity of the learning process may be information indicating how many points its own processing capacity is. Regarding the number of simultaneous executions, since the processing load of the learning process is generally higher than that of the inference process, the information may also be the number of simultaneous executions of the inference process and the learning process (for example, two inference processes and one learning process).

[0172] In step S703, gNB200 determines the model to set (deploy) on UE100 based on the information elements contained in the message received in step S702. This model may be a trained model used by UE100 in inference processing, or it may be an untrained model used by UE100 in training processing.

[0173] In step S704, gNB200 sends a message to UE100 containing the model determined in step S703. UE100 receives the message and uses the model contained in the message to perform machine learning processing (training and / or inference). A specific example of step S704 will be explained in the following second example of operation.

[0174] (Second example of model transfer operation) Figure 21 shows an example of a configuration message including a model and additional information according to the embodiment. The configuration message may be an RRC message sent from gNB200 to UE100, for example, an "RRC Reconfiguration" message as defined in the RRC technical specifications, or a newly defined message (for example, an "AI Deployment" message or an "AI Reconfiguration" message). Alternatively, the configuration message may be a NAS message sent from AMF300A to UE100. Or, if a new layer for executing or controlling machine learning processing (AI / ML processing) is defined, the message may be a message for that new layer.

[0175] In the example in Figure 21, the configuration message includes three models (Model #1 to #3). Each model is included as a container for the configuration message. However, the configuration message may contain only one model. The configuration message further includes, as additional information, three individual additional pieces of information (Info #1 to #3) corresponding to each of the three models (Model #1 to #3), and common additional pieces of information (Meta-Info) that are associated with all three models (Model #1 to #3). Each of the individual additional pieces of information (Info #1 to #3) contains information specific to the corresponding model. The common additional pieces of information (Meta-Info) contain information common to all models within the configuration message.

[0176] Figure 22 shows a second example of model transfer according to the embodiment.

[0177] In step S711, gNB200 sends a configuration message to UE100 that includes the model and additional information. UE100 receives the configuration message. The configuration message includes at least one of the following information elements (B1) to (B6):

[0178] (B1 model) The "model" may be a pre-trained model used by UE100 in inference processing. Alternatively, the "model" may be an untrained model used by UE100 in training processing. In the configuration message, the "model" may be encapsulated (contained). If the "model" is a neural network model, the "model" may be represented by the number of layers (stages), the number of neurons in each layer, and the synapses (weights) between each neuron. For example, a pre-trained (or untrained) neural network model may be represented by a combination of matrices.

[0179] A single configuration message may contain multiple "models." In this case, the multiple "models" may be included in the configuration message in list format. Multiple "models" may be configured for the same purpose, or they may be configured for different purposes. Details on the uses of models will be described later.

[0180] (B2) Model Index The "model index" is an example of additional information (e.g., individual additional information). The "model index" is the index (index number) assigned to a model. In the activation command and deletion message described later, you can specify the model using the "model index". You can also specify the model using the "model index" when changing the model's settings.

[0181] (B3 model application) "Model Usage" is an example of additional information (individual additional information or common additional information). "Model Usage" specifies the function to which the model applies. For example, the function to which the model applies includes 、CThese include SI feedback, beam management (beam estimation, overhead / latency reduction, beam selection accuracy improvement), positioning, modulation / demodulation, coding / decoding (CODEC), and packet compression. The content of the model application and its index (identifier) ​​are predefined in the 3GPP technical specification, and the "model application" may also be specified by an index. For example, CSI feedback is application index #A, beam management is application index #B, and so on, with the model application and its index (identifier) ​​being defined. The UE100 deploys the model with the specified "model application" to the functional block corresponding to the specified application. Note that the "model application" may also be an information element that specifies the input and output data of the model.

[0182] (B4) Model execution requirements "Model execution requirements" is an example of additional information (e.g., individual additional information). "Model execution requirements" are information elements that indicate the performance (required performance) necessary to apply (execute) the model, such as processing delay (required latency).

[0183] (B5) Model Selection Criteria The "model selection criteria" is an example of additional information (individual additional information or common additional information). The UE100 applies (executes) the corresponding model depending on whether the criteria specified in the "model selection criteria" are met. The "model selection criteria" may be the UE100's movement speed. In that case, the "model selection criteria" may be specified as a speed range such as "slow movement" or "fast movement". Alternatively, the "model selection criteria" may be specified as a threshold for movement speed. The "model selection criteria" may be the radio quality measured by the UE100 (e.g., RSRP / RSRQ / SINR). In that case, the "model selection criteria" may be specified as a range for radio quality. Alternatively, the "model selection criteria" may be specified as a threshold for radio quality. The "model selection criteria" may also be the UE100's location (latitude / longitude / altitude). The "model selection criteria" may be set to follow sequential notifications from the network (activation commands described later), or it may be set to specify autonomous selection by the UE100.

[0184] (B6) Whether or not learning processing is necessary The "Necessity of Learning Process" is an information element indicating whether or not learning (or retraining) is necessary for the corresponding model. If learning is required, the type of parameters to be used for learning may be further set. For example, in the case of CSI feedback, CSI-RS and UE movement speed are set to be used as parameters. If learning is required, the method of learning, such as supervised learning, unsupervised learning, reinforcement learning, or deep learning, may be further set. Whether or not to execute the learning process immediately after the model is set may also be further set. If not to execute immediately, the execution of learning may be controlled by the activation command described later. For example, in the case of Federated learning, whether or not to notify gNB200 of the results of the learning process of UE100 may be further set. If it is necessary to notify gNB200 of the results of the learning process of UE100, UE100 may encapsulate the trained model or trained parameters after the learning process is executed and send them to gNB200 via an RRC message or the like. The information element indicating "whether or not a learning process is necessary" may also include an information element indicating whether or not the corresponding model is used only for model inference, in addition to whether or not a learning process is necessary.

[0185] In step S712, UE100 determines whether the model configured in step S711 is deployable (executable). UE100 may perform this determination when activating the model, as described later, and step S713, described later, may be a message notifying of an error at the time of activation. Furthermore, UE100 may perform this determination while the model is in use (while machine learning processing is being executed), rather than at deployment or activation. If the model is determined to be undeployable (step S712: NO), i.e., an error occurs, in step S713, UE100 sends an error message to gNB200. The error message may be an RRC message sent from UE100 to gNB200, for example, a "Failure Information" message defined in the RRC technical specifications, or a newly defined message (for example, an "AI Deployment Failure Information" message). The error message may also be a UCI (Uplink Control Information) defined in the physical layer or a MAC CE (Control Element) defined in the MAC layer. Alternatively, the error message may be a NAS message sent from UE100 to AMF300A. Or, if a new layer (AI / ML layer) for performing machine learning processing (AI / ML processing) is defined, the message may be a message for that new layer.

[0186] An error message includes at least one of the following information elements (C1) through (C3):

[0187] (C1) Model Index This is the model index for models that were determined to be undeployable.

[0188] • (C2) Usage Index This is an index of the uses of models that were determined to be undeployable.

[0189] (C3) Error Cause This is an information element related to the cause of the error. The "cause of the error" may be, for example, "unsupported model," "processing capacity exceeded," "phase in which the error occurred," or "other error." "Unsupported model" may be, for example, that the UE100 cannot support a neural network model, or that it cannot support machine learning processing (AI / ML processing) of a specified function. "Processing capacity exceeded" may be, for example, overload (processing load or memory load exceeding capacity), inability to satisfy the requested processing time, or interrupt processing or priority processing by the application (higher layer). "Phase in which the error occurred" is information indicating when the error occurred. "Phase in which the error occurred" may be divided into categories such as deployment (configuration), activation, and operation. Alternatively, "Phase in which the error occurred" may be divided into categories such as inference processing and training processing. "Other errors" are other causes.

[0190] UE100 may automatically delete the corresponding model if an error occurs. UE100 may also delete the model when it confirms that an error message has been received by gNB200, for example, when an ACK is received at a lower layer. gNB200 may recognize that the model has been deleted when it receives an error message from UE100.

[0191] On the other hand, if it is determined that the model configured in step S711 is deployable (step S712: YES), that is, if no error occurs, in step S714, UE100 deploys the model according to the configuration. "Deployment" may mean making the model applicable. Alternatively, "Deployment" may mean actually applying the model. In the former case, the model is not applied simply by deploying it; it is applied when the model is activated by the activation command described later. In the latter case, once the model is deployed, it enters a state of being in use.

[0192] In step S715, UE100 sends a response message to gNB200 in response to the completion of model deployment. gNB200 receives the response message. UE100 may also send a response message when model activation is completed by the activation command described later. The response message may be an RRC message sent from UE100 to gNB200, for example, the "RRC Reconfiguration Complete" message specified in the RRC technical specification, or a newly defined message (for example, the "AI Deployment Complete" message). The response message may also be a MAC CE specified in the MAC layer. Alternatively, the response message may be a NAS message sent from UE100 to AMF300A. Alternatively, if a new layer for performing machine learning processing (AI / ML processing) is defined, the message may be a message for that new layer.

[0193] In step S716, UE100 may send a measurement report message, which is an RRC message containing the measurement results of the wireless environment, to gNB200. gNB200 receives the measurement report message.

[0194] In step S717, gNB200 selects a model to activate, for example based on a measurement report message, and sends an activation command (selection command) to UE100 to activate the selected model. UE100 receives the activation command. The activation command may be a DCI, MAC CE, RRC message, or an AI / ML layer message. The activation command may include a model index indicating the selected model. The activation command may also include information specifying whether UE100 will perform inference processing or training processing.

[0195] The gNB200 selects models to deactivate based on, for example, a measurement report message, and sends a deactivation command (selection command) to the UE100 to deactivate the selected models. The UE100 receives the deactivation command. The deactivation command may be a DCI, MAC CE, RRC message, or an AI / ML layer message. The deactivation command may include a model index indicating the selected models. Upon receiving the deactivation command, the UE100 may deactivate (cancel application) the specified models without deleting them.

[0196] In step S718, UE100 applies (activates) the specified model upon receiving the activation command. UE100 then performs inference and / or training using the activated model from among the deployed models.

[0197] Subsequently, in step S719, gNB200 sends a delete message to UE100 to delete the model. UE100 receives the delete message. The delete message may be a MAC CE, RRC message, NAS message, or AI / ML layer message. The delete message may include the model index of the model to be deleted. Upon receiving the delete message, UE100 deletes the specified model.

[0198] Furthermore, if the amount of model data sent (transferred) from gNB200 to UE100 is large and / or the number of models is large, it may be difficult to include the models in a single message. Therefore, gNB200 may divide the configuration message containing the models into multiple split messages and send the split messages sequentially. In this case, gNB200 will notify UE100 of the method for sending the split messages.

[0199] Figure 23 shows an example of the operation related to the split transmission of a configuration message according to the embodiment.

[0200] In step S731, gNB200 sends a message to UE100 containing information about the model transfer method. UE100 receives the message. The message includes at least one of the following information elements: "size of data to be sent," "time to complete delivery," "total data capacity," and "transmission method and conditions." The "transmission method and conditions" include at least one of the following information: "continuous setting," "periodic (periodic, aperiodic) setting," "transmission time and duration (e.g., 24:00 to 2 hours daily)," "conditional transmission (e.g., transmit only when there are no battery concerns (e.g., only when charging), or transmit only when resources are available)," and "designation of bearer, channel, and network slice."

[0201] In step S732, UE100 determines whether the data transmission method and transmission conditions notified by gNB200 in step S731 are desirable. If they are not desirable, UE100 sends a change request notification to gNB200. gNB200 may repeat step S731 in response to the change request notification.

[0202] In steps S733, S734, ..., gNB200 sends a split message to UE100. UE100 receives the split message. During such data transmission, gNB200 may send information to UE100 indicating the amount of data transmitted and / or remaining data, for example, information indicating "number transmitted and total number" or "percentage transmitted (%)". UE100 may, at its own discretion, send a request to stop or resume transmission of the split message to gNB200. gNB200 may, at its own discretion, send a notification to UE100 that the transmission of the split message has stopped or that transmission has resumed.

[0203] Furthermore, gNB200 may notify UE100 of the data size of the model (configuration message), and only begin sending the model after receiving approval from UE100. For example, UE100 may return OK if the model can be deployed compared to its remaining memory capacity, and NG if it cannot be deployed. Similarly, negotiation between the sender and receiver may take place regarding the other information mentioned above.

[0204] (Third example of model transfer operation) In this third operational example, UE100 notifies the network of the load status of the machine learning processing (AI / ML processing). This allows the network (e.g., gNB200) to determine how many more models can be deployed (or activated) on UE100 based on the notified load status. This third operational example does not necessarily presuppose the first operational example concerning model transfer described above. Alternatively, this third operational example may presuppose the first operational example.

[0205] Figure 24 shows a third example of model transfer according to the embodiment.

[0206] In step S751, gNB200 sends a message to UE100 that includes a request for information on the AI / ML processing load status or a setting for reporting the AI / ML processing load status. UE100 receives the message. The message may be a MAC CE, RRC message, NAS message, or an AI / ML layer message. The setting for reporting the AI / ML processing load status may include information that sets a report trigger (send trigger), for example, "Periodic" or "Event triggered". "Periodic" sets the reporting period, and UE100 reports at that period. "Event triggered" sets a threshold that is compared to a value indicating the AI / ML processing load status in UE100 (processing load value and / or memory load value), and UE100 reports when the value meets the condition of the threshold. Here, the threshold may be set for each model. For example, the message may associate a model index with a threshold.

[0207] In step S752, UE100 sends a message (report message) to gNB200 containing information indicating the AI / ML processing load status. This message may be an RRC message, for example, a "UE Assistance Information" message or a "Measurement Report" message. Alternatively, this message may be a newly defined message (for example, an "AI Assistance Information" message). This message may be a NAS message or an AI / ML layer message.

[0208] The message includes "processing load status" and / or "memory load status". "Processing load status" may indicate what percentage of processing power (processor capacity) is being used, or what percentage remains available. Alternatively, "processing load status" may express the load in points as described above, notifying how many points are being used and how many points remain available. UE100 may notify "processing load status" for each model. For example, UE100 may include at least one set of "model index" and "processing load status" in the message. "Memory load status" may include memory capacity, memory usage, or remaining memory. UE100 may notify "memory load status" by type, such as model storage memory, AI processor memory, GPU memory, etc.

[0209] In step S752, if UE100 wants to discontinue using a particular model for reasons such as high processing load or poor efficiency, it may include information (model index) indicating the model it wishes to delete or deactivate in the message. UE100 may also send alert information to gNB200 in the message when its own processing load becomes critical.

[0210] In step S753, gNB200 determines model configuration changes based on the message received from UE100 in step S752, and sends a message to UE100 for the model configuration change. This message may be a MAC CE, RRC message, NAS message, or AI / ML layer message. gNB200 may also send the activation or deactivation command described above to UE100.

[0211] (Other embodiments) As described above, in the diagrams referenced in the first to third operation examples concerning model transfer, non-essential processes are indicated by dashed lines. Furthermore, in the first to third operation examples, the communication device 501 is assumed to be a UE100, but the communication device 501 may be a gNB200 or an AMF300A. The communication device 501 may also be a gNB-DU or gNB-CU, which are functional division units of the gNB200. Alternatively, the communication device 501 may be one or more RUs (Radio Units) provided in the gNB-DU. In the first to third operation examples, the communication device 502 is assumed to be a gNB200, but the communication device 502 may also be a UE100 or an AMF300A. The communication device 502 may be a gNB-CU, gNB-DU, or an RU. Furthermore, assuming sidelink relay, communication device 501 may be a remote UE, and communication device 502 may be a relay UE.

[0212] Each of the above-described operation flows can be performed not only independently, but also in combination of two or more operation flows. For example, some steps of one operation flow may be added to another operation flow, or some steps of one operation flow may be replaced with some steps of another operation flow. It is not necessary to execute all steps in each flow; only some steps may be executed.

[0213] In the above embodiment, an example was described in which the base station is an NR base station (gNB), but the base station may also be an LTE base station (eNB). Furthermore, the base station may be a relay node such as an IAB (Integrated Access and Backhaul) node. The base station may also be a DU (Distributed Unit) of an IAB node. The user equipment (terminal equipment) may be a relay node such as an IAB node, or it may be an MT (Mobile Termination) of an IAB node.

[0214] A program may be provided that causes a computer to execute each process performed by the communication device (e.g., UE100 or gNB200). The program may be recorded on a computer-readable medium. Using a computer-readable medium, it is possible to install the program on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transient recording medium. The non-transient recording medium is not particularly limited, but may be a recording medium such as a CD-ROM or DVD-ROM. Furthermore, the circuits that execute each process performed by the communication device may be integrated, and at least a part of the communication device may be configured as a semiconductor integrated circuit (chipset, SoC: System on a chip).

[0215] The terms "based on" and "depending on" used in this disclosure do not mean "based solely on" or "depending solely on" unless otherwise specified. The term "based on" means both "based solely on" and "at least partially on." Similarly, the term "depending on" means both "at least partially on" and "at least partially on." Also, "obtain / acquire" may mean obtaining information from stored information, obtaining information from information received from other nodes, or obtaining information by generating it. The terms "include," "comprise," and their variations do not mean to include only the listed items, but may include only the listed items, or may include additional items in addition to the listed items. Also, the term "or" used in this disclosure is not intended to mean exclusive OR. Furthermore, any reference to elements using designations such as "first," "second," etc., used in this disclosure does not limit the quantity or order of those elements in general. These designations may be used herein as a convenient way to distinguish between two or more elements. Therefore, references to the first and second elements do not imply that only two elements may be employed therein, or that the first element must precede the second element in any way. In this disclosure, where articles are added by translation, such as a, an, and the in English, these articles shall be plural unless it is clearly indicated otherwise by the context.

[0216] Although the embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to those described above, and various design changes can be made without departing from the gist of the invention.

[0217] This application claims priority to Japanese Patent Application No. 2022-069111 (filed on April 19, 2022), and all of its contents are incorporated into the specification of this application.

[0218] (Note) The features of the above-described embodiment are noted below.

[0219] (1) A communication device that communicates with another communication device in a mobile communication system using machine learning technology, A control unit that performs at least one of the following machine learning processes: a learning process that derives a trained model using training data, and an inference process that infers inference result data from inference data using the trained model. The communication device includes a transmitting unit that transmits a message to another communication device containing information elements regarding the processing capacity and / or storage capacity available for the machine learning process. Communication device.

[0220] (2) The aforementioned information element is an information element that indicates the execution capability of the communication device regarding the machine learning processing. The communication device described in (1) above.

[0221] (3) The system further includes a receiving unit that receives a transmission request from another communication device requesting the transmission of the message containing the aforementioned information elements. The transmitting unit, upon receiving the transmission request, transmits the message containing the information elements to the other communication device. The communication device described in (1) or (2) above.

[0222] (4) The control unit includes a processor and / or memory for executing the machine learning process, The aforementioned information element includes information indicating the capabilities of the processor and / or the capabilities of the memory. A communication device as described in any of (1) to (3) above.

[0223] (5) The aforementioned information element includes information indicating the ability to perform the inference process. A communication device as described in any of (1) to (4) above.

[0224] (6) The aforementioned information element includes information indicating the ability to perform the learning process. A communication device as described in any of (1) through (5) above.

[0225] (7) The aforementioned information element is an information element that indicates the load status related to the machine learning processing in the communication device. A communication device as described in any of (1) through (6) above.

[0226] (8) The system further includes a receiving unit that receives information from another communication device requesting or setting the transmission of the message containing the aforementioned information elements, The transmitting unit transmits the message containing the information elements to the other communication device in response to the receiving unit receiving the information. The communication device described in (7) above.

[0227] (9) The transmitting unit transmits the message containing the information elements to the other communication device in response to the value indicating the load status meeting a threshold condition, or periodically thereafter. The communication device described in (7) or (8) above.

[0228] (10) The control unit includes a processor and / or memory for executing the machine learning process, The information element includes information indicating the load status of the processor and / or the load status of the memory. A communication device as described in any of (7) to (9) above.

[0229] (11) The transmitting unit transmits the message, which includes the information element and the model identifier associated with the information element, to the other communication device. The aforementioned model identifier is an identifier that identifies a model in machine learning. A communication device as described in any of (1) through (10) above.

[0230] (12) The system further includes a receiving unit that, after the transmission of the aforementioned message, receives the model used for the machine learning process from the other communication device. A communication device as described in any of (1) through (11) above.

[0231] (13) The other communication device is a base station or core network device, and the communication device is a user device. A communication device as described in any of (1) through (12) above.

[0232] (14) The other communication device is the base station, and the message is an RRC message. The communication device described in (13) above.

[0233] (15) The other communication device is the core network device, and the message is a NAS message. The communication device described in (13) above.

[0234] (16) The other communication device is a core network device, and the communication device is a base station. A communication device as described in any of (1) through (12) above.

[0235] (17) The other communication device is the first base station, and the other communication device is the second base station. A communication device as described in any of (1) through (12) above.

[0236] (18) A communication method performed by a communication device that communicates with another communication device in a mobile communication system that uses machine learning technology, The process involves performing at least one of the following machine learning processes: a training process that derives a trained model using training data, and an inference process that infers inference result data from inference data using the trained model. The communication device transmits a message to another communication device that includes informational elements regarding the processing capacity and / or storage capacity available for the machine learning process. Communication method. [Explanation of Symbols]

[0237] 1: Mobile communication systems 100 :UE 110: Receiving unit 120: Transmitter 130: Control Unit 131:CSI generation unit 132: Location information generation unit 140: GNSS receiver 200 :gNB 210: Transmitter 220: Receiving unit 230: Control Unit 231:CSI generation unit 240: Backhaul Communications Department 400: Location Server 501: Communication device 502: Communication equipment A1: Data Collection Department A2: Model Learning Department A3: Model inference section A4: Data Processing Section A5: Joint Learning Department

Claims

1. A user device that communicates with network nodes in a mobile communication system using machine learning technology, A receiving unit that receives configuration information regarding the AI / ML model from the network node, A control unit that determines whether the functions of the AI / ML model are applicable to the user device, It includes a transmission unit that sends a message to the network node containing information indicating whether or not the functions of the AI / ML model are applicable, The receiving unit receives information from the network node indicating the activation of the applicable AI / ML model. User device.

2. A communication method for a user device that communicates with a network node in a mobile communication system using machine learning technology, Receiving configuration information regarding the AI / ML model from the network node, To determine whether the functions of the AI / ML model can be applied to the user device, The system includes sending a message to the network node containing information indicating whether or not the AI / ML model's functions are applicable, The aforementioned receiving includes receiving from the network node information indicating the activation of the applicable AI / ML model. Communication method.

3. A mobile communication system using machine learning technology, Network nodes and It includes a user device that communicates with the aforementioned network node, The User device is The system receives configuration information regarding the AI / ML model from the network node. It is determined whether the functions of the AI / ML model can be applied to the user device. A message containing information indicating whether the functions of the AI / ML model are applicable is sent to the network node. The user device receives information from the network node indicating the activation of the applicable AI / ML model. Mobile communication system.

4. A chipset for a user device that communicates with a network node in a mobile communication system using machine learning technology, Receiving configuration information regarding the AI / ML model from the network node, To determine whether the functions of the AI / ML model can be applied to the user device, The system includes sending a message to the network node containing information indicating whether or not the AI / ML model's functions are applicable, The aforementioned receiving includes receiving from the network node information indicating the activation of the applicable AI / ML model. Chipset.

5. In a mobile communication system using machine learning technology, a computer in a user device that communicates with a network node, The process involves receiving configuration information regarding the AI / ML model from the network node, A process to determine whether the functions of the AI / ML model can be applied to the user device, The process involves sending a message to the network node containing information indicating whether or not the AI / ML model's functions are applicable, The receiving process includes receiving information from the network node indicating the activation of the applicable AI / ML model. program.

Images