Method and apparatus for wireless communication

Abstract

Disclosed in the present invention are a method and apparatus for wireless communication. Provided is a first node for wireless communication, comprising: a first receiver, configured to receive first signaling, wherein the first signaling is used for scheduling a first signal; and a first transmitter, configured to transmit the first signal, wherein the first signal is transmitted provided that the first symbol of the first signal is not earlier than a first time domain resource. The first time domain resource is at least a first time interval later than the end of the first signaling; and the first time interval depends on whether processing of the first signal is based on AI.

Description

Methods and apparatus for wireless communication Technical Field

[0001] This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to methods and apparatus for transmitting wireless signals in wireless communication systems supporting cellular networks. Background Technology

[0002] In traditional wireless communication, channel coding is used to improve the reliability of wireless communication. Traditional channel coding techniques include Turbo codes, LDPC (Low Density Parity Check Code), polar codes, and so on.

[0003] With the popularization of AI (Artificial Intelligence) and ML (Machine Learning) technologies, various information transmission technologies based on AI / ML (such as encoding, decoding, modulation, demodulation, etc.) have become a research hotspot. In the future technological evolution of 5G and 6G, these AI / ML-based information transmission technologies will be a key research area.

[0004] Since the specifications of AI models (at least in part) may exceed the scope of 3GPP, the specific implementation of AI / ML training and AI / ML inference may be determined by the hardware equipment vendors themselves. It may be based on classic models such as Transformer structure, RNN (Recurrent Neural Network), CNN (Conventional Neural Network), or a hybrid model composed of multiple models. Summary of the Invention

[0005] The applicant discovered through research that existing wireless signal processing and transmission methods may not be able to adapt to the needs of AI / ML after the introduction of AI / ML functionality. Considering the above problems, this application discloses a solution. It should be noted that although the motivation for this application primarily stems from AI / ML-based wireless signal processing technology, this application is also applicable to other AI / ML-based receiving / transmitting technologies, and technologies combining AI / ML-based processing with traditional non-AI / ML processing. This is especially true considering that specific AI / ML algorithms are likely non-standardized or implemented by hardware vendors themselves. Furthermore, adopting a unified solution can reduce implementation complexity or cost, or improve performance. Unless otherwise specified, the embodiments and features in the first node of this application can be applied to the second node. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0006] Where necessary, the interpretation of terms used in this application may be referenced to the descriptions in the TS38 series of specification protocols of the 3GPP (3rd Generation Partner Project).

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

[0008] Receive the first signaling, and the first signaling schedules the first signal;

[0009] Send the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource;

[0010] Wherein, the first time-domain resource ends at least a first time interval after the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0011] As an example, the processing of the first signal mentioned in this application refers to the processing at the transmitting end of the first signal.

[0012] As an example, the problem this application aims to solve includes: how to define time-domain constraints to ensure the transmission of the first signal after introducing AI / ML functions.

[0013] As an example, the problem this application aims to solve includes: how to determine the first time interval.

[0014] As an example, compared with the existing power control calculation method of 3GPP, the above method can make full use of the various information obtained by the first node to obtain the third power, improve the flexibility of power control on the first node side, and help enhance the power control effect, thereby saving transmission power and / or reducing interference between users.

[0015] As an example, the above method can define different time-domain constraints for different situations (the processing of the first signal is based on AI, and the processing of the first signal is not based on AI), which is beneficial to balancing scheduling / configuration flexibility and transmission latency, and to improving overall transmission efficiency.

[0016] As an example, the advantages of the above method include: providing a unified solution for compatibility with different signal processing methods (AI-based methods, non-AI-based methods, or traditional methods), better adapting to various processing capabilities, application scenarios, or terminals, and having good flexibility and adaptability.

[0017] As an example, the advantages of the above method include: supporting AI / ML-based processing of wireless signals and improving the processing performance of wireless signals.

[0018] As an example, the advantages of the above method include ensuring that the transmitting and receiving ends have a consistent understanding of the timing requirements that the transmission of the first signal needs to meet.

[0019] As one example, the first node's processing of the first signal based on AI and the first node's processing of the first wireless channel not based on AI represent different processing capabilities of the first node.

[0020] As one example, the first node is a user equipment.

[0021] As one example, the first node is a terminal.

[0022] According to one aspect of this application, the above method is characterized in that,

[0023] The first time interval depends on a first parameter, the value of which depends on whether the processing of the first signal is based on AI.

[0024] According to one aspect of this application, the above method is characterized in that,

[0025] There is a linear relationship between the first time interval and the value of the first parameter.

[0026] According to one aspect of this application, the above method is characterized in that,

[0027] The first time interval is equal to the maximum value among a plurality of intermediate values; one of the intermediate values ​​has a linear relationship with the value of the first parameter.

[0028] As an example, in the above method, the first time interval is taken as the maximum value among the plurality of intermediate values, which is beneficial to improve adaptability to different configurations or scenarios.

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

[0030] The processing of the first signal is AI-based when at least one of the encoding and modulation that generates the first signal is performed by an AI model.

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

[0032] The processing of the first signal is AI-based when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model.

[0033] As an example, the advantages of the above method include: it facilitates improved transmission performance by using AI-based coding and / or modulation.

[0034] According to one aspect of this application, the above method is characterized in that,

[0035] Send a first information block, the first information block indicating that at least one function is available;

[0036] Whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein the first function includes an AI function.

[0037] As an example, in combination with the above features, the advantages of the solution disclosed in this application include: it can be applied to user equipment with different functions enabled.

[0038] According to one aspect of this application, the above method is characterized in that,

[0039] The first time-domain resource is the next time-domain symbol that is later than the end of the first signaling interval.

[0040] According to one aspect of this application, the above method is characterized in that,

[0041] The first signal carries user data.

[0042] As an example, the user data does not include UCI (Uplink Control Information).

[0043] As one example, the user data includes UL-SCH (Uplink Shared Channel) data.

[0044] As one example, the user data includes transport blocks.

[0045] This application discloses a method used in a second node for wireless communication, characterized by comprising:

[0046] Send the first signaling, and the first signaling schedules the first signal;

[0047] Receive the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource;

[0048] Wherein, the first time-domain resource ends at least a first time interval after the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0049] As one example, the second node is a network-side device.

[0050] In one embodiment, the second node is a base station.

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

[0052] The first time interval depends on a first parameter, the value of which depends on whether the processing of the first signal is based on AI.

[0053] According to one aspect of this application, the above method is characterized in that,

[0054] There is a linear relationship between the first time interval and the value of the first parameter.

[0055] According to one aspect of this application, the above method is characterized in that,

[0056] The first time interval is equal to the maximum value among a plurality of intermediate values; one of the intermediate values ​​has a linear relationship with the value of the first parameter.

[0057] According to one aspect of this application, the above method is characterized in that,

[0058] The processing of the first signal is AI-based when at least one of the encoding and modulation that generates the first signal is performed by an AI model.

[0059] According to one aspect of this application, the above method is characterized in that,

[0060] The processing of the first signal is AI-based when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model.

[0061] As an example, the two communicating parties can reach a consensus on the implementation of signal or signaling encoding and / or modulation (e.g., whether it is performed by an AI model) through information transmission between them.

[0062] According to one aspect of this application, the above method is characterized in that,

[0063] Receive a first information block, the first information block indicating that at least one function is available;

[0064] Whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein the first function includes an AI function.

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

[0066] The first time-domain resource is the next time-domain symbol that is later than the end of the first signaling interval.

[0067] According to one aspect of this application, the above method is characterized in that,

[0068] The first signal carries user data.

[0069] This application discloses a first node used for wireless communication, characterized by comprising:

[0070] A first receiver receives a first signaling instruction, which schedules a first signal.

[0071] A first transmitter transmits the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than a first time domain resource;

[0072] Wherein, the first time-domain resource ends at least a first time interval after the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0073] This application discloses a second node used for wireless communication, characterized by comprising:

[0074] The second transmitter sends the first signaling, which in turn schedules the first signal.

[0075] A second receiver receives the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than a first time domain resource.

[0076] Wherein, the first time-domain resource ends at least a first time interval after the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0077] As an example, this application has the following advantages:

[0078] ● It provides a unified solution with good flexibility and adaptability;

[0079] ● It helps improve system efficiency / performance;

[0080] ●Balancing scheduling / configuration flexibility with transmission latency;

[0081] ● This ensures that the transmitting and receiving ends have a consistent understanding of the time requirements that the transmission of the first signal needs to meet;

[0082] ● It is beneficial to make full use of AI / ML technology to enhance signal transmission. Attached Figure Description

[0083] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0084] Figure 1 shows a flowchart of communication of a first node according to an embodiment of this application;

[0085] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0086] Figure 3 illustrates a schematic diagram of an embodiment of the radio protocol architecture for the user plane and control plane according to an embodiment of this application;

[0087] Figure 4 shows a schematic diagram of the hardware module of a communication node according to an embodiment of this application;

[0088] Figure 5 illustrates a transmission flowchart between a first node and a second node according to an embodiment of this application;

[0089] Figure 6 illustrates a schematic diagram of the time-domain relationship between a first signaling, a first signal, and a first time-domain resource according to an embodiment of this application;

[0090] Figure 7 illustrates a schematic diagram of the time-domain relationship between a first signaling, a first signal, and a first time-domain resource according to an embodiment of this application;

[0091] Figure 8 illustrates whether the processing of a first time interval depending on a first signal according to an embodiment of this application is based on AI;

[0092] Figure 9 illustrates whether the processing of a first time interval depending on a first signal according to an embodiment of this application is based on AI;

[0093] Figure 10 illustrates whether the processing of a first signal according to an embodiment of this application is based on AI;

[0094] Figure 11 illustrates whether the processing of a first signal according to an embodiment of this application is based on AI and whether at least one function is included.

[0095] Figure 12 shows a schematic diagram of a first encoder and a first decoder according to an embodiment of this application;

[0096] Figure 13 shows a schematic diagram of a first encoder according to an embodiment of this application;

[0097] Figure 14 shows a schematic diagram of a first decoder according to an embodiment of this application;

[0098] Figure 15 shows a schematic diagram of an artificial intelligence processing system according to an embodiment of this application;

[0099] Figure 16 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0100] Figure 17 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0101] The technical solution of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0102] Example 1

[0103] Example 1 illustrates a flowchart of communication of a first node according to an embodiment of this application, as shown in Figure 1.

[0104] The first node 100 receives the first signaling in step 101 and sends the first signal in step 102.

[0105] In Example 1, the first signaling schedules the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than a first time domain resource; the first time domain resource is at least a first time interval later than the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0106] As an example, the first signaling is physical layer signaling.

[0107] As an example, the first signaling is transmitted on the PDCCH (Physical Downlink Control Channel).

[0108] As one example, the first signaling includes DCI (Downlink Control Information).

[0109] As one embodiment, the first signaling includes indication information of time-domain resources allocated to the first signal.

[0110] As an example, the first signaling includes scheduling information of the first signal; the scheduling information of the first signal includes at least one of the following: the pattern of the DMRS of the first signal, the number of transport layers of the first signal, the number of ports of the first signal, the number of transport blocks carried by the first signal, the TCI (Transmission configuration indicator) status or the number of beams of the first signal, the MCS (Modulation and coding scheme) of the first signal, the number of RBs (Resource blocks) allocated to the first signal, the number of time-domain symbols allocated to the first signal, the size of the transport block carried by the first signal (TBS), and the HARQ (Hybrid Automatic Repeat reQuest) process number corresponding to the first signal.

[0111] As an example, the first signaling is dynamic scheduling signaling.

[0112] As an example, the first signal is an uplink signal.

[0113] As an example, the first signal carries uplink data.

[0114] As one example, the data carried by the first signal comes from the DRB (Data Radio Bearer).

[0115] As one embodiment, the data carried by the first signal includes a transmission block.

[0116] As an example, the first signal is transmitted in a physical uplink channel.

[0117] As one embodiment, the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource, including: when the first symbol of the first signal is not earlier than the first time domain resource, the first node transmits the first signal.

[0118] As an example, the transmission of the first signal may also depend on the satisfaction of other conditions (which do not conflict with the solution disclosed in this application), and the specific form of the other conditions does not affect the technical advantages of the solution disclosed in this application.

[0119] As an example, the first set of conditions includes that the first symbol of the first signal is not earlier than the first time-domain resource.

[0120] As an example, the first set of conditions includes only the first symbol of the first signal not being earlier than the first time-domain resource.

[0121] As an example, the first set of conditions also includes other conditions that the first symbol of the first signal is not earlier than the first time-domain resource; the first set of conditions being satisfied means that each condition in the first set of conditions is satisfied.

[0122] As one embodiment, the first set of conditions includes: a specific configuration being provided to the first node;

[0123] The specific configuration is configured by RRC layer parameters, and the specific configuration indicates that the uplink signal can be received by the base station.

[0124] As an example, the transmission of the first signal depends on the satisfaction of the first set of conditions.

[0125] As one embodiment, the transmission of the first signal depends on the satisfaction of the first set of conditions, including: when the first set of conditions is satisfied, the first node transmits the first signal.

[0126] As an example, the transmission of the first signal is premised on the satisfaction of the first set of conditions.

[0127] As an example, the first node sends the first signal only when the first set of conditions is met.

[0128] As one embodiment, the transmission of the first signal depends on the satisfaction of the first set of conditions, including: the first node only needs to transmit the first signal when the first set of conditions is satisfied.

[0129] As an example, when the first set of conditions is not met, the first node does not need to send the first signal.

[0130] As an example, the behavior of the first node when the first set of conditions is not met is not defined in the protocol.

[0131] As an example, if the first set of conditions is not met, the first node can determine whether to send the first signal on its own.

[0132] As an example, it is undesirable for the first set of conditions not to be met.

[0133] As an example, the first symbol of the first signal is a time-domain symbol.

[0134] As an example, a time-domain symbol is a time-domain unit defined in a time-domain structure.

[0135] As an example, a time-domain symbol is a time-domain unit defined in the frame structure.

[0136] As an example, a time-domain symbol is an OFDM (Orthogonal Frequency Division Multiplexing) symbol.

[0137] As an example, a time-domain symbol can also be a single-carrier symbol or a multi-carrier symbol, such as a DFT-S-OFDM (Discrete Fourier Transform Spread OFDM) symbol or an FBMC (Filter Bank Multi Carrier) symbol.

[0138] As an example, a time-domain symbol is a symbol in a time slot.

[0139] As an example, a time-domain symbol can be an uplink symbol or a downlink symbol.

[0140] As an example, a time-domain symbol can also be configured to be indistinguishable between uplink and downlink.

[0141] As an example, a time-domain symbol can be an uplink symbol, a downlink symbol, or a flexible symbol.

[0142] As an example, the first symbol of the first signal is the earliest time-domain symbol assigned to the first signal.

[0143] As one embodiment, the first signal includes at least a portion of PUSCH (Physical uplink shared channel).

[0144] As an example, the first signal can be a PUSCH.

[0145] It should be noted that receiving (or transmitting) a wireless channel is a common expression in the art, meaning receiving (or transmitting) on ​​the wireless channel, or meaning receiving (or transmitting) a signal (e.g., modulation symbols) on the wireless channel; expressions that substitute the first signal for the wireless channel are understood by those skilled in the art.

[0146] As an example, the first symbol of the first signal is an uplink symbol.

[0147] As an example, the first symbol of the first signal is the earliest uplink symbol assigned to the first signal.

[0148] As an example, the first time-domain resource is a time-domain symbol.

[0149] As an example, the first symbol of the first signal is an uplink symbol, and the first time domain resource is an uplink symbol.

[0150] As an example, the first time-domain resource is a time-domain symbol; when the start of the first symbol of the first signal is not earlier than the start of the first time-domain resource, the first symbol of the first signal is not earlier than the first time-domain resource.

[0151] As a sub-implementation of the above embodiments, the first symbol of the first signal is an uplink symbol, and the first time domain resource is an uplink symbol.

[0152] As an example, the first time-domain resource is a point in time.

[0153] As an example, the first time-domain resource is a point in time; when the start of the first symbol of the first signal is not earlier than the first time-domain resource, the first symbol of the first signal is not earlier than the first time-domain resource.

[0154] As an example, the termination of the first signaling refers to the termination of the channel carrying the first signaling.

[0155] As an example, the end of the first signaling refers to the end of the last symbol of the first signaling.

[0156] As an example, the end of the first signaling refers to the end of the last symbol of the channel carrying the first signaling.

[0157] As an example, the termination of the first signaling is viewed from the perspective of the receiving end of the first signaling.

[0158] As an example, the termination of the first signaling refers to the termination of reception of the channel carrying the first signaling.

[0159] As an example, the end of the first signaling refers to the end of the reception of the last symbol of the first signaling.

[0160] As an example, the end of the first signaling refers to the end of reception of the last symbol of the channel carrying the first signaling.

[0161] As an example, the last symbol mentioned above is a time-domain symbol.

[0162] As an example, the last symbol mentioned above is from the perspective of the time domain.

[0163] As an example, the channel carrying the first signaling is a physical layer downlink channel.

[0164] As an example, the channel carrying the first signaling is a PDCCH.

[0165] As a sub-implementation of the above embodiments, the first signaling is DCI.

[0166] As an example, the first time-domain resource depends on the end of the first signaling.

[0167] As an example, the first time-domain resource depends on the first time interval.

[0168] As an example, the first time-domain resource is later than the end of the first signaling by the first time interval.

[0169] As a sub-implementation of the above embodiments, the first time domain resource is a point in time.

[0170] As an example, the first time-domain resource is the earliest uplink symbol whose start of the cyclic prefix (CP) is at least one time interval later than the end of the first signaling.

[0171] As an example, the first time-domain resource is the uplink symbol that begins after the first signaling time interval following the end of the first signaling.

[0172] As an example, the advantages of the above method include: it helps to reduce transmission latency.

[0173] As an example, the first time interval is a real number or a positive integer.

[0174] As an example, the unit of the first time interval may be milliseconds (ms) or time-domain symbols.

[0175] As one embodiment, the first time interval is configurable and is determined based on the uplink transmission preparation time.

[0176] As an example, the first time interval is linearly related to the uplink transmission preparation time.

[0177] As an example, the first time interval is equal to the maximum value among a plurality of intermediate values; one of the plurality of intermediate values ​​has a linear relationship with the uplink transmission preparation time.

[0178] As an example, the linear relationship between two values ​​is defined with respect to only the two values ​​as variables (under the above consideration, it can be assumed that the values ​​of other parameters besides the two values ​​are given).

[0179] As one example, the preparation time for the uplink transmission is configurable.

[0180] As an example, the uplink transmission preparation time can be the PUSCH preparation time.

[0181] As an example, the preparation time for the uplink transmission is at least sufficient to generate the first signal after receiving the first signaling.

[0182] As an example, the first signal is generated from data after at least encoding and modulation.

[0183] As an example, the first signal may be generated by at least a portion of the following processes: CRC addition, encoding, rate matching, scrambling, modulation, layer mapping, transform precoding, precoding, mapping to virtual resource blocks, and mapping from virtual resource blocks to physical resource blocks.

[0184] As one embodiment, the processing of the first signal includes preparation for transmitting the first signal.

[0185] As an example, the processing of the first signal includes encoding the data carried by the first signal.

[0186] As one embodiment, the processing of the first signal includes the generation of modulation symbols.

[0187] As one embodiment, the processing of the first signal includes receiving processing for the first signaling.

[0188] As a sub-implementation of the above embodiments, the first signaling schedules the first signal, and the first signaling needs to be correctly received in order to know how to process the first signal. The receiving processing of the first signaling is considered to be part of the processing of the first signal.

[0189] As an example, the processing of the first signal refers to the processing on the first node side.

[0190] As an example, whether the processing of the first signal is based on AI is configurable.

[0191] As an example, whether the processing of the first signal is based on AI is indicated by signaling.

[0192] As a sub-implementation of the above embodiments, the signaling is sent from the second node to the first node.

[0193] As a sub-implementation of the above embodiments, the first signaling includes the signaling.

[0194] As a sub-implementation of the above embodiments, whether the processing of the first signal is based on AI is explicitly or implicitly indicated by the signaling.

[0195] As one example, the processing of the first signal may be based on AI-dependent capability information reported by the first node.

[0196] As an example, the processing of the first signal is AI-based when at least one of the encoding and modulation of the first signal is performed by an AI model.

[0197] As an example, the processing of the first signal is not based on AI, and the encoding and modulation of the first signal are not performed by an AI model.

[0198] As an example, when the encoded bits of the data carried by the first signal are obtained from the output of an AI model, the processing of the first signal is based on AI.

[0199] As a sub-example of the above embodiments, the input of the AI ​​model may be the data carried by the first signal.

[0200] As an example, when the modulation symbol for generating the first signal is obtained from the output of an AI model, the processing of the first signal is based on AI.

[0201] As a sub-example of the above embodiments, the input of the AI ​​model may be the data carried by the first signal.

[0202] As a sub-example of the above embodiments, the input of the AI ​​model may be the encoded bits of the data carried by the first signal.

[0203] As one embodiment, the first signaling is transmitted after being encoded and modulated at least.

[0204] As an example, when the encoding of the first signaling is performed by an AI model, the processing of the first signal is based on AI.

[0205] As an example, based on the correspondence between encoding and decoding: it can generally be assumed that when the encoding of the first signaling at the sending end is performed by an AI model, the decoding of the first signaling at the receiving end is also performed by an AI model.

[0206] As an example, the encoding of the first signaling is performed by an AI model, and the encoded bits of the first signaling are obtained by inputting the content including the first signaling into the AI ​​model.

[0207] As an example, the decoding result of the first signaling is obtained by the output of an AI model, and the input of the AI ​​model may include the content obtained after demodulating the first signaling.

[0208] As an example, when the modulation of the first signaling is performed by an AI model, the processing of the first signal is AI-based.

[0209] As an example, based on the correspondence between modulation and demodulation: it can generally be assumed that when the modulation of the first signaling at the transmitting end is performed by the AI ​​model, the demodulation of the first signaling at the receiving end is also performed by the AI ​​model.

[0210] As an example, the modulation of the first signaling is performed by an AI model. The content, including the first signaling or the encoded bits of the first signaling, is input into the AI ​​model to obtain the corresponding modulation symbols.

[0211] As an example, demodulation of the first signaling is performed by an AI model. The AI ​​model is input with content including the received signal of the first signaling to obtain the corresponding demodulated content, which can be used for subsequent decoding.

[0212] As an example, the process of inputting the AI ​​model and obtaining the output refers to model inference.

[0213] As an example, the above encoding can be channel coding or source-channel joint coding.

[0214] As an example, the above decoding can be decoding for channel coding or decoding for joint source-channel coding.

[0215] As an example, the above encoding is performed by an AI model, or by traditional encoding that is not based on AI (such as Turbo codes, LDPC codes, polar codes, etc.).

[0216] As an example, the processing of the first signal is AI-based when at least one of the encoding and modulation of the first signal is performed by an AI model; the processing of the first signal is not AI-based when the encoding and modulation of the first signal are not performed by an AI model.

[0217] As an example, the processing of the first signal is AI-based when at least one of the encoding and modulation of the first signal is performed by an AI model, or when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model; when the encoding and modulation of the first signaling are not performed by an AI model, and the encoding of the first signaling and the modulation of the first signaling are not performed by an AI model, the processing of the first signal is not AI-based.

[0218] As an example, the processing of the first signal is AI-based when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model; the processing of the first signal is not AI-based when the encoding of the first signaling and the modulation of the first signaling are not performed by an AI model.

[0219] As an example, whether the encoding and / or modulation of the first signal is performed by the AI ​​model can be indicated by information reported by the first node or by information sent by the second node to the first node.

[0220] As an example, the encoding of the first signaling and / or the modulation of the first signaling can be indicated by information reported by the first node or by information sent by the second node to the first node.

[0221] As a typical but non-limiting implementation, for cases where the processing of the first signal is not based on AI, the encoding and modulation of the first signal can use encoding and modulation methods for transport blocks already defined by 3GPP.

[0222] As a typical but non-limiting implementation, in cases where the processing of the first signal is not based on AI, the encoding and modulation of the first signaling can use the encoding and modulation methods for control information already defined by 3GPP.

[0223] As a sub-implementation of the above embodiments, given the encoding method and the modulation method, the corresponding decoding and demodulation can at least use existing technologies, and the specific implementation can be determined by the hardware equipment manufacturer of the first node.

[0224] As one example, the AI ​​includes ML.

[0225] As an example, the AI ​​model is trained using machine learning methods.

[0226] Example 2

[0227] Example 2 illustrates a schematic diagram of a network architecture according to one embodiment of this application, as shown in Figure 2. Figure 2 illustrates the system architecture of 5G NR (New Radio), LTE (Long-Term Evolution), and LTE-A (Long-Term Evolution Advanced). The 5G NR or LTE network architecture 200 may be referred to as 5GS (5G System) / EPS (Evolved Packet System) or some other suitable term. EPS 200 may include a UE (User Equipment) 201, NG-RAN (Next Generation Radio Access Network) 202, EPC (Evolved Packet Core) / 5G-CN (5G-Core Network) 210, HSS (Home Subscriber Server) 220, and Internet service 230. EPS may interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown in the figure, EPS provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks or other cellular networks that provide circuit-switched services. NG-RAN includes NR Node B (gNB) 203 and other gNBs 204. gNB 203 provides user and control plane protocol termination toward UE 201. gNB 203 can connect to other gNBs 204 via an Xn interface (e.g., backhaul). gNB 203 may also be referred to as a base station, base transceiver station, radio base station, radio transceiver, transceiver function, Basic Services Set (BSS), Extended Services Set (ESS), TRP, or some other suitable term. gNB 203 provides UE 201 with an access point to EPC / 5G-CN 210. Examples of UE201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptop computers, personal digital assistants (PDAs), satellite radios, non-terrestrial base station communications, satellite mobile communications, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband IoT devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term.The gNB203 connects to the EPC / 5G-CN 210 via the S1 / NG interface. The EPC / 5G-CN 210 includes an MME (Mobility Management Entity), an AMF (Authentication Management Field), a UPF (User Plane Function) 211, other MMEs, AMFs, and UPFs 214, an S-GW (Service Gateway) 212, and a P-GW (Packet Data Network Gateway) 213. The MME / AMF / UPF 211 is the control node handling signaling between the UE201 and the EPC / 5G-CN 210. Generally, the MME / AMF / UPF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW 212, which is itself connected to the P-GW 213. The P-GW 213 provides UE IP address allocation and other functions. The P-GW213 connects to Internet service 230. Internet service 230 includes carrier-compliant Internet protocol services, specifically including the Internet, intranet, IMS (IP Multimedia Subsystem), and packet-switched streaming services.

[0228] It should be noted that the above embodiment 2 is a non-limiting implementation method; the solution disclosed in this application is also applicable to other network architectures, such as the network architecture of 6G systems.

[0229] As an example, the UE201 corresponds to the first node in this application.

[0230] As an example, gNB203 corresponds to the second node in this application.

[0231] As an example, the wireless link between the UE201 and the node203 includes a cellular link.

[0232] As an example, the gNB203 is a macrocell base station.

[0233] As an example, the gNB203 is a microcell base station.

[0234] As an example, the gNB203 is a PicoCell base station.

[0235] As an example, the gNB203 is a femtocell.

[0236] As an example, the gNB203 is a base station device that supports large latency differences.

[0237] As one example, the gNB203 is a flight platform device.

[0238] As an example, the gNB203 is a satellite device.

[0239] Example 3

[0240] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and control plane according to this application, as shown in Figure 3. Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300. Figure 3 shows the radio protocol architecture for a control plane 300 between a user node device (UE or RSU in V2X, onboard equipment or onboard communication module) and a network node device (gNB, UE or RSU in V2X, onboard equipment or onboard communication module), or between two UEs, using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (physical layer) signal processing functions. Layer 1 will be referred to herein as PHY 301. Layer 2 (L2 layer) 305 is above PHY 301 and is responsible for the link between the user node device and the network node device, as well as between two UEs, through PHY 301. Layer 2 (L2) 305 includes the MAC (Medium Access Control) sublayer 302, the RLC (Radio Link Control) sublayer 303, and the PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the network node devices. The PDCP sublayer 304 provides data encryption and integrity protection, and also supports inter-cell mobility between user nodes and network nodes. The RLC sublayer 303 provides packet segmentation and reassembly, retransmission of lost packets via ARQ, and duplicate packet detection and protocol error detection. The MAC sublayer 302 provides mapping between logical and transport channels and multiplexing of logical channels. The MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) within a cell among user nodes. The MAC sublayer 302 is also responsible for HARQ operations. In the control plane 300, the RRC (Radio Resource Control) sublayer 306 of Layer 3 (L3) is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between network node devices and user node devices. The radio protocol architecture of the user plane 350 includes Layer 1 (L1) and Layer 2 (L2). The radio protocol architecture for user node devices and network node devices in the user plane 350 is largely the same as the corresponding layers and sublayers in the control plane 300 for Physical Layer 351, PDCP sublayer 354 in L2 Layer 355, RLC sublayer 353 in L2 Layer 355, and MAC sublayer 352 in L2 Layer 355. However, PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead.The L2 layer 355 in the user plane 350 also includes an SDAP (Service Data Adaptation Protocol) sublayer 356. The SDAP sublayer 356 is responsible for mapping between QoS flows and data radio bearers (DRBs) to support service diversity. Although not illustrated, the user node equipment may have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., remote UE, server, etc.).

[0241] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node in this application.

[0242] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node in this application.

[0243] As an example, the first node and the second node in this application are the user node device and the network node device in Example 3, respectively.

[0244] As an example, the first signaling in this application is generated in the PHY301.

[0245] As an example, the first signal in this application is generated in the PHY351.

[0246] As an example, the first information block in this application is generated in the PHY301.

[0247] As an example, the first information block in this application is generated in the MAC sublayer 302.

[0248] As an example, the first information block in this application is generated in the RRC sublayer 306.

[0249] As an example, the second information block in this application is generated in the PHY301.

[0250] As an example, the second information block in this application is generated in the MAC sublayer 302.

[0251] As an example, the second information block in this application is generated in the RRC sublayer 306.

[0252] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0253] Example 4

[0254] Example 4 illustrates a hardware module schematic diagram of a communication node according to an embodiment of this application, as shown in Figure 4. Figure 4 is a block diagram of a first communication device 450 and a second communication device 410 communicating with each other in an access network.

[0255] The first communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0256] The second communication device 410 includes a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0257] In the transmission from the second communication device 410 to the first communication device 450, at the second communication device 410, upper-layer data packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements L2 layer functionality. In the transmission from the second communication device 410 to the first communication device 450, the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the first communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for retransmitting lost packets and signaling to the first communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for the L1 layer (i.e., the physical layer). Transmit processor 416 performs channel coding and interleaving to facilitate forward error correction (FEC) at the second communication device 410, and mapping of signal clusters based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), M-Phase Shift Keying (M-PSK), M-QAM). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based and non-codebook-based precoding, and beamforming processing, generating one or more spatial streams. Transmit processor 416 then maps each spatial stream to subcarriers, multiplexes it with a reference signal (e.g., a pilot) in the time and / or frequency domains, and subsequently uses inverse fast Fourier transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol stream. Multi-antenna transmit processor 471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multi-antenna transmitter processor 471 into an radio frequency stream, which is then provided to different antennas 420.

[0258] In the transmission from the second communication device 410 to the first communication device 450, at the first communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 456. The receiver processor 456 and the multi-antenna receiver processor 458 implement various signal processing functions of the L1 layer. The multi-antenna receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 454. The receiver processor 456 uses a Fast Fourier Transform (FFT) to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 456, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 458 after multi-antenna detection to recover any spatial stream destined for the first communication device 450. Symbols on each spatial stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then deinterleaves and decodes the soft decisions to recover the upper-layer data and control signals transmitted by the second communication device 410 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of Layer 2. The controller / processor 459 may be associated with a memory 460 storing program code and data. The memory 460 may be referred to as computer-readable media. In the transmission from the second communication device 410 to the second node 450, the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transport and logical channels to recover upper-layer data packets from the core network. The upper-layer data packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 for Layer 3 processing.

[0259] In the transmission from the first communication device 450 to the second communication device 410, at the first communication device 450, a data source 467 is used to provide upper-layer data packets to the controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmission functions at the second communication device 410 described in the transmission from the second communication device 410 to the first communication device 450, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocation, implementing L2 layer functions for the user plane and control plane. The controller / processor 459 is also responsible for retransmitting lost packets and signaling to the second communication device 410. Transmit processor 468 performs channel coding, interleaving, and modulation mapping. Multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming. Subsequently, transmit processor 468 modulates the generated spatial stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 457, the stream is provided to different antennas 452 via transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by multi-antenna transmit processor 457 into a radio frequency symbol stream before providing it to antenna 452.

[0260] In the transmission from the first communication device 450 to the second communication device 410, the function at the second communication device 410 is similar to the receiving function at the first communication device 450 described in the transmission from the second communication device 410 to the first communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 472 and the receiving processor 470. The receiving processor 470 and the multi-antenna receiving processor 472 jointly implement the L1 layer functions. The controller / processor 475 implements the L2 layer functions. The controller / processor 475 may be associated with a memory 476 that stores program code and data. The memory 476 may be referred to as computer-readable media. In the transmission from the first communication device 450 to the second communication device 410, the controller / processor 475 provides multiplexing between the transmission and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover upper-layer data packets from the UE 450. Upper-layer packets from the controller / processor 475 can be provided to the core network.

[0261] As one embodiment, the first communication device 450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor, and the first communication device 450 at least: receives first signaling, the first signaling scheduling a first signal; transmits the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than a first time domain resource; wherein the first time domain resource is later than the end of the first signaling by at least a first time interval; the first time interval depends on whether the processing of the first signal is based on AI.

[0262] As one embodiment, the first communication device 450 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: receiving a first signaling that schedules a first signal; transmitting the first signal; the transmission of the first signal depending on the first symbol of the first signal not being earlier than a first time-domain resource; wherein the first time-domain resource is later than the end of the first signaling by at least a first time interval; the first time interval depending on whether the processing of the first signal is based on AI.

[0263] As one embodiment, the second communication device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second communication device 410 at least: transmits a first signaling, the first signaling scheduling a first signal; receives the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than a first time-domain resource; wherein the first time-domain resource is later than the end of the first signaling by at least a first time interval; the first time interval depends on whether the processing of the first signal is based on AI.

[0264] As one embodiment, the second communication device 410 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: sending a first signaling that schedules a first signal; receiving the first signal; the transmission of the first signal depending on the first symbol of the first signal not being earlier than a first time-domain resource; wherein the first time-domain resource is later than the end of the first signaling by at least a first time interval; the first time interval depending on whether the processing of the first signal is based on AI.

[0265] As an example, the first communication device 450 is the first node in this application.

[0266] As an example, the second communication device 410 is the second node in this application.

[0267] As an example, the first communication device 450 is a UE, and the second communication device 410 is a base station.

[0268] As an example, at least one of {the antenna 452, the transmitter 454, the multi-antenna transmitter processor 457, the transmitter processor 468, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the first signal.

[0269] As an example, at least one of {the antenna 420, the receiver 418, the multi-antenna receiver processor 472, the receiver processor 470, the controller / processor 475, and the memory 476} is used to receive the first signal.

[0270] As an example, at least one of {the antenna 452, the transmitter 454, the multi-antenna transmitter processor 457, the transmitter processor 468, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the first information block.

[0271] As an example, at least one of {the antenna 420, the receiver 418, the multi-antenna receiving processor 472, the receiving processor 470, the controller / processor 475, and the memory 476} is used to receive the first information block.

[0272] As an example, at least one of {the antenna 452, the receiver 454, the multi-antenna receiving processor 458, the receiving processor 456, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first signaling in this application.

[0273] As an example, at least one of {the antenna 420, the transmitter 418, the multi-antenna transmitter processor 471, the transmitter processor 416, the controller / processor 475, and the memory 476} is used to transmit the first signaling in this application.

[0274] As an example, at least one of {the antenna 452, the transmitter 454, the multi-antenna transmitter processor 457, the transmitter processor 468, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the second information block.

[0275] As an example, at least one of {the antenna 420, the receiver 418, the multi-antenna receiving processor 472, the receiving processor 470, the controller / processor 475, and the memory 476} is used to receive the second information block.

[0276] As an example, at least one of {the antenna 452, the receiver 454, the multi-antenna receiving processor 458, the receiving processor 456, the controller / processor 459, the memory 460, and the data source 467} is used to receive the second information block in this application.

[0277] As an example, at least one of {the antenna 420, the transmitter 418, the multi-antenna transmitter processor 471, the transmitter processor 416, the controller / processor 475, and the memory 476} is used to transmit the second information block in this application.

[0278] Example 5

[0279] Example 5 illustrates a transmission flowchart between a first node and a second node according to an embodiment of this application, as shown in Figure 5. Specifically, in Figure 5, the steps in the dashed box F1 are optional.

[0280] The first node U1 sends a first information block in step S510; receives a first signaling in step S511; and sends a first signal in step S512.

[0281] The second node U2 receives the first information block in step S520; sends the first signaling in step S521; and receives the first signal in step S522.

[0282] In Embodiment 5, the first signaling schedules the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than a first time domain resource; the first time domain resource is at least a first time interval later than the end of the first signaling; the first time interval depends on a first parameter, the value of the first parameter depending on whether the processing of the first signal is based on AI;

[0283] Wherein, the first time interval and the value of the first parameter are linearly related; or, the first time interval is equal to the maximum value among a plurality of intermediate values; and one of the intermediate values ​​is linearly related to the value of the first parameter.

[0284] As a sub-implementation of Embodiment 5, the first information block indicates that at least one function is applicable; whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein the first function includes an AI function.

[0285] As a sub-implementation of Embodiment 5, the first symbol of the first signal is an uplink symbol, and the first time domain resource is an uplink symbol.

[0286] As a sub-implementation of Embodiment 5, the first time-domain resource is the earliest time-domain symbol whose start time is at least later than the end time of the first signaling by the first time interval.

[0287] As a sub-example of Example 5, the first signal carries user data.

[0288] The above embodiment 5 and all its sub-embodiments can be combined arbitrarily with each other.

[0289] As an example, how the second node U2 receives the first signal can be determined by the second node U2 itself, without the need for protocol definition.

[0290] As one embodiment, the first node sends a first information block, the first information block indicating that at least one function is available;

[0291] Whether the processing of the first signal is based on AI depends on whether the at least one function includes a first function; wherein the first function includes an AI function.

[0292] As an example, the first node U1 is the first node in this application.

[0293] As an example, the second node U2 is the second node in this application.

[0294] As an example, the first node U1 is a UE.

[0295] As one example, the second node U2 is a base station.

[0296] As one embodiment, the air interface between the second node U2 and the first node U1 is the Uu interface.

[0297] As one embodiment, the air interface between the second node U2 and the first node U1 includes a cellular link.

[0298] As one embodiment, the air interface between the second node U2 and the first node U1 includes a wireless interface between the base station equipment and the user equipment.

[0299] As one embodiment, the air interface between the second node U2 and the first node U1 includes a wireless interface between satellite equipment and user equipment.

[0300] As one embodiment, the air interface between the second node U2 and the first node U1 includes a wireless interface between the relay device and the user equipment.

[0301] As an example, the steps in the dashed box F1 are present.

[0302] As an example, the step in the dashed box F1 does not exist.

[0303] As one embodiment, the first node receives the second information block, or sends the second information block;

[0304] Whether the processing of the first signal is based on AI depends on the indication of the second information block.

[0305] As one embodiment, the second information block indicates whether the processing of the first signal is based on AI.

[0306] As one embodiment, the second information block includes physical layer signaling.

[0307] As one embodiment, the second information block includes higher-layer signaling.

[0308] As one embodiment, the first node sends the second information block; the second information block belongs to UAI (UE Assistance Information).

[0309] As an example, the first node sends the second information block; the second information block belongs to the UEAssistanceInformation message.

[0310] As one embodiment, the first node sends the second information block; the second information block includes UAI.

[0311] As one embodiment, the first node sends the second information block; the second information block includes a UEAssistanceInformation message.

[0312] As one embodiment, the first node sends the second information block; the second information block belongs to the capability information of the first node.

[0313] As one embodiment, the first node sends the second information block; the second information block includes the capability information of the first node.

[0314] Example 6

[0315] Example 6 illustrates a schematic diagram of the time-domain relationship between a first signaling, a first signal, and a first time-domain resource according to an embodiment of this application, as shown in Figure 6. In Figure 6, the gray-filled portion within the box representing the first signal represents the first symbol of the first signal.

[0316] In Embodiment 6, the first time-domain resource is a time-domain symbol, and the first time-domain resource is later than the end of the first signaling by at least the first time interval; the first signaling schedules the first signal, and the first symbol of the first signal is later than the first time-domain resource.

[0317] As a sub-implementation of Embodiment 6, the reference time point is exactly later than the end of the first signaling time interval, and the interval between the reference time point and the start of the first time domain resource is less than the duration of the first time domain resource.

[0318] As an example, the first time-domain resource is a time-domain symbol, and the start time of the first time-domain resource can be exactly later than the end of the first signaling interval by the first time interval.

[0319] As an example, the first symbol of the first signal may be the first time-domain resource.

[0320] As an example, the first time-domain resource is the next time-domain symbol that is later than the end of the first signaling interval.

[0321] As a sub-implementation of the above embodiments, the phrase "the first time interval is later than the end of the first signaling" means that the start time is later than the end of the first signaling by the first time interval.

[0322] As a sub-implementation of the above embodiment, the phrase "the first time interval is later than the end of the first signaling" means that the start of the corresponding cyclic prefix is ​​later than the end of the first signaling by the first time interval.

[0323] As an example, the first time-domain resource is the earliest time-domain symbol whose start time is at least later than the end of the first signaling interval.

[0324] As an example, the first time-domain resource is the earliest time-domain symbol whose start of the cyclic prefix is ​​at least one time-domain symbol that is later than the end of the first signaling by at least the first time interval.

[0325] As an example, the first time-domain resource is the next uplink symbol that is later than the end of the first signaling interval by the first time-domain symbol.

[0326] As a sub-implementation of the above embodiments, the phrase "the first time interval is later than the end of the first signaling" means that the start time is later than the end of the first signaling by the first time interval.

[0327] As a sub-implementation of the above embodiment, the phrase "the first time interval is later than the end of the first signaling" means that the start of the corresponding cyclic prefix is ​​later than the end of the first signaling by the first time interval.

[0328] As an example, the first time-domain resource is the earliest uplink symbol whose start time is at least later than the end of the first signaling interval.

[0329] As an example, the first time-domain resource is the earliest uplink symbol whose start of the cyclic prefix is ​​at least one time interval later than the end of the first signaling.

[0330] Example 7

[0331] Example 7 illustrates a schematic diagram of the time-domain relationship between a first signaling, a first signal, and a first time-domain resource according to an embodiment of this application, as shown in Figure 7. In Figure 7, the gray-filled portion within the box representing the first signal indicates the first symbol of the first signal.

[0332] In Embodiment 7, the first time domain resource is a point in time, and the first time domain resource is later than the end of the first signaling by the first time interval; the first signaling schedules the first signal, and the first symbol of the first signal is later than the first time domain resource.

[0333] As an example, the first time-domain resource is a point in time, and the first symbol of the first signal may begin exactly at the first time-domain resource.

[0334] Example 8

[0335] Example 8 illustrates whether the processing of a first time interval depending on a first signal according to an embodiment of the present application is based on AI, as shown in Figure 8.

[0336] In Example 8, the first time interval depends on a first parameter, the value of which depends on whether the processing of the first signal is based on AI.

[0337] As one embodiment, there is a linear relationship between the first time interval and the value of the first parameter; the value of the first parameter depends on whether the processing of the first signal is based on AI.

[0338] As an example, the first time interval is denoted by T. proc It means that T proc = (N+d1)(2048+144)·κ2 -μ ·T C Wherein, N is the uplink transmission preparation time, and d1 is configurable.

[0339] As a sub-implementation of the above embodiment, the first parameter is N; if the first time-domain symbol in the PUSCH allocation for the first signal consists only of DM-RS (Demodulation Reference Signal), then d1 = 0, otherwise d1 = 1.

[0340] As a sub-example of the above embodiment, d1 represents the value of the first parameter.

[0341] As an example, the first time interval is denoted by T. proc It means that T proc = (N+d1+d2)(2048+144)·κ2 -μ ·T C Wherein, d2 represents the value of the first parameter, N is the uplink transmission preparation time, and d1 is configurable.

[0342] As a sub-example of the above embodiment, if the first time-domain symbol in the PUSCH allocation for the first signal consists only of DM-RS, then d1 = 0; otherwise, d1 = 1.

[0343] As an example, the first time interval is denoted by T. proc It means that T proc = (N+d1)(2048+144)·κ2 -μ ·T C +d2; where d2 represents the value of the first parameter, N is the uplink transmission preparation time, and d1 is configurable.

[0344] As a sub-example of the above embodiment, if the first time-domain symbol in the PUSCH allocation for the first signal consists only of DM-RS, then d1 = 0; otherwise, d1 = 1.

[0345] As an example, the first time interval is equal to the maximum value among a plurality of intermediate quantities; one of the plurality of intermediate quantities has a linear relationship with the value of the first parameter; the value of the first parameter depends on whether the processing of the first signal is based on AI.

[0346] As an example, the plurality of intermediate quantities is two intermediate quantities.

[0347] As an example, the plurality of intermediate quantities is more than two intermediate quantities.

[0348] As an example, one intermediate quantity other than the intermediate quantity that has a linear relationship with the value of the first parameter is configured.

[0349] As an example, one of the intermediate quantities, other than the one that has a linear relationship with the value of the first parameter, is indicated by the information reported by the first node.

[0350] As an example, the first time interval is denoted by T. proc It means that T proc =max((N+d1)(2048+144)·κ2 -μ ·T C ,d0); where N is the uplink transmission preparation time, d1 is configurable, and d0 depends on the first signaling.

[0351] As a sub-implementation of the above embodiment, the first parameter is N; if the first time-domain symbol in the PUSCH allocation for the first signal consists only of DM-RS, then d1 = 0, otherwise d1 = 1.

[0352] As a sub-example of the above embodiment, d1 represents the value of the first parameter.

[0353] As an example, the first time interval is denoted by T. proc It means that T proc =max((N+d1+d2)(2048+144)·κ2 -μ ·T C ,d0); where d2 represents the value of the first parameter, N is the uplink transmission preparation time, d1 is configurable, and d0 depends on the first signaling.

[0354] As a sub-example of the above embodiment, if the first time-domain symbol in the PUSCH allocation for the first signal consists only of DM-RS, then d1 = 0; otherwise, d1 = 1.

[0355] As an example, the first time interval is denoted by T. proc It means that T proc =max((N+d1)(2048+144)·κ2 -μ ·T C +d2,d0); where d2 represents the value of the first parameter, N is the uplink transmission preparation time, d1 is configurable, and d0 depends on the first signaling.

[0356] As a sub-example of the above embodiment, if the first time-domain symbol in the PUSCH allocation for the first signal consists only of DM-RS, then d1 = 0; otherwise, d1 = 1.

[0357] As an example, in each of the above T proc In this context, the value of the first parameter is represented by one of N, d1, and d2; for details on which one is represented, please refer to the description in the corresponding embodiments or sub-embodiments.

[0358] As an example, if the first signaling triggers a BWP (Bandwidth Part) handover, d0 is equal to the handover time; otherwise, d0 = 0.

[0359] As an example, T c =1 / (Δf) max ·N f ), where Δf max =480·10 3 Hz, N f =4096; constant κ=T s / T c =64, where T s =1 / (Δf) ref ·N f,ref ),Δf ref =15·10 3 Hz, N f,ref =2048

[0360] As an example, μ is configurable.

[0361] As an example, μ is the subcarrier spacing (SCS) configuration.

[0362] As an example, μ is the smallest of the SCS configuration of the downlink channel carrying the first signaling and the SCS configuration of the uplink channel transmitting the first signal.

[0363] As an example, μ corresponds to either the SCS of the downlink channel carrying the first signaling or the SCS of the uplink channel transmitting the first signal, such that T... proc The largest one.

[0364] As one example, the first parameter can be set to different values ​​depending on whether the processing of the first signal is based on AI or not.

[0365] As an example, when the processing of the first signal is based on AI, the value of the first parameter is a first candidate value; when the processing of the first signal is not based on AI, the value of the first parameter is a second candidate value.

[0366] As an example, the first candidate value is a non-negative number.

[0367] As an example, the second candidate value is a non-negative number.

[0368] As an example, the first candidate value is configured, predefined, or reported by the first node.

[0369] As one example, the second candidate value is configured, predefined, or reported by the first node.

[0370] As one example, the preparation time for the uplink transmission is configurable.

[0371] As an example, the preparation time for the uplink transmission can be measured in time-domain symbols.

[0372] As an example, the uplink transmission preparation time can be the PUSCH preparation time.

[0373] As an example, the preparation time for the uplink transmission is at least sufficient to perform the encoding for generating the uplink transmission.

[0374] As an example, the preparation time for the uplink transmission is at least sufficient to perform the encoding and modulation for generating the uplink transmission.

[0375] As an example, the uplink transmission preparation time is at least sufficient to perform CRC addition, encoding, rate matching, scrambling, modulation, resource mapping, and physical antenna mapping for generating the uplink transmission.

[0376] As an example, the preparation time for the uplink transmission is at least sufficient to perform CRC addition, encoding, rate matching, scrambling, modulation, layer mapping, transform precoding, precoding, mapping to virtual resource blocks, and mapping from virtual resource blocks to physical resource blocks for generating the uplink transmission.

[0377] As an example, the first parameter is the preparation time for the uplink transmission.

[0378] As one embodiment, the first parameter is the preparation time for the uplink transmission;

[0379] When determining the first candidate value, it can be considered that the aforementioned coding and / or modulation is performed by an AI model; when determining the second candidate value, it can be considered that the aforementioned coding and modulation is a 3GPP-defined coding and modulation for transport blocks.

[0380] It should be noted that the method for determining the first candidate value and the second candidate value given above is non-restrictive, and its specific description may not need to be reflected in the protocol; the protocol only needs to define the finally determined first candidate value and second candidate value.

[0381] As an example, the first parameter is not the uplink transmission preparation time, and the uplink transmission preparation time may not depend on whether the processing of the first signal is based on AI; in this case, the aforementioned encoding and modulation can be the encoding and modulation for transport blocks already defined by 3GPP; it should be noted that the specific description of determining the uplink transmission preparation time may not need to be reflected in the protocol; the protocol only needs to define the final determination result.

[0382] As an example, the first parameter is not the uplink transmission preparation time; the uplink transmission preparation time can be referred to in section 6.4 of 3GPP TS38.214 (V18.2.0) for PUSCH preparation time.

[0383] As an example, the preparation time for the uplink transmission is at least sufficient to generate the first signal after receiving the first signaling.

[0384] Example 9

[0385] Example 9 illustrates whether the processing of a first time interval depending on a first signal according to an embodiment of the present application is based on AI, as shown in Figure 9.

[0386] In Example 9, whether the first time interval is determined based at least on a second parameter to determine whether the processing dependent on the first signal is based on AI.

[0387] As one embodiment, determining whether the processing dependent on the first signal is based on AI based at least on a second parameter includes:

[0388] When the processing of the first signal is not based on AI: there is a linear relationship between the first time interval and the value of the second parameter;

[0389] When the processing of the first signal is based on AI: the value of the second parameter is not required in the calculation of the first time interval.

[0390] As one embodiment, determining whether the processing dependent on the first signal is based on AI based at least on a second parameter includes:

[0391] When the processing of the first signal is based on AI: there is a linear relationship between the first time interval and the value of the second parameter;

[0392] When the processing of the first signal is not based on AI: the value of the second parameter is not needed in the calculation of the first time interval.

[0393] As one embodiment, determining whether the processing dependent on the first signal is based on AI based at least on a second parameter includes:

[0394] When the processing of the first signal is not based on AI: the first time interval is equal to the maximum value among a plurality of intermediate values; there is a linear relationship between one of the plurality of intermediate values ​​and the value of the second parameter;

[0395] When the processing of the first signal is based on AI: the value of the second parameter is not required in the calculation of the first time interval.

[0396] As one embodiment, determining whether the processing dependent on the first signal is based on AI based at least on a second parameter includes:

[0397] When the processing of the first signal is based on AI: the first time interval is equal to the maximum value among a plurality of intermediate quantities; there is a linear relationship between one of the plurality of intermediate quantities and the value of the second parameter;

[0398] When the processing of the first signal is not based on AI: the value of the second parameter is not needed in the calculation of the first time interval.

[0399] As an example, the plurality of intermediate quantities is two intermediate quantities.

[0400] As an example, the plurality of intermediate quantities is more than two intermediate quantities.

[0401] As an example, one intermediate quantity other than the intermediate quantity that has a linear relationship with the value of the second parameter is configured.

[0402] As an example, one of the intermediate quantities, other than the one that has a linear relationship with the value of the second parameter, is indicated by the information reported by the first node.

[0403] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is based on AI, T proc = (N+d1)(2048+144)·κ2 -μ ·T C When the processing of the first signal is not based on AI, T proc = (N+d1+d3)(2048+144)·κ2 -μ ·T C Wherein, N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0404] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is not based on AI, T proc = (N+d1)(2048+144)·κ2 -μ ·T C When the processing of the first signal is based on AI, T proc = (N+d1+d3)(2048+144)·κ2 -μ ·T C Wherein, N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0405] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is based on AI, T proc = (N+d1)(2048+144)·κ2 -μ ·T C When the processing of the first signal is not based on AI, T proc= (N+d1)(2048+144)·κ2 -μ ·T C +d3; where N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0406] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is not based on AI, T proc = (N+d1)(2048+144)·κ2 -μ ·T C When the processing of the first signal is based on AI, T proc = (N+d1)(2048+144)·κ2 -μ ·T C +d3; where N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0407] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is based on AI, T proc =max((N+d1)(2048+144)·κ2 -μ ·T C ,d0); When the processing of the first signal is not based on AI, T proc =max((N+d1+d3)(2048+144)·κ2 -μ ·T C ,d0); where N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0408] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is not based on AI, T proc =max((N+d1)(2048+144)·κ2 -μ ·T C ,d0); When the processing of the first signal is based on AI, T proc =max((N+d1+d3)(2048+144)·κ2 -μ ·T C ,d0); where N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0409] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is based on AI, T proc=max((N+d1)(2048+144)·κ2 -μ ·T C ,d0); When the processing of the first signal is not based on AI, T proc =max((N+d1)(2048+144)·κ2 -μ ·T C +d3, d0); where N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0410] As an example, the first time interval is denoted by T. proc This indicates that when the processing of the first signal is not based on AI, T proc =max((N+d1)(2048+144)·κ2 -μ ·T C ,d0); When the processing of the first signal is based on AI, T proc =max((N+d1)(2048+144)·κ2 -μ ·T C +d3, d0); where N is the uplink transmission preparation time, and d3 represents the value of the second parameter.

[0411] As an example, d1 is configurable.

[0412] As an example, d1 is 0.

[0413] As an example, d3 may not be equal to 0.

[0414] As one embodiment, the value of the second parameter is a constant, a configured value, or an indication of the reporting information from the first node.

[0415] As an example, the second parameter is a physical layer parameter.

[0416] As an example, the second parameter is a higher-level parameter.

[0417] As an example, if the first signaling triggers a BWP handover, d0 equals the handover time; otherwise, d0 = 0.

[0418] As an example, T c =1 / (Δf) max ·N f ), where Δf max =480·10 3 Hz, N f =4096; constant κ=T s / T c=64, where T s =1 / (Δf) ref ·N f,ref ),Δf ref =15·10 3 Hz, N f,ref =2048.

[0419] As an example, μ is configurable.

[0420] As an example, μ is the subcarrier spacing (SCS) configuration.

[0421] As an example, μ is the smallest of the SCS configuration of the downlink channel carrying the first signaling and the SCS configuration of the uplink channel transmitting the first signal.

[0422] As an example, μ corresponds to either the SCS of the downlink channel carrying the first signaling or the SCS of the uplink channel transmitting the first signal, such that T... proc The largest one.

[0423] As one example, the preparation time for the uplink transmission is configurable.

[0424] As an example, the preparation time for the uplink transmission can be measured in time-domain symbols.

[0425] As an example, the uplink transmission preparation time can be the PUSCH preparation time.

[0426] As an example, the preparation time for the uplink transmission is at least sufficient to perform the encoding for generating the uplink transmission.

[0427] As an example, the preparation time for the uplink transmission is at least sufficient to perform the encoding and modulation for generating the uplink transmission.

[0428] As an example, the uplink transmission preparation time is at least sufficient to perform CRC addition, encoding, rate matching, scrambling, modulation, resource mapping, and physical antenna mapping for generating the uplink transmission.

[0429] As an example, the preparation time for the uplink transmission is at least sufficient to perform CRC addition, encoding, rate matching, scrambling, modulation, layer mapping, transform precoding, precoding, mapping to virtual resource blocks, and mapping from virtual resource blocks to physical resource blocks for generating the uplink transmission.

[0430] As an example, the encoding and modulation mentioned above can be the encoding and modulation for transport blocks that are already defined by 3GPP; it should be noted that the specific description of the preparation time for determining the uplink transmission may not need to be reflected in the protocol; the protocol only needs to define the final determination result.

[0431] As an example, the uplink transmission preparation time can be referenced from the PUSCH preparation time in Section 6.4 of 3GPP TS38.214 (V18.2.0).

[0432] As an example, the preparation time for the uplink transmission is at least sufficient to generate the first signal after receiving the first signaling.

[0433] Example 10

[0434] Example 10 illustrates whether the processing of a first signal according to an embodiment of this application is based on AI, as shown in Figure 10.

[0435] In Example 10, whether the processing of the first signal is based on AI depends on whether the first function is indicated to be available.

[0436] As an example, when the first function is indicated to be available, the processing of the first signal is based on AI.

[0437] As a sub-implementation of the above embodiments, when the first target condition set is satisfied, the processing of the first signal is not based on AI; wherein, the first target condition set includes: the first function is not indicated as available.

[0438] As an example, the first set of target conditions includes only: the first function is not indicated as available.

[0439] As an example, the first target condition set includes more than one condition, and the first target condition set being satisfied means that each of the more than one condition is satisfied.

[0440] As an example, the first set of target conditions further includes: a second function is not indicated as available; wherein the second function includes: processing scheduling signaling using an AI model.

[0441] As an example, whether the processing of the first signal is based on AI depends on whether the first function is instructed to be used.

[0442] As an example, when the first function is indicated to be used, the processing of the first signal is based on AI.

[0443] As a sub-implementation of the above embodiments, when the second set of target conditions is satisfied, the processing of the first signal is not based on AI; wherein, the second set of target conditions includes: the first function is not indicated to be used.

[0444] As an example, the second set of target conditions includes only: the first function is not indicated to be used.

[0445] As an example, the second target condition set includes more than one condition, and the second target condition set being satisfied means that each of the more than one condition is satisfied.

[0446] As one embodiment, the second set of target conditions further includes: a second function is not indicated to be used; wherein the second function includes: processing scheduling signaling using an AI model.

[0447] As an example, the indication of the first function may be an indication of signaling sent by the second node to the first node.

[0448] As an example, the indication of the first function may be an indication of signaling sent from the first node to the second node.

[0449] As an example, the indication of the second function may be an indication of signaling sent by the second node to the first node.

[0450] As an example, the indication of the second function may be an indication of signaling sent from the first node to the second node.

[0451] As an example, there is no corresponding signaling indicating that the first function is available / used, and the first function is not indicated as available / used.

[0452] As an example, there is signaling indicating that the first function is unavailable / not used, and the first function is not indicated as available / used.

[0453] As an example, there is no corresponding signaling indicating that the second function is available / used, and the second function is not indicated as available / used.

[0454] As an example, there is signaling indicating that the second function is unavailable / not used, and the second function is not indicated as available / used.

[0455] As one example, the first function includes using AI functionality.

[0456] As an example, the AI ​​function is a function implemented using an AI model.

[0457] As one example, the first function includes: processing uplink data using an AI model.

[0458] As one embodiment, the first function includes: encoding and / or corresponding modulation of uplink data by an AI model.

[0459] As one embodiment, the use of an AI model to process scheduling signaling includes: the AI ​​model performing the encoding and / or corresponding modulation of the scheduling signaling of the uplink signal.

[0460] As an example, the configuration information for the first function includes the first candidate value.

[0461] Example 11

[0462] Example 11 illustrates a schematic diagram illustrating whether the processing of a first signal according to an embodiment of the present application is based on AI and whether at least one function is included, as shown in Figure 11.

[0463] In embodiment 11, the first node sends a first information block; the first information block indicates that at least one function is available;

[0464] When the at least one function includes the first function, the processing of the first signal is based on AI.

[0465] As an example, when the third set of objective conditions is satisfied, the processing of the first signal is not based on AI; wherein the third set of objective conditions includes: the at least one function does not include the first function.

[0466] As an example, a function is available, including: the first node having the ability or state to use this function.

[0467] As an example, one available feature includes: the existence of an AI model that can be used to perform the relevant operations for this feature.

[0468] As an example, one available feature includes: the AI ​​model for this feature has been trained.

[0469] As an example, one available feature includes: the parameters of the AI ​​model used for this feature have been loaded.

[0470] As one example, the first function includes using AI functionality.

[0471] As an example, the AI ​​function is a function implemented using an AI model.

[0472] As one example, the first function includes: processing uplink data using an AI model.

[0473] As one embodiment, the first function includes: encoding and / or corresponding modulation of uplink data by an AI model.

[0474] As an example, the third set of target conditions includes only the following: the at least one function does not include the first function.

[0475] As an example, the third objective condition set includes more than one condition, and the third objective condition set being satisfied means that each of the more than one condition is satisfied.

[0476] As an example, the third set of objective conditions further includes: the at least one function does not include the second function; wherein the second function includes: processing scheduling signaling using an AI model.

[0477] As one embodiment, the use of an AI model to process scheduling signaling includes: the AI ​​model performing the encoding and / or corresponding modulation of the scheduling signaling of the uplink signal.

[0478] As an example, the configuration information for the first function includes the first candidate value.

[0479] As one embodiment, the first information block includes physical layer signaling.

[0480] As one embodiment, the first information block includes higher-layer signaling.

[0481] As an example, the first information block belongs to UAI (UE Assistance Information).

[0482] As an example, the first information block belongs to the UEAssistanceInformation message.

[0483] As one example, the first information block includes UAI.

[0484] As one embodiment, the first information block includes a UEAssistanceInformation message.

[0485] As an example, the first information block belongs to the capability information of the first node.

[0486] As one embodiment, the first information block includes the capability information of the first node.

[0487] Example 12

[0488] Example 12 illustrates a schematic diagram of a first encoder and a first decoder according to an embodiment of the present application, as shown in Figure 12.

[0489] In embodiment 12(1), the input of the first encoder includes L+1 data blocks arranged in sequence, namely the first data block, data block #1, data block #2, ..., data block #L; the data sending end sends the output Vi of the first encoder to the data receiving end; Vi is a bit block.

[0490] Generally speaking, how the data receiver uses the output Vi of the first encoder to recover the first data block is implementation-dependent, i.e., determined by the hardware vendor of the data receiver; the first decoder in embodiment 12(1) is only a non-limiting implementation. As shown in Figure 12(1), the input of the first decoder includes Vi and L data blocks arranged in sequence, namely data block #1, data block #2, ..., data block #L.

[0491] In Example 12(1), when the output Wi of the first decoder passes the CRC check, the first data block is correctly received; when the output Wi of the first decoder fails the CRC check, the first data block is not correctly received.

[0492] As an example, any one of the L+1 data blocks arranged in sequence is a bit block, and the output Wi of the first decoder is a bit block.

[0493] In the above embodiments, the input and output of the first encoder are both bit blocks, and the input and output of the first decoder are both bit blocks; therefore, the training dataset used to train the AI ​​model is also a quantized bit block.

[0494] As a sub-implementation of the above embodiment, the CRC check applies the CRC bit block of the first data block.

[0495] As an example, any one of the L+1 data blocks arranged in sequence includes at least one service data, which is a complex number or a vector; the output Wi of the first decoder is a data block.

[0496] In the above embodiments, the input and output of the first encoder are data blocks and bit blocks, respectively, and the input and output of the first decoder are bit blocks and data blocks, respectively; therefore, the training dataset used to train the AI ​​model is also a data block.

[0497] As a sub-implementation of the above embodiment, the CRC check applies a CRC bit block of a reference bit block, which is obtained by quantizing the first data block.

[0498] In embodiment 12 (2), the output of the first encoder at time #i is Vi; the input of the first encoder at time #i is data block #i, and L past encoded outputs Vi-1, Vi-2, ..., Vi-L (where the subscripts represent time); the input of the first decoder includes Vi and L past decoded outputs Wi-1, Wi-2, ..., Wi-L.

[0499] The delay described in (2) of Figure 12 is merely an exemplary implementation and can be replaced by other operations, such as an RNN model or a linear algorithm such as a sliding filter.

[0500] The first encoder and the first decoder can adopt various AI models such as transformer and CNN, which are determined by the hardware vendor.

[0501] The embodiments concerning check bits or service data involved in embodiment 12(1) are still applicable to embodiment 12(2), and will not be repeated here.

[0502] As an example, the structure and parameters of the AI ​​model may be obtained by downloading from a network device, or they may be specified in a standard, or they may be implementation-related (i.e., determined by the hardware device manufacturer).

[0503] As an example, both the first encoder and the first decoder are AI-based.

[0504] As one embodiment, the first encoder is used to encode the data carried by the first signal.

[0505] As one embodiment, the first encoder is used for encoding the first signaling.

[0506] As one example, the first decoder is used for decoding the first signaling.

[0507] Example 13

[0508] Example 13 illustrates a schematic diagram of a first encoder according to an embodiment of this application, as shown in Figure 13. In Figure 13, the first encoder includes P1 coding layers, namely coding layers #1, #2, ..., #P1.

[0509] As an example, P1 is 2, meaning that the P1 encoding layers include encoding layer #1 and encoding layer #2, where encoding layer #1 is a convolutional layer and encoding layer #2 is a fully connected layer, respectively. In the convolutional layer, at least one convolutional kernel is used to convolve the input of the first encoder to generate a corresponding feature map. At least one feature map output by the convolutional layer is reshaped into a vector and input to the fully connected layer. The fully connected layer transforms the vector into the output of the first encoder. For a more detailed description, please refer to CNN-related technical literature, such as Chao-Kai Wen, Deep Learning for Massive MIMO CSI Feedback, IEEE WIRELESS COMMUNICATIONS LETTERS, VOL.7, NO.5, OCTOBER 2018, etc.

[0510] As an example, P1 is 3, that is, the P1 coding layers include fully connected layers, convolutional layers, and pooling layers.

[0511] Example 14

[0512] Example 14 illustrates a schematic diagram of a first decoder according to an embodiment of this application, as shown in Figure 14. In Figure 14, the first decoder includes a preprocessing layer and P2 decoding layer groups, namely decoding layer groups #1, #2, ..., #P2, each decoding layer group including at least one decoding layer.

[0513] As an example, the preprocessing layer is a fully connected layer.

[0514] As an example, any two decoding layer groups in the P2 decoding layer groups have the same structure, which includes the number of decoding layers, the size of the input parameters of each decoding layer, the size of the output parameters, etc.

[0515] As an example, the decoding layer group #j includes L layers, namely layers #1, #2, ..., #L; the decoding layer group is any one of the P2 decoding layer groups.

[0516] As an example, L is 4, the first layer in the L layer is the input layer, and the last three layers in the L layer are convolutional layers. For a more detailed description, please refer to CNN-related technical literature, such as Chao-Kai Wen, Deep Learning for Massive MIMO CSI Feedback, IEEE WIRELESS COMMUNICATIONS LETTERS, VOL.7, NO.5, OCTOBER 2018, etc.

[0517] As an example, the L layer includes at least one convolutional layer and one pooling layer.

[0518] Example 15

[0519] Example 15 illustrates a schematic diagram of an artificial intelligence processing system according to an embodiment of this application, as shown in Figure 15. In Figure 15, an AI processing system includes a first processor, a second processor, a third processor, and a fourth processor.

[0520] In Example 15, the first processor sends a first dataset to the second processor, and the second processor uses the first dataset to train and generate a target first type parameter set. The target first type parameter set describes an AI model, and the first dataset is also referred to as the training dataset.

[0521] The second processor sends the generated target first-class parameter set to the third processor, which uses the target first-class parameter set to perform inference on the second dataset to obtain a first-class output, and then sends the first-class output to the fourth processor; the second dataset is also referred to as the inference dataset.

[0522] As an example, the AI ​​processing system described above can be used to infer encoded bits.

[0523] As an example, the AI ​​processing system described above can be used to infer and obtain the decoded bits.

[0524] As an example, the AI ​​processing system described above can be used to infer modulation symbols.

[0525] As an example, the AI ​​processing system described above can be used to infer the demodulated content.

[0526] As one example, the first dataset may include data blocks.

[0527] As an example, the first dataset may include blocks of bits.

[0528] As an example, the first dataset may include measured data.

[0529] As an example, the first dataset may include data in a format agreed upon by both communicating parties.

[0530] As one example, the second dataset may include data blocks.

[0531] As one example, the second dataset may include bit blocks.

[0532] As one example, the second dataset may include measured data.

[0533] As an example, the second dataset may include data in a format agreed upon by both communicating parties.

[0534] As one embodiment, the third processor sends a first type of feedback to the second processor, and the first type of feedback is used to trigger a recalculation or update of the target first type of parameter group.

[0535] As an example, the fourth processor sends a second type of feedback to the first processor, which is used to trigger the collection of the first dataset or the collection of the second dataset.

[0536] As one embodiment, the first processor is located on an application server or on a network device side.

[0537] As one embodiment, the second processor is located at the first node.

[0538] As one embodiment, the second processor is located on the application server or on the network device side.

[0539] As an example, the third processor obtains the second dataset from the upper layer, and the third processor is located at the first node.

[0540] As one embodiment, the fourth processor is located at the first node, or at the second node.

[0541] As one embodiment, the first processor is deployed in the CN (core network) domain MnF (Management Function), and / or the RAN (Radio Access Network) domain MnF, and / or the cross-domain management system.

[0542] As an example, the third processor constructs an AI model based on the target first type of parameter group, then inputs the second dataset into the constructed model to obtain the first type of output, and then sends the first type of output to the fourth processor.

[0543] As one embodiment, the third processor calculates the error between the first type of output and the actual data to determine the performance of the trained model; the actual data is the data received after the second dataset and passed from the first processor.

[0544] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the second processing opportunity will recalculate the target first type of parameter set.

[0545] As an example, when the error is too large or the update has not been performed for too long, the performance of the trained model is considered to be unsatisfactory.

[0546] Example 16

[0547] Example 16 illustrates a structural block diagram of a processing apparatus in a first node according to an embodiment of this application; as shown in Figure 16. In Figure 16, the processing apparatus A00 in the first node includes a first receiver A01 and a first transmitter A02.

[0548] As one example, the first node is a user equipment.

[0549] As an example, the first node is a user device that supports AI / ML functions.

[0550] As an example, the first node is a user equipment in a 6G network.

[0551] As an example, the first receiver A01 includes at least one of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460, and data source 467.

[0552] As one embodiment, the first receiver A01 includes at least the first five of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiver processor 458, receiver processor 456, controller / processor 459, memory 460, and data source 467.

[0553] As one embodiment, the first receiver A01 includes at least the first four of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiver processor 458, receiver processor 456, controller / processor 459, memory 460, and data source 467.

[0554] As one embodiment, the first receiver A01 includes at least the first three of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460, and data source 467.

[0555] As one embodiment, the first receiver A01 includes at least two of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiving processor 458, receiving processor 456, controller / processor 459, memory 460, and data source 467.

[0556] As an example, the first transmitter A02 includes at least one of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0557] As an example, the first transmitter A02 includes at least the first five of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0558] As an example, the first transmitter A02 includes at least the first four of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0559] As an example, the first transmitter A02 includes at least three of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0560] As one embodiment, the first transmitter A02 includes at least two of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmission processor 457, transmission processor 468, controller / processor 459, memory 460, and data source 467.

[0561] As one embodiment, the first receiver A01 receives a first signaling, and the first signaling schedules a first signal;

[0562] The first transmitter A02 transmits the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource;

[0563] Wherein, the first time-domain resource ends at least a first time interval after the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0564] As an example, the first time interval depends on a first parameter, the value of which depends on whether the processing of the first signal is based on AI.

[0565] As an example, the first time interval and the value of the first parameter are linearly related.

[0566] As an example, the first time interval is equal to the maximum value among a plurality of intermediate values; one of the intermediate values ​​has a linear relationship with the value of the first parameter.

[0567] As an example, the processing of the first signal is AI-based when at least one of the encoding and modulation of the first signal is performed by an AI model.

[0568] As an example, the processing of the first signal is AI-based when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model.

[0569] As one embodiment, the first transmitter A02 transmits a first information block, the first information block indicating that at least one function is available;

[0570] Whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein the first function includes an AI function.

[0571] As an example, the first time-domain resource is the next time-domain symbol that is later than the end of the first signaling interval.

[0572] As an example, the first signal carries user data.

[0573] As one embodiment, the first receiver A01 receives the second information block, or the first transmitter A02 transmits the second information block; wherein whether the processing of the first signal is based on AI depends on the indication of the second information block.

[0574] As one embodiment, the first receiver A01 receives a first signaling, and the first signaling schedules a first signal;

[0575] The first transmitter A02 transmits the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than a first time domain resource; the first time domain resource is later than the end of the first signaling by at least a first time interval; whether the first time interval is determined based at least on a second parameter to determine whether the processing dependent on the first signal is based on AI.

[0576] As a sub-implementation of the above embodiments, the first information block indicates that at least one function is applicable; whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein, the first function includes an AI function.

[0577] As a sub-implementation of the above embodiments, the first symbol of the first signal is an uplink symbol, and the first time domain resource is an uplink symbol.

[0578] As a sub-implementation of the above embodiments, the first time-domain resource is the earliest time-domain symbol whose start time is at least later than the end time of the first signaling by the first time interval.

[0579] As a sub-implementation of the above embodiments, the first signal carries user data.

[0580] The above embodiments and all their sub-embodiments can be combined arbitrarily with each other.

[0581] As one embodiment, the first receiver A01 receives a first signaling, and the first signaling schedules a first signal;

[0582] The first transmitter A02 transmits the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource;

[0583] Wherein, the first time-domain resource ends at least a first time interval after the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0584] As a sub-implementation of the above embodiments, the first time interval depends on a first parameter, and the value of the first parameter depends on whether the processing of the first signal is based on AI.

[0585] As a sub-implementation of the above embodiments, the first time interval and the value of the first parameter are linearly related; or, the first time interval is equal to the maximum value among a plurality of intermediate quantities; and one of the intermediate quantities is linearly related to the value of the first parameter.

[0586] As a sub-implementation of the above embodiments, when at least one of the encoding and modulation of the first signal is performed by an AI model, the processing of the first signal is based on AI.

[0587] As a sub-implementation of the above embodiments, when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model, the processing of the first signaling is based on AI.

[0588] As a sub-implementation of the above embodiment, the first transmitter A02 transmits a first information block, the first information block indicating that at least one function is available;

[0589] Whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein the first function includes an AI function.

[0590] As a sub-implementation of the above embodiments, the first time-domain resource is the earliest time-domain symbol whose start time is at least later than the end time of the first signaling by the first time interval.

[0591] As a sub-implementation of the above embodiments, the first signal carries user data.

[0592] As a sub-implementation of the above embodiments, the first symbol of the first signal is an uplink symbol, and the first time domain resource is an uplink symbol.

[0593] As a sub-implementation of the above embodiments, whether the first time interval is determined based at least on the second parameter to determine whether the processing dependent on the first signal is based on AI.

[0594] The above embodiments and all their sub-embodiments can be combined arbitrarily with each other.

[0595] Example 17

[0596] Example 17 illustrates a structural block diagram of a processing device for a second node according to an embodiment of this application; as shown in Figure 17. In Figure 17, the processing device B00 in the second node includes a second transmitter B01 and a second receiver B02.

[0597] As one embodiment, the second node includes a network-side device.

[0598] As one embodiment, the second node includes at least the former of base station equipment and core network equipment.

[0599] In one embodiment, the second node is a base station.

[0600] As one example, the second node is a satellite device.

[0601] As one example, the second node is a relay node.

[0602] As one embodiment, the second node is one of the testing apparatus, testing equipment, and testing instruments.

[0603] As one embodiment, the second transmitter B01 includes at least one of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0604] As one embodiment, the second transmitter B01 includes at least the first five of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0605] As one embodiment, the second transmitter B01 includes at least the first four of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0606] As one embodiment, the second transmitter B01 includes at least the first three of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0607] As one embodiment, the second transmitter B01 includes at least the first two of the following in Figure 4 of this application: antenna 420, transmitter 418, multi-antenna transmission processor 471, transmission processor 416, controller / processor 475, and memory 476.

[0608] As one embodiment, the second receiver B02 includes at least one of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiving processor 472, receiving processor 470, controller / processor 475, and memory 476.

[0609] As one embodiment, the second receiver B02 includes at least the first five of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiver processor 472, receiver processor 470, controller / processor 475, and memory 476.

[0610] As one embodiment, the second receiver B02 includes at least the first four of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiver processor 472, receiver processor 470, controller / processor 475, and memory 476.

[0611] As one embodiment, the second receiver B02 includes at least the first three of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiver processor 472, receiver processor 470, controller / processor 475, and memory 476.

[0612] As one embodiment, the second receiver B02 includes at least two of the following in Figure 4 of this application: antenna 420, receiver 418, multi-antenna receiver processor 472, receiver processor 470, controller / processor 475, and memory 476.

[0613] As one embodiment, the second transmitter B01 sends a first signaling, which schedules a first signal;

[0614] The second receiver B02 receives the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource;

[0615] Wherein, the first time-domain resource ends at least a first time interval after the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

[0616] As an example, the first time interval depends on a first parameter, the value of which depends on whether the processing of the first signal is based on AI.

[0617] As an example, the first time interval and the value of the first parameter are linearly related.

[0618] As an example, the first time interval is equal to the maximum value among a plurality of intermediate values; one of the intermediate values ​​has a linear relationship with the value of the first parameter.

[0619] As an example, the processing of the first signal is AI-based when at least one of the encoding and modulation of the first signal is performed by an AI model.

[0620] As an example, the processing of the first signal is AI-based when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model.

[0621] As one embodiment, the second receiver B02 receives a first information block, the first information block indicating that at least one function is available;

[0622] Whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein the first function includes an AI function.

[0623] As an example, the first time-domain resource is the next time-domain symbol that is later than the end of the first signaling interval.

[0624] As an example, the first signal carries user data.

[0625] As one embodiment, the second transmitter B01 transmits a second information block, or the second receiver B02 receives a second information block; wherein whether the processing of the first signal is based on AI depends on the indication of the second information block.

[0626] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The user equipment, terminal, and UE in this application include, but are not limited to, drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablets, laptops, vehicle-mounted communication devices, wireless sensors, internet cards, IoT terminals, RFID terminals, NB-IoT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base station or system equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, home base stations, relay base stations, gNB (NR Node B), TRP (Transmitter Receiver Point), and other wireless communication equipment.

[0627] Those skilled in the art will understand that this application may be implemented in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A first node for wireless communication, characterized in that, include: A first receiver receives a first signaling instruction, which schedules a first signal. The first transmitter sends the first signal; The transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource; Wherein, the first time-domain resource is at least a first time interval later than the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

2. The first node according to claim 1, characterized in that, The first time interval depends on a first parameter, the value of which depends on whether the processing of the first signal is based on AI.

3. The first node according to claim 2, characterized in that, The first time interval and the value of the first parameter have a linear relationship; Alternatively, the first time interval is equal to the maximum value among a plurality of intermediate quantities; and there is a linear relationship between one of the plurality of intermediate quantities and the value of the first parameter.

4. The first node according to any one of claims 1 to 3, characterized in that, The processing of the first signal is AI-based when at least one of the encoding and modulation of the first signal is performed by an AI model; Alternatively, the processing of the first signal is AI-based when at least one of the encoding of the first signaling and the modulation of the first signaling is performed by an AI model.

5. The first node according to any one of claims 1 to 4, characterized in that, include: The first transmitter sends a first information block, the first information block indicating that at least one function is available; Whether the processing of the first signal is based on AI includes: whether the at least one function includes a first function; wherein the first function includes an AI function.

6. The first node according to any one of claims 1 to 5, characterized in that, The first time-domain resource is the earliest time-domain symbol whose start time is at least later than the end time of the first signaling interval.

7. The first node according to any one of claims 1 to 6, characterized in that, The first signal carries user data.

8. A second node for wireless communication, characterized in that, include: The second transmitter sends the first signaling, which in turn schedules the first signal. A second receiver receives the first signal; The transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource; Wherein, the first time-domain resource is at least a first time interval later than the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

9. A method for a first node in wireless communication, characterized in that, include: Receive the first signaling, and the first signaling schedules the first signal; Send the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource; Wherein, the first time-domain resource is at least a first time interval later than the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

10. A method for a second node in wireless communication, characterized in that, include: Send the first signaling, and the first signaling schedules the first signal; Receive the first signal; the transmission of the first signal depends on the first symbol of the first signal not being earlier than the first time domain resource; Wherein, the first time-domain resource is at least a first time interval later than the end of the first signaling; the first time interval depends on whether the processing of the first signal is based on AI.

Images