Method used for wireless communication, and apparatus

Abstract

Disclosed in the present application are a method for wireless communication, and an apparatus. The method comprises: a first node receiving a plurality of reference signals, wherein the plurality of reference signals comprise a first reference signal; and determining a target reference signal on the basis of a plurality of reception qualities, wherein the target reference signal is one of the plurality of reference signals. The plurality of reception qualities are respectively reception qualities of the plurality of reference signals, and a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; among the plurality of reception qualities, only the computing of the first reception quality comprises coherent combination of reception signals from a plurality of antenna ports. The described method has the advantages of improving the receiving performance of reference signals, or improving the transmission efficiency, and enhancing the overall performance of systems.

Description

Methods and apparatus used for wireless communication

[0001] This application claims priority to Chinese Patent Application No. 202411577760.9, filed on November 5, 2024, entitled "Method and Apparatus for Wireless Communication", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to schemes and apparatus related to reference signals in wireless communication systems. Background Technology

[0003] In traditional wireless communication, user equipment (UE) reports various auxiliary information obtained through measurements of downlink signals and / or channels, such as channel information, beam management-related auxiliary information, and positioning-related auxiliary information. Channel information includes, but is not limited to, one or more of the following: Channel State Information Reference Signal Resource Indicator (CSI-RS, CRI), Rank Indicator (RI), Precoding Matrix Indicator (PMI), or Channel Quality Indicator (CQI). The UE can use this information to select appropriate transmission parameters or report this information. The network equipment selects appropriate transmission parameters for the UE based on the reported information, such as the cell to be used, modulation and coding scheme (MCS), transmitted precoding matrix indicator (TPMI), and transmission configuration indication (TCI). Furthermore, UE reporting can be used to optimize network parameters, such as improving cell coverage and switching base stations on / off based on the UE's location.

[0004] In traditional cellular communication, the antenna port is used to describe reference signal resources; unlike the physical antenna, the antenna port can be considered a virtualization / overlay operation of the physical antenna.

[0005] With the adoption of new technologies, the increase in the number of antennas, the diversification of application scenarios, and the increasing demands on system performance, traditional measurement and reporting methods incur significant redundancy overhead. Therefore, in NR R (release) 18, research on artificial intelligence (AI) / machine learning (ML) technologies was initiated to explore their impact on system performance and design. Compared to traditional processing methods, AI / ML offers advantages such as training-based and deployment-required features. According to the 3GPP standard TS38.300, AI / ML models and algorithms exceed the scope of 3GPP (3rd Generation Partnership Project). Summary of the Invention

[0006] Research has revealed that when AI / ML functions are introduced, existing measurement mechanisms, reporting mechanisms, and related configuration signaling may not be able to meet the needs of AI / ML.

[0007] To address the aforementioned problems, this application discloses a solution. It should be noted that while many embodiments of this application are geared towards AI / ML, this application is also applicable to other solutions, such as traditional channel information calculation or reporting schemes. Although the specification of this application involves descriptions of some AI / ML models and algorithms, those skilled in the art will understand that these descriptions are not essential or irreplaceable for solutions related to wireless cellular communication. Furthermore, adopting a unified solution for different scenarios (including but not limited to AI / ML-based solutions and traditional CSI reporting schemes) helps reduce hardware complexity and cost. Where there is no conflict, the embodiments and features in the embodiments of the first node of this application can be applied to the second node, and vice versa. Where there is no conflict, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0008] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS38 series.

[0009] As an example, the interpretation of the terms in this application is based on the definitions in the 3GPP specification protocol TS28 series.

[0010] This application discloses a method for use in a first node of wireless communication, comprising: receiving a plurality of reference signals, the plurality of reference signals including a first reference signal; determining a target reference signal based on a plurality of reception qualities, the target reference signal being one of the plurality of reference signals; wherein the plurality of reception qualities are reception qualities of the plurality of reference signals, and a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0011] As an example, the above method utilizes coherent combining operations to obtain more accurate channel reception quality, thereby improving the accuracy of the first reception quality calculation.

[0012] As an example, the above method utilizes coherent combining operations to obtain more accurate channel reception quality, thereby improving the accuracy of determining the target reference signal.

[0013] As an example, the above method avoids the sender of the first reference signal performing coherent combining, thus reducing air interface overhead.

[0014] As an example, multiple reference signals are transmitted on the same cell.

[0015] Specifically, according to one aspect of this application, it includes: generating first channel information; wherein coherent combining of received signals from multiple antenna ports is based on the first channel information.

[0016] As an example, the above method avoids the first node reporting the first channel information to the senders of multiple reference signals, thus reducing air interface overhead.

[0017] As an example, the above method avoids the first node randomly selecting the coherent merging vector, thereby improving the reception performance of the first reference signal.

[0018] Specifically, according to one aspect of this application, for any one of the plurality of reference signals other than the first reference signal, only one antenna port is used for transmission.

[0019] Specifically, according to one aspect of this application, for any one of the plurality of reference signals other than the first reference signal, only two antenna ports are used for transmission.

[0020] As an example, the above two aspects reduce the air interface overhead caused by the reference signal and improve transmission efficiency.

[0021] Specifically, according to one aspect of this application, the above method includes: sending a first signaling signal, the first signaling signaling a target reference signal.

[0022] The above method helps nodes on both sides of the communication to keep their understanding of the current channel state synchronized.

[0023] Specifically, according to one aspect of this application, the above method includes: a first processor performing ML training based on a target precoding vector; wherein the target reference signal is different from a first reference signal; any reference signal other than the first reference signal among a plurality of reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0024] As an example, the above method improves the reception performance of any reference signal other than the first reference signal.

[0025] As an example, the above method allows the sender to adjust the precoding vector of any reference signal other than the first reference signal.

[0026] Specifically, according to one aspect of this application, the method includes: receiving a second signaling; wherein the second signaling is an associated precoding vector indicated by any of a plurality of reference signals other than a first reference signal.

[0027] As an example, the above method provides configuration flexibility.

[0028] As an example, the second signaling is higher-layer signaling.

[0029] Compared to the association between dynamic indication reference signals and precoded vectors, the above embodiments reduce air interface overhead.

[0030] Specifically, according to one aspect of this application, the target reference signal is a reference signal among a plurality of reference signals that satisfies a first set of conditions other than the first reference signal, the first set of conditions including the target reference signal having the best value among a plurality of reception qualities.

[0031] Specifically, according to one aspect of this application, any of the multiple reception qualities other than the first reception quality is the reference signal received power (RSRP).

[0032] Specifically, according to one aspect of this application, any one of the multiple reception qualities is RSRP.

[0033] In the prior art, RSRP calculation does not include coherent combining. The above-mentioned aspects specifically extend the definition of RSRP, that is, the first reception quality is also included in RSRP. This extension can lead to minor standardization changes while having good compatibility.

[0034] The two aspects mentioned above have good compatibility, and RSRP can more intuitively reflect the channel quality and provide better performance.

[0035] This application discloses a method for use in a second node of wireless communication, comprising: transmitting a plurality of reference signals, the plurality of reference signals including a first reference signal; receiving a first signaling, the first signaling indicating a target reference signal; wherein the target reference signal is one of the plurality of reference signals, the determination of the target reference signal depends on a plurality of reception qualities; the plurality of reception qualities are reception qualities of the plurality of reference signals, a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0036] Specifically, according to one aspect of this application, the above method includes: performing ML training based on a target precoding vector; wherein the target reference signal is different from a first reference signal; any reference signal other than the first reference signal among a plurality of reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0037] Typically, precoding vectors are used for precoding associated reference signals or for beamforming.

[0038] Specifically, according to one aspect of this application, for any one of the plurality of reference signals other than the first reference signal, only one antenna port is used for transmission.

[0039] Specifically, according to one aspect of this application, it includes: transmitting a second signaling; wherein the second signaling indicates an associated precoding vector for any of a plurality of reference signals other than a first reference signal.

[0040] Specifically, according to one aspect of this application, the target reference signal is a reference signal among a plurality of reference signals that satisfies a first set of conditions other than the first reference signal, the first set of conditions including the target reference signal having the best value among a plurality of reception qualities.

[0041] Specifically, according to one aspect of this application, any of the multiple reception qualities other than the first reception quality is RSRP.

[0042] Specifically, according to one aspect of this application, any one of the multiple reception qualities is RSRP.

[0043] This application discloses a first node for wireless communication, comprising: a first receiver for receiving a plurality of reference signals, the plurality of reference signals including a first reference signal; and a first processor for determining a target reference signal based on a plurality of reception qualities, the target reference signal being one of the plurality of reference signals; wherein the plurality of reception qualities are reception qualities of the plurality of reference signals, and a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0044] This application discloses a second node used for wireless communication, comprising: a first transmitter for transmitting a plurality of reference signals, the plurality of reference signals including a first reference signal; and a second processor for receiving a first signaling instruction indicating a target reference signal; wherein the target reference signal is one of the plurality of reference signals, and the determination of the target reference signal depends on a plurality of reception qualities; the plurality of reception qualities are the reception qualities of the plurality of reference signals, and a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0045] As an example, compared with conventional solutions, this application has the following advantages:

[0046] Higher accuracy and real-time performance of channel information, resulting in enhanced overall system performance;

[0047] Lower air interface overhead;

[0048] More flexible and diverse input information;

[0049] Better flexibility and adaptability;

[0050] Enhanced reliability and robustness. Attached Figure Description

[0051] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0052] Figure 1 illustrates a flowchart of determining a target reference signal according to an embodiment of this application;

[0053] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0054] Figure 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application;

[0055] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0056] Figure 5 illustrates a flowchart of the transmission between a first node N1 and a second node N2 according to an embodiment of this application;

[0057] Figure 6 shows a schematic diagram of a time subunit according to an embodiment of this application;

[0058] Figure 7 illustrates a flowchart of transmitting a first signaling according to an embodiment of this application;

[0059] Figure 8 illustrates a schematic diagram of the deployment of AI / ML functionality in a radio access network (RAN) domain according to an embodiment of this application;

[0060] Figure 9 shows a schematic diagram of the AI / ML function deployment of a UE according to an embodiment of this application;

[0061] Figure 10 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0062] Figure 11 shows a flowchart based on artificial intelligence or machine learning according to an embodiment of this application;

[0063] Figure 12 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0064] Figure 13 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0065] The technical solutions of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Considering performance, flexibility, complexity, overhead, and compatibility, those skilled in the art are motivated to flexibly combine the embodiments in different drawings without conflict, including but not limited to the embodiments in Figure 1 and the embodiments in Figures 5-12, the embodiments in Figure 5 and the embodiments in Figures 6-12, etc.

[0066] Example 1

[0067] Example 1 illustrates a flowchart of determining a target reference signal according to an embodiment of this application, as shown in Figure 1. In the first node 100 shown in Figure 1, each block represents a step.

[0068] In Example 1, the first node 100 receives multiple reference signals in step 101, including a first reference signal; and in step 102, a target reference signal is determined based on multiple reception qualities, wherein the target reference signal is one of the multiple reference signals.

[0069] In Example 1, the multiple reception qualities are the reception qualities of multiple reference signals, and the first reception quality among the multiple reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the multiple reception qualities includes coherent combining of the received signals from multiple antenna ports.

[0070] Typically, the number of antenna ports included in a multi-antenna port configuration is configurable.

[0071] As an example, the number of antenna ports included in the plurality of antenna ports is a positive integer power of 2.

[0072] As an example, the number of antenna ports included in the plurality of antenna ports does not exceed 128.

[0073] As an example, the first node 100 is a UE, and any one of the multiple reference signals is a downlink reference signal.

[0074] As one example, the downlink reference signal includes the synchronization signal physical broadcast channel block (SS / PBCH block, SSB).

[0075] As an example, the downlink reference signal includes a positioning reference signal (PRS).

[0076] As an example, the first node 100 is a UE, and any one of the multiple reference signals is a channel state information reference signal (CSI-RS).

[0077] As a sub-implementation of the above embodiments, any one of the multiple reference signals occupies one CSI-RS resource.

[0078] The above embodiments and sub-embodiments have good compatibility; however, in order to adapt to the performance requirements of future, such as 6G cellular networks, the multiple reference signals may also be other types of reference signals to better meet the performance requirements of AI / ML.

[0079] As one example, quasi co-location (QCL) is used for transmitting multiple reference signals between any two antenna ports.

[0080] As an example, the QCL type for any two antenna ports used to transmit multiple reference signals is type D.

[0081] As one example, the first reference signal is transmitted through multiple antenna ports.

[0082] As a sub-implementation of the above embodiments, the number of antenna ports used to transmit the first reference signal is configurable.

[0083] As one embodiment, any antenna port used to transmit the first reference signal is connected to any one of a plurality of antenna ports, namely, the antenna port QCL.

[0084] As an example, any one of the multiple reference signals occupies one RS resource.

[0085] As an example, multiple reference signals are transmitted in the same time unit, and the duration of the time unit does not exceed 10 milliseconds.

[0086] As a sub-implementation of the above embodiments, the time resources occupied by any two of the multiple reference signals are orthogonal (i.e., they do not overlap in time).

[0087] The above embodiments can reduce the variation in reception quality caused by channel changes, while allowing each reference signal to use an independent beamforming vector.

[0088] As an example, a time unit is a wireless frame.

[0089] As an example, a time unit is a subframe.

[0090] As an example, a time unit is a time slot.

[0091] As an example, any one of the multiple reception qualities is the reception power.

[0092] As an example, any one of the multiple reception qualities is the equivalent block error rate (BLER), which is obtained by mapping the received power.

[0093] As an example, any one of the multiple receive qualities is the reference signal received quality (RSRQ), which is obtained by mapping the received power.

[0094] As an example, the received power is RSRP.

[0095] As an example, RSRP is L1-RSRP (Layer 1-RSRP).

[0096] As an example, RSRP is L3-RSRP (Layer 3-RSRP).

[0097] As an example, in addition to the first reception quality, the other reception quality among the multiple reception qualities is RSRP.

[0098] As an example, the unit of any of the multiple reception qualities is watts (W).

[0099] As an example, the unit of any one of the multiple reception qualities is dBm (millidecibels).

[0100] Typically, the target reference signal is the reference signal corresponding to the best of several reception qualities.

[0101] As an example, when none of the multiple reception qualities are better than the first reception quality, the target reference signal is the first reference signal; when at least one of the multiple reception qualities is better than the first reception quality, the target reference signal is the reference signal corresponding to the reception quality that is better than the first reception quality.

[0102] As a sub-implementation of the above embodiments, the first node selects a target reference signal from reference signals with better reception quality than the first reference signal. This selection can be random or optimal, etc.

[0103] In the above embodiments, "better than" may have different meanings depending on the different types of reception quality.

[0104] As an example, the reception quality is the received power or RSRP, which is better than or higher than a first threshold.

[0105] As an example, the unit of the first threshold is dB.

[0106] As an example, the first threshold is a ratio.

[0107] As an example, the first threshold is configurable.

[0108] As an example, the reception quality is equivalent to BLER, better than or lower than, or better than or lower than a second threshold.

[0109] As an example, the second threshold is a ratio.

[0110] As an example, the second threshold is configurable.

[0111] The aforementioned first or second threshold ensures that the target reference signal is preferentially selected as the first reference signal, thus avoiding frequent reporting or training.

[0112] As an example, the specific implementation of determining the target reference signal based on multiple reception qualities is determined by the equipment manufacturer of the first node 100.

[0113] As one example, coherent combining includes phase adjustment and summing multiple received signals from multiple antenna ports after phase adjustment.

[0114] As one example, coherent combining includes a power normalization operation to ensure fairness.

[0115] The calculation of the first reception quality can be determined by the equipment manufacturer. A non-limiting implementation method is given below:

[0116] The first node 100 receives received signals (or reference signals) s1, s2, ..., s from multiple antenna ports on the same time-frequency resource block. L (L is the number of antenna ports), the coherently combined received signal on the same time-frequency resource block is:

[0117] a1s1 + a2s2 + ... + a L s L

[0118] Where a1, a2, ..., a L Each element in the array is a complex number; typically, the phase of a1 is fixed at 0.

[0119] A typical power normalization scheme is as follows:

[0120] To simplify the calculation, |a i | can also be simplified to

[0121] The first node 100 calculates the power of the received signal after coherent combining on the same time-frequency resource block. Furthermore, the first node 100 calculates the average power of the received signal after coherent combining on multiple time-frequency resource blocks to obtain the first reception quality.

[0122] As an example, multiple time-frequency resource blocks are frequency-division or time-division.

[0123] As an example, a time-frequency resource block is a resource block (RB).

[0124] As an example, a time-frequency resource block occupies 12 consecutive subcarriers in the frequency domain and belongs to one time slot in the time domain.

[0125] As an example, the received signal from each of the multiple antenna ports occupies one and only one resource element (RE) in a time-frequency resource block.

[0126] As an example, received signals from multiple antenna ports occupy and only occupy L REs in a time-frequency resource block.

[0127] Generally speaking, coherent combining of received signals from multiple antenna ports means that the amplitudes of the received signals are amplified, improving reception performance or transmission efficiency. However, the gain from coherent combining depends on obtaining accurate relative phases between the multiple antenna ports; generally, the more accurate the relative phase, the greater the gain.

[0128] As an example, a first reference signal is used to calculate the relative phase required for coherent merging.

[0129] Example 2

[0130] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0131] Figure 2 illustrates network architecture 200. Network architecture 200 is a 5G New Radio (NR) / Long-Term Evolution (LTE) / Long-Term Evolution Advanced (LTE-A) system, or a 5G+ network architecture, or a 6G network architecture, or a network architecture adopted in future evolutions of 3GPP; network architecture 200 may be referred to as 5GS (5G system) / Evolved Packet System (EPS), or network architecture 200 may be referred to as 6GS (6G system); network architecture 200 includes at least one of User Equipment (UE) 201, radio access network (RAN) 202, core network 210, home subscriber server (HSS) / unified data management (UDM) 220, and Internet service 230. Network architecture 200 can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown in Figure 2, network architecture 200 provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN includes node 203. The RAN may also include other nodes 204. Node 203 provides user and control plane protocol termination toward UE 201. Node 203 may be connected to other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. Node 203 may also be referred to as a base station, base transceiver station, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), TRP (transmitter-receiver node), or some other suitable term. Core network 210 is a 5G core network (5GC) / evolved packet core (EPC), or core network 210 is 6GC; node 203 provides UE 201 with an access point to core network 210. Examples of UE201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, non-terrestrial base station communications, satellite mobile communications, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband IoT devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices.Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, radio terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. Node 203 is connected to the core network 210 via the S1 / NG interface. The core network 210 includes a mobility management entity (MME) / authentication management field (AMF) / session management function (SMF) 211, other MMEs / AMFs / SMFs 214, a service gateway (S-GW) / user plane function (UPF) 212, and a packet data network gateway (P-GW) / UPF 213. The MME / AMF / SMF 211 is the control node that handles signaling between UE201 and the core network 210. In general, the MME / AMF / SMF211 provides bearer and connection management. All user Internet Protocol (IP) packets are transmitted through the S-GW / UPF212, which is itself connected to the P-GW / UPF213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF213 connects to Internet Service 230. Internet Service 230 includes operator-compliant Internet Protocol services, specifically including the Internet, intranet, IP multimedia subsystem (IMS), and packet switching services.

[0132] As an example, the first node includes UE201.

[0133] As an example, the second node includes node 203.

[0134] As an example, the wireless link between UE201 and node 203 includes a cellular link.

[0135] Example 3

[0136] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in Figure 3.

[0137] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and control plane according to this application, as shown in Figure 3. Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300. Figure 3 shows the radio protocol architecture for the control plane 300 between a first communication node device (UE, gNB, or RSU in V2X) and a second communication node device (gNB, UE, or RSU in V2X), or between two UEs, using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (physical layer) signal processing functions. Layer 1 will be referred to herein as PHY 301. Layer 2 (L2 layer) 305 is above PHY 301 and is responsible for the link between the first communication node device and the second communication node device, or between two UEs. Layer L2 305 includes a Medium Access Control (MAC) sublayer 302, a Radio Link Control (RLC) sublayer 303, and a Packet Data Convergence Protocol (PDCP) sublayer 304, which terminate at the second communication node device. PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. PDCP sublayer 304 also provides security through encrypted data packets and supports cross-cell mobility between the second communication node devices and the first communication node device. RLC sublayer 303 provides upper-layer packet segmentation and reassembly, retransmission of lost packets, and packet reordering to compensate for out-of-order reception due to HARQ. MAC sublayer 302 provides multiplexing between logical and transport channels. MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) within a cell among the first communication node devices. MAC sublayer 302 is also responsible for HARQ operations. The radio resource control (RRC) sublayer 306 in layer 3 (L3) of control plane 300 is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second communication node device and the first communication node device. The radio protocol architecture of user plane 350 includes layer 1 (L1) and layer 2 (L2). The radio protocol architecture for the first and second communication node devices in user plane 350 is substantially the same as the corresponding layers and sublayers in control plane 300 for physical layer 351, PDCP sublayer 354 in L2 layer 355, RLC sublayer 353 in L2 layer 355, and MAC sublayer 352 in L2 layer 355. However, PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead.The L2 layer 355 in the user plane 350 also includes a Service Data Adaptation Protocol (SDAP) sublayer 356, which is responsible for mapping between QoS streams and data radio bearers (DRBs) to support service diversity. Although not illustrated, the first communication node device may have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., a remote UE, server, etc.).

[0138] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node.

[0139] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node.

[0140] As an example, in this application, "higher layer" refers to a layer above the physical layer.

[0141] As an example, the first signaling is generated in RRC sublayer 306.

[0142] As an example, the first signaling is generated in PHY301 or PHY351.

[0143] As an example, the reference signal is generated in PHY301 or PHY351.

[0144] As an example, the second signal is generated in MAC sublayer 302 or MAC sublayer 352.

[0145] As an example, the second signaling is generated in RRC sublayer 306.

[0146] Example 4

[0147] Example 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of this application, as shown in Figure 4. Figure 4 is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0148] The first communication device 410 includes a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0149] The second communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0150] In the transmission from the first communication device 410 to the second communication device 450, at the first communication device 410, upper-layer data packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements L2 layer functionality. In the downlink (DL), the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ operation, retransmission of lost packets, and signaling to the second communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for the L1 layer (i.e., the physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and constellation mapping based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), and M-quadrature amplitude modulation (M-QAM). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, generating one or more... Parallel streams. Transmit processor 416 then maps each parallel stream to a subcarrier, multiplexes the modulated symbols with a reference signal (e.g., a pilot) in the time and / or frequency domains, and then uses an inverse fast Fourier transform (IFFT) to generate a physical channel carrying the time-domain O-stream. Multi-antenna transmit processor 471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by multi-antenna transmit processor 471 into an RF stream, which is then provided to different antennas 420.

[0151] In the transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 456. The receiver processor 456 and the multi-antenna receiver processor 458 implement various signal processing functions of the L1 layer. The multi-antenna receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 454. The receiver processor 456 uses a Fast Fourier Transform (FFT) to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 456, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 458 after multi-antenna detection to recover any parallel stream destined for the second communication device 450. Symbols on each parallel stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted by the first communication device 410 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of Layer 2 (L2). The controller / processor 459 may be associated with a memory 460 that stores program code and data. The memory 460 may be referred to as computer-readable media. In the DL (Layered Logic), the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer packets from the core network. The upper-layer packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 (L3) for L3 processing. The controller / processor 459 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0152] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper-layer data packets to the controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmission functions at the first communication device 410 described in the DL, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on the radio resource allocation of the first communication device 410, implementing L2 layer functions for the user plane and control plane. The controller / processor 459 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the first communication device 410. Transmit processor 468 performs modulation mapping and channel coding processing, while multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming processing. Subsequently, transmit processor 468 modulates the generated parallel stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 457, the stream is provided to different antennas 452 via transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by multi-antenna transmit processor 457 into a radio frequency symbol stream before providing it to antenna 452.

[0153] In the transmission from the second communication device 450 to the first communication device 410, the function at the first communication device 410 is similar to the receiving function at the second communication device 450 described in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 472 and the receiving processor 470. The receiving processor 470 and the multi-antenna receiving processor 472 jointly implement the L1 layer functions. The controller / processor 475 implements the L2 layer functions. The controller / processor 475 may be associated with a memory 476 that stores program code and data. The memory 476 may be referred to as computer-readable media. The controller / processor 475 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer data packets from the second communication device 450. The upper-layer data packets from the controller / processor 475 may be provided to the core network. The controller / processor 475 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0154] As one embodiment, the second communication device 450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second communication device 450 means at least: receiving a plurality of reference signals, the plurality of reference signals including a first reference signal; determining a target reference signal based on a plurality of reception qualities, the target reference signal being one of the plurality of reference signals; wherein the plurality of reception qualities are reception qualities of the plurality of reference signals, and a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0155] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: receiving a plurality of reference signals, the plurality of reference signals including a first reference signal; determining a target reference signal based on a plurality of reception qualities, the target reference signal being one of the plurality of reference signals; wherein the plurality of reception qualities are reception qualities of the plurality of reference signals, and a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0156] As one embodiment, the first communication device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The first communication device 410 means at least: transmitting a plurality of reference signals, the plurality of reference signals including a first reference signal; receiving a first signaling, the first signaling indicating a target reference signal; wherein the target reference signal is one of the plurality of reference signals, the determination of the target reference signal depends on a plurality of reception qualities; the plurality of reception qualities are respectively the reception qualities of the plurality of reference signals, the first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0157] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: transmitting a plurality of reference signals, the plurality of reference signals including a first reference signal; receiving a first signaling, the first signaling indicating a target reference signal; wherein the target reference signal is one of the plurality of reference signals, the determination of the target reference signal depends on a plurality of reception qualities; the plurality of reception qualities are reception qualities of the plurality of reference signals, a first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of received signals from a plurality of antenna ports.

[0158] As an example, the first node in this application includes a second communication device 450.

[0159] As an example, the second node in this application includes a first communication device 410.

[0160] As one embodiment, some or all of the following are used to receive multiple reference signals: {antenna 452, receiver 454, receiver processor 456, multi-antenna receiver processor 458, controller / processor 459, memory 460}; and some or all of the following are used to transmit multiple reference signals: {antenna 420, transmitter 418, transmitter processor 416, multi-antenna transmitter processor 471, controller / processor 475}.

[0161] As one embodiment, some or all of the following are used to determine the target reference signal based on multiple reception qualities: {multi-antenna receiver processor 458, controller / processor 459, memory 460, data source 467}.

[0162] As one embodiment, some or all of the following are used to receive the first signaling: {antenna 420, receiver 418, receiver processor 470, multi-antenna receiver processor 472, controller / processor 475, memory 476}; and some or all of the following are used to transmit the first signaling: {antenna 452, transmitter 454, transmitter processor 468, multi-antenna transmitter processor 457, controller / processor 459, memory 460, data source 467}.

[0163] Example 5

[0164] Example 5 illustrates a transmission flowchart between a first node N1 and a second node N2 according to an embodiment of this application, as shown in Figure 5. In Figure 5, the second node N1 and the first node N2 are communication nodes that transmit data via an air interface. In Figure 5, the second reference signal, step S102, the steps in block F0, the steps in block F1, and the steps in block F2 are all optional. It should be noted that the order of the steps in Figure 5 is only one specific implementation, and the order of the steps can be adjusted without conflict.

[0165] For the second node N2, a second signaling is sent in step S200; and multiple reference signals are sent in step S201, including a first reference signal.

[0166] For the first node N1, in step S100, a second signaling is received; in step S101, multiple reference signals are received, including a first reference signal; in step S103, a target reference signal is determined based on multiple reception qualities, and the target reference signal is one of the multiple reference signals.

[0167] In Example 5, the second signaling configures multiple reference signals; the multiple reception qualities are the reception qualities of the multiple reference signals, and the first reception quality among the multiple reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the multiple reception qualities includes coherent combining of the received signals from multiple antenna ports.

[0168] As an example, the first node N1 is the first node in this application, and the second node N2 is the second node in this application.

[0169] As one embodiment, the air interface between the second node U1 and the first node U2 includes the wireless interface between the base station equipment and the user equipment.

[0170] As an example, the second node N2 and the first node N1 are a base station and a user equipment, respectively.

[0171] As an example, both the second node N2 and the first node N1 are user equipment.

[0172] As an example, the second node N2 is the serving cell sustaining base station of the first node N1.

[0173] As an example, the first node N1 generates first channel information in step S102; wherein, the coherent combining of received signals from multiple antenna ports is based on the first channel information.

[0174] As one example, channel measurements of a first reference signal are used to generate first channel information, and the first reference signal is transmitted by multiple antenna ports.

[0175] In one embodiment, the second node N2 transmits the second reference signal in step S201, and the first node N1 receives the second reference signal in step S101; wherein, channel measurements of the second reference signal are used to generate first channel information, and the second reference signal is transmitted by multiple antenna ports.

[0176] It should be noted that if the second reference signal is located before multiple reference signals, the execution time of step S102 is not limited to after "receiving multiple reference signals" in step S101.

[0177] As those skilled in the art will understand, the first channel information represents the parameters of the wireless channel between multiple antenna ports and the first node N1. Its specific form depends on different receiver algorithms and can be determined by the supplier of the first node N1, or it can be explicitly defined by a standard. For different forms, different algorithms are used to calculate the coherent combining vectors based on the first channel information (e.g., a1, a2, ..., a... in Example 2). L The following are some non-limiting implementation methods.

[0178] As an example, the first channel information is an R-row L-column matrix, where R is the number of receiving antennas of the first node N1, and L is the number of antenna ports. Each element in the R-row L-column matrix is ​​the channel impulse response between an antenna port and a receiving antenna. The first node N1 can use different algorithms to decompose the R-row L-column matrix to obtain a coherently combined vector. Typical algorithms include singular value decomposition (SVD), QR decomposition, etc.

[0179] As an example, the first channel information is a precoding matrix or a precoding vector.

[0180] As an example, the first channel information includes small-scale characteristics.

[0181] As an example, the first channel information includes a channel matrix.

[0182] As an example, the channel matrix is ​​in the spatial-frequency domain.

[0183] As an example, the channel matrix is ​​in the angular-delay domain projection.

[0184] As an example, the first channel information includes an eigenvector, and the conjugate transpose of the eigenvector is used for coherent combining.

[0185] As an example, the first channel information includes a feature vector and an eigenvalue, and the conjugate transpose of the feature vector is used for coherent combining.

[0186] As an example, the first channel information includes the predicted CSI.

[0187] As one example, the first channel information includes interference information and / or noise information.

[0188] As an example, the second signaling is RRC signaling.

[0189] As one example, the second signaling includes RRC signaling and a medium access control (MAC) control element (CE).

[0190] As an example, RRC signaling is carried by the ServingCellConfig IE.

[0191] As an example, RRC signaling is carried by CSI-MeasConfig IE.

[0192] As an example, RRC signaling is carried by the ServingCellConfigCommon IE.

[0193] As an example, RRC signaling is carried by the ServingCellConfigCommonSIB IE.

[0194] As an example, the RRC signaling includes multiple NZP-CSI-RS-Resources, each of which is configured with multiple reference signals.

[0195] As an example, RRC signaling includes multiple CSI-ResourceConfigs, each of which configures multiple reference signals.

[0196] As an example, RRC signaling includes at least some fields in CSI-ReportConfig.

[0197] As an example, RRC signaling includes the AI ​​model ID (identity).

[0198] As an example, the first channel information is obtained based on ML inference (also known as AI / ML inference).

[0199] As an example, the input to ML inference includes either a received first reference signal or a received second reference signal.

[0200] As an example, the input to ML inference includes a channel matrix, which is obtained based on measurements of a first reference signal, or the channel matrix is ​​obtained based on measurements of a second reference signal.

[0201] As an example, the AI ​​model ID included in the second signaling indexes the ML model (also known as the AI ​​model) used for ML inference.

[0202] As an example, the ML model is based on a neural network (NN).

[0203] As an example, the ML model is based on conventional neural networks (CNN).

[0204] As an example, the ML model is based on a transformer architecture.

[0205] As an example, the output of ML inference includes channel information, such as a channel matrix or CSI.

[0206] As an example, the first node N1 sends a first signaling in step S104, the first signaling indicating a target reference signal; the second node N2 receives the first signaling in step S202.

[0207] For the second node N2, the first signaling effectively indicates information related to the channel state, which is beneficial for the second node N2 to perform operations such as scheduling and reconfiguration. However, as those skilled in the art know, these operations are often algorithms determined by the equipment vendor itself. A non-limiting implementation method is described below.

[0208] As a sub-implementation of the above embodiment, the second node N2 (after receiving the first signaling) performs ML training based on the target precoding vector; wherein the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among the multiple reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0209] In the context of AI / ML, ML training, also known as training or AI training, is an operation relative to ML inference, used to determine the parameters of an AI model. Inference using the determined AI model can be performed at the second node N2 or at the first node N1.

[0210] One advantage of the above sub-implementation is the reduced complexity of the first node N1. Furthermore, compared to feeding back accurate channel state parameters, the first signaling can save signaling overhead and improve transmission efficiency. Further, the second node N2 can flexibly select precoding vectors to precode or beamform the associated reference signals as needed, without notifying the first node N1, further improving scheduling flexibility. It should be noted that the selection of precoding vectors can be determined by the equipment vendor of the second node N2, and is implementation-dependent; the precoding vectors can also be non-codebook-based. For example, the second node N2 can flexibly set the direction of the precoding vectors based on the UE distribution in the cell; or, for example, the second node N2 can oversample based on the PMI fed back by the first node N1, and the multiple beam directions obtained from the oversampling correspond to multiple precoding vectors.

[0211] If the ML inference is performed by the first node N1, the second node N2 can pass the AI ​​model obtained after ML training to the first node N1 so that the first node N1 can improve the quality of ML inference.

[0212] Instead of having the second node N2 perform ML training, an alternative is to have the first node N1 perform ML training, as shown in the following example.

[0213] As an example, in step S105, the first node N1 performs ML training based on the target precoding vector; wherein the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among the multiple reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0214] The above embodiments can reduce the complexity of the second node N2 and avoid transmitting the AI ​​model obtained after ML training (if the ML inference is performed by the first node N1). In addition, the above embodiments may also avoid transmitting the first signaling.

[0215] As a sub-implementation of the above embodiments, the second signaling indicates the associated precoding vector for any of the plurality of reference signals other than the first reference signal.

[0216] As a specific implementation of the above sub-example, the precoding vector is based on the codebook.

[0217] As an example, ML training is reinforcement learning.

[0218] The above embodiments can update the AI ​​model in a timely manner or improve the performance of ML inference. Regardless of whether ML training is performed by the first node N1 or the second node N2, the above embodiments can avoid the increased complexity caused by frequent retraining. In addition, the computation of associated pre-encoded vectors can be considered as candidate answers designed for reinforcement learning; there are some classic algorithms in the AI / ML field, and a non-limiting implementation method is introduced below.

[0219] The ML entity maintains a precoded vector dictionary, which contains a large number of precoded vectors. Each precoded vector corresponds to a vector or matrix in the dictionary, and these vectors or matrices may contain hundreds of elements. The mapping from precoded vectors to vectors or matrices is sometimes referred to as an embedded representation. The precoded vector dictionary itself may be associated with the corresponding AI model or be trained with the corresponding AI model during ML training. The result obtained from ML inference, such as channel information, is itself an output vector or matrix of the same dimension. From the vectors or matrices in the precoded vector dictionary, the X precoded vectors corresponding to the X vectors or matrices that have the largest projection onto the output vector or matrix are selected as candidate answers.

[0220] As an example, the second signaling is transmitted on the physical downlink shared channel (PDSCH).

[0221] As an example, the first signaling is transmitted on the physical uplink control channel (PUCCH).

[0222] The above embodiments can improve feedback speed and avoid performance degradation.

[0223] As an example, the steps in box F1 and the steps in box F2 will not occur simultaneously.

[0224] As an example, the first node N1 sends a third signaling, which indicates whether ML training function is supported or included; when the third signaling indicates that ML training function is not supported or not included, the step in block F2 does not occur.

[0225] As an example, the second node N2 receives a third signaling; when the third signaling indicates that ML training functionality is not supported or is not included, the second node N2 configures or schedules the transmission of the first signaling.

[0226] As an example, the third signaling is RRC signaling.

[0227] As an example, the third signaling indicates the capabilities of the first node N1.

[0228] As an example, the third signaling is the UECapabilityInformation information element (IE).

[0229] As an example, the third signaling is sent before the multiple reference signals are received.

[0230] Example 6

[0231] Example 6 illustrates a schematic diagram of a time subunit according to an embodiment of the present application, as shown in FIG6.

[0232] In Example 6, K time sub-units are arranged sequentially in time, namely time sub-unit #1, time sub-unit #2, ..., time sub-unit #K, each occupied by K reference signals (i.e., multiple reference signals). Two adjacent time sub-units among the K time sub-units are either continuous or discontinuous in the time domain.

[0233] As an example, each of the K time sub-units belongs to a time slot.

[0234] As one embodiment, each of the K time sub-units includes one multi-carrier symbol, or two multi-carrier symbols.

[0235] As an example, the multicarrier symbol is an orthogonal frequency division multiplexing (OFDM) symbol.

[0236] As an example, the multicarrier symbol is a Discrete Fourier Transform Spread OFDM (DFT-S-OFDM) symbol.

[0237] As an example, the multicarrier symbol is the filter bank multicarrier (FBMC) symbol.

[0238] As an example, multicarrier symbols include a cyclic prefix (CP).

[0239] As an example, the K reference signals are aperiodic CSI-RS.

[0240] As an example, K time sub-units are indicated by downlink control information (DCI).

[0241] The two embodiments described above allow the base station to dynamically adjust the precoding vector, thereby improving the reception performance of the downlink reference signal or increasing the efficiency of reinforcement learning.

[0242] As an example, the K reference signals are periodic; the K time sub-units are the time-domain resources occupied by one occurrence of the K reference signals.

[0243] As a sub-example of the above embodiment, for any one of the K reference signals, the multicarrier symbol occupied in the time domain appears periodically.

[0244] The above embodiments make the selection of target reference signals more robust, avoiding frequent or unnecessary reinforcement learning due to dynamic errors in channel information.

[0245] As a sub-example of the above embodiments, multiple reception qualities are L3-RSRP.

[0246] Example 7

[0247] Example 7 illustrates a flowchart of transmitting a first signaling according to an embodiment of this application, as shown in Figure 7.

[0248] In Example 7, the target reference signal is different from the first reference signal; the first node determines whether the first condition set is satisfied in step S701; if yes, the first signaling is sent in step S702; if no, the process ends.

[0249] The first set of conditions includes at least one of a plurality of reception qualities that is better than the first reception quality.

[0250] As an example, when the difference between one reception quality and another reception quality is not less than (or greater than) a first threshold, one reception quality is superior to the other reception quality.

[0251] As a sub-example of the above embodiments, reception quality is reception power.

[0252] As a sub-example of the above embodiment, among the multiple reception qualities, the first reception quality is the received power after coherent combining, and the other reception qualities are RSRP. RSRP may be L1-RSRP, L3-RSRP, CSI-RSRP, or synchronization signal reference signal received power (SS-RSRP), etc.

[0253] As a sub-implementation of the above embodiments, the received power is a linear average of the received power on all REs carrying the corresponding reference signals within a time-frequency resource (where the first received quality includes coherent combining), and the time-frequency resource is configurable.

[0254] As an example, a time-frequency resource is the measurement frequency bandwidth of the corresponding reference signal in the frequency domain.

[0255] As an example, any one of the multiple reference signals appears multiple times in the time domain dimension of a time-frequency resource.

[0256] As an example, the time interval between any one of the multiple reference signals in the time domain is T1 time slots, and a time-frequency resource includes T2 times T1 time slots in the time domain, where T1 and T2 are configurable.

[0257] As an example, when the difference between one reception quality and another reception quality is not less than (or greater than) a first threshold, one reception quality is superior to the other reception quality.

[0258] As an example, the unit of the first threshold is dB.

[0259] As an example, the first threshold is a ratio.

[0260] As an example, the first threshold is configurable.

[0261] As an example, if the first set of conditions is not satisfied, the first node continues to receive reference signals to determine whether the first set of conditions is satisfied.

[0262] Example 8

[0263] Example 8 illustrates a schematic diagram of the deployment of AI / ML functionality in a Radio Access Network (RAN) domain according to an embodiment of this application, as shown in Figure 8. The gNB in ​​Example 8 can be replaced with, for example, an eNB, or a network device such as a 6G base station.

[0264] AI / ML related functions include ML training (also known as AI training, or AI / ML training), ML testing, and ML inference (also known as AI inference, or AI / ML inference), etc. ML training, ML testing, and ML inference functions can be deployed independently or co-located. Deployment of AI / ML related functions can be implemented through software, such as downloading and / or running executable files; or it can be implemented through a combination of software and hardware, such as accelerating specific computing units through hardware to improve computing speed or save power.

[0265] ML training functionality can be deployed in a cross-domain management system or a domain-specific management system. Domain-specific management systems are used to manage the RAN domain or the CN (Core Network) domain. For example, ML training functionality for management data analytics (MDA) can be deployed in the MDAF (MDA function); ML training for network data analytics can be deployed in the network data analytics function (NWDAF), meaning the ML training functionality is a model training logical function (MTLF).

[0266] The ML inference function can also be deployed in a cross-domain management system or a domain-specific management system; for example, the ML inference function is an MDAF, or the ML inference function is an analytics logical function (AnLF) located in the NWDAF.

[0267] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[0268] In Example 8, the RAN domain ML training function 1402 is located in the RAN domain management function 1403; while the ML inference function is located in the base station, that is, the AI / ML inference function 1404 is located in gNB 1405, the AI / ML inference function 1406 is located in gNB 1407, and so on.

[0269] In Figure 8, the management of ML inference functions of multiple base stations is completed by RAN domain management function 1403, that is, data interaction with RAN domain management service (MnS) consumer / cross-domain management 1401 (as shown by the dashed arrow in Figure 8).

[0270] Optionally, the management of ML inference function can also be completed by the base station itself, that is, each base station can independently interact with the RAN domain MnS consumer / cross-domain management 1401.

[0271] It should be noted that Example 8 is merely a non-limiting implementation; optionally, the ML training function of the RAN domain may also be deployed in the base station; or optionally, some base stations may deploy both the ML inference function and the ML training function of the RAN domain, while some base stations may only deploy the ML inference function.

[0272] As an example, one of the gNBs (or base stations) in Example 8 is the second node of this application.

[0273] As an example, the second processor includes an AL / ML inference function, namely 1404 or 1406, as shown in Figure 8.

[0274] As an example, one of the AL / ML inference functions in Figure 8 performs ML training based on a target precoding vector; the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among the multiple reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0275] Example 9

[0276] Example 9 illustrates a schematic diagram of the deployment of AI / ML functionality in a UE according to one embodiment of this application; as shown in Figure 9. The RAN domain ML training function 1505 in Figure 9 is optional.

[0277] UE function 1504 is deployed in the first node of this application. UE function 1504 includes AI / ML inference function 1506. AI / ML inference function 1506 uses ML model (also known as AI model) for inference. An ML model is typically trained before being used for AI / ML inference.

[0278] As an example, UE function 1504 includes RAN domain ML training function 1505, which runs training data through an ML model to obtain relevant loss and adjusts the parameters of the ML model based on the calculated loss; ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0279] The above embodiments can reduce the complexity of the base station, or save air interface resources caused by reporting training data; however, the above embodiments place high demands on the processing capabilities of the UE side.

[0280] Optionally, UE function 1504 also includes CN domain ML training functionality (not shown in Figure 9).

[0281] Optionally, UE function 1504 also includes an AI / ML deployment function (not shown in Figure 9) for loading ML models and data.

[0282] As an example, the first node indicates whether it supports ML training function (RAN domain or CN domain) through capability reporting. The capability reporting is RRC signaling or non-access stratum (NAS) signaling.

[0283] As an example, the ML model, along with the associated metadata, is loaded by the first node from a network device or a remote server.

[0284] Optionally, UE function 1504 is a management service (MnS) producer that provides data to CN domain management function (MnF) 1501, and / or RAN domain MnF 1502, and / or cross-domain management system 1503 for management or analysis (as shown by double arrow 1507).

[0285] Optionally, UE function 1504 is an MnS consumer that loads data from CN domain MnF1501, and / or RAN domain MnF1502, and / or cross-domain management system 1503 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1507).

[0286] As an example, the first channel information in this application is obtained through inference by the AI / ML inference function 1506.

[0287] As an example, the RAN domain ML training function 1505 performs ML training based on a target precoding vector; wherein the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among a plurality of reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0288] As an example, the first processor includes an AL / ML inference function 1506 in Figure 9.

[0289] As an example, ML models are based on neural networks.

[0290] As an example, the ML model is based on conventional neural networks (CNN).

[0291] As an example, the ML model is based on a transformer architecture.

[0292] Example 10

[0293] Example 10 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application; as shown in Figure 10. Figure 10 includes a third processor, a fourth processor, a fifth processor, and a sixth processor.

[0294] In Example 10, the third processor sends a first dataset to the fourth processor and a second dataset to the fifth processor; the fourth processor generates a target first-class parameter set based on the first dataset and sends the generated target first-class parameter set to the fifth processor; the fifth processor processes the second dataset using the target first-class parameter set to obtain a first-class output, and (optionally) the fifth processor sends the first-class output to the sixth processor. In Figure 10, the first-class feedback and the second-class feedback are optional; the fourth processor includes ML training functionality; the fifth processor includes ML inference functionality.

[0295] As one example, the sixth processor includes ML testing functionality.

[0296] As one example, the sixth processor includes performance monitoring / evaluation of the ML model.

[0297] As an example, the fifth processor sends a first type of feedback to the fourth processor. The first type of feedback is used to trigger the recalculation or update of the target first type of parameter set, that is, to trigger ML initial training or ML retraining.

[0298] As one embodiment, the sixth processor sends a second type of feedback to the third processor. The second type of feedback is used to generate a first dataset or a second dataset, or it is used to trigger the sending of the first dataset or the sending of the second dataset.

[0299] As one example, the third processor generates a first dataset and a second dataset based on the measurement of the reference signal.

[0300] As an example, the fifth processor belongs to the first node, and the sixth processor belongs to the second node.

[0301] As an example, the first type of output includes first channel information.

[0302] As an example, the first type of output includes an index of the target reference signal.

[0303] As one example, the second dataset includes measurements for the first reference signal, or includes measurements for the second reference signal.

[0304] As an example, the first dataset includes training data.

[0305] As an example, the fourth processor is used to train the ML model, and the trained model is described by the target first class of parameter sets.

[0306] As an example, the fourth processor belongs to the first node.

[0307] The above embodiments avoid passing the first dataset to the second node.

[0308] As one example, the fourth processor belongs to the second node.

[0309] The above embodiments support joint training and optimize system performance.

[0310] As an example, the fourth processor belongs to the core network.

[0311] The above embodiments support network-wide joint training, further optimizing system performance.

[0312] As an example, the second dataset includes inference data.

[0313] As an example, the fifth processor belongs to the first node.

[0314] As an example, the fifth processor constructs a model based on the target first type of parameter set, and then inputs the second dataset into the constructed model to obtain the first type of output.

[0315] As an example, the fifth processor generates a recovery dataset based on the first type of output, and the error between the recovery dataset and the second dataset is used to generate the first type of feedback.

[0316] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the fourth processing opportunity recalculates the target first type of parameter set.

[0317] As an example, when the error is too large or the update has not been performed for too long, the performance of the trained model is considered unsatisfactory.

[0318] As an example, the target first type of parameter group includes one or more of the following: convolution kernel size, number of convolutional layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[0319] As an example, the target first type of parameter group includes one or more of the following: convolution kernel, pooling kernel, pooling function, activation function, parameters of pooling function, or parameters of activation function.

[0320] Example 11

[0321] Example 11 illustrates a flowchart based on artificial intelligence or machine learning according to an embodiment of this application, as shown in Figure 11. Figure 11 includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation. In Example 11, the third and fourth operations belong to the first stage, the fifth operation belongs to the second stage, the sixth operation belongs to the third stage, and the seventh operation belongs to the fourth stage. In Figure 11, the lines with arrows indicate the sequence of the process.

[0322] As an example, the third operation includes AI / ML training, the fourth operation includes AI / ML testing, the fifth operation includes AI / ML emulation, the sixth operation includes AI / ML entity loading, and the seventh operation includes AI / ML inference.

[0323] As an example, the first phase includes a training phase, the second phase includes an emulation phase, the third phase includes a deployment phase, and the fourth phase includes an emulation phase.

[0324] As an example, the first stage includes AI / ML model training.

[0325] As an example, the first phase includes AI / ML model training and AI / ML testing.

[0326] As an example, AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[0327] As an example, AI / ML model training relies on training data.

[0328] As an example, AI / ML model training includes AI / ML entity validation.

[0329] As an example, AI / ML entity verification is used to evaluate the performance of AI / ML entities.

[0330] As an example, AI / ML entity verification relies on verification data.

[0331] As an example, if the AI / ML entity verification results do not meet expectations, the AI / ML model will be retrained.

[0332] As an example, AI / ML testing includes testing validated AI / ML entities to estimate the performance of the trained AI / ML model.

[0333] As an example, if the AI / ML test results meet expectations, the AI / ML entity proceeds to the next stage; otherwise, the AI / ML model will be retrained.

[0334] As an example, AI / ML testing relies on test data.

[0335] As an example, the second stage includes AI / ML simulation, which performs inference of AI / ML entities in a simulation environment.

[0336] As an example, AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using AI / ML entities.

[0337] As an example, the second stage is optional.

[0338] As an example, the third stage includes AI / ML entity loading, which is to obtain trained AI / ML entities to obtain the desired AI / ML inference functions.

[0339] As an example, the third stage is optional.

[0340] As an example, when the training and inference functions are co-located, the third stage is no longer needed.

[0341] As an example, the fourth stage includes AI / ML inference.

[0342] Example 12

[0343] Example 12 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of this application; as shown in Figure 12. In Figure 12, the processing apparatus 1600 in the first node includes a first receiver 1601 and a first processor 1602.

[0344] A first receiver 1601 receives multiple reference signals, including a first reference signal; a first processor 1602 determines a target reference signal based on multiple reception qualities, the target reference signal being one of the multiple reference signals.

[0345] In Example 12, the multiple reception qualities are the reception qualities of multiple reference signals, and the first reception quality among the multiple reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the multiple reception qualities includes coherent combining of the received signals from multiple antenna ports.

[0346] As one example, any two antenna ports QCL are used to transmit multiple reference signals.

[0347] As one example, the first reference signal is transmitted through multiple antenna ports.

[0348] As an example, at least one antenna port of the first reference signal is connected to any one of a plurality of antenna ports, QCL.

[0349] As an example, any one of the multiple reference signals occupies one RS resource.

[0350] As one example, multiple reference signals are transmitted in the same time unit.

[0351] As one embodiment, a first receiver 1601 generates first channel information; wherein coherent combining of received signals from multiple antenna ports is based on the first channel information; the first channel information is obtained based on inference.

[0352] As an example, the first channel information is generated based on measurements of a first reference signal.

[0353] As an example, the first channel information is generated based on measurements of reference signals transmitted for multiple antenna ports.

[0354] As an example, for any one of the multiple reference signals other than the first reference signal, only one antenna port is used for transmission.

[0355] As one embodiment, the first processor 1602 sends a first signaling instruction, which indicates a target reference signal.

[0356] As one embodiment, the first processor 1602 performs ML training based on a target precoding vector; wherein the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among a plurality of reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0357] As a sub-implementation of the above embodiment, the first receiver 1601 receives a second signaling; wherein the second signaling is a precoding vector associated with any of the multiple reference signals other than the first reference signal.

[0358] As an example, the target reference signal is a reference signal that satisfies a first set of conditions among a plurality of reference signals and other than the first reference signal. The first set of conditions includes the target reference signal having the best reception quality among a plurality of reception qualities.

[0359] As an example, any of the multiple reception qualities other than the first reception quality is RSRP.

[0360] As an example, the first node is the user equipment.

[0361] As an example, the first node is a relay node device.

[0362] As an example, the first node is the terminal.

[0363] As an example, the first receiver 1601 includes at least one of the following in embodiment 4: {antenna 452, receiver 454, receiver processor 456, multi-antenna receiver processor 458, controller / processor 459, memory 460, data source 467}.

[0364] As an example, the first processor 1602 includes at least one of the following in embodiment 4: {antenna 452, receiver / transmitter 454, receiver processor 456, transmitter processor 468, multi-antenna receiver processor 458, multi-antenna transmitter processor 457, controller / processor 459, memory 460, data source 467}.

[0365] Example 13

[0366] Example 13 illustrates a structural block diagram of a processing device for a second node according to an embodiment of this application; as shown in Figure 13. In Figure 13, the processing device 1700 in the second node includes a first transmitter 1701 and a second processor 1702.

[0367] A first transmitter 1701 transmits multiple reference signals, including a first reference signal; a second processor 1702 receives a first signaling instruction, which indicates the target reference signal.

[0368] In Example 13, the target reference signal is one of a plurality of reference signals, and the determination of the target reference signal depends on a plurality of reception qualities; the plurality of reception qualities are the reception qualities of the plurality of reference signals, and the first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; the calculation of only the first reception quality among the plurality of reception qualities includes coherent combining of the received signals from the plurality of antenna ports.

[0369] As one embodiment, the second processor 1702 performs ML training based on the target precoding vector; wherein the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among the multiple reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

[0370] As an example, in addition to the first reference signal, the generation of any of the plurality of reference signals depends on an associated precoding vector; the precoding vector is used to generate the associated reference signal.

[0371] In the above embodiments, there are various specific implementation methods for generating associated reference signals using precoded vectors, which can be determined by the equipment manufacturer of the second node. Typical precoding or beamforming algorithms include different algorithms such as maximum ratio combining (MRC), minimum mean square error (MMSE), and zero forcing (ZF); in addition, the precoding or beamforming algorithm can consider suppressing interference between multiple users.

[0372] As an example, for any one of the multiple reference signals other than the first reference signal, only one antenna port is used for transmission.

[0373] As one embodiment, a first transmitter 1701 transmits a second signaling; wherein the second signaling is a precoded vector associated with any of the plurality of reference signals other than the first reference signal.

[0374] As an example, the target reference signal is a reference signal that satisfies a first set of conditions among a plurality of reference signals and other than the first reference signal. The first set of conditions includes the target reference signal having the best reception quality among a plurality of reception qualities.

[0375] As an example, any of the multiple reception qualities other than the first reception quality is RSRP.

[0376] As an example, any one of the multiple reception qualities is RSRP.

[0377] As one example, the second node is a base station device.

[0378] As one example, the second node is the user equipment.

[0379] As an example, the second node is a relay node device.

[0380] As an example, the first transmitter 1702 includes at least one of the following in embodiment 4: {antenna 420, receiver / transmitter 418, transmission processor 416, multi-antenna transmission processor 471, controller / processor 475, memory 476}.

[0381] As an example, the second processor 1702 includes at least one of the following in embodiment 4: {antenna 420, receiver / transmitter 418, receiver processor 470, transmitter processor 416, multi-antenna receiver processor 472, multi-antenna transmitter processor 471, controller / processor 475, memory 476}.

[0382] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The user equipment, terminal, and UE in this application include, but are not limited to, drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablets, laptops, vehicle-mounted communication equipment, vehicles, RSUs, wireless sensors, internet access cards, IoT terminals, RFID terminals, NB-IoT terminals, machine-type communication (MTC) terminals, enhanced MTC (eMTC) terminals, data cards, internet access cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base stations or system equipment in this application include, but are not limited to, macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNBs, gNBs, transmitter receiver points (TRPs), GNSS, relay satellites, satellite base stations, airborne base stations, roadside units (RSUs), drones, and testing equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[0383] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A method for use in a terminal, characterized in that, include: Receive multiple reference signals, the multiple reference signals including a first reference signal; A target reference signal is determined based on multiple reception qualities, wherein the target reference signal is one of the multiple reference signals; Wherein, the plurality of reception qualities are the reception qualities of the plurality of reference signals, and the first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; Of the multiple reception qualities, only the calculation of the first reception quality includes coherent combining of received signals from multiple antenna ports.

2. The method according to claim 1, characterized in that, include: Generate the first channel information; The coherent combining of the received signals from the plurality of antenna ports is based on the first channel information.

3. The method according to claim 1 or 2, characterized in that, For any of the plurality of reference signals other than the first reference signal, only one antenna port is used for transmission.

4. The method according to any one of claims 1 to 3, characterized in that, include: Send a first signaling instruction, which indicates the target reference signal.

5. The method according to any one of claims 1 to 3, characterized in that, include: Perform machine learning training based on the target pre-encoded vector; The target reference signal is different from the first reference signal; Any one of the plurality of reference signals other than the first reference signal is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

6. The method according to claim 5, characterized in that, include: Receive second signaling; Wherein, the second signaling is the precoding vector associated with any of the plurality of reference signals other than the first reference signal.

7. The method according to any one of claims 1 to 6, characterized in that, The target reference signal is a reference signal among the plurality of reference signals that, other than the first reference signal, satisfies a first set of conditions, wherein the first set of conditions includes the target reference signal whose reception quality is the best among the plurality of reception qualities.

8. The method according to any one of claims 1 to 7, characterized in that, Any of the multiple reception qualities other than the first reception quality is RSRP.

9. A terminal, characterized in that, The terminal includes: one or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the terminal to perform the method as described in any one of claims 1 to 8.

10. A method for use in a base station, characterized in that, include: Send multiple reference signals, the multiple reference signals including a first reference signal; Receive the first signaling, which indicates the target reference signal; Wherein, the target reference signal is one of the plurality of reference signals, and the determination of the target reference signal depends on a plurality of reception qualities; the plurality of reception qualities are the reception qualities of the plurality of reference signals, and the first reception quality among the plurality of reception qualities is the reception quality of the first reference signal; Of the multiple reception qualities, only the calculation of the first reception quality includes coherent combining of received signals from multiple antenna ports.

11. The method according to claim 10, characterized in that, include: ML training is performed based on a target precoding vector; wherein the target reference signal is different from the first reference signal; any reference signal other than the first reference signal among the plurality of reference signals is associated with a precoding vector, wherein the target precoding vector is associated with the target reference signal.

12. The method according to claim 10 or 11, characterized in that, For any of the plurality of reference signals other than the first reference signal, only one antenna port is used for transmission.

13. The method according to any one of claims 10 to 12, characterized in that, include: Send a second signaling; wherein the second signaling is the precoding vector associated with any of the plurality of reference signals other than the first reference signal.

14. The method according to any one of claims 10 to 12, characterized in that, include: The target reference signal is a reference signal among the plurality of reference signals that, other than the first reference signal, satisfies a first set of conditions, wherein the first set of conditions includes the target reference signal whose reception quality is the best among the plurality of reception qualities.

15. The method according to claim 14, characterized in that, include: Any of the multiple reception qualities other than the first reception quality is RSRP.

16. A base station, characterized in that, The base station includes: one or more processors and a memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the base station to perform the method as described in any one of claims 10 to 15.

Images