Measurement data collection for model training

Abstract

Exemplary embodiments of this disclosure relate to RAN nodes, entities, methods, apparatus, and computer-readable media for collecting measurements for model training. In this solution, the RAN node may report physical layer measurements to a data acquisition entity, thus enabling further applications (such as model training in a training entity). In some examples, physical layer measurements may be reported to multiple data acquisition entities, thus eliminating the need for additional requests for physical layer measurements and thus reducing overhead.

Description

Technical Field

[0001] The present disclosure relates to wireless communications, and more particularly, to radio access network (RAN) nodes, entities, methods, apparatuses, and computer-readable media for measurement collection for model training.

Background Art

[0002] A wireless communication system may include one or more network communication devices, such as base stations, which may also be known as eNodeB (eNB), next generation NodeB (gNB), or other appropriate terminology. Each network communication device, such as a base station, may support wireless communication for one or more user communication devices, which may also be known as user equipment (UE) or other appropriate terminology. The wireless communication system may support wireless communication with one or more user communication devices by using resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, etc.) or frequency resources (e.g., subcarriers, carriers)). Further, the wireless communication system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, 5G radio access technology, among other suitable radio access technologies beyond fifth generation (5G) (e.g., sixth generation (6G)).

Summary of the Invention

Problems to be Solved by the Invention

[0003] An artificial intelligence (AI) model may be obtained by machine learning (ML) or deep learning (DL), which may be referred to as an AI / ML model, and is widely used in various application fields.

[0004] AI / ML models may be deployed in user equipment (UE), base stations (such as gNB), or core network functions (such as location management functions (LMF)), and the models are trained by training entities. Training entities may acquire collected data for training, and therefore, training entities may be referred to as data acquisition entities in this disclosure. However, how data acquisition entities may acquire data for training needs further consideration. [Means for solving the problem]

[0005] This disclosure relates to RAN nodes, entities, methods, apparatus, and computer-readable media for acquiring measurement values ​​for model training. According to the proposed solution, a data acquisition entity may receive physical layer measurement values ​​from a RAN node.

[0006] In several implementations, a RAN node is provided. The RAN node comprises at least one memory and at least one processor coupled to at least one memory, the at least one processor configured to cause the RAN node to receive a first message from a first entity instructing the RAN node to collect physical layer measurements and report them to at least one data acquisition entity, collect physical layer measurements based on the first message, and send a second message to at least one data acquisition entity containing some or all of the physical layer measurements, the some or all of which are used for model training.

[0007] In several implementations, a first entity is provided. The first entity comprises at least one memory and at least one processor coupled to the at least one memory, the at least one processor configured to cause the first entity to acquire information associated with physical layer measurements for model training and to send a first message to a RAN node instructing the RAN node to collect physical layer measurements and report them to at least one data acquisition entity.

[0008] In several implementations, a data acquisition entity is provided. The data acquisition entity comprises at least one memory and at least one processor coupled to at least one memory, the at least one processor configured to cause the data acquisition entity to receive a second message from a RAN node containing some or all of the physical layer measurements, and to use some or all of the physical layer measurements or provide them to a model training entity.

[0009] In several implementations, a method is provided that is performed by a RAN node. The method includes the steps of: receiving a first message from a first entity instructing the RAN node to collect physical layer measurements and report them to at least one data collection entity; collecting physical layer measurements based on the first message; and sending a second message to at least one data collection entity containing some or all of the physical layer measurements, wherein some or all of the physical layer measurements are used for model training.

[0010] In several implementations, a method is provided that is carried out by a first entity. The method includes the steps of acquiring information associated with physical layer measurements for model training, and sending a first message to a RAN node instructing the RAN node to collect physical layer measurements and report them to at least one data acquisition entity.

[0011] In several implementations, a method is provided that is performed by the data acquisition entity. The method includes the steps of receiving a second message from a RAN node containing some or all of the physical layer measurements, and using some or all of the physical layer measurements or providing them to the model training entity.

[0012] In several implementations, a processor for wireless communication is provided. The processor comprises at least one controller coupled with at least one memory, the at least one controller configured to cause the processor to: receive a first message from a first entity instructing a RAN node to collect physical layer measurements and report them to at least one data acquisition entity; collect physical layer measurements based on the first message; and transmit a second message to at least one data acquisition entity, which includes some or all of the physical layer measurements, the some or all of which are used for model training.

[0013] In several implementations, a processor for wireless communication is provided. The processor comprises at least one controller coupled with at least one memory, the at least one controller configured to cause the processor to acquire information associated with physical layer measurements for model training and to send a first message to the RAN node instructing the RAN node to collect physical layer measurements and report them to at least one data acquisition entity.

[0014] In several implementations, a processor for wireless communication is provided. The processor comprises at least one controller coupled with at least one memory, the at least one controller configured to cause the processor to receive a second message from a RAN node containing some or all of the physical layer measurements, and to use some or all of the physical layer measurements or provide them to a model training entity.

[0015] In the methods and some implementations of RAN nodes described herein, the first entity further includes a maintenance and operations management (OAM) system that transmits cell traffic trace messages to the AMF.

[0016] The methods and some implementations of the RAN node described herein further include collecting physical layer measurements from one or more specific UEs based on the determination that the first message indicates one or more specific UEs, or collecting physical layer measurements from at least one selected UE based on the determination that the first message does not indicate one or more specific UEs.

[0017] The methods and some implementations of RAN nodes described herein further include transmitting some or all of the information in the first message to a RAN distributed unit (DU), where the RAN node is a RAN central unit (CU).

[0018] The methods and some implementations of the RAN node described herein further include transmitting some or all of the information in the first message to the RAN CU user plane (UP), where the RAN node is the RAN CU control plane (CP).

[0019] The methods and some implementations of RAN nodes described herein further include transmitting some or all of the information in the first message to a target RAN node, where the RAN node is the source RAN node for a particular UE during the handover.

[0020] Some implementations of the methods and data acquisition entities described herein further include sending a first message to a RAN node instructing the RAN node to collect and report physical layer measurements, the first message including a data acquisition request message.

[0021] In the methods, RAN nodes, first entities, and several implementations of the data acquisition entities described herein, the first entity comprises an Access and Mobility Management Function (AMF), the first message includes a trace initiation message, and the trace initiation message includes an Information Element (IE) associated with the data acquisition configuration that instructs to collect and report physical layer measurements.

[0022] In some implementations of the methods, RAN nodes, first entities, and data acquisition entities described herein, the IE associated with the data acquisition configuration is included in the drive test minimization (MDT) configuration IE.

[0023] In the methods described herein, the RAN node, the first entity, and some implementations of the data collection entity, the cell traffic trace message includes one of the following: a trace recording session reference, a trace reference, the cell global identity (CGI) of the serving cell, or at least one address of at least one data collection entity.

[0024] In some implementations of the method, RAN node, first entity, and data acquisition entity described herein, the first entity is at least one of the data acquisition entities, the first message includes a data acquisition request message, and the first message is transmitted between the RAN node and the first entity by an interface and / or by an end-to-end protocol.

[0025] In the methods, RAN nodes, first entities, and several implementations of the data acquisition entities described herein, the data acquisition request message includes a partial support instruction indicating that some of the physical layer measurements are required.

[0026] In some implementations of the methods, RAN nodes, first entities, and data collection entities described in this specification, the physical layer measurement values include one of: ground truth channel state information (CSI) in scalar quantization and / or codebook-based quantization; a pair of first information and second information, where the first information includes a raw channel or eigenvector, and the second information includes a latent space vector with or without quantization; a pair of third information and fourth information, where the third information includes a quantized latent space vector, and the fourth information includes target CSI to be restored as a proxy model output; one or more CSI including a raw channel matrix, a precoding matrix indicator (PMI), or an eigenvector; one or more Layer 1 Reference Signal Received Power (L1-RSRP) measurements based on set B or a subset of set B, where set B includes a set of beams for prediction input; one or more L1-RSRP measurements based on set A or a subset of set A, where set A includes a set of beams for prediction output; one or more L1-RSRP measurements based on set A or a subset of set A and corresponding beam indicators; top-k beam indicators, a channel impulse response of a reference signal, a power delay profile of a reference signal, a delay profile of a reference signal, RSRP of a reference signal, Reference Signal Received Quality (RSRQ) of a reference signal, Reference Signal Time Difference (RSTD) of a reference signal, or ground truth location coordinates.

[0027] In some implementations of the methods, RAN nodes, first entities, and data collection entities described in this specification, the first message includes a request for assistance information associated with the physical layer measurement values to be collected, and the assistance information includes one of a timestamp, a scenario, an identity of a cell, a physical layer configuration, a quality indication, or line-of-sight or non-line-of-sight.

[0028] In some implementations of the methods, RAN nodes, first entities, and data collection entities described herein, the first message includes one of: at least one criterion for data collection, a duration for data collection, a periodicity for data collection, an event for triggering data collection, or an indication of a modality for the second message.

[0029] In some implementations of the methods, RAN nodes, first entities, and data collection entities described herein, the at least one criterion includes one of: a required scenario, a required physical layer configuration, a required quality indication, a required line-of-sight or non-line-of-sight, an involved area, an involved frequency, an involved cell, an involved beam, and an involved UE type.

[0030] In some implementations of the methods, RAN nodes, first entities, and data collection entities described herein, the first message includes at least one address of at least one data collection entity.

[0031] In some implementations of the methods, RAN nodes, first entities, and data collection entities described herein, part or all of the physical layer measurements in the second message are conveyed in a container of an encoded format.

[0032] In some implementations of the methods, RAN nodes, first entities, and data collection entities described herein, UE identity information is removed from part or all of the physical layer measurements in the second message.

[0033] In some implementations of the methods, RAN nodes, first entities, and data collection entities described herein, part or all of the physical layer measurements in the second message are grouped into a plurality of groups corresponding to a plurality of UEs, and each of the plurality of groups has a unique index.

[0034] In some implementations of the methods, RAN nodes, first entities, and data acquisition entities described herein, some or all of the physical layer measurements in the second message are grouped into groups corresponding to multiple features, each feature being associated with an attribute of the physical layer measurement. [Brief explanation of the drawing]

[0035] [Figure 1] This figure shows an example of a wireless communication system in which several embodiments of the present disclosure may be implemented. [Figure 2] This is a schematic diagram of an exemplary communication network in which several embodiments of the present disclosure may be implemented. [Figure 3] This is a signaling diagram illustrating a communication process according to some exemplary embodiments of the present disclosure. [Figure 4] This is a signaling diagram illustrating a communication process according to some exemplary embodiments of the present disclosure. [Figure 5] This figure shows an example of a device suitable for implementing the embodiments of the present disclosure. [Figure 6] This figure shows an example of a processor suitable for implementing some embodiments of the present disclosure. [Figure 7] This is a flowchart of an exemplary method implemented in a RAN node according to the aspects of this disclosure. [Figure 8] This is a flowchart of an exemplary method implemented in the first entity according to the aspects of this disclosure. [Figure 9] This is a flowchart of an exemplary method implemented in a data collection entity according to the aspects of this disclosure. [Modes for carrying out the invention]

[0036] Throughout the drawings, the same or similar reference numbers represent the same or similar elements.

[0037] Herein, the principles of this disclosure are described with reference to several embodiments. These embodiments are described for illustrative purposes only and should be understood as helping those skilled in the art to understand and implement this disclosure without implying any limitation on the scope of this disclosure. The disclosures described herein can be implemented in various ways other than those described below. In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as they are generally understood by those skilled in the art to which this disclosure belongs.

[0038] References in this disclosure to “one embodiment,” “exemplary embodiment,” “embodiment,” and “some embodiments” indicate that the embodiments described may include certain features, structures, or characteristics, but not all embodiments are required to include such features, structures, or characteristics. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when certain features, structures, or characteristics are described in relation to a particular embodiment, it is stated that this is within the scope of what a person skilled in the art would know to affect such features, structures, or characteristics in relation to other embodiments, whether explicitly stated or not.

[0039] Terms such as “first” and “second” may be used herein to describe various elements, but it should be understood that these elements should not be limited by these terms. These terms are used merely to distinguish one element from another. For example, without departing from the scope of the embodiment, the first element may be called the second element, and similarly, the second element may be called the first element. The term “and / or” as used herein includes any combination of one or more of the enumerated terms. In some examples, values, procedures, or devices are referred to as “best,” “lowest,” “highest,” “minimum,” “maximum,” etc. It should be understood that such descriptions may involve a choice between many used functional alternatives, and such a choice is intended to indicate that it is not necessarily superior to, smaller, higher, or otherwise preferable to other choices.

[0040] The terms used herein are for the purpose of describing only specific embodiments and are not intended to limit embodiments. The singular forms “a,” “an,” and “the” as used herein also include the plural form unless the context otherwise explicitly indicates. It should be further understood that, as used herein, the terms “comprises,” “comprising,” “has,” “having,” “includes,” and / or “including” specify the existence of the described function, element, component, etc., but do not exclude the existence or addition of one or more other functions, elements, components, and / or combinations thereof. For example, the term “includes” and its variations should be read as non-restrictive terms meaning “includes, but not limited to.” The term “based on” should be read as “at least partially based on.” The terms “one embodiment” and “a certain embodiment” should be read as “at least one embodiment.” The term “another embodiment” should be read as “at least one other embodiment.” The use of expressions such as "A and / or B" can mean either "A only," "B only," or "both A and B." Other explicit and implicit definitions may be described below.

[0041] Figure 1 shows an example of a wireless communication system 100 in which several embodiments of the present disclosure may be implemented. The wireless communication system 100 may include one or more network entities 102 (also called network equipment (NEs)), one or more UEs 104, a core network 106, and a packet data network 108. The wireless communication system 100 may support a variety of radio access technologies. In some implementations, the wireless communication system 100 may be a 4G network, such as a Long-Term Evolution (LTE) network or an LTE Advanced (LTE-A) network. In some other implementations, the wireless communication system 100 may be a 5G network, such as a New Radio (NR) network. In other implementations, the wireless communication system 100 may be a combination of 4G and 5G networks, or other suitable radio access technologies, including IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20. The wireless communication system 100 may support radio access technologies beyond 5G. Furthermore, the wireless communication system 100 may support technologies such as time-division multiple access (TDMA), frequency-division multiple access (FDMA), or code-division multiple access (CDMA).

[0042] One or more network entities 102 may be distributed across a geographical area to form a wireless communication system 100. One or more of the network entities 102 described herein may be a network node, base station, network element, radio access network (RAN), transceiver base station, access point, NodeB, eNodeB (eNB), next-generation NodeB (gNB), or other appropriate terms, or may include them, or may be referred to as such. The network entities 102 and UE 104 may communicate via a communication link 110, which may be wireless or wired. For example, the network entities 102 and UE 104 may perform wireless communication via a Uu interface (e.g., receiving and transmitting signaling).

[0043] Network entity 102 may provide a geographic coverage area 112 that network entity 102 can support for services (e.g., voice, video, packet data, messages, broadcasts, etc.) for one or more UEs 104 within that geographic coverage area 112. For example, network entity 102 and UE 104 may support wireless communication of signals associated with services (e.g., voice, video, packet data, messages, broadcasts, etc.) according to one or more radio access technologies. In some implementations, network entity 102 may be mobile and, for example, a satellite associated with a non-terrestrial network. In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, or different geographic coverage areas 112 may be associated with different network entities 102. The information and signals described herein may be represented using any of a wide variety of technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned throughout the description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0044] One or more UEs 104 may be distributed across the geographical area of ​​the wireless communication system 100. The UEs 104 may include, or be referred to as, mobile devices, wireless devices, remote devices, remote units, handheld devices, or subscriber devices, or any other appropriate term. In some implementations, the UEs 104 may be referred to as units, stations, terminals, or clients, among other examples. Additionally or alternatively, the UEs 104 may be referred to as Internet of Things (IoT) devices, any Internet of Things (IoE) devices, or machine-type communications (MTC) devices, among other examples. In some implementations, the UEs 104 may be stationary within the wireless communication system 100. In some implementations, the UEs 104 may be mobile within the wireless communication system 100.

[0045] One or more UE104s may be devices of different forms or with different capabilities. Several examples of UE104s are shown in Figure 1. UE104s may be capable of communicating with various types of devices, such as network entities 102, other UE104s, or network equipment (e.g., core network 106, packet data network 108, relay devices, integrated access and backhaul (IAB) nodes, or other network equipment), as shown in Figure 1. Additionally or alternatively, UE104s may support communication with other network entities 102 or UE104s, which may act as relays in the wireless communication system 100.

[0046] UE104 may also support direct wireless communication with other UE104s via communication link 114. For example, UE104 may support direct wireless communication with another UE104 via a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-all (V2X) deployments, or cellular V2X deployments, communication link 114 may be called a side link (SL). For example, UE104 may support direct wireless communication with another UE104 via the PC5 interface.

[0047] A network entity 102 may support communication with the core network 106, or with another network entity 102, or both. For example, a network entity 102 may interface with the core network 106 through one or more backhaul links 116 (e.g., via S1, N2, N3, or another network interface). Network entities 102 may communicate with each other via the backhaul links 116 (e.g., via X2, Xn, or another network interface). In some implementations, network entities 102 may communicate with each other directly (e.g., between network entities 102). In some other implementations, network entities 102 may communicate with each other or indirectly (e.g., via the core network 106). In some implementations, one or more network entities 102 may include sub-components such as access network entities, which may be examples of access node controllers (ANCs). The ANC may communicate with one or more UE104 through one or more other access network transmitting entities, which may be called radio heads, smart radio heads, or transmit / receive points (TRPs).

[0048] In some implementations, the network entity 102 may consist of a decoupled architecture, which may be configured to use a physically or logically distributed protocol stack between two or more network entities 102, such as an access backhaul integration (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN)). For example, the network entity 102 may include one or more of the following, or any combination thereof: a central unit (CU), a distributed unit (DU), a radio unit (RU), a RAN intelligent controller (RIC) (e.g., a near real-time RIC (near RT RIC), a non-real-time RIC (non-RT RIC)), a service management and orchestration (SMO) system.

[0049] RU may also be called a radio head, smart radio head, remote radio head (RRH), remote radio unit (RRU), or transmit / receive point (TRP). One or more components of network entity 102 in a separated RAN architecture may be co-located, or one or more components of network entity 102 may be located in distributed locations (e.g., separate physical locations). In some implementations, one or more network entities 102 in a separated RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0050] The functional division between CUs, DUs, and RUs may be flexible and may support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, radio frequency functions, and any combination thereof) are performed in the CU, DU, or RU. For example, a functional division of the protocol stack may be used between the CU and DU so that the CU may support one or more layers of the protocol stack and the DU may support one or more different layers of the protocol stack. In some implementations, the CU may host higher protocol layer (e.g., Layer 3 (L3), Layer 2 (L2)) functionalities and signaling (e.g., Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), Packet Data Convergence Protocol (PDCP)). A CU may be connected to one or more DUs or RUs, each of which may host lower protocol layers such as Layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, each of which may be at least partially controlled by the CU.

[0051] As an addition or alternative, a functional decomposition of the protocol stack may be used between the DU and RU so that the DU can support one or more layers of the protocol stack and the RU can support one or more different layers of the protocol stack. The DU may support one or more different cells (for example, through one or more RUs). In some implementations, the functional decomposition between the CU and the DU, or between the DU and the RU, may be within the protocol layer (for example, some functions for the protocol layer may be performed by one of the CU, DU, or RU, and other functions of the protocol layer may be performed by one of the different CU, DU, or RU).

[0052] A CU may be further functionally divided into CU control plane (CU-CP) and CU user plane (CU-UP) functions. A CU may be connected to one or more DUs via midhaul communication links (e.g., F1, F1-C, F1-U), and a DU may be connected to one or more RUs via fronthaul communication links (e.g., open fronthaul (FH) interfaces). In some implementations, the midhaul or fronthaul communication links may be implemented according to interfaces (e.g., channels) between layers of protocol stacks supported by each network entity 102 communicating via such communication links.

[0053] The core network 106 can support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The core network 106 may be an advanced packet core (EPC) or a 5G core (5GC), which may include control plane entities that manage access and mobility (e.g., a mobility management entity (MME), an access and mobility management function (AMF)), as well as user plane entities that route packets or interconnect to external networks (e.g., a serving gateway (S-GW), a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entities may manage non-access layer (NAS) functions such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for one or more UEs 104 served by one or more network entities 102 associated with the core network 106.

[0054] The core network 106 may communicate with the packet data network 108 via one or more backhaul links 116 (for example, via S1, N2, N3, or another network interface). The packet data network 108 may include an application server 118. In some implementations, one or more UEs 104 may communicate with the application server 118. The UEs 104 may establish a session with the core network 106 (for example, a protocol data unit (PDU) session) via a network entity 102. The core network 106 may use the established session (for example, an established PDU session) to route traffic (for example, control information, data, etc.) between the UEs 104 and the application server 118. The PDU session may be an example of a logical connection between the UEs 104 and the core network 106 (for example, one or more network functions of the core network 106).

[0055] In the wireless communication system 100, the network entities 102 and UE104 can use the resources of the wireless communication system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, etc.) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communication). In some implementations, the network entities 102 and UE104 may support different resource structures. For example, the network entities 102 and UE104 may support different frame structures. In some implementations, for example in 4G, the network entities 102 and UE104 may support a single frame structure. In some other implementations, for example in 5G, and in other suitable radio access technologies, the network entities 102 and UE104 may support various frame structures (i.e., multiple frame structures). The network entities 102 and UE104 may support various frame structures based on one or more numerologies.

[0056] One or more numerologies may be supported in the wireless communication system 100, and the numerologies may include subcarrier intervals and cyclic prefixes. A first numerology (e.g., μ=0) may be associated with a first subcarrier interval (e.g., 15 kHz) and a typical cyclic prefix. In some implementations, the first numerology (e.g., μ=0) associated with the first subcarrier interval (e.g., 15 kHz) may use one slot per subframe. A second numerology (e.g., μ=1) may be associated with a second subcarrier interval (e.g., 30 kHz) and a typical cyclic prefix. A third numerology (e.g., μ=2) may be associated with a third subcarrier interval (e.g., 60 kHz) and a typical cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., μ=3) may be associated with a fourth subcarrier interval (e.g., 120 kHz) and a typical cyclic prefix. A fifth numerology (e.g., μ=4) may be associated with a fifth subcarrier interval (e.g., 240 kHz) and a typical cyclic prefix.

[0057] The time intervals of resources (e.g., communication resources) may be organized according to frames (also called wireless frames). Each frame may have a duration, for example, 10 milliseconds (ms). In some implementations, each frame may contain multiple subframes. For example, each frame may contain 10 subframes, each subframe may have a duration, for example, 1 ms. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0058] As an addition or alternative, the time intervals of resources (e.g., communication resources) may be organized according to slots. For example, a subframe may contain a certain number (e.g., a quantity) of slots. The number of slots in each subframe may depend on one or more numerologies supported in the wireless communication system 100. For example, the first, second, third, fourth, and fifth numerologies (i.e., μ=0, μ=1, μ=2, μ=3, μ=4) associated with the respective subcarrier intervals of 15kHz, 30kHz, 60kHz, 120kHz, and 240kHz may use one slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and sixteen slots per subframe, respectively. Each slot may contain a certain number (e.g., a quantity) of symbols (e.g., OFDM symbols). In some implementations, the number (e.g., a quantity) of slots for a subframe may depend on the numerology. For a standard cyclic prefix, a slot may contain 14 symbols. For an extended cyclic prefix (e.g., applicable to a 60 kHz subcarrier interval), a slot may contain 12 symbols. The relationships between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for standard and extended cyclic prefixes may depend on the numerology. It should be understood that references to a first numerology (e.g., μ=0) associated with a first subcarrier interval (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0059] In the wireless communication system 100, the electromagnetic (EM) spectrum can be divided into various classes, frequency bands, frequency channels, etc., based on frequency or wavelength. For example, the wireless communication system 100 may support one or more operating frequency bands, such as frequency range designations FR1 (410 MHz to 7.125 GHz), FR2 (24.25 GHz to 52.6 GHz), FR3 (7.125 GHz to 24.25 GHz), FR4 (52.6 GHz to 114.25 GHz), FR4a or FR4-1 (52.6 GHz to 71 GHz), and FR5 (114.25 GHz to 300 GHz). In some implementations, network entities 102 and UE 104 may conduct wireless communication over one or more of these operating frequency bands. In some implementations, FR1 may be used by network entities 102 and UE 104, in particular, among other equipment or devices for cellular communication traffic (e.g., control information, data). In some implementations, FR2 can be used by network entities 102 and UE104, in particular, among other equipment or devices for short-range, high-data-rate capabilities.

[0060] FR1 may be associated with one or more numerologies (e.g., at least three). For example, FR1 may be associated with a first numerology including a 15 kHz subcarrier interval (e.g., μ=0), a second numerology including a 30 kHz subcarrier interval (e.g., μ=1), and a third numerology including a 60 kHz subcarrier interval (e.g., μ=2). FR2 may be associated with one or more numerologies (e.g., at least two). For example, FR2 may be associated with a third numerology including a 60 kHz subcarrier interval (e.g., μ=2), and a fourth numerology including a 120 kHz subcarrier interval (e.g., μ=3).

[0061] In this disclosure, the term “data collection entity” may be used interchangeably with data collection node, entity for collecting data for model training, node for collecting data for model training, etc. In this disclosure, the term “model training entity” may be used interchangeably with training entity, AI / ML model training entity, training node, AI / ML model training node, entity for model training, node for model training, etc.

[0062] The Third Generation Partnership Project (3GPP®) discusses the use of AI / ML technology for optimizing physical layer behavior, also known as AI for air interfaces, in use cases such as channel state information (CSI) feedback compression, CSI time domain prediction, beam spatial domain prediction, beam time domain prediction, AI / ML-assisted positioning estimation, and direction positioning.

[0063] Depending on the use case, AI / ML models can also be deployed in UE / gNB / LMF (i.e., inference entities) and trained in gNB, operation supervision and maintenance (OAM) systems, over-the-top (OTT) servers, UE, LMF, or core network (CN) functions in addition to LMF, as listed in Table 1 below.

[0064] [Table 1]

[0065] To train an AI / ML model, the AI / ML training entity needs to collect Layer 1 (L1) measurements for AI / ML training. Several examples of training data are listed below for each use case.

[0066] When an AI / ML model is used for CSI compression, (1) for UE-side Type 1 training and UE-first Type 3 training, ground truth CSI from the network (NW) in scalar quantization and / or codebook-based quantization (e.g., e-Type II), and / or assistive information for categorizing the data for the purpose of distinguishing data characteristics by specific configurations, scenarios, sites, etc.; (2) for NW-first training in training cooperation Type 3, CSI generation model training dataset (e.g., raw channels or eigenvectors as model inputs and pre-quantized or post-quantized latent space vectors as model outputs), and / or assistive information for categorizing the data for the purpose of distinguishing data characteristics by specific configurations, scenarios, sites, etc.; (3) for monitoring UE-side proxy model training, proxy model training dataset (e.g., post-quantized latent space vectors as proxy model inputs and target CSI to be reconstructed as proxy model outputs), and / or assistive information for categorizing the data for the purpose of distinguishing data characteristics by specific configurations, scenarios, sites, etc.

[0067] When an AI / ML model is used for CSI prediction, the type of CSI is a raw channel matrix, or a precoded matrix indicator (PMI), or an eigenvector, as well as / or supporting information for model management, such as site / scenario / dataset-related information, including continuous CSI (historical CSI and future CSI).

[0068] When an AI / ML model is used for beam prediction, (1) Set B: Layer 1 reference signal received power (L1-RSRP) measurements based on Set B or a subset of Set B. (2) Label data may be one of the following: L1-RSRP measurements based on Set A or a subset of Set A, partial L1-RSRP measurements based on Set A or a subset of Set A + beam indicators, and / or indicators for the top k beams. (3) Time-related information, e.g., timestamps. (4) Supporting information includes one or more site / scenario / dataset-related information, e.g., dataset ID, gNB-side supporting information, and / or UE-side supporting information.

[0069] When AI / ML models are used for positioning, (1) Measurement type: Channel Impulse Response (CIR) / Power Delay Profile (PDP) / Delay Profile (DP), and / or Reference Signal Received Power (RSRP) / Reference Signal Received Quality (RSRQ) / Reference Signal Time Difference (RSTD). (2) Label type: Location coordinates, timing estimate, Line of Sight (LOS) / Non-Line of Sight (NLOS). (3) Supporting information, timestamp, quality indicator, RS configuration.

[0070] Since L1 measurements are determined in the UE, in addition to the LMF, how data acquisition entities such as OAM, OTT servers, LMF, or CN functions (e.g., AIML training entities) collect L1 measurements for training should be further considered.

[0071] Embodiments of this disclosure provide a communication solution in which a RAN node may report physical layer measurements to a data acquisition entity, thereby enabling further applications (such as model training in a training entity). In some examples, physical layer measurements may be reported to multiple data acquisition entities, thereby eliminating the need for additional requests for physical layer measurements and thus reducing overhead. The principles and implementations of this disclosure are described in detail below with reference to the drawings.

[0072] Figure 2 shows a schematic diagram of an exemplary communication network 200 in which several embodiments of the present disclosure may be implemented. As shown in Figure 2, the communication network 200 may include a RAN node 210, a first entity 220, and a data collection entity 230.

[0073] RAN node 210 may be a base station such as a gNB, or RAN node 210 may be a CU or DU of a base station, or RAN node 210 may be a CU-UP or CU-CP of a CU. As shown in Figure 2, RAN node 210 may serve multiple UEs such as 201-1 to 201-N.

[0074] In some implementations, the data acquisition entity 230 may be the same as the AI / ML model training entity. In some other implementations, the data acquisition entity 230 may be different from the AI / ML model training entity; for example, the data acquisition entity 230 may collect data (such as L1 measurements) and provide the data to the AI / ML model training entity. In some embodiments, the data acquisition entity 230 may be any of the following: OAM, OTT server, LMF, Network Data Analysis Function (NWDAF), Data Acquisition Coordination Function (DCCF), Data Acquisition Application Function (DCAF), Application Function (AF), another network function in CN, etc.

[0075] In some implementations, the data collection entity 230 is outside the RAN domain; for example, the data collection entity 230 is neither a UE nor a base station. In some implementations, there may be multiple data collection entities.

[0076] In this disclosure, the first entity 220 may be one of the AMF, OAM, or data collection entities. In some implementations, if the first entity 220 is a data collection entity, it may be the same as or different from the data collection entity 230.

[0077] Please understand that the number of devices in Figure 2 is given for illustrative purposes only and does not imply any limitation to this disclosure.

[0078] To collect L1 measurements in the data acquisition entity 230, the UE may transfer data to the AI / ML training entity, as there may be no interface between them, and the transfer may be carried out via the user plane (UP) or the non-accessible layer (NAS), which may be inefficient and may require some additional radio resources. Another possible approach may be to use an existing trace / drive test minimization (MDT) framework, where the OAM or trace acquisition entity (TCE) can collect UE measurements via the gNB. One advantage of using the trace / MDT framework is that it is based on radio resource management (RRM) measurements, making it efficient for the AI / ML training entity to retrieve training data directly from the gNB. However, there is no agreement on how L1 measurements should be transferred when the trace / MDT framework is used.

[0079] Further reference is made to Figure 3, which shows a signaling diagram illustrating a communication process 300 according to several exemplary embodiments of the present disclosure. Process 300 may involve a RAN node 210, a first entity 220, and a data acquisition entity 230, as shown in Figure 2. It will be understood that process 300 may be applied to other communication scenarios, although this will not be described in detail.

[0080] Process 300 may be considered trace / MDT-based data acquisition for L1 measurement acquisition, taking multiple entities into account. In some implementations, the data to be acquired includes physical layer measurements (which also refer to L1 measurements). In some implementations, data acquisition may also be called measurement acquisition, L1 measurement acquisition, etc. In some implementations, physical layer measurements (L1 measurements) may be used for model training in an AI / ML training entity (the same as or different from the data acquisition entity 230), for example, the model may be used for CSI feedback compression, CSI time-domain prediction, beam-space-domain prediction, beam-time-domain prediction, AI / ML-assisted positioning estimation, or direction positioning.

[0081] In process 300, the first entity 220 acquires information associated with physical layer measurements in 310. In some implementations, the data acquisition entity 230 may decide to collect physical layer measurements and provide the information associated with those measurements to the first entity 220.

[0082] In some examples, the data acquisition entity 230 may include an OAM, and if the OAM wants to collect L1 measurements to train an NW-side CSI / beam prediction AI / ML model, the OAM may provide relevant information to the first entity 220. In some examples, the data acquisition entity 230 may include an NWDAF, and if the NWDAF wants to collect L1 measurements to train an UE-side CSI / beam prediction AI / ML model, the NWDAF may provide relevant information to the first entity 220. In some examples, the data acquisition entity 230 may include an LMF, and if the LMF wants to collect L1 measurements to train an LMF-side positioning AI / ML model, the LMF may provide relevant information to the first entity 220. For example, the relevant information may include a data acquisition configuration for its own purposes.

[0083] During process 300, the first entity 220 sends a first message to the RAN node 210 in 320. The first message may instruct the RAN node 210 to collect physical layer measurements and to report the collected physical layer measurements to at least one data acquisition entity 230. In some examples, the first message may instruct the RAN node 210 to send the collected physical layer measurements to at least one data acquisition entity 230 (for example, in a second message).

[0084] In some exemplary embodiments, the first message may indicate that physical layer measurements should be reported to at least one data acquisition entity 230 in a file-based format or in a streaming-based format. In some examples, the first message may include at least one data acquisition configuration.

[0085] In some examples, the first message may indicate multiple data collection entities, for example, by including multiple addresses of multiple data collection entities. For example, the addresses may take the form of an Internet Protocol (IP) address, a fully qualified domain name (FQDN), a uniform resource identifier (URI), a uniform resource location (URL), etc. For example, an IP address may be used for file-based data collection reports. For example, a URI may be used for streaming-based data collection reports.

[0086] For example, the first message may include a list of addresses for multiple data collection entities, and the first message may further include data collection configurations for each data collection entity. For example, different data collection configurations may be associated with different data collection entities.

[0087] In some implementations, the first entity 220 may be an AMF. In some examples, the first message is sent via the NG interface. In some examples, the first message may be implemented as a trace initiation message, for example, a signaling-based trace / MDT configuration may be applied. In some examples, the trace initiation message may include an information element (IE) associated with a data collection configuration that instructs to collect and report physical layer measurements. For example, a data collection configuration IE may be included.

[0088] In some embodiments, the trace start message includes a trace activation IE, and the trace activation IE includes a data acquisition configuration IE. In some examples, the trace activation IE further includes an MDT configuration IE, for example, the data acquisition configuration IE may be in parallel with the MDT configuration IE. In some examples, the data acquisition configuration IE may include a bit string that can indicate the activation of physical layer measurements. For example, the bit string may include multiple bits (e.g., a bitmap) corresponding to multiple measurements, where bit "1" (or "0") may indicate that the corresponding measurement is activated.

[0089] In some examples, the data collection configuration IE may further include other information associated with the collection, such as criteria, periodicity, and events, which will be discussed below. In some examples, the data collection configuration IE may further include at least one ID or at least one address of at least one data collection entity 230.

[0090] As a concrete example, Table 2 below shows an example of a trace activation IE that includes a data collection configuration IE.

[0091] [Table 2]

[0092] In some other embodiments, the trace start message includes a trace activation IE, the trace activation IE includes an MDT configuration IE, where the MDT configuration IE includes a data acquisition configuration IE. For example, the data acquisition configuration may be considered part of the trace / MDT configuration.

[0093] In some examples, the MDT configuration IE (e.g., the data acquisition configuration IE) may include a bit string that can indicate the activation of physical layer measurements. For example, the bit string may include multiple bits (e.g., a bitmap) corresponding to multiple measurements, where a bit "1" (or "0") may indicate that the corresponding measurement is activated.

[0094] In some examples, the MDT configuration IE (e.g., the data collection configuration IE) may further include other information associated with the collection, such as criteria, periodicity, and events, which are discussed below. In some examples, the MDT configuration IE (e.g., the data collection configuration IE) may further include at least one ID or at least one address of at least one data collection entity 230. In some examples, a new job type may be defined, for example, the newly defined job type may be "data collection".

[0095] As a concrete example, Table 3 below shows an example of an MDT configuration IE that includes a data collection configuration IE.

[0096] [Table 3A]

[0097] [Table 3B]

[0098] In some implementations, the first entity 220 may be an OAM system. In some examples, the first message may be sent directly, for example, by applying a management-based trace / MDT configuration. In some examples, the first message may include at least one data collection configuration configured by the OAM system.

[0099] In some exemplary embodiments, the first message may represent a physical layer measurement, for example, a bitmap. In some examples, the physical layer measurement may include a ground truth CSI in scalar quantization and / or codebook-based quantization, such as a CSI ground truth value like e-type II. In some examples, the physical layer measurement may include a pair of first and second information, where the first information comprises a raw channel or eigenvector and the second information comprises a latent space vector with or without quantization, for example, the first information may be further used as a model input and the second information may be further used as a model output. In some examples, the physical layer measurement may include a pair of third and fourth information, where the third information comprises a quantized latent space vector and the fourth information comprises a target CSI to be reconstructed as a proxy model output, for example, the third information may be further used as a proxy model input and the fourth information may be further used as a proxy model output. In some examples, the physical layer measurement may include one or more CSIs, such as a raw channel matrix, PMI, or eigenvector. In some examples, the physical layer measurement may include one or more L1-RSRP measurements based on set B or a subset of set B, where set B includes a set of beams for the predictive input and set B may be represented as one or more synchronous signal block (SSB) indices. In some examples, the physical layer measurement may include one or more L1-RSRP measurements based on set A or a subset of set A, where set A includes a set of beams for the predictive output and set A may be represented as one or more SSB indices. In some examples, the physical layer measurement may include one or more L1-RSRP measurements based on set A or a subset of set A and the corresponding beam indicators. In some examples, the physical layer measurement may include the top k beam indicators, for example, the top k best beams. In some examples, the physical layer measurement may include one or more of the CIR, PDP, DP, L1-RSRP, L1-RSRQ, or L1-RSTD of the measured reference signal.In some cases, physical layer measurements may include ground truth location coordinates, which may be, for example, known location coordinates of a power receiving unit (PRU), or estimated location determined, for example, by using another positioning method (e.g., without using an AI / ML model).

[0100] In some exemplary embodiments, the first message may further instruct the RAN node 210 to provide support information for collecting physical layer measurements. In some examples, the first message may include a request for support information. In some examples, the support information may include a timestamp for data collection, e.g., the time when the physical layer measurements are collected. In some examples, the support information may include a scenario for data collection, e.g., the scenario may be one of indoor, outdoor, large cell, small cell, etc. In some examples, the support information may include the cell identity for data collection, e.g., the cell ID of the serving cell where the UE is located, where the physical layer measurements can be determined by the UE. In some examples, the support information may include a physical layer configuration for data collection, e.g., a physical layer configuration configured by the RAN node 210 to the UE. In some examples, the support information may include a quality instruction for data collection. For example, the quality instruction may indicate whether the physical layer measurements are reliable or accurate. For example, the quality instruction may indicate a reliable rate or an accurate rate for the physical layer measurements. For example, if the signal-to-noise ratio (SNR) is low, the physical layer measurements may be of poor quality. In some cases, the supporting information may include NLOS or LOS.

[0101] In some exemplary embodiments, the first message may include at least one criterion for data collection. In some examples, at least one criterion may indicate one or more of the following: required scenario, required physical layer configuration, required quality indication, required line of sight or non-line of sight. In some examples, at least one criterion may indicate an area of ​​involvement, e.g., a list of areas of involvement. In some examples, at least one criterion may indicate a frequency of involvement, e.g., a list of frequencies of involvement. In some examples, at least one criterion may indicate a cell of involvement, e.g., cell information for a list of cells of involvement may be included in the first message. In some examples, at least one criterion may indicate a beam of involvement, e.g., a list of beams of involvement may be included in the first message. In some examples, at least one criterion may indicate a type of involved UE, e.g., an IoT UE type, a stationary UE type, a mobile UE type, or a multi-input multiple-output (MIMO) capable UE type.

[0102] In some exemplary embodiments, the first message may indicate the duration and / or periodicity for data collection. In some examples, the duration may be represented by a time interval value. In some examples, the duration may be represented by a start time and an end time.

[0103] In some exemplary embodiments, the first message may indicate one or more events to trigger data collection.

[0104] In some exemplary embodiments, the first message may indicate one or more specific UEs. For example, it may contain information about one specific UE or more specific UEs.

[0105] In some exemplary embodiments, the first message may include a formatted instruction for the second message to at least one data acquisition entity 230. In some examples, the first message may instruct the RAN node 210 to report the second message in UE unit format or feature unit format, which will be discussed below.

[0106] During process 300, upon receiving the first message from the first entity 220, RAN node 210 collects physical layer measurements at 330.

[0107] In some implementations, if the first message indicates one or more specific UEs, the RAN node 210 may collect physical layer measurements from one or more specific UEs.

[0108] In some implementations, if the first message does not indicate one or more specific UEs, the RAN node 210 may select at least one UE and collect physical layer measurements from the selected UE. In some examples, the RAN node 210 may select at least one UE based on at least one criterion indicated by the first message, for example, at least one UE that satisfies at least one criterion.

[0109] In some implementations, if the first message indicates at least one criterion, the RAN node 210 only needs to collect physical layer measurements according to at least one criterion.

[0110] In some implementations, if the first message indicates duration and / or periodicity, the RAN node 210 can collect physical layer measurements according to the duration and / or periodicity.

[0111] In some implementations, the RAN node 210 may be configured to report physical layer measurements for one or more specific UEs or at least one selected UE.

[0112] As an addition or alternative, in the case of a RAN CU-DU isolation architecture, the CU of RAN node 210 may receive the first message, and further, the CU may forward some or all of the information in the first message to the DU of RAN node 210, for example, via the F1 interface.

[0113] As an addition or alternative, in the case of a RAN CU-CP CU-UP isolation architecture, the CU-CP of RAN node 210 may receive the first message, and further, the CU-CP may forward some or all of the information in the first message to the CP-UP of RAN node 210, for example via the E1 interface.

[0114] As an addition or alternative, during a handover of a UE (such as a specific UE indicated by the first message or a UE selected by RAN node 210), RAN node 210 may be the source gNB for the handover, and RAN node 210 may further transmit some or all of the information in the first message to the target RAN node (e.g., the target gNB) via, for example, the Xn interface.

[0115] In some implementations, if the first entity 220 is an OAM system, the RAN node 210 may, as an addition or alternative, further send cell traffic trace messages to the AMF. In some exemplary embodiments, the cell traffic trace message may include one or more of the following: a trace recording session reference, a trace reference, the serving cell's cell global identity (CGI), or at least one address of at least one data collection entity.

[0116] In some examples, where data collection anonymization is required, the International Mobile Equipment Identification Number (IMEI) Track Area Code (TAC) may be included in the second message, and RAN node 210 may send a cell traffic trace message to the AMF via the NG interface, where the cell traffic trace message includes a trace recording session reference, a trace reference, a serving cell CGI, and at least one address (in the form of an IP address, FQDN, URI, or URL) of at least one data collection entity. For example, the cell traffic trace message may further indicate the job type (which may be "data collection") within a privacy indicator IE.

[0117] Upon receiving a cell traffic trace message from RAN node 210, AMF can further look up the subscriber identity (IMEI(SV)) of a given cell from the cell's database and send the IMEI-TAC, along with the trace recording session reference, trace reference, and serving cell CGI, to at least one data collection entity 230.

[0118] As a concrete example, Table 4 below shows an example of a cell traffic trace message that includes at least one address of at least one data collection entity.

[0119] [Table 4A]

[0120] [Table 4B]

[0121] During process 300, RAN node 210 sends a second message to at least one data acquisition entity 230 in 340, the second message may contain some or all of the physical layer measurements. Specifically, the second message may contain the collected physical layer measurements.

[0122] In some implementations, if the first message requests support information associated with the physical layer measurement, in other words, if the RAN node 210 is configured to provide support information, the second message may further include the requested support information.

[0123] In some implementations, the collected physical layer measurements may be grouped into multiple groups, and at least one of these groups may be included in a second message and sent to at least one data collection entity 230.

[0124] In some exemplary embodiments, the grouping operation may be in a specific format, such as a UE unit format or a feature unit format. The UE unit format may also be called a UE central format, and the feature unit format may also be called a functional unit format, feature central format, etc. In some examples, if the first message contains a format instruction, the indicated format may be used by the RAN node 210.

[0125] In some implementations, collected physical layer measurements may be grouped into multiple groups corresponding to multiple UEs. In some embodiments, a UE-centric format may be used, for example, where physical layer measurements collected from the same UE are grouped and associated with a unique ID / index. For example, the unique ID / index may not be any UE-specific ID used in the network, such as a Subscriber Persistent Identifier (SUPI), Mobile Electronic Device Installation (MEI), or Radio Network Temporary Identifier (RNTI). For example, the unique ID / index may be assigned by RAN node 210 to distinguish UEs. In some examples, timestamps of measurements in a group may be included in a second message, for example, measurements in a group may be determined by the same UE at different points in time.

[0126] In some examples, if there is a different RAN node, it is acceptable to assign different IDs / indexes to the same UE, meaning that different RAN nodes may assign different IDs / indexes to the same UE under mobility scenarios.

[0127] A group of collected physical layer measurements corresponding to a specific UE may be useful for training time-predictive AI / ML models, for example, a sequence of physical layer measurements taken by the same UE at different points in time can be used as model input.

[0128] In some implementations, collected physical layer measurements may be grouped into multiple groups corresponding to multiple features. In some embodiments, multiple features may be associated with multiple attributes of the physical layer measurements. For example, features may be a specific beam, a specific beamset, a specific location (e.g., ground truth location), etc.

[0129] In some embodiments, a feature-centered approach may be used. For example, collected physical layer measurements from the same beamset B may be grouped together without further distinction being needed as to whether those physical layer measurements originated from different UEs or whether those physical layer measurements were measured at different time points. In some examples, the feature-centered approach may be useful in the case of spatial domain prediction, where physical layer measurements from a particular beamset B are used as input to predict physical layer measurements from a particular beamset A at the same time point.

[0130] As another example, in fingerprint-based positioning, a combination of physical layer measurements and ground truth location is used for training.

[0131] In some embodiments, when a feature-centric style is used, UE information or time information is not included in the second message; for example, UE information or time information may not be necessary.

[0132] In process 300, the physical layer measurements in the second message may be used for further purposes. In some implementations, the data acquisition entity 230 uses or provides the physical layer measurements in 350.

[0133] In some embodiments, if the data acquisition entity 230 can be used as a model training entity, the data acquisition entity 230 may further train the AI / ML model using physical layer measurements, for example, by constructing a training set based on physical layer measurements.

[0134] In some embodiments, if there is another model training entity, the data acquisition entity 230 may further provide (e.g., transmit) physical layer measurements to the model training entity. For example, the model training entity may further train the AI / ML model by using the physical layer measurements.

[0135] According to some embodiments discussed with reference to Figure 3, a RAN node may report physical layer measurements to a data acquisition entity, thus enabling further use (such as model training in a training entity). In some examples, physical layer measurements may be reported to multiple data acquisition entities, thus eliminating the need for additional requests for physical layer measurements and thus reducing overhead.

[0136] Further reference is made to Figure 4, which shows a signaling diagram illustrating a communication process 400 according to some exemplary embodiments of the present disclosure. Process 400 may involve a RAN node 210 and a data acquisition entity 230, as shown in Figure 2. It will be understood that process 400 may be applied to other communication scenarios, although this will not be described in detail.

[0137] Process 400 may be considered a dedicated procedure for L1 measurement acquisition. In some implementations, the data to be acquired includes physical layer measurements (which also refer to L1 measurements). In some implementations, data acquisition may also be called measurement acquisition, L1 measurement acquisition, etc. In some implementations, physical layer measurements (L1 measurements) may be used for model training in an AI / ML training entity (the same as or different from the data acquisition entity 230), for example, the model may be used for CSI feedback compression, CSI time domain prediction, beam space domain prediction, beam time domain prediction, AI / ML assisted positioning estimation, or direction positioning.

[0138] There is either a direct interface or an end-to-end (E2E) protocol between the data acquisition entity 230 and the RAN node 210. For example, if the data acquisition entity 230 is an AMF, there is a known interface with the RAN node 210. For example, if the data acquisition entity 230 is an LMF, there is an E2E protocol (e.g., NRPPa) with the RAN node 210.

[0139] In process 400, the data acquisition entity 230 determines the information associated with the physical layer measurements in 410. In some implementations, the data acquisition entity 230 may decide to collect physical layer measurements and therefore generate information associated with the physical layer measurements. In some implementations, there may be multiple data acquisition entities, for example, one or more data acquisition entities other than the data acquisition entity 230, and the data acquisition entity 230 may determine the information associated with the physical layer measurements based on a combination of information from the data acquisition entity 230 and one or more data acquisition entities other than the data acquisition entity 230.

[0140] During process 400, data acquisition entity 230 sends a first message to RAN node 210 at 420. The first message may instruct RAN node 210 to collect physical layer measurements and report the collected physical layer measurements to at least one data acquisition entity, where at least one data acquisition entity includes data acquisition entity 230. For example, at least one data acquisition entity may further include one or more data acquisition entities other than data acquisition entity 230. In some examples, the first message may instruct RAN node 210 to send the collected physical layer measurements to at least one data acquisition entity (for example, in a second message).

[0141] In some exemplary embodiments, the first message may indicate that physical layer measurements should be reported to at least one data acquisition entity 230 in a file-based format or in a streaming-based format. In some examples, the first message may include at least one data acquisition configuration.

[0142] In some implementations, the first message may be a data collection request message. In some embodiments, the data collection request message may include a data collection configuration. In some examples, the details of the first message may refer to those discussed with reference to Figure 3 and are therefore not repeated here.

[0143] In some embodiments, the first message may further include a partial support instruction. In some examples, the partial support instruction may indicate that some of the physical layer measurements are required.

[0144] In some cases, a partial support instruction may indicate whether partial support is permitted. In some cases, RAN node 210 may provide only a portion of the physical layer measurements. In some cases, if all physical layer measurements (such as M-type L1 measurements) are required inputs for training the AI / ML model, partial support should not be enabled (i.e., disabled or not permitted). In some other cases, if some of the physical layer measurements are optional inputs for training the AI / ML model, partial support may be enabled (i.e., permitted).

[0145] In some examples, partial support indications may be shown by an IE (such as a single indicator IE) in the data acquisition request message. In some examples, a partial support indication may include multiple indicators corresponding to multiple physical layer measurements, each indicator of whether the corresponding physical layer measurement is mandatory or optional.

[0146] In some embodiments, the first message may further include ID information associated with the data collection session. In some examples, the ID information may be used to indicate a triggered data collection session.

[0147] In some embodiments, the first message may further include one or more addresses of one or more data collection entities other than data collection entity 230. For example, the addresses may be in the form of an IP address, FQDN, URI, URL, etc.

[0148] For example, the first message may include a list of addresses of multiple data collection entities, and the first message may further include a data collection configuration for each data collection entity.

[0149] As a concrete example, Table 5 below shows an example of a list of addresses in a data collection request message.

[0150] [Table 5]

[0151] As a concrete example, let's assume that the data collection entity 230 is an LMF. If the LMF wants to collect data to train an AI / ML model, the AI / ML model will be used for AI-based positioning within a particular cell. In some examples, the LMF may configure RAN node 210 to collect all DL CSI measurements for several SSBs, along with associated ground truth location information, from possible UEs within a particular cell via a data collection request message using the NR Positioning Protocol A (NRPPa) protocol. In some examples, the data collection request message may indicate a duration (e.g., the next hour), which may instruct the RAN node to report the collected measurements once in the next hour. In some examples, the data collection request message may further indicate a duration (e.g., the next hour) and periodicity (every minute), which may instruct RAN node 210 to report the collected measurements periodically (every minute) over the next hour.

[0152] As an addition or alternative, RAN node 210 may send a response to data acquisition entity 230 at 425. In some implementations, the response to the first message may be a data acquisition response message. In some implementations, the response is sent via a direct interface or an E2E protocol.

[0153] In some examples, if all physical layer measurements indicated by the first message can be collected by the RAN node 210, or if some of the required physical layer measurements (partially supported or permitted) can be collected by the RAN node 210, a data collection response message may be sent to the data collection entity 230.

[0154] In process 400, upon receiving the first message, RAN node 210 collects some or all of the physical layer measurements in 430. Operation 430 may be similar to operation 330 discussed with reference to Figure 3, and is therefore not repeated here.

[0155] As an addition or alternative, in the case of a RAN CU-DU isolation architecture, the CU of RAN node 210 may receive the first message, and further, the CU may forward some or all of the information in the first message to the DU of RAN node 210, for example, via the F1 interface.

[0156] As an addition or alternative, in the case of a RAN CU-CP CU-UP isolation architecture, the CU-CP of RAN node 210 may receive the first message, and further, the CU-CP may forward some or all of the information in the first message to the CP-UP of RAN node 210, for example via the E1 interface.

[0157] As an addition or alternative, during a handover of a UE (such as a specific UE indicated by the first message or a UE selected by RAN node 210), RAN node 210 may be the source gNB for the handover, and RAN node 210 may further transmit some or all of the information in the first message to the target RAN node (e.g., the target gNB) via, for example, the X1 interface.

[0158] During process 400, RAN node 210 sends a second message to at least one data acquisition entity (including data acquisition entity 230) in 440, the second message may contain some or all of the physical layer measurements. Specifically, the second message may contain the collected physical layer measurements.

[0159] In some implementations, the second message may be a data acquisition report message, and the second message may be transmitted between the RAN node 210 and the data acquisition entity 230 via a direct interface or an E2E protocol.

[0160] In some implementations, the second message may contain the same ID as the one included in the first message (the data collection request message).

[0161] In some exemplary embodiments, the collected physical layer measurements in the second message may be transmitted in a container of an encoded format. In some exemplary embodiments, UE identification information may be removed from the collected physical layer measurements in the second message. For example, RAN node 210 may remove UE identification information from the data acquisition report message.

[0162] In some implementations, the collected physical layer measurements may be grouped into multiple groups, and at least one of these groups may be included in a second message and sent to the data collection entity 230.

[0163] In some exemplary embodiments, the grouping operation may be in a specific format, such as a UE unit format or a feature unit format. The UE unit format may also be called a UE central format, and the feature unit format may also be called a feature central format. In some examples, if the first message contains a format instruction, the indicated format may be used by the RAN node 210.

[0164] In some implementations, collected physical layer measurements may be grouped into multiple groups corresponding to multiple UEs. In some embodiments, a UE-centric format may be used, for example, where physical layer measurements collected from the same UE are grouped and associated with a unique ID / index. For example, the unique ID / index may not be any UE-specific ID used in the network. In some examples, timestamps of the measurements in the group may be included in a second message, for example, where measurements in a group may be determined by the same UE at different points in time.

[0165] In some examples, if there is a different RAN node, it is acceptable to assign different IDs / indexes to the same UE, meaning that different RAN nodes may assign different IDs / indexes to the same UE under mobility scenarios.

[0166] A group of collected physical layer measurements corresponding to a specific UE may be useful for training time-predictive AI / ML models, for example, a sequence of physical layer measurements taken by the same UE at different points in time can be used as model input.

[0167] In some implementations, collected physical layer measurements may be grouped into multiple groups corresponding to multiple features. In some embodiments, multiple features may be associated with multiple attributes of the physical layer measurements. For example, features may be a specific beam, a specific beamset, a specific location (e.g., ground truth location), etc.

[0168] In some embodiments, a feature-centered approach may be used. For example, collected physical layer measurements from the same beamset B may be grouped together without further distinction being needed as to whether those physical layer measurements originated from different UEs or whether those physical layer measurements were measured at different time points. In some examples, the feature-centered approach may be useful in the case of spatial domain prediction, where physical layer measurements from a particular beamset B are used as input to predict physical layer measurements from a particular beamset A at the same time point.

[0169] As another example, in fingerprint-based positioning, a combination of physical layer measurements and ground truth location is used for training.

[0170] In some embodiments, when a feature-centric style is used, UE information or time information is not included in the second message; for example, UE information or time information may not be necessary.

[0171] As a concrete example, assuming that the data acquisition entity 230 is an LMF, the LMF can configure RAN node 210 to collect all DL CSI measurements for several SSBs, along with associated ground truth location information, from possible UEs within a specific cell via a data acquisition request message using the NRPPa protocol. Furthermore, the LMF may further specify a duration (e.g., the next hour) and periodicity (every minute), which may instruct RAN node 210 to report the collected measurements periodically (every minute) over the next hour. In this case, RAN node 210 can configure possible UEs within a specific cell to measure and report CSI measurements for several SSBs, and RAN node 210 can further report to the LMF periodically within the duration using data acquisition report messages.

[0172] In process 400, the physical layer measurements in the second message may be used for further purposes. In some implementations, the data acquisition entity 230 uses or provides the physical layer measurements in 450.

[0173] In some embodiments, if the data acquisition entity 230 can be used as a model training entity, the data acquisition entity 230 may further train the AI / ML model using physical layer measurements, for example, by constructing a training set based on physical layer measurements.

[0174] In some embodiments, if there is another model training entity, the data acquisition entity 230 may further provide (e.g., transmit) physical layer measurements to the model training entity. For example, the model training entity may further train the AI / ML model by using the physical layer measurements.

[0175] According to some embodiments discussed with reference to Figure 4, an existing interface or protocol between the data acquisition entity and the RAN node may be used for procedures to request and report physical layer measurements, so that the data acquisition entity may obtain physical layer measurements, and thus model training may be successfully performed.

[0176] Figure 5 shows an example of a device 500 suitable for implementing an embodiment of the present disclosure. Device 500 may be an example of a RAN node as described herein. Device 500 may support wireless communication with a RAN node 210, a first entity 220, a data acquisition entity 230, or any combination thereof. Device 500 may include components for bidirectional communication, including components for transmitting and receiving communications, such as a processor 502, memory 504, transceiver 506, and optionally an I / O controller 508. These components may communicate electrically via one or more interfaces (e.g., buses) or otherwise be coupled (e.g., operably, communicatively, functionally, electronically, electrically).

[0177] The processor 502, memory 504, transceiver 506, or various combinations thereof or various components thereof may be examples of means for carrying out various aspects of the disclosure described herein. For example, the processor 502, memory 504, transceiver 506, or various combinations thereof or components thereof may support a method for carrying out one or more of the operations described herein.

[0178] In some implementations, the processor 502, memory 504, transceiver 506, or various combinations or components thereof, may be implemented in hardware (for example, in a communication management circuit configuration). The hardware may include a processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, which may be configured as means for performing the functions described herein or otherwise supporting such means. In some implementations, the processor 502 and the memory 504 coupled with the processor 502 may be configured to perform one or more of the functions described herein (for example, the processor 502 executes instructions stored in the memory 504).

[0179] For example, the processor 502 may support wireless communication in device 500 according to the examples disclosed herein. The processor 502 may be configured to operate to support means for sending a request to a first RAN node to add a direct route between the first RAN node and the UE, wherein an indirect route exists between the second RAN node and the UE via a relay UE, and means for receiving a response from the first RAN node that includes at least a first configuration of the direct route. The processor 502 may be configured to operate to support means for receiving a request from a second RAN node to add a direct route between the first RAN node and the UE, wherein an indirect route exists between the second RAN node and the UE via a relay UE, and means for sending a response to the second RAN node that includes at least a first configuration of the direct route. The processor 502 may be configured to operate in a manner that supports means for sending a request to a second RAN node for a PCell change or for releasing an indirect path, wherein there is a direct path between the first RAN node and the UE, and an indirect path between the second RAN node and the UE via a relay UE, and means for receiving a response from the second RAN node to accept or reject the request. The processor 502 may be configured to operate in a manner that supports means for receiving a request from a first RAN node for a PCell change or for releasing an indirect path, wherein there is a direct path between the first RAN node and the UE, and an indirect path between the second RAN node and the UE via a relay UE, and means for sending a response to the first RAN node to accept or reject the request.

[0180] The processor 502 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some implementations, the processor 502 may be configured to operate a memory array using a memory controller. In some implementations, the memory controller may be integrated into the processor 502. The processor 502 may be configured to execute computer-readable instructions stored in memory (e.g., memory 504) to cause device 500 to perform various functions of this disclosure.

[0181] Memory 504 may include random access memory (RAM) and read-only memory (ROM). Memory 504 may store computer-readable computer-executable code, which, when executed by processor 502, causes device 500 to perform various functions described herein. The code may be stored in a non-temporary computer-readable medium, such as system memory or another type of memory. In some implementations, the code may not be directly executable by processor 502, but (for example, when compiled and executed) can cause the computer to perform the functions described herein. In some implementations, memory 504 may include a basic input / output system (BIOS) that may control basic hardware or software operations, in particular, interactions with peripheral components or peripheral devices.

[0182] The I / O controller 508 can manage input and output signals for device 500. The I / O controller 508 can also manage peripheral devices not integrated into device 500. In some implementations, the I / O controller 508 may represent physical connections or ports to external peripheral devices. In some implementations, the I / O controller 508 may use an operating system such as iOS®, ANDROID®, MS-WINDOWS®, OS / 2®, UNIX®, LINUX®, or another known operating system. In some implementations, the I / O controller 508 may be implemented as part of a processor, such as processor 502. In some implementations, a user may interact with device 500 via the I / O controller 508 or via hardware components controlled by the I / O controller 508.

[0183] In some implementations, device 500 may include a single antenna 510. However, in other implementations, device 500 may have two or more antennas 510 (e.g., multiple antennas), including multiple antenna panels or antenna arrays, and these antennas may be capable of simultaneously transmitting or receiving multiple wireless transmissions. Transceiver 506 may communicate bidirectionally with one or more antennas 510, wired or wireless links, as described herein. For example, transceiver 506 may represent a wireless transceiver and communicate bidirectionally with another wireless transceiver. Transceiver 506 may include a modem for demodulating packets received from one or more antennas 510, and for modulating packets and providing the modulated packets to one or more antennas 510 for transmission. Transceiver 506 may include one or more transmit chains, one or more receive chains, or a combination thereof.

[0184] The transmit chain may be configured to generate and transmit signals (e.g., control information, data, packets). The transmit chain may include at least one modulator for modulating data into a carrier signal and preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques, such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes such as phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmit chain may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over a wireless medium. The transmit chain may also include one or more antennas 510 for transmitting the amplified signal to the air or a wireless medium.

[0185] The receiving chain may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiving chain may include one or more antennas 510 for receiving signals over air or a wireless medium. The receiving chain may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiving chain may include at least one demodulator configured to demodulate the received signal and to obtain transmitted data by inverting the modulation technique applied during the transmission of the signal. The receiving chain may include at least one decoder for decoding the demodulated signal to receive transmitted data.

[0186] Figure 6 shows an example of a processor 600 suitable for implementing some embodiments of the present disclosure. The processor 600 may be an example of a processor configured to perform various operations according to the examples described herein. The processor 600 may include a controller 602 configured to perform various operations according to the examples described herein. The processor 600 may optionally include at least one memory 604, such as an L1 / L2 / L3 cache. Additionally or alternatively, the processor 600 may optionally include one or more arithmetic logic units (ALUs) 606. One or more of these components may communicate telecommunications via one or more interfaces (e.g., buses) or otherwise be coupled (e.g., operationally, communicatively, functionally, electronically, electrically).

[0187] The processor 600 may be a processor chipset, which may include a protocol stack (e.g., a software stack) that is executed by the processor chipset to perform various operations as described herein (e.g., receive, acquire, retrieve, transmit, output, forward, store, decide, identify, access, write, read). The processor chipset may include one or more cores, one or more caches (e.g., the processor chipset (e.g., processor 600) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase-change memory (PCM), etc., which are local to or contained therein)).

[0188] The controller 602 may be configured to manage and coordinate various operations of the processor 600 (e.g., signaling, receiving, acquiring, retrieving, transmitting, outputting, forwarding, storing, deciding, identifying, accessing, writing, and reading) so that the processor 600 supports various operations as described herein. For example, the controller 602 may act as a control unit for the processor 600 and generate control signals that manage the operation of various components of the processor 600. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating the timing of operations.

[0189] The controller 602 may be configured to fetch instructions from memory 604 (e.g., acquire, retrieve, receive) and to determine subsequent instructions to be executed so that the processor 600 can support various operations as illustrated herein. The controller 602 may be configured to track the memory address of the instruction associated with memory 604. The controller 602 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 602 may be configured to translate instructions and to determine control signals to be output to other components of the processor 600 so that the processor 600 can support various operations as illustrated herein. Additionally or alternatively, the controller 602 may be configured to manage the flow of data within the processor 600. The controller 602 may be configured to control the transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 600.

[0190] Memory 604 may include one or more caches (for example, memory local to or contained within the processor 600), or other memory such as RAM, ROM, DRAM, SDRAM, SRAM, MRAM, or flash memory. In some implementations, memory 604 may be located within or on the processor chipset (for example, local to the processor 600). In some other implementations, memory 604 may be located outside the processor chipset (for example, remote to the processor 600).

[0191] Memory 604 may store computer-readable computer-executable code, which, when executed by the processor 600, causes the processor 600 to perform various functions described herein. The code may be stored in a non-temporary computer-readable medium, such as system memory or another type of memory. The controller 602 and / or the processor 600 may be configured to execute computer-readable instructions stored in memory 604 for causing the processor 600 to perform various functions. For example, the processor 600 and / or the controller 602 may be coupled to or with memory 604, and the processor 600, controller 602, and memory 604 may be configured to perform various functions described herein. In some examples, the processor 600 may include multiple processors, and memory 604 may include multiple memories. One or more of the multiple processors may be coupled to one or more of the multiple memories, and they may be configured individually or collectively to perform various functions described herein.

[0192] One or more ALU606s may be configured to support various operations as illustrated in the examples described herein. In some implementations, one or more ALU606s may be located within or on a processor chipset (e.g., processor 600). In some other implementations, one or more ALU606s may be located outside the processor chipset (e.g., processor 600). One or more ALU606s may perform one or more operations on data, such as addition, subtraction, multiplication, and division. For example, one or more ALU606s may receive input operands and operation codes, which determine the operation to be performed. One or more ALU606s may consist of various logic and arithmetic circuits, including adders, subtractors, shifters, and logic gates, for processing and handling data according to the operations. As an addition or alternative, one or more ALU606s may support logical operations such as AND, OR, exclusive OR (XOR), not-OR (NOR), and not-AND (NAND), enabling one or more ALU606s to handle conditional operations, comparisons, and bitwise operations.

[0193] The processor 600 may support wireless communication as illustrated herein. The processor 600 may be configured or capable of supporting means for operation as described in some embodiments of this disclosure.

[0194] Figure 7 shows a flowchart of Method 700 as performed by a RAN node according to an aspect of this disclosure. The operation of Method 700 may be implemented by a device or its components as described herein. For example, the operation of Method 700 may be performed by the RAN node 210 in Figure 2. In some implementations, the device may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0195] In 710, the method may include the step of receiving a first message from a first entity instructing a RAN node to collect physical layer measurements and report them to at least one data acquisition entity. The operation of 710 may be carried out according to the examples described herein. In some implementations, the operation of 710 may be carried out by a RAN node 210 as described with reference to Figure 2.

[0196] In 720, the method may include the step of collecting physical layer measurements based on a first message. The operation of 720 may be carried out according to the examples described herein. In some implementations, the operation of 720 may be carried out by a RAN node 210 as described with reference to Figure 2.

[0197] In 730, the method may include the step of sending a second message containing some or all of the physical layer measurements to at least one data acquisition entity, the physical layer measurements of which are used for model training. The operation of 730 may be carried out according to the examples described herein. In some implementations, the operation of 730 may be carried out by the RAN node 210 described with reference to Figure 2.

[0198] Figure 8 shows a flowchart of Method 800 as performed by a first entity according to an aspect of this disclosure. The operation of Method 800 may be performed by a device or its components, as described herein. For example, the operation of Method 800 may be performed by the first entity 220 in Figure 2. In some implementations, the device may execute a set of instructions for controlling the functional elements of the device to perform the described functions. In addition or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0199] In 810, the method may include the step of acquiring information associated with physical layer measurements for model training. The operation of 810 may be carried out according to the examples described herein. In some implementations, the operation of 810 may be carried out by the first entity 220 described with reference to Figure 2.

[0200] In 820, the method may include sending a first message to a RAN node instructing the RAN node to collect physical layer measurements and report them to at least one data acquisition entity. The operation of 820 may be carried out according to the examples described herein. In some implementations, the operation of 820 may be carried out by a first entity 220 described with reference to Figure 2.

[0201] Figure 9 shows a flowchart of Method 900 as performed by a data acquisition entity according to an aspect of this disclosure. The operation of Method 900 may be performed by a device or its components, as described herein. For example, the operation of Method 900 may be performed by the data acquisition entity 230 in Figure 2. In some implementations, the device may execute a set of instructions to control the functional elements of the device to perform the described functions. In addition or alternatively, the device may perform aspects of the described functions using dedicated hardware.

[0202] In 910, the method may include the step of receiving a second message from a RAN node containing some or all of the physical layer measurements. The operation of 910 may be carried out according to the examples described herein. In some implementations, the operation of 910 may be carried out by a data acquisition entity 230 as described with reference to Figure 2.

[0203] In 920, the method may include a step of using some or all of the physical layer measurements or providing them to the model training entity. The operation of 920 may be carried out according to the examples described herein. In some implementations, the operation of 920 may be carried out by the data acquisition entity 230 described with reference to Figure 2.

[0204] It should be noted that the methods described herein represent possible implementations, that the operations and steps may be rearranged or possibly modified, and that other implementations are possible. Furthermore, two or more embodiments of these methods may be combined.

[0205] The various exemplary blocks and components described in this disclosure may be implemented or carried out using general-purpose processors, DSPs, ASICs, CPUs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor may be a microprocessor, but alternatively, the processor may be any processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors working with a DSP core, or any other such configuration).

[0206] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or a combination thereof. When implemented in software executed by a processor, the functions may be stored in or transmitted through a computer-readable medium as one or more instructions or codes. Other examples and implementations fall within the scope of this disclosure and the accompanying claims. For example, due to the nature of the software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination thereof. The features implementing the functions may also be physically located in various locations, including the distribution of parts of the functions so that they are implemented in various physical locations.

[0207] Computer-readable media include both non-temporary computer storage media and communication media, including any media that facilitate the transfer of computer programs from one location to another. Non-temporary storage media can be any available media that can be accessed by a general-purpose or dedicated computer. For example, non-temporary computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-temporary media that can be used to carry or store desired program code means in the form of instructions or data structures, and can be accessed by a general-purpose or dedicated computer or a general-purpose or dedicated processor.

[0208] As used herein, including in the claims, the article “a” preceding an element is unrestricted and is understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” used in a list of items (for example, a list of items ending with a phrase such as “at least one of,” “one or more of,” or “one or both of”) indicates an inclusive list, for example, such that a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” should not be interpreted as a reference to a closed set of conditions. For example, an exemplary step described as “based on condition A” may be based on both condition A and condition B without departing from the scope of this disclosure. In other words, as used herein, the phrase “based on” should be construed in the same way as the phrase “at least partially based on.” Furthermore, as used herein, including in the claims, “set” may include one or more elements.

[0209] The descriptions herein are provided to enable those skilled in the art to create or use this disclosure. Various modifications of this disclosure will become apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the scope of this disclosure. Accordingly, this disclosure should be given the broadest scope that is consistent with the principles and novel features disclosed herein, and is not limited to the examples and designs described herein. [Explanation of Symbols]

[0210] 100 Wireless Communication Systems 102 Network Entities 104 UE 106 Core Network 108 Packet Data Network 110 Communication Link 112 Geographic Coverage Areas 114 Communication Link 116 Backhaul link, communication link 118 Application Server 200 Communication Networks 210 RANNode 220 First Entity 230 Data Collection Entities 500 devices 502 Processors 504 memory 506 Transceiver 508 I / O Controller 600 Processors 602 Controller 604 memory 606 ALU

Claims

1. At least one memory, The at least one processor coupled with the at least one memory and A wireless access network (RAN) node comprising, the at least one processor of the RAN node, Receiving a first message from a first entity instructing the RAN node to collect physical layer measurements and report them to at least one data acquisition entity, Collecting the physical layer measurements based on the first message, Sending a second message containing some or all of the aforementioned physical layer measurements to the at least one data acquisition entity, wherein some or all of the aforementioned physical layer measurements are used for model training. A RAN node configured to perform the following actions.

2. The RAN node according to claim 1, wherein the first entity comprises an access and mobility management function (AMF), the first message includes a trace start message, and the trace start message includes an information element (IE) associated with a data acquisition configuration that instructs to collect and report physical layer measurements.

3. The RAN node according to claim 2, wherein the IE associated with the data acquisition configuration is included in a drive test minimization (MDT) configuration IE.

4. The first entity comprises an Operations Management and Maintenance (OAM) system, and the at least one processor provides the RAN node, The RAN node according to claim 1, further configured to send cell traffic trace messages to the AMF.

5. The cell traffic trace message is, See trace recording session. Trace reference, Serving cell's cell global identity (CGI), or At least one address of the aforementioned at least one data collection entity, A RAN node according to claim 4, comprising one of the following.

6. The RAN node according to claim 1, wherein the first entity is one of the at least one data collection entities, the first message includes a data collection request message, and the first message is transmitted between the RAN node and the first entity by an interface and / or by an end-to-end protocol.

7. The RAN node according to claim 6, wherein the data acquisition request message includes a partial support instruction indicating that some of the physical layer measurements are required.

8. The aforementioned physical layer measurement values ​​are Grand Truth Channel State Information (CSI) in scalar quantization and / or codebook-based quantization, A pair of first and second pieces of information, wherein the first piece of information includes a raw channel or eigenvector, and the second piece of information includes a latent space vector with or without quantization, A pair of third and fourth pieces of information, wherein the third piece of information includes a quantized latent space vector, and the fourth piece of information includes a target CSI to be reconstructed as a proxy model output. One or more CSIs including a raw channel matrix, pre-coded matrix indicator (PMI), or eigenvectors, One or more Layer 1 reference signal received power (L1-RSRP) measurements based on set B or a subset of set B, wherein set B includes a set of beams for predictive input, L1-RSRP measurements, One or more L1-RSRP measurements based on set A or a subset of set A, wherein set A includes a set of beams for predictive output, One or more L1-RSRP measurements based on Set A or a subset of Set A and the corresponding beam indicator. The top k beam indicators, Channel impulse response of the reference signal, Power delay profile of the reference signal, Reference signal delay profile, RSRP of the reference signal, Reference signal reception quality (RSRQ), The reference signal time difference (RSTD) of the reference signal, or Ground truth location coordinates, A RAN node according to any one of claims 1 to 7, comprising one of the following.

9. The first message includes a request for support information associated with the physical layer measurements to be collected, the support information being: Timestamp, scenario, Cell identity, Physical layer configuration, Quality instructions, or Line of sight or line of sight, A RAN node according to any one of claims 1 to 8, comprising one of the following.

10. The first message mentioned above is, At least one criterion for data collection, Duration for the aforementioned data collection, The periodicity for the aforementioned data collection, An event to trigger the aforementioned data collection, or Instructions for the format of the second message, A RAN node according to any one of claims 1 to 9, comprising one of the following.

11. The aforementioned at least one criterion is, Required scenario, Required physical layer configuration, Required quality instructions, Required line of sight or non-line of sight, Area of ​​involvement, Involved frequency, Involved cells, Involved beam, Involved User Equipment (UE) type, A RAN node according to claim 10, comprising one of the following.

12. The RAN node according to any one of claims 1 to 11, wherein the first message includes at least one address of the at least one data collection entity.

13. The RAN node according to any one of claims 1 to 12, wherein the part or all of the physical layer measurements in the second message are transmitted in a container of an encoded format.

14. The RAN node according to any one of claims 1 to 13, wherein the UE identification information is removed from the part or all of the physical layer measurements in the second message.

15. The RAN node according to any one of claims 1 to 14, wherein some or all of the physical layer measurements in the second message are grouped into a plurality of groups corresponding to a plurality of UEs, and each of the plurality of groups has a unique index.

16. The RAN node according to any one of claims 1 to 14, wherein the part or all of the physical layer measurements in the second message are grouped into groups corresponding to a plurality of features, and each feature is associated with an attribute of the physical layer measurement.

17. The RAN node is a RAN central unit (CU), and the at least one processor is provided to the RAN node, A RAN node according to any one of claims 1 to 16, further configured to transmit some or all of the information in the first message to a RAN distributed unit (DU).

18. The RAN node is a source RAN node for a specific UE during handover, and the at least one processor is connected to the RAN node. A RAN node according to any one of claims 1 to 16, further configured to transmit some or all of the information in the first message to a target RAN node.

19. At least one memory, The at least one processor coupled with the at least one memory and A first entity comprising, wherein the at least one processor provides to the first entity, To acquire information associated with physical layer measurements for model training, Sending a first message to a Wireless Access Network (RAN) node instructing the RAN node to collect the physical layer measurements and report them to at least one data acquisition entity. A first entity configured to perform the following action.

20. At least one memory, A data acquisition entity comprising at least one memory and at least one processor coupled thereto, wherein the at least one processor provides the data acquisition entity with Receiving a second message from a Wireless Access Network (RAN) node, which includes some or all of the physical layer measurements, Using some or all of the aforementioned physical layer measurements, or providing them to the model training entity. A data collection entity configured to perform the following actions.

Images