Information block reception-related method and apparatus for use in node for wireless communication

Abstract

The present application discloses an information block reception-related method and apparatus for use in a node for wireless communication. Provided is a method for a terminal, comprising: receiving a target information block; and sending first indication information, candidate values of the first indication information comprising a first candidate subset and a first candidate value, and the first candidate subset comprising a plurality of candidate values, wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, at least one candidate value in the first candidate subset further indicates information related to an ML model other than that the target information block is not correctly received, and the first candidate value indicates that the target information block is correctly received.

Description

Method and apparatus related to information block reception in a node for wireless communication

[0001] This application claims priority to the Chinese patent application No. 202411337132.3, filed on September 24, 2024, entitled “Method and apparatus related to information block reception in a node for wireless communication”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to a transmission method and apparatus in a wireless communication system, in particular, a transmission method and apparatus of a wireless signal in a wireless communication system supporting a cellular network. BACKGROUND

[0003] With the continuous progress and deepening application of various technologies including AI (Artificial Intelligence) / ML (Machine Learning) technology, the ability of the network side to process and utilize information will be increasingly enhanced. In order to fully utilize the capabilities of the network side to optimize system scheduling, more effective information needs to be provided for the network side to make decisions. SUMMARY

[0004] How to enhance the reporting of feedback information of a terminal applying ML technology is a problem worth studying. In view of the above problem, the present application discloses a solution. It should be noted that the present application can be applied to various wireless communication scenarios, such as 5G networks, 6G networks, Internet of Things, etc., and similar technical effects can be achieved. In addition, the adoption of a unified solution in different scenarios (including but not limited to 5G networks, 6G networks, Internet of Things) helps to reduce hardware complexity and cost. In the case of no conflict, the embodiments in the first node and the features in the embodiments of the present application can be applied to the second node, and vice versa. In the case of no conflict, the embodiments of the present application and the features in the embodiments can be arbitrarily combined with each other.

[0005] As an embodiment, the explanation of the terms in the present application is based on the definition of the specification agreement TS38 series of 3GPP.

[0006] As an embodiment, the explanation of the terms in the present application is based on the definition of the specification agreement TS28 series of 3GPP.

[0007] The present application discloses a method in a first node used for wireless communication, characterized in that, comprising:

[0008] receiving a target information block;

[0009] transmitting first indication information, candidate values of the first indication information including a first candidate subset and a first candidate value, the first candidate subset including a plurality of candidate values;

[0010] wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to the ML model in addition to the target information block not being correctly received; and the first candidate value indicates that the target information block is correctly received.

[0011] As an embodiment, the first node is a terminal.

[0012] As an embodiment, the problem to be solved by the present application includes how to feed back information about whether an information block is correctly received or not and information related to the ML model.

[0013] As an embodiment, the problem to be solved by the present application includes how to efficiently report more information to the base station for decision-making.

[0014] As an embodiment, the above method can report additional information in the case that the target information block is not correctly received, so as to facilitate subsequent retransmission of the target information block.

[0015] As an embodiment, the above method is beneficial to distinguish different states in which the target information block is not correctly received, and is beneficial to the network side to obtain more terminal reception information.

[0016] As an embodiment, AI / ML technology has great potential in improving communication performance; by reporting information related to the ML model through the above method, it is beneficial to improve communication performance and efficiency.

[0017] As an embodiment, the benefits of the above method include: it is beneficial to improve the ML model or enhance the use effect of the ML model by reporting information related to the ML model.

[0018] As an embodiment, the advantage of the scheme disclosed by the present application is that the reception result of the target information block and the corresponding ML model related information are jointly indicated, which is beneficial to save indication overhead, and the utilization efficiency of the indication information is high.

[0019] According to an aspect of the present application, the above method is characterized in that,

[0020] In the candidate values of the first indication information, only the first candidate value indicates that the target information block is correctly received.

[0021] According to an aspect of the present application, the above method is characterized in that,

[0022] The first candidate subset includes a second candidate value; the second candidate value indicates a first ID (identity), the first ID identifying at least one ML model.

[0023] According to an aspect of the present application, the above method is characterized in that,

[0024] The first candidate subset includes a third candidate value, the third candidate value indicating that an encoding manner corresponding to the first ML model is used for retransmission of the target information block.

[0025] According to an aspect of the present application, the above method is characterized in that,

[0026] The first candidate subset includes a fourth candidate value, the fourth candidate value indicating that an encoding manner corresponding to a traditional decoder is used for retransmission of the target information block.

[0027] According to an aspect of the present application, the above method is characterized in that,

[0028] The first candidate subset includes a fifth candidate value, the fifth candidate value indicating that a speed matching manner corresponding to the first ML model is used for retransmission of the target information block.

[0029] According to an aspect of the present application, the above method is characterized in that,

[0030] The first candidate subset includes a sixth candidate value, the sixth candidate value only indicating that the target information block is not correctly received.

[0031] According to an aspect of the present application, the above method is characterized in that,

[0032] The target information block includes one transport block, and the first indication information includes multiple bits.

[0033] The present application discloses a method used in a second node for wireless communication, characterized in that, comprising:

[0034] transmitting a target information block;

[0035] receiving first indication information, candidate values of the first indication information including a first candidate subset and a first candidate value, the first candidate subset including multiple candidate values;

[0036] wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to an ML model in addition to that the target information block is not correctly received; the first candidate value indicates that the target information block is correctly received.

[0037] As an embodiment, the second node is a base station.

[0038] As an embodiment, the second node is a network-side device.

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

[0040] Among the candidate values of the first indication information, only the first candidate value indicates that the target information block is correctly received.

[0041] According to an aspect of the present application, the above method is characterized in that,

[0042] The first candidate subset includes a second candidate value; the second candidate value indicates a first ID, and the first ID identifies at least one ML model.

[0043] According to an aspect of the present application, the above method is characterized in that,

[0044] The first candidate subset includes a third candidate value, and the third candidate value indicates that an encoding mode corresponding to a first ML model is used for retransmission of the target information block.

[0045] According to an aspect of the present application, the above method is characterized in that,

[0046] The first candidate subset includes a fourth candidate value, and the fourth candidate value indicates that an encoding mode corresponding to a traditional decoder is used for retransmission of the target information block.

[0047] According to an aspect of the present application, the above method is characterized in that,

[0048] The first candidate subset includes a fifth candidate value, and the fifth candidate value indicates that a speed matching mode corresponding to a first ML model is used for retransmission of the target information block.

[0049] According to an aspect of the present application, the above method is characterized in that,

[0050] The first candidate subset includes a sixth candidate value, and the sixth candidate value only indicates that the target information block is not correctly received.

[0051] According to an aspect of the present application, the above method is characterized in that,

[0052] The target information block includes one transport block, and the first indication information includes multiple bits.

[0053] The present application discloses a first node used for wireless communication, characterized in that, comprising:

[0054] A first receiver receives a target information block.

[0055] a first transmitter configured to transmit first indication information, candidate values of the first indication information including a first candidate subset and a first candidate value, the first candidate subset including a plurality of candidate values;

[0056] wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to the ML model in addition to that the target information block is not correctly received; and the first candidate value indicates that the target information block is correctly received.

[0057] The present application discloses a second node for wireless communication, characterized in that it comprises:

[0058] a second transmitter configured to transmit a target information block;

[0059] a second receiver configured to receive first indication information, candidate values of the first indication information including a first candidate subset and a first candidate value, the first candidate subset including a plurality of candidate values;

[0060] wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to the ML model in addition to that the target information block is not correctly received; and the first candidate value indicates that the target information block is correctly received.

[0061] As an embodiment, the present application has the following advantages:

[0062] • The indication of the information block not being correctly received is enhanced;

[0063] • The retransmission efficiency is improved;

[0064] • The ML model is improved or the use effect of the ML model is enhanced;

[0065] • The utilization efficiency of the indication information is high;

[0066] • More terminal receiving information is provided for the network side, which is beneficial to system optimization. BRIEF DESCRIPTION OF DRAWINGS

[0067] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments thereof, read in conjunction with the accompanying drawings:

[0068] Fig. 1 shows a processing flowchart of a first node according to an embodiment of the present application;

[0069] Fig. 2 shows a schematic diagram of a network architecture according to an embodiment of the present application;

[0070] FIG. 3 shows a schematic diagram of a radio protocol architecture for the user and control planes according to one embodiment of the application;

[0071] FIG. 4 shows a schematic diagram of a first communication device and a second communication device according to one embodiment of the application;

[0072] FIG. 5 shows a signal transmission flow diagram according to one embodiment of the application;

[0073] FIG. 6 shows an explanatory schematic diagram of candidate values of first indication information according to one embodiment of the application;

[0074] FIG. 7 shows an explanatory schematic diagram of a first candidate subset according to one embodiment of the application;

[0075] FIG. 8 shows an explanatory schematic diagram of a first candidate subset according to one embodiment of the application;

[0076] FIG. 9 shows an explanatory schematic diagram of a first candidate subset according to one embodiment of the application;

[0077] FIG. 10 shows an explanatory schematic diagram of a second candidate subset according to one embodiment of the application;

[0078] FIG. 11 shows a schematic diagram of RAN (Radio Access Network) domain AI / ML function deployment according to one embodiment of the application;

[0079] FIG. 12 shows a schematic diagram of UE AI / ML function deployment according to one embodiment of the application;

[0080] FIG. 13 shows a schematic diagram of an artificial intelligence or machine learning based processing system according to one embodiment of the application;

[0081] FIG. 14 shows a flow diagram of an artificial intelligence or machine learning based processing according to one embodiment of the application;

[0082] FIG. 15 shows a structural block diagram of a processing apparatus for use in a first node according to one embodiment of the application;

[0083] FIG. 16 shows a structural block diagram of a processing apparatus for use in a second node according to one embodiment of the application. DETAILED DESCRIPTION

[0084] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily without conflict.

[0085] Embodiment 1

[0086] Embodiment 1 illustrates a process flowchart of a first node according to an embodiment of the present application, as shown in FIG. 1.

[0087] In Embodiment 1, the first node in the present application receives a target information block in step 101; and sends first indication information in step 102.

[0088] In Embodiment 1, candidate values of the first indication information include a first candidate subset and a first candidate value, the first candidate subset includes a plurality of candidate values, each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to the ML model in addition to the target information block not being correctly received; and the first candidate value indicates that the target information block is correctly received.

[0089] As an embodiment, the target information block includes a plurality of bits.

[0090] As an embodiment, the target information block includes user data.

[0091] As an embodiment, the target information block includes at least one transport block.

[0092] As an embodiment, the target information block is one transport block.

[0093] As an embodiment, the target information block is transmitted after at least channel coding.

[0094] As an embodiment, the target information block is transmitted after at least channel coding, modulation, and resource mapping.

[0095] As an embodiment, the target information block is transmitted after at least CRC (Cyclic Redundancy Check) addition, channel coding, rate matching, modulation, and resource mapping.

[0096] As an embodiment, the first indication information includes a plurality of bits.

[0097] As an embodiment, the first indication information includes RRC layer control information.

[0098] As an embodiment, the benefits of the above method include: high control information transmission reliability.

[0099] As an embodiment, the first indication information includes physical layer control information.

[0100] As an embodiment, the benefits of the above method include: small control delay.

[0101] As one embodiment, the first indication information comprises UCI (Uplink Control Information).

[0102] As one embodiment, the first indication information comprises HARQ-ACK (Hybrid Automatic Repeat reQuest Acknowledgement) information.

[0103] As one embodiment, the first indication information is transmitted after at least sequence generation and resource mapping.

[0104] As one embodiment, the first indication information is transmitted after at least channel coding.

[0105] As one embodiment, the first indication information is transmitted after at least channel coding, modulation and resource mapping.

[0106] As one embodiment, the first indication information is transmitted after at least CRC addition, channel coding, rate matching, modulation and resource mapping.

[0107] As one embodiment, the first indication information comprises a plurality of bits, the candidate values of the first indication information are a range of values of the first indication information.

[0108] As one embodiment, the first indication information comprises 2 bits, the candidate values of the first indication information comprise 00, 01, 10, 11, and the value of the first indication information is one of 00, 01, 10, 11.

[0109] As one sub-embodiment of the above embodiment, the first candidate value is 11, and the first candidate subset comprises 01, 10, 00.

[0110] As one sub-embodiment of the above embodiment, the first candidate subset comprises two of 00, 01, 10, 11; the second candidate subset comprises the other two of 00, 01, 10, 11, each candidate value in the second candidate subset indicates that the target information block is correctly received, and the first candidate value is one of the second candidate subset.

[0111] As one embodiment, the first indication information comprises 3 bits, the candidate values of the first indication information comprise 000, 001, 010, 011, 100, 101, 110, 111, and the value of the first indication information is one of 000, 001, 010, 011, 100, 101, 110, 111.

[0112] As a sub-embodiment of the above-mentioned embodiment, the first candidate value is 111, and the first candidate subset includes 001, 010, 011, 100, 101, 110, and 000.

[0113] As a sub-embodiment of the above-mentioned embodiment, the first candidate subset includes at least two of 000, 001, 010, 011, 100, 101, 110, and 111; the second candidate subset includes the rest of 000, 001, 010, 011, 100, 101, 110, and 111 except the first candidate subset, each candidate value in the second candidate subset indicates that the target information block is correctly received, and the first candidate value is one of the second candidate subset.

[0114] As an embodiment, the candidate value of the first indication information is predefined.

[0115] As an embodiment, one of the candidate values of the first indication information is a decimal value.

[0116] As an embodiment, one of the candidate values of the first indication information can also be a predefined value other than a numerical value.

[0117] As an embodiment, the indication content of one candidate value of the first indication information is predefined.

[0118] As an embodiment, the indication content of one candidate value of the first indication information is configured.

[0119] As an embodiment, the first candidate value is one of the candidate values of the first indication information, and the first candidate subset is the rest of the candidate values of the first indication information except the first candidate value.

[0120] As an embodiment, the first candidate value is predefined.

[0121] As an embodiment, the value of the first indication information is one of the candidate values of the first indication information.

[0122] As an embodiment, one candidate value in the first candidate subset only indicates that the target information block is not correctly received.

[0123] As an embodiment, each candidate value in the first candidate subset indicates information other than that the target information block is not correctly received.

[0124] As an embodiment, at least one candidate value in the first candidate subset further indicates ML model dependent information other than that the target information block is not correctly received.

[0125] Embodiment 2

[0126] Embodiment 2 illustrates a diagram of a network architecture according to one embodiment of the application, as shown in FIG. 2. FIG. 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 can be referred to as a 5GS (5G System) / EPS (Evolved Packet System) 200 or some other suitable terminology. The 5GS / EPS 200 includes a UE (User Equipment) 201, a RAN (Radio Access Network) 202, a 5GC (5G Core Network, 5G Core Network) / EPC (Evolved Packet Core) 210, a HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and at least one of an Internet service 230. The 5GS / EPS can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown, the 5GS / EPS provides packet-switched services, however, one of skill in the art will readily appreciate that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN includes a node 203 and other nodes 204. The node 203 provides user and control plane protocol terminations toward the UE 201. The node 203 can be connected to the other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. The node 203 can also be referred to as a base station, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a Basic Service Set (BSS), an Extended Service Set (ESS), a TRP (Transmitter Receiver Point), or some other suitable terminology. The node 203 provides an access point to the 5GC / EPC 210 for a UE 201.Examples of UE 201 include a cellular phone, a smart phone, a Session Initiation Protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a non-terrestrial base station communication, a satellite mobile communication, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., MP3 player), a camera, a game console, a drone, a flying vehicle, a narrowband internet of things device, a machine type communication device, a land vehicle, a car, a wearable device, or any other similar functional device. Those skilled in the art will also Node 203 is connected by an S1 / NG interface to 5GC / EPC 210. 5GC / EPC 210 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 that processes the signaling between UE 201 and 5GC / EPC 210. Generally, MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocal) packets are transferred through S-GW / UPF 212, which is itself connected to P-GW / UPF 213. P-GW provides UE IP address allocation, as well as other functions. P-GW / UPF 213 is connected to Internet services 230. Internet services 230 include operator corresponding Internet protocol services, which can specifically include the Internet, an intranet, IMS (IP Multimedia Subsystem), and packet switching services.

[0127] It should be noted that the above embodiment 2 is only a non-limiting implementation; the solutions disclosed in this application are also applicable to other network architectures, such as the network architecture of a 6G system.

[0128] As one embodiment, the UE 201 corresponds to the first node in this application.

[0129] As one embodiment, the gNB 203 corresponds to the second node in this application.

[0130] As one embodiment, the wireless link between the UE 201 and the node 203 includes a cellular network link.

[0131] As one embodiment, the gNB 203 is a macro cellular (Marco Cellular) base station.

[0132] As one embodiment, the gNB 203 is a micro cell (Micro Cell) base station.

[0133] As one embodiment, the gNB 203 is a pico cell (Pico Cell) base station.

[0134] As one embodiment, the gNB 203 is a femto cell (Femtocell).

[0135] As one embodiment, the gNB 203 is a base station device supporting large latency difference.

[0136] As one embodiment, the gNB 203 is a flying platform device.

[0137] As one embodiment, the gNB 203 is a satellite device.

[0138] Embodiment 3

[0139] Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300, Figure 3 shows the radio protocol architecture for the control plane 300 between a first communication node device (UE, gNB or RSU (Road Side Unit) in V2X (Vehicle to Everything), a vehicle mounted device or a vehicle mounted communication module) and a second communication node device (gNB, UE or RSU in V2X, a vehicle mounted device or a vehicle mounted communication module), or between two UEs, in 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 as the PHY 301 herein. Layer 2 (L2 layer) 305 is above the PHY 301 and is responsible for the link between the first communication node device and the second communication node device and between two UEs through the PHY 301. The L2 305 includes a MAC (Medium Access Control) sublayer 302, a RLC (Radio Link Control) sublayer 303 and a PDCP (Packet Data Convergence Protocol) sublayer 304, which are terminated at the second communication node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. The PDCP sublayer 304 also provides security through encryption of data packets, and provides support for mobility of the first communication node device between the second communication node devices. The RLC sublayer 303 provides segmentation and reassembly of upper layer data packets, retransmission of lost data packets, and reordering of data packets to compensate for out-of-order reception due to HARQ (Hybrid Automatic Repeat Qequest). The MAC sublayer 302 provides multiplexing between logical and transport channels. The MAC sublayer 302 is also responsible for allocating the various radio resources (e.g., resource blocks) in one cell among the UEs. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in L3 in the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second communication node device and the first communication node device.The radio protocol architecture for the user plane 350 comprises Layer 1 (L1) and Layer 2 (L2) and is substantially the same as the corresponding layers and sublayers in the control plane 300 for the first communication node device and the second communication node device, except for the PDCP sublayer 354 in the L2 layer 355 in the user plane 350, which also provides header compression for upper layer data packets to reduce radio transmission overhead, but the radio protocol architecture for the user plane 350 does not include the RRC sublayer. The L2 layer 355 in the user plane 350 also includes an SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between a QoS (Quality of Service) flow and a data radio bearer (DRB) to support diverse service

[0140] As one embodiment, the wireless protocol architecture in FIG. 3 is applicable to the first node in the present application.

[0141] As one embodiment, the wireless protocol architecture in FIG. 3 is applicable to the second node in the present application.

[0142] As one embodiment, the target information block in the present application is generated at the PHY 351.

[0143] As one embodiment, the target information block in the present application is generated at the MAC sublayer 352.

[0144] As one embodiment, the target information block in the present application is generated at the SDAP sublayer 356.

[0145] As one embodiment, the first indication information in the present application is generated at the PHY 301.

[0146] As one embodiment, the first indication information in the present application is generated at the MAC sublayer 302.

[0147] Embodiment 4

[0148] Embodiment 4 shows a schematic diagram of a first communication device and a second communication device according to the present 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.

[0149] The first communication device 410 comprises a controller / processor 475, a memory 476, a receive processor 470, a transmit processor 416, a multi-antenna receive processor 472, a multi-antenna transmit processor 471, a transmitter / receiver 418 and an antenna 420.

[0150] The second communication device 450 comprises a controller / processor 459, a memory 460, a data source 467, a transmit processor 468, a receive processor 456, a multi-antenna transmit processor 457, a multi-antenna receive processor 458, a transmitter / receiver 454 and an antenna 452.

[0151] In the transmission from the first communication device 410 to the second communication device 450, at the first communication device 410, upper layer packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements functionality of the L2 layer. In the transmission from the first communication device 410 to the second communication device 450, the controller / processor 475 provides header compression, ciphering, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocations for the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for retransmission of lost packets, and signaling to the second communication device 450. The transmit processor 416 and the multiple antenna transmit processor 471 implement various signal processing functions for the LI layer (i.e., physical layer). The transmit processor 416 implements coding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and mapping of coded and interleaved data onto various signal constellations 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)). The multiple antenna transmit processor 471 performs digital spatial pre-coding of the coded and modulated symbols, including codebook-based and non-codebook-based pre-coding, and beamforming processing, to generate one or more spatial streams. The transmit processor 416 then maps to each spatial stream to the subcarriers, multiplexes with reference signals (e.g., pilot) in the time and / or frequency domain, and then performs an inverse fast Fourier transform (IFFT) to generate a time-domain multicarrier symbol stream for the physical channel. The multiple antenna transmit processor 471 then performs transmit analog pre-coding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multiple antenna transmit processor 471 into a radio frequency stream, and then provides the radio frequency stream to the corresponding antenna 420.

[0152] 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 respective antenna 452. Each receiver 454 recovers information modulated onto an RF carrier and converts the RF stream into a baseband multicarrier symbol stream, which is provided to the receive processor 456. The receive processor 456 and the multi-antenna receive processor 458 implement various signal processing functions of the Ll layer. The multi-antenna receive processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receivers 454. The receive processor 456 converts the baseband multicarrier symbol stream from the receive analog precoding / beamforming operations from the time domain to the frequency domain using a Fast Fourier Transform (FFT). In the frequency domain, the physical layer data signals and the reference signals are demultiplexed by the receive processor 456, where the reference signals will be used for channel estimation, and the data signals are recovered after multi-antenna detection in the multi-antenna receive processor 458 for any spatial streams destined for the second communication device 450. The symbols on each spatial stream are demodulated and recovered by the receive processor 456 and generate soft decisions. The receive processor 456 then decodes and de-interleaves the soft decisions to recover the upper layer data and control signals transmitted by the first communication device 410 on the physical channels. The upper layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of the L2 layer. The controller / processor 459 can be associated with a memory 460 that stores program codes and data. The memory 460 can be referred to as a computer-readable medium. In the transmission from the first communication device 410 to the second communication device 450, the controller / processor 459 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer data packets from the core network. The upper layer data packets are then provided to all protocol layers above the L2 layer. Various control signals can also be provided to the L3 for L3 processing.

[0153] 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 a controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmit function described at the first communication device 410 in the transmission from the first communication device 410 to the second communication device 450, the controller / processor 459 implements header compression, ciphering, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocations for the user plane and control plane. The controller / processor 459 is also responsible for retransmission of lost packets, and signaling to the first communication device 410. The transmit processor 468 performs modulation mapping, channel coding processing, multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, and then the transmit processor 468 modulates the generated spatial streams into multi-carrier / single-carrier symbol streams, which are then provided to different antennas 452 via the transmitters 454 after analog precoding / beamforming operations in the multi-antenna transmit processor 457. Each transmitter 454 first converts the baseband symbol stream provided by the multi-antenna transmit processor 457 into a radio frequency signal, and then provides the radio frequency signal to the antenna 452.

[0154] In the transmission from the second communication device 450 to the first communication device 410, the functions at the first communication device 410 are similar to the receive functions described at the second communication device 450 in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives a radio frequency signal through its respective antenna 420, converts the received radio frequency signal into a baseband signal, and provides the baseband signal to the multi-antenna receive processor 472 and the receive processor 470. The receive processor 470 and the multi-antenna receive processor 472 together implement the functionality of the L1 layer. The controller / processor 475 implements the functionality of the L2 layer. The controller / processor 475 can be associated with a memory 476 that stores program codes and data. The memory 476 can be referred to as a computer readable medium. In the transmission from the second communication device 450 to the first communication device 410, the controller / processor 475 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer data packets from the UE 450. Upper layer data packets from the controller / processor 475 can be provided to a core network.

[0155] As one embodiment, the first node in the present application comprises the second communication device 450, and the second node in the present application comprises the first communication device 410.

[0156] As one sub-example of the above embodiment, the first node is a user equipment and the second node is a relay node.

[0157] As one sub-example of the above embodiment, the first node is a user equipment and the second node is a base station equipment.

[0158] As one sub-example of the above embodiment, the first node is a relay node and the second node is a base station equipment.

[0159] As one embodiment, the second communication device 450 comprises at least one processor and at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the second communication device 450 to perform the following actions: receiving a target information block; transmitting first indication information, candidate values of the first indication information comprising a first candidate subset and a first candidate value, the first candidate subset comprising a plurality of candidate values; wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to a ML model in addition to the target information block not being correctly received; the first candidate value indicating that the target information block is correctly received.

[0160] As one sub-example of the above embodiment, the second communication device 450 corresponds to the first node in the present application.

[0161] As one embodiment, the second communication device 450 comprises a memory storing a computer readable program of instructions which, when executed by at least one processor, causes the actions comprising: receiving a target information block; transmitting first indication information, candidate values of the first indication information comprising a first candidate subset and a first candidate value, the first candidate subset comprising a plurality of candidate values; wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to a ML model in addition to the target information block not being correctly received; the first candidate value indicating that the target information block is correctly received.

[0162] As one sub-example of the above embodiment, the second communication device 450 corresponds to the first node in the present application.

[0163] As one embodiment, the first communication device 410 comprises: at least one processor and at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the performance of the following: transmitting a target information block; receiving first indication information, candidate values of the first indication information comprising a first candidate subset and a first candidate value, the first candidate subset comprising a plurality of candidate values; wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to a ML model in addition to the target information block not being correctly received; the first candidate value indicating that the target information block is correctly received.

[0164] As one sub-embodiment of the above-mentioned embodiment, the first communication device 410 corresponds to the second node in the present application.

[0165] As one embodiment, the first communication device 410 comprises: a memory storing a program of computer readable instructions to produce actions when executed by at least one processor, the actions comprising: transmitting a target information block; receiving first indication information, candidate values of the first indication information comprising a first candidate subset and a first candidate value, the first candidate subset comprising a plurality of candidate values; wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to a ML model in addition to the target information block not being correctly received; the first candidate value indicating that the target information block is correctly received.

[0166] As one sub-embodiment of the above-mentioned embodiment, the first communication device 410 corresponds to the second node in the present application.

[0167] As one embodiment, the first node in the present application comprises the second communication device 450.

[0168] As one embodiment, the second node in the present application comprises the first communication device 410.

[0169] As one embodiment, at least one of {the antenna 452, the transmitter 454, the multi-antenna transmission processor 457, the transmission processor 468, the controller / processor 459, the memory 460, the data source 467} is used to transmit the first indication information in the present application.

[0170] As an embodiment, at least one of {the antenna 420, the receiver 418, the multi-antenna reception processor 472, the reception processor 470, the controller / processor 475, the memory 476} is configured to receive the first indication information in the present application.

[0171] As an embodiment, at least one of {the antenna 452, the receiver 454, the multi-antenna reception processor 458, the reception processor 456, the controller / processor 459, the memory 460, the data source 467} is configured to receive the target information block in the present application.

[0172] As an embodiment, at least one of {the antenna 420, the transmitter 418, the multi-antenna transmission processor 471, the transmission processor 416, the controller / processor 475, the memory 476} is configured to transmit the target information block in the present application.

[0173] Embodiment 5

[0174] Embodiment 5 illustrates a signal transmission flowchart according to an embodiment of the present application, as shown in FIG. 5. In FIG. 5, the first node N1 and the second node N2 communicate through an air interface.

[0175] The first node N1 receives the target information block in step S511; and transmits the first indication information in step S512.

[0176] The second node N2 transmits the target information block in step S521; and receives the first indication information in step S522.

[0177] In embodiment 5, the candidate values of the first indication information include a first candidate subset and a first candidate value, the first candidate subset includes a plurality of candidate values; each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to the ML model in addition to the target information block not being correctly received; the first candidate value indicates that the target information block is correctly received.

[0178] As a sub-embodiment of embodiment 5, in the candidate values of the first indication information, only the first candidate value indicates that the target information block is correctly received.

[0179] As a sub-embodiment of embodiment 5, the first candidate subset includes a second candidate value; the second candidate value indicates a first ID, and the first ID identifies at least one ML model.

[0180] As a sub-example of Example 5, the first candidate subset includes a third candidate value, the third candidate value indicating that a coding manner corresponding to the first ML model is used for retransmission of the target information block.

[0181] As a sub-example of Example 5, the first candidate subset includes a fourth candidate value, the fourth candidate value indicating that a coding manner corresponding to a legacy decoder is used for retransmission of the target information block.

[0182] As a sub-example of Example 5, the first candidate subset includes a fifth candidate value, the fifth candidate value indicating that a speed adaptation matching manner corresponding to the first ML model is used for retransmission of the target information block.

[0183] As a sub-example of Example 5, the first candidate subset includes a sixth candidate value, the sixth candidate value only indicating that the target information block is not correctly received.

[0184] As a sub-example of Example 5, the target information block includes one transport block, and the first indication information includes multiple bits.

[0185] The various sub-examples of Example 5 can be combined with each other in any manner.

[0186] As an example, the first node N1 is the first node in the present application.

[0187] As an example, the second node N2 is the second node in the present application.

[0188] As an example, the second node N2 and the first node N1 are a base station and a user equipment, respectively.

[0189] As an example, the second node N2 is a serving cell maintaining base station of the first node N1.

[0190] As an example, the air interface between the second node N2 and the first node N1 is a Uu interface.

[0191] As an example, the air interface between the second node N2 and the first node N1 includes a cellular link.

[0192] As an example, the air interface between the second node N2 and the first node N1 includes a wireless interface between a base station device and a user equipment.

[0193] As an example, the air interface between the second node N2 and the first node N1 includes a wireless interface between a satellite device and a user equipment.

[0194] As an embodiment, the air interface between the second node N2 and the first node N1 comprises a wireless interface between a relay device and a user equipment.

[0195] As an embodiment, the initial transmission of the target information block is performed in step S521.

[0196] Embodiment 6

[0197] Embodiment 6 illustrates an explanatory diagram of candidate values of the first indication information according to an embodiment of the present application, as shown in FIG. 6.

[0198] In embodiment 6, the candidate values of the first indication information comprise a first candidate subset and a first candidate value; the first candidate value indicates that the target information block is correctly received; the first candidate subset comprises K candidate values; each of the K candidate values indicates that the target information block is not correctly received; at least K-1 of the K candidate values indicate other content in addition to indicating that the target information block is not correctly received, and K is greater than 1.

[0199] As an embodiment, the up-down order between the rows in the table in FIG. 6 does not represent a specific candidate value order; how the candidate values of the first indication information are ordered does not affect the effect of the scheme disclosed in the present application.

[0200] As an embodiment, the K is configurable.

[0201] As an embodiment, the K is predefined.

[0202] As an embodiment, at least one candidate value in the first candidate subset indicates other content in addition to indicating that the target information block is not correctly received, and the other content is content in a predefined content range.

[0203] As an embodiment, at least one candidate value in the first candidate subset indicates other content in addition to indicating that the target information block is not correctly received, and the other content is content in a configured content range.

[0204] As an embodiment, at least one of the indication content #1,..., the indication content #K-1, and the indication content #K depends on an ML model.

[0205] As an embodiment, the indication content #K exists.

[0206] As an embodiment, the indication content #K does not exist.

[0207] As an embodiment, the indication content #1,..., the indication content #K-1, and the indication content #K (if present) are different from each other.

[0208] As an embodiment, the candidate values of the first indication information are all values with specific indication content.

[0209] As an embodiment, when a value has no specific indication content, the value does not belong to the candidate values of the first indication information.

[0210] As an embodiment, the other information (other than that the target information block is not correctly received) indicated by the candidate values in the first candidate subset is for providing the second node to make a decision.

[0211] Embodiment 7

[0212] Embodiment 7 illustrates an illustrative diagram of a first candidate subset according to an embodiment of the present application, as shown in FIG. 7.

[0213] In embodiment 7, the first candidate subset includes a second candidate value; the second candidate value indicates a first ID, and the first ID identifies at least one ML model.

[0214] As an embodiment, when the first indication information takes the value of the second candidate value: the receiving end of the first indication information can know, through the first ID indicated by the second candidate value, that the first node tends to use the ML model identified by the first ID to decode the target information block; according to the above knowledge, the target information block sending end can optimize the retransmission of the target information block.

[0215] As an embodiment, when the first indication information takes the value of the second candidate value: the receiving end of the first indication information can know, through the first ID indicated by the second candidate value, that the first node tends to use the speed matching mode corresponding to the first ID identified ML model to retransmit; according to the above knowledge, the target information block sending end can optimize the retransmission of the target information block.

[0216] As an embodiment, an ML model is an AI model.

[0217] As an embodiment, an ML model includes a mathematical algorithm that can be trained by data and human expert input as examples to replicate the decisions made by experts when providing the same information.

[0218] As an embodiment, the plurality of candidate values in the first candidate subset respectively indicate different IDs, and each of the different IDs identifies at least one ML model.

[0219] As one embodiment, the first ID is any one of the different IDs.

[0220] Embodiment 8

[0221] Embodiment 8 illustrates an explanatory diagram of a first candidate subset according to one embodiment of the present application, as shown in FIG. 8.

[0222] In embodiment 8, the first candidate subset includes a third candidate value, which indicates that the encoding manner corresponding to the first ML model is used for retransmission of the target information block.

[0223] As one embodiment, the third candidate value indicating that the encoding manner corresponding to the first ML model is used for retransmission of the target information block includes that the third candidate value indicates that the encoding manner corresponding to the first ML model can be used for retransmission of the target information block.

[0224] As one embodiment, the third candidate value indicating that the encoding manner corresponding to the first ML model is used for retransmission of the target information block includes that the third candidate value indicates that the encoding manner corresponding to the first ML model is preferentially used for retransmission of the target information block.

[0225] As one embodiment, the third candidate value indicating that the encoding manner corresponding to the first ML model is used for retransmission of the target information block includes that the third candidate value indicates that the encoding manner corresponding to the first ML model can be preferentially used for retransmission of the target information block.

[0226] As one embodiment, the first candidate subset includes two candidate values: one of which indicates that one encoding manner corresponding to the first ML model can be used for retransmission of the target information block, and the other of which indicates that another encoding manner corresponding to the first ML model can be used for retransmission of the target information block.

[0227] As one embodiment, the encoding manner corresponding to the first ML model is an encoding manner corresponding to an ID identifying the first ML model.

[0228] As one embodiment, the first ML model is at least available for decoding.

[0229] As one embodiment, the first ML model is an ML model determined to be suitable for decoding performed for at least one encoding manner; each of the at least one encoding manner is an encoding manner corresponding to the first ML model.

[0230] As an embodiment, generally speaking, for an information block encoded using the encoding manner corresponding to the first ML model, the receiving end uses the first ML model to perform decoding to obtain better decoding performance.

[0231] As an embodiment, the encoding manner corresponding to the first ML model is reported by the first node.

[0232] As an embodiment, the correspondence between the first ML model and the corresponding encoding manner is determined by configuration.

[0233] As an embodiment, the first ML model and the corresponding encoding manner can be obtained by iteratively training between the two communication parties.

[0234] As an embodiment, the first candidate subset includes a fourth candidate value, and the fourth candidate value indicates that the encoding manner corresponding to the traditional decoder is used for retransmission of the target information block.

[0235] As an embodiment, the fourth candidate value indicates that the encoding manner corresponding to the traditional decoder is used for retransmission of the target information block, including: the fourth candidate value indicates that the encoding manner corresponding to the traditional decoder can be used for retransmission of the target information block.

[0236] As an embodiment, the fourth candidate value indicates that the encoding manner corresponding to the traditional decoder is used for retransmission of the target information block, including: the fourth candidate value indicates that the encoding manner corresponding to the traditional decoder is used for retransmission of the target information block.

[0237] As an embodiment, the fourth candidate value indicates that the encoding manner corresponding to the traditional decoder is used for retransmission of the target information block, including: the fourth candidate value indicates that the encoding manner corresponding to the traditional decoder can be used for retransmission of the target information block.

[0238] As an embodiment, the traditional decoder does not use an ML model to perform decoding.

[0239] As an embodiment, the traditional decoder is suitable for decoding for an encoding manner, and the encoding manner is the encoding manner corresponding to the traditional decoder.

[0240] As an embodiment, the encoding in the present application includes channel encoding, and the decoding in the present application includes decoding corresponding to the channel encoding.

[0241] As an embodiment, the encoding in the present application is channel encoding, and the decoding in the present application is channel decoding.

[0242] As an embodiment, the encoding in the present application is source channel joint encoding, and the decoding in the present application is decoding corresponding to the source channel joint encoding.

[0243] As an embodiment, the first ML model can be used for signal processing.

[0244] As an embodiment, the first ML model is obtained by training.

[0245] As an embodiment, an encoding manner is an encoding manner of an LDPC code.

[0246] As an embodiment, an encoding manner is an encoding manner of a Turbo code.

[0247] As an embodiment, an encoding manner is an encoding manner of a Polar code.

[0248] As an embodiment, an encoding manner is an encoding manner of a convolutional code.

[0249] As an embodiment, the encoding manner corresponding to the traditional decoder is one of the above-mentioned encoding manners.

[0250] As an embodiment, an encoding manner corresponding to the first ML model is one of the above-mentioned encoding manners.

[0251] As an embodiment, an encoding manner corresponding to the first ML model is an encoding manner of inputting information bits into a trained ML model at a sending end to output encoding bits.

[0252] As an embodiment, the retransmission of the target information block needs to be performed by the second node.

[0253] Embodiment 9

[0254] Embodiment 9 illustrates an illustrative diagram of a first candidate subset according to an embodiment of the present application, as shown in FIG. 9.

[0255] In embodiment 9, the first candidate subset includes a fifth candidate value, and the fifth candidate value indicates that a plug-and-play matching manner corresponding to the first ML model is used for retransmission of the target information block.

[0256] As an embodiment, the fifth candidate value indicates that the plug-and-play matching manner corresponding to the first ML model is used for retransmission of the target information block, including that the fifth candidate value indicates that the plug-and-play matching manner corresponding to the first ML model can be used for retransmission of the target information block.

[0257] As an embodiment, the fifth candidate value indicates that the first ML model corresponding matching mode is used for retransmission of the target information block, including: the fifth candidate value indicates that the first ML model corresponding matching mode is used for retransmission of the target information block.

[0258] As an embodiment, the fifth candidate value indicates that the first ML model corresponding matching mode is used for retransmission of the target information block, including: the fifth candidate value indicates that the first ML model corresponding matching mode can be used for retransmission of the target information block.

[0259] As an embodiment, the first ML model corresponding matching mode includes an RV (Redundancy Version) sequence.

[0260] As an embodiment, the RV sequence is composed of multiple elements.

[0261] As an embodiment, in the RV sequence, each element is an RV identified by an RV number.

[0262] As an embodiment, in the RV sequence, each element is an RV number.

[0263] As an embodiment, an RV number is one of RV0, RV1, RV2 and RV3.

[0264] As an embodiment, the first ML model corresponding matching mode is used for retransmission of the target information block, including: the corresponding RV sequence is used for each subsequent retransmission of the target information block in turn (and in a sequence cycle).

[0265] As an embodiment, the first ML model corresponding matching mode is reported by the first node.

[0266] As an embodiment, the corresponding relationship between the first ML model and the corresponding matching mode is determined by configuration.

[0267] As an embodiment, the first ML model and the corresponding matching mode can be obtained by iteratively training between the two parties.

[0268] As an embodiment, the first candidate subset includes a sixth candidate value, and the sixth candidate value only indicates that the target information block is not correctly received.

[0269] As an embodiment, the sixth candidate value does not indicate information other than that the target information block is not correctly received.

[0270] As an embodiment, when the first indication information takes the sixth candidate value: the information known by the receiving end of the first indication information through the indication of the first indication information is only that the target information block is not correctly received.

[0271] As an embodiment, the first candidate subset can include the second candidate value, the third candidate value, the fourth candidate value, the fifth candidate value and the sixth candidate value, or only part of the second candidate value, the third candidate value, the fourth candidate value, the fifth candidate value and the sixth candidate value; non-limiting, for example, the first candidate subset includes the second candidate value and the sixth candidate value, and does not include the third candidate value, the fourth candidate value and the fifth candidate value; for another example, the first candidate subset includes the third candidate value, and does not include the second candidate value, the fourth candidate value, the fifth candidate value and the sixth candidate value.

[0272] Embodiment 10

[0273] Embodiment 10 illustrates a schematic diagram of the second candidate subset according to an embodiment of the present application, as shown in FIG. 10.

[0274] In embodiment 10, the candidate values of the first indication information include the first candidate subset and the second candidate subset, each candidate value in the second candidate subset indicates that the target information block is correctly received, the first candidate value is one of the second candidate subset, and at least one candidate value in the second candidate subset other than the first candidate value indicates information related to the ML model in addition to indicating that the target information block is correctly received.

[0275] As an embodiment, the candidate values of the first indication information only include the first candidate subset and the second candidate subset.

[0276] As an embodiment, the first candidate value only indicates that the target information block is correctly received.

[0277] As an embodiment, one candidate value in the second candidate subset other than the first candidate value indicates an ID identifying the ML model.

[0278] As an embodiment, the second candidate subset includes a seventh candidate value and an eighth candidate value; the seventh candidate value indicates that the target information block is correctly received when using one ML model to process the reception of the target information block; and the eighth candidate value indicates that the target information block is not correctly received when using the one ML model to process the reception of the target information block.

[0279] As an embodiment, the second candidate subset includes a seventh candidate value and an eighth candidate value; the seventh candidate value indicates that the target information block can be correctly received when a reception for the target information block is processed using one ML model; the eighth candidate value indicates that the target information block cannot be correctly received when the reception for the target information block is processed using the one ML model.

[0280] As an embodiment, the first indication information has a value of the eighth candidate value, and the target information block is correctly received; the target information block is not correctly received when the reception for the target information block is processed using the one ML model, and the correct reception of the target information block is based on processing of an ML model other than the one ML model or a processing module of another type.

[0281] As an embodiment, the first node can attempt to process the reception for the target information block using different manners until the target information block is correctly received or all manners cannot make the target information block correctly received.

[0282] As an embodiment, an indication content of one candidate value in the second candidate subset depends on a relationship between at least one ML model and the reception of the target information block.

[0283] As an embodiment, one candidate value in the second candidate subset indicates that the target information block is correctly received when a reception for the target information block is processed using one ML model.

[0284] As an embodiment, one candidate value in the second candidate subset indicates that the target information block is correctly received when a reception for the target information block is processed using one ML model; another candidate value in the second candidate subset indicates that the target information block is correctly received when the reception for the target information block is processed using another ML model.

[0285] As an embodiment, one candidate value in the second candidate subset indicates that the target information block can be correctly received when a reception for the target information block is processed using one ML model.

[0286] As an embodiment, one candidate value in the second candidate subset indicates that the target information block can be correctly received when a reception for the target information block is processed using one ML model; another candidate value in the second candidate subset indicates that the target information block can be correctly received when the reception for the target information block is processed using another ML model.

[0287] As one embodiment, one candidate value in the second candidate subset indicates that the target information block can be correctly received using each of the plurality of ML models to process the reception of the target information block.

[0288] As one embodiment, processing the reception of the target information block using one ML model comprises performing signal processing using this ML model after receiving a signal carrying the target information block.

[0289] As one embodiment, processing the reception of the target information block using one ML model comprises performing at least channel decoding for the target information block using this ML model.

[0290] Embodiment 11

[0291] Embodiment 11 illustrates a schematic diagram of RAN (Radio Access Network) domain AI / ML function deployment according to one embodiment of the present application, as shown in FIG. 11. The gNB in Embodiment 11 can be replaced by e.g. eNB, or 6G base station, or other network device.

[0292] The AI / ML related functions include ML training function (also referred to as AI training, or AI / ML training), ML testing function, ML inference function (also referred to as AI inference, or AI / ML inference), etc. The ML training function, ML testing function, ML inference function can be deployed independently, or co-located. The deployment of AI / ML related functions can be implemented by software, e.g. executable file download and / or running; or implemented by software combined with hardware, e.g. specific computing unit is accelerated by hardware to improve operation speed or save power consumption.

[0293] For ML training function, it can be deployed in cross-domain management system, or domain-specific management system, which is used to manage RAN domain or CN (Core Network) domain. For example, for MDA (Management Data Analytics) ML training function can be deployed in MDAF (MDA function); for network data analytics ML training can be deployed in NWDAF (Network Data Analytics Function), i.e. ML training function is MTLF (Model Training logical function).

[0294] For ML inference function, it can also be deployed in cross-domain management system, or domain-specific management system; for example, ML inference function is MDAF, or ML inference function is AnLF (Analytics logical function) in NWDAF.

[0295] Similarly, ML testing function can also be deployed in cross-domain management system, or domain-specific management system.

[0296] In embodiment 11, RAN domain ML training function 1402 is located in RAN domain management function 1403; and ML inference function is located in base station, i.e. AI / ML inference function 1404 is located in gNB 1405, AI / ML inference function 1406 is located in gNB 1407, and so on.

[0297] In FIG. 11, management of ML inference function of multiple base stations is completed by RAN domain management function 1403, i.e. data interaction is performed with RAN domain MnS (Management Service) consumer / cross-domain management 1401 (as shown by the dashed arrow in FIG. 11).

[0298] Optionally, management of ML inference function can also be completed by base station itself, i.e. each base station can independently perform data interaction with RAN domain MnS consumer / cross-domain management 1401.

[0299] It should be noted that embodiment 11 is only a non-limiting implementation; optionally, RAN domain ML training function can also be deployed in base station; or optionally, part of base stations deploy ML inference function and RAN domain ML training function, and part of base stations only deploy ML inference function.

[0300] As one embodiment, one gNB (or base station) in Embodiment 11 is the second node of the present application.

[0301] As one embodiment, the second node includes an AL / ML inference function in FIG. 11, i.e., 1404 or 1406.

[0302] Embodiment 12

[0303] Embodiment 12 illustrates a schematic diagram of AI / ML function deployment of a UE according to one embodiment of the present application, as shown in FIG. 12. The RAN domain ML training function 1505 in FIG. 12 is optional.

[0304] The UE function 1504 is deployed in the first node of the present application, and the UE function 1504 includes an AI / ML inference function 1506; the AI / ML inference function 1506 uses a ML model (also referred to as an AI model) for inference; one ML model is usually trained before being used for AI / ML inference.

[0305] As one embodiment, the UE function 1504 includes a RAN domain ML training function 1505, which runs training data through a ML model to derive a related loss, and adjusts 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.

[0306] The above embodiments can reduce the complexity of the base station, or save the air interface resources caused by reporting training data; however, the above embodiments put higher requirements on the processing capability of the UE side.

[0307] Optionally, the UE function 1504 further includes a CN domain ML training function (not included in FIG. 12).

[0308] Optionally, the UE function 1504 further includes an AI / ML deployment function (not included in FIG. 12), which is used to load ML models and data.

[0309] As one embodiment, the first node indicates whether the ML training function (RAN domain or CN domain) is supported through capability reporting, and the capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0310] As an embodiment, the ML model, and related metadata, is loaded by the first node from a network device or a remote server.

[0311] As an embodiment, the first node loads the ML model.

[0312] Optionally, the UE function 1504 is a MnS producer providing data for management or analytics to the CN domain MnF 1501, and / or the RAN domain MnF 1502, and / or the cross-domain management system 1503 (as indicated by double arrow 1507).

[0313] Optionally, the UE function 1504 is a MnS consumer loading data from the CN domain MnF 1501, and / or the RAN domain MnF 1502, and / or the cross-domain management system 1503 for AI / ML related management, such as management data requests, ML model activation, and / or ML training, etc. (as indicated by double arrow 1507).

[0314] As an embodiment, the second signaling in the present application includes content obtained through inference of the AI / ML inference function 1506.

[0315] As an embodiment, the first node includes an AL / ML inference function 1506 in FIG. 12.

[0316] As an embodiment, the ML model is based on a neural network.

[0317] As an embodiment, the ML model is based on a CNN (Conventional Neural Networks).

[0318] As an embodiment, the ML model is based on a Transformer architecture.

[0319] Embodiment 13

[0320] Embodiment 13 illustrates a schematic diagram of an artificial intelligence or machine learning based processing system according to an embodiment of the present application, as shown in FIG. 13. FIG. 13 includes a first processing machine, a second processing machine, a third processing machine, and a fourth processing machine.

[0321] In Embodiment 13, the first processor sends a first data set to the second processor, and sends a second data set to the third processor; the second processor generates a target first-type parameter group according to the first data set, and sends the generated target first-type parameter group to the third processor; the third processor processes the second data set using the target first-type parameter group to obtain a first-type output, and (optionally) sends the first-type output to the fourth processor. In FIG. 13, the first-type feedback and the second-type feedback are optional; the second processor includes an ML training function; and the third processor includes an ML inference function.

[0322] As an embodiment, the fourth processor includes an ML testing function.

[0323] As an embodiment, the fourth processor includes performance monitoring / evaluation of the ML model.

[0324] As an embodiment, the third processor sends first-type feedback to the second processor, and the first-type feedback is used to trigger re-computation or update of the target first-type parameter group, i.e., trigger ML initial training or ML re-training.

[0325] As an embodiment, the fourth processor sends second-type feedback to the first processor, and the second-type feedback is used to generate the first data set or the second data set, or the second-type feedback is used to trigger sending of the first data set or sending of the second data set.

[0326] As an embodiment, the first processor generates the first data set and the second data set according to measurement of a reference signal.

[0327] As an embodiment, the first-type output includes the first channel information.

[0328] As an embodiment, the first-type output includes an index of the target reference signal.

[0329] As an embodiment, the second data set includes measurement of the first reference signal, or includes measurement of the second reference signal.

[0330] As an embodiment, the first data set includes training data.

[0331] As an embodiment, the second processor is used to train an ML model, and the trained model is described by the target first-type parameter group.

[0332] As an embodiment, the third processor constructs a model according to the target first-type parameter group, and then inputs the second data set into the constructed model to obtain the first-type output.

[0333] As an embodiment, the third processor generates a recovery data set according to the first-type output, and an error of the recovery data set and the second data set is used to generate the first-type feedback.

[0334] As an embodiment, the first-type feedback is used to reflect the performance of the trained model; when the performance of the trained model cannot meet the requirement, the second processor recalculates the target first-type parameter group.

[0335] As an embodiment, when the error is too large or the time for updating is too long, the performance of the trained model is considered to be unable to meet the requirement.

[0336] As an embodiment, the target first-type parameter group includes one or more of a convolution kernel size, a convolution layer number, a convolution step, a pooling kernel size, a pooling kernel step, a pooling function, an activation function, or a feature map number.

[0337] As an embodiment, the target first-type parameter group includes one or more of a convolution kernel, a pooling kernel, a pooling function, an activation function, a parameter of the pooling function, or a parameter of the activation function.

[0338] Embodiment 14

[0339] Embodiment 14 illustrates a flowchart based on artificial intelligence or machine learning according to an embodiment of the present application, as shown in FIG. 14. FIG. 14 includes a first operation, a second operation, a third operation, a fourth operation, and a fifth operation. In embodiment 14, the first operation and the second operation belong to a first stage, the third operation belongs to a second stage, the fourth operation belongs to a third stage, and the fifth operation belongs to a fourth stage. In FIG. 14, a line with an arrow indicates the order of the flow.

[0340] As an embodiment, the first operation includes AI / ML training, the second operation includes AI / ML testing, the third operation includes AI / ML emulation, the fourth operation includes AI / ML entity loading, and the fifth operation includes AI / ML inference.

[0341] As an embodiment, the first phase comprises a training phase, the second phase comprises an emulation phase, the third phase comprises a deployment phase, and the fourth phase comprises an inference phase.

[0342] As an embodiment, the first phase comprises AI / ML model training.

[0343] As an embodiment, the first phase comprises AI / ML model training and AI / ML testing.

[0344] As an embodiment, the AI / ML model training comprises initial training and re-training of one or a set of AI / ML entities.

[0345] As an embodiment, the AI / ML model training relies on training data.

[0346] As an embodiment, the AI / ML model training comprises AI / ML entity validation.

[0347] As an embodiment, the AI / ML entity validation is used to evaluate the performance of the AI / ML entity.

[0348] As an embodiment, the AI / ML entity validation relies on validation data.

[0349] As an embodiment, if the result of AI / ML entity validation does not meet the expectation, the AI / ML model will be re-trained.

[0350] As an embodiment, the AI / ML testing comprises testing the validated AI / ML entity to evaluate the performance of the trained AI / ML model.

[0351] As an embodiment, if the result of AI / ML testing meets the expectation, the AI / ML entity proceeds to the next phase; otherwise, the AI / ML model will be re-trained.

[0352] As an embodiment, the AI / ML testing relies on testing data.

[0353] As an embodiment, the second phase comprises AI / ML emulation, which performs inference of the AI / ML entity in an emulation environment.

[0354] As one embodiment, the AI / ML simulation is estimating the performance of AI / ML entity inference in a simulation environment before using the AI / ML entity.

[0355] As one embodiment, the second stage is optional.

[0356] As one embodiment, the third stage includes AI / ML entity loading for obtaining trained AI / ML entity for desired AI / ML inference function.

[0357] As one embodiment, the third stage is optional.

[0358] As one embodiment, the third stage is not needed when training function and inference function are co-located.

[0359] As one embodiment, the fourth stage includes AI / ML inference.

[0360] Embodiment 15

[0361] Embodiment 15 illustrates a block diagram of a structure for a processing device in a first node according to one embodiment of the present application, as shown in FIG. 15. In FIG. 15, the processing device A00 in the first node includes a first receiver A01 and a first transmitter A02.

[0362] As one embodiment, the first node is a user equipment.

[0363] As one embodiment, the first node is a relay node.

[0364] As one embodiment, the first node is a vehicle mounted communication device.

[0365] As one embodiment, the first receiver A01 includes at least one of the antenna 452, the receiver 454, the multi-antenna reception processor 458, the reception processor 456, the controller / processor 459, the memory 460 and the data source 467 in FIG. 4 of the present application.

[0366] As one embodiment, the first receiver A01 includes at least the first five of the antenna 452, the receiver 454, the multi-antenna reception processor 458, the reception processor 456, the controller / processor 459, the memory 460 and the data source 467 in FIG. 4 of the present application.

[0367] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0368] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0369] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0370] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0371] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0372] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0373] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0374] As an example, the first receiver A01 includes at least the first three of the antenna 452, receiver 454, multi-antenna receive processor 458, receive processor 456, controller / processor 459, memory 460, and data source 467 of FIG. 4 of the present application.

[0375] As an example, the first receiver A01, receives target information blocks;

[0376] The first transmitter A02 transmits first indication information, candidate values of the first indication information including a first candidate subset and a first candidate value, the first candidate subset including a plurality of candidate values;

[0377] Wherein, each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to the ML model in addition to the target information block not being correctly received; the first candidate value indicates that the target information block is correctly received.

[0378] As an embodiment, in the candidate values of the first indication information, only the first candidate value indicates that the target information block is correctly received.

[0379] As an embodiment, the first candidate subset includes a second candidate value; the second candidate value indicates a first ID (identity), the first ID identifying at least one ML model.

[0380] As an embodiment, the first candidate subset includes a third candidate value, the third candidate value indicating that an encoding manner corresponding to a first ML model is used for retransmission of the target information block.

[0381] As an embodiment, the first candidate subset includes a fourth candidate value, the fourth candidate value indicating that an encoding manner corresponding to a traditional decoder is used for retransmission of the target information block.

[0382] As an embodiment, the first candidate subset includes a fifth candidate value, the fifth candidate value indicating that a speed matching manner corresponding to a first ML model is used for retransmission of the target information block.

[0383] As an embodiment, the first candidate subset includes a sixth candidate value, the sixth candidate value only indicating that the target information block is not correctly received.

[0384] As an embodiment, the target information block includes one transport block, and the first indication information includes a plurality of bits.

[0385] Embodiment 16

[0386] Embodiment 16 illustrates a structural block diagram of a processing apparatus in a second node according to an embodiment of the present application, as shown in FIG. 16. In FIG. 16, the processing apparatus B00 in the second node includes a second transmitter B01 and a second receiver B02.

[0387] As an embodiment, the second node is a base station.

[0388] As an embodiment, the second node is a satellite device.

[0389] As one embodiment, the second node is a relay node.

[0390] As one embodiment, the second node is one of a test device, test equipment, test meter.

[0391] As one embodiment, the second transmitter B01 includes at least one of the antenna 420, transmitter 418, multi-antenna transmit processor 471, transmit processor 416, controller / processor 475, and memory 476 of FIG. 4.

[0392] As one embodiment, the second transmitter B01 includes at least the first five of the antenna 420, transmitter 418, multi-antenna transmit processor 471, transmit processor 416, controller / processor 475, and memory 476 of FIG. 4.

[0393] As one embodiment, the second transmitter B01 includes at least the first four of the antenna 420, transmitter 418, multi-antenna transmit processor 471, transmit processor 416, controller / processor 475, and memory 476 of FIG. 4.

[0394] As one embodiment, the second transmitter B01 includes at least the first three of the antenna 420, transmitter 418, multi-antenna transmit processor 471, transmit processor 416, controller / processor 475, and memory 476 of FIG. 4.

[0395] As one embodiment, the second transmitter B01 includes at least the first two of the antenna 420, transmitter 418, multi-antenna transmit processor 471, transmit processor 416, controller / processor 475, and memory 476 of FIG. 4.

[0396] As one embodiment, the second receiver B02 includes at least one of the antenna 420, receiver 418, multi-antenna receive processor 472, receive processor 470, controller / processor 475, and memory 476 of FIG. 4.

[0397] As one embodiment, the second receiver B02 includes at least the first five of the antenna 420, receiver 418, multi-antenna receive processor 472, receive processor 470, controller / processor 475, and memory 476 of FIG. 4.

[0398] As an embodiment, the second receiver B02 comprises at least the first four of the antenna 420, the receiver 418, the multi-antenna reception processor 472, the reception processor 470, the controller / processor 475 and the memory 476 in the application FIG. 4.

[0399] As an embodiment, the second receiver B02 comprises at least the first three of the antenna 420, the receiver 418, the multi-antenna reception processor 472, the reception processor 470, the controller / processor 475 and the memory 476 in the application FIG. 4.

[0400] As an embodiment, the second receiver B02 comprises at least the first two of the antenna 420, the receiver 418, the multi-antenna reception processor 472, the reception processor 470, the controller / processor 475 and the memory 476 in the application FIG. 4.

[0401] As an embodiment, the second transmitter B01 transmits the target information block;

[0402] The second receiver B02 receives the first indication information, the candidate values of the first indication information comprising a first candidate subset and a first candidate value, the first candidate subset comprising a plurality of candidate values;

[0403] Wherein, each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to the ML model in addition to the target information block not being correctly received; the first candidate value indicates that the target information block is correctly received.

[0404] As an embodiment, in the candidate values of the first indication information, only the first candidate value indicates that the target information block is correctly received.

[0405] As an embodiment, the first candidate subset comprises a second candidate value; the second candidate value indicates a first ID, and the first ID identifies at least one ML model.

[0406] As an embodiment, the first candidate subset comprises a third candidate value, and the third candidate value indicates that an encoding mode corresponding to the first ML model is used for retransmission of the target information block.

[0407] As an embodiment, the first candidate subset comprises a fourth candidate value, and the fourth candidate value indicates that an encoding mode corresponding to a traditional decoder is used for retransmission of the target information block.

[0408] As an embodiment, the first candidate subset includes a fifth candidate value, the fifth candidate value indicating that a speed matching manner corresponding to the first ML model is used for retransmission of the target information block.

[0409] As an embodiment, the first candidate subset includes a sixth candidate value, the sixth candidate value only indicating that the target information block is not correctly received.

[0410] As an embodiment, the target information block includes one transport block, and the first indication information includes multiple bits.

[0411] A person of ordinary skill in the art can understand that all or part of the steps in the above method can be instructed by a program to complete the relevant hardware, and the program can be stored in a computer readable storage medium, such as a read-only memory, a hard disk, or an optical disk, etc. Alternatively, all or part of the steps of 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 the form of hardware or in the form of a software function module, and the present application is not limited to any specific form of combination of software and hardware. The user equipment, terminal and UE in the present application include but are not limited to unmanned aerial vehicles, communication modules on unmanned aerial vehicles, remote control aircraft, aircraft, small aircraft, mobile phones, tablet computers, notebooks, vehicle-mounted communication devices, vehicles, vehicles, RSUs, wireless sensors, network cards, Internet of Things 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, network cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablet computers, and other wireless communication devices. The base station or system device in the present 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, air base stations, RSUs, unmanned aerial vehicles, test equipment such as transceivers or signaling testers that simulate part of the functions of base stations, and other wireless communication devices.

[0412] Those skilled in the art will appreciate that the application can be practiced by other than the described embodiments, which are presented for purposes of illustration and not of limitation, without departing from the core or essential teaching of the application. The present embodiments are thus to be considered in all respects as illustrative and not restrictive, and all changes coming within the meaning and equivalency range of the appended claims are intended to be embraced therein.

Claims

A method for a terminal, characterized in that, The method comprises: receiving a target information block; sending first indication information, candidate values of the first indication information comprising a first candidate subset and a first candidate value, the first candidate subset comprising a plurality of candidate values; wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to an ML model in addition to the target information block not being correctly received; and the first candidate value indicates that the target information block is correctly received. The method of claim 1, wherein Among the candidate values of the first indication information, only the first candidate value indicates that the target information block is correctly received. The method according to claim 1 or 2, characterized in that The first candidate subset comprises a second candidate value; the second candidate value indicates a first ID, the first ID identifying at least one ML model. The method according to any one of claims 1 to 3, characterized in that The first candidate subset comprises a third candidate value, the third candidate value indicating that an encoding mode corresponding to a first ML model is used for retransmission of the target information block. The method according to any one of claims 1 to 4, characterized in that The first candidate subset comprises a fourth candidate value, the fourth candidate value indicating that an encoding mode corresponding to a traditional decoder is used for retransmission of the target information block. The method according to any one of claims 1 to 5, characterized in that The first candidate subset comprises a fifth candidate value, the fifth candidate value indicating that a speed matching mode corresponding to a first ML model is used for retransmission of the target information block. The method according to any one of claims 1 to 6, characterized in that The first candidate subset comprises a sixth candidate value, the sixth candidate value only indicating that the target information block is not correctly received. The method according to any one of claims 1 to 7, characterized in that The target information block comprises one transport block, and the first indication information comprises a plurality of bits. A terminal, characterized in that, The terminal comprises one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is configured to store computer program code comprising computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the terminal to perform the method of any one of claims 1 to 8. A method for a base station, characterized in that The method comprises: sending a target information block; receiving first indication information, candidate values of the first indication information comprising a first candidate subset and a first candidate value, the first candidate subset comprising a plurality of candidate values; wherein each candidate value in the first candidate subset indicates that the target information block is not correctly received, and at least one candidate value in the first candidate subset further indicates information related to an ML model in addition to the target information block not being correctly received; and the first candidate value indicates that the target information block is correctly received. The method of claim 10, wherein Among the candidate values of the first indication information, only the first candidate value indicates that the target information block is correctly received. The method according to claim 10 or 11, characterized in that The first candidate subset comprises a second candidate value; the second candidate value indicates a first ID, the first ID identifying at least one ML model. The method according to any one of claims 10 to 12, characterized in that The first candidate subset comprises a third candidate value, the third candidate value indicating that an encoding mode corresponding to a first ML model is used for retransmission of the target information block. The method according to any one of claims 10 to 13, characterized in that The first candidate subset comprises a fourth candidate value, the fourth candidate value indicating that an encoding mode corresponding to a traditional decoder is used for retransmission of the target information block. The method according to any one of claims 10 to 14, characterized in that The first candidate subset includes a fifth candidate value, and the fifth candidate value indicates that a speed matching manner corresponding to the first ML model is used for retransmission of the target information block. The method according to any one of claims 10 to 15, characterized in that The first candidate subset includes a sixth candidate value, and the sixth candidate value only indicates that the target information block is not correctly received. The method according to any one of claims 10 to 16, characterized in that The target information block includes one transport block, and the first indication information includes multiple bits. 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, and the memory is configured to store computer program code including computer instructions, and the one or more processors invoke the computer instructions to cause the base station to perform the method in any one of claims 10 to 17.

Images