Method and apparatus used in nodes for wireless communication and artificial intelligence

Abstract

Disclosed in the present application are a method and apparatus used in nodes for wireless communication and artificial intelligence. A first node receives a first information block, wherein the first information block indicates a plurality of resource sets; a first signal is transmitted in a first resource block, wherein the first resource block belongs to one of the plurality of resource sets; the first signal carries a random access preamble, and transmission of the first signal is based on contention; the plurality of resource sets are respectively targeted at a plurality of feature combinations, and any one of the plurality of feature combinations comprises at least one feature for AI / ML; and the first resource block comprises at least one of a time domain resource, a frequency domain resource or a sequence resource. In the present application, a feature combination supported by a terminal or a feature combination for triggering random access by the terminal is indicated by means of resource occupation of a signal in a random access procedure, such that a base station can acquire terminal information earlier.

Description

A method and apparatus in a node used for wireless communication and artificial intelligence

[0001] This application claims priority to the Chinese patent application No. 202411237705.5, filed on September 04, 2024, entitled "A method and apparatus in a node used for wireless communication and artificial intelligence", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to a signal transmission method and apparatus in a wireless communication system, and in particular to a random access method and apparatus. BACKGROUND

[0003] Utilizing AI / ML (Artificial Intelligence / Machine Learning) technology to improve the performance of 5G networks is an important part of realizing the deep integration of 5G and AI / ML and building intelligent 5G-Advanced (5.5G) networks. The 3GPP (3rd Generation Partnership Project) standard organization has started to study the standardization of intelligent RAN (Radio Access Networks) since Rel-16 (Release-16), mainly focusing on intelligent use cases, data collection enhancement, potential impact on RAN nodes and interfaces, etc. In Rel-18, the establishment of AI / ML-based 5G air interface enhancement has officially started the international standardization work of the integration of 5G air interface and AI / ML, mainly focusing on the study of use cases, life cycle management (LCM), simulation verification, data collection, etc.

[0004] At present, the development of AI / ML has entered the stage of large models. Communication large models can realize autonomous networks and intelligent services, support network operation optimization, and improve network efficiency. The deep integration of communication and AI is an important direction for future communication evolution. AI will empower the development and upgrading of 5G, 5.5G, and 6G, bringing new management modes such as automatic management of frequency bands and traffic, real-time analysis of user data and network load, and prediction of network status. SUMMARY

[0005] In the current standard, the network can configure specific random access resources for different features or feature combinations through random access resource partitioning (RACH partitioning) and feature combination preambles (Feature Combination Preambles), so that the network can identify the feature or feature combination triggering random access as soon as possible according to the received Msg1. The inventors have found that in future wireless communication systems, especially after the introduction of AI / ML, how to indicate more information to the base station as soon as possible in the random access process to promote the deep integration of AI / ML and communication is a problem worth studying.

[0006] To solve the above problems, a solution is disclosed in the present application. It should be noted that in the description of the above problems, NR system is taken as an example, and the present application is also applicable to scenarios such as future 6G system, and similar technical effects of NR system can be achieved. Further, although the original intention of the present application is for AI / ML scenarios, the present application can also be applied to other non-AI / ML scenarios. Further, a unified design scheme for different scenarios (such as other non-AI / ML scenarios, including but not limited to Vehicle to Everything (V2X), capacity enhancement system, near distance communication system, NTN (Non Terrestrial Network), IoT (Internet of Things), URLLC (Ultra Reliable Low Latency Communication) network, etc.) can also help to reduce hardware complexity and cost. In the case of no conflict, the embodiments in any node of the present application and the features in the embodiments can be applied to any other node. In the case of no conflict, the embodiments of the present application and the features in the embodiments can be arbitrarily combined with each other.

[0007] In particular, the explanation of the terminology, nouns, functions, and variables in the present application (if not specifically stated) can refer to the definitions in TS38 series, TS37 series in the technical standards (TS) of 3GPP (the 3rd Generation Partnership Project). If necessary, TS38.211, TS38.212, TS38.213, TS38.214, TS38.215, TS38.300, TS38.304, TS38.305, TS38.321, TS38.331, TS37.355, TS38.423 in the 3GPP technical standards can be referred to for the understanding of the present application.

[0008] As an embodiment, the explanation of the terminology in the present application refers to the definitions in the specification agreement TS38 series of 3GPP.

[0009] As an embodiment, the explanation of the terminology in the present application refers to the definitions in the specification agreement TS37 series of 3GPP.

[0010] As an embodiment, the explanation of the terminology in the present application refers to the definitions in the specification agreement Rel-17 version of 3GPP.

[0011] As an embodiment, the explanation of the terminology in the present application refers to the definitions in the specification agreement Rel-18 version of 3GPP.

[0012] The present application discloses a method for a first node in wireless communication and artificial intelligence, comprising:

[0013] receiving a first information block, the first information block indicating a plurality of resource sets;

[0014] sending a first signal in a first resource block, the first resource block belonging to one of the plurality of resource sets;

[0015] wherein the first signal carries a random access preamble, the sending of the first signal is contention-based; the plurality of resource sets are respectively for a plurality of characteristic combinations, at least one of the plurality of characteristic combinations includes at least one AI / ML-related characteristic; the first resource block includes at least one of time domain resources, frequency domain resources, or sequence resources.

[0016] As an embodiment, the problem to be solved by the present application includes: how to improve the probability of successful random access.

[0017] As an embodiment, the problem to be solved by the present application includes: how to indicate more information as early as possible.

[0018] As an embodiment, the problem to be solved by the present application includes: how to promote the deep integration of AI / ML and communication through enhancing the random access process.

[0019] As an embodiment, the characteristics of the above method include: in the present application, the base station configures the terminal with multiple resource sets based on a combination of characteristics, and when the terminal performs a random access process based on different resource sets, the base station can determine whether the first node supports AI / ML characteristics or the random access process performed by the first node is triggered based on AI / ML characteristics based on random access preamble resource occupation in the random access process.

[0020] As an embodiment, the characteristics of the above method include: in the present application, the terminal can select appropriate random access resources based on UE capability or random access trigger reason, and then indicate more information in the random access process through resource occupation as early as possible.

[0021] As an embodiment, the characteristics of the above method include: the first node is the terminal.

[0022] As an embodiment, the characteristics of the above method include: the first signal includes PRACH.

[0023] As an embodiment, the characteristics of the above method include: the first signal indicates whether the first node supports the deployment of an AI / ML model.

[0024] As an embodiment, the characteristics of the above method include: the first signal indicates whether the first node deploys an AI / ML model.

[0025] As an embodiment, the characteristics of the above method include: the first signal indicates whether the random access process associated with the first signal is triggered based on AI / ML.

[0026] As an embodiment, the benefits of the above method include: the present application supports the deep integration of AI and communication, improves the adaptability and intelligent level of the communication system, and thus improves the performance, efficiency and user experience of the communication system.

[0027] As an embodiment, the benefits of the above method include: through the resource occupation of the signal in the random access process, the terminal supports the combination of characteristics or the combination of characteristics that triggers the random access of the terminal, so that the base station can obtain terminal information earlier, and then apply AI / ML model to wireless communication as early as possible.

[0028] As an embodiment, the benefits of the above method include that, in the random access process, the base station acquires terminal information as early as possible, which can be based on more information for scheduling optimization and resource allocation, and improve the probability of random access success.

[0029] As an embodiment, the benefits of the above method include that the impact on the current standard is small, and good compatibility is achieved.

[0030] According to an aspect of the present application, the above method is characterized in that it comprises:

[0031] transmitting a second signal;

[0032] The second signal is for random access. One of the AI / ML characteristics included in the combination of characteristics is to determine whether the first node supports AI / ML capability. The second signal indicates AI / ML information of the first node, and the AI / ML information of the first node includes at least one of the following:

[0033] ID of the AI / ML model supported by the first node;

[0034] Functionality corresponding to the AI / ML model supported by the first node;

[0035] Training data set supported by the first node;

[0036] Associated ID supported by the first node;

[0037] Category corresponding to the first node for AI / ML.

[0038] As an embodiment, the ID refers to IDentify, proof.

[0039] As an embodiment, the ID refers to IDentification, identity.

[0040] As an embodiment, the ID refers to IDentity, identity or identification.

[0041] As an embodiment, the ID refers to IDentifier, identifier.

[0042] As an embodiment, the ID refers to InDex, index.

[0043] As an embodiment, the above method has the characteristics that the transmission of the first signal is earlier than the transmission of the second signal.

[0044] As an embodiment, the method has the characteristics that: the first signal carries limited information, and the first signal is contention-based, which may need to be retransmitted due to collisions in terminal transmission, and carrying a large amount of specific information in the first signal not only wastes resources but also increases the difficulty of decoding by the base station; the second signal provides more reliable uplink transmission based on the resources allocated by the base station, and then carries specific AI / ML information supported by the terminal in the second signal.

[0045] As an embodiment, the method has the characteristics that: when the first signal indicates that the first node supports AI / ML capability, the second signal carries AI / ML information supported by the first node.

[0046] As an embodiment, the method has the characteristics that: the first signal and the second signal in the random access process jointly indicate the information of the AI / ML capability supported by the UE.

[0047] As an embodiment, the method has the benefits that: the second signal indicates specific AI / ML information supported by the terminal, so that the base station can perform more accurate resource allocation and scheduling according to the capability of the UE, and optimize the resource utilization efficiency of the network.

[0048] As an embodiment, the method has the benefits that: it ensures that the terminal successfully accesses the network and fully develops the terminal capability.

[0049] As an embodiment, the method has the benefits that: it fully develops the advantages of different signals and ensures reliable transmission of different uplink signals.

[0050] According to an aspect of the present application, the method has the characteristics that: the time domain resources occupied by the first resource block belong to a first time domain resource set, and the first node supports AI / ML capability; the time domain resources occupied by the first resource block do not belong to the first time domain resource set, and the first node does not support AI / ML capability.

[0051] As an embodiment, the present application solves the problem of how the base station determines whether the terminal supports AI / ML capability according to the first signal.

[0052] As an embodiment, the method has the characteristics that: in the present application, the base station configures specific time domain resources for terminals supporting AI / ML capability feature combinations, and determines whether the terminal supports AI / ML capability by the time domain resources occupied by the PRACH sent by the terminal.

[0053] As an embodiment, the method has the characteristics that: the multiple resource sets are multiple time domain resource sets, and the first time domain resource set belongs to the multiple time domain resource sets.

[0054] As an embodiment, the method has the feature that the multiple time domain resource sets include multiple RO occupied time domain resources.

[0055] As an embodiment, the method has the feature that the first time domain resource set includes multiple RO occupied time domain resources.

[0056] As an embodiment, the method has the benefit of simplicity, without complex frequency domain resource and sequence resource management.

[0057] According to an aspect of the present application, the method has the feature that the frequency domain resources occupied by the first resource block belong to a first frequency domain resource set, and the first node supports AI / ML capability; the frequency domain resources occupied by the first resource block do not belong to the first frequency domain resource set, and the first node does not support AI / ML capability.

[0058] As an embodiment, the present application addresses the problem of how the base station determines whether the terminal supports AI / ML capability based on the first signal.

[0059] As an embodiment, the method has the feature that in the present application, the base station configures specific frequency domain resources for terminals supporting AI / ML capability feature combinations, and determines whether the terminal supports AI / ML capability by the frequency domain resources occupied by the PRACH sent by the terminal.

[0060] As an embodiment, the method has the feature that the multiple resource sets are multiple frequency domain resource sets, and the first frequency domain resource set belongs to the multiple frequency domain resource sets.

[0061] As an embodiment, the method has the feature that any frequency resource set in the multiple frequency domain resource sets includes frequency domain resources occupied in one time instance, and the one time instance includes RO occupied time domain resources.

[0062] As an embodiment, the method has the feature that any frequency domain resource set in the multiple frequency domain resource sets occupies continuous frequency domain resources.

[0063] As an embodiment, the method has the feature that the multiple frequency domain resource sets occupy nested frequency domain resources.

[0064] As an embodiment, the method has the benefit of better spectrum efficiency.

[0065] As an embodiment, the method has the benefit that frequency reuse can improve system concurrent access capability.

[0066] According to an aspect of the present application, the method is characterized in that: the sequence resources occupied by the first resource block belong to a first sequence resource set, and the first node supports AI / ML capability; the sequence resources occupied by the first resource block do not belong to the first sequence resource set, and the first node does not support AI / ML capability.

[0067] As an embodiment, the problem to be solved by the present application includes: how the base station determines whether the terminal supports AI / ML capability according to the first signal.

[0068] As an embodiment, the method is characterized in that: in the present application, the base station configures specific sequence resources for the terminal supporting the AI / ML capability feature combination, and determines whether the terminal supports AI / ML capability by the sequence resources occupied by the PRACH sent by the terminal.

[0069] As an embodiment, the method is characterized in that: the plurality of resource sets are a plurality of sequence resource sets, and the first sequence resource set belongs to the plurality of sequence resource sets.

[0070] As an embodiment, the method is characterized in that: any sequence resource set in the plurality of sequence resource sets corresponds to at least one SSB.

[0071] As an embodiment, the method is characterized in that: sequence resources can provide more reliable information transmission.

[0072] As an embodiment, the method is characterized in that: when the load of the UE supporting AI / ML capability and the UE not supporting AI / ML capability in the cell is unbalanced, compared with frequency resources and / or time domain resources, using sequence resources to deliver Boolean information can reduce the probability of signal collision and retransmission.

[0073] According to an aspect of the present application, the method is characterized in that: the second signal includes a first field, and the first field included in the second signal indicates the AI / ML information of the first node; when the first node does not support AI / ML capability, the value of the first field included in the second signal is fixed or predefined.

[0074] As an embodiment, the method is characterized in that: the first signal indicates whether the first node supports AI / ML capability; when the first node supports AI / ML capability, the second signal indicates specific information of AI / ML supported by the first node; when the first node does not support AI / ML capability, the field indicating the specific information of AI / ML supported by the first node in the second signal is set to a reserved value.

[0075] As an embodiment, the method has the feature that the first signal and the second signal jointly indicate AI / ML information of the first node.

[0076] As an embodiment, the method has the benefit of good compatibility, ensuring that terminals that do not support AI / ML capabilities can also correctly access the network, avoiding service interruption or performance degradation of terminals due to not supporting AI / ML capabilities.

[0077] As an embodiment, the method has the benefit of establishing consensus between the base station and the terminal, reducing the probability of base station decoding errors, and improving user experience.

[0078] As an embodiment, the method has the benefit of simplicity and ease of deployment.

[0079] According to an aspect of the present application, the method is characterized in that the first signal is Msg1 and the second signal is Msg3; or the first signal is PRACH in MsgA and the second signal is PUSCH in MsgA.

[0080] As an embodiment, the method has the feature that the present application simultaneously supports 4-step random access procedures and 2-step random access procedures.

[0081] As an embodiment, the method has the feature that the first signal is PRACH and the second signal is PUSCH.

[0082] As an embodiment, the method has the benefit that 4-step random access procedures ensure the reliability of random access in high-load environments, 2-step random access procedures can reduce terminal power consumption and access latency, the present application simultaneously supports 2-step random access and 4-step random access, allowing the base station to select the most suitable random access procedure according to the current channel state and traffic demand, achieving a balance between performance and reliability.

[0083] As an embodiment, the method has the benefit of improving compatibility with existing systems and reducing the impact on existing networks.

[0084] As an embodiment, the method has the benefit of providing greater flexibility for future network evolution and optimization.

[0085] According to an aspect of the present application, the method is characterized in that the first node is a user equipment.

[0086] According to an aspect of the present application, the method is characterized in that the first node is a terminal.

[0087] The application discloses a method in a second node for wireless communication and artificial intelligence, comprising:

[0088] sending a first information block, the first information block indicating a plurality of resource sets;

[0089] receiving a first signal in a first resource block, the first resource block belonging to one of the plurality of resource sets;

[0090] wherein the first signal carries a random access preamble, the sending of the first signal is contention-based; the plurality of resource sets are respectively for a plurality of characteristic combinations, at least one of the plurality of characteristic combinations includes at least one AI / ML-related characteristic; the first resource block includes at least one of time domain resources, frequency domain resources, or sequence resources.

[0091] As an embodiment, the above-mentioned method includes the following characteristics: the second node is a base station.

[0092] As an embodiment, the above-mentioned method includes the following characteristics: the second node is a gNB.

[0093] As an embodiment, the above-mentioned method includes the following characteristics: the second node is an eNB.

[0094] As an embodiment, the above-mentioned method includes the following characteristics: the receiving of the first signal in the first resource block includes detecting the first signal in the resource set where the first resource block is located.

[0095] As an embodiment, the above-mentioned method includes the following characteristics: the receiving of the first signal in the first resource block includes detecting the first signal in the plurality of resource sets.

[0096] As an embodiment, the second node does not know that the first signal is sent in the first resource block before receiving the first signal.

[0097] As an embodiment, the sending of the first signal in the first resource block is contention-based.

[0098] According to an aspect of the application, the above-mentioned method includes the following characteristics:

[0099] receiving a second signal;

[0100] wherein the second signal is for random access; the sender of the second signal is a first node, one AI / ML-related characteristic included in the plurality of characteristic combinations is to determine that the first node supports AI / ML capability; the second signal indicates AI / ML information of the first node, the AI / ML information of the first node includes at least one of the following:

[0101] - an ID of an AI / ML model supported by the first node;

[0102] - a Functionality corresponding to an AI / ML model supported by the first node;

[0103] - a training data set supported by the first node;

[0104] - an Associated ID supported by the first node;

[0105] - a Category corresponding to the first node for AI / ML.

[0106] According to an aspect of the present application, the above method is characterized in that the time domain resource occupied by the first resource block belongs to a first time domain resource set, and the first node supports an AI / ML capability; the time domain resource occupied by the first resource block does not belong to the first time domain resource set, and the first node does not support an AI / ML capability.

[0107] According to an aspect of the present application, the above method is characterized in that the frequency domain resource occupied by the first resource block belongs to a first frequency domain resource set, and the first node supports an AI / ML capability; the frequency domain resource occupied by the first resource block does not belong to the first frequency domain resource set, and the first node does not support an AI / ML capability.

[0108] According to an aspect of the present application, the above method is characterized in that the sequence resource occupied by the first resource block belongs to a first sequence resource set, and the first node supports an AI / ML capability; the sequence resource occupied by the first resource block does not belong to the first sequence resource set, and the first node does not support an AI / ML capability.

[0109] According to an aspect of the present application, the above method is characterized in that the second signal includes a first field, the first field included in the second signal indicates the AI / ML information of the first node; when the first node does not support an AI / ML capability, the value of the first field included in the second signal is fixed or predefined.

[0110] According to an aspect of the present application, the above method is characterized in that the first signal is Msg1 and the second signal is Msg3; or the first signal is PRACH in MsgA and the second signal is PUSCH in MsgA.

[0111] According to an aspect of the present application, the above method is characterized in that the second node is a base station.

[0112] The application discloses a device for a first node in wireless communication and artificial intelligence, comprising:

[0113] a first receiver, receiving a first information block indicating a plurality of resource sets;

[0114] a first transmitter, transmitting a first signal in a first resource block belonging to one of the plurality of resource sets;

[0115] wherein the first signal carries a random access preamble, and the transmission of the first signal is contention-based; the plurality of resource sets are respectively for a plurality of characteristic combinations, at least one of the plurality of characteristic combinations includes at least one AI / ML characteristic; and the first resource block includes at least one of time domain resources, frequency domain resources or sequence resources.

[0116] The application discloses a device for a second node in wireless communication and artificial intelligence, comprising:

[0117] a second transmitter, transmitting a first information block indicating a plurality of resource sets;

[0118] a second receiver, receiving a first signal in a first resource block belonging to one of the plurality of resource sets;

[0119] wherein the first signal carries a random access preamble, and the transmission of the first signal is contention-based; the plurality of resource sets are respectively for a plurality of characteristic combinations, at least one of the plurality of characteristic combinations includes at least one AI / ML characteristic; and the first resource block includes at least one of time domain resources, frequency domain resources or sequence resources.

[0120] As an embodiment, compared with the conventional scheme, the application has the following advantages, but is not limited to:

[0121] In the application, AI and communication are deeply integrated, the adaptability and intelligent level of the communication system are improved, and the performance, efficiency and user experience of the communication system are improved;

[0122] In the random access stage, the base station can determine whether the terminal supports AI / ML capability through PRACH, so that the base station can adjust the resource allocation strategy in time according to the terminal capability, reduce unnecessary signaling interaction and overhead, and improve the utilization rate of network resources;

[0123] A plurality of different PRACH information carrying modes are provided, and the network can select a suitable indication mode based on different deployment scenarios to improve the compatibility, flexibility and adaptability of the standard. BRIEF DESCRIPTION OF DRAWINGS

[0124] Other features, objects, and advantages of the application will become more apparent from the following detailed description when read in connection with the following accompanying drawings:

[0125] Figure 1 shows a flow diagram of transmissions by a first node according to one embodiment of the application;

[0126] Figure 2 shows a schematic diagram of a network architecture according to one embodiment of the application;

[0127] Figure 3 shows a schematic diagram of an embodiment of a radio protocol architecture for the user and control planes according to one embodiment of the application;

[0128] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to one embodiment of the application;

[0129] Figure 5 shows a flow diagram of transmissions between a first node and a second node according to one embodiment of the application;

[0130] Figure 6 shows a schematic diagram of a plurality of time domain resource sets according to one embodiment of the application;

[0131] Figure 7 shows a schematic diagram of a plurality of frequency domain resource sets according to one embodiment of the application;

[0132] Figure 8 shows a schematic diagram of a plurality of sequence resource sets according to one embodiment of the application;

[0133] Figure 9 shows a schematic diagram of a second signal according to one embodiment of the application;

[0134] Figure 10 shows a schematic diagram of RAN domain AI / ML function deployment according to one embodiment of the application;

[0135] Figure 11 shows a schematic diagram of AI / ML function deployment for a UE according to one embodiment of the application;

[0136] Figure 12 shows a schematic diagram of an artificial intelligence or machine learning based processing system according to one embodiment of the application;

[0137] Figure 13 shows a schematic diagram of artificial intelligence or machine learning according to one embodiment of the application;

[0138] Figure 14 shows a structural block diagram for a processing apparatus in a first node according to one embodiment of the application;

[0139] Figure 15 shows a structural block diagram for a processing apparatus in a second node according to one embodiment of the application. DETAILED DESCRIPTION

[0140] The technical solutions of the present application will be further described in detail below with reference to the drawings. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily without conflict. Based on performance, flexibility, complexity, overhead and compatibility, etc., the person skilled in the art has the motivation to flexibly combine the embodiments in different drawings without conflict, including but not limited to the embodiments in FIG. 1 and the embodiments in FIG. 5-FIG. 15, the embodiments in FIG. 5 and the embodiments in FIG. 6-FIG. 15, etc.

[0141] Embodiment 1

[0142] Embodiment 1 illustrates a flowchart of the first node transmission according to an embodiment of the present application, as shown in FIG. 1. In FIG. 1, each block represents a step. In particular, the order of the steps in the blocks does not represent a specific time sequence between the steps.

[0143] The first node receives a first information block in step 101, the first information block indicating a plurality of resource sets; and transmits a first signal in a first resource block in step 102, the first resource block belonging to one of the plurality of resource sets.

[0144] In embodiment 1, the first signal carries a random access preamble, and the transmission of the first signal is based on contention; the plurality of resource sets are respectively for a plurality of characteristic combinations, at least one of the plurality of characteristic combinations including at least one AI / ML characteristic; and the first resource block includes at least one of a time domain resource, a frequency domain resource or a sequence resource.

[0145] As an embodiment, the AI / ML refers to Artificial Intelligence / Machine Learning.

[0146] As an embodiment, the AI / ML includes Machine Learning.

[0147] As an embodiment, the AI / ML includes Deep Learning.

[0148] As an embodiment, the first node is a User Equipment (UE).

[0149] As an embodiment, the first node is a terminal.

[0150] As an embodiment, the first node is the first node in the present application.

[0151] As one embodiment, the first node receives the first information block.

[0152] As one embodiment, the first information block is carried by higher layer signaling.

[0153] As one embodiment, the first information block is transmitted by RRC (Radio Resource Control) signaling.

[0154] As one embodiment, the first information block includes one or more RRC IEs (Information Elements).

[0155] As one embodiment, the first information block includes one or more fields in one RRC IE.

[0156] As one embodiment, the first information block includes information in one or more fields of each of a plurality of RRC IEs.

[0157] As one embodiment, the first information block is one RRC IE.

[0158] As one embodiment, the first information block includes a system broadcast message.

[0159] As one embodiment, the first information block includes some or all fields included in RMSI (Remaining Minimum System Information).

[0160] As one embodiment, the first information block includes RMSI.

[0161] As one embodiment, the first information block includes some or all fields included in MIB (Master Information Block).

[0162] As one embodiment, the first information block includes MIB.

[0163] As one embodiment, the first information block includes some or all fields included in one SIB (System Information Block).

[0164] As one embodiment, the first information block includes SIB.

[0165] As one embodiment, the first information block includes some or all fields of SIB1 (System Information Block 1).

[0166] As one embodiment, the first information block includes SIB1.

[0167] As one embodiment, the first information block includes SIBx, x being a positive integer.

[0168] As one embodiment, the first information block includes ServingCellConfigCommonSIB IE.

[0169] As one embodiment, the first information block includes one or more fields of ServingCellConfigCommonSIB IE.

[0170] As one embodiment, the first information block includes UplinkConfigCommonSIB IE.

[0171] As one embodiment, the first information block includes one or more fields of UplinkConfigCommonSIB IE.

[0172] As one embodiment, the first information block includes BWP-UplinkCommon IE.

[0173] As one embodiment, the first information block includes one or more fields of BWP-UplinkCommon IE.

[0174] As one embodiment, the first information block includes AdditionalRACH-ConfigList IE.

[0175] As one embodiment, the first information block includes one or more fields of AdditionalRACH-ConfigList IE.

[0176] As one embodiment, the first information block includes AdditionalRACH-Config IE.

[0177] As one embodiment, the first information block includes one or more fields of AdditionalRACH-Config IE.

[0178] As one embodiment, the first information block includes RACH-ConfigCommon IE.

[0179] As one embodiment, the first information block includes one or more fields in the RACH-ConfigCommon IE.

[0180] As one embodiment, the first information block includes the MsgA-ConfigCommon IE.

[0181] As one embodiment, the first information block includes one or more fields in the MsgA-ConfigCommon IE.

[0182] As one embodiment, the first information block includes the RACH-ConfigCommonTwoStepRA IE.

[0183] As one embodiment, the first information block includes one or more fields in the RACH-ConfigCommonTwoStepRA IE.

[0184] As one embodiment, the first information block includes the FeatureCombinationPreambles IE.

[0185] As one embodiment, the first information block includes one or more fields in the FeatureCombinationPreambles IE.

[0186] As one embodiment, the first information block includes the FeatureCombination IE.

[0187] As one embodiment, the first information block includes one or more fields in the FeatureCombination IE.

[0188] As one embodiment, the first information block indicates the plurality of resource sets.

[0189] As one embodiment, the plurality of resource sets includes a plurality of time domain resource sets.

[0190] As one subembodiment of this embodiment, any two of the plurality of time domain resource sets are orthogonal in time domain.

[0191] As one subembodiment of this embodiment, at least two of the plurality of time domain resource sets are orthogonal in time domain.

[0192] As one subembodiment of this embodiment, any one of the plurality of time domain resource sets occupies one slot in time domain.

[0193] As one subembodiment of this embodiment, any of the plurality of time-domain resource sets occupies a positive integer number of multicarrier symbols in time domain.

[0194] As one embodiment, the plurality of resource sets comprises a plurality of time-domain resource sets, and the first information block indirectly indicates the plurality of time-domain resource sets.

[0195] As one subembodiment of this embodiment, the indirect indication comprises indicating a position of time-domain resources included in one of the plurality of time-domain resource sets by indicating a row of a predefined table.

[0196] As one subembodiment of this embodiment, the indirect indication comprises indicating a position of time-domain resources included in the plurality of time-domain resource sets by indicating another IE.

[0197] As one subembodiment of this embodiment, the indirect indication comprises indirectly indicating a starting position of time-domain resources occupied by each of the plurality of time-domain resource sets.

[0198] As one subembodiment of this embodiment, the indirect indication comprises indirectly indicating a length of time-domain resources occupied by each of the plurality of time-domain resource sets.

[0199] As one subembodiment of this embodiment, the indirect indication comprises indirectly indicating a subframe in which each of the plurality of time-domain resource sets is located.

[0200] As one subembodiment of this embodiment, the indirect indication comprises indirectly indicating a slot in which each of the plurality of time-domain resource sets is located in a subframe.

[0201] As one subembodiment of this embodiment, the indirect indication comprises indirectly indicating a slot in which each of the plurality of time-domain resource sets is located.

[0202] As one subembodiment of this embodiment, any of the plurality of time-domain resource sets occupies time-domain resources in a period, and the indirect indication comprises indirectly indicating a period and an offset value in time domain for each of the plurality of time-domain resource sets.

[0203] As one subembodiment of this embodiment, any of the plurality of time-domain resource sets occupies time-domain resources in a period, and the indirect indication comprises indirectly indicating a period and an offset value in time domain for each of the plurality of time-domain resource sets.

[0204] As one embodiment, the plurality of resource sets comprises a plurality of frequency domain resource sets.

[0205] As one sub-embodiment of this embodiment, any two of the plurality of frequency domain resource sets are orthogonal in frequency domain.

[0206] As one sub-embodiment of this embodiment, at least two of the plurality of frequency domain resource sets are orthogonal in frequency domain.

[0207] As one sub-embodiment of this embodiment, any one of the plurality of frequency domain resource sets occupies a positive integer number of RBs (Resource Blocks) in frequency domain.

[0208] As one sub-embodiment of this embodiment, any one of the plurality of frequency domain resource sets occupies a positive integer number of subcarriers in frequency domain.

[0209] As one sub-embodiment of this embodiment, any one of the plurality of frequency domain resource sets corresponds to one subband in frequency domain.

[0210] As one sub-embodiment of this embodiment, the first information block directly indicates the plurality of frequency domain resource sets.

[0211] As one sub-embodiment of this sub-embodiment, the direct indication comprises directly configuring a starting position of each of the plurality of frequency domain resource sets.

[0212] As one sub-embodiment of this sub-embodiment, the direct indication comprises directly configuring a length of frequency domain resources included in each of the plurality of frequency domain resource sets.

[0213] As one sub-embodiment of this sub-embodiment, the direct indication comprises directly configuring a number of frequency division multiplexing of the plurality of frequency domain resource sets in one time instance.

[0214] As one sub-embodiment of this embodiment, the first information block indirectly indicates the plurality of frequency domain resource sets.

[0215] As one sub-embodiment of this embodiment, the indirect indication comprises indirectly indicating a length of frequency domain resources occupied by the plurality of frequency domain resource sets by indicating a pre-defined table.

[0216] As one sub-embodiment of this sub-embodiment, the indirect indication comprises indirectly indicating a length of frequency domain resources occupied by the plurality of frequency domain resource sets by indicating other parameters.

[0217] As an implementation of the sub-embodiment, the indirect indication comprises indicating a SubCarrier Spacing (SCS) of the multiple frequency domain resource sets by indicating a predefined table.

[0218] As an implementation, the multiple resource sets comprise multiple time-frequency resource sets.

[0219] As a sub-embodiment of the implementation, time-frequency resources occupied by any two of the multiple time-frequency resource sets are orthogonal.

[0220] As a sub-embodiment of the implementation, REs (Resource Elements) occupied by any two of the multiple time-frequency resource sets are orthogonal.

[0221] As a sub-embodiment of the implementation, any of the multiple time-frequency resource sets occupies a positive integer number of multicarrier symbols in the time domain and a positive integer number of RBs in the frequency domain.

[0222] As an implementation, the first information block directly configures REs occupied by the multiple time-frequency resource sets.

[0223] As an implementation, the first information block indirectly indicates time domain resources occupied by the multiple time-frequency resource sets.

[0224] As an implementation, the first information block directly indicates frequency domain resources occupied by the multiple time-frequency resource sets.

[0225] As an implementation, the first information block indirectly indicates frequency domain resources occupied by the multiple time-frequency resource sets.

[0226] As an implementation, the first information block indirectly indicates positions and quantities of multicarrier symbols occupied by any of the multiple time-frequency resource sets in the time domain, and directly indicates positions and quantities of RBs occupied by a carrier frequency of any of the multiple time-frequency resource sets.

[0227] As an implementation, the multiple resource sets comprise multiple sequence resource sets.

[0228] As a sub-embodiment of the implementation, sequence resources occupied by any two of the multiple sequence resource sets are orthogonal.

[0229] As one subembodiment of the embodiment, any one of the plurality of sequence resource sets comprises a plurality of sequence resources, and the plurality of sequence resources respectively correspond to a plurality of sequences, and any two of the plurality of sequences are different.

[0230] As one subembodiment of the embodiment, any two of the plurality of sequence resource sets respectively correspond to different root sequence lengths.

[0231] As one subembodiment of the embodiment, any two of the plurality of sequence resource sets respectively correspond to different random access channel formats.

[0232] As one subembodiment of the embodiment, the first information block directly indicates the root sequence length of the plurality of sequence resource sets.

[0233] As one subembodiment of the embodiment, the first information block indirectly indicates the sequence number of the root sequence of the plurality of sequence resource sets.

[0234] As one subembodiment of the embodiment, the first information block indirectly indicates the random access channel format of the plurality of sequence resource sets.

[0235] As one subembodiment of the embodiment, the first information block indirectly indicates the cyclic shift of the plurality of sequence resource sets.

[0236] As one subembodiment of the embodiment, the first information block indirectly indicates the N CS .

[0237] As one embodiment, the meaning of the two sequences being different in the present application includes that the two sequences have different generation formulas.

[0238] As one embodiment, the meaning of the two sequences being different in the present application includes that the two sequences respectively correspond to different root sequences.

[0239] As one embodiment, the meaning of the two sequences being different in the present application includes that the two sequences respectively adopt root sequences corresponding to different physical indexes.

[0240] As one embodiment, the meaning of the two sequences being different in the present application includes that the two sequences respectively correspond to different cyclic shifts.

[0241] As one embodiment, the meaning of the two sequences being different in the present application includes that the two sequences respectively correspond to different N CS .

[0242] As one embodiment, the cyclic shift and N CS For the specific definition, please refer to clause 5.3.2 of 3GPP (3rd Generation Partner Project) TS (Technical Specification) 38.211.

[0243] As one embodiment, the first node transmits the first signal in the first resource block.

[0244] As one embodiment, the first signal is a baseband signal.

[0245] As one embodiment, the first signal is a radio frequency signal.

[0246] As one embodiment, the first signal is a wireless signal.

[0247] As one embodiment, the first signal is generated by a pseudo-random sequence.

[0248] As one embodiment, the first signal includes a ZC sequence (Zadoff-Chu sequence).

[0249] As one embodiment, the first signal is generated by a ZC sequence.

[0250] As one embodiment, the first signal includes a PRACH (Physical Random Access CHannel).

[0251] As one embodiment, the first signal is a PRACH.

[0252] As one embodiment, the first signal includes a RACH (Random Access CHannel).

[0253] As one embodiment, the first signal is a RACH.

[0254] As one embodiment, the first signal includes a Preamble.

[0255] As one embodiment, the first signal is a Preamble.

[0256] As one embodiment, the first signal includes only one Preamble.

[0257] As an example, the first signal comprises Msg1 (Message 1).

[0258] As an example, the first signal is Msg1.

[0259] As an example, Msg1 in the present application refers to Massage 1.

[0260] As an example, Msg1 in the present application refers to Msg 1.

[0261] As an example, Msg1 in the present application refers to MSG1.

[0262] As an example, the first signal comprises MsgA (Message A).

[0263] As an example, the first signal is PRACH in MsgA.

[0264] As an example, MsgA in the present application refers to Massage A.

[0265] As an example, MsgA in the present application refers to Msg A.

[0266] As an example, MsgA in the present application refers to MSGA.

[0267] As an example, the first resource block corresponds to a time domain resource.

[0268] As an example, the first resource block corresponds to a frequency domain resource.

[0269] As an example, the first resource block corresponds to a time-frequency resource.

[0270] As an example, the first resource block corresponds to an RO.

[0271] As an example, RO in the present application refers to RACH Occasion.

[0272] As an example, RO in the present application refers to PRACH Occasion.

[0273] As an example, RO in the present application refers to RA (Random Access) Occasion.

[0274] As an example, the first resource block corresponds to a sequence resource.

[0275] As an example, the first resource block corresponds to a Preamble.

[0276] As an embodiment, the time domain resource occupied by the first signal is the time domain resource corresponding to the first resource block.

[0277] As an embodiment, the frequency domain resource occupied by the first signal is the frequency domain resource corresponding to the first resource block.

[0278] As an embodiment, the time-frequency resource occupied by the first signal is the time-frequency resource corresponding to the first resource block.

[0279] As an embodiment, the random access preamble carried by the first signal is the sequence resource corresponding to the first resource block.

[0280] As an embodiment, the first resource block belongs to one of the multiple resource sets.

[0281] As an embodiment, the multiple resource sets include at least a first resource set, and the first resource set includes at least the first resource block.

[0282] As an embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set includes multiple resource blocks, and the first resource block is one of the multiple resource blocks.

[0283] As an embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set includes only one resource block, and the first resource block is the resource block.

[0284] As an embodiment, the first signal carries a random access preamble.

[0285] As an embodiment, the first signal includes a random access preamble.

[0286] As an embodiment, the first signal includes only one random access preamble.

[0287] As an embodiment, the random access preamble carried by the first signal is not designated by the sender of the first information block.

[0288] As an embodiment, the random access preamble carried by the first signal is not assigned by the sender of the first information block.

[0289] As an embodiment, the random access preamble carried by the first signal is selected by a MAC (Medium Access Control) entity of the first node in random access preambles used for CBRA (Contention Based Random Access).

[0290] As an embodiment, the transmission of the first signal is contention-based.

[0291] As an embodiment, the transmission of the first signal belongs to a procedure of contention-based random access.

[0292] As an embodiment, the first node initiates a CBRA (Contention Based Random Access) procedure, and the CBRA procedure includes the transmission of the first signal.

[0293] As an embodiment, the multiple resource sets are respectively for the multiple feature combinations.

[0294] As an embodiment, any feature combination of the multiple feature combinations includes at least one feature.

[0295] As an embodiment, the meaning that the multiple resource sets are respectively for multiple feature combinations includes that higher layer signaling configuring the multiple resource sets indicates the multiple feature combinations at the same time.

[0296] As an embodiment, the meaning that the multiple resource sets are respectively for multiple feature combinations includes that the multiple feature combinations are associated to the multiple resource sets.

[0297] As an embodiment, the meaning that the multiple resource sets are respectively for multiple feature combinations includes that the multiple resource sets are one-to-one corresponding to the multiple feature combinations.

[0298] As an embodiment, the meaning that the multiple resource sets are respectively for multiple feature combinations includes that the multiple resource sets respectively correspond to the multiple feature combinations.

[0299] As an embodiment, the meaning that the multiple resource sets are respectively for multiple feature combinations includes that a given resource set of the multiple resource sets is only valid in a random access procedure of a given feature combination of the multiple feature combinations corresponding to the given resource set.

[0300] As an embodiment, the meaning that the multiple resource sets are respectively for multiple feature combinations includes that a given resource set of the multiple resource sets is used to determine a feature combination of the multiple feature combinations corresponding to the given resource set.

[0301] As one embodiment, the meaning that the plurality of resource sets respectively correspond to a plurality of combinations of characteristics includes that a given resource set to which the first resource block in the plurality of resource sets belongs is used to determine a combination of characteristics corresponding to the given resource set in the plurality of combinations of characteristics.

[0302] As one embodiment, at least one of the plurality of combinations of characteristics includes at least one AI / ML-related characteristic.

[0303] As one embodiment, any of the plurality of combinations of characteristics includes at least one AI / ML-related characteristic.

[0304] As one embodiment, at least one of the plurality of combinations of characteristics includes at least a first one of the following characteristics:

[0305] -AI / ML;

[0306] -RedCap (Reduced Capability);

[0307] -eRedCap (enhanced RedCap);

[0308] -SDT (Small Data Transmission);

[0309] -NS (Network Slice);

[0310] -Msg1 repetition;

[0311] -Msg3 repetition.

[0312] As one embodiment, the plurality of combinations of characteristics includes a first combination of characteristics and a second combination of characteristics, the first combination of characteristics being support of AI / ML capability, and the second combination of characteristics being no support of AI / ML capability.

[0313] As one embodiment, the plurality of combinations of characteristics includes at least one combination of characteristics, the at least one combination of characteristics corresponding to a combination of a plurality of types of characteristics.

[0314] As one sub-embodiment of this embodiment, the plurality of types of characteristics include a first type of characteristic, the first type of characteristic being used to determine whether AI / ML is supported.

[0315] As one dependent embodiment of this sub-embodiment, the first type of characteristic is one of support of AI / ML capability, no support of AI / ML capability.

[0316] As one sub-example of this example, the plurality of types of characteristics includes a second type of characteristic that is used to determine functionality of the supported AI / ML model.

[0317] As one dependent example of this sub-example, the second type of characteristic indicates one of a set of AI / ML models for a given functionality, the set of AI / ML models for the given functionality including at least one of:

[0318] - an AI / ML model for CSI (Channel State Information);

[0319] - an AI / ML model for BM (Beam Management);

[0320] - an AI / ML model for mobility;

[0321] - an AI / ML model for data transmission.

[0322] As one dependent example of this sub-example, the second type of characteristic indicates one of a set of AI / ML models for a given functionality, the set of AI / ML models for the given functionality including at least one of:

[0323] - an AI / ML model for RAN (Radio Access Network);

[0324] - an AI / ML for CN (Core Network);

[0325] - an AI / ML model for OAM (Operations, Administration and Maintenance).

[0326] As one dependent example of this sub-example, the second type of characteristic indicates one of a set of AI / ML models for a given functionality, the set of AI / ML models for the given functionality including at least one of:

[0327] - an AI / ML model for PHY (PHYsical);

[0328] - an AI / ML model for MAC (Medium Access Control);

[0329] - an AI / ML model for RRC;

[0330] - AI / ML model for sensing.

[0331] As one sub-embodiment of this sub-embodiment, the second type of characteristic represents one of a set of AI / ML model for a given function, the set of AI / ML model for the given function comprising at least one of:

[0332] - AI / ML model for ES (Energy Saving);

[0333] - AI / ML model for NS;

[0334] - AI / ML model for ISAC (Integrated Sensing and Communication).

[0335] As one sub-embodiment of this embodiment, the plurality of types of characteristics comprises a third type of characteristic, the third type of characteristic being used to determine a number of supported AI / ML models.

[0336] As one sub-embodiment of this sub-embodiment, the third type of characteristic represents one of a set of AI / ML model number values supported; the set of AI / ML model number values supported comprising at least one of:

[0337] - 1 AI / ML model is supported;

[0338] - 2 AI / ML models are supported;

[0339] - K1 AI / ML models are supported, K1 being a positive integer greater than 2.

[0340] As one sub-embodiment of this embodiment, the plurality of types of characteristics comprises a fourth type of characteristic, the fourth type of characteristic being used to determine a maximum computing power of AI / ML supported by the terminal.

[0341] As one sub-embodiment of this sub-embodiment, the fourth type of characteristic represents one of a set of maximum computing power of AI / ML supported by the first node number values; the set of maximum computing power of AI / ML supported by the first node number values comprising at least one of:

[0342] - the maximum computing power of AI / ML supported number value is equal to 1;

[0343] - the maximum computing power of AI / ML supported number value is equal to 2;

[0344] - the maximum computing power of AI / ML supported number value is equal to 4;

[0345] - the maximum number of AI / ML supported is equal to K2, K2 being a positive integer greater than 4.

[0346] As a sub-embodiment of this embodiment, one of the combinations of features comprises a combination of at least two of the first type of features, the second type of features, the third type of features and the fourth type of features.

[0347] As an embodiment, the plurality of combinations of features comprises a first combination of features, the first combination of features comprising at least a first one of the following features:

[0348] - AI / ML;

[0349] - RedCap;

[0350] - eRedCap;

[0351] - SDT;

[0352] - NS;

[0353] - Msg1 repetition;

[0354] - Msg3 repetition.

[0355] As a sub-embodiment of this embodiment, the AI / ML being set to true indicates that the set of resources corresponding to the first combination of features is valid when AI / ML features are supported by the first node.

[0356] As a sub-embodiment of this embodiment, the AI / ML being set to true indicates that the set of resources corresponding to the first combination of features can be used for random access when AI / ML features are supported by the first node.

[0357] As a sub-embodiment of this embodiment, the AI / ML being set to true indicates that the set of resources corresponding to the first combination of features is valid when random access is triggered based on AI / ML features by the first node.

[0358] As an embodiment, the plurality of combinations of features comprises a third combination of features, the third combination of features comprising one or more of the following features:

[0359] - AI / ML based CSI;

[0360] - AI / ML based BM;

[0361] - AI / ML based mobility;

[0362] - AI / ML based data transmission.

[0363] As one sub-embodying of the embodiment, at least one of the third characteristic combination is set to true indicates that the resource set corresponding to the third characteristic combination is valid when the first node supports any of the at least one characteristic.

[0364] As one sub-embodying of the embodiment, at least one of the third characteristic combination is set to true indicates that the resource set corresponding to the third characteristic combination can be used for random access when the first node supports any of the at least one characteristic.

[0365] As one sub-embodying of the embodiment, at least one of the third characteristic combination is set to true indicates that the resource set corresponding to the third characteristic combination is valid when the first node is triggered for random access based on any of the at least one characteristic.

[0366] As one embodiment, the plurality of characteristic combinations comprises a fourth characteristic combination, the fourth characteristic combination comprises one or more of the following characteristics:

[0367] - AI / ML model for PHY;

[0368] - AI / ML model for MAC;

[0369] - AI / ML model for RRC;

[0370] - AI / ML model for sensing.

[0371] As one sub-embodying of the embodiment, at least one of the fourth characteristic combination is set to true indicates that the resource set corresponding to the fourth characteristic combination is valid when the first node supports any of the at least one characteristic.

[0372] As one sub-embodying of the embodiment, at least one of the fourth characteristic combination is set to true indicates that the resource set corresponding to the fourth characteristic combination can be used for random access when the first node supports any of the at least one characteristic.

[0373] As one sub-embodying of the embodiment, at least one of the fourth characteristic combination is set to true indicates that the resource set corresponding to the fourth characteristic combination is valid when the first node is triggered for random access based on any of the at least one characteristic.

[0374] As one embodiment, the plurality of characteristic combinations comprises a fifth characteristic combination, the fifth characteristic combination comprises one or more of the following characteristics:

[0375] - AI / ML model for energy saving;

[0376] - AI / ML model for NS;

[0377] - AI / ML model for ISAC.

[0378] As one sub embodiment of the embodiment, at least one feature in the fifth feature combination being set to true indicates that the resource set corresponding to the fifth feature combination is valid when the first node supports any of the at least one feature.

[0379] As one sub embodiment of the embodiment, at least one feature in the fifth feature combination being set to true indicates that the resource set corresponding to the fifth feature combination can be used for random access when the first node supports any of the at least one feature.

[0380] As one sub embodiment of the embodiment, at least one feature in the fifth feature combination being set to true indicates that the resource set corresponding to the fifth feature combination is valid when the first node is triggered for random access based on any of the at least one feature.

[0381] As one embodiment, the plurality of feature combinations comprises a sixth feature combination, the sixth feature combination comprises one of the following features:

[0382] - support 1 AI / ML model;

[0383] - support 2 AI / ML models;

[0384] - support K1 AI / ML models, the K1 is a positive integer greater than 2.

[0385] As one sub embodiment of the embodiment, at least one feature in the sixth feature combination being set to true indicates that the resource set corresponding to the sixth feature combination is valid when the first node supports any of the at least one feature.

[0386] As one sub embodiment of the embodiment, at least one feature in the sixth feature combination being set to true indicates that the resource set corresponding to the sixth feature combination can be used for random access when the first node supports any of the at least one feature.

[0387] As one sub embodiment of the embodiment, at least one feature in the sixth feature combination being set to true indicates that the resource set corresponding to the sixth feature combination is valid when the first node is triggered for random access based on any of the at least one feature.

[0388] As an embodiment, the described at…, the described when… and the described if in this application mean that the device will make corresponding processing under certain objective conditions, which is not limited to time, and does not require the device to have a judgment action when it is implemented, nor means that there are other limitations.

[0389] As an embodiment, the described including in this application means non-exclusive containing, which is not limited to the listed entities, steps or units; optionally, it also includes other entities, steps or units not listed, or optionally, it also includes other entities, steps or units inherent to the implementation of this application.

[0390] As an embodiment, the first resource block includes at least one of time domain resources, frequency domain resources or sequence resources.

[0391] As an embodiment, the first resource block includes time domain resources.

[0392] As a sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the plurality of resource sets, the first resource set includes a plurality of time domain resource blocks, and the first resource block is one of the plurality of time domain resource blocks.

[0393] As an embodiment, the first resource block includes frequency domain resources.

[0394] As a sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the plurality of resource sets, the first resource set includes a plurality of frequency domain resource blocks, and the first resource block is one of the plurality of frequency domain resource blocks.

[0395] As an embodiment, the first resource block includes time domain resources and frequency domain resources.

[0396] As a sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the plurality of resource sets, the first resource set includes a plurality of time-frequency resource blocks, and the first resource block is one of the plurality of time-frequency resource blocks.

[0397] As an embodiment, the first resource block includes sequence resources.

[0398] As a sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the plurality of resource sets, the first resource set includes a plurality of sequence resources, and the first resource block occupies one of the plurality of sequence resources.

[0399] As an embodiment, the first resource block includes time domain resources, frequency domain resources and sequence resources.

[0400] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprises multiple time-frequency resource blocks, the multiple time-frequency resource blocks respectively correspond to at least one sequence resource, the first resource block occupies a given time-frequency resource block of the multiple time-frequency resource blocks, and the first resource block occupies one of the at least one sequence resource corresponding to the given resource block.

[0401] Embodiment 2

[0402] Embodiment 2 illustrates a schematic diagram of a network architecture according to one embodiment of the present application, as shown in FIG. 2.

[0403] FIG. 2 illustrates a network architecture 200. The network architecture 200 is a network architecture for LTE (Long-Term Evolution), LTE-A (Long-Term Evolution Advanced), 5G systems, 5G-Advanced, and future 6G systems. The network architecture for LTE, LTE-A, 5G systems, 5G-Advanced, and future 6G systems is referred to as EPS (Evolved Packet System). The 5G NR or LTE network architecture can be referred to as 5GS (5G System) / EPS or some other suitable terminology; the 6G network architecture can be referred to as 6GS (6G System) / EPS or some other suitable terminology. The network architecture 200 can include one or more UEs 201, a RAN (Next Generation Radio Access Network) 202, a core network 210, a HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet services 230. The network architecture 200 can be interconnected with other access networks, but these entities / interfaces are not shown for simplicity. As shown in FIG. 2, the network architecture 200 provides packet-switched services, however, those skilled in the art will readily appreciate that the various concepts presented throughout this application are amenable to use with networked systems providing circuit-switched services. The RAN 202 includes Node Bs 203 and other nodes 204. The Node Bs 203 provide user and control plane protocol terminations toward the UEs 201. The Node Bs 203 can be connected to the other nodes 204 via an Xn interface (e.g., backhaul). The Node Bs 203 can also be referred to as base stations, base transceiver stations, radio base stations, radio transceivers, transceiver functions, basic service sets (BSSs), extended service sets (ESSs), TRPs (Transmitter Receiver Points), or some other suitable terminology. The Node Bs 203 provide access points to the core network 210 for the UEs 201; the core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or alternatively, the core network 210 is a 6GC.Examples of a UE 201 include a cellular phone, a smart phone, a Session Initiation Protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., MP3 player), a camera, a game console, a drone, a flying vehicle, a narrowband physical web device, a machine type communication device, a land transport vehicle, a car, a wearable device, or any other similar functional device. Those skilled in the art will also The node 203 is connected by an SI / NG interface to the core network 210. The core network 210 includes a MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MME / AMF / SMF 214, a S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that processes the signaling between the UE 201 and the 5G-CN / EPC 210. The MME / AMF / SMF 211 generally provides bearer and connection management. All user Internet Protocol (IP) packets are transferred through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation as well as other functions. The P-GW / UPF 213 is connected to the Internet services 230. The Internet services 230 include operator- correspondent Internet Protocol services, which can specifically include the Internet, intranet, IMS (IP Multimedia Subsystem), and packet-switched services.

[0404] As one embodiment, the first node described in this application comprises the UE 201.

[0405] As one embodiment, the second node described in the present application comprises the node 203.

[0406] As one embodiment, the node 203 is a macro cell base station.

[0407] As one embodiment, the node 203 is a micro cell base station.

[0408] As one embodiment, the node 203 is a pico cell base station.

[0409] As one embodiment, the node 203 is a femto cell.

[0410] As one embodiment, the node 203 is a base station device supporting large latency difference.

[0411] As one embodiment, the node 203 is a flying platform device.

[0412] As one embodiment, the node 203 is a satellite device.

[0413] As one embodiment, the node 203 is a test device (e.g. a transceiver simulating part of the functions of a base station, a signaling tester).

[0414] As one embodiment, the UE 201 comprises a mobile phone.

[0415] As one embodiment, the UE 201 comprises a vehicle, including a car.

[0416] As one embodiment, the wireless link from the UE 201 to the node 203 is an uplink, which is used to perform uplink transmission.

[0417] As one embodiment, the wireless link from the node 203 to the UE 201 is a downlink, which is used to perform downlink transmission.

[0418] As one embodiment, the wireless link between the node 203 and the UE 201 comprises a cellular network link.

[0419] As one embodiment, the node 203 and the UE 201 are connected through a Uu air interface.

[0420] As one embodiment, the sender of the first information block described in the present application comprises the node 203.

[0421] As one embodiment, the receiver of the first information block in the present application comprises the UE 201.

[0422] As one embodiment, the transmitter of the first signal in the present application comprises the UE 201.

[0423] As one embodiment, the receiver of the first signal in the present application comprises the node 203.

[0424] As one embodiment, the transmitter of the second signal in the present application comprises the UE 201.

[0425] As one embodiment, the receiver of the second signal in the present application comprises the node 203.

[0426] As one embodiment, the node 203 supports deployment of a network-side (NW-side) AI / ML model.

[0427] As one embodiment, the UE 201 supports deployment of a UE-side AI / ML model.

[0428] As one embodiment, the node 203 supports AI / ML-based coverage enhancement.

[0429] As one embodiment, the UE 201 supports AI / ML-based coverage enhancement.

[0430] As one embodiment, the node 203 supports AI / ML-based RA (Random Access).

[0431] As one embodiment, the UE 201 supports AI / ML-based RA.

[0432] As one embodiment, the UE 201 supports a 5G system.

[0433] As one embodiment, the node 203 supports a 5G system.

[0434] As one embodiment, the UE 201 supports at least a 6G system.

[0435] As one embodiment, the node 203 supports at least a 6G system.

[0436] Embodiment 3

[0437] Embodiment 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture of a user plane and a control plane according to one embodiment of the present application, as shown in FIG. 3.

[0438] Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300, Figure 3 shows the radio protocol architecture for the control plane 300 between a first communication node device (UE or RSU (Road Side Unit) in V2X (Vehicle to Everything), a vehicle mounted device or a vehicle mounted communication module) and a second node device (gNB, UE or RSU in V2X, a vehicle mounted device or a vehicle mounted communication module), or between two UEs, using three layers: Layer 1 (L1), Layer 2 (L2) and Layer 3 (L3). L1 is the lowest layer and implements various PHY (PHYsical layer) signal processing functions. L1 will be referred to as the PHY 301 in this document. Layer 2 305 is above the PHY 301 and is responsible for the link between the first node device and the second node device, or between two UEs, through the PHY 301. Layer 2 305 includes a MAC (Medium Access Control) sublayer 302, a RLC (Radio Link Control) sublayer 303 and a PDCP (Packet Data Convergence Protocol) sublayer 304, which are terminated at the second node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. The PDCP sublayer 304 also provides security, by encrypting packets, and handover support for the first communication node device between second communication node devices. The RLC sublayer 303 provides segmentation and reassembly of upper layer packets, retransmission of lost packets, and reordering of packets to compensate for out-of-order reception due to HARQ (Hybrid Automatic Repeat reQuest). The MAC sublayer 302 provides multiplexing between logical and transport channels. The MAC sublayer 302 is also responsible for allocating the various radio resources (e.g., resource blocks) in one cell among the UEs. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in Layer 3 in the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second communication node device and the first communication node device.The radio protocol architecture of the user plane 350 includes Layer 1 (L1) and Layer 2 (L2), which are substantially the same as the corresponding layers and sublayers in the control plane 300 for the first communication node device and the second communication node device for the physical layer 351, the PDCP sublayer 354 in L2 355, the RLC sublayer 353 in L2 355, and the MAC sublayer 352 in L2 355, but the PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead. Also included in L2 355 in the user plane 350 is the SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between QoS (Quality of Service) flows and data radio bearers (DRBs) to support diverse traffic types. Although not illustrated, the first communication node device can have several upper layers above L2 355, including a network layer (e.g., IP (Internet Protocol) layer) that terminates at the P-GW on the network side and an application layer that terminates at the other end of the connection (e.g., a remote UE, a server, etc.).

[0439] As one embodiment, the radio protocol architecture in FIG. 3 is applicable to the first node in the present application.

[0440] As one embodiment, the radio protocol architecture in FIG. 3 is applicable to the second node in the present application.

[0441] As one embodiment, the first information block in the present application is generated at the RRC 306.

[0442] As one embodiment, the first signal in the present application is generated at the PHY 301 or the PHY 351.

[0443] As one embodiment, the second signal in the present application is generated at the MAC sublayer 302 or the MAC sublayer 352.

[0444] As one embodiment, the second signal in the present application is generated at the PHY 301 or the PHY 351.

[0445] As one embodiment, the higher layer in the present application refers to a layer above the physical layer.

[0446] As one embodiment, the higher layer in the present application includes the RRC layer.

[0447] As one embodiment, the higher layer signaling in the present application includes the RRC IE.

[0448] As one embodiment, the higher layer signaling described in the present application comprises RRC messages.

[0449] As one embodiment, the higher layer described in the present application comprises a MAC layer.

[0450] As one embodiment, the higher layer signaling described in the present application comprises a MAC CE.

[0451] Embodiment 4

[0452] Embodiment 4 illustrates a schematic diagram of a first communication device and a second communication device according to one embodiment of the present application, as shown in FIG. 4. FIG. 4 is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0453] The first communication device 410 comprises a controller / processor 475, a memory 476, a receive processor 470, a transmit processor 416, a multi-antenna receive processor 472, a multi-antenna transmit processor 471, a transmitter / receiver 418, and an antenna 420.

[0454] The second communication device 450 comprises a controller / processor 459, a memory 460, a data source 467, a transmit processor 468, a receive processor 456, a multi-antenna transmit processor 457, a multi-antenna receive processor 458, a transmitter / receiver 454, and an antenna 452.

[0455] In transmissions from the first communication device 410 to the second communication device 450, at the first communication device 410, upper layer packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements functionality of L2. In DL, the controller / processor 475 provides header compression, ciphering, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocations for second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the second communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for Ll (i.e., physical layer). The transmit processor 416 implements coding and interleaving to facilitate forward error correction (FEC) at the second communication device 450 and mapping onto signal constellations based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-ary phase shift keying (M-PSK), M-ary quadrature amplitude modulation (M-QAM)). The multi-antenna transmit processor 471 performs digital spatial pre-coding of the coded and modulated symbols, including codebook-based and non-codebook-based pre-coding and beamforming processing, to generate one or more parallel streams. The transmit processor 416 then maps to each of the parallel streams to subcarriers, multiplexes the modulated symbols in time domain and / or frequency domain with reference signals (e.g., pilot) and then performs an inverse fast Fourier transform (IFFT) to generate time domain multicarrier symbol streams. The multi-antenna transmit processor 471 then performs transmit analog pre-coding / beamforming operations on the time domain multicarrier symbol streams. Each transmitter 418 converts the baseband multicarrier symbol streams provided by the multi-antenna transmit processor 471 into radio frequency signals that are transmitted via the corresponding antennas 420.

[0456] In transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its respective antenna 452. Each receiver 454 recovers information modulated onto an RF carrier and converts the RF stream into a baseband, multicarrier symbol stream to receive processor 456. The receive processor 456 and the multi-antenna receive processor 458 implement various signal processing functions of the LI. The multi-antenna receive processor 458 performs receive analog precoding / beamforming operation on the baseband, multicarrier symbol stream from the receivers 454. The receive processor 456 converts the baseband, multicarrier symbol stream from the receive analog precoding / beamforming operation from the time domain to the frequency domain using a Fast Fourier Transform (FFT). In the frequency domain, the physical layer data signals and the reference signals are demultiplexed by the receive processor 456, where the reference signals will be used for channel estimation, and the data signals are recovered after multi-antenna detection in the multi-antenna receive processor 458 for any parallel streams destined to the second communication device 450. The symbols on each parallel stream are demodulated and recovered in the receive processor 456 and generate soft decisions. The receive processor 456 then decodes and de-interleaves the soft decisions to recover the upper layer data and control signals transmitted by the first communication device 410 on the physical channels. The upper layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of the L2. The controller / processor 459 can be associated with a memory 460 that stores program codes and data. The memory 460 can be referred to as a computer-readable medium. In the DL, the controller / processor 459 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer data packets from the core network. The upper layer data packets are then provided to all protocol layers above the L2. Various control signals can also be provided to the L3 for L3 processing. The controller / processor 459 is also responsible for error detection using an ACK and / or negative ACK (NACK) protocol to support HARQ operations.

[0457] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper layer packets to a controller / processor 459. The data source 467 represents all protocol layers above L2. Similar to the transmit function described at the first communication device 410 in the DL, the controller / processor 459 implements header compression, ciphering, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocations for the first communication device 410, implements L2 layer functionality for the user plane and control plane. The controller / processor 459 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the first communication device 410. A transmit processor 468, in conjunction with a multi-antenna transmit processor 457, performs modulation mapping, channel coding processing, digital multi-antenna spatial pre-coding including codebook-based and non-codebook-based precoding, and beamforming processing, and then the transmit processor 468 generates parallel streams of symbols that are modulated onto different carriers, and the modulated symbol streams are then provided to different antennas 452 via transmitters 454 after analog pre-coding / beamforming operations in the multi-antenna transmit processor 457. Each transmitter 454 converts a baseband symbol stream into a radio frequency signal that is transmitted via the corresponding antenna 452.

[0458] In the transmission from the second communication device 450 to the first communication device 410, the functionality at the first communication device 410 is similar to the functionality described in connection with the reception at the second communication device 450 in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives a radio frequency signal through its respective antenna 420, converts the received radio frequency signal into a baseband signal, and provides the baseband signal to a multi-antenna receive processor 472 and a receive processor 470. The receive processor 470 and the multi-antenna receive processor 472 together implement L1 functionality. A controller / processor 475 implements L2 functionality. The controller / processor 475 can be associated with a memory 476 that stores program codes and data. The memory 476 can be referred to as a computer-readable medium. The controller / processor 475 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer packets from the second communication device 450. Upper layer packets from the controller / processor 475 can be provided to a core network. The controller / processor 475 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.

[0459] As one embodiment, the second communication device 450 comprises: at least one processor and at least one memory including a computer program code; the at least one memory and the computer program code are configured to, with the at least one processor, cause the second communication device 450 to perform at least: receive the first information block as defined in the present application; transmit the first signal as defined in the present application in the first resource block as defined in the present application, the first resource block belonging to one of the plurality of resource sets; the first signal carrying a random access preamble, the transmission of the first signal being contention-based; the plurality of resource sets being respectively for a plurality of property combinations, at least one of the plurality of property combinations comprising at least one property for AI / ML; the first resource block comprising at least one of a time domain resource, a frequency domain resource, or a sequence resource.

[0460] As one embodiment, the second communication device 450 comprises: a memory storing a computer readable program of instructions which, when executed by at least one processor, causes performance of actions comprising: receiving the first information block as defined in the present application; transmitting the first signal as defined in the present application in the first resource block as defined in the present application.

[0461] As one embodiment, the first communication device 410 comprises: at least one processor and at least one memory including a computer program code; the at least one memory and the computer program code are configured to, with the at least one processor, cause the first communication device 410 to perform at least: transmit the first information block as defined in the present application; receive the first signal as defined in the present application in the first resource block as defined in the present application, the first resource block belonging to one of the plurality of resource sets; the first signal carrying a random access preamble, the transmission of the first signal being contention-based; the plurality of resource sets being respectively for a plurality of property combinations, at least one of the plurality of property combinations comprising at least one property for AI / ML; the first resource block comprising at least one of a time domain resource, a frequency domain resource, or a sequence resource.

[0462] As one embodiment, the first communication device 410 comprises: a memory storing a computer readable program of instructions which, when executed by at least one processor, causes performance of actions comprising: transmitting the first information block as defined in the present application; receiving the first signal as defined in the present application in the first resource block as defined in the present application.

[0463] As one embodiment, the first node as defined in the present application comprises the second communication device 450.

[0464] As an embodiment, the second node described in the present application comprises the first communication device 410.

[0465] As an embodiment, at least one of {the antenna 420, the transmitter 418, the transmission processor 416, the multi-antenna transmission processor 471, the controller / processor 475, the memory 476} is used to send the first information block described in the present application; at least one of {the antenna 452, the receiver 454, the reception processor 456, the multi-antenna reception processor 458, the controller / processor 459, the memory 460, the data source 467} is used to receive the first information block described in the present application.

[0466] As an embodiment, at least one of {the antenna 452, the transmitter 454, the transmission processor 468, the multi-antenna transmission processor 457, the controller / processor 459, the memory 460, the data source 467} is used to send the first signal described in the present application in the first resource block; at least one of {the antenna 420, the receiver 418, the reception processor 470, the multi-antenna reception processor 472, the controller / processor 475, the memory 476} is used to receive the first signal described in the present application in the first resource block.

[0467] As an embodiment, at least one of {the antenna 452, the transmitter 454, the transmission processor 468, the multi-antenna transmission processor 457, the controller / processor 459, the memory 460, the data source 467} is used to send the second signal described in the present application; at least one of {the antenna 420, the receiver 418, the reception processor 470, the multi-antenna reception processor 472, the controller / processor 475, the memory 476} is used to receive the second signal described in the present application.

[0468] Embodiment 5

[0469] Embodiment 5 illustrates a flowchart of the transmission between the first node and the second node according to an embodiment of the present application, as shown in FIG. 5. In FIG. 5, the first node U1 communicates with the second node N2 through a wireless link, and the steps in block 51 are optional. It is particularly pointed out that the order in this embodiment does not limit the order of signal transmission and implementation in the present application.

[0470] For the first node U1, the first information block is received in step S510; the first signal is sent in the first resource block in step S511; and the second signal is sent in step S5110.

[0471] For the second node N2, the first information block is transmitted in step S520; the first signal is received in the first resource block in step S520; the second signal is received in step S5210.

[0472] In embodiment 5, the first information block indicates a plurality of resource sets; the first resource block belongs to one of the plurality of resource sets; the first signal carries a random access preamble, transmission of the first signal is contention-based; the plurality of resource sets are respectively for a plurality of characteristic combinations, at least one of the plurality of characteristic combinations includes at least one AI / ML-related characteristic; the first resource block includes at least one of time domain resources, frequency domain resources, or sequence resources.

[0473] As an embodiment, the first node U1 is the first node in the present application.

[0474] As an embodiment, the second node N2 is the second node in the present application.

[0475] As an embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between a base station device and a user equipment.

[0476] As an embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between a relay node device and a user equipment.

[0477] As an embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between a user equipment and a user equipment.

[0478] As an embodiment, the second node N2 and the first node U1 communicate through a Uu interface.

[0479] As an embodiment, the second node N2 is a serving cell maintenance base station of the first node U1.

[0480] As an embodiment, the logical channel occupied by the first information block includes a BCCH (Broadcast CHannel).

[0481] As an embodiment, the transport channel occupied by the first information block includes a DL-SCH (DownLink-Shared CHannel).

[0482] As an embodiment, the physical layer channel occupied by the first information block includes a PBCH (Physical Broadcast CHannel).

[0483] As an embodiment, the physical layer channel occupied by the first information block comprises a PDSCH (Physical Downlink Shared CHannel).

[0484] As an embodiment, the step S510 is before the step S511; the step S520 is before the step S521.

[0485] As an embodiment, the step in the block 51 in the figure 5 exists; the method applied to the first node in the application comprises: sending a second signal; the second signal is for random access; one AI / ML-related characteristic included in the plurality of characteristic combinations is determining that the first node supports AI / ML capability; the second signal indicates AI / ML information of the first node, and the AI / ML information of the first node comprises at least one of the following:

[0486] - an ID of an AI / ML model supported by the first node;

[0487] - a Functionality corresponding to an AI / ML model supported by the first node;

[0488] - a training data set supported by the first node;

[0489] - an Associated ID supported by the first node;

[0490] - a Category for AI / ML corresponding to the first node.

[0491] As an embodiment, the ID refers to IDentify, proof.

[0492] As an embodiment, the ID refers to IDentification, identity.

[0493] As an embodiment, the ID refers to IDentity, identity or identification.

[0494] As an embodiment, the ID refers to IDentifier, identifier.

[0495] As an embodiment, the ID refers to InDex, index.

[0496] As an embodiment, the first node receives scheduling signaling sent by the second node before sending the second signal.

[0497] As one embodiment, the first node receives a RAR (Random Access Response) UL grant sent by the second node before sending the second signal.

[0498] As one embodiment, the second signal is associated to a UE Contention Resolution Identity.

[0499] As one embodiment, the second signal comprises a Msg3.

[0500] As one embodiment, the first signal is a Msg1 and the second signal is a Msg3.

[0501] As one embodiment, the first node does not receive scheduling signaling sent by the second node before sending the second signal.

[0502] As one embodiment, the second signal comprises a PUSCH (Physical Uplink Shared CHannel) of a MsgA.

[0503] As one embodiment, the first signal is a PRACH in a MsgA and the second signal is a PUSCH in the MsgA.

[0504] As one embodiment, the second signal comprises at least one MAC subPDU (sub Protocol Data Unit) and one MAC subhead in one MAC subPDU.

[0505] As one embodiment, the second signal comprises a MAC CE (Control Element).

[0506] As one embodiment, the second signal comprises a UE Contention Resolution Identity MAC CE.

[0507] As one embodiment, the second signal comprises one of a C (Cell)-RNTI (Radio Network Temporary Identifier) MAC CE or a CCCH (Common Control Channel) SDU (Service Data Unit).

[0508] As one embodiment, the second signal includes at least one C-RNTI MAC CE.

[0509] As one embodiment, the second signal includes a C-RNTI MAC CE.

[0510] As one embodiment, the second signal includes at least one C-RNTI MAC CE.

[0511] As one embodiment, the second signal includes one C-RNTI MAC CE and a MAC subheader corresponding to the one C-RNTI MAC CE.

[0512] As one embodiment, the second signal includes a CCCH SDU.

[0513] As one embodiment, the second signal includes at least one CCCH SDU.

[0514] As one embodiment, the second signal includes one CCCH SDU and a MAC subheader corresponding to the one CCCH SDU.

[0515] As one embodiment, the second signal indicates an ID of an AI / ML model supported by the first node.

[0516] As one embodiment, the second signal indicates a Functionality corresponding to an AI / ML model supported by the first node.

[0517] As one embodiment, the second signal indicates a Functionality ID corresponding to an AI / ML model supported by the first node.

[0518] As one embodiment, the second signal indicates a Functionality Group (FG) corresponding to an AI / ML model supported by the first node.

[0519] As one embodiment, the second signal indicates an ID of an AI / ML model supported by the first node and a Functionality corresponding to an AI / ML model supported by the first node.

[0520] As one embodiment, the second signal indicates an ID of an AI / ML model supported by the first node and a Functionality ID corresponding to an AI / ML model supported by the first node.

[0521] As an embodiment, the second signal indicates an ID of an AI / ML model supported by the first node and a Functionality of a reference model corresponding to the AI / ML model ID.

[0522] As an embodiment, the second signal indicates an ID of an AI / ML model supported by the first node and a Functionality ID of a reference model corresponding to the AI / ML model ID.

[0523] As an embodiment, the second signal indicates a training data set supported by the first node.

[0524] As an embodiment, the second signal indicates a training data set ID supported by the first node.

[0525] As an embodiment, the second signal indicates a type of a training data set supported by the first node.

[0526] As an embodiment, the second signal indicates a reporting manner of a training data set supported by the first node.

[0527] As an embodiment, the second signal indicates whether the first node supports pre-processing of a training data set.

[0528] As an embodiment, the second signal indicates an Associated ID supported by the first node.

[0529] As an embodiment, the second signal indicates a training data set associated with an Associated ID supported by the first node.

[0530] As an embodiment, the second signal indicates an Associated ID and an ID of an AI / ML model supported by the first node.

[0531] As an embodiment, the second signal indicates an ID of an AI / ML model supported by the first node and an Associated ID associated with the ID of the AI / ML model.

[0532] As an embodiment, the second signal indicates a training data set supported by the first node and an Associated ID associated with the training data set.

[0533] As an embodiment, the second signal indicates an identification manner of an AI / ML model supported by the first node and a training data set.

[0534] As one embodiment, the second signal indicates a Category for AI / ML corresponding to the first node.

[0535] As one embodiment, the second signal indicates a type of AI / ML model supported by the first node.

[0536] As one sub-embodiment of this embodiment, the type of AI / ML model includes an architecture of the AI / ML model.

[0537] As one sub-embodiment of this embodiment, the type of AI / ML model includes at least one of a UE-side AI / ML model, a network-side model, and a dual-side model.

[0538] As one embodiment, the second signal indicates a model identification type of an AI / ML model supported by the first node.

[0539] As one sub-embodiment of this embodiment, the model identification type includes at least one of a model identification Type A and a model identification Type B.

[0540] As one sub-embodiment of this embodiment, the model identification type includes at least one of a model identification Type A and a model identification Type B.

[0541] As one sub-embodiment of this embodiment, the model identification type includes at least one of a model identification Type A, a model identification Type B1, and a model identification Type B2.

[0542] As one sub-embodiment of this embodiment, the model identification type includes at least one of a model identification based on radio signaling and a model identification not based on radio signaling.

[0543] As one sub-embodiment of this embodiment, the model identification type includes at least one of a model identification initiated by a terminal and a model identification initiated by a base station.

[0544] As one embodiment, the transmission channel occupied by the second signal comprises an UL-SCH (UpLink-Shared CHannel).

[0545] As one embodiment, the physical layer channel occupied by the second signal comprises a PUSCH.

[0546] As one embodiment, the steps in the block 51 in FIG. 5 exist; the step S511 is before the step S5110; the step S521 is before the step S5210.

[0547] As one embodiment, the steps in the block 51 in FIG. 5 exist; the step S511 comprises the step S5110; the step S521 comprises the step S5210.

[0548] As one embodiment, the steps in the block 51 in FIG. 5 exist; the operation of the step S511 and the step S5110 is in the same time slot; the operation of the step S521 and the step S5210 is in the same time slot.

[0549] Embodiment 6

[0550] Embodiment 6 illustrates a schematic diagram of a plurality of time domain resource sets according to one embodiment of the present application, as shown in FIG. 6. In FIG. 6, the rectangle with thick line box represents the time domain resources occupied by the plurality of time domain resource sets, wherein the rectangle with cross diamond filling represents the time domain resources occupied by the first time domain resource set in the plurality of time domain resource sets; it is worth noting that FIG. 6 is only illustrative, and the present application does not limit the proportion and position relationship of the time domain resources included in the plurality of time domain resource sets and the time domain resources included in the first time domain resource set in the time domain.

[0551] In embodiment 6, the time domain resources occupied by the first resource block belong to the first time domain resource set, and the first node supports AI / ML capability; the time domain resources occupied by the first resource block do not belong to the first time domain resource set, and the first node does not support AI / ML capability.

[0552] As one embodiment, the plurality of time domain resource sets occupy discontinuous time domain resources.

[0553] As one embodiment, the first time domain resource set occupies discontinuous time domain resources.

[0554] As one embodiment, the first time domain resource set belongs to the plurality of time domain resource sets.

[0555] As an embodiment, the fact that the time domain resource occupied by the first resource block belongs to the first time domain resource set means that the first time domain resource set includes the time domain resource occupied by the first resource block.

[0556] As an embodiment, the fact that the time domain resource occupied by the first resource block belongs to the first time domain resource set means that the first time domain resource set includes the time domain resource occupied by the first resource block.

[0557] As an embodiment, the fact that the time domain resource occupied by the first resource block belongs to the first time domain resource set means that the first time domain resource set includes the time domain resource occupied by the first resource block.

[0558] As an embodiment, the fact that the time domain resource occupied by the first resource block belongs to the first time domain resource set means that the first time domain resource set includes the time domain resource occupied by the first resource block.

[0559] As an embodiment, the fact that the time domain resource occupied by the first resource block belongs to the first time domain resource set means that the first time domain resource set includes the time domain resource occupied by the first resource block.

[0560] Embodiment 7

[0561] Embodiment 7 illustrates a schematic diagram of a plurality of frequency domain resource sets according to an embodiment of the present application, as shown in FIG. 7. In FIG. 7, the rectangle with a thick line frame represents the frequency domain resource occupied by the plurality of frequency domain resource sets, wherein the rectangle filled with gray pure color represents the frequency domain resource occupied by the first frequency domain resource set in the plurality of frequency domain resource sets; it is worth noting that FIG. 7 is only illustrative, and the present application does not limit the frequency domain resource included in the plurality of frequency domain resource sets and the proportion and location relationship in the frequency domain of the frequency domain resource included in the first frequency domain resource set.

[0562] In embodiment 7, the frequency domain resource occupied by the first resource block belongs to the first frequency domain resource set, and the first node supports AI / ML capability; the frequency domain resource occupied by the first resource block does not belong to the first frequency domain resource set, and the first node does not support AI / ML capability.

[0563] As an embodiment, the plurality of frequency domain resource sets occupy discontinuous frequency domain resources.

[0564] As an embodiment, the plurality of frequency domain resource sets occupy continuous frequency domain resources.

[0565] As an embodiment, any of the multiple frequency domain resource sets occupies contiguous frequency domain resources in a time instance.

[0566] As an embodiment, the multiple frequency domain resource sets occupy non-contiguous frequency domain resources in a time instance.

[0567] As an embodiment, the multiple frequency domain resource sets occupy nested frequency domain resources.

[0568] As an embodiment, the multiple frequency domain resource sets occupy nested frequency domain resources in a time instance.

[0569] As an embodiment, the first frequency domain resource set occupies contiguous frequency domain resources in a time instance.

[0570] As an embodiment, the first frequency domain resource set belongs to the multiple frequency domain resource sets.

[0571] As an embodiment, the first resource block occupying frequency domain resources belonging to the first frequency domain resource set means that the first frequency domain resource set includes the frequency domain resources occupied by the first resource block.

[0572] As an embodiment, the first resource block occupying frequency domain resources belonging to the first frequency domain resource set means that the first frequency domain resource set includes frequency domain resources other than the frequency domain resources occupied by the first resource block.

[0573] As an embodiment, the first resource block occupying frequency domain resources belonging to the first frequency domain resource set means that the first frequency domain resource set does not include frequency domain resources other than the frequency domain resources occupied by the first resource block.

[0574] As an embodiment, the first resource block occupying frequency domain resources not belonging to the first frequency domain resource set means that the frequency domain resources occupied by the first resource block belong to a second frequency domain resource set, and the second frequency domain resource set and the first frequency domain resource set are orthogonal in frequency domain.

[0575] As an embodiment, the first resource block occupying frequency domain resources not belonging to the first frequency domain resource set means that the first frequency domain resource set is orthogonal to the frequency domain resources occupied by the first resource block.

[0576] As an embodiment, the first resource block occupying frequency domain resources not belonging to the first frequency domain resource set means that the first frequency domain resource set is orthogonal to the frequency domain resources occupied by the first resource block in a time instance.

[0577] As an embodiment, the meaning that the frequency domain resource occupied by the first resource block does not belong to the first frequency domain resource set includes that the first frequency domain resource set includes a plurality of resource blocks, and the plurality of resource blocks does not include the first resource block.

[0578] As a sub-embodiment of the embodiment, at least one resource block in the plurality of resource blocks is orthogonal to the first resource.

[0579] As a sub-embodiment of the embodiment, at least one resource block in the plurality of resource blocks includes the frequency domain resource of the first resource block.

[0580] As a sub-embodiment of the embodiment, at least one resource block in the plurality of resource blocks belongs to the first resource block.

[0581] As a sub-embodiment of the embodiment, the frequency domain resource included in any resource block in the plurality of resource blocks does not overlap with the first resource block in a time instance.

[0582] As a sub-embodiment of the embodiment, the frequency domain resource included in any resource block in the plurality of resource blocks is orthogonal to the first resource block in a time instance.

[0583] As an embodiment, the meaning that the frequency domain resource occupied by the first resource block does not belong to the first frequency domain resource set includes that the first resource block occupies the frequency domain resource in the plurality of frequency domain resource sets except the first frequency domain resource set.

[0584] As an embodiment, the time instance in the present application refers to one or more multicarrier symbols.

[0585] As an embodiment, the time instance in the present application refers to the time domain resource occupied by one RO.

[0586] Embodiment 8

[0587] Embodiment 8 illustrates a schematic diagram of a plurality of sequence resource sets according to an embodiment of the present application, as shown in FIG. 8. In FIG. 8, the rectangle with a thick line box represents the sequence domain resource occupied by the plurality of sequence resource sets, wherein the rectangle filled with a cross indicates the sequence resource occupied by the first sequence resource set in the plurality of sequence resource sets. It is worth noting that FIG. 8 is only illustrative, and the present application does not limit the number of sequence resources included in the plurality of sequence resource sets and the first sequence resource set, nor the ratio of the two.

[0588] In Embodiment 8, the sequence resource occupied by the first resource block belongs to a first sequence resource set, and the first node supports an AI / ML capability; the sequence resource occupied by the first resource block does not belong to the first sequence resource set, and the first node does not support the AI / ML capability.

[0589] As an embodiment, the multiple sequence resource sets are generated from a same root sequence.

[0590] As an embodiment, the multiple sequence resource sets are not generated from a same root sequence.

[0591] As an embodiment, a length of any sequence in the multiple sequence resource sets is the same.

[0592] As an embodiment, sequence resources in the multiple sequence resource sets correspond to different time-frequency resources.

[0593] As an embodiment, any sequence resource set in the multiple sequence resource sets corresponds to at least one SS (Synchronization Signal) / PBCH block.

[0594] As an embodiment, the first sequence resource set includes multiple sequences.

[0595] As an embodiment, the first sequence resource set includes one sequence.

[0596] As an embodiment, the fact that the sequence resource occupied by the first resource block belongs to the first sequence resource set includes that the first sequence resource set includes the sequence resource occupied by the first resource block.

[0597] As an embodiment, the fact that the sequence resource occupied by the first resource block belongs to the first sequence resource set includes that the first sequence resource set includes sequence resources other than the sequence resource occupied by the first resource block.

[0598] As an embodiment, the fact that the sequence resource occupied by the first resource block belongs to the first sequence resource set includes that the first sequence resource set does not include sequence resources other than the sequence resource occupied by the first resource block.

[0599] As an embodiment, the fact that the sequence resource occupied by the first resource block does not belong to the first sequence resource set includes that the sequence resource occupied by the first resource block belongs to a second sequence resource set, and sequence resources included in the second sequence resource set are orthogonal to sequence resources included in the first sequence resource set.

[0600] As a sub-example of this example, any sequence resource included in the second set of sequence resources is different from any sequence resource included in the first set of sequence resources.

[0601] As one example, the first set of sequence resources being orthogonal to the sequence resource occupied by the first resource block means that the first set of sequence resources is orthogonal to the sequence resource occupied by the first resource block.

[0602] As one example, the first set of sequence resources being orthogonal to the sequence resource occupied by the first resource block means that the first set of sequence resources is orthogonal to the sequence resource occupied by the first resource block.

[0603] As one example, the first set of sequence resources being orthogonal to the sequence resource occupied by the first resource block means that the first set of sequence resources is orthogonal to the sequence resource occupied by the first resource block.

[0604] Example 9

[0605] Example 9 illustrates a diagram of a second signal according to one embodiment of the present application, as shown in FIG. 9. In FIG. 9, the second signal includes a first field, and the first field included in the second signal indicates the AI / ML information of the first node in the present application.

[0606] In Example 9, when the first node does not support AI / ML capability, the value of the first field included in the second signal is fixed or predefined.

[0607] As one example, when the first node does not support AI / ML capability, the value of the first field included in the second signal is fixed.

[0608] As one example, the value of the first field included in the second signal being fixed means that the value of the first field included in the second signal is all 0.

[0609] As one example, the value of the first field included in the second signal being fixed means that the value of the first field included in the second signal is all 1.

[0610] As one example, the value of the first field included in the second signal being fixed means that the value of the first field included in the second signal is reserved.

[0611] As an embodiment, the value of the first field comprised by the second signal being fixed means that the value of the first field comprised by the second signal is default.

[0612] As an embodiment, the value of the first field comprised by the second signal being fixed means that the value of the first field comprised by the second signal is default.

[0613] As an embodiment, the value of the first field comprised by the second signal is predefined when the first node does not support AI / ML capability.

[0614] As an embodiment, the value of the first field comprised by the second signal being predefined means that the value of the first field comprised by the second signal is configured by higher layer signaling.

[0615] As an embodiment, the value of the first field comprised by the second signal being predefined means that the value of the first field comprised by the second signal is configured by RRC signaling.

[0616] Embodiment 10

[0617] Embodiment 10 illustrates a schematic diagram of RAN domain AI / ML function deployment according to an embodiment of the present application, as shown in FIG. 10. In FIG. 10, gNB can be replaced by eNB, or 6G base station, etc. network device.

[0618] In embodiment 10, the management of ML inference functions of multiple base stations is completed by RAN domain management function 1002, i.e. data interaction with RAN domain MnS (Management Service) consumer / cross-domain management 1001 (as shown by the dashed arrow in FIG. 10). RAN domain ML training function 1003 is located in RAN domain management function 1002; while ML inference function is located in base station, i.e. AI / ML inference function 1004 is located in gNB 1005, AI / ML inference function 1006 is located in gNB 1007, ….

[0619] AI / ML related functions include ML training function (also referred to as AI training, or AI / ML training), ML testing function, ML inference function (also referred to as AI inference, or AI / ML inference), etc. The ML training function, the ML testing function, and the ML inference function can be deployed independently, or can be co-located. The deployment of the AI / ML related functions can be implemented by software, such as the download and / or running of an executable file; or can be implemented by software in combination with hardware, such as accelerating a specific computing unit by hardware to improve the operation speed or save power consumption.

[0620] For the ML training function, it can be deployed in a cross-domain management system, or a domain-specific management system for managing a RAN domain or a CN (Core Network) domain. For example, for the ML training function of MDA (Management Data Analytics), it can be deployed in MDAF (Management Data Analytics Function); for the ML training of network data analytics, it can be deployed in NWDAF (NetWork Data Analytics Function), i.e., the ML training function is MTLF (Model Training Logical Function).

[0621] For the ML inference function, it can also be deployed in a cross-domain management system, or a domain-specific management system; for example, the ML inference function is MDAF, or the ML inference function is AnLF (Analytics Logical Function) in NWDAF.

[0622] Similarly, the ML testing function can also be deployed in a cross-domain management system, or a domain-specific management system.

[0623] Optionally, the management of the ML inference function can also be completed by the base station itself, i.e., each base station can independently interact with the RAN domain MnS consumer / cross-domain management 1001 for data interaction.

[0624] It is noted that Embodiment 10 is just one non-limiting implementation; alternatively, the ML training function of the RAN domain can also be deployed at the base station; or alternatively, some base stations deploy both the ML inference function and the ML training function of the RAN domain, while some base stations only deploy the ML inference function.

[0625] As one embodiment, one gNB (or base station) in Embodiment 10 is the second node of the present application.

[0626] Embodiment 11

[0627] Embodiment 11 illustrates a schematic diagram of AI / ML function deployment of a UE according to one embodiment of the present application, as shown in FIG. 11. In FIG. 11, the RAN domain ML training function 1104 is optional.

[0628] The UE function 1103 is deployed in the first node of the present application, and the UE function 1103 includes the AI / ML inference function 1105; the AI / ML inference function 1105 uses a ML model (also referred to as an AI model) for inference; one ML model is usually trained before being used for AI / ML inference.

[0629] As one embodiment, the UE function 1103 includes the RAN domain ML training function 1104, which runs training data through a ML model to derive a related loss, and adjusts parameters of the ML model based on the calculated loss; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0630] The above embodiments can reduce the complexity of the base station, or save the air interface resources caused by reporting training data; however, the above embodiments put higher requirements on the processing capability of the UE side.

[0631] Alternatively, the UE function 1103 also includes a CN domain ML training function (not included in FIG. 11).

[0632] Alternatively, the UE function 1103 also includes an AI / ML deployment function (not included in FIG. 11) for loading ML models and data.

[0633] As one embodiment, the first node indicates whether the ML training function (RAN domain or CN domain) is supported through capability reporting, and the capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0634] As one embodiment, the ML model, and related metadata, is loaded by the first node from a network device or a remote server.

[0635] Optionally, the UE function 1103 is a MnS producer providing data to a CN domain MnF and / or a RAN domain MnF and / or a cross-domain management system 1101 for management or analytics (as indicated by double arrow 1102).

[0636] Optionally, the UE function 1103 is a MnS consumer loading data from a CN domain MnF and / or a RAN domain MnF and / or a cross-domain management system 1101 for AI / ML related management, such as management data requests, ML model activation, and / or ML training, etc. (as indicated by double arrow 1102).

[0637] As one embodiment, the ML model is based on NN (Neural Networks).

[0638] As one embodiment, the ML model is based on ANN (Artificial Neural Networks).

[0639] As one embodiment, the ML model is based on CNN (Convolutional Neural Networks).

[0640] As one embodiment, the ML model is based on LLM (Large Language Model) architecture.

[0641] As one embodiment, the ML model is based on Transformer architecture.

[0642] As one embodiment, the ML model is based on GPT (Generative Pre-Trained).

[0643] As one embodiment, the ML model is based on LSTM (Long Short-Term Memory).

[0644] As one embodiment, the ML model is based on MLP (MultiLayer Perceptron).

[0645] As one embodiment, the ML model is based on GAN (Generative Adversarial Nets).

[0646] As one embodiment, the ML model is based on a light-weight neural network.

[0647] As one sub-embodiment of this embodiment, the light-weight neural network includes one or more of MobileNet, ShuffleNet, and SqueezeNet.

[0648] Embodiment 12

[0649] Embodiment 12 illustrates a schematic diagram of an artificial intelligence or machine learning based processing system according to one embodiment of the present application, as shown in FIG. 12. In FIG. 12, the artificial intelligence or machine learning based processing system includes a first processing machine, a second processing machine, a third processing machine, and a fourth processing machine.

[0650] In Embodiment 12, the first processing machine sends a first data set to the second processing machine, and a second data set to the third processing machine; the second processing machine generates a target first-class parameter group according to the first data set, and sends the generated target first-class parameter group to the third processing machine; the third processing machine processes the second data set using the target first-class parameter group to obtain a first-class output, and optionally, sends the first-class output to the fourth processing machine. In FIG. 12, a first-class feedback and a second-class feedback are optional; the second processing machine includes an ML training function; and the third processing machine includes an ML inference function.

[0651] As one embodiment, the fourth processing machine includes an ML testing function.

[0652] As one embodiment, the fourth processing machine includes performance monitoring / evaluation of the ML model.

[0653] As one embodiment, the third processing machine sends a first-class feedback to the second processing machine; the first-class feedback is used to trigger re-computation or update of the target first-class parameter group, i.e., trigger ML initial training or ML re-training.

[0654] As one embodiment, the fourth processing machine sends a second-class feedback to the first processing machine; the second-class feedback is used to generate the first data set or the second data set, or the second-class feedback is used to trigger sending of the first data set or sending of the second data set.

[0655] As an embodiment, the third handler belongs to the first node, and the fourth handler belongs to the second node.

[0656] As an embodiment, the third handler belongs to the first node.

[0657] As an embodiment, the first data set comprises training data.

[0658] As an embodiment, an Associated ID supported by the first node is associated to the first data set.

[0659] As an embodiment, the first data set is collected at the first node side.

[0660] As an embodiment, the first data set is collected at the second node side.

[0661] As an embodiment, the first signal indicates whether the first node supports the first handler.

[0662] As an embodiment, the first signal indicates whether the first node deploys the first handler.

[0663] As an embodiment, the first signal indicates whether the first node supports the deployment of the first handler.

[0664] As an embodiment, the first signal indicates the number of the first handlers deployed by the first node.

[0665] As an embodiment, the first signal indicates the computing power of the first handlers deployed by the first node.

[0666] As an embodiment, the first signal indicates the functions of the first handlers deployed by the first node.

[0667] As an embodiment, the second signal indicates the first data set.

[0668] As an embodiment, the second signal indicates the first data set associated by the first node.

[0669] As an embodiment, the second handler is used for training an ML model, and the trained model is described by the target first-type parameter group.

[0670] As an embodiment, the second handler belongs to the first node; the above method avoids transmitting the first data set to the second node.

[0671] As an embodiment, the second processing machine belongs to the second node in the present application; the above method supports joint training, and optimizes system performance.

[0672] As an embodiment, the second processing machine belongs to the core network; the above method supports joint training of the whole network, and further optimizes system performance.

[0673] As an embodiment, the second data set includes inference data.

[0674] As an embodiment, the third processing machine constructs a model according to the target first-type parameter group, and then inputs the second data set into the constructed model to obtain the first-type output.

[0675] As an embodiment, the third processing machine generates a recovery data set according to the first-type output, and the error of the recovery data set and the second data set is used to generate the first-type feedback.

[0676] As an embodiment, the first-type feedback is used to reflect the performance of the trained model; when the performance of the trained model cannot meet the requirements, the second processing machine will recalculate the target first-type parameter group.

[0677] As an embodiment, when the error is too large or the time of updating is too long, the performance of the trained model is considered to be unable to meet the requirements.

[0678] As an embodiment, the target first-type parameter group includes one or more of a convolution kernel, a pool core, a pooling function, an activation function, a parameter of the pooling function, or a parameter of the activation function.

[0679] As an embodiment, the target first-type parameter group includes one or more of a convolution kernel size, a convolution layer number, a convolution step, a pool core size, a pool core step, a pooling function, an activation function, or a feature map number.

[0680] Embodiment 13

[0681] Embodiment 13 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of the present application, as shown in FIG. 13. In FIG. 13, the first operation and the second operation belong to the first stage, the third operation belongs to the second stage, the fourth operation belongs to the third stage, and the fifth operation belongs to the fourth stage; the line with an arrow represents the order of the flow.

[0682] As one embodiment, the first operation comprises AI / ML training, the second operation comprises AI / ML testing, the third operation comprises AI / ML emulation, the fourth operation comprises AI / ML entity loading, and the fifth operation comprises AI / ML inference.

[0683] As one embodiment, the first phase comprises a training phase, the second phase comprises an emulation phase, the third phase comprises a deployment phase, and the fourth phase comprises an inference phase.

[0684] As one embodiment, the first phase comprises AI / ML model training.

[0685] As one embodiment, the first phase comprises AI / ML model training and AI / ML testing.

[0686] As one embodiment, the AI / ML model training comprises initial training and re-training of one or a set of AI / ML entities.

[0687] As one embodiment, the AI / ML model training relies on training data.

[0688] As one embodiment, the AI / ML model training comprises AI / ML entity validation.

[0689] As one embodiment, the AI / ML entity validation is used to evaluate the performance of the AI / ML entity.

[0690] As one embodiment, the AI / ML entity validation relies on validation data.

[0691] As one embodiment, if the result of AI / ML entity validation does not meet the expectation, the AI / ML model will be re-trained.

[0692] As one embodiment, the AI / ML testing comprises testing the validated AI / ML entity to evaluate the performance of the trained AI / ML model.

[0693] As one embodiment, if the result of AI / ML testing meets the expectation, the AI / ML entity proceeds to the next phase; otherwise, the AI / ML model will be re-trained.

[0694] As one embodiment, the AI / ML testing relies on test data.

[0695] As one embodiment, the second stage includes AI / ML simulation, which simulates the inference of the AI / ML entity in a simulation environment.

[0696] As one embodiment, the AI / ML simulation estimates the performance of the inference of the AI / ML entity in a simulation environment before the AI / ML entity is used.

[0697] As one embodiment, the second stage is optional.

[0698] As one embodiment, the third stage includes AI / ML entity loading, which is to obtain the trained AI / ML entity to obtain the desired AI / ML inference function.

[0699] As one embodiment, the third stage is optional.

[0700] As one embodiment, the third stage is no longer needed when the training function and the inference function are co-located.

[0701] As one embodiment, the fourth stage includes AI / ML inference.

[0702] Embodiment 14

[0703] Embodiment 14 illustrates a structural block diagram of a processing apparatus in a first node according to one embodiment of the present application, as shown in FIG. 14. In FIG. 14, the processing apparatus 1400 in the first node includes a first receiver 1401 and a first transmitter 1402.

[0704] In embodiment 14, the first receiver 1401 receives a first information block, the first information block indicating a plurality of resource sets; the first transmitter 1402 transmits a first signal in a first resource block, the first resource block belonging to one of the plurality of resource sets.

[0705] In embodiment 14, the first signal carries a random access preamble, the transmission of the first signal is based on contention; the plurality of resource sets are respectively for a plurality of characteristic combinations, at least one of the plurality of characteristic combinations includes at least one AI / ML characteristic; the first resource block includes at least one of time domain resources, frequency domain resources or sequence resources.

[0706] As an embodiment, the first transmitter 1402 transmits a second signal; the second signal is for random access; a combination of the plurality of characteristics comprises a characteristic for AI / ML that is determining that the first node supports AI / ML capability; the second signal indicates AI / ML information of the first node, the AI / ML information of the first node comprising at least one of:

[0707] - an ID of an AI / ML model supported by the first node;

[0708] - a Functionality corresponding to an AI / ML model supported by the first node;

[0709] - a set of training data supported by the first node;

[0710] - an Associated ID supported by the first node;

[0711] - a Category for AI / ML corresponding to the first node.

[0712] As an embodiment, time domain resources occupied by the first resource block belong to a first set of time domain resources, and the first node supports AI / ML capability; time domain resources occupied by the first resource block do not belong to the first set of time domain resources, and the first node does not support AI / ML capability.

[0713] As an embodiment, frequency domain resources occupied by the first resource block belong to a first set of frequency domain resources, and the first node supports AI / ML capability; frequency domain resources occupied by the first resource block do not belong to the first set of frequency domain resources, and the first node does not support AI / ML capability.

[0714] As an embodiment, sequence resources occupied by the first resource block belong to a first set of sequence resources, and the first node supports AI / ML capability; sequence resources occupied by the first resource block do not belong to the first set of sequence resources, and the first node does not support AI / ML capability.

[0715] As an embodiment, the second signal comprises a first field, and the first field included in the second signal indicates the AI / ML information of the first node; when the first node does not support AI / ML capability, a value of the first field included in the second signal is fixed or predefined.

[0716] As an embodiment, the first signal is Msg1 and the second signal is Msg3; or the first signal is PRACH in MsgA and the second signal is PUSCH in MsgA.

[0717] As one embodiment, the first resource block comprises time domain resources.

[0718] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprising multiple time domain resource blocks, the first resource block being one of the multiple time domain resource blocks.

[0719] As one embodiment, the first resource block comprises frequency domain resources.

[0720] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprising multiple frequency domain resource blocks, the first resource block being one of the multiple frequency domain resource blocks.

[0721] As one embodiment, the first resource block comprises time domain resources and frequency domain resources.

[0722] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprising multiple time-frequency resource blocks, the first resource block being one of the multiple time-frequency resource blocks.

[0723] As one embodiment, the first resource block comprises sequence resources.

[0724] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprising multiple sequence resources, the first resource block occupying one of the multiple sequence resources.

[0725] As one embodiment, the second signal indicates a type of AI / ML model supported by the first node.

[0726] As one sub-embodiment of this embodiment, the type of AI / ML model comprises an architecture of the AI / ML model.

[0727] As one sub-embodiment of this embodiment, the type of AI / ML model comprises at least one of a UE-side AI / ML model, a network-side model, and a double-side model.

[0728] As one embodiment, the second signal indicates a type of AI / ML model identification supported by the first node.

[0729] As one subembodiment of this embodiment, the identification of the model comprises at least one of model identification Type A, model identification Type B1, and model identification Type B2.

[0730] As one subembodiment of this embodiment, the identification of the model comprises at least one of model identification Type A, model identification Type B1, and model identification Type B2.

[0731] As one subembodiment of this embodiment, the identification of the model comprises at least one of model identification Type A, model identification Type B1, and model identification Type B2.

[0732] As one embodiment, the first node 1400 is a user equipment.

[0733] As one embodiment, the first node 1400 is a terminal.

[0734] As one embodiment, the first node 1400 is a relay node device.

[0735] As one embodiment, the first receiver 1401 comprises at least one of {the antenna 452, the receiver 454, the receive processor 456, the multi-antenna receive processor 458, the controller / processor 459, the memory 460, the data source 467} in embodiment 4.

[0736] As one embodiment, the first transmitter 1402 comprises at least one of {the antenna 452, the transmitter 454, the transmit processor 468, the multi-antenna transmit processor 457, the controller / processor 459, the memory 460, the data source 467} in embodiment 4.

[0737] Embodiment 15

[0738] Embodiment 15 illustrates a structural block diagram of a processing apparatus in a second node according to one embodiment of the application, as shown in FIG. 15. In FIG. 15, the processing apparatus 1500 in the second node comprises a second transmitter 1501 and a second receiver 1502.

[0739] In embodiment 15, the second transmitter 1501 transmits a first information block, the first information block indicating a plurality of resource sets; the second receiver 1502 receives a first signal in a first resource block, the first resource block belonging to one of the plurality of resource sets.

[0740] In embodiment 15, the first signal carries a random access preamble, transmission of the first signal is contention-based; the multiple sets of resources are respectively for multiple combinations of characteristics, at least one of the multiple combinations of characteristics comprises at least one AI / ML-related characteristic; the first resource block comprises at least one of time domain resources, frequency domain resources, or sequence resources.

[0741] As an embodiment, the second receiver 1502 receives a second signal; the second signal is for random access; a transmitter of the second signal is a first node, one AI / ML-related characteristic comprised in the multiple combinations of characteristics is to determine that the first node supports AI / ML capability; the second signal indicates AI / ML information of the first node, the AI / ML information of the first node comprises at least one of:

[0742] - an ID of an AI / ML model supported by the first node;

[0743] - a Functionality corresponding to an AI / ML model supported by the first node;

[0744] - a set of training data supported by the first node;

[0745] - an Associated ID supported by the first node;

[0746] - a Category for AI / ML corresponding to the first node.

[0747] As an embodiment, time domain resources occupied by the first resource block belong to a first set of time domain resources, the first node supports AI / ML capability; time domain resources occupied by the first resource block do not belong to the first set of time domain resources, the first node does not support AI / ML capability.

[0748] As an embodiment, frequency domain resources occupied by the first resource block belong to a first set of frequency domain resources, the first node supports AI / ML capability; frequency domain resources occupied by the first resource block do not belong to the first set of frequency domain resources, the first node does not support AI / ML capability.

[0749] As an embodiment, sequence resources occupied by the first resource block belong to a first set of sequence resources, the first node supports AI / ML capability; sequence resources occupied by the first resource block do not belong to the first set of sequence resources, the first node does not support AI / ML capability.

[0750] As one embodiment, the second signal comprises a first field, the first field comprised in the second signal indicates the AI / ML information of the first node; when the first node does not support AI / ML capability, a value of the first field comprised in the second signal is fixed or predefined.

[0751] As one embodiment, the first signal is Msg1 and the second signal is Msg3; or the first signal is PRACH in MsgA and the second signal is PUSCH in MsgA.

[0752] As one embodiment, the first resource block comprises time domain resource.

[0753] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprises multiple time domain resource blocks, and the first resource block is one of the multiple time domain resource blocks.

[0754] As one embodiment, the first resource block comprises frequency domain resource.

[0755] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprises multiple frequency domain resource blocks, and the first resource block is one of the multiple frequency domain resource blocks.

[0756] As one embodiment, the first resource block comprises time domain resource and frequency domain resource.

[0757] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprises multiple time-frequency resource blocks, and the first resource block is one of the multiple time-frequency resource blocks.

[0758] As one embodiment, the first resource block comprises sequence resource.

[0759] As one sub-embodiment of this embodiment, the first resource block belongs to a first resource set of the multiple resource sets, the first resource set comprises multiple sequence resources, and the first resource block occupies one of the multiple sequence resources.

[0760] As one embodiment, the second signal indicates a type of AI / ML model supported by the first node.

[0761] As one sub-embodiment of this embodiment, the type of AI / ML model comprises a backbone of the AI / ML model.

[0762] As one subembodiment of this embodiment, the type of the AI / ML model includes at least one of a UE-side AI / ML model, a Network-side model, and a dual-side model.

[0763] As one embodiment, the second signal indicates a type of AI / ML model identification supported by the first node.

[0764] As one subembodiment of this embodiment, the manner of the model identification includes at least one of model identification Type A, model identification Type B1, and model identification Type B2.

[0765] As one subembodiment of this embodiment, the manner of the model identification includes at least one of model identification not based on air interface signaling and model identification based on air interface signaling.

[0766] As one subembodiment of this embodiment, the manner of the model identification includes at least one of terminal-initiated model identification and base station-initiated model identification.

[0767] As one embodiment, the second node 1500 is a base station device.

[0768] As one embodiment, the second node 1500 is a user equipment.

[0769] As one embodiment, the second node 1500 is a TRP.

[0770] As one embodiment, the second transmitter 1501 includes at least one of the antenna 420, the transmitter 418, the transmit processor 415, the multi-antenna transmit processor 471, the controller / processor 475, and the memory 476 in embodiment 4.

[0771] As one embodiment, the second receiver 1502 includes at least one of the antenna 420, the receiver 418, the receive processor 470, the multi-antenna receive processor 472, the controller / processor 475, and the memory 476 in embodiment 4.

[0772] Those skilled in the art can understand that all or part of the steps in the foregoing method can be instructed by programs to related hardware, and the programs can be stored in a computer readable storage medium, such as a read-only memory, a hard disk, an optical disk or the like. Alternatively, all or part of the steps of the foregoing embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module unit in the foregoing embodiments can be implemented in the form of hardware or in the form of a software function module, and the present application is not limited to any specific form of combination of software and hardware. The user equipment, terminal and UE in the present application include but are not limited to unmanned aerial vehicles, communication modules on unmanned aerial vehicles, remote control aircraft, aircraft, small aircraft, mobile phones, tablet computers, notebook computers, vehicle-mounted communication devices, vehicles, vehicles, RSUs, wireless sensors, network cards, Internet of Things terminals, RFID (Radio Frequency Identification) terminals, NB-IoT (Narrow Band Internet of Things) terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, network cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablet computers and other wireless communication devices. The base station or system device in the present application includes but is not limited to macro cellular base stations, micro cellular base stations, small cellular base stations, home base stations, relay base stations, eNB (evolved Node B), gNB, TRP, GNSS (Global Navigation Satellite System), relay satellites, satellite base stations, air base stations, RSUs, unmanned aerial vehicles, test equipment such as wireless communication devices that simulate part of the functions of base stations or signaling testers, and the like.

[0773] Those skilled in the art will understand that the application can be implemented by other specified forms without departing from the core or essential characteristics thereof. Therefore, the presently disclosed embodiments should in no way be considered as descriptive rather than limiting. The scope of the application is determined by the appended claims rather than the preceding description, and all modifications within the equivalent meaning and range of the claims are considered to be included therein.

Claims

1. A method in a terminal for wireless communication with artificial intelligence, characterized by, Comprising: receiving a first information block, the first information block indicating a plurality of resource sets; transmitting a first signal in a first resource block, the first resource block belonging to one of the plurality of resource sets; wherein the first signal carries a random access preamble, the transmission of the first signal is contention-based; the plurality of resource sets are respectively for a plurality of property combinations, at least one of the plurality of property combinations comprises at least one property for AI / ML; the first resource block comprises at least one of time domain resources, frequency domain resources or sequence resources.

2. The method of claim 1, wherein, Comprising: transmitting a second signal; wherein the second signal is for random access; one of the plurality of property combinations comprises a property for AI / ML that determines that the terminal supports AI / ML capability; the second signal indicates AI / ML information of the terminal, the AI / ML information of the terminal comprises at least one of: an ID of an AI / ML model supported by the terminal; a Functionality corresponding to an AI / ML model supported by the terminal; a training data set supported by the terminal; an Associated ID supported by the terminal; a Category for AI / ML corresponding to the terminal.

3. The method according to any one of claims 1 or 2, characterized in that, time domain resources occupied by the first resource block belong to a first time domain resource set, and the terminal supports AI / ML capability; time domain resources occupied by the first resource block do not belong to the first time domain resource set, and the terminal does not support AI / ML capability.

4. The method of any one of claims 1 or 2, wherein, frequency domain resources occupied by the first resource block belong to a first frequency domain resource set, and the terminal supports AI / ML capability; frequency domain resources occupied by the first resource block do not belong to the first frequency domain resource set, and the terminal does not support AI / ML capability.

5. The method of any one of claims 1 or 2, wherein, sequence resources occupied by the first resource block belong to a first sequence resource set, and the terminal supports AI / ML capability; sequence resources occupied by the first resource block do not belong to the first sequence resource set, and the terminal does not support AI / ML capability.

6. The method according to any one of claims 2 to 5, characterized in that, the second signal comprises a first field, the first field of the second signal indicating the AI / ML information of the terminal; when the terminal does not support AI / ML capability, a value of the first field of the second signal is fixed or predefined.

7. The method according to any one of claims 2 to 6, characterized in that, the first signal is Msg1 and the second signal is Msg3; or the first signal is PRACH in MsgA and the second signal is PUSCH in MsgA.

8. A terminal, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the terminal to perform the method according to any one of claims 1-7. 9.A method in a base station for wireless communication and artificial intelligence, the method comprising: Comprising: transmitting a first information block, the first information block indicating a plurality of resource sets; receive a first signal in a first resource block, the first resource block belonging to one of the plurality of resource sets; wherein the first signal carries a random access preamble, the transmission of the first signal is contention-based; the plurality of resource sets are respectively for a plurality of characteristic combinations, any of the plurality of characteristic combinations comprises at least one AI / ML-related characteristic; the first resource block comprises at least one of time domain resources, frequency domain resources, or sequence resources.

10. The method of claim 9, wherein, comprise: receive a second signal; wherein the second signal is for random access; the transmitter of the second signal is a terminal, one AI / ML-related characteristic comprised in the plurality of characteristic combinations is to determine that the terminal supports AI / ML capability; the second signal indicates AI / ML information of the terminal, the AI / ML information of the terminal comprises at least one of: an ID of an AI / ML model supported by the terminal; a Functionality corresponding to the AI / ML model supported by the terminal; a training data set supported by the terminal; an Associated ID supported by the terminal; a Category for AI / ML corresponding to the terminal.

11. The method according to any one of claims 9 or 10, characterized in that, time domain resources occupied by the first resource block belong to a first time domain resource set, and the terminal supports AI / ML capability; time domain resources occupied by the first resource block do not belong to the first time domain resource set, and the terminal does not support AI / ML capability.

12. The method of any one of claims 9 or 10, wherein, frequency domain resources occupied by the first resource block belong to a first frequency domain resource set, and the terminal supports AI / ML capability; frequency domain resources occupied by the first resource block do not belong to the first frequency domain resource set, and the terminal does not support AI / ML capability.

13. The method of any one of claims 9 or 10, wherein, sequence resources occupied by the first resource block belong to a first sequence resource set, and the terminal supports AI / ML capability; sequence resources occupied by the first resource block do not belong to the first sequence resource set, and the terminal does not support AI / ML capability.

14. The method according to any one of claims 10 to 13, characterized in that, the second signal comprises a first field, the first field comprised in the second signal indicates the AI / ML information of the terminal; when the terminal does not support AI / ML capability, a value of the first field comprised in the second signal is fixed or predefined.

15. The method according to any one of claims 10 to 14, characterized in that, the first signal is Msg1 and the second signal is Msg3; or the first signal is PRACH in MsgA and the second signal is PUSCH in MsgA.

16. A base station, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprise computer instructions, and the one or more processors invoke the computer instructions to cause the base station to perform the method according to any one of claims 9-15.

Images