Method and apparatus related to ML model and used in node for wireless communication

Abstract

Disclosed in the present application are a method and apparatus related to an ML model and used in a node for wireless communication. A first node for wireless communication. The first node is characterized by comprising: a first receiver, which receives a first channel, wherein a first bit block is transmitted on the first channel, whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is an initial transmission of the first bit block, and the first ID identifies at least one ML model.

Description

Methods and apparatus related to ML models in nodes used for wireless communication

[0001] This application claims priority to Chinese Patent Application No. 202411606683.5, filed on November 11, 2024, entitled “Method and apparatus relating to ML model in a node 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 methods and apparatus for transmitting wireless signals in wireless communication systems supporting cellular networks. Background Technology

[0003] In NRR (release) 18, research on AI (Artificial Intelligence) / ML (Machine Learning) 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. With the continuous improvement of AI / ML technologies, their application will be a potentially crucial component of future wireless communication systems. Summary of the Invention

[0004] How to leverage bit block transmission enhancement for AI / ML functions in wireless communication is a problem worthy of research. To address this problem, this application discloses a solution. Unless otherwise specified, the embodiments and features in the first node of this application can be applied to the second node, and vice versa. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0005] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS38 series.

[0006] As an example, the interpretation of the terms in this application is based on the definitions in the 3GPP specification protocol TS28 series.

[0007] This application discloses a method used in a first node of wireless communication, characterized by comprising:

[0008] Receive the first channel, and transmit the first bit block on the first channel;

[0009] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0010] As one example, the first node is a terminal.

[0011] As an example, the problem this application aims to solve includes: how to determine the relationship between the channel and the ML model based on whether the transmission of bit blocks on the channel is the initial transmission.

[0012] As an example, the above method can perform separate processing for the initial transmission and retransmission of bit blocks.

[0013] As an example, the advantages of the above method include: it facilitates the selection of appropriate data to complete AI / ML functions in wireless communication.

[0014] As an example, the advantages of the above method include: improving the performance of the communication system.

[0015] According to one aspect of this application, the above method is characterized in that,

[0016] The first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before it is correctly decoded.

[0017] According to one aspect of this application, the above method is characterized in that,

[0018] When the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID.

[0019] As an example, if the initial transmitted bit block is received correctly (in which case the bit block does not need to be retransmitted), the channel quality is generally good. Using the corresponding channel information for training / reinforcement learning / performance monitoring of the ML model is beneficial for obtaining a better and more effective ML model.

[0020] According to one aspect of this application, the above method is characterized in that,

[0021] When the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

[0022] According to one aspect of this application, the above method is characterized by comprising:

[0023] Receive the first signaling;

[0024] Whether the first channel is associated with the first ID depends on the indication of the first signaling when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block.

[0025] As an example, the advantages of the above method include: it facilitates control over the quality of data used for training / reinforcement learning / performance monitoring of ML models.

[0026] As an example, the advantages of the above method include: high flexibility.

[0027] According to one aspect of this application, the above method is characterized by comprising:

[0028] Receive a second channel, on which the first bit block is transmitted, and the second channel is later than the first channel;

[0029] Wherein, the first bit block is correctly decoded after being received by the second channel, and the first channel is not associated with the first ID.

[0030] According to one aspect of this application, the above method is characterized by comprising:

[0031] Receive second signaling;

[0032] Receive a second channel, on which the first bit block is transmitted, and the second channel is later than the first channel;

[0033] The first bit block is correctly decoded after being received by the second channel, and whether the first channel is associated with the first ID depends on the indication of the second signaling.

[0034] As an example, the advantages of the above method include: it facilitates control over the quality of data used for training / reinforcement learning / performance monitoring of ML models.

[0035] As an example, the advantages of the above method include: high flexibility.

[0036] According to one aspect of this application, the above method is characterized in that,

[0037] The first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0038] As an example, combined with the above features, the solution disclosed in this application is beneficial to improving the effectiveness of data in the dataset.

[0039] According to one aspect of this application, the above method is characterized in that,

[0040] The first channel is associated with the first ID, including: information obtained from measurements of the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0041] As an example, combined with the above features, the solution disclosed in this application is beneficial to improving the effectiveness of data in the dataset.

[0042] This application discloses a method used in a second node for wireless communication, characterized by comprising:

[0043] The first channel is transmitted, and the first bit block is transmitted on the first channel;

[0044] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0045] In one embodiment, the second node is a base station.

[0046] According to one aspect of this application, the above method is characterized in that,

[0047] The first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before it is correctly decoded.

[0048] According to one aspect of this application, the above method is characterized in that,

[0049] When the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID.

[0050] According to one aspect of this application, the above method is characterized in that,

[0051] When the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

[0052] According to one aspect of this application, the above method is characterized by comprising:

[0053] Send the first signaling;

[0054] Whether the first channel is associated with the first ID depends on the indication of the first signaling when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block.

[0055] According to one aspect of this application, the above method is characterized by comprising:

[0056] The first bit block is transmitted on a second channel, which is later than the first channel.

[0057] Wherein, the first bit block is correctly decoded after being received by the second channel, and the first channel is not associated with the first ID.

[0058] According to one aspect of this application, the above method is characterized by comprising:

[0059] Send a second signaling message;

[0060] The first bit block is transmitted on a second channel, which is later than the first channel.

[0061] The first bit block is correctly decoded after being received by the second channel, and whether the first channel is associated with the first ID depends on the indication of the second signaling.

[0062] As an example, the second node can obtain the decoding status of the first bit block through the feedback information sent by the first node.

[0063] According to one aspect of this application, the above method is characterized in that,

[0064] The first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0065] According to one aspect of this application, the above method is characterized in that,

[0066] The first channel is associated with the first ID, including: information obtained from measurements of the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0067] This application discloses a first node used for wireless communication, characterized in that it comprises:

[0068] A first receiver receives a first channel, and a first bit block is transmitted on the first channel.

[0069] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0070] This application discloses a second node used for wireless communication, characterized in that it comprises:

[0071] The second transmitter transmits through the first channel, and the first bit block is transmitted on the first channel;

[0072] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model. Attached Figure Description

[0073] 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:

[0074] Figure 1 shows a processing flowchart of the first node according to an embodiment of this application;

[0075] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0076] Figure 3 illustrates a schematic diagram of the wireless protocol architecture of the user plane and control plane according to an embodiment of this application;

[0077] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0078] Figure 5 shows a signal transmission flowchart according to an embodiment of this application;

[0079] Figure 6 shows an illustrative diagram illustrating a first channel associated with a first ID according to an embodiment of this application;

[0080] Figure 7 shows an illustrative diagram illustrating a first channel associated with a first ID according to an embodiment of this application;

[0081] Figure 8 illustrates a schematic diagram of the deployment of AI / ML functions in a RAN (Radio Access Network) domain according to an embodiment of this application;

[0082] Figure 9 shows a schematic diagram of the AI / ML function deployment of a UE according to an embodiment of this application;

[0083] Figure 10 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0084] Figure 11 shows a flowchart based on artificial intelligence or machine learning according to an embodiment of this application;

[0085] Figure 12 illustrates whether a first channel is associated with a first ID depending on whether the transmission of a first bit block on the first channel is the initial transmission of the first bit block, according to an embodiment of this application.

[0086] Figure 13 illustrates a schematic diagram of the relationship between the third signaling and the first channel according to an embodiment of this application;

[0087] Figure 14 illustrates a schematic diagram of the relationship between a third signaling, a first channel, and at least one reference signal according to an embodiment of this application;

[0088] Figure 15 shows a signal transmission flowchart according to an embodiment of this application;

[0089] Figure 16 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0090] Figure 17 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0091] The technical solution 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.

[0092] Example 1

[0093] Example 1 illustrates a processing flowchart of the first node according to an embodiment of this application, as shown in Figure 1.

[0094] In Embodiment 1, the first node in this application receives the first channel in step 101.

[0095] In Example 1, a first bit block is transmitted on the first channel; whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first ID identifying at least one ML model.

[0096] As an example, the first channel is a channel used for transmitting data.

[0097] As an example, the first channel is a channel used for transmitting control information.

[0098] As an example, the first channel is a downlink channel.

[0099] As an example, the first channel is a physical layer channel.

[0100] As an example, the first channel is PDSCH (Physical Downlink Shared Channel).

[0101] As an example, the first channel is PDCCH (Physical Downlink Control Channel).

[0102] As one embodiment, receiving the first channel includes: performing signal reception on the first channel.

[0103] As one embodiment, receiving the first channel includes: receiving at least the first bit block on the first channel.

[0104] As one example, the first bit block includes multiple bits.

[0105] As one example, the first bit block includes data bits.

[0106] As one embodiment, the first bit block includes control information bits.

[0107] As one embodiment, the first bit block includes a transport block.

[0108] As an example, the first bit block is transmitted on the first channel after at least channel coding.

[0109] As an example, the first bit block is transmitted on the first channel after at least channel coding and resource mapping.

[0110] As an example, the first bit block is transmitted on the first channel after undergoing at least the following processes: CRC attachment, code block segmentation and code block CRC attachment, channel coding, rate matching, code block concatenation, scrambling, modulation, layer mapping, antenna port mapping, mapping to virtual resource blocks, and mapping from virtual to physical resource blocks.

[0111] As an example, whether the first channel is associated with the first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, and whether the first channel is associated with the first ID depends on whether the transmission of the first bit block on the first channel is a retransmission of the first bit block, are equivalent.

[0112] As an example, the transmission of the first bit block other than the initial transmission is: the retransmission of the first bit block.

[0113] As an example, the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, and the transmission of the first bit block on the first channel is a retransmission of the first bit block; these two are equivalent.

[0114] As an example, the first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before it is correctly decoded.

[0115] As an example, the first bit block may be transmitted only once or multiple times before it is correctly decoded.

[0116] As an example, the first ID (identity) identifies at least one dataset.

[0117] As an example, the first ID is configured to the first node.

[0118] As an example, the two communicating parties reach a consensus on the content identified by the first ID.

[0119] As an example, the number of ML models identified by the first ID is 1.

[0120] As an example, the first ID identifies more than one ML model.

[0121] As an example, an ML model is an AI model.

[0122] As an example, an ML model includes a mathematical algorithm that can be trained using data and human expert input as examples to replicate the decisions made by experts when provided with the same information.

[0123] As one embodiment, the first channel is associated with the first ID, including: the first channel is associated with the target dataset; wherein the first ID indicates the target dataset.

[0124] As one embodiment, the first channel is associated with the first ID, including: the target dataset depends on the first channel; wherein the first ID indicates the target dataset.

[0125] As one embodiment, the first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset; wherein the first ID indicates the target dataset.

[0126] As an example, when the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is not associated with the first ID; when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is associated with the first ID.

[0127] As one embodiment, the transmission of the first bit block on the first channel is the initial transmission of the first bit block, and the first channel is not associated with the first ID; or, the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, and the first channel is associated with the first ID.

[0128] As an example, when the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID.

[0129] As an example, when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

[0130] As one embodiment, the first node receives the first signaling;

[0131] Whether the first channel is associated with the first ID depends on the indication of the first signaling when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block.

[0132] As one embodiment, the transmission of the first bit block on the first channel is the initial transmission of the first bit block, and the first channel is associated with the first ID; or, the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, and the first channel is not associated with the first ID.

[0133] As one embodiment, the first node receives the first signaling;

[0134] The transmission of the first bit block on the first channel is the initial transmission of the first bit block, and the first channel is associated with the first ID; or, the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, and whether the first channel is associated with the first ID depends on the indication of the first signaling.

[0135] Example 2

[0136] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2. Figure 2 illustrates a network architecture 200 for a 5G NR (New Radio) / LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution Advanced) system. The 5G NR / LTE / LTE-A network architecture 200 may be referred to as 5GS (5G System) / EPS (Evolved Packet System) 200, or some other suitable term. 5GS / EPS 200 includes at least one of UE (User Equipment) 201, RAN (Radio Access Network) 202, 5GC (5G Core Network) / EPC (Evolved Packet Core) 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet service 230. 5GS / EPS can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown in the figure, 5GS / EPS 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 and other nodes 204. Node 203 provides user and control plane protocol termination to UE 201. Node 203 can 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 Point), or some other suitable term. Node 203 provides UE 201 with an access point to the 5GC / EPC 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, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. Node 203 connects to 5GC / EPC210 via the S1 / NG interface. 5GC / EPC210 includes MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MME / AMF / SMF 214, S-GW (Service Gateway) / UPF (User Plane Function) 212, and P-GW (Packet Data Network Gateway) / UPF 213. MME / AMF / SMF 211 is the control node handling signaling between UE201 and 5GC / EPC210. ​​Generally, MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through S-GW / UPF 212, which is itself connected to P-GW / UPF 213. 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 Internet, intranet, IMS (IP Multimedia Subsystem), and packet switching services.

[0137] As an example, the UE201 corresponds to the first node in this application.

[0138] As an example, gNB203 corresponds to the second node in this application.

[0139] As an example, the wireless link between the UE201 and the node203 includes a cellular link.

[0140] As an example, the gNB203 is a macrocell base station.

[0141] As an example, the gNB203 is a microcell base station.

[0142] As an example, the gNB203 is a PicoCell base station.

[0143] As an example, the gNB203 is a femtocell.

[0144] As an example, the gNB203 is a base station device that supports large latency differences.

[0145] As one example, the gNB203 is a flight platform device.

[0146] As an example, the gNB203 is a satellite device.

[0147] Example 3

[0148] 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 a first communication node device (UE, gNB, or V2X (Vehicle to Everything) RSU (Road Side Unit), on-board equipment, or on-board communication module) and a second communication node device (gNB, UE, or V2X RSU, on-board equipment, or on-board communication module), or the control plane 300 between two UEs, using three layers: Layer 1 (L1), Layer 2 (L2), and Layer 3 (L3). L1 is the lowest layer and implements various PHY (Physical Layer) signal processing functions. L1 will be referred to herein as PHY301. Layer 2 (L2) 305 sits above PHY 301 and is responsible for the link between the first and second communication node devices and between the two UEs via PHY 301. L2 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second communication node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. It also provides security through encrypted data packets and supports cross-region mobility between the second and first communication node devices. The 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 (Hybrid Automatic Repeat Request). MAC sublayer 302 provides multiplexing between the 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 RRC (Radio Resource Control) sublayer 306 in L3 of the control plane 300 is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second and first communication node devices.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 largely 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 packets to reduce radio transmission overhead. L2 layer 355 in user plane 350 also includes SDAP (Service Data Adaptation Protocol) sublayer 356. SDAP sublayer 356 is responsible for mapping between QoS (Quality of Service) 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., the IP (Internet Protocol) 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.).

[0149] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node in this application.

[0150] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node in this application.

[0151] As an example, the first signaling in this application is generated in the PHY301.

[0152] As an example, the first signaling in this application is generated in the MAC sublayer 302.

[0153] As an example, the first signaling in this application is generated in the RRC sublayer 306.

[0154] As an example, the first channel in this application is generated by the PHY301 or the PHY351.

[0155] As an example, the second channel in this application is generated in the PHY301 or the PHY351.

[0156] As an example, the at least one reference signal in this application is generated in the PHY301 or the PHY351.

[0157] As an example, the second signaling in this application is generated in the RRC sublayer 306, the MAC sublayer 302, or the PHY 301.

[0158] As an example, the third signaling in this application is generated in the RRC sublayer 306, the MAC sublayer 302, or the PHY 301.

[0159] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0160] Example 4

[0161] Example 4 illustrates a schematic diagram of a first communication device and a second communication device according to 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.

[0162] 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.

[0163] 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.

[0164] 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 transmission from the first communication device 410 to the second communication device 450, 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 retransmitting 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 mapping of signal clusters based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), M-Phase Shift Keying (M-PSK), 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 to generate one or more spatial streams. Transmit processor 416 then maps each spatial stream to a subcarrier, multiplexes it 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 multicarrier symbol 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 a different antenna 420.

[0165] 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 spatial stream destined for the second communication device 450. Symbols on each spatial 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. The controller / processor 459 may be associated with a memory 460 storing program code and data. The memory 460 may be referred to as computer-readable media. In the transmission from the first communication device 410 to the second communication device 450, the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transport and logical channels to recover upper-layer data packets from the core network. The upper-layer data packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 for Layer 3 processing.

[0166] 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 transmission from the first communication device 410 to the second communication device 450, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocation, implementing L2 layer functions for the user plane and control plane. The controller / processor 459 is also responsible for retransmitting 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 spatial 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.

[0167] 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. In the transmission from the second communication device 450 to the first communication device 410, the controller / processor 475 provides multiplexing between the transmission and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover upper-layer data packets from the UE 450. Upper-layer packets from the controller / processor 475 can be provided to the core network.

[0168] As an example, the first node in this application includes the second communication device 450, and the second node in this application includes the first communication device 410.

[0169] As a sub-implementation of the above embodiments, the first node is a user equipment and the second node is a relay node.

[0170] As a sub-implementation of the above embodiments, the first node is a user equipment and the second node is a base station equipment.

[0171] As a sub-implementation of the above embodiments, the first node is a relay node and the second node is a base station device.

[0172] 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 first channel, on which a first bit block is transmitted;

[0173] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0174] As a sub-implementation of the above embodiments, the second communication device 450 corresponds to the first node in this application.

[0175] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that produces actions when executed by at least one processor, the actions including: receiving a first channel and transmitting a first bit block on the first channel;

[0176] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0177] As a sub-implementation of the above embodiments, the second communication device 450 corresponds to the first node in this application.

[0178] 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 first channel, on which a first bit block is transmitted;

[0179] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0180] As a sub-implementation of the above embodiments, the first communication device 410 corresponds to the second node in this application.

[0181] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that produces actions when executed by at least one processor, the actions including: transmitting a first channel, and transmitting a first bit block on the first channel;

[0182] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0183] As a sub-implementation of the above embodiments, the first communication device 410 corresponds to the second node in this application.

[0184] As an example, the first node in this application includes the second communication device 450.

[0185] As an example, the second node in this application includes the first communication device 410.

[0186] As an example, at least one of {the antenna 452, the receiver 454, the multi-antenna receiving processor 458, the receiving processor 456, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first signaling in this application.

[0187] As an example, at least one of {the antenna 420, the transmitter 418, the multi-antenna transmitter processor 471, the transmitter processor 416, the controller / processor 475, and the memory 476} is used to transmit the first signaling in this application.

[0188] As an example, at least one of {the antenna 452, the receiver 454, the multi-antenna receiver processor 458, the receiver processor 456, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first channel in this application.

[0189] As an example, at least one of {the antenna 420, the transmitter 418, the multi-antenna transmitter processor 471, the transmitter processor 416, the controller / processor 475, and the memory 476} is used to transmit the first channel in this application.

[0190] As an example, at least one of {the antenna 452, the receiver 454, the multi-antenna receiving processor 458, the receiving processor 456, the controller / processor 459, the memory 460, and the data source 467} is used to receive the second signaling in this application.

[0191] As an example, at least one of {the antenna 420, the transmitter 418, the multi-antenna transmitter processor 471, the transmitter processor 416, the controller / processor 475, and the memory 476} is used to transmit the second signaling in this application.

[0192] As an example, at least one of {the antenna 452, the receiver 454, the multi-antenna receiving processor 458, the receiving processor 456, the controller / processor 459, the memory 460, and the data source 467} is used to receive the second channel in this application.

[0193] As an example, at least one of {the antenna 420, the transmitter 418, the multi-antenna transmitter processor 471, the transmitter processor 416, the controller / processor 475, and the memory 476} is used to transmit the second channel in this application.

[0194] As an example, at least one of {the antenna 452, the transmitter 454, the multi-antenna transmitter processor 457, the transmitter processor 468, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the third signaling in this application.

[0195] As an example, at least one of {the antenna 420, the receiver 418, the multi-antenna receiving processor 472, the receiving processor 470, the controller / processor 475, and the memory 476} is used to receive the third signaling in this application.

[0196] Example 5

[0197] Example 5 illustrates a signal transmission flowchart according to an embodiment of this application, as shown in Figure 5. In Figure 5, the first node N1 and the second node N2 communicate via an air interface. In Figure 5, the steps in the dashed box F1 are optional.

[0198] The first node N1 receives the first signaling in step S511 and the first channel in step S512.

[0199] The second node N2 sends the first signaling in step S521 and sends the first channel in step S522.

[0200] In embodiment 5, a first bit block is transmitted on the first channel; whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first ID identifying at least one ML model; the first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before the first bit block is correctly decoded; when the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID;

[0201] The first channel is associated with the first ID, including: a signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset; or, the first channel is associated with the first ID, including: information obtained from measurements of the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0202] As a sub-example of Example 5, when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

[0203] As a sub-example of embodiment 5, when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, whether the first channel is associated with the first ID depends on the indication of the first signaling.

[0204] As an example, the first node N1 is the first node in this application.

[0205] As an example, the second node N2 is the second node in this application.

[0206] In one embodiment, the second node N2 and the first node N1 are a base station and a user equipment, respectively.

[0207] In one embodiment, both the second node N2 and the first node N1 are user equipment.

[0208] As one example, the second node N2 is the serving cell sustaining base station of the first node N1.

[0209] As one embodiment, the air interface between the second node N2 and the first node N1 is a Uu interface.

[0210] As one embodiment, the air interface between the second node N2 and the first node N1 includes a cellular link.

[0211] As one embodiment, the air interface between the second node N2 and the first node N1 includes a wireless interface between the base station equipment and the user equipment.

[0212] As one embodiment, the air interface between the second node N2 and the first node N1 includes a wireless interface between satellite equipment and user equipment.

[0213] As one embodiment, the air interface between the second node N2 and the first node N1 includes a wireless interface between the relay device and the user equipment.

[0214] As an example, an ML model is based on a neural network.

[0215] As an example, an ML model is based on CNN (Conventional Neural Networks).

[0216] As an example, an ML model is based on the Transformer architecture.

[0217] As an example, the output of an ML inference includes channel information, such as a channel matrix or CSI.

[0218] As an example, the steps in the dashed box F1 are present.

[0219] As an example, the steps in the dashed box F1 are not present.

[0220] As an example, the first node also sends feedback information indicating that the first bit block has been correctly decoded, and the second node receives the feedback information.

[0221] Example 6

[0222] Example 6 illustrates a schematic diagram of a first channel being associated with a first ID according to an embodiment of this application, as shown in FIG6.

[0223] In Example 6, the first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset; wherein the first ID indicates the target dataset.

[0224] As one embodiment, the first channel not being associated with the first ID includes: the signal on the first channel not belonging to the target dataset.

[0225] As an example, the target dataset is used for training the at least one ML model.

[0226] As an example, the target dataset is used for reinforcement learning of the at least one ML model.

[0227] As an example, the target dataset is used for performance monitoring of the at least one ML model.

[0228] As an example, the target dataset is used for testing the at least one ML model.

[0229] As an example, the target dataset is used as input for inference based on the at least one ML model.

[0230] As an example, the target dataset is used for training one or more ML models in the at least one ML model.

[0231] As an example, the target dataset is used for reinforcement learning of one or more ML models in the at least one ML model.

[0232] As an example, the target dataset is used for performance monitoring of one or more ML models in the at least one ML model.

[0233] As an example, the target dataset is used for testing one or more ML models in the at least one ML model.

[0234] As an example, the target dataset is used as input for inference based on one or more of the at least one ML model.

[0235] Example 7

[0236] Example 7 illustrates a schematic diagram of a first channel being associated with a first ID according to an embodiment of the present application, as shown in Figure 7.

[0237] In embodiment 7, the first channel is associated with the first ID, including: information obtained from measurements of the first channel belongs to the target dataset; wherein the first ID indicates the target dataset.

[0238] As an example, the advantages of the above method include: it helps to optimize the target dataset, thereby improving the corresponding ML model.

[0239] As one example, the first channel is not associated with the first ID, including: the target dataset does not include information obtained based on measurements for the first channel.

[0240] As an example, the target dataset is used for training the at least one ML model.

[0241] As an example, the target dataset is used for reinforcement learning of the at least one ML model.

[0242] As an example, the target dataset is used for performance monitoring of the at least one ML model.

[0243] As an example, the target dataset is used for testing the at least one ML model.

[0244] As an example, the target dataset is used as input for inference based on the at least one ML model.

[0245] As an example, the target dataset is used for training one or more ML models in the at least one ML model.

[0246] As an example, the target dataset is used for reinforcement learning of one or more ML models in the at least one ML model.

[0247] As an example, the target dataset is used for performance monitoring of one or more ML models in the at least one ML model.

[0248] As an example, the target dataset is used for testing one or more ML models in the at least one ML model.

[0249] As an example, the target dataset is used as input for inference based on one or more of the at least one ML model.

[0250] As an example, the information obtained from the measurement for the first channel includes channel information.

[0251] As an example, the information obtained from the measurement for the first channel includes a channel matrix.

[0252] As an example, the information obtained from the measurement of the first channel includes the channel matrix corresponding to the measured first channel.

[0253] As an example, the measurement for the first channel includes the measurement of the DM-RS (Demodulation Reference Signal) corresponding to the first channel.

[0254] Example 8

[0255] Example 8 illustrates a schematic diagram of RAN (Radio Access Network) domain AI / ML function deployment 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.

[0256] 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.

[0257] ML training functionality can be deployed in a cross-domain management system or a domain-specific management system; the domain-specific management system is used to manage the RAN domain or the CN (Core Network) domain. For example, ML training functionality for MDA (Management Data Analytics) can be deployed on MDAF (MDA Function); ML training for network data analytics can be deployed on NWDAF (Network Data Analytics Function), meaning the ML training functionality is an MTLF (Model Training Logical Function).

[0258] 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 MDAF, or the ML inference function is AnLF (Analytics logical function) located in NWDAF.

[0259] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[0260] 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.

[0261] 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 MnS (Management Service) consumer / cross-domain management 1401 (as shown by the dashed arrow in Figure 8).

[0262] 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.

[0263] 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.

[0264] As an example, one of the gNBs (or base stations) in Example 8 is the second node of this application.

[0265] As an example, the second node includes one of the AL / ML inference functions in Figure 8, namely 1404 or 1406.

[0266] Example 9

[0267] Example 9 illustrates a schematic diagram of the AI / ML function deployment of 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.

[0268] UE function 1504 is deployed in the first node of this application, and the UE function 1504 includes AI / ML inference function 1506; the AI / ML inference function 1506 uses an ML model (also called an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[0269] As an example, the UE function 1504 includes a RAN domain ML training function 1505, which runs training data through an ML model to obtain a relevant loss and adjusts the parameters of the ML model based on the calculated loss; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0270] 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.

[0271] Optionally, the UE function 1504 also includes a CN domain ML training function (not shown in Figure 9).

[0272] Optionally, the UE function 1504 also includes an AI / ML deployment function—not shown in Figure 9—for loading ML models and data.

[0273] 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 NAS (Non-Access Stratum) signaling.

[0274] As an example, the ML model and the associated metadata are loaded by the first node from a network device or a remote server.

[0275] As an example, the first node loads the at least one ML model.

[0276] As an example, the first node can load multiple ML models, where the at least one ML model is a proper subset of the multiple ML models, and the ML models other than the at least one ML model are identified by an ID other than the first ID.

[0277] Optionally, the UE function 1504 is an MnS (Management Service) producer that provides data to the CN domain MnF (Management Function) 1501, and / or the RAN domain MnF 1502, and / or the cross-domain management system 1503 for management or analysis (as shown by double arrow 1507).

[0278] Optionally, the UE function 1504 is an MnS consumer that loads data from the CN domain MnF (Management Function) 1501, and / or the RAN domain MnF 1502, and / or the 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).

[0279] As an example, the second signaling in this application includes content inferred by the AI / ML inference function 1506.

[0280] As an example, the first node includes an AL / ML inference function 1506 in Figure 9.

[0281] As an example, the ML model is based on a neural network.

[0282] As an example, the ML model is based on CNN (Conventional Neural Networks).

[0283] As an example, the ML model is based on the Transformer architecture.

[0284] Example 10

[0285] 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.

[0286] 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.

[0287] As one embodiment, the sixth processor includes ML testing functionality.

[0288] As an example, the sixth processor includes performance monitoring / evaluation of the ML model.

[0289] 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.

[0290] As one embodiment, the sixth processor sends a second type of feedback to the third processor, the second type of feedback being used to generate the first dataset or the second dataset, or the second type of feedback being used to trigger the sending of the first dataset or the second dataset.

[0291] As one embodiment, the third processor generates the first dataset and the second dataset based on the measurement of the reference signal.

[0292] As one embodiment, the fifth processor belongs to the first node, and the sixth processor belongs to the second node.

[0293] As an example, the first type of output includes the first channel information.

[0294] As an example, the first type of output includes the index of the target reference signal.

[0295] As one embodiment, the second dataset includes measurements for the first reference signal, or includes measurements for the second reference signal.

[0296] As an example, the first dataset includes training data.

[0297] As an example, the fourth processor is used to train an ML model, and the trained model is described by the target first class of parameter sets.

[0298] As an example, the fourth processor belongs to the first node.

[0299] The above embodiments avoid passing the first dataset to the second node.

[0300] As one example, the fourth processor belongs to the second node.

[0301] The above embodiments support joint training and optimize system performance.

[0302] As an example, the fourth processor belongs to the core network.

[0303] The above embodiments support network-wide joint training, further optimizing system performance.

[0304] As an example, the second dataset includes inference data.

[0305] As an example, the fifth processor belongs to the first node.

[0306] As an example, the fifth processor constructs a model based on the target first type of parameter group, and then inputs the second dataset into the constructed model to obtain the first type of output.

[0307] 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.

[0308] 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.

[0309] 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 to be unsatisfactory.

[0310] As an example, the target first type of parameter group includes one or more of the following: convolution kernel size, number of convolution layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[0311] 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.

[0312] Example 11

[0313] 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 a first stage, the fifth operation belongs to a second stage, the sixth operation belongs to a third stage, and the seventh operation belongs to a fourth stage. In Figure 11, the lines with arrows indicate the sequence of the process.

[0314] 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.

[0315] As one embodiment, the first stage includes a training phase, the second stage includes an emulation phase, the third stage includes a deployment phase, and the fourth stage includes an emulation phase.

[0316] As an example, the first stage includes AI / ML model training.

[0317] As an example, the first stage includes AI / ML model training and AI / ML testing.

[0318] As an example, the AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[0319] As an example, the training of the AI / ML model depends on training data.

[0320] As an example, the AI / ML model training includes AI / ML entity validation.

[0321] As an example, the AI / ML entity verification is used to evaluate the performance of the AI / ML entity.

[0322] As an example, the AI / ML entity verification relies on verification data.

[0323] As an example, if the AI / ML entity verification results do not meet expectations, the AI / ML model will be retrained.

[0324] As an example, the AI / ML testing includes testing the validated AI / ML entities to estimate the performance of the trained AI / ML model.

[0325] 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.

[0326] As an example, the AI / ML test relies on test data.

[0327] As one embodiment, the second stage includes AI / ML simulation, which performs AI / ML entity inference in a simulation environment.

[0328] As an example, the AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using AI / ML entities.

[0329] As one embodiment, the second stage is optional.

[0330] 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 function.

[0331] As an example, the third stage is optional.

[0332] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[0333] As an example, the fourth stage includes AI / ML inference.

[0334] Example 12

[0335] Example 12 illustrates a schematic diagram of whether a first channel is associated with a first ID depending on whether the transmission of a first bit block on the first channel is the initial transmission of the first bit block, as shown in Figure 12.

[0336] In embodiment 12, the first node receives a first signaling; when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, whether the first channel is associated with the first ID follows the indication of the first signaling.

[0337] As an example, the first signaling indicates whether the signal on the first channel belongs to the target dataset.

[0338] As an example, the first signaling indicates whether information obtained based on measurements of the first channel belongs to the target dataset.

[0339] As one example, the first signaling schedules the first channel.

[0340] As an example, the first signaling is downlink scheduling signaling.

[0341] As an example, the first signaling is DCI (Downlink Control Information).

[0342] As an example, the first signaling is higher-layer signaling.

[0343] As an example, the first signaling is RRC layer signaling.

[0344] Example 13

[0345] Example 13 illustrates a schematic diagram of the relationship between a third signaling and a first channel according to an embodiment of this application, as shown in Figure 13.

[0346] In embodiment 13, the first node sends a third signaling; the first channel is associated with the first ID, and at least one of the indication content of the third signaling and the triggering of the third signaling depends on the reception of the first channel.

[0347] As an example, the second node in this application receives the third signaling.

[0348] As an example, the third signaling is physical layer signaling.

[0349] As an example, the third signaling is MAC layer signaling.

[0350] As an example, the advantages of the above method include: minimal delay in the indication taking effect.

[0351] As an example, the third signaling is higher-layer signaling.

[0352] As an example, the third signaling includes information for performance monitoring / evaluation of the ML model.

[0353] As an example, the indication content of the third signaling depends on the reception of the first channel.

[0354] As an example, the reception of the first channel includes the reception of signals on the first channel.

[0355] As one embodiment, the reception of the first channel includes measurements performed to obtain the channel matrix corresponding to the first channel.

[0356] As an example, the indication content of the third signaling depends on an ML model.

[0357] As an example, the indication content of the third signaling depends on one or more of the at least one ML model.

[0358] As an example, the indication content of the third signaling depends on the output inferred from one of the at least one ML models, and the input of the inference depends on the reception of the first channel.

[0359] As an example, the indication content of the third signaling includes an output inferred from one of the at least one ML models, the input of which depends on the reception of the first channel.

[0360] As an example, the input to the inference includes a signal on the first channel.

[0361] As an example, the input to the inference includes a channel matrix, which is obtained based on measurements for the first channel.

[0362] As an example, the output obtained from inference based on one of the at least one ML models includes channel information, such as a channel matrix or CSI (Channel State Information).

[0363] As an example, the triggering of the third signaling depends on the reception of the first channel.

[0364] As an example, the triggering of the third signaling depends on the ML model.

[0365] As an example, the triggering of the third signaling depends on one or more of the at least one ML model.

[0366] As an example, the triggering of the third signaling depends on the output inferred from one of the at least one ML models, and the input of the inference depends on the reception of the first channel.

[0367] As an example, the output obtained from inference based on one of the at least one ML models includes SINR (Signal-to-Interference-and-Noise Ratio), and the third signaling is triggered when the SINR is less than a predefined or configured threshold.

[0368] As an example, the output obtained from inference based on one of the at least one ML models includes SINR, and the third signaling is triggered when the SINR is not less than a predefined or configured threshold.

[0369] As an example, the average received power is obtained based on measurements of the signal on the first channel, and the third signaling is triggered when the average received power is less than a predefined or configured threshold.

[0370] As an example, the average received power is obtained based on measurements of the signal on the first channel, and the third signaling is triggered when the average received power is not less than a predefined or configured threshold.

[0371] As an example, the SINR is obtained based on measurements of the signal on the first channel, and the third signaling is triggered when the SINR is less than a predefined or configured threshold.

[0372] As an example, the SINR is obtained based on measurements of the signal on the first channel, and the third signaling is triggered when the SINR is not less than a predefined or configured threshold.

[0373] As one embodiment, the third signaling includes indication information of the first ID.

[0374] Example 14

[0375] Example 14 illustrates a schematic diagram illustrating the relationship between a third signaling, a first channel, and at least one reference signal according to an embodiment of this application, as shown in Figure 14.

[0376] In embodiment 14, the first node sends a third signaling; the first channel is associated with the first ID, and at least one of the indication content of the third signaling and the triggering of the third signaling depends on the reception of the first channel and at least one reference signal.

[0377] As an example, the second node in this application receives the third signaling.

[0378] As an example, the reception of the first channel includes the reception of signals on the first channel.

[0379] As one embodiment, the reception of the first channel includes measurements performed to obtain the channel matrix corresponding to the first channel.

[0380] As an example, the indication content of the third signaling depends on the reception of the first channel and the at least one reference signal.

[0381] As an example, the triggering of the third signaling depends on the reception of the first channel and the at least one reference signal.

[0382] As an example, the target channel quality is the best channel quality in the first channel quality group; the output obtained by inference from one of the at least one ML models includes the first channel quality, and the corresponding input includes the signal on the first channel; the first channel quality group includes the first channel quality.

[0383] As an example, each of the at least one reference signal is taken as input, and inference is performed according to the ML model to output a channel quality of one of the first channel quality groups.

[0384] As an example, one of the channel qualities in the first channel quality group is the estimated average received power under a given precoding.

[0385] As an example, one of the channel qualities in the first channel quality group is SINR.

[0386] As an example, a channel quality in the first channel quality group is calculated based on measurements of each of the at least one reference signal.

[0387] As an example, for the signal on the first channel, the corresponding channel quality is the estimated average received power under a given precoding; for each of the at least one reference signal, the corresponding channel quality is RSRP (Reference Signal Received Power).

[0388] As an example, the third signaling is physical layer signaling.

[0389] As an example, the third signaling is MAC layer signaling.

[0390] As an example, the advantages of the above method include: minimal delay in the indication taking effect.

[0391] As an example, the third signaling is higher-layer signaling.

[0392] As an example, the third signaling indicates the signal corresponding to the target channel quality.

[0393] As an example, the third signaling is triggered when the signal corresponding to the target channel quality is the signal on the first channel.

[0394] As an example, the at least one reference signal is a downlink reference signal.

[0395] As an example, the at least one reference signal is used for channel detection.

[0396] As an example, the at least one reference signal is CSI-RS (Channel State Information Reference Signal).

[0397] As one embodiment, the third signaling includes indication information of the first ID.

[0398] Example 15

[0399] Example 15 illustrates a signal transmission flowchart according to an embodiment of this application, as shown in Figure 15. In Figure 15, the first node N3 and the second node N4 communicate via an air interface. In Figure 15, the steps in the dashed box F2 are optional.

[0400] The first node N3 receives the first channel in step S1511; receives the second signaling in step S1512; and receives the second channel in step S1513.

[0401] The second node N4 transmits the first channel in step S1521; transmits the second signaling in step S1522; and transmits the second channel in step S1523.

[0402] In embodiment 15, a first bit block is transmitted on the first channel and also on the second channel, which is later than the first channel. The first bit block is correctly decoded after being received on the second channel. The first channel is not associated with a first ID, or whether the first channel is associated with the first ID depends on the indication of the second signaling. The first ID identifies at least one ML model.

[0403] As a sub-example of Example 15, the first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0404] As a sub-example of Example 15, the first channel is associated with the first ID, including: information obtained from measurements of the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0405] In Example 15, the first bit block was not correctly decoded before the second channel was received.

[0406] In Figure 15, the transmission / reception of the first channel precedes the transmission / reception of the second signaling; alternatively, the transmission / reception of the first channel may also occur after the transmission / reception of the second signaling.

[0407] As an example, the first node N3 is the first node in this application.

[0408] As an example, the second node N4 is the second node in this application.

[0409] In one embodiment, the second node N4 and the first node N3 are a base station and a user equipment, respectively.

[0410] In one embodiment, both the second node N4 and the first node N3 are user equipment.

[0411] As one example, the second node N4 is the serving cell sustaining base station of the first node N3.

[0412] As one embodiment, the air interface between the second node N4 and the first node N3 is a Uu interface.

[0413] As one embodiment, the air interface between the second node N4 and the first node N3 includes a cellular link.

[0414] As one embodiment, the air interface between the second node N4 and the first node N3 includes a wireless interface between the base station equipment and the user equipment.

[0415] As one embodiment, the air interface between the second node N4 and the first node N3 includes a wireless interface between satellite equipment and user equipment.

[0416] As one embodiment, the air interface between the second node N4 and the first node N3 includes a wireless interface between the relay device and the user equipment.

[0417] As an example, an ML model is based on a neural network.

[0418] As an example, an ML model is based on CNN (Conventional Neural Networks).

[0419] As an example, an ML model is based on the Transformer architecture.

[0420] As an example, the output of an ML inference includes channel information, such as a channel matrix or CSI.

[0421] As an example, the steps in the dashed box F2 are present.

[0422] As an example, the steps in the dashed box F2 are not present.

[0423] As an example, the first node also sends feedback information indicating that the first bit block was not correctly decoded after receiving the first channel, and the second node receives the feedback information.

[0424] As an example, the first node also sends feedback information indicating that the first bit block was correctly decoded after receiving the second channel, and the second node receives the feedback information.

[0425] As one example, the second channel is a channel used for transmitting data.

[0426] As one embodiment, the second channel is a channel used for transmitting control information.

[0427] As one example, the second channel is a downlink channel.

[0428] As one example, the second channel is a physical layer channel.

[0429] As an example, the second channel is PDSCH.

[0430] As an example, the second channel is PDCCH.

[0431] As an example, from a time domain perspective, the second channel follows the first channel, and the two do not overlap in time domain.

[0432] As one embodiment, receiving the second channel includes: performing signal reception on the second channel.

[0433] As one embodiment, receiving the second channel includes: receiving at least the first bit block on the second channel.

[0434] As an example, the transmission of the first bit block on the second channel is a retransmission of the first bit block.

[0435] As an example, the transmission of the first bit block on the first channel is the initial transmission of the first bit block.

[0436] As an example, the first bit block is also transmitted on at least one channel preceding the first channel.

[0437] As an example, the first node will perform decoding on the first bit block after merging the signals received on the first channel and the second channel.

[0438] As an example, the first bit block is correctly decoded after being received on the second channel, and the transmission of the first bit block on the second channel is the last transmission of the first bit block before it is correctly decoded.

[0439] As an example, the first bit block is correctly decoded after being received on the second channel, and the first channel is not associated with the first ID.

[0440] As one embodiment, the second signaling schedules the second channel.

[0441] As one example, the second signaling is downlink scheduling signaling.

[0442] As an example, the second signaling is DCI.

[0443] As one example, the second signaling is higher-layer signaling.

[0444] As an example, the second signaling is RRC layer signaling.

[0445] As an example, whether the first channel is associated with the first ID follows the indication of the second signaling.

[0446] As an example, the second signaling at least indicates whether the signal on the first channel belongs to the target dataset.

[0447] As one embodiment, the second signaling indicates whether the signal on the channel(s) preceding the second channel for transmitting the first bit block belongs to the target dataset.

[0448] As one embodiment, the second signaling at least indicates whether the information obtained based on measurements of the first channel belongs to the target dataset.

[0449] As an example, the second signaling indicates whether information obtained from measurements of the channel(s) used to transmit the first bit block prior to the second channel belongs to the target dataset.

[0450] As an example, when the transmission of the first bit block on the first channel is the initial transmission of the first bit block and a first condition is met, the first channel is associated with the first ID; the first condition includes: the first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before the first bit block is correctly decoded.

[0451] When the second condition is met, the first channel is not associated with the first ID, or whether the first channel is associated with the first ID depends on the signaling indication; the second condition includes: the first bit block is correctly decoded, and the transmission of the first bit block on a channel following the first channel is the last transmission of the first bit block before the first bit block was correctly decoded.

[0452] Example 16

[0453] Example 16 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application, as shown in Figure 16. In Figure 16, the processing apparatus A00 in the first node includes a first receiver A01 and a first transmitter A02.

[0454] As one example, the first node is a user equipment.

[0455] As an example, the first node is a relay node.

[0456] As one example, the first node is an in-vehicle communication device.

[0457] As an example, the first receiver A01 includes at least one of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460, and data source 467.

[0458] As an example, the first receiver A01 includes at least the first five of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiver processor 458, receiver processor 456, controller / processor 459, memory 460, and data source 467.

[0459] As one embodiment, the first receiver A01 includes at least the first four of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460, and data source 467.

[0460] As one embodiment, the first receiver A01 includes at least the first three of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460, and data source 467.

[0461] As one embodiment, the first receiver A01 includes at least two of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460, and data source 467.

[0462] As an example, the first transmitter A02 includes at least one of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0463] As an example, the first transmitter A02 includes at least the first five of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0464] As an example, the first transmitter A02 includes at least the first four of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0465] As an example, the first transmitter A02 includes at least three of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0466] As one embodiment, the first transmitter A02 includes at least two of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0467] As one embodiment, the first receiver A01 receives a first channel, and a first bit block is transmitted on the first channel;

[0468] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0469] As an example, the first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before it is correctly decoded.

[0470] As an example, when the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID.

[0471] As an example, when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

[0472] As one embodiment, the first receiver A01 receives the first signaling;

[0473] Whether the first channel is associated with the first ID depends on the indication of the first signaling when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block.

[0474] As one embodiment, the first receiver A01 receives a second channel, the first bit block is transmitted on the second channel, and the second channel is later than the first channel;

[0475] Wherein, the first bit block is correctly decoded after being received by the second channel, and the first channel is not associated with the first ID.

[0476] As one embodiment, the first receiver A01 receives the second signaling;

[0477] The first receiver A01 receives the second channel, and the first bit block is transmitted on the second channel, which is later than the first channel;

[0478] The first bit block is correctly decoded after being received by the second channel, and whether the first channel is associated with the first ID depends on the indication of the second signaling.

[0479] As one embodiment, the first channel is associated with the first ID; the first transmitter A02 sends a third signaling;

[0480] In this case, at least one of the indication content of the third signaling and the triggering of the third signaling depends on the reception of the first channel.

[0481] As one embodiment, the first channel is associated with the first ID; the first transmitter A02 sends a third signaling;

[0482] The indication content of the third signaling and the triggering of the third signaling both depend on the reception of the first channel and at least one reference signal.

[0483] As an example, the third signaling is sent after the first channel is received.

[0484] As one embodiment, the third signaling is transmitted after the second channel is received.

[0485] As one embodiment, the first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0486] As one embodiment, the first channel is associated with the first ID, including: information obtained from measurements of the first channel belongs to a target dataset, and the first ID indicates the target dataset.

[0487] Example 17

[0488] Example 17 illustrates a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application, as shown in Figure 17. In Figure 17, the processing apparatus B00 in the second node includes a second transmitter B01 and a second receiver B02.

[0489] In one embodiment, the second node is a base station.

[0490] As one example, the second node is a satellite device.

[0491] As one example, the second node is a relay node.

[0492] As one embodiment, the second node is one of the testing device, testing equipment, or testing instrument.

[0493] As one embodiment, the second transmitter B01 includes at least one of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0494] As one embodiment, the second transmitter B01 includes at least the first five of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0495] As one embodiment, the second transmitter B01 includes at least the first four of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0496] As one embodiment, the second transmitter B01 includes at least the first three of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0497] As one embodiment, the second transmitter B01 includes at least two of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0498] As one embodiment, the second receiver B02 includes at least one of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiving processor 472, receiving processor 470, controller / processor 475, and memory 476.

[0499] As one embodiment, the second receiver B02 includes at least the first five of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiver processor 472, receiver processor 470, controller / processor 475, and memory 476.

[0500] As one embodiment, the second receiver B02 includes at least the first four of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiving processor 472, receiving processor 470, controller / processor 475, and memory 476.

[0501] As one embodiment, the second receiver B02 includes at least the first three of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiving processor 472, receiving processor 470, controller / processor 475, and memory 476.

[0502] As one embodiment, the second receiver B02 includes at least two of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiving processor 472, receiving processor 470, controller / processor 475, and memory 476.

[0503] As one embodiment, the second transmitter B01 transmits through the first channel, and the first bit block is transmitted on the first channel;

[0504] Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

[0505] As an example, the first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before it is correctly decoded.

[0506] As an example, when the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID.

[0507] As an example, when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

[0508] As one embodiment, the second transmitter B01 sends a first signaling;

[0509] Whether the first channel is associated with the first ID depends on the indication of the first signaling when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block.

[0510] As one embodiment, the second transmitter B01 transmits through a second channel, on which the first bit block is transmitted, and the second channel is later than the first channel;

[0511] Wherein, the first bit block is correctly decoded after being received by the second channel, and the first channel is not associated with the first ID.

[0512] As one embodiment, the second transmitter B01 sends a second signaling;

[0513] The second transmitter B01 transmits through the second channel, on which the first bit block is transmitted, and the second channel is later than the first channel;

[0514] The first bit block is correctly decoded after being received by the second channel, and whether the first channel is associated with the first ID depends on the indication of the second signaling.

[0515] As one embodiment, the first channel is associated with the first ID; the second receiver B02 receives the third signaling;

[0516] In this case, at least one of the indication content of the third signaling and the triggering of the third signaling depends on the reception of the first channel.

[0517] As one embodiment, the first channel is associated with the first ID; the second receiver B02 receives the third signaling;

[0518] The indication content of the third signaling and the triggering of the third signaling both depend on the reception of the first channel and at least one reference signal.

[0519] As one embodiment, the first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset.

[0520] As one embodiment, the first channel is associated with the first ID, including: information obtained from measurements of the first channel belongs to a target dataset, and the first ID indicates the target dataset.

[0521] 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. Correspondingly, 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 cards, IoT terminals, RFID (Radio Frequency Identification) terminals, NB-IoT (Narrow Band Internet of Things) terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base station or system equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNB (evolved Node B), gNB, TRP, GNSS (Global Navigation Satellite System), relay satellites, satellite base stations, airborne base stations, RSUs, unmanned aerial vehicles, and test equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[0522] 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 a terminal, characterized in that, include: Receive the first channel, and transmit the first bit block on the first channel; Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

2. The method according to claim 1, characterized in that, The first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before it is correctly decoded.

3. The method according to claim 1 or 2, characterized in that, When the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID.

4. The method according to any one of claims 1 to 3, characterized in that, When the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

5. The method according to any one of claims 1 to 3, characterized in that, include: Receive the first signaling; Whether the first channel is associated with the first ID depends on the indication of the first signaling when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block.

6. The method according to claim 1, characterized in that, include: Receive a second channel, on which the first bit block is transmitted, and the second channel is later than the first channel; Wherein, the first bit block is correctly decoded after being received by the second channel, and the first channel is not associated with the first ID.

7. The method according to any one of claims 1 to 6, characterized in that, The first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset.

8. 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 7.

9. A method for a base station, characterized in that, include: The first channel is transmitted, and the first bit block is transmitted on the first channel; Whether the first channel is associated with a first ID depends on whether the transmission of the first bit block on the first channel is the initial transmission of the first bit block, where the first ID identifies at least one ML model.

10. The method according to claim 9, characterized in that, The first bit block is correctly decoded, and the transmission of the first bit block on the first channel is the last transmission of the first bit block before it is correctly decoded.

11. The method according to claim 9 or 10, characterized in that, When the transmission of the first bit block on the first channel is the initial transmission of the first bit block, the first channel is associated with the first ID.

12. The method according to any one of claims 9 to 11, characterized in that, When the transmission of the first bit block on the first channel is not the initial transmission of the first bit block, the first channel is not associated with the first ID.

13. The method according to any one of claims 9 to 11, characterized in that, include: Send the first signaling; Whether the first channel is associated with the first ID depends on the indication of the first signaling when the transmission of the first bit block on the first channel is not the initial transmission of the first bit block.

14. The method according to claim 9, characterized in that, include: The first bit block is transmitted on a second channel, which is later than the first channel. Wherein, the first bit block is correctly decoded after being received by the second channel, and the first channel is not associated with the first ID.

15. The method according to any one of claims 9 to 13, characterized in that, The first channel is associated with the first ID, including: the signal on the first channel belongs to the target dataset, and the first ID indicates the target dataset.

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 9 to 15.

Images