A method and apparatus for CSI reporting in a node used for wireless communication

Abstract

A method and apparatus for CSI reporting in a node used for wireless communication are disclosed. A first node receives at least one CSI reporting configuration; receives a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH; determines whether to send a target CSI on the first PUSCH; sends the target CSI on the first PUSCH only when a first condition is met; a target CSI reporting configuration is used to configure reporting of the target CSI; the target CSI reporting configuration indicates a first set of resources; the first condition comprises that a first symbol is not earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol whose CP starts a first time interval after an end of a last symbol of the first PDCCH; the first time interval depends on whether a generation manner of the target CSI is based on AI.

Description

TECHNICAL FIELD

[0001] The present application relates to a transmission method and device in a wireless communication system, and in particular to a scheme and device for CSI (Channel State Information) reporting in a wireless communication system. BACKGROUND

[0002] In a conventional wireless communication, a UE (User Equipment) reports various assistance information, such as channel information, beam management related assistance information, positioning related assistance information, etc., by measuring downlink signals and / or channels. The channel information includes, but is not limited to, one or more of CRI (CSI-RS Resource Indicator), RI (Rank Indicator), PMI (Precoding Matrix Indicator), CQI (Channel quality indicator), or beam indication. The UE can use the information to select appropriate transmission parameters by itself or report the information. The network device selects appropriate transmission parameters for the UE according to the UE's report, such as cell camping, MCS (Modulation and Coding Scheme), TPMI (Transmitted Precoding Matrix Indicator), TCI (Transmission Configuration Indication), etc. In addition, the UE report can be used to optimize network parameters, such as better cell coverage, switching base stations according to UE location, etc.

[0003] With the adoption of new technologies, the increase in the number of antennas, the diversification of application scenarios, and the improvement of system performance requirements, the traditional measurement and reporting method will bring a lot of redundant overhead. Therefore, in NR (New Radio) Rel-18 (Release-18), the research on AI (Artificial Intelligence) / ML (Machine Learning) technology is initiated to explore its impact on system performance and system design. Compared with the traditional processing method, AI / ML has the characteristics of being based on training and needing to be deployed. SUMMARY

[0004] Applicant found through research that when AI / ML function is introduced, the existing measurement mechanism, reporting mechanism and related configuration signaling may not be able to adapt to the needs of AI / ML. In view of the above problems, the present application discloses a solution. It should be pointed out 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 achieves similar technical effects as NR system; 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, such as traditional CSI (Channel State Information) reporting solutions; further, a unified design solution for different scenarios (such as other non-AI / ML scenarios, including but not limited to V2X (Vehicle to Everything), capacity enhancement system, near distance communication system, NTN (NonTerrestrial Network), IoT (Internet of Things), URLLC (UltraReliable 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.

[0005] In particular, the explanation of the terminology, nouns, functions and variables in the present application (if not specially stated) can refer to the definitions in the specification protocols TS28 series, TS36 series, TS38 series, TS37 series of 3GPP. If necessary, reference can be made to 3GPP standards TS38.211, TS38.212, TS38.213, TS38.214, TS38.215, TS38.321, TS38.331, TS38.305, TS38.304, TS37.355 to assist understanding of the present application.

[0006] The present application discloses a method used in a first node for wireless communication, characterized in that it comprises:

[0007] receiving at least one CSI reporting configuration; receiving a first DCI on a first PDCCH, the first DCI triggering the reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used to configure the reporting of the at least one CSI;

[0008] determining whether to transmit a target CSI on the first PUSCH; transmitting the target CSI on the first PUSCH only when a first condition is met;

[0009] wherein a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration is one of the at least one CSI reporting configuration, the target CSI is one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set is used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set includes one or more RS resources; the first condition includes that a first symbol is not earlier than a first reference symbol, the first symbol is a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol is a next uplink symbol whose CP starts at a first time interval after an end of a last symbol of the first PDCCH; the first time interval depends on whether a generation manner of the target CSI is based on AI.

[0010] As an embodiment, the AI (Artificial Intelligence) includes ML (Machine Learning).

[0011] As an embodiment, the problem to be solved by the present application includes: how to determine whether to transmit CSI on a PUSCH.

[0012] As an embodiment, the essence of the above method includes: transmitting CSI on a PUSCH only when a first condition is met.

[0013] As an embodiment, the essence of the above method includes: whether to transmit CSI on a PUSCH depends on whether a generation manner of the CSI is based on AI.

[0014] As an embodiment, the benefits of the above method include: supporting AI-based CSI reporting.

[0015] As an embodiment, the benefits of the above method include: ensuring consistency of understanding of CSI reporting by a transceiver.

[0016] As an embodiment, the benefits of the above method include: improving accuracy and effectiveness of CSI reporting.

[0017] As an embodiment, the benefits of the above method include: whether to transmit CSI on a PUSCH depends on the first time interval, simplifying system design and reducing scheme complexity.

[0018] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0019] According to an aspect of the present disclosure, the calculation formula of the first time interval depends on a first parameter, and the first parameter depends on whether the generation manner of the target CSI is based on AI.

[0020] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0021] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0022] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0023] According to an aspect of the present disclosure, when the generation manner of the target CSI is based on AI, the target CSI includes N information blocks, the N information blocks respectively include channel information of N time units, and N is a positive integer greater than 1; and the first time interval depends on at least one of the N time units.

[0024] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0025] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0026] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0027] According to an aspect of the present disclosure, when the first resource set is composed of one or more aperiodic RS resources, the first condition further includes that the second symbol is not earlier than a second reference symbol, and the second reference symbol is a next uplink symbol at a second time interval after the end of the last symbol of the first RS in the first resource set.

[0028] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0029] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0030] As an example, the above method has the benefit of enhancing the flexibility and robustness of the system, better adapting to different transmission conditions and application scenarios, and improving the overall performance of the system.

[0031] According to an aspect of the present application, when the generation manner of the target CSI is based on AI, the first time interval is associated with the first type identifier associated with the generation manner of the target CSI.

[0032] As an embodiment, the first operation is based on training or AI.

[0033] As an embodiment, the benefits of the above method include supporting AI / ML-based CSI reporting.

[0034] As an embodiment, the benefits of the above method include improving the accuracy and effectiveness of CSI reporting.

[0035] As an embodiment, the benefits of the above method include improving the overall performance of the system.

[0036] According to an aspect of the present application, when the generation manner of the target CSI is based on AI, the first time interval is associated with the first type identifier associated with the generation manner of the target CSI.

[0037] As an embodiment, the benefits of the above method include adapting to various different scenarios and terminals, and improving the adaptability and flexibility of the system.

[0038] As an embodiment, the benefits of the above method include simplifying system design and having good flexibility.

[0039] According to an aspect of the present application, when the generation manner of the target CSI is based on AI, the first time interval is associated with the first type identifier associated with the generation manner of the target CSI.

[0040] As an embodiment, the benefits of the above method include simplifying system design and reducing the implementation complexity of the scheme.

[0041] As an embodiment, the benefits of the above method include enhancing the flexibility of the system and improving the overall performance of the system.

[0042] According to an aspect of the present application, when the generation manner of the target CSI is based on AI, the first time interval is associated with the first type identifier associated with the generation manner of the target CSI.

[0043] As an embodiment, the benefits of the above method include reducing the overhead required to obtain the target CSI.

[0044] As an embodiment, benefits of the above method include: reducing measurement resource required to obtain the target CSI.

[0045] As an embodiment, benefits of the above method include: enhancing flexibility of the system, improving overall performance of the system.

[0046] According to an aspect of the present application, it is characterized by comprising:

[0047] ignoring the first DCI when the first condition is not satisfied;

[0048] wherein no HARQ-ACK or transport block is multiplexed on the first PUSCH.

[0049] As an embodiment, the essence of the above method includes: not sending CSI on PUSCH and ignoring the corresponding DCI when the first condition is not satisfied.

[0050] As an embodiment, benefits of the above method include: being compatible with current system design and standards, improving forward and backward compatibility of the system.

[0051] As an embodiment, benefits of the above method include: improving stability and robustness of the system.

[0052] The present application discloses a method used in a second node for wireless communication, characterized by comprising:

[0053] sending at least one CSI reporting configuration; sending a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used to configure reporting of the at least one CSI;

[0054] The target receiver of the first DCI determines whether to send target CSI on the first PUSCH; the target receiver of the first DCI sends the target CSI on the first PUSCH only when a first condition is met; a target CSI reporting configuration is used to configure reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set including one or more RS resources; the first condition includes that a first symbol is not earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, and the first reference symbol being a next uplink symbol whose CP starts at a first time interval after the end of a last symbol of the first PDCCH; and the first time interval depends on whether a generation manner of the target CSI is based on AI.

[0055] According to an aspect of the present application, it is characterized in that comprising:

[0056] determining whether to receive target CSI on the first PUSCH; and receiving the target CSI on the first PUSCH only when the first condition is met.

[0057] According to an aspect of the present application, it is characterized in that a calculation formula of the first time interval depends on a first parameter, and the first parameter depends on whether a generation manner of the target CSI is based on AI.

[0058] According to an aspect of the present application, it is characterized in that when the generation manner of the target CSI is based on AI, the target CSI includes N information blocks, the N information blocks respectively including channel information of N time units, N being a positive integer greater than 1; and the first time interval depends on at least one of the N time units.

[0059] According to an aspect of the present application, it is characterized in that when the first resource set is composed of one or more aperiodic RS resources, the first condition further includes that a second symbol is not earlier than a second reference symbol, and the second reference symbol is a next uplink symbol whose CP starts at a second time interval after the end of a last symbol of a first RS in the first resource set.

[0060] According to an aspect of the present application, the generation manner of the target CSI is based on AI, including: the generation manner of the target CSI includes the target receiver of the first DCI performing a first operation, an input of the first operation depends on a measurement based on the first resource set, and the target CSI depends on an output of the first operation.

[0061] According to an aspect of the present application, the generation manner of the target CSI is based on AI, including: the generation manner of the target CSI is associated to a first type identifier.

[0062] According to an aspect of the present application, when the generation manner of the target CSI is based on AI, the first time interval depends on the first type identifier to which the generation manner of the target CSI is associated.

[0063] According to an aspect of the present application, the generation manner of the target CSI is based on AI, including: the target CSI indicates at least one resource in a second resource set, and the second resource set includes resources not belonging to the first resource set.

[0064] According to an aspect of the present application, the method comprises:

[0065] When the first condition is not met, the target receiver of the first DCI ignores the first DCI;

[0066] When the first condition is not met, the target receiver of the first DCI ignores the first DCI.

[0067] According to an aspect of the present application, the method comprises:

[0068] When the first condition is not met, the target receiver of the first DCI ignores the first DCI.

[0069] When the first condition is not met, the target receiver of the first DCI ignores the first DCI.

[0070] The present application discloses a terminal, characterized in that the terminal comprises: one or more processors and a memory;

[0071] The memory is coupled to the one or more processors, and the memory is configured to store computer program code including computer instructions, and the one or more processors are configured to invoke the computer instructions to enable the terminal to perform the method in the first node.

[0072] A base station is disclosed, and the base station comprises one or more processors and a memory;

[0073] The memory is coupled with the one or more processors, and the memory is configured to store computer program codes including computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the base station to perform the method in the second node.

[0074] A first node for wireless communication is disclosed, and the first node comprises:

[0075] A first receiver configured to receive at least one CSI reporting configuration, and receive a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used to configure reporting of the at least one CSI;

[0076] A first processor configured to determine whether to transmit a target CSI on the first PUSCH, and transmit the target CSI on the first PUSCH only when a first condition is met;

[0077] The target CSI reporting configuration is one of the at least one CSI reporting configuration, and the target CSI is one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set comprising one or more RS resources; the first condition comprises that a first symbol is not earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, and the first reference symbol being a next uplink symbol after a first time interval from an end of a last symbol of the first PDCCH; the first time interval depends on whether a generation manner of the target CSI is based on AI.

[0078] A second node for wireless communication is disclosed, and the second node comprises:

[0079] A second processor configured to transmit at least one CSI reporting configuration, and transmit a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used to configure reporting of the at least one CSI;

[0080] The target receiver of the first DCI determines whether to send target CSI on the first PUSCH; the target receiver of the first DCI sends the target CSI on the first PUSCH only when a first condition is met; a target CSI reporting configuration is used to configure reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set including one or more RS resources; the first condition includes that a first symbol is not earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol whose CP starts at a first time interval after an end of a last symbol of the first PDCCH; the first time interval depends on whether a generation manner of the target CSI is based on AI.

[0081] As an embodiment, compared with the conventional scheme, the present application has the following advantages:

[0082] - ensure consistency of CSI reporting understanding of the transceiver;

[0083] - support AI-based CSI reporting;

[0084] - reduce system measurement resources and overhead;

[0085] - improve the forward and backward compatibility of the system;

[0086] - improve the flexibility and adaptability of the system;

[0087] - improve the reliability and robustness of the system;

[0088] - simplify system design and reduce the complexity of scheme implementation;

[0089] - improve the accuracy and effectiveness of information reporting;

[0090] - enhance the overall performance of the system. BRIEF DESCRIPTION OF DRAWINGS

[0091] Other characteristics, objects and advantages of the present application will become more apparent after reading the following detailed description of non-restrictive embodiments, with reference to the accompanying drawings:

[0092] Figure 1 A flowchart of a first DCI, at least one CSI reporting configuration and target CSI according to an embodiment of the present application is shown;

[0093] Figure 2 A diagram illustrating a network architecture is shown in accordance with an embodiment of the application;

[0094] Figure 3 A diagram illustrating an embodiment of a wireless protocol architecture of a user plane and a control plane is shown in accordance with an embodiment of the application;

[0095] Figure 4 A diagram illustrating a first communication device and a second communication device is shown in accordance with an embodiment of the application;

[0096] Figure 5 A flow diagram illustrating a wireless transmission is shown in accordance with an embodiment of the application;

[0097] Figure 6 A diagram illustrating a calculation formula of a first time interval is shown in accordance with an embodiment of the application;

[0098] Figure 7 A diagram illustrating N information blocks and N time units is shown in accordance with an embodiment of the application;

[0099] Figure 8 A diagram illustrating a second symbol and a second reference symbol is shown in accordance with an embodiment of the application;

[0100] Figure 9 A diagram illustrating a first operation is shown in accordance with an embodiment of the application;

[0101] Figure 10 A diagram illustrating a first type of identification is shown in accordance with an embodiment of the application;

[0102] Figure 11 A diagram illustrating a first time interval and a first type of identification relationship is shown in accordance with an embodiment of the application;

[0103] Figure 12 A diagram illustrating a second resource set is shown in accordance with an embodiment of the application;

[0104] Figure 13 A diagram illustrating a first condition not being satisfied is shown in accordance with an embodiment of the application;

[0105] Figure 14 A diagram illustrating a second operation is shown in accordance with an embodiment of the application;

[0106] Figure 15 A diagram illustrating a first operation is shown in accordance with another embodiment of the application;

[0107] Figure 16 A diagram illustrating a deployment of a first operation is shown in accordance with an embodiment of the application;

[0108] Figure 17 A schematic diagram of an artificial intelligence or machine learning based processing system is shown according to an embodiment of the present application;

[0109] Figure 18 A schematic diagram of an artificial intelligence or machine learning based processing system is shown according to an embodiment of the present application;

[0110] Figure 19 A structural block diagram of a processing apparatus in a first node is shown according to an embodiment of the present application;

[0111] Figure 20 A structural block diagram of a processing apparatus in a second node is shown according to an embodiment of the present application. DETAILED DESCRIPTION

[0112] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings. It should be noted that the embodiments 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, for example, but not limited to, the embodiments in the drawings of Figure 1 , the embodiments in the drawings of Figure 5 , the embodiments in the drawings of Figure 20 , the embodiments in the drawings of Figure 5 , the embodiments in the drawings of Figure 6 , the embodiments in the drawings of Figure 20 , etc.

[0113] Example 1

[0114] Embodiment 1 illustrates a flowchart of a first DCI, at least one CSI reporting configuration and a target CSI according to an embodiment of the present application, as shown in FIG. 100. Each block in FIG. 100 represents a step. In particular, the order of the steps in the blocks does not represent a specific time sequence between the steps. Figure 1 Figure 1

[0115] In embodiment 1, the first node in the present application receives at least one CSI reporting configuration in step 101; receives a first DCI on a first PDCCH in step 102; determines whether to send a target CSI on the first PUSCH in step 103; and only when a first condition is met, sends the target CSI on the first PUSCH in step 104;

[0116] ​​The first DCI triggers reporting of at least one CSI on a first PUSCH, at least one CSI reporting configuration is used to configure reporting of the at least one CSI, a target CSI reporting configuration is used to configure reporting of a target CSI, the target CSI reporting configuration is one of the at least one CSI reporting configuration, the target CSI is one of the at least one CSI, the target CSI reporting configuration indicates a first resource set, the first resource set is used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set includes one or more RS resources, the first condition includes that a first symbol is not earlier than a first reference symbol, the first symbol is a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol is a next uplink symbol after a first time interval from the end of a last symbol of the first PDCCH, and the first time interval depends on whether generation of the target CSI is based on AI.

[0117] As an embodiment, the at least one CSI reporting configuration is carried by higher layer signaling.

[0118] As an embodiment, the at least one CSI reporting configuration is carried by RRC (Radio Resource Control) signaling.

[0119] As an embodiment, the at least one CSI reporting configuration is carried by one RRC IE (Information Element).

[0120] As an embodiment, the at least one CSI reporting configuration is carried by at least one RRC IE.

[0121] As an embodiment, the at least one CSI reporting configuration includes information in one or more fields in at least one RRC IE.

[0122] As an embodiment, the at least one CSI reporting configuration includes information in one or more fields in each of a plurality of RRC IEs.

[0123] As an embodiment, the at least one CSI reporting configuration includes part or all of the fields in a CSI-ReportConfig IE.

[0124] As an embodiment, the at least one CSI reporting configuration includes part or all of the fields in a ServingCellConfig IE.

[0125] As one embodiment, the at least one CSI reporting configuration includes some or all of the fields in the CSI-MeasConfig IE.

[0126] As one embodiment, the at least one CSI reporting configuration includes some or all of the fields in the ServingCellConfigCommon IE.

[0127] As one embodiment, the at least one CSI reporting configuration includes some or all of the fields in the ServingCellConfigCommonSIB IE.

[0128] As one embodiment, any of the at least one CSI reporting configuration is transmitted on PDSCH.

[0129] As one embodiment, the CSI reporting configured by any of the at least one CSI reporting configuration is periodic.

[0130] As one embodiment, the CSI reporting configured by any of the at least one CSI reporting configuration is semi-persistent.

[0131] As one embodiment, the CSI reporting configured by any of the at least one CSI reporting configuration is aperiodic.

[0132] As one embodiment, any of the at least one CSI reporting configuration is an RRC IE.

[0133] As one embodiment, any of the at least one CSI reporting configuration belongs to the CSI-ReportConfig IE.

[0134] As one embodiment, any of the at least one CSI reporting configuration belongs to the ServingCellConfig IE.

[0135] As one embodiment, any of the at least one CSI reporting configuration belongs to the CSI-MeasConfig IE.

[0136] As one embodiment, any of the at least one CSI reporting configuration belongs to the ServingCellConfigCommon IE.

[0137] As one embodiment, any of the at least one CSI reporting configuration belongs to the ServingCellConfigCommonSIB IE.

[0138] As one embodiment, the first set of resources includes one or more RS resources.

[0139] As one embodiment, the first set of resources includes one or more downlink RS resources.

[0140] As one embodiment, the first set of resources includes periodic RS resources.

[0141] As one embodiment, the first set of resources includes semi-persistent RS resources.

[0142] As one embodiment, the first set of resources includes aperiodic RS resources.

[0143] As one embodiment, the first set of resources consists of one or more aperiodic RS resources.

[0144] As one embodiment, a resource in the first set of resources includes at least one of an antenna port, a TCI (Transmission Configuration Indication) state, QCL (Quasi Co-Location) information, a time-frequency resource, a time-frequency code resource, a beam, an RS resource, a vector, or a matrix.

[0145] As one embodiment, the first set of resources includes one or more RS (Reference Signal) resource sets, and one RS resource set includes one or more RS resources.

[0146] As one embodiment, the first set of resources includes at least one of at least one CSI-RS resource set, at least one CSI-SSB (Channel State Information-Synchronization Signal Block) resource set, or at least one CSI-IM (Channel State Information-Interference Measurement) resource set.

[0147] As one embodiment, the first set of resources includes at least one RS resource set for channel measurement.

[0148] As one embodiment, the first set of resources includes at least one RS resource set for channel measurement and at least one RS resource set for interference measurement.

[0149] As one embodiment, the first set of resources comprises at least one set of RS resources for interference measurement.

[0150] As one sub-embodiment of the above embodiment, one set of RS resources for channel measurement comprises one or more RS resources.

[0151] As one sub-embodiment of the above embodiment, one set of RS resources for interference measurement comprises one or more RS resources.

[0152] As one embodiment, one set of RS resources for channel measurement comprises one or more RS resources, any RS resource in the one set of RS resources for channel measurement is a CSI-RS resource or a synchronization signal resource.

[0153] As one embodiment, one set of RS resources for interference measurement comprises one or more RS resources, any RS resource in the one set of RS resources for interference measurement is a CSI-IM resource or a NZP (non-zero power) CSI-RS resource for interference measurement.

[0154] As one embodiment, the first set of resources comprises one or more RS resources, any RS resource in the first set of resources is a CSI-RS (Channel State Information Reference Signal) resource or a synchronization signal resource.

[0155] As one embodiment, the synchronization signal resource comprises at least a resource occupied by a synchronization signal.

[0156] As one embodiment, the synchronization signal resource is an SSB (Synchronization Signal Block).

[0157] As one embodiment, the synchronization signal resource is an SS / PBCH (synchronization signal / physical broadcast channel) block resource.

[0158] As one embodiment, the first set of resources consists of at least one aperiodic CSI-RS resource for channel measurement.

[0159] As an embodiment, the first resource set consists of at least one of at least one aperiodic CSI-RS resource for channel measurement, at least one aperiodic CSI-IM resource for interference measurement, or at least one aperiodic NZP CSI-RS resource for interference measurement.

[0160] As an embodiment, the first resource set consists of one or more aperiodic RS resources; the first resource set consists of at least one of at least one aperiodic CSI-RS resource for channel measurement, at least one aperiodic CSI-IM resource for interference measurement, or at least one aperiodic NZP CSI-RS resource for interference measurement.

[0161] As an embodiment, the first resource set consists of at least one CSI-RS resource.

[0162] As an embodiment, the first resource set comprises at least one of a CSI-RS resource or a SS / PBCH block resource.

[0163] As an embodiment, the reference resource is a CSI reference resource.

[0164] As an embodiment, the reference resource is a CSI reference resource of the target CSI.

[0165] As an embodiment, the benefits of the above method include: maintaining existing standards and system design, reducing complexity.

[0166] As an embodiment, the target CSI reporting configuration indicates at least one resource configuration, and the at least one resource configuration indicates the first resource set.

[0167] As an embodiment, the target CSI reporting configuration comprises at least one resource configuration, and the at least one resource configuration indicates the first resource set.

[0168] As an embodiment, one resource configuration is used to configure a CSI resource.

[0169] As an embodiment, one resource configuration is an IE CSI-ResourceConfig.

[0170] As an embodiment, one resource configuration is carried by an RRC IE.

[0171] As an embodiment, one resource configuration is carried by a CSI-ResourceConfig IE.

[0172] As an embodiment, the target CSI reporting configuration indicates configuration information of the first resource set.

[0173] As an embodiment, the target CSI reporting configuration indicates an identity of the first resource set.

[0174] As an embodiment, the first DCI triggers the target CSI on a first PUSCH.

[0175] As an embodiment, the first DCI triggers reporting of at least one CSI on a first PUSCH, the reporting of the at least one CSI including the target CSI.

[0176] As an embodiment, the first DCI triggers reporting of at least one CSI on a first PUSCH, the reporting of the at least one CSI including the target CSI; and the target CSI reporting configuration is used to configure the reporting of the target CSI.

[0177] As an embodiment, the receiving the first DCI on the first PDCCH comprises receiving a second signal on the first PDCCH, the second signal carrying the first DCI.

[0178] As an embodiment, the first PDCCH comprises a plurality of REs.

[0179] Typically, one RE occupies one symbol in time domain and one subcarrier in frequency domain.

[0180] As an embodiment, the first PDCCH occupies at least one symbol in time domain and at least one subcarrier in frequency domain.

[0181] As an embodiment, the first PDCCH occupies at least one symbol in time domain and at least one RB in frequency domain.

[0182] As an embodiment, the symbol is a single carrier symbol.

[0183] As an embodiment, the symbol is a multi-carrier symbol.

[0184] As an embodiment, the multi-carrier symbol is an OFDM symbol.

[0185] As an embodiment, the symbol is obtained after OFDM symbol generation of an output of transform precoding.

[0186] As an embodiment, the multi-carrier symbol is a SC-FDMA (Single Carrier-Frequency Division Multiple Access) symbol.

[0187] As an embodiment, the multi-carrier symbol is a DFT-S-OFDM (Discrete Fourier Transform Spread OFDM) symbol.

[0188] As an embodiment, the multi-carrier symbol is a FBMC (Filter Bank Multi Carrier) symbol.

[0189] As an embodiment, the multi-carrier symbol comprises a CP (Cyclic Prefix).

[0190] As an embodiment, the first DCI comprises a CSI request field, the CSI request field in the first DCI triggering at least one CSI on a first PUSCH.

[0191] As an embodiment, the first DCI comprises a CSI request field, the CSI request field in the first DCI indicating at least one CSI reporting configuration, the at least one CSI reporting configuration being used for configuring reporting of the at least one CSI.

[0192] As an embodiment, the first DCI comprises a CSI request field, the CSI request field in the first DCI indicating at least one CSI reporting configuration, a target CSI reporting configuration being one of the at least one CSI reporting configuration, the at least one CSI reporting configuration being used for configuring reporting of the at least one CSI, the target CSI reporting configuration being used for configuring reporting of the target CSI.

[0193] As an embodiment, the target CSI is generated depending on measurements obtained based on the first set of resources.

[0194] As an embodiment, the target CSI is generated depending on channel measurements and / or interference measurements obtained based on the first set of resources.

[0195] As one embodiment, the measurement based on the first set of resources is used to generate the target CSI.

[0196] As one embodiment, the channel measurement and / or interference measurement based on the first set of resources is used to generate the target CSI.

[0197] As one embodiment, the measurement based on one or more RS resources in the first set of resources is used to generate the target CSI.

[0198] As one embodiment, the measurement based on no later than a transmission occasion of a reference resource in one or more RS resources in the first set of resources is used to generate the target CSI.

[0199] As one embodiment, the measurement based on no later than one or more transmission occasions of a reference resource in one or more RS resources in the first set of resources is used to generate the target CSI.

[0200] As one embodiment, the channel measurement obtained based on the first set of resources refers to a channel measurement obtained based on at least one reference signal transmitted in the first set of resources.

[0201] As one embodiment, the channel measurement obtained based on the first set of resources refers to a channel measurement obtained in the first set of resources.

[0202] As one embodiment, the channel measurement obtained based on the first set of resources comprises at least one of a channel matrix, a raw channel matrix, an eigenvector, and an eigenvalue.

[0203] As one embodiment, the channel measurement obtained based on the first set of resources comprises one or more of a BLER, a delay spread, a Doppler spread, a Doppler shift, a mean delay, a mean gain, a path loss, and an RSRP.

[0204] As one embodiment, the interference measurement obtained based on the first set of resources refers to an interference measurement obtained based on at least one reference signal transmitted in the first set of resources.

[0205] As one embodiment, the interference measurement obtained based on the first set of resources refers to an interference measurement obtained in the first set of resources.

[0206] As one embodiment, the interference measurement obtained based on the first set of resources comprises at least one of an interference power, an interference variance, or an interference power spectral density.

[0207] As one embodiment, the interference measurements obtained based on the first set of resources comprise at least one of an interference channel matrix, an interference covariance matrix, an interference eigenvector, an interference eigenvalue, an interference beam.

[0208] As one embodiment, the measurements based on the first set of resources comprise a channel matrix obtained based on measurements for the first set of resources.

[0209] As one embodiment, the measurements based on the first set of resources comprise a matrix or a vector obtained after pre-processing a channel matrix obtained based on measurements for the first set of resources.

[0210] As one embodiment, the channel matrix is in a spatial-frequency domain.

[0211] As one embodiment, the channel matrix is in an angular-delay domain projection.

[0212] As one embodiment, the pre-processing comprises one or more of quantization, DFT (Discrete Fourier Transform), matrix decomposition, matrix transformation or projection, spatial-to-angular domain transformation, angular-to-spatial domain transformation, frequency-to-time domain transformation and time-to-frequency domain transformation, truncation, padding, mapping, labeling.

[0213] As one embodiment, the at least one CSI is the target CSI, or, the at least one CSI comprises a plurality of CSIs, and the target CSI is one of the plurality of CSIs.

[0214] As one embodiment, the at least one CSI comprises only one CSI, the at least one CSI is the target CSI, and the at least one CSI reporting configuration is the target CSI reporting configuration.

[0215] As one embodiment, the at least one CSI comprises a plurality of CSIs, and the at least one CSI reporting configuration comprises a plurality of CSI reporting configurations, the plurality of CSI reporting configurations are respectively used to configure the plurality of CSIs.

[0216] As one embodiment, the at least one CSI comprises a plurality of CSIs, the at least one CSI reporting configuration comprises a plurality of CSI reporting configurations, the plurality of CSI reporting configurations are respectively used to configure the plurality of CSIs, and the target CSI is any one of the plurality of CSIs.

[0217] As one embodiment, the target CSI comprises at least one CSI reporting quantity.

[0218] As one embodiment, the target CSI includes one or more of a PMI (Precoding Matrix Indicator), a CRI (CSI-RS Resource Indicator), an SS / PBCH Block Resource indicator (SSBRI), a beam indication, a resource indication, a CQI (Channel Quality Indicator), an RI (Rank Indicator), a LI (Layer Indicator), an RSRP (reference signal received power), a SINR (signal-to-noise and interference ratio), a Capability Index, or a TDCP (Time Domain Channel Properties).

[0219] As one embodiment, the target CSI includes one or more of a channel matrix, an eigenvector, an eigenvalue, or a precoding matrix.

[0220] As one embodiment, the target CSI includes one or more of a beam indication, a CRI (CSI-RS Resource Indicator), an SS / PBCH Block Resource indicator (SSBRI), or an RSRP (reference signal received power).

[0221] As one embodiment, the target CSI includes one or more of a beam indication, a number of beams, a CRI, an SS / PBCH Block Resource indicator, a number of CRIs or SSBRI, an RSRP, a differential RSRP, Probability information, or confidence information.

[0222] As one embodiment, the Probability information indicates a probability that a corresponding beam is one or more optimal beams.

[0223] As an embodiment, the probability information indicates a probability that the corresponding RS resource is one or more optimal RS resources.

[0224] As an embodiment, the confidence information indicates accuracy of the RSRP.

[0225] As an embodiment, the confidence information indicates accuracy of the differential RSRP.

[0226] As an embodiment, the essence of the above method includes monitoring the AI model based on performance parameters of AI-based CSI reporting.

[0227] As an embodiment, the benefits of the above method include improving the performance of the AI-based CSI reporting scheme and improving the overall performance of the system.

[0228] As an embodiment, the target CSI includes RSRP.

[0229] As an embodiment, the target CSI includes at least one resource indicator and RSRP.

[0230] As an embodiment, the target CSI includes at least one resource indicator.

[0231] As an embodiment, the target CSI includes at least one resource indicator, and one resource indicator in the target CSI is used to indicate a beam or an RS resource.

[0232] As an embodiment, the target CSI includes at least one resource indicator, and one resource indicator in the target CSI is used to indicate a beam, a CSI-RS resource, or an SS / PBCH block resource.

[0233] As an embodiment, the target CSI includes at least one resource indicator; one resource indicator in the target CSI is used to indicate a beam, or one resource indicator in the target CSI is a CRI (CSI-RS Resource Indicator) or an SS / PBCH block resource indicator (SSBRI).

[0234] As an embodiment, the target CSI includes predicted CSI.

[0235] As an embodiment, the target CSI includes CSI for a future period of time.

[0236] As an embodiment, the target CSI includes predicted beam information.

[0237] As one embodiment, the target CSI includes beam information for a future time period.

[0238] As one sub-embodiment of the above embodiment, the future time period includes at least one time domain resource after a current time domain resource.

[0239] As one sub-embodiment of the above embodiment, the future time period includes at least one time unit after a current time unit.

[0240] As one sub-embodiment of the above embodiment, the future time period includes at least one slot after a current slot.

[0241] As one sub-embodiment of the above embodiment, the future time period includes at least one symbol after a current symbol.

[0242] As one embodiment, benefits of the above method include: reducing channel measurement overhead.

[0243] As one embodiment, benefits of the above method include: improving accuracy and real-time performance of CSI reporting, and enhancing overall system performance.

[0244] As one embodiment, the target CSI includes compressed CSI.

[0245] As one embodiment, the compressed CSI is based on non-codebook.

[0246] As one embodiment, the compressed CSI is neither defined in 3GPP Rel-18 nor defined in versions before 3GPP Rel-18.

[0247] As one embodiment, a target receiver of the compressed CSI is unaware of channel parameters recovered by the compressed CSI for a sender of the compressed CSI.

[0248] As one embodiment, benefits of the above method include: saving CSI feedback overhead, and improving overall system performance.

[0249] As one embodiment, the target CSI is AI-based.

[0250] As one embodiment, the target CSI is not AI-based.

[0251] As one embodiment, the amount of reporting included in the target CSI depends on whether the generation of the target CSI is AI-based.

[0252] As an example, whether the target CSI is based on a non-codebook depends on whether the generation of the target CSI is based on AI; when the generation of the target CSI is based on AI, the target CSI is based on a non-codebook; when the generation of the target CSI is not based on AI, the target CSI is based on a codebook.

[0253] As an example, when the generation of the target CSI is not based on AI, the target CSI belongs to the CSI defined by 3GPPRel-18.

[0254] As an example, when the generation of the target CSI is based on AI, the target CSI does not belong to the CSI defined in versions 3GPPRel-18 and earlier.

[0255] As an example, whether the target CSI includes confidence information depends on whether the generation of the target CSI is based on AI; the target CSI includes confidence information only when the generation of the target CSI is based on AI.

[0256] As an example, when the generation of the target CSI is based on AI, the target CSI includes predicted CSI, predicted beam information, or compressed CSI.

[0257] As an example, the advantages of the above method include: supporting AI-based CSI reporting schemes.

[0258] As an example, the advantages of the above method include minimal changes to existing systems and standards.

[0259] As an example, the benefits of the above method include: enhancing system flexibility and improving overall system performance.

[0260] As an example, the target CSI indicates at least one RS resource in the first resource set.

[0261] As an example, the target CSI indicates at least one resource in a second resource set, the second resource set including resources that do not belong to the first resource set.

[0262] As an example, when the target CSI is generated based on AI, the target CSI indicates at least one resource in a second resource set, the second resource set including resources that do not belong to the first resource set.

[0263] As an embodiment, when the generation of the target CSI is based on AI, the target CSI indicates at least one resource in a second resource set, the second resource set including resources not belonging to the first resource set; when the generation of the target CSI is not based on AI, the target CSI indicates at least one RS resource in the first resource set.

[0264] As an embodiment, the above method has the benefit of reducing the overhead required to obtain the target CSI.

[0265] As an embodiment, the above method has the benefit of reducing the measurement resources required to obtain the target CSI.

[0266] As an embodiment, the above method has the benefit of making small changes to existing systems and standards.

[0267] As an embodiment, for the case where the generation of the target CSI is not based on AI, how to generate the target CSI is determined by the manufacturer of the first node, or in other words, is implementation dependent. A typical but non-limiting implementation is described below:

[0268] The first node first performs measurement on the first resource set to obtain a channel parameter matrix H r×t , where r and t are the number of receive antennas and the number of antenna ports of the target CSI-RS resource, respectively; the channel parameter matrix H r×t is power adjusted, and the adjusted channel parameter matrix is , where P is the ratio of the assumed PDSCH EPRE to the target CSI-RS EPRE (i.e., the first power control offset); under the condition of using a precoding matrix W t×1 , the precoded channel parameter matrix is , where 1 is the rank or the number of layers, in one case 1 is a positive integer not greater than t, and in another case the precoding matrix is an identity matrix, in which case t = 1; H r×t · W t×1The equivalent channel capacity is then used to determine the CQI included in the target CSI reporting by, for example, looking up a table. Generally, the calculation of the equivalent channel capacity requires the first node to estimate the interference (including noise), which can be more accurately obtained by the first node using the measurements of the second set of occasions in the present application. Generally, the direct mapping of the equivalent channel capacity to the value of CQI depends on the receiver performance, or the modulation scheme, and other hardware-related factors.

[0269] As an embodiment, for the case that the generation of the target CSI is based on AI, how to generate the target CSI is determined by the manufacturer of the first node, or in other words, is implementation dependent. Without loss of generality, the AI model or parameters used to generate the target CSI are determined by the manufacturer of the first node.

[0270] As an embodiment, the determining whether to transmit the target CSI on the first PUSCH comprises determining whether to transmit the target CSI on the first PUSCH and the target CSI is valid.

[0271] As an embodiment, the determining whether to transmit the target CSI on the first PUSCH comprises determining whether to transmit the target CSI on the first PUSCH or to ignore the first DCI.

[0272] As an embodiment, the determining whether to transmit the target CSI on the first PUSCH comprises determining whether to transmit the target CSI on the first PUSCH or to abandon transmitting the target CSI on the first PUSCH.

[0273] Typically, the target CSI is transmitted on the first PUSCH only when the first condition is satisfied; wherein the target CSI transmitted on the first PUSCH is valid.

[0274] As an embodiment, the target CSI being valid comprises the target CSI being an updated CSI.

[0275] As an embodiment, the target CSI being valid comprises the target CSI being different from a most recent CSI configured for the target CSI reporting prior to the first PUSCH.

[0276] As an embodiment, the target CSI being valid comprises the target CSI being different from a most recent CSI configured for the target CSI reporting prior to the first PUSCH.

[0277] As an embodiment, the target CSI is valid including: the target CSI is not necessarily the same as a latest CSI reporting configured for the target CSI on the first PUSCH.

[0278] As an embodiment, the target CSI is valid including: whether the target CSI is different from a latest CSI reporting configured for the target CSI on the first PUSCH depends on a measurement of a latest RS occasion of the first resource set no later than a CSI reference resource of the target CSI.

[0279] As an embodiment, the target CSI is valid including: the target CSI is generated based on at least a measurement of a latest RS occasion of the first resource set no later than a CSI reference resource of the target CSI.

[0280] As an embodiment, the target CSI is valid including: the target CSI is updated CSI based on at least a measurement of a latest RS occasion of the first resource set no later than a CSI reference resource of the target CSI.

[0281] As an embodiment, the first resource set consists of one or more aperiodic RS resources; the target CSI is valid including: the target CSI is generated based on a measurement of an aperiodic RS resource of the first resource set triggered by the first DCI.

[0282] As an embodiment, the first resource set consists of one or more aperiodic RS resources; the target CSI is valid including: the target CSI is updated based on a measurement of an aperiodic RS resource of the first resource set triggered by the first DCI.

[0283] As an embodiment, the first PUSCH includes a plurality of REs (Resource Elements).

[0284] As an embodiment, the first PUSCH occupies at least one symbol in time domain, and the first PUSCH occupies at least one subcarrier in frequency domain.

[0285] As an embodiment, the first PUSCH occupies at least one symbol in time domain, and the first PUSCH occupies at least one RB (resource block) in frequency domain.

[0286] As an embodiment, the transmitting the target CSI on the first PUSCH includes: transmitting a first signal on the first PUSCH; wherein the first signal carries the target CSI.

[0287] As one embodiment, the first signal comprises a baseband signal.

[0288] As one embodiment, the first signal comprises a wireless signal.

[0289] As one embodiment, the first signal comprises a radio frequency signal.

[0290] As one embodiment, the transmitting the target CSI on the first PUSCH comprises that the target CSI is used to generate a signal transmitted on the first PUSCH after channel coding.

[0291] As one embodiment, the transmitting the target CSI on the first PUSCH comprises that the target CSI is used to generate a signal transmitted on the first PUSCH after channel coding and modulation.

[0292] As one embodiment, the transmitting the target CSI on the first PUSCH comprises that the target CSI is used to generate a signal transmitted on the first PUSCH after bit sequence generation and channel coding.

[0293] As one embodiment, the transmitting the target CSI on the first PUSCH comprises that the target CSI is used to generate a signal transmitted on the first PUSCH after bit sequence generation, channel coding and modulation.

[0294] As one embodiment, the transmitting the target CSI on the first PUSCH comprises that the target CSI is used to generate a signal transmitted on the first PUSCH after bit sequence generation, code block segmentation and CRC attachment, channel coding, rate matching and code block concatenation.

[0295] As one embodiment, the transmitting the target CSI on the first PUSCH comprises that the target CSI is multiplexed to the first PUSCH after bit sequence generation, code block segmentation and CRC attachment, channel coding, rate matching and code block concatenation.

[0296] Typically, the first symbol takes into account a timing advance.

[0297] Typically, the first symbol and the first reference symbol both take into account a timing advance.

[0298] As an embodiment, the first symbol is the first uplink symbol in the first PUSCH for carrying the target CSI.

[0299] As an embodiment, the first reference symbol is the Z ref , the Z ref has the specific meaning referring to the section 5.4 of 3GPP TS 38.214.

[0300] Typically, the next uplink symbol refers to the earliest uplink symbol in time.

[0301] Typically, the last symbol of the first PDCCH refers to the latest symbol occupied by the first PDCCH.

[0302] Typically, the first reference symbol is the next uplink symbol starting at a first time interval after the end of the last symbol of the first PDCCH includes that the first reference symbol is the earliest uplink symbol later than the last symbol of the first PDCCH and satisfying a reference condition, the reference condition including that the time interval between the end of the last symbol of the first PDCCH and the first reference symbol is no less than the first time interval.

[0303] As an embodiment, the first time interval is a real number or an integer.

[0304] As an embodiment, the unit of the first time interval is millisecond (ms).

[0305] As an embodiment, the unit of the first time interval is symbol.

[0306] As an embodiment, the first time interval is T proc，CSI , the T proc，CSI has the specific meaning referring to the section 5.4 of 3GPP TS 38.214.

[0307] Typically, the determination of whether to send the target CSI on the first PUSCH depends on whether the first condition is satisfied.

[0308] As one embodiment, the first condition is not satisfied when the first symbol is earlier than the first reference symbol; the first condition is satisfied when the first symbol is not earlier than the first reference symbol.

[0309] As one embodiment, the first resource set consists of one or more periodic or semi-persistent RS resources; the first condition is not satisfied when the first symbol is earlier than the first reference symbol; the first condition is satisfied when the first symbol is not earlier than the first reference symbol.

[0310] As one embodiment, the transmitting the target CSI on the first PUSCH only when the first condition is satisfied comprises ignoring the first DCI when the first condition is not satisfied.

[0311] As one embodiment, the transmitting the target CSI on the first PUSCH only when the first condition is satisfied comprises dropping the transmitting the target CSI on the first PUSCH when the first condition is not satisfied.

[0312] As one embodiment, the transmitting the target CSI on the first PUSCH only when the first condition is satisfied comprises: transmitting the target CSI on the first PUSCH and the target CSI is valid when the first condition is satisfied; transmitting the target CSI on the first PUSCH and the target CSI is not updated when the first condition is not satisfied.

[0313] As one embodiment, no HARQ-ACK or transport block is multiplexed on the first PUSCH; the transmitting the target CSI on the first PUSCH only when the first condition is satisfied comprises ignoring the first DCI when the first condition is not satisfied.

[0314] As one embodiment, no HARQ-ACK or transport block is multiplexed on the first PUSCH; the transmitting the target CSI on the first PUSCH only when the first condition is satisfied comprises dropping the transmitting the target CSI on the first PUSCH when the first condition is not satisfied.

[0315] As an example, the target CSI is multiplexed with a HARQ-ACK or a transport block on the first PUSCH; the transmitting the target CSI on the first PUSCH only when the first condition is met includes: transmitting the target CSI on the first PUSCH and the target CSI is valid when the first condition is met; transmitting the target CSI on the first PUSCH and the target CSI is not updated when the first condition is not met.

[0316] Typically, no HARQ-ACK or transport block is multiplexed on the first PUSCH.

[0317] As an example, the above method has the benefits of improving the flexibility and overall performance of the system.

[0318] As an example, the above method has the benefits of improving the stability and robustness of the system.

[0319] As an example, the above method has the benefits of making small changes to the existing system and standards.

[0320] As an example, the target CSI is generated based on AI includes: the target CSI is generated using an AI model; the target CSI is not generated based on AI includes: the target CSI is not generated using an AI model.

[0321] As an example, the target CSI is generated based on AI includes: the target CSI includes information based on artificial intelligence or machine learning; the target CSI is not generated based on AI includes: the target CSI does not include information based on artificial intelligence or machine learning.

[0322] As an example, the target CSI is generated based on AI includes: the target CSI includes information generated based on a neural network; the target CSI is not generated based on AI includes: the target CSI does not include information generated based on a neural network.

[0323] As an example, the target CSI is generated based on AI includes: the target CSI includes information generated based on a CNN (Conventional Neural Networks); the target CSI is not generated based on AI includes: the target CSI does not include information generated based on a CNN.

[0324] As an embodiment, the generation manner of the target CSI is based on AI includes that: the generation of the target CSI includes a first operation performed by a sender of the target CSI, an input of the first operation depends on a measurement based on the first resource set, and the target CSI depends on an output of the first operation; the generation manner of the target CSI is not based on AI includes that: the generation of the target CSI does not include the first operation performed by the sender of the target CSI.

[0325] As an embodiment, the generation manner of the target CSI is based on AI includes that: the target CSI reporting configuration indicates a first type of identifier; the generation manner of the target CSI is not based on AI includes that: the target CSI reporting configuration does not indicate the first type of identifier.

[0326] As an embodiment, the generation manner of the target CSI is based on AI includes that: the generation of the target CSI is associated to a first type of identifier; the generation manner of the target CSI is not based on AI includes that: the generation of the target CSI is not associated to the first type of identifier.

[0327] As an embodiment, the above method has the benefits of: simplifying system design, reducing implementation complexity.

[0328] As an embodiment, the above method has the benefits of: improving flexibility and overall performance of the system.

[0329] As an embodiment, when the generation manner of the target CSI is not based on AI, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch ; wherein the specific meanings of the Z, the κ, the μ, the T C and the T switch refer to the 5.4 section of 3GPP TS 38.214.

[0330] As an embodiment, when the generation manner of the target CSI is not based on AI, the first time interval is T proc，CSI ; the specific meaning of the T proc，CSI refers to the 5.4 section of 3GPP TS 38.214.

[0331] As an embodiment, the above method has the benefits of: small changes to existing standards and systems.

[0332] As an embodiment, the first time interval depends on whether the generation manner of the target CSI is based on AI includes that: the determination method of the first time interval depends on whether the generation manner of the target CSI is based on AI.

[0333] As an embodiment, the first time interval depends on whether the generation manner of the target CSI is based on AI includes: the calculation formula of the first time interval depends on whether the generation manner of the target CSI is based on AI.

[0334] As an embodiment, the first time interval depends on whether the generation manner of the target CSI is based on AI includes: the calculation formula of the first time interval is different in the case that the generation manner of the target CSI is based on AI and the case that the generation manner of the target CSI is not based on AI.

[0335] As an embodiment, the first time interval depends on whether the generation manner of the target CSI is based on AI includes: the calculation formula of the first time interval is a first calculation formula when the generation manner of the target CSI is based on AI; the calculation formula of the first time interval is a second calculation formula when the generation manner of the target CSI is not based on AI; wherein the first calculation formula and the second calculation formula are different.

[0336] As an embodiment, the first time interval depends on whether the generation manner of the target CSI is based on AI includes: the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch +W when the generation manner of the target CSI is based on AI, wherein the W is an integer or a real number greater than zero; the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch when the generation manner of the target CSI is not based on AI; wherein the Z, the κ, the μ, the T C , and the T switch refer to the specific meanings in the chapter 5.4 of the 3GPP TS 38.214.

[0337] As an embodiment, the first time interval depends on whether the generation manner of the target CSI is based on AI includes: the first time interval is a·[(Z)(2048+144)·κ2 -μ ·T C +T switch ] when the generation manner of the target CSI is based on AI, wherein the a is an integer or a real number greater than 1; the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch when the generation manner of the target CSI is not based on AI; wherein the Z, the κ, the μ, the TC and the T switch The specific meaning of the T

[0338] As an embodiment, the benefits of the above method include: reserving more CSI calculation time for AI-based CSI reporting, better supporting AI models and calculations, and improving the accuracy and effectiveness of CSI reporting.

[0339] As an embodiment, the benefits of the above method include: improving the overall performance of the system.

[0340] As an embodiment, the first time interval depends on whether the generation of the target CSI is based on AI, including: when the generation of the target CSI is based on AI, the first time interval is a first reference interval; when the generation of the target CSI is not based on AI, the first time interval is a second reference interval.

[0341] As an embodiment, the first reference interval is not equal to the second reference interval.

[0342] As an embodiment, the first reference interval is a real number, and the second reference interval is a real number.

[0343] As an embodiment, the first reference interval is an integer, and the second reference interval is an integer.

[0344] As an embodiment, the unit of the first reference interval is millisecond (ms), and the unit of the second reference interval is millisecond.

[0345] As an embodiment, the unit of the first reference interval is symbol, and the unit of the second reference interval is symbol.

[0346] As an embodiment, the first reference interval includes multiple candidate values.

[0347] As an embodiment, the first reference interval is calculated by a formula.

[0348] As an embodiment, the first reference interval is fixed.

[0349] As an embodiment, the first reference interval is configurable.

[0350] As an embodiment, the first reference interval is configured by higher layer signaling.

[0351] As an embodiment, the generation of the target CSI uses an AI model; and the first reference interval depends on the AI model.

[0352] As an embodiment, the target CSI depends on an output of the first operation, and the first reference interval depends on the first operation.

[0353] As an embodiment, the generation of the target CSI is associated to a first type of identity; and the first reference interval depends on the first type of identity.

[0354] As an embodiment, the first reference interval depends on UE capability information.

[0355] As an embodiment, the above method has the benefits of improving the stability and robustness of the system.

[0356] As an embodiment, the above method has the benefits of improving the flexibility and overall performance of the system.

[0357] As an embodiment, the second reference interval includes multiple candidate values.

[0358] As an embodiment, the second reference interval is calculated by a formula.

[0359] As an embodiment, the second reference interval is fixed.

[0360] As an embodiment, the second reference interval is configurable.

[0361] As an embodiment, the second reference interval is configured by higher layer signaling.

[0362] As an embodiment, the second reference interval is (Z)(2048+144)·κ2 -μ ·T C +T switch ; where the specific meanings of Z, κ, μ, T C and T switch refer to the 5.4 section of 3GPP TS 38.214.

[0363] As an embodiment, the second reference interval is T proc，CSI ; the specific meaning of T proc，CSI refers to the 5.4 section of 3GPP TS 38.214.

[0364] As an embodiment, the essence of the above method includes setting different CSI calculation times for AI-based CSI reporting and non-AI-based CSI reporting.

[0365] As an embodiment, the above method has the benefits of small changes to existing standards and systems.

[0366] As an embodiment, the benefits of the above method include: improving the flexibility of the system, adapting to different scenarios and requirements of transmission and application.

[0367] As an embodiment, the first time interval depending on whether the generation mode of the target CSI is based on AI includes: the parameters on which the first time interval depends depend on whether the generation mode of the target CSI is based on AI.

[0368] As an embodiment, the first time interval depending on whether the generation mode of the target CSI is based on AI includes: the parameters on which the calculation formula of the first time interval depends depend on whether the generation mode of the target CSI is based on AI.

[0369] As an embodiment, the first time interval depending on whether the generation mode of the target CSI is based on AI includes: the calculation formula of the first time interval depends on a first parameter, and the first parameter depends on whether the generation mode of the target CSI is based on AI.

[0370] As an embodiment, the first time interval depending on whether the generation mode of the target CSI is based on AI includes: whether the calculation formula of the first time interval depends on a second parameter depends on whether the generation mode of the target CSI is based on AI; only when the generation mode of the target CSI is based on AI, the calculation formula of the first time interval depends on the second parameter.

[0371] As an embodiment, the calculation formula of the first time interval depending on the second parameter includes: the first time interval and the second parameter are in a linear relationship.

[0372] As an embodiment, the calculation formula of the first time interval depending on the second parameter includes: the first time interval and the second parameter are in a non-linear relationship.

[0373] As an embodiment, the calculation formula of the first time interval depending on the second parameter includes: when the generation mode of the target CSI is based on AI, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch +W, wherein the specific meanings of Z, κ, μ, T C , and T switch refer to section 5.4 of 3GPP TS 38.214; W is the second parameter.

[0374] As an embodiment, the unit of the second parameter is millisecond (ms).

[0375] As an embodiment, the unit of the second parameter is symbol.

[0376] As an embodiment, the second parameter is an integer or a real number greater than 0.

[0377] As an embodiment, the formula of the calculation of the first time interval depending on the second parameter includes: when the generation mode of the target CSI is based on AI, the first time interval is a·[(Z)(2048+144)·κ2 -μ ·T C +T switch ], wherein the specific meanings of the Z, the κ, the μ, the T C and the T switch refer to the 5.4 chapter of 3GPP TS 38.214; a is the second parameter.

[0378] As an embodiment, the second parameter is an integer or a real number greater than 1.

[0379] As an embodiment, the essence of the above method includes: reserving a longer CSI calculation time for AI-based CSI reporting.

[0380] As an embodiment, the benefits of the above method include: better support for AI models and calculations, and improved accuracy and effectiveness of CSI reporting.

[0381] As an embodiment, the first time interval depending on whether the generation mode of the target CSI is based on AI includes: whether the first time interval depends on a first capability parameter depending on whether the generation mode of the target CSI is based on AI; only when the generation mode of the target CSI is based on AI, the first time interval depends on the first capability parameter.

[0382] As an embodiment, the first time interval depending on whether the generation mode of the target CSI is based on AI includes: when the generation mode of the target CSI is based on AI, the first time interval depends on a first capability parameter; when the generation mode of the target CSI is not based on AI, the first time interval depends on a second capability parameter; the first capability parameter and the second capability parameter are both capability parameters reported by the first node.

[0383] As an embodiment, the first time interval depending on whether the generation mode of the target CSI is based on AI includes: when the generation mode of the target CSI is based on AI, the first time interval depends on a first capability parameter and a second capability parameter; when the generation mode of the target CSI is not based on AI, the first time interval only depends on the second capability parameter; the first capability parameter and the second capability parameter are both capability parameters reported by the first node.

[0384] As an embodiment, the first capability parameter and the second capability parameter represent different capability parameters reported by the first node.

[0385] As an embodiment, the first capability parameter represents an AI-related capability parameter reported by the first node.

[0386] As an embodiment, the second capability parameter represents an AI-unrelated capability parameter reported by the first node.

[0387] As an embodiment, the second capability parameter comprises a beamReportTiming IE.

[0388] As an embodiment, the second capability parameter comprises a beamSwitchTiming IE.

[0389] As an embodiment, the second capability parameter comprises a codebookType IE.

[0390] As an embodiment, the second capability parameter comprises at least one of a beamReportTiming IE and a beamSwitchTiming IE.

[0391] As an embodiment, the second capability parameter comprises at least one of a codebookType IE, a beamReportTiming IE and a beamSwitchTiming IE.

[0392] As an embodiment, the method further comprises: considering UE capability information when determining the first time interval; and considering different UE capability information for AI-based and AI-unrelated CSI reporting.

[0393] As an embodiment, the method has the advantage of enhancing the reliability and robustness of the system.

[0394] As an embodiment, the first time interval depending on the first capability parameter comprises: a calculation formula of the first time interval depending on the first capability parameter.

[0395] As an embodiment, the first time interval depending on the first capability parameter comprises: the first time interval and the first capability parameter are in a linear relationship.

[0396] As an embodiment, the first time interval depending on the first capability parameter comprises: the first time interval and the first capability parameter are in a non-linear relationship.

[0397] As one embodiment, the first time interval depending on the first capability parameter includes that the first time interval depends on a first parameter, and the first parameter depends on the first capability parameter.

[0398] As one embodiment, the first time interval depending on the first capability parameter includes that a calculation formula of the first time interval depends on a first parameter, and a value of the first parameter depends on the first capability parameter.

[0399] As one embodiment, the first time interval depending on the second capability parameter includes that a calculation formula of the first time interval depends on the second capability parameter.

[0400] As one embodiment, the first time interval depending on the second capability parameter includes that the first time interval and the second capability parameter are in a linear relationship.

[0401] As one embodiment, the first time interval depending on the second capability parameter includes that the first time interval and the second capability parameter are in a non-linear relationship.

[0402] As one embodiment, the first time interval depending on the second capability parameter includes that the first time interval depends on a first parameter, and the first parameter depends on the second capability parameter.

[0403] As one embodiment, the first time interval depending on the second capability parameter includes that a calculation formula of the first time interval depends on a first parameter, and a value of the first parameter depends on the second capability parameter.

[0404] As one embodiment, the above method has the benefits of enhancing the reliability and robustness of the system.

[0405] As one embodiment, the above method has the benefits of improving the flexibility and overall performance of the system.

[0406] Example 2

[0407] Embodiment 2 illustrates a schematic diagram of a network architecture according to one embodiment of the present application, as shown in FIG. 2. Figure 2 As shown in FIG. 2.

[0408] FIG. 3 illustrates a schematic diagram of a network architecture according to one embodiment of the present application, as shown in FIG. 3. Figure 2This describes the network architecture 200 for LTE (Long-Term Evolution), LTE-A (Long-Term Evolution Advanced), and future 5G systems. The network architecture 200 for LTE, LTE-A, and future 5G systems is referred to as EPS (Evolved Packet System) 200. The 5G NR or LTE network architecture 200 can be referred to as 5GS (5G System) / EPS (Evolved Packet System) 200 or some other suitable terminology. The 5GS / EPS200 may include one or more UEs (User Equipment) 201, a UE 241 communicating with UE 201 via a sidelink, NG-RAN (Next Generation Radio Access Network) 202, 5GC (5G Core Network) / EPC (Evolved Packet Core) 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet services 230. The 5GS / EPS200 can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. (See attached...) Figure 2As shown, the 5GS / EPS 200 provides packet-switched services, however one of ordinary skill in the art will readily understand that the various concepts presented throughout this application are extensible to networks providing circuit-switched services. The NG-RAN 202 includes a NR (New Radio) NodeB (gNB) 203 and other gNBs 204. The gNB 203 provides user and control plane protocol terminations towards the UE 201. The gNB 203 can be connected to the other gNBs 204 via an Xn interface (e.g., backhaul). The gNB 203 can also be referred to as a base station, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a TRP (transmit reception point), or some other suitable terminology. The gNB 203 provides access to the 5GC / EPC 210 for the UE 201. Examples of UEs 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 UAV, a narrowband physical web device, a machine type communication device, a land vehicle, a car, a wearable device, or any other similar functional device. The UE 201 can also be referred to as a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wirelessAll user Internet Protocal (IP) packets are transferred through the S-GW / UPF 212, which is connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation in addition to other functions. The P-GW / UPF 213 is connected to the Internet services 230. The Internet services 230 include operator corresponding Internet protocol services, which can include the Internet, intranet, IMS (IP Multimedia Subsystem), and packet switching services, in particular.

[0409] As an embodiment, the first node in the present application comprises the UE 201.

[0410] As an embodiment, the second node in the present application comprises the gNB 203.

[0411] As an embodiment, the UE 201 comprises a mobile phone.

[0412] As an embodiment, the UE 201 comprises a vehicle, such as a car.

[0413] As an embodiment, the gNB 203 is a macro cell base station.

[0414] As an embodiment, the gNB 203 is a micro cell base station.

[0415] As an embodiment, the gNB 203 is a pico cell base station.

[0416] As an embodiment, the gNB 203 is a femto cell base station.

[0417] As an embodiment, the gNB 203 is a base station device supporting large latency difference.

[0418] As an embodiment, the gNB 203 is a flying platform device.

[0419] As an embodiment, the gNB 203 is a satellite device.

[0420] As an embodiment, the gNB 203 is a test device (e.g. a transceiver simulating part of the functions of a base station, a signaling tester).

[0421] As an embodiment, the wireless link from the UE 201 to the gNB 203 is an uplink, which is used to perform uplink transmission.

[0422] As one embodiment, a wireless link from the gNB 203 to the UE 201 is a downlink, which is used to perform downlink transmission.

[0423] As one embodiment, a wireless link between the UE 201 and the gNB 203 comprises a cellular network link.

[0424] As one embodiment, a connection between the UE 201 and the gNB 203 is through a Uu air interface.

[0425] As one embodiment, a sender of the at least one CSI reporting configuration comprises the gNB 203.

[0426] As one embodiment, a receiver of the at least one CSI reporting configuration comprises the UE 201.

[0427] As one embodiment, a sender of the target CSI reporting configuration comprises the gNB 203.

[0428] As one embodiment, a receiver of the target CSI reporting configuration comprises the UE 201.

[0429] As one embodiment, a sender of the first DCI comprises the gNB 203.

[0430] As one embodiment, a receiver of the first DCI comprises the UE 201.

[0431] As one embodiment, a sender of the first resource set comprises the gNB 203.

[0432] As one embodiment, a receiver of the first resource set comprises the UE 201.

[0433] As one embodiment, a sender of the at least one CSI comprises the UE 201.

[0434] As one embodiment, a receiver of the at least one CSI comprises the gNB 203.

[0435] As one embodiment, a sender of the target CSI comprises the UE 201.

[0436] As one embodiment, a receiver of the target CSI comprises the gNB 203.

[0437] As one embodiment, the UE 201 supports a 6G system.

[0438] As one embodiment, the gNB 203 supports a 6G system.

[0439] As an example, the UE 201 supports at least a 5G system.

[0440] As an example, the gNB203 supports at least 5G systems.

[0441] As an example, the UE 201 supports AI.

[0442] As an example, the gNB203 supports AI.

[0443] Example 3

[0444] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in the attached diagram. Figure 3 As shown.

[0445] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and a control plane according to this application, as shown in the attached diagram. Figure 3 As shown. Figure 3 This is a schematic diagram illustrating an embodiment of a radio protocol architecture for the user plane 350 and the control plane 300. Figure 3The radio protocol architecture for the control plane 300 between a first communication node device (UE, gNB, or RSU in V2X) and a second communication node device (gNB, UE, or RSU in V2X), or between two UEs, is shown with three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer), which is the lowest layer, implements various PHY (Physical layer) signal processing functions. The L1 layer will be referred to as the PHY 301 herein. Layer 2 (L2 layer) 305 is above the PHY 301 and is responsible for the link between the first communication node device and the second communication node device, or between two UEs. The L2 layer 305 includes a MAC (Medium Access Control) sublayer 302, a RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which are terminated at the second communication node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. The PDCP sublayer 304 also provides security functions, such as ciphering / de-ciphering of the data packets, and header compression. The RLC sublayer 303 provides segmentation and reassembly of upper layer data packets, retransmission of lost data packets, and reordering of data packets to compensate for out-of-order reception due to HARQ. 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 (L3 layer) in the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second communication node device and the first communication node device. The radio protocol architecture for the user plane 350 includes Layer 1 (L1 layer) and Layer 2 (L2 layer), which are substantially the same as the corresponding layers and sublayers in the control plane 300 for the PHY 351, the PDCP sublayer 354 in the L2 layer 355, the RLC sublayer 353 in the L2 layer 355, and the MAC sublayer 352 in the L2 layer 355 for the first communication node device and the second communication node device, but the PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead.The L2 layer 355 in the user plane 350 also includes a SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for the mapping between a QoS flow and a data radio bearer (DRB) to support the diversity of services. Although not illustrated, the first communication node device can have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) that terminates at a 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.).

[0446] As one embodiment, the wireless protocol architecture in FIG. 3A is applicable to the first node in the present application. Figure 3

[0447] As one embodiment, the wireless protocol architecture in FIG. 3A is applicable to the first node in the present application. Figure 3

[0448] As one embodiment, the higher layer in the present application refers to a layer above the physical layer.

[0449] As one embodiment, the at least one CSI is generated at the PHY 301 or the PHY 351.

[0450] As one embodiment, the target CSI is generated at the PHY 301 or the PHY 351.

[0451] As one embodiment, the reference signal in the first resource set is generated at the PHY 301 or the PHY 351.

[0452] As one embodiment, the at least one CSI is generated at the PHY 301 or the PHY 351.

[0453] As one embodiment, the at least one CSI is generated at the MAC 302 or the MAC 352.

[0454] As one embodiment, the target CSI is generated at the PHY 301 or the PHY 351.

[0455] As one embodiment, the target CSI is generated at the MAC 302 or the MAC 352.

[0456] Example 4

[0457] 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. 3B. The first communication device and the second communication device in FIG. 3B are similar to the first communication device and the second communication device in FIG. 3A, respectively. Figure 4 Figure 4 ​​​is a block diagram of a first communication device 410 and a second communication device 450 that communicate with each other in an access network.

[0458] The first communication device 410 includes 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 antennas 420.

[0459] The second communication device 450 includes 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 antennas 452.

[0460] In a transmission from the first communication device 410 to the second communication device 450, at the first communication device 410, upper layer packets from a core network are provided to the controller / processor 475. The controller / processor 475 implements functionality of the L2 layer. In the DL, the controller / processor 475 provides header compression, ciphering, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocations for the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for 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 the LI layer (i.e., physical layer). The transmit processor 416 implements coding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and constellation mapping based on various modulation schemes (e.g., binary phase-shift keying (BPSK), quadrature phase-shift keying (QPSK), M-phase-shift keying (M-PSK), M-quadrature amplitude modulation (M-QAM)). The multi-antenna transmit processor 471 performs digital spatial pre-coding on the coded and modulated symbols, including codebook-based and non-codebook-based pre-coding, and beamforming processing, generating one or more parallel streams. The transmit processor 416 then maps to each of the parallel streams to subcarriers, multiplexes the modulated symbols with reference signals (e.g., pilot) in time domain and / or frequency domain, and then performs an inverse fast Fourier transform (IFFT) to generate time domain multi-carrier symbol streams. The multi-antenna transmit processor 471 then performs transmit analog pre-coding / beamforming operations on the time domain multi-carrier symbol streams. Each transmitter 418 converts the baseband multi-carrier symbol streams provided by the multi-antenna transmit processor 471 into radio frequency signals, which are then provided to the various antennas 420.

[0461] 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 Ll layer. 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 into the time domain using a Fast Fourier Transform (FFT). In the time domain, a physical layer data signal and the reference signal are demultiplexed from the baseband, multicarrier symbol stream by the receive processor 456, where the reference signal will be used for channel estimation and the data signal is recovered after multi-antenna detection in the multi-antenna receive processor 458 for any parallel streams destined for 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 layer. The controller / processor 459 can be associated with a memory 460 that stores program codes and data. The memory 460 can be referred to as a computer readable medium. In the DL (DownLink), the controller / processor 459 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer data packets from the core network. The upper layer data packets are then provided to all protocol layers above the L2 layer. Various control signals can also be provided to the L3 for L3 processing. The controller / processor 459 is also responsible for error detection using an acknowledgement (ACK) and / or negative acknowledgement (NACK) protocol to support HARQ operations.

[0462] 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 the L2 layer. 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 performs modulation mapping, channel coding processing, and a multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, and then the transmit processor 468 modulates the generated parallel streams into multiple carrier / singular carrier symbol streams, which are then processed by the analog precoding / beamforming operation in the multi-antenna transmit processor 457 and provided to different antennas 452 via transmitters 454. Each transmitter 454 first converts the baseband symbol stream provided by the multi-antenna transmit processor 457 into a radio frequency signal, and then provides the radio frequency signal to the antenna 452.

[0463] 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 jointly implement the functionality of the L1 layer. A controller / processor 475 implements the functionality of the L2 layer. The controller / processor 475 can be associated with a memory 476 that stores program codes and data. The memory 476 can be referred to as a computer readable medium. 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.

[0464] As an embodiment, the second communication device 450 comprises at least one processor and at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the second communication device 450 to perform the following: receive at least one CSI reporting configuration; receive a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used for configuring reporting of the at least one CSI; determine whether to send a target CSI on the first PUSCH; send the target CSI on the first PUSCH only when a first condition is met; wherein a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicating a first set of resources, the first set of resources being used for at least one of channel measurement or interference resource measurement of the target CSI, the first set of resources comprising one or more RS resources; the first condition comprising a first symbol not being earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol after an end of a last symbol of the first PDCCH with a first time interval, the first time interval depending on whether a generation manner of the target CSI is based on AI.

[0465] As an 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 actions comprising: receiving at least one CSI reporting configuration; receiving a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used for configuring reporting of the at least one CSI; determining whether to transmit a target CSI on the first PUSCH; transmitting the target CSI on the first PUSCH only when a first condition is met; wherein a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicating a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set comprising one or more RS resources; the first condition comprising a first symbol not being earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol after an end of a last symbol of the first PDCCH with a CP starting at a first time interval, the first time interval depending on whether a generation manner of the target CSI is based on AI.

[0466] As an embodiment, the first communication device 410 comprises at least one processor and at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the first communication device 410 to perform the following: transmitting at least one CSI reporting configuration; transmitting a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used for configuring reporting of the at least one CSI; wherein a target receiver of the first DCI determines whether to transmit a target CSI on the first PUSCH; the target receiver of the first DCI transmits the target CSI on the first PUSCH only when a first condition is met; a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set comprising one or more RS resources; the first condition comprises a first symbol not being earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol after an end of a last symbol of the first PDCCH with a CP starting at a first time interval, the first time interval depending on whether a generation manner of the target CSI is based on AI.

[0467] As an 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 actions comprising: transmitting at least one CSI reporting configuration; transmitting a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used for configuring reporting of the at least one CSI; wherein a target receiver of the first DCI determines whether to transmit a target CSI on the first PUSCH; the target receiver of the first DCI transmits the target CSI on the first PUSCH only when a first condition is met; a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicates a first set of resources, the first set of resources being used for at least one of channel measurement or interference resource measurement of the target CSI, the first set of resources comprising one or more RS resources; the first condition comprises a first symbol not being earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol whose CP starts at a first time interval after an end of a last symbol of the first PDCCH; the first time interval depending on whether a generation manner of the target CSI is based on AI.

[0468] As an embodiment, the first node in the present application comprises the second communication device 450.

[0469] As an embodiment, the second node in the present application comprises the first communication device 410.

[0470] As an embodiment, at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, the data source 467} is used for receiving the at least one CSI reporting configuration; at least one of {the antenna 420, the transmitter 418, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, the memory 476} is used for transmitting the at least one CSI reporting configuration.

[0471] As one embodiment, 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} is configured to receive the first DCI; at least one of {the antenna 420, the transmitter 418, the transmit processor 416, the multi-antenna transmit processor 471, the controller / processor 475, the memory 476} is configured to transmit the first DCI.

[0472] As one embodiment, 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} is configured to receive the RS resource in the first resource set; at least one of {the antenna 420, the transmitter 418, the transmit processor 416, the multi-antenna transmit processor 471, the controller / processor 475, the memory 476} is configured to transmit the RS resource in the first resource set.

[0473] As one embodiment, at least one of {the antenna 420, the receiver 418, the receive processor 470, the multi-antenna receive processor 472, the controller / processor 475, the memory 476} is configured to receive the target CSI on the first PUSCH; 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} is configured to transmit the target CSI on the first PUSCH.

[0474] Example 5

[0475] Embodiment 5 illustrates a flowchart of wireless transmission according to one embodiment of the present application, as shown in FIG. 5. In FIG. 5, the second node U1 and the first node U2 are communication nodes for over-the-air interface transmission. In FIG. 5, the steps in block F51 to block F55 are optional. Figure 5 Figure 5 In FIG. 5, the second node U1 and the first node U2 are communication nodes for over-the-air interface transmission. In FIG. 5, the steps in block F51 to block F55 are optional. Figure 5

[0476] ​​For the second node U1, deploying the second operation in step S511; sending the at least one CSI reporting configuration in step S512; sending the first DCI on the first PDCCH in step S513; sending the signal in the first set of resources in step S514; receiving the target CSI on the first PUSCH only when the first condition is met in step S515; performing the second operation in step S516.

[0477] For the first node U2, deploying the first operation in step S521; receiving the at least one CSI reporting configuration in step S522; receiving the first DCI on the first PDCCH in step S523; receiving the signal in the first set of resources in step S524; performing the first operation in step S525; determining whether to send the target CSI on the first PUSCH in step S526; sending the target CSI on the first PUSCH only when the first condition is met in step S527.

[0478] In embodiment 5, the first DCI triggers reporting of at least one CSI on the first PUSCH, the at least one CSI reporting configuration is used for configuring reporting of the at least one CSI; a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration is one of the at least one CSI reporting configuration, the target CSI is one of the at least one CSI; the target CSI reporting configuration indicates a first set of resources, the first set of resources is used for at least one of channel measurement or interference resource measurement of the target CSI, the first set of resources comprises one or more RS resources; the first condition comprises that a first symbol is not earlier than a first reference symbol, the first symbol is a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol is a next uplink symbol after a first time interval from an end of a last symbol of the first PDCCH; the first time interval depends on whether a generation manner of the target CSI is based on AI.

[0479] As an embodiment, the first node U2 is the first node in the present application.

[0480] As an embodiment, the second node U1 is the second node in the present application.

[0481] As an embodiment, the air interface between the second node U1 and the first node U2 comprises a wireless interface between a base station device and a user equipment.

[0482] As an embodiment, the air interface between the second node U1 and the first node U2 comprises a wireless interface between a relay node device and a user equipment.

[0483] As an embodiment, the air interface between the second node U1 and the first node U2 comprises a wireless interface between a user equipment and a user equipment.

[0484] As an embodiment, the second node U1 is a serving cell maintaining base station of the first node U2.

[0485] As an embodiment, the step in block F53 in the method in the first node for wireless communication exists; the method in the first node for wireless communication comprises: receiving a signal in the first resource set. Figure 5

[0486] As an embodiment, the step in block F53 in the method in the second node for wireless communication exists; the method in the second node for wireless communication comprises: transmitting a signal in the first resource set. Figure 5

[0487] As an embodiment, transmitting a signal in the first resource set means transmitting a wireless signal in the first resource set.

[0488] As an embodiment, transmitting a signal in the first resource set means transmitting a reference signal in the first resource set.

[0489] As an embodiment, receiving a signal in the first resource set means receiving a wireless signal in the first resource set.

[0490] As an embodiment, receiving a signal in the first resource set means receiving a reference signal in the first resource set.

[0491] As an embodiment, the step in block F52 in the method in the first node for wireless communication exists. Figure 5

[0492] As an embodiment, the step in block F52 in the method in the second node for wireless communication exists. Figure 5

[0493] As an embodiment, the step in block F52 in the method in the first node for wireless communication exists. Figure 5

[0494] As an embodiment, the step in block F52 in the method in the second node for wireless communication exists, the step in block F54 in the method in the first node for wireless communication exists, the step in block F55 in the method in the second node for wireless communication exists, the first node and the second node adopt a two-sided AI model. Figure 5 As an embodiment, the step in block F52 in the method in the first node for wireless communication exists, the step in block F54 in the method in the first node for wireless communication exists, the step in block F55 in the method in the second node for wireless communication does not exist, the first node adopts a single side AI model.​​​​​

[0495] As an embodiment, the steps in block F51 in Figure 5 As an embodiment, the steps in block F51 in

[0496] As an embodiment, the deployment of the second operation is earlier than the sending of the at least one CSI reporting configuration.

[0497] As an embodiment, the deployment of the second operation is later than the sending of the at least one CSI reporting configuration.

[0498] As an embodiment, the steps in block F55 in Figure 5 As an embodiment, the steps in block F55 in

[0499] As an embodiment, the steps in block F55 in Figure 5 As an embodiment, when the generation of the target CSI is based on AI, the steps in block F54 are present, the steps in block F55 are present, the first operation is for CSI compression, the second operation is for CSI recovery, and the first node and the second node employ a two-sided AI model.

[0500] As an embodiment, the steps in block F55 in Figure 5 As an embodiment, when the generation of the target CSI is based on AI, the steps in block F54 are present, the steps in block F55 are not present, the first operation is for beam prediction, and the first node employs a single side AI model.

[0501] As an embodiment, the deployment of the first operation is earlier than the receiving of the at least one CSI reporting configuration.

[0502] As an embodiment, the deployment of the first operation is later than the receiving of the at least one CSI reporting configuration.

[0503] As an embodiment, the output of the first operation comprises the target CSI; and the input of the second operation comprises the target CSI.

[0504] As an embodiment, the first node is a user (consumer).

[0505] As an embodiment, the first node is a user (consumer) of an AI function.

[0506] As an embodiment, the first node is a user of AI inference.

[0507] As one embodiment, the first node is a user of AI training.

[0508] As one embodiment, the first node is a user of MnS (Management Service).

[0509] As one embodiment, the first node is a producer of AI inference.

[0510] As one embodiment, the first node is a producer of AI training.

[0511] Example 6

[0512] Embodiment 6 illustrates a diagram of a formula of the first time interval according to one embodiment of the present application; as shown in FIG. 6. Figure 6

[0513] In Embodiment 6, the formula of the first time interval depends on a first parameter, which depends on whether the generation of the target CSI is based on AI.

[0514] As one embodiment, the first parameter is a real number or an integer.

[0515] As one embodiment, the first parameter is a real number or an integer greater than 0.

[0516] As one embodiment, the first parameter is a real number or an integer greater than 1.

[0517] As one embodiment, the unit of the first parameter is millisecond (ms).

[0518] As one embodiment, the unit of the first parameter is second (s).

[0519] As one embodiment, the unit of the first parameter is symbol.

[0520] As one embodiment, the unit of the first parameter is slot.

[0521] As one embodiment, the unit of the first parameter is subframe.

[0522] As one embodiment, the value of the first parameter is configurable.

[0523] As one embodiment, the value of the first parameter is fixed.

[0524] As one embodiment, the first parameter includes one or more candidate values. ​

[0525] As an embodiment, the value of the first parameter depends on UE capability information.

[0526] As an embodiment, the value of the first parameter depends on UE capability information; the UE capability information includes at least one of codebookType IE, beamReportTiming IE and beamSwitchTiming IE.

[0527] As an embodiment, the essence of the above method includes: considering UE capability information when determining the first time interval.

[0528] As an embodiment, the benefit of the above method includes: enhancing the reliability and robustness of the system.

[0529] As an embodiment, the first parameter is Z.

[0530] As an embodiment, the first parameter is Z(m).

[0531] As an embodiment, the first parameter is one of Z1, Z2, Z3.

[0532] As an embodiment, the first parameter is T switch .

[0533] As an embodiment, the specific meaning of the Z, the Z(m), the Z1, the Z2, the Z3, the T switch is referred to the chapter 5.4 of 3GPP TS 38.214.

[0534] As an embodiment, the benefit of the above method includes: using existing standards and system design, reducing implementation complexity.

[0535] As an embodiment, the first time interval and the first parameter are a functional relationship.

[0536] As an embodiment, the first time interval and the first parameter are a mapping relationship.

[0537] As an embodiment, the first time interval and the first parameter are a linear relationship.

[0538] As an embodiment, the first time interval and the first parameter are a nonlinear relationship.

[0539] As an embodiment, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch , wherein the Z, the κ, the μ, the TC and the specific meaning of T switch is referred to the section 5.4 of 3GPP TS 38.214; the first parameter is the Z.

[0540] As an embodiment, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch , wherein the specific meaning of Z, κ, μ, T C and T switch is referred to the section 5.4 of 3GPP TS 38.214; the first parameter is the T switch .

[0541] As an embodiment, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch +W, wherein the specific meaning of Z, κ, μ, T C and T switch is referred to the section 5.4 of 3GPP TS 38.214; W is an integer or real number greater than 0; the first parameter is the Z.

[0542] As an embodiment, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch +W, wherein the specific meaning of Z, κ, μ, T C and T switch is referred to the section 5.4 of 3GPP TS 38.214; W is an integer or real number greater than 0; the first parameter is the T switch .

[0543] As an embodiment, the first time interval is a·[(Z)(2048+144)·κ2 -μ ·T C +T switch ], wherein the specific meaning of Z, κ, μ, T C and T switch is referred to the section 5.4 of 3GPP TS 38.214; a is an integer or real number greater than 1; the first parameter is the Z.

[0544] As an embodiment, the first time interval is a·[(Z)(2048+144)·κ2 -μ ·T C +Tswitch ], wherein the Z, the K, the m, the T C and the T switch have the specific meaning referred to in section 5.4 of 3GPP TS 38.214; the a is an integer or real number larger than 1; the first parameter is the T switch .

[0545] As an embodiment, the first time interval is wherein the Z(m), the K, the m, the T C and the T switch have the specific meaning referred to in section 5.4 of 3GPP TS 38.214; the first parameter is the Z(m).

[0546] As an embodiment, the first time interval is wherein the Z(m), the K, the m, the T C and the T switch have the specific meaning referred to in section 5.4 of 3GPP TS 38.214; the first parameter is the T switch .

[0547] As an embodiment, the first time interval is (Z1)(2048+144) K2 -μ T C + T switch wherein the Z1, the K, the m, the T C and the T switch have the specific meaning referred to in section 5.4 of 3GPP TS 38.214; the first parameter is the Z1.

[0548] As an embodiment, the first time interval is (Z1)(2048+144) K2 -μ T C + T switch wherein the Z1, the K, the m, the T C and the T switch have the specific meaning referred to in section 5.4 of 3GPP TS 38.214; the first parameter is the T switch .

[0549] As an embodiment, the first time interval is (Z2)(2048+144) K2 -μ T C + T switch wherein the Z2, the K, the m, the T C and the T switchFor the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is Z2.

[0550] As an example, the first time interval is (Z2)(2048+144)·κ2 -μ ·T C +T switch Among them, Z2, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is the T switch .

[0551] As an example, the first time interval is (Z3)(2048+144)·κ2 -μ ·T C +T switch Among them, Z3, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is Z3.

[0552] As an example, the first time interval is (Z3)(2048+144)·κ2 -μ ·T C +T switch Among them, Z3, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is the T switch

[0553] As an example, the first time interval is (Z2+Z′2)(2048+144)·κ2 -μ ·T C +T switch Among them, Z2, Z′2, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is Z2.

[0554] As an example, the first time interval is (Z2+Z′2)(2048+144)·κ2 -μ ·T C +T switch Among them, Z2, Z′2, κ, μ, and T C and the T switchFor the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is the T switch .

[0555] As an example, the first time interval is (Z2+14(K-1)m)(2048+144)·κ2 -μ ·T C +T switch Among them, Z2, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is Z2.

[0556] As an example, the first time interval is (Z2+14(K-1)m)(2048+144)·κ2 -μ ·T C +T switch Among them, Z2, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS38.214; the first parameter is the T switch .

[0557] As an example, the first time interval is (Z2+14(K-1)m+Z′2)(2048+144)·κ2 -μ ·T C +T switch Among them, Z2, Z′2, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS 38.214; the first parameter is Z2.

[0558] As an example, the first time interval is (Z2+14(K-1)m+Z′2)(2048+144)·κ2 -μ ·T C +T switch Among them, Z2, Z′2, κ, μ, and T C and the T switch For the specific meaning, please refer to section 5.4 of 3GPP TS 38.214; the first parameter is the T switch .

[0559] As an example, the first time interval is (Z2+w)(2048+144)·κ2 -μ ·T C +T switchwherein the specific meanings of Z2, κ, μ, T C and T switch are referred to the section 5.4 of 3GPP TS 38.214; the first parameter is T -μ .

[0560] As an embodiment, the first time interval is (Z2+w)(2048+144)·κ2 C ·T switch , wherein the specific meanings of Z2, κ, μ, T C and T switch are referred to the section 5.4 of 3GPP TS 38.214; the first parameter is T switch .

[0561] As an embodiment, the first time interval is (Z2+w+Z′2)(2048+144)·κ2 -μ ·T C +T switch , wherein the specific meanings of Z2, Z′2, κ, μ, T C and T switch are referred to the section 5.4 of 3GPP TS 38.214; the first parameter is Z2.

[0562] As an embodiment, the first time interval is (Z2+w+Z′2)(2048+144)·κ2 -μ ·T C +T switch , wherein the specific meanings of Z2, Z′2, κ, μ, T C and T switch are referred to the section 5.4 of 3GPP TS 38.214; the first parameter is T switch .

[0563] As an embodiment, the benefits of the above method include: maintaining the existing standards and system design, reducing implementation complexity.

[0564] As an embodiment, the benefits of the above method include: improving the flexibility and overall performance of the system.

[0565] As an embodiment, the determination of the first parameter depends on whether the generation mode of the target CSI is based on AI.

[0566] As an embodiment, when the generation mode of the target CSI is not based on AI, the first parameter is Z; when the generation mode of the target CSI is based on AI, the first parameter is not Z.

[0567] As an embodiment, when the generation manner of the target CSI is not based on AI, the first parameter is T switch ; when the generation manner of the target CSI is based on AI, the first parameter is not T switch .

[0568] As an embodiment, when the generation manner of the target CSI is not based on AI, the first parameter is Z1; when the generation manner of the target CSI is based on AI, the first parameter is not Z1.

[0569] As an embodiment, when the generation manner of the target CSI is not based on AI, the first parameter is Z2; when the generation manner of the target CSI is based on AI, the first parameter is not Z2.

[0570] As an embodiment, the reporting quantity of the target CSI includes RSRP; when the generation manner of the target CSI is not based on AI, the first parameter is Z3; when the generation manner of the target CSI is based on AI, the first parameter is not Z3.

[0571] As an embodiment, when the generation manner of the target CSI is based on AI, the first parameter is not any one of Z1, Z2, and Z3.

[0572] As an embodiment, when the generation manner of the target CSI is based on AI, the first parameter is not Z(m) defined in 3GPP TS 38.214 in version 18 and previous versions.

[0573] As an embodiment, the essence of the above method includes: processing the AI-based and non-AI-based schemes in different cases.

[0574] As an embodiment, the benefits of the above method include: better adaptation to various application scenarios, and good flexibility.

[0575] As an embodiment, the value of the first parameter depends on whether the generation manner of the target CSI is based on AI.

[0576] As an embodiment, when the generation manner of the target CSI is based on AI, the candidate value of the first parameter belongs to a first candidate value range, and the first candidate value range includes one or more candidate values; when the generation manner of the target CSI is not based on AI, the candidate value of the first parameter belongs to a second candidate value range, and the first candidate value range includes one or more candidate values.

[0577] As one embodiment, any of the first candidate value range and the second candidate value range is a real number or an integer.

[0578] As one embodiment, any of the first candidate value range and the second candidate value range is a real number or an integer greater than 0.

[0579] As one embodiment, any of the first candidate value range and the second candidate value range is a real number or an integer greater than 1.

[0580] As one embodiment, the unit of any of the first candidate value range and the second candidate value range is millisecond (ms).

[0581] As one embodiment, the unit of any of the first candidate value range and the second candidate value range is second (s).

[0582] As one embodiment, the unit of any of the first candidate value range and the second candidate value range is symbol.

[0583] As one embodiment, the unit of any of the first candidate value range and the second candidate value range is slot.

[0584] As one embodiment, the unit of any of the first candidate value range and the second candidate value range is subframe.

[0585] As one embodiment, the second candidate value range includes 10, 13, 25, 43.

[0586] As one embodiment, the second candidate value range includes 22, 33, 44, 97, 388, 776.

[0587] As one embodiment, the second candidate value range includes 40, 72, 141, 152, 608, 1216.

[0588] As one embodiment, the second candidate value range includes 22, 33, min(44, X2+KB1), min(97, X3+KB2), min(388, X5+KB3), min(776, X6+KB4); where the specific meanings of X2, X3, X5, X6, KB1, KB2, KB3, KB4 refer to the 5.4 chapter of 3GPP TS 38.214.

[0589] As one embodiment, the essence of the above method includes: processing AI-based and non-AI-based schemes on a case-by-case basis.

[0590] As an embodiment, benefits of the above method include: using existing standards and system design, reducing implementation complexity.

[0591] As an embodiment, the first candidate value range and the second candidate value range are different.

[0592] As an embodiment, the first candidate value range and the second candidate value range include the same number of candidate values.

[0593] As an embodiment, the first candidate value range is sorted in descending order of candidate values; the second candidate value range is sorted in descending order of candidate values; any candidate value in the sorted first candidate value range is greater than the candidate value at the same position in the sorted second candidate value range.

[0594] As an embodiment, the essence of the above method includes: reserving longer CSI calculation time for AI-based CSI reporting.

[0595] As an embodiment, benefits of the above method include: better support for AI models and calculations, improving the accuracy and effectiveness of CSI reporting.

[0596] As an embodiment, whether the first parameter depends on the first capability parameter depends on whether the generation mode of the target CSI is based on AI; only when the generation mode of the target CSI is based on AI, the first parameter depends on the first capability parameter.

[0597] As an embodiment, when the generation mode of the target CSI is based on AI, the first parameter depends on the first capability parameter; when the generation mode of the target CSI is not based on AI, the first parameter depends on the second capability parameter; the first capability parameter and the second capability parameter are both capability parameters reported by the first node.

[0598] As an embodiment, when the generation mode of the target CSI is based on AI, the first parameter depends on the first capability parameter and the second capability parameter; when the generation mode of the target CSI is not based on AI, the first parameter only depends on the second capability parameter; the first capability parameter and the second capability parameter are both capability parameters reported by the first node.

[0599] As an embodiment, the first capability parameter and the second capability parameter represent different capability parameters reported by the first node.

[0600] As an embodiment, the first capability parameter represents an AI-related capability parameter reported by the first node.

[0601] As an embodiment, the second capability parameter indicates a capability parameter reported by the first node which is not related to AI.

[0602] As an embodiment, the second capability parameter comprises a beamReportTiming IE.

[0603] As an embodiment, the second capability parameter comprises a beamSwitchTiming IE.

[0604] As an embodiment, the second capability parameter comprises a codebookType IE.

[0605] As an embodiment, the second capability parameter comprises a beamReportTiming IE and a beamSwitchTiming IE.

[0606] As an embodiment, the second capability parameter comprises at least one of a codebookType IE, a beamReportTiming IE and a beamSwitchTiming IE.

[0607] As an embodiment, the method further comprises: considering UE capability information when determining the first time interval; and considering different UE capability information for AI-based and AI-agnostic CSI reporting.

[0608] As an embodiment, the method has the advantage of enhancing the reliability and robustness of the system.

[0609] Example 7

[0610] Embodiment 7 illustrates a schematic diagram of N information blocks and N time units according to an embodiment of the present application; as shown in FIG. 7. Figure 7 In Embodiment 7, information block #1, …, information block #N are N information blocks; time unit #1, …, time unit #N are N time units. Figure 7

[0611] In Embodiment 7, when the generation manner of the target CSI is AI-based, the target CSI comprises N information blocks, the N information blocks respectively comprise channel information of N time units, N is a positive integer greater than 1; the first time interval depends on at least one of the N time units.

[0612] As an embodiment, the target CSI comprises N information blocks, the N information blocks respectively comprise CSI of N time units, N is a positive integer greater than 1; the generation of any information block in the N information blocks depends on measurement based on the first resource set. ​

[0613] As an embodiment, the N information blocks respectively comprise predicted CSI of N time units.

[0614] As an embodiment, the N information blocks respectively comprise predicted beam information of N time units.

[0615] As an embodiment, the N information blocks respectively comprise compressed CSI of N time units.

[0616] As an embodiment, any information block of the N information blocks indicates at least one resource in the first resource set.

[0617] As an embodiment, the essence of the above method comprises: supporting joint reporting of CSI of multiple time units.

[0618] As an embodiment, the essence of the above method comprises: supporting an AI-based CSI prediction or compression scheme.

[0619] As an embodiment, the benefits of the above method comprise: reducing system overhead and information feedback delay, and enhancing transmission efficiency of the system.

[0620] As an embodiment, the benefits of the above method comprise: improving accuracy and real-time performance of CSI reporting, and improving overall performance of the system.

[0621] As an embodiment, the target CSI comprises a plurality of information blocks, and the number of information blocks included in the target CSI is not less than the N.

[0622] As an embodiment, the target CSI comprises a plurality of information blocks, and the plurality of information blocks included in the target CSI comprise the N information blocks.

[0623] As an embodiment, one time unit comprises one or more slots.

[0624] As an embodiment, one time unit comprises one or more subframes.

[0625] As an embodiment, one time unit comprises a plurality of consecutive symbols.

[0626] As an embodiment, the N time units are orthogonal to each other.

[0627] As an embodiment, the N time units are different from each other.

[0628] As an embodiment, there are two time units in the N time units that overlap.

[0629] As an embodiment, the N time units are consecutive.

[0630] As one embodiment, the N time units are equally spaced.

[0631] As one embodiment, the interval between any two adjacent time units of the N time units is P time units, where P is a positive integer.

[0632] As one embodiment, the benefits of the above method include: preserving existing system design and standards.

[0633] As one embodiment, the benefits of the above method include: enhancing flexibility and robustness of the system.

[0634] In general, how the first node determines the N or at least one of the N time units is up to the hardware vendor, and some non-limiting embodiments are described as follows:

[0635] As one embodiment, the first node determines the N time units based on channel variation.

[0636] As one embodiment, the first node determines the N time units based on time correlation of the channel.

[0637] As one embodiment, the first node determines the N time units based on moving speed.

[0638] As one embodiment, the first node determines the N time units based on at least one of channel variation, time correlation of the channel, or moving speed.

[0639] As one embodiment, the first node determines the N time units to be time units with fast channel variation (e.g., variation greater than a threshold).

[0640] As one embodiment, the first node determines the N time units based on its moving speed.

[0641] As one embodiment, the first node determines the N time units to be time units with low time correlation (e.g., lower than a threshold).

[0642] As one embodiment, the first time interval depending on at least one of the N time units includes: the first time interval depending on a target time unit of the N time units.

[0643] As one embodiment, the target time unit is the earliest one of the N time units.

[0644] As one embodiment, the target time unit is the latest one of the N time units.

[0645] As one embodiment, the target time unit is a designated one of the N time units.

[0646] As one embodiment, the first time interval depending on a target time unit of the N time units comprises: the first time interval depending on a time interval between the target time unit and a last symbol of the first PDCCH.

[0647] As one embodiment, the first time interval depending on a time interval between the target time unit and a last symbol of the first PDCCH comprises: the first time interval depending on a time interval between a start symbol of the target time unit and a last symbol of the first PDCCH.

[0648] As one embodiment, the first time interval depending on at least one of the N time units comprises: the first time interval depending on a target symbol of the N time units.

[0649] As one embodiment, the target symbol is an earliest one of the N time units.

[0650] As one embodiment, the target symbol is a latest one of the N time units.

[0651] As one embodiment, the target symbol is a designated one of the N time units.

[0652] As one embodiment, the first time interval depending on a target symbol of the N time units comprises: the first time interval depending on a time interval between the target symbol and a last symbol of the first PDCCH.

[0653] As one embodiment, the above method has the benefit of enhancing flexibility of the system.

[0654] As one embodiment, the above method has the benefit of making small changes to existing standards and system design.

[0655] As one embodiment, the first time interval depending on at least one of the N time units comprises: the first time interval depending on the N.

[0656] As an embodiment, the first time interval depending on the N comprises: the N belongs to one of V1 candidate value ranges, any candidate value range of the V1 candidate value ranges comprises one or more positive integers, V1 is a positive integer greater than 1; V1 time intervals respectively correspond to the V1 candidate value ranges one by one, the first time interval is one of the V1 time intervals corresponding to the candidate value range to which the N belongs.

[0657] As an embodiment, the first time interval depending on the N comprises: the first time interval depending on a first parameter, the first parameter depending on the N.

[0658] As an embodiment, the first time interval depending on the N comprises: the first time interval and the first parameter are in a linear relationship, the first parameter depending on the N.

[0659] As an embodiment, the first time interval depending on the N comprises: the first time interval and the first parameter are in a linear relationship, the first parameter and the N are in a linear relationship.

[0660] As an embodiment, the first parameter depending on the N comprises: the N belongs to one of V1 candidate value ranges, any candidate value range of the V1 candidate value ranges comprises one or more positive integers, V1 is a positive integer greater than 1; V1 candidate values of the first parameter respectively correspond to the V1 candidate value ranges one by one, the first parameter is one of the V1 candidate values of the first parameter corresponding to the candidate value range to which the N belongs.

[0661] As an embodiment, the essence of the above method comprises: CSI calculation time depending on the amount of information carried by CSI reporting or the number of time units targeted by CSI reporting.

[0662] As an embodiment, the benefits of the above method comprise: more accurate setting of CSI calculation time, effective use of system resources, and improvement of the accuracy and real-time performance of CSI reporting.

[0663] As an embodiment, the benefits of the above method comprise: enhancing the flexibility of the system and the overall performance of the system.

[0664] As an embodiment, the first time interval depending on at least one of the N time units comprises: the first time interval depending on the length of the N time units.

[0665] As an embodiment, the first time interval depending on the length of the N time units comprises: the first time interval and the length of the N time units are in a linear relationship.

[0666] As an embodiment, the first time interval depending on the length of the N time units comprises that the length of the N time units belongs to one of V1 candidate value ranges, any candidate value range of the V1 candidate value ranges comprises one or more real numbers or integers, V1 is a positive integer greater than 1; V1 time intervals respectively correspond to the V1 candidate value ranges one by one, and the first time interval is one of the V1 time intervals corresponding to the candidate value range to which the length of the N time units belongs.

[0667] As an embodiment, the first time interval depending on the length of the N time units comprises that the first time interval depends on a first parameter, and the first parameter depends on the length of the N time units.

[0668] As an embodiment, the first time interval depending on the length of the N time units comprises that the first time interval and a first parameter are in a linear relationship, and the first parameter and the length of the N time units are in a linear relationship.

[0669] As an embodiment, the essence of the above method comprises that the CSI calculation time depends on the length of the time unit to which the CSI reporting is directed.

[0670] As an embodiment, the advantage of the above method comprises that the CSI calculation time is more accurately set, system resources are effectively utilized, and the accuracy and real-time performance of CSI reporting are improved.

[0671] As an embodiment, the advantage of the above method comprises that the flexibility of the system and the overall performance of the system are enhanced.

[0672] Example 8

[0673] Embodiment 8 is a schematic diagram of a second symbol and a second reference symbol according to an embodiment of the present application; as shown in FIG. 8. Figure 8 In the embodiment, RS#1, …, RS#n, … are one or more aperiodic RS resources in the first resource set. Figure 8

[0674] In Embodiment 8, when the first resource set is composed of one or more aperiodic RS resources, the first condition further comprises that the second symbol is not earlier than a second reference symbol, and the second reference symbol is a next uplink symbol whose CP starts after a second time interval from the end of the last symbol of the first RS in the first resource set.

[0675] As an embodiment, the first RS is the latest aperiodic RS in time in the first resource set.

[0676] ​As one embodiment, the first RS is the earliest in time of the aperiodic RSs in the first resource set.

[0677] As one embodiment, the first RS is the latest or earliest in time of the aperiodic RSs in the first resource set.

[0678] As one embodiment, the first resource set consists of one or more aperiodic RS resources, and the first RS is one of the first resource set triggered by the first DCI.

[0679] As one embodiment, the first resource set consists of one or more aperiodic RS resources, and the first RS is the latest in time of the first resource set triggered by the first DCI.

[0680] As one embodiment, the first resource set consists of one or more aperiodic RS resources, and the first RS is the latest or earliest in time of the first resource set triggered by the first DCI.

[0681] As one embodiment, the above method has the benefits of preserving existing system design and standards, and enhancing system consistency.

[0682] Typically, the second symbol takes into account timing advance.

[0683] Typically, both the second symbol and the second reference symbol take into account timing advance.

[0684] As one embodiment, the second symbol is the first uplink symbol in the first PUSCH for carrying the at least one CSI.

[0685] As one embodiment, the at least one CSI includes only one CSI, the at least one CSI is the target CSI, the at least one CSI reporting configuration is the target CSI reporting configuration, and the first symbol is the second symbol.

[0686] As one embodiment, the at least one CSI includes multiple CSIs, the at least one CSI reporting configuration includes multiple CSI reporting configurations, the multiple CSI reporting configurations are respectively used for configuring the multiple CSIs, and the first symbol is the same as or different from the second symbol.

[0687] As one embodiment, the second reference symbol is Z'ref (n), the Z' ref The specific meaning of (n) refers to the 5.4 section of 3GPP TS 38.214.

[0688] Typically, the second reference symbol is the next uplink symbol after the end of the last symbol of the first RS in the first resource set by a second time interval includes: the second reference symbol is the earliest uplink symbol later than the last symbol of the first RS in the first resource set and satisfies a reference condition, the reference condition includes that the time interval between the end of the last symbol of the first RS in the first resource set and the second reference symbol is not less than the second time interval.

[0689] As an embodiment, the second time interval is a real number or an integer.

[0690] As an embodiment, the unit of the second time interval is millisecond (ms).

[0691] As an embodiment, the unit of the second time interval is symbol.

[0692] As an embodiment, the second time interval is T' proc，CSI , the T' proc，CSI The specific meaning of (n) refers to the 5.4 section of 3GPP TS 38.214.

[0693] As an embodiment, the second time interval is (Z'(2048+144)·κ2 -μ ·T C , wherein the specific meaning of Z', κ, μ, T C The specific meaning of (n) refers to the 5.4 section of 3GPP TS 38.214.

[0694] As an embodiment, the benefits of the above method include: maintaining the existing system design and standard, and enhancing the consistency of the system.

[0695] As an embodiment, the first condition not being satisfied includes: when the first symbol is earlier than the first reference symbol, or the second symbol is earlier than the second reference symbol, the first condition is not satisfied; when the first symbol is not earlier than the first reference symbol and the second symbol is not earlier than the second reference symbol, the first condition is satisfied.

[0696] As an embodiment, the first set of resources consists of one or more aperiodic RS resources; the first condition not being satisfied includes: the first condition not being satisfied when the first symbol is earlier than the first reference symbol, or the second symbol is earlier than the second reference symbol; the first condition being satisfied when the first symbol is not earlier than the first reference symbol and the second symbol is not earlier than the second reference symbol.

[0697] As an embodiment, the above method has the benefit of: small modification to existing system and standard.

[0698] As an embodiment, the above method has the benefit of: enhancing the reliability and robustness of the system.

[0699] Example 9

[0700] Embodiment 9 illustrates a schematic diagram of a first operation according to an embodiment of the present application; as shown in FIG. 9. Figure 9

[0701] In Embodiment 9, the manner of generating the target CSI based on AI includes: the manner of generating the target CSI includes performing a first operation, an input of the first operation depends on a measurement based on the first set of resources, and the target CSI depends on an output of the first operation.

[0702] As an embodiment, the first operation is based on training or AI.

[0703] As an embodiment, the first operation is obtained by training.

[0704] As an embodiment, the first operation is based on a neural network.

[0705] As an embodiment, the first operation includes an AI entity.

[0706] As an embodiment, the first operation includes a part of an AI entity.

[0707] As an embodiment, the first operation includes a part of an AI entity for inference.

[0708] As an embodiment, the first operation is performed by an AI entity.

[0709] As an embodiment, the first operation is performed by an AI function.

[0710] ​As one embodiment, the AI function includes at least one of an AI inference function, an AI training function, an AI management function.

[0711] As one embodiment, the training for obtaining the first operation is performed by the first node.

[0712] As one embodiment, the training for obtaining the first operation is performed by an MDA function (Management Data Analytics Function).

[0713] As one embodiment, the training for obtaining the first operation is performed by an MDAS (Management Data Analytics Service) producer.

[0714] As one embodiment, the training for obtaining the first operation is performed by a NWDAF (Network Data Analytics Function).

[0715] As one embodiment, the training for obtaining the first operation is performed by a core network.

[0716] As one embodiment, the training for obtaining the first operation is performed by an AI training producer.

[0717] As one embodiment, the first operation includes inference.

[0718] As one embodiment, the first operation is AI inference.

[0719] As one embodiment, the first operation includes AI inference for CSI.

[0720] As one embodiment, the first operation is AI inference for CSI.

[0721] As one embodiment, the first operation includes AI inference for at least one of beam prediction, CSI prediction, CSI estimation, or CSI compression.

[0722] As one embodiment, the benefits of the above method include improved performance of measurement and reporting of CSI (including beam), including more accurate CSI, lower reference signal overhead and reporting overhead, thus improving overall system performance.

[0723] As one embodiment, the benefits of the above method include more accurate and complete CSI, lower reference signal overhead, improved real-time performance of CSI.

[0724] As one embodiment, the first operation is a deployment.

[0725] As one embodiment, the first operation is obtained by a load.

[0726] As one embodiment, the first operation is obtained from a serving cell of the first node.

[0727] As one embodiment, the first operation is obtained from a maintenance base station of the serving cell of the first node.

[0728] As one embodiment, the first operation is obtained from a core network.

[0729] As one embodiment, the first operation includes one or more of a convolution, a pooling, a concatenation, and an activation.

[0730] As one embodiment, the first operation includes at least one of a fully connected layer, a pooling layer, at least one convolution layer, and at least one encoding layer.

[0731] As one embodiment, an encoding layer includes at least one convolution layer and a pooling layer.

[0732] As one embodiment, in a convolution layer, at least one convolution kernel is used to convolve an input to generate a corresponding feature map, at least one feature map output by the convolution layer is reshaped into a vector input to a fully connected layer; the fully connected layer converts the one vector into an output.

[0733] As one embodiment, some or all of a convolution kernel size, a number of convolution layers, a convolution step, a pooling kernel size, a pooling kernel step, a pooling function, an activation function, and a number of feature maps of the first operation are obtained by training.

[0734] As one embodiment, some or all of a convolution kernel, a pooling kernel, a pooling function, an activation function, a parameter of the pooling function, and a parameter of the activation function of the first operation are obtained by training.

[0735] As one embodiment, the first operation includes a pre-processing.

[0736] As one embodiment, the pre-processing includes one or more of a matrix decomposition, a matrix transformation, and a projection.

[0737] As one embodiment, the pre-processing includes one or more of a quantization, a spatial-to-angle domain transformation, an angle-to-spatial domain transformation, a frequency-to-time domain transformation, and a time-to-frequency domain transformation.

[0738] As one embodiment, the pre-processing includes at least one of truncation and / or padding, DFT (Discrete Fourier Transform), mapping, and labeling.

[0739] As one embodiment, the first operation includes post-processing.

[0740] As one embodiment, the post-processing includes at least one of DFT (Discrete Fourier Transform), quantization, truncation and / or padding.

[0741] As one embodiment, the post-processing includes one or more of angle domain to spatial domain transformation, spatial domain to angle domain transformation, time domain to frequency domain transformation, and frequency domain to time domain transformation.

[0742] As one embodiment, the measurement based on the first set of resources includes pre-compression channel information, and the output of the first operation includes post-compression channel information.

[0743] As one embodiment, the benefits of the above method include: being applicable to channel compression, saving feedback overhead.

[0744] As one embodiment, the measurement based on the first set of resources includes measured channel information, and the output of the first operation includes predicted channel information.

[0745] As one embodiment, the measurement based on the first set of resources includes measured channel information, and the output of the first operation includes spatial beam prediction.

[0746] As one embodiment, the benefits of the above method include: reducing RS resource overhead, and reducing feedback delay.

[0747] As one embodiment, the measurement based on the first set of resources includes historic channel information, and the output of the first operation includes predicted channel information.

[0748] As one embodiment, the measurement based on the first set of resources includes historic channel information, and the output of the first operation includes Temporal beam prediction.

[0749] As one embodiment, the benefits of the above method include: reducing channel information feedback delay, and improving real-time performance of channel information acquisition.

[0750] As one embodiment, the measurement based on the first set of resources comprises current channel information, and the output of the first operation comprises channel information after a period of time.

[0751] As one embodiment, the benefits of the above method comprise: improving CSI accuracy and real-time, reducing RS overhead.

[0752] As one embodiment, the measurement based on the first set of resources comprises incomplete channel information, and the output of the first operation comprises complete channel information.

[0753] As one embodiment, the benefits of the above method comprise: reducing RS overhead, improving CSI accuracy and completeness.

[0754] As one embodiment, the measurement based on the first set of resources comprises channel information of P1 antenna ports, and the output of the first operation comprises channel information of P2 antenna ports, wherein P1 and P2 are positive integers greater than 1, and P1 is less than P2.

[0755] As one sub-embodiment of the above embodiment, the P1 antenna ports are a proper subset of the P2 antenna ports.

[0756] As one sub-embodiment of the above embodiment, the P2 antenna ports belong to the second set of resources.

[0757] As one embodiment, the input of the first operation further comprises the second set of resources.

[0758] As one embodiment, the output of the first operation comprises one or more of beam indication, CRI (CSI-RS Resource Indicator), SS / PBCH Block Resource indicator (SSBRI), or RSRP (reference signal received power).

[0759] As one embodiment, the output of the first operation comprises one or more of PMI, CRI, CQI, RI, LI, SSBRI, RSRP, SINR, capability index and TDCP.

[0760] As one embodiment, the output of the first operation comprises one or more of channel impulse response, small-scale characteristics, channel matrix.

[0761] As an embodiment, the output of the first operation comprises one or more of a delay spread, a Doppler spread, a Doppler shift, a mean delay, and a mean gain.

[0762] As an embodiment, the output of the first operation comprises the target CSI.

[0763] As an embodiment, the input of the first operation is dependent on measurements based on the first set of resources.

[0764] As an embodiment, the generation of the target CSI is based on AI, and the input of the first operation is dependent on measurements based on the first set of resources.

[0765] As an embodiment, the input of the first operation being dependent on measurements based on the first set of resources comprises that measurements (channel measurements and / or interference measurements) based on the first set of resources are used to generate the input of the first operation.

[0766] As an embodiment, the target CSI is dependent on the output of the first operation.

[0767] As an embodiment, the target CSI being dependent on the output of the first operation comprises that the target CSI comprises the output of the first operation.

[0768] As an embodiment, the target CSI being dependent on the output of the first operation comprises that the target CSI comprises a post-processed output of the first operation.

[0769] As an embodiment, the target CSI being dependent on the output of the first operation comprises that the output of the first operation is used to generate the target CSI.

[0770] As an embodiment, the target CSI being dependent on the output of the first operation comprises that the output of the first operation, after being post-processed, is used to generate the target CSI.

[0771] As an embodiment, the input of the first operation is dependent on measurements based on the first set of resources, and the target CSI is dependent on the output of the first operation.

[0772] As an embodiment, the generation of the target CSI comprises performing a first operation, the input of the first operation is dependent on measurements based on the first set of resources, and the target CSI is dependent on the output of the first operation.

[0773] As an embodiment, the benefits of the above method comprise supporting AI-based schemes and improving the accuracy and real-time performance of information reporting.

[0774] As an embodiment, the benefits of the above method include: improving the overall performance of the system.

[0775] As an embodiment, the first operation is associated to the first type of identification.

[0776] As an embodiment, the target CSI reporting configuration indicates the first type of identification, and the first operation is associated to the first type of identification.

[0777] As an embodiment, an AI model used by the first operation is identified by the first type of identification.

[0778] As an embodiment, an AI entity or AI function to which the first operation belongs is identified by the first type of identification.

[0779] As an embodiment, an AI entity or AI function that performs the first operation is identified by the first type of identification.

[0780] As an embodiment, the benefits of the above method include: identifying an AI model / entity / function by the first type of identification, simplifying the design and unifying the understanding of different AI entities / functions among multiple nodes.

[0781] As an embodiment, the first type of identification is used to identify or indicate a set of reference resources, and measurements on the set of reference resources are used to obtain a training dataset for the first operation.

[0782] As an embodiment, the first type of identification is used to identify configuration information of a set of reference resources, and measurements on the set of reference resources are used to obtain a training dataset for the first operation.

[0783] As an embodiment, the training used to obtain the first operation is identified by the first type of identification.

[0784] As an embodiment, a dataset used for training of the first operation is identified by the first type of identification.

[0785] As an embodiment, the target CSI reporting configuration indicates the first operation by indicating the first type of identification.

[0786] As an embodiment, the benefits of the above method include: identifying the inference generated by an AI training or AI training dataset by identifying the AI training or AI training dataset, establishing consensus among different AI functions, and further simplifying the design.

[0787] Example 10

[0788] Embodiment 10 illustrates a schematic diagram of a first type of identification according to an embodiment of the present application; as shown inFigure 10 As shown.

[0789] In embodiment 10, the generation manner of the target CSI is based on AI, including that the generation manner of the target CSI is associated with a first type of identifier.

[0790] As an embodiment, the first type of identifier is a non-negative integer.

[0791] As an embodiment, the first type of identifier is a string.

[0792] As an embodiment, the first type of identifier is a model identifier.

[0793] As an embodiment, the first type of identifier is used to identify an AI model, an AI entity or an AI function.

[0794] As an embodiment, the first type of identifier is used by the first node to determine an AI model, an AI entity or an AI function.

[0795] As an embodiment, the target CSI reporting configuration indicates the use of an AI model, an AI entity or an AI function by indicating the first type of identifier.

[0796] As an embodiment, the above method has the benefits of identifying an AI model, an AI entity or an AI function through the first type of identifier, simplifying system design, and unifying the understanding of different AI models, AI entities or AI functions among multiple nodes.

[0797] As an embodiment, the first type of identifier is used to identify or indicate a resource set.

[0798] As an embodiment, the first type of identifier is used to identify or indicate a resource set, and the measurement of the resource set is used to obtain a training data set.

[0799] As an embodiment, the first type of identifier is used to identify or indicate a training data set.

[0800] As an embodiment, the above method has the benefits of identifying an AI training or an AI training data set, recognizing the inference generated by this AI training or AI training data set, establishing consensus among different AI functions, and further simplifying system design.

[0801] As an embodiment, the generation manner of the target CSI is associated with the first type of identifier includes that the generation of the target CSI is associated with the first type of identifier through the target CSI reporting configuration.

[0802] As an embodiment, the target CSI generation manner being associated to the first type of identity comprises: the target CSI reporting configuration indicating the first type of identity; and the target CSI reporting configuration indicating the target CSI generation.

[0803] As an embodiment, the target CSI generation manner being associated to the first type of identity comprises: the target CSI generation manner comprising performing a first operation, an input of the first operation depending on measurement based on the first resource set, the target CSI depending on an output of the first operation, and the first operation being associated to the first type of identity.

[0804] As an embodiment, the above method has the benefit of supporting AI-based CSI reporting.

[0805] As an embodiment, the target CSI generation manner being associated to the first type of identity comprises: the target CSI generation manner using an AI model identified by the first type of identity.

[0806] As an embodiment, the target CSI generation manner being associated to the first type of identity comprises: an AI entity identified by the first type of identity generating the target CSI.

[0807] As an embodiment, the target CSI generation manner being associated to the first type of identity comprises: the target CSI being generated by an AI entity, and the first type of identity being used to identify the AI entity or a function.

[0808] As an embodiment, the target CSI generation manner being associated to the first type of identity comprises: the target CSI generation manner belonging to an AI function, and the first type of identity being used to identify the AI function.

[0809] As an embodiment, the target CSI generation manner not being associated to the first type of identity comprises: the target CSI generation manner comprising a first operation performed by a target receiver of the target CSI reporting configuration, an input of the first operation depending on measurement based on the first resource set, the target CSI depending on an output of the first operation, and the first operation not being associated to the first type of identity.

[0810] As an embodiment, the target CSI generation manner not being associated to the first type of identity comprises: the target CSI generation manner not using an AI model identified by the first type of identity.

[0811] As an embodiment, the target CSI generation manner not being associated to the first type of identity comprises: an AI entity identified by the first type of identity not being used to generate the target CSI.

[0812] As an embodiment, the first type of identification to which the generation manner of the target CSI is associated includes: the target CSI is generated by an AI entity, and the first type of identification is not used to identify the AI entity or a function.

[0813] As an embodiment, the first type of identification to which the generation manner of the target CSI is associated includes: the generation manner of the target CSI belongs to an AI function, and the first type of identification is not used to identify the AI function.

[0814] As an embodiment, the above method has the benefits of: simplifying system design, and reducing the implementation complexity of the scheme.

[0815] As an embodiment, the above method has the benefits of: improving the flexibility of the system, and adapting to different transmission and application scenarios.

[0816] Example 11

[0817] Embodiment 11 illustrates a schematic diagram of a first time interval and a first type of identification relationship according to an embodiment of the present application; as shown in FIG. 11. Figure 11 As an embodiment, the first time interval is dependent on the first type of identification to which the generation manner of the target CSI is associated.

[0818] In embodiment 11, when the generation manner of the target CSI is based on AI, the first time interval is dependent on the first type of identification to which the generation manner of the target CSI is associated.

[0819] As an embodiment, the first type of identification to which the generation manner of the target CSI is associated belongs to one of V identification sets, any identification set of the V identification sets includes one or more first types of identification, and V is a positive integer greater than 1; the first reference symbol is dependent on the identification set to which the first type of identification belongs.

[0820] As an embodiment, the first type of identification to which the generation manner of the target CSI is associated belongs to one of V identification sets, any identification set of the V identification sets includes one or more first types of identification, and V is a positive integer greater than 1; the first time interval is dependent on the identification set to which the first type of identification belongs.

[0821] As an embodiment, the calculation formula of the first time interval is dependent on the first type of identification to which the generation manner of the target CSI is associated.

[0822] As an embodiment, the first type of identifier is a first type of identifier associated to a generation manner of the target CSI, the first type of identifier belongs to one of V identifier sets, any identifier set of the V identifier sets comprises one or more first type of identifiers, and V is a positive integer greater than 1; and the calculation formula of the first time interval depends on the identifier set to which the first type of identifier belongs.

[0823] As an embodiment, the first type of identifier is a first type of identifier associated to a generation manner of the target CSI, the first type of identifier belongs to one of V identifier sets, any identifier set of the V identifier sets comprises one or more first type of identifiers, and V is a positive integer greater than 1; and the calculation formula of the first time interval comprises V formulas, the V formulas and the V identifier sets correspond to each other, and the calculation formula of the first time interval is the calculation formula corresponding to the identifier set to which the first type of identifier belongs.

[0824] As an embodiment, the first time interval depends on the first parameter, and the first parameter depends on the first type of identifier associated to the generation manner of the target CSI.

[0825] As an embodiment, the first time interval and the first parameter are in a linear relationship, and the first parameter depends on the first type of identifier associated to the generation manner of the target CSI.

[0826] As an embodiment, the first time interval and the first parameter are in a linear relationship; the first parameter belongs to one of V candidate value ranges, any candidate value range of the V candidate value ranges comprises one or more integers or real numbers, V is a positive integer greater than 1; the first type of identifier belongs to one of V identifier sets, any identifier set of the V identifier sets comprises one or more first type of identifiers, V is a positive integer greater than 1; the V candidate value ranges and the V identifier sets correspond to each other, and the first parameter is a candidate value in the candidate value range corresponding to the identifier set to which the first type of identifier belongs among the V candidate value ranges.

[0827] As an embodiment, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch , wherein the specific meanings of the Z, the κ, the μ, the T C , and the T switch refer to the 5.4 chapter of 3GPP TS 38.214; and the Z depends on the first type of identifier associated to the generation manner of the target CSI.

[0828] As an embodiment, the first time interval is (Z)(2048+144)·κ2 -μ ·T C +T switch +W, wherein the Z, the κ, the μ, the T C and the T switch refer to the 5.4 section of 3GPP TS 38.214; the W depends on the first type identifier associated to the generation manner of the target CSI.

[0829] As an embodiment, the essence of the above method includes: setting different CSI calculation times for CSI reporting associated to different first type identifiers.

[0830] As an embodiment, the essence of the above method includes: considering the influence of unused AI models, AI entities or AI functions when setting CSI calculation time.

[0831] As an embodiment, the benefits of the above method include: better support for AI models and calculations, and improved accuracy and effectiveness of CSI reporting.

[0832] As an embodiment, the benefits of the above method include: improving the overall performance of the system.

[0833] Example 12

[0834] Embodiment 12 illustrates a schematic diagram of a second resource set according to an embodiment of the present application; as shown in the accompanying Figure 12 In the embodiment 12, resource #1, …, resource #m, … are at least one resource in the second resource set. Figure 12

[0835] In the embodiment 12, the generation manner of the target CSI based on AI includes: the target CSI indicates at least one resource in the second resource set, and the second resource set includes resources not belonging to the first resource set.

[0836] As an embodiment, the second resource set includes the first resource set and resources outside the first resource set.

[0837] As an embodiment, the first resource set includes one or more RS resources, the second resource set includes one or more RS resources, and the second resource set includes RS resources in the first resource set and RS resources outside the first resource set.

[0838] As an embodiment, the number of resources included in the first resource set is less than the number of resources included in the second resource set.

[0839] ​As an embodiment, the second set of resources comprises resources not belonging to the first set of resources, the resources in the second set of resources comprise at least one of an antenna port, a TCI state, QCL information, a frequency resource, a time-frequency code resource, a beam, a RS resource, a vector, or a matrix.

[0840] As an embodiment, the second set of resources comprises at least one training dataset.

[0841] As an embodiment, the second set of resources comprises one or more RS (Reference Signal) resource sets, one RS resource set comprising one or more RS resources.

[0842] As an embodiment, the second set of resources comprises at least one of at least one CSI-RS resource set, at least one CSI-SSB resource set, or at least one CSI-IM resource set.

[0843] As an embodiment, the second set of resources comprises one or more RS resources, any RS resource in the second set of resources being a CSI-RS resource or a synchronization signal resource.

[0844] As an embodiment, the target CSI reporting configuration comprises at least one resource configuration, the at least one resource configuration indicating the first set of resources and the second set of resources.

[0845] As an embodiment, the target CSI reporting configuration indicates one resource configuration, the one resource configuration indicating the first set of resources and the second set of resources.

[0846] As an embodiment, the target CSI reporting configuration indicates two resource configurations, the two resource configurations respectively indicating the first set of resources and the second set of resources.

[0847] As an embodiment, the target CSI reporting configuration indicates configuration information of the second set of resources.

[0848] As an embodiment, the target CSI reporting configuration indicates an identity of the second set of resources.

[0849] As an embodiment, the target CSI reporting configuration indicates a first type of identity, the second set of resources depending on the first type of identity.

[0850] As an embodiment, the second set of resources depending on the first type of identity comprises that the first type of identity is used to identify the second set of resources.

[0851] As an embodiment, the second resource set depending on the first type of indication comprises that the first type of indication is used to identify a reference resource set, and the reference resource set comprises the second resource set.

[0852] As an embodiment, the second resource set depending on the first type of indication comprises that the first type of indication is used to identify a reference resource set, and the reference resource set comprises the second resource set, and the target CSI reporting configuration is used to indicate the second resource set from the reference resource set.

[0853] As an embodiment, information other than the target CSI reporting configuration indicates the second resource set.

[0854] As an embodiment, the information other than the target CSI reporting configuration indicating the second resource set comprises a higher layer parameter.

[0855] As an embodiment, the information other than the target CSI reporting configuration indicating the second resource set comprises an RRC parameter.

[0856] As an embodiment, the information other than the target CSI reporting configuration indicating the second resource set comprises a MAC CE.

[0857] As an embodiment, the information other than the target CSI reporting configuration indicating the second resource set comprises DCI (downlink control information).

[0858] As an embodiment, the generation manner of the target CSI is based on AI, and the first node is not required to measure the second resource set.

[0859] As an embodiment, the generation manner of the target CSI is based on AI, the first resource set is used for measurement, and the second resource set is used for prediction.

[0860] As an embodiment, the generation manner of the target CSI is based on AI, the first resource set is used for measurement, and the second resource set is used for prediction.

[0861] As an embodiment, the generation manner of the target CSI is based on AI, and only the first resource set in the first resource set and the second resource set is used for measurement.

[0862] As one embodiment, the first set of resources and only the first set of resources of the second set of resources being used for measurement comprises: only the first set of resources of the first set of resources and the second set of resources being used for measurement by the first node.

[0863] As one embodiment, the first set of resources and only the first set of resources of the second set of resources being used for measurement comprises: the first set of resources being used for measurement by the first node, the first node not being required to measure part or all of the second set of resources.

[0864] As one embodiment, the first node not being required to measure the second set of resources comprises: the first node not measuring part or all of the second set of resources.

[0865] As one embodiment, the first node not being required to measure the second set of resources comprises: whether the first node measures part or all of the second set of resources being implementation dependent or self-determined by the first node.

[0866] Example 13

[0867] Embodiment 13 illustrates a diagram of the first condition not being satisfied according to one embodiment of the application; as shown in FIG. 13. Figure 13

[0868] In Embodiment 13, the first DCI is ignored when the first condition is not satisfied; wherein no HARQ-ACK or transport block is multiplexed on the first PUSCH.

[0869] As one embodiment, the when the first condition is not satisfied comprises: when the first symbol is earlier than the first reference symbol.

[0870] As one embodiment, the when the first condition is not satisfied comprises: when the second symbol is earlier than the second reference symbol.

[0871] As one embodiment, the when the first condition is not satisfied comprises: when the first symbol is earlier than the first reference symbol or the second symbol is earlier than the second reference symbol.

[0872] As one embodiment, no HARQ-ACK or transport block is multiplexed on the first PUSCH; the first DCI is ignored when the first condition is not satisfied.

[0873] ​As one embodiment, the first set of resources consists of one or more aperiodic RS resources; no HARQ-ACK or transport block is multiplexed on the first PUSCH; the first node ignores the first DCI when the first condition is not satisfied.

[0874] As one embodiment, the first set of resources consists of one or more periodic or semi-persistent RS resources; the first node ignores the first DCI when the first condition is not satisfied; wherein no HARQ-ACK or transport block is multiplexed on the first PUSCH.

[0875] As one embodiment, the first set of resources consists of one or more periodic or semi-persistent RS resources; the first processor ignores the first DCI when the first condition is not satisfied; wherein no HARQ-ACK or transport block is multiplexed on the first PUSCH.

[0876] As one embodiment, HARQ-ACK or transport block is multiplexed on the first PUSCH; the target CSI is transmitted on the first PUSCH and the target CSI is not updated when the first condition is not satisfied.

[0877] As one embodiment, the first set of resources consists of one or more aperiodic RS resources; HARQ-ACK or transport block is multiplexed on the first PUSCH; the target CSI is transmitted on the first PUSCH and the target CSI is not updated when the first condition is not satisfied.

[0878] As one embodiment, the first node ignores the first DCI or the target CSI is transmitted on the first PUSCH and the target CSI is not updated when the first condition is not satisfied.

[0879] As one embodiment, the first processor ignores the first DCI or the target CSI is transmitted on the first PUSCH and the target CSI is not updated when the first condition is not satisfied.

[0880] As one embodiment, the ignoring the first DCI comprises: dropping transmitting signals on the first PUSCH.

[0881] As one embodiment, the ignoring the first DCI comprises: dropping transmitting the target CSI on the first PUSCH.

[0882] As one embodiment, the ignoring the first DCI includes dropping transmitting the at least one CSI on the first PUSCH.

[0883] As one embodiment, the transmitting the target CSI on the first PUSCH and the target CSI being not updated includes the first node not being expected to transmit the target CSI on the first PUSCH and the target CSI being valid.

[0884] As one embodiment, the transmitting the target CSI on the first PUSCH and the target CSI being not updated includes the first node not being expected to transmit the target CSI on the first PUSCH and the target CSI being updated.

[0885] As one embodiment, the target CSI being not updated includes the first node not being expected to update the target CSI.

[0886] As one embodiment, the target CSI being not updated includes whether the target CSI is actually updated being implementation dependent or self-determined by the first node.

[0887] As one embodiment, the target CSI being not updated includes the target CSI not being valid.

[0888] As one embodiment, the target CSI being not updated includes the target CSI being the same as a latest one of the CSI reported configurations on the target CSI earlier than the first PUSCH.

[0889] As one embodiment, the target CSI being not updated includes the target CSI being irrelevant to a measurement based on a latest RS occasion of a CSI reference resource of the target CSI in the first resource set.

[0890] As one embodiment, the target CSI being not updated includes the target CSI being irrelevant to a measurement based on a latest RS occasion of a CSI reference resource of the target CSI in the first resource set.

[0891] As one embodiment, the target CSI being not updated includes the target CSI not being updated based on a measurement of at least a latest RS occasion of a CSI reference resource of the target CSI in the first resource set.

[0892] As one embodiment, the first set of resources consists of one or more aperiodic RS resources; the target CSI not being updated comprises: the target CSI being independent of measurements based on aperiodic RS resources in the first set of resources triggered by the first DCI.

[0893] As one embodiment, the first set of resources consists of one or more aperiodic RS resources; the target CSI not being updated comprises: the target CSI not being generated based on measurements of aperiodic RS resources in the first set of resources triggered by the first DCI.

[0894] As one embodiment, the first set of resources consists of one or more aperiodic RS resources; the target CSI not being updated comprises: the target CSI not being updated based on measurements of aperiodic RS resources in the first set of resources triggered by the first DCI.

[0895] Example 14

[0896] Embodiment 14 illustrates a schematic diagram of a second operation according to one embodiment of the application; as shown in FIG. 14. Figure 14

[0897] In Embodiment 14, the output of the first operation comprises a first CSI, the target CSI carries the first CSI, and the first CSI is used by a target receiver of the target CSI as input of the second operation to generate a second CSI.

[0898] As one embodiment, the first operation is for CSI compression, the second operation is for CSI recovery, and the first node and the second node employ a two-sided AI model.

[0899] As one embodiment, the target CSI comprises the first CSI.

[0900] As one embodiment, the first CSI is used to generate the target CSI after being post-processed.

[0901] As one embodiment, the first CSI comprises N sub-CSIs, and the N information blocks respectively carry the N sub-CSIs.

[0902] As one embodiment, the first CSI comprises an output of the first operation.

[0903] As one embodiment, the second CSI comprises a recovery of at least part of the input of the first operation.

[0904] ​As one embodiment, the second CSI comprises one or more of a PMI (Precoding Matrix Indicator), a CRI (CSI-RS Resource Indicator), a SS / PBCH Block Resource indicator (SSBRI), a beam indication, a resource indication, a CQI (Channel Quality Indicator), a RI (Rank Indicator), a LI (Layer Indicator), a RSRP (reference signal received power), a SINR (signal-to-noise and interference ratio), a Capability Index, or a TDCP (Time Domain Channel Properties).

[0905] As one embodiment, the second CSI comprises one or more of a channel matrix, an eigenvector, an eigenvalue, or a precoding matrix.

[0906] As one embodiment, the second operation is an inverse operation of the first operation.

[0907] As one embodiment, the second operation is based on training.

[0908] As one embodiment, the training for obtaining the second operation is performed by the target receiver of the target CSI.

[0909] As one embodiment, the training for obtaining the second operation is performed by an MDA function.

[0910] As one embodiment, the training for obtaining the second operation is performed by an MDAS producer.

[0911] As one embodiment, the training for obtaining the second operation is performed by a NWDAF.

[0912] As one embodiment, the training for obtaining the second operation is performed by a core network.

[0913] As one embodiment, the training for obtaining the second operation is performed by an AI (Artificial Intelligence) training producer.

[0914] As one embodiment, the first operation and the second operation are obtained through different training.

[0915] As one embodiment, the first operation and the second operation are obtained through independent training.

[0916] As one embodiment, the benefits of the above method include: saving air interface overhead, having better flexibility, being able to adapt to different terminals, and having better forward compatibility.

[0917] As one embodiment, the first operation and the second operation are obtained through joint training.

[0918] As one embodiment, the benefits of the above method include: optimizing system performance.

[0919] As one embodiment, the training of the second operation depends on the first operation.

[0920] As one embodiment, the producer of the second operation trains the second operation according to the output of the first operation.

[0921] Example 15

[0922] Embodiment 15 illustrates a schematic diagram of a first operation according to another embodiment of the present application; as shown in FIG. 15. In embodiment 15, the first operation includes K1 sub-operations, and K1 is a positive integer not greater than 1. Figure 15

[0923] In embodiment 15, the K1 sub-operations are respectively denoted as sub-operation #0, …, sub-operation #(K1-1).

[0924] As one embodiment, each of the K1 sub-operations is based on training.

[0925] As one embodiment, at least one of the K1 sub-operations is based on training.

[0926] As one embodiment, each of the K1 sub-operations based on training is based on training performed by the same performer.

[0927] As one embodiment, two of the K1 sub-operations are based on training performed by different performers.

[0928] As one embodiment, at least one of the K1 sub-operations is deployment-required.

[0929] ​As one embodiment, at least one of the K1 sub-operations is loading.

[0930] As one embodiment, all loading sub-operations of the K1 sub-operations are loading from the same producer.

[0931] As one embodiment, two loading sub-operations of the K1 sub-operations are loading from different producers.

[0932] As one embodiment, at least one of the K1 sub-operations is not training based.

[0933] As one embodiment, at least one of the K1 sub-operations is based on a codebook for precoding defined in 3GPP R18 or a version before 3GPP R18.

[0934] As one embodiment, one or more of the K1 sub-operations is AI based.

[0935] As one embodiment, one or more of the K1 sub-operations includes inference.

[0936] As one embodiment, one or more of the K1 sub-operations includes AI inference.

[0937] As one embodiment, one or more of the K1 sub-operations includes AI inference for CSI.

[0938] As one embodiment, the AI (Artificial Intelligence) includes ML (Machine Learning).

[0939] As one embodiment, one or more of the K1 sub-operations includes pre-processing.

[0940] As one embodiment, one or more of the K1 sub-operations includes post-processing.

[0941] As one embodiment, two of the K1 sub-operations are serial, as in Figure 15 all sub-operations in 15(a), sub-operation #2 to sub-operation #(K1-1) in 15(b), and sub-operation #0 to sub-operation #(K1-4) in 15(c).

[0942] As one embodiment, two sub-operations being serial means that the output of one of the two sub-operations is used as the input of the other of the two sub-operations.

[0943] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A. Figure 15 Figure 15 As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0944] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0945] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0946] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0947] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0948] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0949] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0950] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0951] As an example, two of the K1 sub-operations are parallel, such as sub-operation #0 and sub-operation #1 in (b), attached hereto as Exhibit A.

[0952] Example 16

[0953] Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A. Figure 16 Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A. Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A.

[0954] Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A. Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A.

[0955] Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A. Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A.

[0956] Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A. Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A.

[0957] Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A. Exhibit 16 illustrates a deployment of a first operation diagram according to an embodiment of the present application; as shown in (a), attached hereto as Exhibit A.

[0958] As one embodiment, the deploying comprises obtaining an AI entity comprising an AI function to perform the first operation.

[0959] As one embodiment, the deploying comprises loading the first operation.

[0960] As one embodiment, the deploying comprises making a request to load the first operation.

[0961] As one embodiment, the request in the Figure 16 is the request to load the first operation made by the first node.

[0962] As one embodiment, the response in the Figure 16 is the response to the request to load the first operation made by the first node.

[0963] As one embodiment, the first operation is obtained from a serving cell of the first node.

[0964] As one embodiment, the first operation is obtained from a maintaining base station of a serving cell of the first node.

[0965] As one embodiment, the first operation is obtained from a core network.

[0966] As one embodiment, the first operation is obtained from a first producer.

[0967] As one embodiment, the first producer provides the first operation to the first node through the response in the Figure 16 .

[0968] As one embodiment, the deploying is done by an AI function.

[0969] As one embodiment, the deploying is done by an AI deployment function.

[0970] As one embodiment, the deploying is done by an AI inference function.

[0971] As one embodiment, the deploying is done by an AI entity.

[0972] As one embodiment, the deploying comprises obtaining the first operation from a first producer.

[0973] As one embodiment, the deploying comprises making a request to load the first operation to a first producer.

[0974] As one embodiment, the deploying comprises loading the first operation from a first producer.

[0975] As one embodiment, the first producer generates and provides at least one of an AL entity and an AL function.

[0976] As one embodiment, the first producer is a producer of the first operation.

[0977] As one embodiment, a sender of the target CSI reporting configuration is the first producer.

[0978] As one embodiment, a sender of the target CSI reporting configuration is different from the first producer.

[0979] As one embodiment, a training for obtaining the first operation is performed by the first producer.

[0980] As one embodiment, a performer of the training for obtaining the first operation is different from the first producer.

[0981] Example 17

[0982] Embodiment 17 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. 17. Figure 17 As shown in FIG. 17, the processing system comprises a third processor, a fourth processor and a fifth processor. Figure 17 (a) comprises the third processor, the fourth processor and the fifth processor, and Figure 17 (b) comprises the third processor, the fourth processor, the fifth processor and a sixth processor.

[0983] In Embodiment 17(a), the third processor sends a first data set to the fourth processor and a second data set to the fifth processor; the fourth processor generates a target first type parameter set according to the first data set, and the fourth processor sends the generated target first type parameter set to the fifth processor; the fifth processor processes the second data set using the target first type parameter set to obtain a first type output. In the attached Figure 17 (a), the first type feedback is optional.

[0984] In embodiment 17(b), the third processor sends a first data set to the fourth processor, and sends a second data set to the fifth processor; the fourth processor generates a target first-type parameter group according to the first data set, and sends the generated target first-type parameter group to the fifth processor; the fifth processor processes the second data set using the target first-type parameter group to obtain a first-type output, and sends the first-type output to the sixth processor. In the following description of embodiment 17(b), the first-type output is also referred to as a first-type result. Figure 17 As an example, in embodiment 17(b), the first-type feedback and the second-type feedback are optional.

[0985] As an example, in embodiment 17(b), the fifth processor sends the first-type feedback to the fourth processor, and the first-type feedback is used to trigger re-computation or update of the target first-type parameter group. Figure 17 As an example, in embodiment 17(b), the fifth processor sends the first-type output to the second node in the present application.

[0986] As an example, in embodiment 17(b), the sixth processor includes the second operation. Figure 17 As an example, in embodiment 17(b), (a) uses a single-sided AI model for beam prediction or channel information prediction, and the fifth processor performs the first operation for beam prediction or channel information prediction.

[0987] As an example, in embodiment 17(b), (b) uses a two-sided AI model for CSI compression, and the first operation is used for compressing CSI, and the second operation is used for recovering CSI. Figure 17

[0988] As an example, the AI includes ML (Machine Learning) inference.

[0989] As an example, the fifth processor performs the first operation.

[0990] As an example, the sixth processor includes the second operation.

[0991] As an example, the fifth processor sends the first-type feedback to the fourth processor, and the first-type feedback is used to trigger re-computation or update of the target first-type parameter group.

[0992] As an example, the sixth processor sends the second-type feedback to the third processor, and the second-type feedback is used to generate the first data set or the second data set, or the second-type feedback is used to trigger sending of the first data set or sending of the second data set.

[0993] ​As an embodiment, the third processor generates the first data set and the second data set according to measurement of the first type of wireless signal, the first type of wireless signal including downlink RS.

[0994] As an embodiment, the fifth processor belongs to the first node, and the sixth processor belongs to the second node.

[0995] As an embodiment, the target CSI belongs to the first type of output.

[0996] As an embodiment, the second data set includes the input of the first operation.

[0997] As an embodiment, the second data set includes information obtained based on the target CSI reporting configuration and the M1 configurations.

[0998] As an embodiment, the first data set includes training data.

[0999] As an embodiment, the fourth processor belongs to a producer of the first operation.

[1000] As an embodiment, the fourth processor includes an AI training producer.

[1001] As an embodiment, the fourth processor includes an AI training function.

[1002] As an embodiment, the fourth processor is used for model training, and a trained model is described by the target first type of parameter group.

[1003] As an embodiment, the fourth processor belongs to the first node.

[1004] The above embodiment avoids passing the first data set to the second node.

[1005] As an embodiment, the fourth processor belongs to the second node.

[1006] The above embodiment supports joint training and optimizes system performance.

[1007] As an embodiment, the fourth processor belongs to a core network.

[1008] The above embodiment supports full-network joint training and further optimizes system performance.

[1009] As an embodiment, the second data set includes inference data.

[1010] As one embodiment, the fifth handler comprises an AI inference producer.

[1011] As one embodiment, the fifth handler comprises an AI inference function.

[1012] As one embodiment, the fifth handler belongs to the first node.

[1013] As one embodiment, the fifth handler 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.

[1014] As one embodiment, the first operation is described by the target first-type parameter group.

[1015] As one embodiment, the target first-type parameter group is used to construct the first operation.

[1016] As one embodiment, the fifth handler comprises the second operation.

[1017] As one embodiment, the fifth handler generates a recovery data set according to the first-type output, and an error of the recovery data set and the second data set is used to generate the first-type feedback.

[1018] As one sub-embodiment of the above embodiment, the generation of the recovery data set adopts the second operation.

[1019] As one 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 fourth handler recalculates the target first-type parameter group.

[1020] As one embodiment, when the error is too large or the update is not performed for too long a time, the performance of the trained model is considered to be unable to meet the requirements.

[1021] As one embodiment, the target first-type parameter group comprises one or more of a convolution kernel size, a convolution layer number, a convolution step, a pooling kernel size, a pooling kernel step, a pooling function, an activation function, or a feature map number.

[1022] As one embodiment, the target first-type parameter group comprises one or more of a convolution kernel, a pooling kernel, a pooling function, an activation function, a parameter of the pooling function, or a parameter of the activation function.

[1023] Example 18

[1024] Embodiment 18 illustrates an AI or machine learning based schematic diagram according to an embodiment of the present application; as shown in FIG. 18. FIG. 18 is a flowchart illustrating an exemplary process for AI or machine learning based schematic diagram according to an embodiment of the present application. The process includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation; the arrowed lines represent the order of the flow. Figure 18 The process includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation; the arrowed lines represent the order of the flow. Figure 18 The process includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation; the arrowed lines represent the order of the flow.

[1025] In Embodiment 18, the third and fourth operations belong to a first phase, the fifth operation belongs to a second phase, the sixth operation belongs to a third phase, and the seventh operation belongs to a fourth phase.

[1026] As an embodiment, the third operation includes AI training, the fourth operation includes AI testing, the fifth operation includes AI emulation, the sixth operation includes AI entity loading, and the seventh operation includes AI inference.

[1027] As an embodiment, the first phase includes a training phase, the second phase includes an emulation phase, the third phase includes a deployment phase, and the fourth phase includes an inference phase.

[1028] As an embodiment, the first phase includes at least one of model training and testing.

[1029] As an embodiment, the AI model training includes initial training and re-training of one or a set of AI entities.

[1030] As an embodiment, the AI model training includes AI entity validation.

[1031] As an embodiment, the AI entity validation is used to evaluate the performance of the AI entity.

[1032] As an embodiment, if the result of AI entity validation does not meet the expectation, the AI model will be re-trained.

[1033] As an embodiment, the AI testing includes testing the validated AI entity to evaluate the performance of the trained AI model.

[1034] As one example, if the result of the AI testing meets expectations, the AI entity proceeds to the next stage; otherwise, the AI model is retrained.

[1035] As one example, the second stage includes AI simulation, which simulates inference of the AI entity in a simulation environment.

[1036] As one example, the AI simulation estimates performance of inference of the AI entity in the simulation environment before the AI entity is used.

[1037] As one example, the second stage is optional.

[1038] As one example, the third stage includes AI entity loading, which is to obtain the trained AI entity to obtain desired AI inference functionality.

[1039] As one example, the third stage is optional.

[1040] As one example, the third stage is not needed when the training functionality and the inference functionality are co-located.

[1041] As one example, the fourth stage includes AI inference.

[1042] As one example, the seventh operation includes the first operation.

[1043] As one example, the seventh operation includes the second operation.

[1044] Example 19

[1045] Embodiment 19 illustrates a structural block diagram of a processing apparatus in a first node according to an embodiment of the present application; as shown in FIG. 19. In FIG. 19, the processing apparatus 1900 in the first node includes a first receiver 1901 and a first processor 1902. Figure 19 As shown in FIG. 19, the processing apparatus 1900 in the first node includes a first receiver 1901 and a first processor 1902. Figure 19 As shown in FIG. 19, the processing apparatus 1900 in the first node includes a first receiver 1901 and a first processor 1902.

[1046] The first receiver 1901 receives at least one CSI reporting configuration; receives a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used to configure reporting of the at least one CSI;

[1047] The first processor 1902 determines whether to send a target CSI on the first PUSCH; sends the target CSI on the first PUSCH only when a first condition is met;

[1048] In Embodiment 19, a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration is one of the at least one CSI reporting configuration, the target CSI is one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set is used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set includes one or more RS resources; the first condition includes that a first symbol is not earlier than a first reference symbol, the first symbol is a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol is a next uplink symbol whose CP starts at a first time interval after the end of a last symbol of the first PDCCH; the first time interval depends on whether the generation manner of the target CSI is based on AI.

[1049] As an embodiment, a calculation formula of the first time interval depends on a first parameter, the first parameter depends on whether the generation manner of the target CSI is based on AI.

[1050] As an embodiment, when the generation manner of the target CSI is based on AI, the target CSI includes N information blocks, the N information blocks respectively include channel information of N time units, N is a positive integer greater than 1; the first time interval depends on at least one of the N time units.

[1051] As an embodiment, when the first resource set is composed of one or more aperiodic RS resources, the first condition further includes that a second symbol is not earlier than a second reference symbol, the second reference symbol is a next uplink symbol whose CP starts at a second time interval after the end of a last symbol of a first RS in the first resource set.

[1052] As an embodiment, the generation manner of the target CSI based on AI includes that the generation manner of the target CSI includes performing a first operation, an input of the first operation depends on measurement based on the first resource set, and the target CSI depends on an output of the first operation.

[1053] As an embodiment, the generation manner of the target CSI based on AI includes that the generation manner of the target CSI is associated to a first type identifier.

[1054] As an embodiment, when the generation manner of the target CSI is based on AI, the first time interval depends on the first type identifier to which the generation manner of the target CSI is associated.

[1055] As an embodiment, the target CSI is generated based on AI includes that the target CSI indicates at least one resource in a second resource set, the second resource set includes resources not belonging to the first resource set.

[1056] As an embodiment, any of the N information blocks indicates at least one resource in a second resource set, the second resource set includes resources not belonging to the first resource set.

[1057] As an embodiment, the first processor 1902 ignores the first DCI when the first condition is not satisfied; wherein no HARQ-ACK or transport block is multiplexed on the first PUSCH.

[1058] As an embodiment, the output of the first operation includes a first CSI, the target CSI carries the first CSI, and the first CSI is used by a target receiver of the target CSI as an input of a second operation to generate a second CSI.

[1059] As an embodiment, the first processor 1902 deploys the first operation.

[1060] As an embodiment, the first operation is associated to the first type of identity.

[1061] As an embodiment, the first operation is based on training or based on AI.

[1062] As an embodiment, the second operation is based on training or based on AI.

[1063] As an embodiment, the first node is a user equipment.

[1064] As an embodiment, the first node is a relay node equipment.

[1065] As an embodiment, the first receiver 1901 includes at least one of {antenna 452, receiver 454, receive processor 456, multi-antenna receive processor 458, controller / processor 459, memory 460, data source 467} in embodiment 4.

[1066] As an embodiment, the first processor 1902 includes at least one of {antenna 452, receiver / transmitter 454, receive processor 456, transmit processor 468, multi-antenna receive processor 458, multi-antenna transmit processor 457, controller / processor 459, memory 460, data source 467} in embodiment 4.

[1067] Example 20

[1068] Embodiment 20 illustrates a structural block diagram of a processing apparatus in a second node according to an embodiment of the present application; as shown in FIG. 20, the processing apparatus 2000 in the second node comprises a second processor 2001. Figure 20 Figure 20 In the embodiment, the processing apparatus 2000 in the second node comprises a second processor 2001.

[1069] The second processor 2001, sends at least one CSI reporting configuration; sends a first DCI on a first PDCCH, the first DCI triggers reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration is used for configuring reporting of the at least one CSI.

[1070] In Embodiment 20, a target receiver of the first DCI determines whether to send a target CSI on the first PUSCH; only when a first condition is met, the target receiver of the first DCI sends the target CSI on the first PUSCH; a target CSI reporting configuration is used for configuring reporting of the target CSI, the target CSI reporting configuration is one of the at least one CSI reporting configuration, the target CSI is one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set is used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set comprises one or more RS resources; the first condition comprises that a first symbol is not earlier than a first reference symbol, the first symbol is a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol is a next uplink symbol whose CP starts at a first time interval after the end of the last symbol of the first PDCCH; the first time interval depends on whether the generation mode of the target CSI is based on AI.

[1071] As an embodiment, the second processor 2001 determines whether to receive a target CSI on the first PUSCH; only when a first condition is met, the target CSI is received on the first PUSCH.

[1072] As an embodiment, the calculation formula of the first time interval depends on a first parameter, the first parameter depends on whether the generation mode of the target CSI is based on AI.

[1073] As an embodiment, when the generation mode of the target CSI is based on AI, the target CSI comprises N information blocks, the N information blocks respectively comprise channel information of N time units, N is a positive integer greater than 1; the first time interval depends on at least one of the N time units.

[1074] ​As an embodiment, when the first set of resources consists of one or more aperiodic RS resources, the first condition further comprises that the second symbol is not earlier than a second reference symbol, the second reference symbol being a next uplink symbol after a second time interval from an end of a last symbol of a first RS in the first set of resources.

[1075] As an embodiment, the generation manner of the target CSI is based on AI comprises that the generation manner of the target CSI comprises that the target receiver of the first DCI performs a first operation, an input of the first operation depends on a measurement based on the first set of resources, and the target CSI depends on an output of the first operation.

[1076] As an embodiment, the generation manner of the target CSI is based on AI comprises that the generation manner of the target CSI is associated to a first type identifier.

[1077] As an embodiment, when the generation manner of the target CSI is based on AI, the first time interval depends on the first type identifier to which the generation manner of the target CSI is associated.

[1078] As an embodiment, the generation manner of the target CSI is based on AI comprises that the target CSI indicates at least one resource in a second set of resources, the second set of resources comprising resources not belonging to the first set of resources.

[1079] As an embodiment, any of the N information blocks indicates at least one resource in a second set of resources, the second set of resources comprising resources not belonging to the first set of resources.

[1080] As an embodiment, the second processor 2001, when the first condition is not satisfied, gives up receiving a signal on the first PUSCH or gives up receiving the target CSI on the first PUSCH;

[1081] As an embodiment, when the first condition is not satisfied, the target receiver of the first DCI ignores the first DCI; wherein no HARQ-ACK or transport block is multiplexed on the first PUSCH.

[1082] As an embodiment, the output of the first operation comprises a first CSI, the target CSI carries the first CSI, and the first CSI is used by the target receiver of the target CSI as an input of a second operation to generate a second CSI.

[1083] As one embodiment, the second processor 2001 performs a second operation; wherein the output of the first operation comprises the first CSI, the target CSI carries the first CSI, and the first CSI is used by a target receiver of the target CSI as input of the second operation to generate a second CSI.

[1084] As one embodiment, the second processor 2001 deploys the second operation.

[1085] As one embodiment, the first operation is associated to the first type of identity.

[1086] As one embodiment, the first operation is training-based or AI-based.

[1087] As one embodiment, the second operation is training-based or AI-based.

[1088] As one embodiment, the second node is a base station device.

[1089] As one embodiment, the second node is a user equipment.

[1090] As one embodiment, the second node is a relay node device.

[1091] As one embodiment, the second processor 2001 comprises at least one of {antennas 420, receivers / transmitters 418, receive processor 470, transmit processor 416, multi-antenna receive processor 472, multi-antenna transmit processor 471, controller / processor 475, memory 476} in embodiment 4.

[1092] Those skilled in the art can understand that all or part of the steps in the foregoing method can be instructed by programs to complete the 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, notebooks, vehicle-mounted communication devices, wireless sensors, network cards, Internet of Things terminals, RFID terminals, NB-IOT 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, home base stations, relay base stations, gNB (NR NodeB) NR NodeB, TRP (Transmitter Receiver Point) and other wireless communication devices.

[1093] The above only describes the preferred embodiments of the present application and is not intended to limit the protection scope of the present application. Any changes and modifications made on the basis of the embodiments described in the specification, if they can obtain similar technical effects, should be considered as obvious and belong to the protection scope of the present application.

Claims

1. A method in a first node for wireless communication, characterized by, Comprising: receiving at least one CSI reporting configuration; receiving a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used to configure reporting of the at least one CSI; determining whether to transmit a target CSI on the first PUSCH; transmitting the target CSI on the first PUSCH only when a first condition is satisfied; wherein a target CSI reporting configuration is used to configure reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicating a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set comprising one or more RS resources; the first condition comprising a first symbol not being earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol whose CP starts a first time interval after an end of a last symbol of the first PDCCH; the first time interval depending on whether a generation manner of the target CSI is based on AI.

2. The method of claim 1, wherein, A calculation formula of the first time interval depends on a first parameter, the first parameter depending on whether the generation manner of the target CSI is based on AI.

3. The method according to claim 1 or 2, characterized in that, When the generation manner of the target CSI is based on AI, the target CSI comprises N information blocks, the N information blocks respectively comprising channel information of N time units, N being a positive integer greater than 1; the first time interval depending on at least one of the N time units.

4. The method according to any one of claims 1 to 3, characterized in that, When the first resource set consists of one or more aperiodic RS resources, the first condition further comprises a second symbol not being earlier than a second reference symbol, the second reference symbol being a next uplink symbol whose CP starts a second time interval after an end of a last symbol of a first RS in the first resource set.

5. The method according to any one of claims 1 to 4, characterized in that, The generation manner of the target CSI being based on AI comprises: the generation manner of the target CSI comprising performing a first operation, an input of the first operation depending on measurement based on the first resource set, the target CSI depending on an output of the first operation.

6. The method according to any one of claims 1 to 5, characterized in that, The generation manner of the target CSI being based on AI comprises: the generation manner of the target CSI being associated to a first type of identifier.

7. The method of claim 6, wherein, When the generation manner of the target CSI is based on AI, the first time interval depending on the first type of identifier to which the generation manner of the target CSI is associated.

8. The method according to any one of claims 1 to 7, characterized in that, The generation manner of the target CSI being based on AI comprises: the target CSI indicating at least one resource in a second resource set, the second resource set comprising resources not belonging to the first resource set.

9. The method according to any one of claims 1 to 8, characterized in that, Comprising: ignoring the first DCI when the first condition is not satisfied; wherein no HARQ-ACK or transport block is multiplexed on the first PUSCH.

10. A terminal, characterized by comprising: The terminal comprises one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is configured to store computer program codes including 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 1-9.

11. A method in a second node for wireless communication, the method comprising: comprising: transmitting at least one CSI reporting configuration; transmitting a first DCI on a first PDCCH, the first DCI triggering reporting of at least one CSI on a first PUSCH, the at least one CSI reporting configuration being used to configure reporting of the at least one CSI; wherein a target receiver of the first DCI determines whether to transmit a target CSI on the first PUSCH; the target receiver of the first DCI transmits the target CSI on the first PUSCH only when a first condition is satisfied; a target CSI reporting configuration is used to configure reporting of the target CSI, the target CSI reporting configuration being one of the at least one CSI reporting configuration, the target CSI being one of the at least one CSI; the target CSI reporting configuration indicates a first resource set, the first resource set being used for at least one of channel measurement or interference resource measurement of the target CSI, the first resource set comprising one or more RS resources; the first condition comprises that a first symbol is not earlier than a first reference symbol, the first symbol being a first uplink symbol in the first PUSCH for carrying the at least one CSI, the first reference symbol being a next uplink symbol after a first time interval from an end of a last symbol of the first PDCCH; the first time interval depending on whether a generation manner of the target CSI is based on AI.

12. The method of claim 11, wherein, comprising: determining whether to receive a target CSI on the first PUSCH; receiving the target CSI on the first PUSCH only when a first condition is satisfied.

13. The method according to claim 11 or 12, characterized in that, A calculation formula of the first time interval depends on a first parameter, the first parameter depending on whether a generation manner of the target CSI is based on AI.

14. The method of any one of claims 11-13, wherein, When the generation manner of the target CSI is based on AI, the target CSI comprises N information blocks, the N information blocks respectively comprising channel information of N time units, N being a positive integer greater than 1; the first time interval depending on at least one of the N time units.

15. The method according to any one of claims 11 to 14, characterized in that, When the first resource set is composed of one or more aperiodic RS resources, the first condition further comprises that a second symbol is not earlier than a second reference symbol, the second reference symbol being a next uplink symbol after a second time interval from an end of a last symbol of a first RS in the first resource set.

16. The method according to any one of claims 11 to 15, characterized in that, The generation manner of the target CSI is based on AI includes that the generation manner of the target CSI comprises the target receiver of the first DCI performing a first operation, an input of the first operation depends on a measurement based on the first resource set, and the target CSI depends on an output of the first operation.

17. The method of any one of claims 11 to 16, wherein, The generation manner of the target CSI is based on AI includes that the generation manner of the target CSI is associated to a first type identifier.

18. The method of claim 17, wherein, When the generation manner of the target CSI is based on AI, the first time interval depends on the first type identifier to which the generation manner of the target CSI is associated.

19. The method of any one of claims 11-18, wherein, The generation manner of the target CSI is based on AI includes that the target CSI indicates at least one resource in a second resource set, and the second resource set comprises resources not belonging to the first resource set.

20. The method of any one of claims 11-19, wherein, Comprise: When the first condition is not satisfied, abandon receiving a signal on the first PUSCH, or abandon receiving the target CSI on the first PUSCH; Wherein, no HARQ-ACK or transport block is multiplexed on the first PUSCH.

21. The method of any one of claims 11-19, wherein, When the first condition is not satisfied, the target receiver of the first DCI ignores the first DCI; wherein, no HARQ-ACK or transport block is multiplexed on the first PUSCH.

22. A base station, comprising: The base station comprises one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is configured to store computer program code, the computer program code comprising computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the base station to perform the method according to any one of claims 11-21.

Images