Method and apparatus used for wireless communication

Abstract

Disclosed in the present application are a method and apparatus used for wireless communication. The method comprises: a first node sending a first report, and receiving first signaling, wherein the first report indicates L0 first-type resources, L0 being a positive integer; the first signaling indicates that the number of occupied first-type resources is adjusted by P1, P1 being an integer; and the L0 first-type resources are used for inference. The method provides a signaling architecture for resource occupation in AI inference or ML inference, which is beneficial to making full use of the advantages of AI-based or ML-based technology to improve system performance.

Description

Method and apparatus for wireless communication TECHNICAL FIELD

[0001] The present application relates to transmission methods and apparatuses in wireless communication systems, and in particular to schemes and apparatuses related to resource occupation in wireless communication systems. BACKGROUND

[0002] In the evolution of communication systems from 5G (Generation) to 5G-Advanced and 6G, more advanced technologies are proposed and researched to improve the performance of wireless communication systems in various aspects and to meet the needs of more application scenarios. Typical technologies include but are not limited to AI (Artificial Intelligence) or ML (Machine Learning), full duplex mode or sub-band non-overlapping full duplex (SBFD), and reconfigurable intelligent surface (RIS).

[0003] One of the most significant features of 6G systems compared to 5G systems will be more intelligent. AI / ML aims to greatly improve the performance of wireless communication using advanced artificial intelligence and machine learning technologies. With AI / ML technologies, 6G systems can not only intelligently provide high-quality services such as scheduling, data reception, signal processing, coding and decoding, measurement and reporting, etc. according to the perception and learning of the surrounding environment, but also intelligently achieve self-optimization and self-maintenance of the network. In NR (New Radio) R (release) 18, AI / ML technology research has been initiated.

[0004] Compared with traditional processing methods, AI / ML has some unique characteristics, such as model dependence, training-based, the need for deployment, and different requirements for computing / processing power and storage capacity than traditional technologies.

[0005] According to 3GPP (3rd Generation Partner Project) standard TS38.300, AI / ML models and algorithms are beyond the scope of 3GPP. SUMMARY

[0006] Applicant has found, through research, that AI inference or ML inference requires resource occupation, such as but not limited to computing resource and / or storage resource. When AI / ML technology is introduced, the existing resource occupation related design can not be able to adapt to the requirement of AI / ML. To solve the above problem, the present application discloses a solution. It should be noted that although the motivation of the present application comes from the application of AI / ML model, and a large number of embodiments are developed for AI / ML, the present application is also applicable to other solutions, such as traditional receiving algorithm, traditional measurement and reporting solution, traditional scheduling algorithm, etc. Although the present application involves some description of AI / ML model and algorithm in the specification, however, those skilled in the art know that these descriptions are not necessary or irreplaceable for the solution related to wireless cellular communication. In addition, using a unified solution for different scenarios (including but not limited to AI / ML based solution and traditional algorithm / solution) helps to reduce signaling overhead / complexity, reduce hardware complexity and cost. In the case of no conflict, the embodiments in the first node and the features in the embodiments of the present application can be applied to the second node, and vice versa. In the case of no conflict, the embodiments of the present application and the features in the embodiments can be arbitrarily combined with each other.

[0007] When needed, the explanation of the terms in the present application is referred to the definition in the specification protocol TS38 series of 3GPP, or, the definition in the specification protocol TS28 series of 3GPP.

[0008] The present application discloses a method in a first node used for wireless communication, characterized in that, comprising:

[0009] sending a first report, the first report indicating L0 first type resources, L0 being a positive integer;

[0010] receiving a first signaling, the first signaling indicating that the number of occupied first type resources is adjusted by P1, P1 being an integer;

[0011] wherein the L0 first type resources are used for inference.

[0012] As an embodiment, the problem to be solved by the present application includes how the two parties of communication coordinate the resource occupation for inference; in the above method, the first signaling received by the first node indicates the adjustment of the number of occupied first type resources, which solves this problem.

[0013] As an embodiment, the benefits of the above method include providing a signaling architecture for resource occupation of AI or ML based technology, especially AI inference or ML inference, which is beneficial to fully play the advantages of AI or ML based technology to improve system performance.

[0014] As an embodiment, the performance of inference is significantly improved with the increase of the number of parameters of the AI / ML model, and the larger the number of parameters is, the more computation and storage space are required for inference; therefore, there is a mutual constraint relationship between the performance of inference and resource occupation; how to optimize the application of inference in the communication system based on this mutual constraint relationship is a problem to be solved; in the above method, the first node receives an indication of the adjustment of the number of occupied first-type resources, which solves this problem.

[0015] As an embodiment, the benefits of the above method include improving the efficiency and robustness of the system.

[0016] As an embodiment, the benefits of the above method include simplifying system design and facilitating implementation.

[0017] As an embodiment, the benefits of the above method include good flexibility, adapting to different terminals and different application scenarios.

[0018] According to an aspect of the present application, it comprises:

[0019] sending a second report;

[0020] wherein the second report indicates that L1 first-type resources are not occupied, and L1 is a positive integer.

[0021] As an embodiment, the benefits of the above method include facilitating the network side to reasonably schedule according to the number of available first-type resources, optimizing the scheduling of the network side, and improving the performance of the first node and the overall network performance.

[0022] According to an aspect of the present application, it comprises:

[0023] determining L2, wherein L2 is a positive integer;

[0024] wherein L2 first-type resources are occupied, and L2 depends on P1.

[0025] As an embodiment, the benefits of the above method include achieving a better trade-off between the performance of inference and resource occupation, improving resource utilization, and optimizing performance.

[0026] According to an aspect of the present application, the L2 first-type resources are occupied by a first operation; the candidate of the number of first-type resources occupied by the first operation includes M values, M is a positive integer greater than 1, the M values are positive integers respectively, and L2 is one of the M values.

[0027] As one embodiment, the essence of the above method includes that the first signaling indicates an adjustment to the number of the first type of resources occupied by the first operation.

[0028] As one embodiment, the essence of the above method includes that the first operation can obtain different performance under the condition of occupying different number of the first type of resources, and the sender of the first signaling indicates that the first operation occupies more or less first type of resources according to actual performance.

[0029] As one embodiment, the benefit of the above method includes that a better trade-off between performance and resource occupation of the first operation is obtained, and the performance and resource utilization of the first operation are optimized.

[0030] According to one aspect of the present application, it is characterized in that the L2 first type of resources are occupied by a first function, the first function has P candidate operations, P is a positive integer greater than 1, L2 is the number of first type of resources occupied by a first candidate operation, and the first candidate operation is a candidate operation used for the first function among the P candidate operations.

[0031] As one embodiment, the essence of the above method includes that the first signaling indicates an adjustment to the number of the first type of resources occupied by the first function.

[0032] As one embodiment, the essence of the above method includes that the first function can be completed by any candidate operation among P candidate operations with different resource occupation requirements and different performance, and the sender of the first signaling indicates that the first function adopts a candidate operation occupying more or less first type of resources according to actual performance.

[0033] As one embodiment, the benefit of the above method includes that a better trade-off between performance and resource occupation of the first function is obtained, and the performance and resource utilization of the first function are optimized.

[0034] According to one aspect of the present application, it is characterized in that it includes:

[0035] Receiving on a first physical layer channel;

[0036] Wherein, the scheme adopted by the receiving on the first physical layer channel depends on the P1.

[0037] As one embodiment, the essence of the above method includes that there are multiple candidate schemes for receiving a physical layer channel, the multiple candidate schemes have different resource occupation requirements and different performance, and the sender of the first signaling indicates that the first node adopts a candidate scheme occupying more or less first type of resources to receive a physical layer channel according to actual performance.

[0038] As an embodiment, benefits of the above method include a better tradeoff between the reception performance of the physical layer channel and the resource occupation, optimizing the system performance and resource utilization.

[0039] According to an aspect of the present application, it is characterized in that comprising:

[0040] sending a first CSI;

[0041] wherein the scheme adopted by the calculation of the first CSI depends on the P1.

[0042] As an embodiment, the essence of the above method includes that there are multiple candidate schemes for the calculation of the CSI, the multiple candidate schemes have different resource occupation requirements and different performances, and the sender of the first signaling instructs the first node to adopt the candidate scheme occupying more or less first type resources to receive the calculation of the CSI according to the actual performance.

[0043] As an embodiment, benefits of the above method include a better tradeoff between the performance of the CSI and the resource occupation, optimizing the system performance and resource utilization.

[0044] According to an aspect of the present application, it is characterized in that at least one first type resource of the L0 first type resources comprises one or more first type sub-resources and one or more second type sub-resources; at least the first type sub-resource of the first type sub-resource and the second type sub-resource is used for inference.

[0045] As an embodiment, benefits of the above method include good forward compatibility.

[0046] As an embodiment, benefits of the above method include better flexibility, suitable for different terminals.

[0047] The present application discloses a method in a second node used for wireless communication, characterized in that comprising:

[0048] receiving a first report, the first report indicating L0 first type resources, the L0 being a positive integer;

[0049] sending a first signaling, the first signaling indicating that the number of occupied first type resources is adjusted by P1, the P1 being an integer;

[0050] wherein the L0 first type resources are used for inference.

[0051] According to an aspect of the present application, it is characterized in that comprising:

[0052] receiving a second report;

[0053] The second report indicates that L1 first-type resources are not occupied, where L1 is a positive integer.

[0054] According to an aspect of the present application, a sender of the first report determines L2, where L2 is a positive integer; and L2 first-type resources are occupied, where L2 depends on P1.

[0055] According to an aspect of the present application, the L2 first-type resources are occupied by a first operation; candidates of the number of first-type resources occupied by the first operation include M values, where M is a positive integer greater than 1, the M values are positive integers respectively, and L2 is one of the M values.

[0056] According to an aspect of the present application, the L2 first-type resources are occupied by a first function, the first function has P candidate operations, P is a positive integer greater than 1, L2 is the number of first-type resources occupied by a first candidate operation, and the first candidate operation is a candidate operation used for the first function among the P candidate operations.

[0057] According to an aspect of the present application, it comprises:

[0058] The first report is sent on a first physical layer channel.

[0059] A target receiver of the first physical layer channel depends on P1 in a scheme for receiving on the first physical layer channel.

[0060] According to an aspect of the present application, it comprises:

[0061] The first CSI is received.

[0062] A scheme for calculating the first CSI depends on P1.

[0063] According to an aspect of the present application, at least one first-type resource of the L0 first-type resources comprises one or more first-type sub-resources and one or more second-type sub-resources; and at least the first-type sub-resource of the first-type sub-resource and the second-type sub-resource is used for inference.

[0064] The present application discloses a first node used for wireless communication, which comprises:

[0065] A first transmitter sends a first report, where the first report indicates L0 first-type resources, and L0 is a positive integer.

[0066] The first processor receives first signaling, the first signaling indicating that the number of occupied first-type resources is adjusted by P1, P1 being an integer.

[0067] The L0 first-type resources are used for inference.

[0068] The second node for wireless communication is disclosed, and has characteristics that include:

[0069] The first receiver receives first reporting, the first reporting indicating L0 first-type resources, L0 being a positive integer.

[0070] The second transmitter transmits first signaling, the first signaling indicating that the number of occupied first-type resources is adjusted by P1, P1 being an integer.

[0071] The L0 first-type resources are used for inference.

[0072] As an embodiment, compared with a conventional scheme, the present application has the following advantages:

[0073] It is convenient for both parties to coordinate the occupation of resources used for inference.

[0074] The advantages of AI or ML-based technology are fully utilized to improve system performance.

[0075] The efficiency and robustness of the system are improved.

[0076] Flexible signaling design, suitable for different terminals and different application scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0077] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments with reference to the attached drawings:

[0078] FIG. 1 shows a flowchart of first reporting and first signaling according to an embodiment of the present application;

[0079] FIG. 2 shows a schematic diagram of a network architecture according to an embodiment of the present application;

[0080] FIG. 3 shows a schematic diagram of an embodiment of a wireless protocol architecture of a user plane and a control plane according to an embodiment of the present application;

[0081] FIG. 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of the present application;

[0082] FIG. 5 shows a transmission between a first node and a second node according to an embodiment of the present application;

[0083] Figure 6 shows a schematic diagram of a second report according to one embodiment of the application;

[0084] Figure 7 shows a schematic diagram of L2 according to one embodiment of the application;

[0085] Figure 8 shows a schematic diagram of L2 according to one embodiment of the application;

[0086] Figure 9 shows a schematic diagram of L2 according to one embodiment of the application;

[0087] Figure 10 shows a schematic diagram of L2 first type resources occupied by a first operation according to one embodiment of the application;

[0088] Figure 11 shows a schematic diagram of the number of first type resources occupied by a first operation according to one embodiment of the application;

[0089] Figure 12 shows a schematic diagram of L2 first type resources occupied by a first function according to one embodiment of the application;

[0090] Figure 13 shows a schematic diagram of a first function having P candidate operations according to one embodiment of the application;

[0091] Figure 14 shows a schematic diagram of receiving on a first physical layer channel with K1 candidate schemes according to one embodiment of the application;

[0092] Figure 15 shows a schematic diagram of a first operation used for receiving on a first physical layer channel according to one embodiment of the application;

[0093] Figure 16 shows a schematic diagram of a first function including receiving on a first physical layer channel according to one embodiment of the application;

[0094] Figure 17 shows a schematic diagram of a first CSI computation with K2 candidate schemes according to one embodiment of the application;

[0095] Figure 18 shows a schematic diagram of a first operation used for first CSI computation according to one embodiment of the application;

[0096] Figure 19 shows a schematic diagram of a first function including the first CSI computation according to one embodiment of the application;

[0097] Figure 20 shows a schematic diagram of at least one first type resource of L0 first type resources including one or more first type sub-resources and one or more second type sub-resources according to one embodiment of the application;

[0098] Figure 21 shows a schematic diagram of deploying a given operation according to one embodiment of the application;

[0099] FIG. 22 shows a schematic diagram of an artificial intelligence or machine learning based processing system according to an embodiment of the present application;

[0100] FIG. 23 shows a schematic diagram of an artificial intelligence or machine learning based processing system according to an embodiment of the present application;

[0101] FIG. 24 shows a schematic diagram of AI function deployment according to an embodiment of the present application;

[0102] FIG. 25 shows a schematic diagram of AI function deployment according to an embodiment of the present application;

[0103] FIG. 26 shows a schematic diagram of AI function deployment according to an embodiment of the present application;

[0104] FIG. 27 shows a schematic diagram of AI function deployment according to an embodiment of the present application;

[0105] FIG. 28 shows a structural block diagram of a processing apparatus in a first node according to an embodiment of the present application;

[0106] FIG. 29 shows a structural block diagram of a processing apparatus in a second node according to an embodiment of the present application. DETAILED DESCRIPTION

[0107] 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 combine the embodiments in different drawings flexibly without conflict, for example, but not limited to, the embodiments in FIG. 1 and the embodiments in FIG. 5-FIG. 29, the embodiments in FIG. 5 and the embodiments in FIG. 6-FIG. 29, etc.

[0108] Embodiment 1

[0109] Embodiment 1 shows a flowchart of a first report and a first signaling according to an embodiment of the present application, as shown in FIG. 1. In 100 shown in FIG. 1, each block represents a step. In particular, the order of the steps in the blocks does not represent a specific time sequence between the steps.

[0110] In embodiment 1, the first node sends a first report in step 101; receives a first signaling in step 102. Wherein, the first report indicates L0 first type resources, L0 is a positive integer; the first signaling indicates that the number of occupied first type resources is adjusted P1, P1 is an integer; the L0 first type resources are used for reasoning.

[0111] As one embodiment, the first report is carried by a higher layer message.

[0112] As one embodiment, the first report is carried by a RRC message.

[0113] As one embodiment, the first report is carried by RRC signaling.

[0114] As one embodiment, the first report is carried by a MAC CE.

[0115] As one embodiment, the first report includes UE capability information.

[0116] As one embodiment, the first report is carried by a UE capability IE.

[0117] As one embodiment, the first report includes information in all or part of the fields in one UE capability IE.

[0118] As one embodiment, the first report includes information in one or more UE capability IEs.

[0119] As one embodiment, the first report includes capability reporting of the first node.

[0120] As one embodiment, the first report includes UE processing capability of the first node.

[0121] As one embodiment, the first report includes UE capability indication of the first node.

[0122] As one embodiment, the first report is only applicable to one carrier or one serving cell of the first node.

[0123] As one embodiment, the first report is applicable to all component carriers of the first node.

[0124] As one embodiment, the first report is applicable to all component carriers of the first node that belong to the same cell group.

[0125] As an embodiment, the first report is applicable to all component carriers of the first node belonging to a same band or band combination.

[0126] As an embodiment, the first report is applicable to all serving cells of the first node.

[0127] As an embodiment, the first report is applicable to all serving cells of the first node belonging to a same cell group.

[0128] As an embodiment, the first report is applicable to all serving cells of the first node belonging to a same band or band combination.

[0129] Typically, the same cell group is a Master Cell Group (MCG) or a Secondary Cell Group (SCG).

[0130] As an embodiment, the first report indicates that the maximum number of the first type of resources occupied is the L0.

[0131] As an embodiment, the first report indicates that the maximum number of the first type of resources supported by the first node is the L0.

[0132] As an embodiment, the essence of the above method includes that the first node reports the maximum number of the first type of resources supported, and the benefits of the above method include that the target receiver of the first report can optimize scheduling according to the number of the first type of resources that the first node can support.

[0133] As an embodiment, the benefits of the above method include saving reporting overhead.

[0134] As an embodiment, the L0 is greater than 1.

[0135] As an embodiment, the L0 is equal to 1.

[0136] As an embodiment, the L0 is the total number of the first type of resources.

[0137] As an embodiment, the L0 is the total number of the first type of resources of the first node.

[0138] As an embodiment, the L0 is the total number of the first type of resources deployed in the first node.

[0139] As an embodiment, the L0 is the maximum number of the first type of resources.

[0140] As one embodiment, the L0 is a maximum of a number of the first type of resources occupied.

[0141] As one embodiment, the L0 is a maximum of a number of the first type of resources supported by the first node.

[0142] As one embodiment, the L0 is a maximum of a number of the first type of resources that the first node can provide.

[0143] As one embodiment, the L0 is a maximum of a number of the first type of resources simultaneously supported by the first node.

[0144] As one embodiment, the L0 is a maximum of a number of the first type of resources that the first node can simultaneously provide.

[0145] As one embodiment, the first node simultaneously supports the L0 first type of resources.

[0146] As one embodiment, the first node can simultaneously provide the L0 first type of resources.

[0147] As one embodiment, the L0 is a total number of the first type of resources on one carrier or one serving cell.

[0148] As one embodiment, the L0 is a total number of the first type of resources on one carrier or one serving cell by the first node.

[0149] As one embodiment, the L0 is a maximum of the first type of resources occupied on one carrier or one serving cell.

[0150] As one embodiment, the L0 is a maximum of the first type of resources supported on one carrier or one serving cell by the first node.

[0151] As one embodiment, the L0 is a maximum of the first type of resources that the first node can provide on one carrier or one serving cell.

[0152] As one embodiment, the L0 is a maximum of the first type of resources simultaneously supported on one carrier or one serving cell by the first node.

[0153] As one embodiment, the L0 is a maximum of the first type of resources that the first node can simultaneously provide on one carrier or one serving cell.

[0154] As one embodiment, the carrier refers to a component carrier.

[0155] As one embodiment, the one serving cell is a SpCell (Special Cell) or a SCell (Secondary Cell).

[0156] As one embodiment, the L0 is a total number of the first type of resources over all carriers or all serving cells.

[0157] As one embodiment, the L0 is a total number of the first type of resources over all carriers or all serving cells.

[0158] As one embodiment, the L0 is a maximum value of the first type of resources occupied over all carriers or all serving cells.

[0159] As one embodiment, the L0 is a maximum value of the first type of resources supported by the first node over all carriers or all serving cells.

[0160] As one embodiment, the L0 is a maximum value of the first type of resources that can be provided by the first node over all carriers or all serving cells.

[0161] As one embodiment, the L0 is a maximum value of the first type of resources simultaneously supported by the first node over all carriers or all serving cells.

[0162] As one embodiment, the L0 is a maximum value of the first type of resources that can be simultaneously provided by the first node over all carriers or all serving cells.

[0163] As one embodiment, the all carriers refer to all component carriers.

[0164] As one embodiment, the all carriers refer to all component carriers belonging to the same cell group.

[0165] As one embodiment, the all carriers refer to all component carriers belonging to the same frequency band or frequency band combination.

[0166] As one embodiment, the all serving cells refer to all serving cells configured by the first node.

[0167] As one embodiment, the all serving cells refer to all serving cells belonging to the same cell group.

[0168] As one embodiment, the all serving cells refer to all serving cells belonging to the same frequency band or frequency band combination.

[0169] As one embodiment, the first report is carried by a MAC CE (Medium Access Control layer Control Element).

[0170] As one embodiment, the first report is carried by a DCI (Downlink Control Information).

[0171] As one embodiment, the first report indicates that the L0 first-type resources are not occupied.

[0172] As one embodiment, the benefits of the above method include providing the target receiver of the first report with more detailed information about the number of available first-type resources remaining at the first node, which provides a basis for further optimization on the network side.

[0173] As one embodiment, the L0 is the total number of unoccupied first-type resources on one carrier or one serving cell.

[0174] As one embodiment, the L0 is the total number of unoccupied first-type resources on all carriers or all serving cells.

[0175] As one embodiment, the first-type resources include storage units.

[0176] As one embodiment, the first-type resources include processing units or computing units.

[0177] As one embodiment, the first-type resources include storage units and processing or computing units.

[0178] As one embodiment, the first-type resources include CSI processing units (Channel Status Information CSI processing units).

[0179] As one embodiment, the first-type resources are different from CSI processing units.

[0180] As one embodiment, the first-type resources include CSI processing units and resources different from CSI processing units.

[0181] As one embodiment, the first-type resources are used for storage.

[0182] As one embodiment, the first-type resources are used for computing or processing.

[0183] As one embodiment, the first-type resources are used for storage and computing.

[0184] As an embodiment, the first type of resources are used for storage and processing.

[0185] As an embodiment, the first type of resources are used for storage required for inference.

[0186] As an embodiment, the first type of resources are used for computation or processing required for inference.

[0187] As an embodiment, the first type of resources are used for storage required for inference and computation or processing required for inference.

[0188] As an embodiment, the first type of resources are used for CSI (Channel State Information) processing.

[0189] As an embodiment, the first type of resources are not used for CSI processing.

[0190] As an embodiment, the first type of resources are used for processing that does not include inference.

[0191] As an embodiment, the first type of resources are used for CSI processing that does not include inference.

[0192] As an embodiment, the first type of resources are used only for inference.

[0193] As an embodiment, the first type of resources are used for inference and processing that does not include inference.

[0194] As an embodiment, the first type of resources are not used for processing that does not include inference.

[0195] As an embodiment, the inference refers to AI (Artificial Intelligence) inference.

[0196] As an embodiment, the inference refers to ML (Machine Learning) inference.

[0197] As an embodiment, the inference refers to AI inference or ML inference.

[0198] As an embodiment, the inference is used for one or more of CSI compression, CSI prediction, and beam management.

[0199] As an embodiment, the inference is used for data reception.

[0200] As an embodiment, the inference is used for downlink data reception.

[0201] As one embodiment, the inference is used for PDSCH (Physical Downlink Shared Channel) reception.

[0202] As one embodiment, the inference is used for one or more of channel estimation, MIMO (Multiple Input Multiple Output) reception, demodulation, channel decoding, and CRC (Cyclic Redundancy Check) check.

[0203] As one embodiment, the inference is used for positioning.

[0204] As one embodiment, the inference is used for scheduling.

[0205] As one embodiment, the inference is used for semantic-based error correction.

[0206] As one embodiment, the first signaling comprises RRC signaling.

[0207] As one embodiment, the first signaling comprises MAC CE.

[0208] As one embodiment, the first signaling comprises DCI (Downlink Control Information).

[0209] As one embodiment, the first signaling is DCI.

[0210] As one embodiment, the P1 is greater than 0, equal to 0, or less than 0.

[0211] As one embodiment, the absolute value of the P1 is less than the L0.

[0212] As one embodiment, the P1 is greater than 0, and the first signaling indicates that the number of occupied first-type resources is increased by the P1.

[0213] As one embodiment, the P1 is equal to 0, and the first signaling indicates that the number of occupied first-type resources is maintained.

[0214] As one embodiment, the P1 is less than 0, and the first signaling indicates that the number of occupied first-type resources is decreased by the absolute value of the P1.

[0215] As one embodiment, the P1 is greater than 0, and the first signaling indicates that the number of occupied first-type resources is increased by at least the P1.

[0216] As one embodiment, the P1 is less than 0, and the first signaling indicates that the number of occupied first-type resources is reduced by at most the absolute value of the P1.

[0217] As one embodiment, the adjusting includes increasing, decreasing, and keeping unchanged.

[0218] As one embodiment, the adjusted P1 includes being adjusted by at least the P1.

[0219] As one embodiment, the adjusted P1 includes being adjusted by at most the P1.

[0220] As one embodiment, the P1 is greater than 0, and the adjusted P1 includes being increased by the P1.

[0221] As one embodiment, the P1 is greater than 0, and the adjusted P1 includes being increased by at least the P1.

[0222] As one embodiment, the P1 is greater than 0, and the adjusted P1 includes being increased by at most the P1.

[0223] As one embodiment, the P1 is less than 0, and the adjusted P1 includes being decreased by the absolute value of the P1.

[0224] As one embodiment, the P1 is less than 0, and the adjusted P1 includes being decreased by at most the absolute value of the P1.

[0225] As one embodiment, the P1 is less than 0, and the adjusted P1 includes being decreased by at least the absolute value of the P1.

[0226] As one embodiment, the P1 is equal to 0, and the adjusted P1 includes being kept unchanged.

[0227] As one embodiment, the adjusted P1 of the number of occupied first-type resources includes the number of occupied first-type resources being adjusted to be not less than the sum of the number of currently occupied first-type resources and the P1.

[0228] As one embodiment, the adjusted P1 of the number of occupied first-type resources includes the number of occupied first-type resources being adjusted to be not greater than the sum of the number of currently occupied first-type resources and the P1.

[0229] As one embodiment, the adjusted P1 of the number of occupied first-type resources includes the number of occupied first-type resources being adjusted to be closest to the sum of the number of currently occupied first-type resources and the P1.

[0230] As one embodiment, when the P1 is greater than 0, the number of occupied first-type resources is adjusted by P1 includes the number of occupied first-type resources is adjusted to be no less than the sum of the number of currently occupied first-type resources and the P1.

[0231] As one embodiment, when the P1 is less than 0, the number of occupied first-type resources is adjusted by P1 includes the number of occupied first-type resources is adjusted to be no more than the sum of the number of currently occupied first-type resources and the P1.

[0232] As one embodiment, the first signaling indicates that the total number of occupied first-type resources is adjusted by the P1.

[0233] As one embodiment, the first signaling indicates that the total number of occupied first-type resources on one carrier is adjusted by the P1.

[0234] As one embodiment, the first signaling indicates that the total number of occupied first-type resources on all carriers is adjusted by the P1.

[0235] As one embodiment, the first signaling indicates that the total number of occupied first-type resources on one serving cell is adjusted by the P1.

[0236] As one embodiment, the first signaling indicates that the total number of occupied first-type resources on all serving cells is adjusted by the P1.

[0237] As one embodiment, the first signaling indicates that the number of first-type resources occupied by one operation is adjusted by the P1, the one operation includes reasoning.

[0238] As one embodiment, the first signaling indicates that the total number of first-type resources occupied by a plurality of operations is adjusted by the P1, each operation in the plurality of operations includes reasoning.

[0239] As one sub-embodiment of the above embodiment, any two operations in the plurality of operations occupy first-type resources at a time that overlaps.

[0240] As one embodiment, the first signaling indicates that the number of first-type resources occupied by one function is adjusted by the P1, the one function relies on reasoning.

[0241] As one sub-embodiment of the above embodiment, implementation of the one function relies on reasoning.

[0242] As one sub-embodiment of the above embodiment, the first node implements the one function using an operation that includes reasoning.

[0243] As one embodiment, the first signaling indicates that a total number of first type resources occupied by a plurality of functions is adjusted by the P1, each function of the plurality of functions relies on inference.

[0244] As one sub-embodiment of the above embodiment, implementation of each function of the plurality of functions relies on inference.

[0245] As one sub-embodiment of the above embodiment, the first node implements any function of the plurality of functions using operations including inference.

[0246] As one sub-embodiment of the above embodiment, any two functions of the plurality of functions overlap in time in occupying the first type resources.

[0247] Embodiment 2

[0248] Embodiment 2 illustrates a schematic diagram of a network architecture according to one embodiment of the present application, as shown in FIG. 2.

[0249] FIG. 2 illustrates a network architecture 200. The network architecture 200 is a 5G NR (New Radio) / LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution Advanced) system, or the network architecture 200 is a 5G+ network architecture, or the network architecture 200 is a 6G network architecture, or the network architecture 200 is a network architecture adopted in 3GPP future continued evolution; the network architecture 200 can be referred to as 5GS (5G System) / EPS (Evolved Packet System), or the network architecture 200 can be referred to as 6GS (6G System); the network architecture 200 includes a UE (User Equipment) 201, a RAN (Radio Access Network) 202, a core network 210, at least one of a HSS (Home Subscriber Server) / UDM (Unified Data Management) 220 and an Internet service 230. The network architecture 200 can be interconnected with other access networks, but these entities / interfaces are not shown for simplicity. As illustrated, the network architecture 200 provides packet-switched services, however, those skilled in the art will readily appreciate that the various concepts presented throughout this application are amenable to use with networked systems including, but not limited to, 5G, 6G, and other 3GPP future continued evolution networks that provide circuit-switched services. The RAN includes a node 203. The RAN can also include other nodes 204. The node 203 provides user and control plane protocol terminations toward the UE 201. The node 203 can be connected to the other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. The node 203 can also be referred to as a base station, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a TRP (Transmit Receive Point), or some other suitable terminology. The core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC; the node 203 provides an access point to the core network 210 for the UE 201.Examples of a UE 201 include a cellular phone, a smart phone, a session initiation protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a non-tethered base station communication, a satellite mobile communication, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., MP3 player), a camera, a game console, a drone, a flying vehicle, a narrowband internet of things device, a machine type communication device, a land vehicle, a car, a wearable device, or any other similar functional device. Those skilled in the art will also The node 203 is connected by an S1 / NG interface to the core network 210. The core network 210 includes a MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MME / AMF / SMF 214, a S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Date Network Gateway) / UPF 213. The MME / AMF / SMF 211 is a control node that handles signaling between the UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocal) packets are transferred through the S-GW / UPF 212, which itself is connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation as well as other functions. The P-GW / UPF 213 is connected to the Internet services 230. The Internet services 230 include operator corresponding Internet protocol services, which can specifically include the Internet, an intranet, an IMS (IP Multimedia Subsystem), and a packet switching service.

[0250] As one embodiment, the first node comprises the UE 201.

[0251] As one embodiment, the second node comprises the node 203.

[0252] As one embodiment, the wireless link between the UE 201 and the node 203 comprises a cellular network link.

[0253] As one embodiment, the sender of the first report comprises the UE 201.

[0254] As one embodiment, the receiver of the first report comprises the node 203.

[0255] As one embodiment, the sender of the first signaling comprises the node 203.

[0256] As one embodiment, the receiver of the first signaling comprises the UE 201.

[0257] As one embodiment, the sender of the second report comprises the UE 201.

[0258] As one embodiment, the receiver of the second report comprises the node 203.

[0259] As one embodiment, the UE 201 supports AI or ML based operations.

[0260] As one embodiment, the node 203 supports AI or ML based operations.

[0261] Embodiment 3

[0262] Embodiment 3 illustrates a schematic diagram of an embodiment of a radio protocol architecture for the user plane and control plane, according to one embodiment of the application, as shown in FIG. 3.

[0263] Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300, Figure 3 showing three layers of the 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: Layer 1, Layer 2, and Layer 3. Layer 1 (LI layer) is the lowest layer and implements various PHY (Physical layer) signal processing functions. The LI 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 terminate the functions of 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 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 the use of RRC signaling between the second communication node device and the first communication node device for configuring the lower layers. The radio protocol architecture for the user plane 350 includes Layer 1 (LI layer) and Layer 2 (L2 layer), which are substantially the same as the corresponding layers and sublayers in the control plane 300 for the physical layer 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.).

[0264] As one embodiment, the wireless protocol architecture in FIG. 3 is applicable to the first node.

[0265] As one embodiment, the wireless protocol architecture in FIG. 3 is applicable to the second node.

[0266] As one embodiment, the higher layer in this application refers to a layer above the physical layer.

[0267] As one embodiment, the first report is generated at the RLC sublayer 353.

[0268] As one embodiment, the first report is generated at the PDCP sublayer 354.

[0269] As one embodiment, the first report is generated at the SDAP sublayer 356.

[0270] As one embodiment, the first signaling is generated at the PHY 301 or the PHY 351.

[0271] As one embodiment, the first signaling is generated at the MAC sublayer 302 or the MAC sublayer 352.

[0272] As one embodiment, the second report is generated at the MAC sublayer 302 or the MAC sublayer 352.

[0273] As one embodiment, the second report is generated at the PHY 301 or the PHY 351.

[0274] As one embodiment, the first physical layer channel is generated at the PHY 301 or the PHY 351.

[0275] As one embodiment, the first CSI is generated at the PHY 301 or the PHY 351.

[0276] Embodiment 4

[0277] Embodiment 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of the present application, as shown in FIG. 4. FIG. 4 is a block diagram of a first communication device 410 and a second communication device 450 in communication with each other over an access network.

[0278] 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.

[0279] 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.

[0280] 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 (DownLink), 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, to generate one or more parallel streams. The transmit processor 416 then maps each parallel stream to a subcarrier, multiplexes the modulated symbols in the time and / or frequency domain with reference signals (e.g., pilot), and then performs a Fast Fourier Transform (FFT) to produce a time-domain multi-carrier symbol stream. The multi-antenna transmit processor 471 then performs transmit analog pre-coding / beamforming operations on the time-domain multi-carrier symbol stream. Each transmitter 418 converts the baseband multi-carrier symbol stream provided by the multi-antenna transmit processor 471 into a radio frequency signal that is transmitted via a respective antenna 420.

[0281] In the transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its respective antenna 452. Each receiver 454 recovers information modulated onto an RF carrier and converts the RF stream into a baseband multi-carrier symbol stream that provides to the receive processor 456. The receive processor 456 and the multi-antenna receive processor 458 implement various signal processing functions of the L1 layer. The multi-antenna receive processor 458 performs receive analog precoding / beamforming operation on the baseband multi-carrier symbol stream from the receivers 454. The receive processor 456 converts the baseband multi-carrier symbol stream from the receive analog precoding / beamforming operation from the time domain to the frequency domain using a Fast Fourier Transform (FFT). In the frequency domain, the physical layer data signals and the reference signals are demultiplexed by the receive processor 456, where the reference signals will be used for channel estimation, and the data signals are recovered after multi-antenna detection in the multi-antenna receive processor 458 for any parallel streams destined to the second communication device 450. The symbols on each parallel stream are demodulated and recovered in the receive processor 456 and generate soft decisions. The receive processor 456 then decodes and de-interleaves the soft decisions to recover the upper layer data and control signals transmitted by the first communication device 410 on the physical channels. The upper layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of the L2 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, 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.

[0282] 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, in conjunction with a multi-antenna transmit processor 457, performs modulation mapping, channel coding processing, digital multi-antenna spatial processing, including codebook-based and non-codebook-based precoding, and beamforming processing, and then the transmit processor 468 creates parallel streams of coded and modulated symbols for the different antenna ports, which are provided to different antennas 452 via separate transmitters 454 after analog precoding / beamforming at the multi-antenna transmit processor 457. Each transmitter 454 then converts the baseband streams into radio frequency signals and transmits the radio frequency signals via the antennas 452.

[0283] 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, in conjunction with the controller / processor 475, implement the L1 layer functions. The controller / processor 475 implements the L2 layer functions. 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.

[0284] As one embodiment, the second communication device 450 comprises: at least one processor and at least one memory including a computer program code; the at least one memory and the computer program code are configured to, with the at least one processor, cause the second communication device 450 to perform at least the following: transmitting the first report; receiving the first signaling. The first report indicates L0 first-type resources, L0 being a positive integer; the first signaling indicates that the number of occupied first-type resources is adjusted by P1, P1 being an integer; the L0 first-type resources are used for inference.

[0285] As one embodiment, the second communication device 450 comprises: a memory storing a computer readable program of instructions which, when executed by at least one processor, causes actions comprising: transmitting the first report; receiving the first signaling.

[0286] As one embodiment, the first communication device 410 comprises: at least one processor and at least one memory including a computer program code; the at least one memory and the computer program code are configured to, with the at least one processor, cause the first communication device 410 to perform at least the following: receiving the first report; transmitting the first signaling. The first report indicates L0 first-type resources, L0 being a positive integer; the first signaling indicates that the number of occupied first-type resources is adjusted by P1, P1 being an integer; the L0 first-type resources are used for inference.

[0287] As one embodiment, the first communication device 410 comprises: a memory storing a computer readable program of instructions which, when executed by at least one processor, causes actions comprising: receiving the first report; transmitting the first signaling.

[0288] As one embodiment, the first node in the present application comprises the second communication device 450.

[0289] As one embodiment, the second node in the present application comprises the first communication device 410.

[0290] As one embodiment, at least one of {the antenna 420, the receiver 418, the reception processor 470, the multi-antenna reception processor 472, the controller / processor 475, the memory 476} is configured to receive the first report; at least one of {the antenna 452, the transmitter 454, the transmission processor 468, the multi-antenna transmission processor 457, the controller / processor 459, the memory 460, the data source 467} is configured to transmit the first report.

[0291] 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 signaling; 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 signaling.

[0292] 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 second report; 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 second report.

[0293] Embodiment 5

[0294] Embodiment 5 illustrates a flowchart of 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 transmission over an air interface. In FIG. 5, the steps in the blocks F51 to F58 are optional, respectively.

[0295] For the second node U1, the first report is received in step S511; the second CSI is received in step S5102; the second report is received in step S5103; the first signaling is transmitted in step S512; the first CSI is transmitted in step S5105.

[0296] For the first node U2, the first operation is deployed in step S5201; at least one of the P candidate operations is deployed in step S5202; the first report is transmitted in step S521; the second CSI is transmitted in step S5204; the second report is transmitted in step S5205; the first signaling is received in step S522; the L2 is determined in step S5206; the first CSI is received in step S5208.

[0297] In Embodiment 5, the first report indicates L0 first-type resources, L0 being a positive integer; the first signaling indicates that the number of occupied first-type resources is adjusted by P1, P1 being an integer; and the L0 first-type resources are used for inference.

[0298] As an embodiment, the first node U2 is the first node in the present application.

[0299] As an embodiment, the second node U1 is the second node in the present application.

[0300] 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.

[0301] 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.

[0302] 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.

[0303] As an embodiment, the second node U1 is a serving cell maintaining base station of the first node U2.

[0304] As an embodiment, the first report is transmitted on a PUSCH (Physical Uplink Shared Channel).

[0305] As an embodiment, the first signaling is transmitted on a PDSCH (Physical Downlink Shared Channel).

[0306] As an embodiment, the step in block F55 in Figure 5 exists, the second report indicates that L1 first-type resources are unoccupied, L1 being a positive integer.

[0307] As an embodiment, the second report is transmitted on a PUSCH.

[0308] As an embodiment, the second report is earlier than the first signaling.

[0309] As an embodiment, the benefits of the above method include facilitating the network side to more reasonably adjust the number of occupied first-type resources according to the number of available first-type resources.

[0310] As an embodiment, the step in block F56 in Figure 5 exists, L2 being a positive integer; L2 first-type resources are occupied, L2 depending on P1.

[0311] As one embodiment, the L2 first-type resources are occupied by a first operation; candidates of the number of first-type resources occupied by the first operation include M values, the M is a positive integer greater than 1, the M values are positive integers respectively, and the L2 is one of the M values.

[0312] As one sub-embodiment of the above embodiment, the M values are all different from each other.

[0313] As one sub-embodiment of the above embodiment, each of the M values is a candidate of the number of first-type resources occupied by the first operation.

[0314] As one sub-embodiment of the above embodiment, the first report indicates the maximum value of the M values.

[0315] As one sub-embodiment of the above embodiment, the first report indicates the maximum value and the minimum value of the M values.

[0316] As one sub-embodiment of the above embodiment, the first report indicates the M values.

[0317] The above method has the advantages of providing more information to facilitate the network side to further optimize scheduling.

[0318] As one sub-embodiment of the above embodiment, the first report indicates the first operation and the maximum value of the M values.

[0319] As one sub-embodiment of the above embodiment, the first operation is associated with a first identifier, and the first report indicates the first identifier and the maximum value of the M values.

[0320] As one sub-embodiment of the above embodiment, the M values are unknown to the sender of the first signaling.

[0321] The above method has the advantages of supporting different terminals more flexibly.

[0322] The above method has the advantages of saving air interface overhead.

[0323] As one embodiment, the step in block F51 in FIG. 5 exists, and the above method used in the first node for wireless communication includes deploying the first operation.

[0324] As one embodiment, the step in block F51 in FIG. 5 does not exist, and the first operation does not need to be deployed.

[0325] As one sub-embodiment of the above embodiment, the training of the first operation is performed by the first node.

[0326] As one embodiment, the L2 first-type resources are occupied by a first function, the first function has P candidate operations, P is a positive integer greater than 1, L2 is a number of first-type resources occupied by a first candidate operation, the first candidate operation is a candidate operation used for the first function among the P candidate operations.

[0327] As one embodiment, the step in block F52 in FIG. 5 exists, and the method in the first node used for wireless communication includes deploying at least one candidate operation among the P candidate operations.

[0328] As one embodiment, the step in block F52 in FIG. 5 does not exist, and each candidate operation among the P candidate operations does not need to be deployed.

[0329] As one sub-embodiment of the above embodiment, training of each candidate operation among the P candidate operations is performed by the first node.

[0330] As one embodiment, the step in block F57 in FIG. 5 exists, and a scheme adopted by the receiving on the first physical layer channel depends on the P1.

[0331] As one embodiment, the first physical layer channel includes a PDSCH.

[0332] As one embodiment, the first physical layer channel is a PDSCH.

[0333] As one embodiment, the first physical layer channel includes a PDCCH.

[0334] As one embodiment, the first physical layer channel includes a PSSCH (Physical Sidelink Shared Channel).

[0335] As one embodiment, the first physical layer channel carries at least one transport block or code block.

[0336] As one embodiment, the receiving on the first physical layer channel includes one or more of channel estimation, MIMO reception, demodulation, channel decoding, and CRC check.

[0337] As one embodiment, the first node determines a scheme adopted by the receiving on the first physical layer channel according to the P1.

[0338] As one embodiment, the scheme adopted by the receiving on the first physical layer channel includes inference.

[0339] As one embodiment, the receiving on the first physical layer channel has multiple candidate schemes, at least one of the multiple candidate schemes includes an inference.

[0340] As one embodiment, the receiving on the first physical layer channel has multiple candidate schemes, each of the multiple candidate schemes includes an inference.

[0341] As one embodiment, the receiving on the first physical layer channel includes performing the first operation.

[0342] As one embodiment, the receiving on the first physical layer channel includes performing the first candidate operation.

[0343] As one embodiment, the steps in blocks F57 and F53 in FIG. 5 are both present, the method in the first node for wireless communication includes receiving on a second physical layer channel; a scheme employed by the receiving on the first physical layer channel depends on a scheme employed by the receiving on the second physical layer channel and the PI.

[0344] As one sub-embodiment of the above embodiment, the first physical layer channel is a PDSCH, and the second physical layer channel is a PDSCH.

[0345] As one embodiment, the receiving of the second physical layer channel by the first node is later than the sending of the second report.

[0346] As one embodiment, the receiving of the second physical layer channel by the first node is earlier than the sending of the second report.

[0347] As one embodiment, the receiving of the second physical layer channel by the first node is earlier than the receiving of the first signaling.

[0348] As one embodiment, the method in the second node for wireless communication includes sending on the second physical layer channel.

[0349] As one embodiment, the step in block F58 in FIG. 5 is present, a scheme employed by the calculation of the first CSI depends on the PI.

[0350] As one embodiment, the first CSI is transmitted on a PUSCH (Physical Uplink Shared Channel).

[0351] As one embodiment, the first CSI is transmitted on a PUCCH (Physical Uplink Control Channel).

[0352] As one embodiment, the first CSI comprises channel information.

[0353] As one embodiment, the first CSI comprises one or more of CQI, PMI, CRI, LI, RI, SSBRI, RSRP, SINR, capability index, and TDCP.

[0354] As one embodiment, the first CSI comprises compressed CSI.

[0355] As one embodiment, the first CSI comprises predicted CSI.

[0356] As one embodiment, the first CSI comprises predicted beam information.

[0357] As one embodiment, the beam information comprises one or more of CRI, SSBRI, RSRP, and SINR.

[0358] As one embodiment, the first CSI comprises channel matrix.

[0359] As one embodiment, the first CSI comprises precoding matrix.

[0360] As one embodiment, the scheme employed for the computation of the first CSI comprises inference.

[0361] As one embodiment, the computation of the first CSI has multiple candidate schemes, at least one of the multiple candidate schemes comprises inference.

[0362] As one embodiment, the computation of the first CSI has multiple candidate schemes, each of the multiple candidate schemes comprises inference.

[0363] As one embodiment, the computation of the first CSI comprises performing the first operation.

[0364] As one embodiment, the computation of the first CSI comprises performing the first candidate operation.

[0365] As one embodiment, both steps in block F58 and F54 in FIG. 5 exist, the method in the first node for wireless communication comprises transmitting a second CSI; wherein the scheme employed for the computation of the first CSI depends on the scheme employed for the computation of the second CSI and the P1.

[0366] As one embodiment, the second CSI is transmitted on PUSCH (Physical Uplink Shared Channel).

[0367] As an embodiment, the second CSI is transmitted on a PUCCH (Physical Uplink Control Channel).

[0368] As an embodiment, the method in the second node for wireless communication comprises receiving the second CSI.

[0369] As an embodiment, the first node transmits the second CSI later than the second report.

[0370] As an embodiment, the first node transmits the second CSI earlier than the second report.

[0371] As an embodiment, the first node transmits the second CSI earlier than the reception of the first signaling.

[0372] As an embodiment, at least one of the L0 first-type resources comprises one or more first-type sub-resources and one or more second-type sub-resources; at least the first-type sub-resources among the first-type sub-resources and the second-type sub-resources are used for inference.

[0373] Embodiment 6

[0374] Embodiment 6 illustrates a schematic diagram of a second report according to an embodiment of the present application; as shown in FIG. 6. In embodiment 6, the second report indicates that L1 first-type resources are not occupied.

[0375] As an embodiment, the first report indicates that the maximum value of the number of occupied first-type resources is the L0, and the second report indicates that L1 first-type resources are not occupied.

[0376] As an embodiment, the first report indicates that the maximum value of the number of first-type resources supported by the first node is the L0, and the second report indicates that L1 first-type resources are not occupied.

[0377] As an embodiment, the second report is carried by higher layer signaling.

[0378] As an embodiment, the second report is carried by RRC (Radio Resource Control) signaling.

[0379] As an embodiment, the second report is carried by MAC CE (Medium Access Control layer Control Element).

[0380] As one embodiment, the second report is carried by DCI (Downlink Control Information).

[0381] As one embodiment, the L1 is a positive integer not greater than the L0.

[0382] As one embodiment, the L1 is equal to the L0.

[0383] As one embodiment, the L1 is less than the L0.

[0384] As one embodiment, the P1 is not greater than the L1.

[0385] As one embodiment, the L1 is a number of first-type resources of the L0 first-type resources that are not occupied.

[0386] As one embodiment, the L1 first-type resources are L1 unoccupied first-type resources of the L0 first-type resources.

[0387] As one embodiment, the number of unoccupied first-type resources of the L0 first-type resources is the L1.

[0388] As one embodiment, the number of unoccupied first-type resources of the L0 first-type resources is greater than the L1.

[0389] As one embodiment, only the L1 first-type resources of the L0 first-type resources are unoccupied.

[0390] As one embodiment, at least one first-type resource of the L0 first-type resources is unoccupied in addition to the L1 first-type resources.

[0391] As one embodiment, the second report indicates the L1.

[0392] As one embodiment, the second report indicates that the number of unoccupied first-type resources is the L1.

[0393] As one embodiment, the second report indicates that the number of unoccupied first-type resources of the L0 first-type resources is the L1.

[0394] As one embodiment, the second report indicates that L1 first-type resources of the L0 first-type resources are unoccupied.

[0395] As one embodiment, the second report indicates that at least L1 unoccupied first-type resources of the L0 first-type resources.

[0396] As one embodiment, the second report indicating L1 first-type resources not occupied means that the second report indicates a number of first-type resources not occupied among the L0 first-type resources is the L1.

[0397] As one embodiment, the second report indicating L1 first-type resources not occupied means that the second report indicates L1 first-type resources not occupied among the L0 first-type resources.

[0398] As one embodiment, the second report indicating L1 first-type resources not occupied means that the second report indicates at least L1 first-type resources not occupied among the L0 first-type resources.

[0399] As one embodiment, the second report indicates L1 first-type resources not occupied among the L0 first-type resources; which first-type resource or resources of the L0 first-type resources not occupied is unknown to a target recipient of the second report.

[0400] As one embodiment, the second report indicates L1 first-type resources not occupied among the L0 first-type resources and indicates which first-type resource or resources not occupied.

[0401] As one embodiment, the L1 depends on a total number of first-type resources occupied.

[0402] As one embodiment, the L1 depends on a total number of first-type resources occupied at a point in time.

[0403] As one embodiment, the L1 depends on a total number of first-type resources occupied in a symbol or time slot.

[0404] As one embodiment, the L1 depends on a total number of first-type resources occupied on one carrier or one serving cell.

[0405] As one embodiment, the L1 depends on a total number of first-type resources occupied on all carriers or all serving cells.

[0406] As one embodiment, the L1 depends on a total number of first-type resources occupied on one carrier or one serving cell at a point in time.

[0407] As one embodiment, the L1 depends on a total number of first-type resources occupied on all carriers or all serving cells at a point in time.

[0408] As one embodiment, the L1 depends on a total number of first-type resources occupied on one carrier or one serving cell in a symbol or time slot.

[0409] As one embodiment, the LI depends on a total number of first type resources occupied in one symbol or time slot across all carriers or across all serving cells.

[0410] As one embodiment, the LI is a number of first type resources not occupied at one point in time.

[0411] As one embodiment, the LI is a number of first type resources not occupied in one symbol or time slot.

[0412] As one embodiment, the LI is a number of first type resources not occupied on one carrier or on one serving cell.

[0413] As one embodiment, the LI is a number of first type resources not occupied across all carriers or across all serving cells.

[0414] As one embodiment, the LI is a number of first type resources not occupied on one carrier or on one serving cell at one point in time.

[0415] As one embodiment, the LI is a number of first type resources not occupied across all carriers or across all serving cells at one point in time.

[0416] As one embodiment, the LI is a number of first type resources not occupied on one carrier or on one serving cell in one symbol or time slot.

[0417] As one embodiment, the LI is a number of first type resources not occupied across all carriers or across all serving cells in one symbol or time slot.

[0418] As one embodiment, a first type resource being occupied includes the one first type resource not being free.

[0419] As one embodiment, a first type resource being occupied includes the one first type resource having been used for inference.

[0420] As one embodiment, a first type resource being occupied includes the one first type resource having been used for inference required computation or processing.

[0421] As one embodiment, a first type resource being occupied includes the one first type resource having been used for inference required storage.

[0422] As one embodiment, a first type resource being occupied includes the one first type resource having been used for inference required storage and inference required computation or processing.

[0423] As one embodiment, one first-type resource being unoccupied includes the one first-type resource being idle.

[0424] As one embodiment, one first-type resource being unoccupied includes the one first-type resource not having been used for inference.

[0425] As one embodiment, one first-type resource being unoccupied includes the one first-type resource not having been used for computation or processing required for inference.

[0426] As one embodiment, one first-type resource being unoccupied includes the one first-type resource not having been used for storage required for inference.

[0427] As one embodiment, one first-type resource being unoccupied includes the one first-type resource not having been used for storage and computation or processing required for inference.

[0428] As one embodiment, if one first-type resource is occupied, the one first-type resource cannot be used for new inference requirements; if one first-type resource is unoccupied, the one first-type resource can be used for new inference requirements.

[0429] As one embodiment, the LI depends on a number of first-type resources occupied by one operation, the one operation including inference.

[0430] As one sub-embodiment of the above embodiment, the LI depends on a difference between the LO and the number of first-type resources occupied by the one operation.

[0431] As one sub-embodiment of the above embodiment, the LI is equal to a difference between the LO and the number of first-type resources occupied by the one operation.

[0432] As one embodiment, the LI depends on a total number of first-type resources occupied by a plurality of operations, each operation of the plurality of operations including inference.

[0433] As one sub-embodiment of the above embodiment, the LI depends on a difference between the LO and the total number of first-type resources occupied by the plurality of operations.

[0434] As one sub-embodiment of the above embodiment, the LI is equal to a difference between the LO and the total number of first-type resources occupied by the plurality of operations.

[0435] As one sub-embodiment of the above embodiment, a time overlap of first-type resources occupied by any two operations of the plurality of operations.

[0436] As one embodiment, the LI depends on a number of first-type resources occupied by one function, the one function depending on inference.

[0437] As one sub-example of the above example, the implementation of the one function relies on inference.

[0438] As one sub-example of the above example, the one function is implemented by inference.

[0439] As one sub-example of the above example, the one function is implemented by an operation comprising inference.

[0440] As one sub-example of the above example, the L1 relies on the difference between the L0 and the number of first-type resources occupied by the one function.

[0441] As one sub-example of the above example, the L1 is equal to the difference between the L0 and the number of first-type resources occupied by the one function.

[0442] As one example, the L1 relies on the total number of first-type resources occupied by a plurality of functions, each of the plurality of functions relying on inference.

[0443] As one sub-example of the above example, the implementation of each of the plurality of functions relies on inference.

[0444] As one sub-example of the above example, any of the plurality of functions is implemented by inference.

[0445] As one sub-example of the above example, any of the plurality of functions is implemented by an operation comprising inference.

[0446] As one sub-example of the above example, the L1 relies on the difference between the L0 and the total number of first-type resources occupied by the plurality of functions.

[0447] As one sub-example of the above example, the L1 is equal to the difference between the L0 and the total number of first-type resources occupied by the plurality of functions.

[0448] As one sub-example of the above example, any two of the plurality of functions overlap in time in occupying first-type resources.

[0449] As one example, the first-type resources occupied by one operation refer to the first-type resources occupied by one execution of the one operation.

[0450] As one example, the first-type resources occupied by one function refer to the first-type resources occupied by inference implementing the one function.

[0451] As one example, the first-type resources occupied by one function refer to the first-type resources occupied by operations implementing the one function.

[0452] As an embodiment, the first type of resources occupied by one function refers to the first type of resources occupied by one execution of operations including inference for implementing the one function.

[0453] Embodiment 7

[0454] Embodiment 7 illustrates a schematic diagram of L2 according to an embodiment of the present application; as shown in FIG. 7. In embodiment 7, the L2 depends on the P1.

[0455] As an embodiment, the L2 is a positive integer no greater than the L0.

[0456] As an embodiment, the L2 increases with the increase of the P1.

[0457] As an embodiment, when the P1 is equal to A1, the L2 is equal to B1; when the P1 is equal to A2, the L2 is equal to B2; the A2 is greater than the A1, and the B2 is no less than the B1.

[0458] As an embodiment, the L2 and the P1 are linearly related, and the linear coefficient between the L2 and the P1 is 1.

[0459] As an embodiment, the P1 is greater than 0, and the linear coefficient between the L2 and the P1 is 1.

[0460] As an embodiment, the P1 is less than 0, and the absolute values of the L2 and the P1 are linearly related, and the linear coefficient between the absolute values of the L2 and the P1 is -1.

[0461] As an embodiment, the L2 is the smallest one of multiple candidate values no less than the sum of L3 and the P1, and the L3 is the number of the first type of resources occupied before the L2 is determined.

[0462] As an embodiment, the L2 is unknown to the sender of the first signaling.

[0463] As an embodiment, the benefits of the above method include better adaptation to different terminals and reduced air interface overhead.

[0464] As an embodiment, the L2 first type of resources are the first type of resources occupied on one carrier or one serving cell.

[0465] As an embodiment, the L2 first type of resources are the first type of resources occupied on all carriers or all serving cells.

[0466] As one embodiment, the L2 first type resources are first type resources occupied by one operation, the one operation including inference.

[0467] As one embodiment, the L2 first type resources are first type resources occupied by multiple operations, each of the multiple operations including inference.

[0468] As one embodiment, the L2 first type resources are first type resources occupied by one function, the one function relying on inference.

[0469] As one embodiment, the L2 first type resources are first type resources occupied by multiple functions, each of the multiple functions relying on inference.

[0470] As one embodiment, the L2 is a total number of first type resources occupied on one carrier or one serving cell.

[0471] As one embodiment, the L2 is a total number of first type resources occupied on all carriers or all serving cells.

[0472] As one embodiment, the L2 is a number of first type resources occupied by one operation, the one operation including inference.

[0473] As one embodiment, the L2 is a total number of first type resources occupied by multiple operations, each of the multiple operations including inference.

[0474] As one embodiment, the L2 is a number of first type resources occupied by one function, the one function relying on inference.

[0475] As one embodiment, the L2 is a total number of first type resources occupied by multiple functions, each of the multiple functions relying on inference.

[0476] As one embodiment, the L2 first type resources are first type resources occupied on one carrier or one serving cell after the first signaling.

[0477] As one embodiment, the L2 first type resources are first type resources occupied on all carriers or all serving cells after the first signaling.

[0478] As one embodiment, the L2 first type resources are first type resources occupied by one or multiple operations after the first signaling, the operations including inference.

[0479] As one embodiment, the L2 first type resources are first type resources occupied by one or multiple functions after the first signaling, the functions relying on inference.

[0480] As one embodiment, the L2 is a total number of the first type of resources occupied on one carrier after the first signaling.

[0481] As one embodiment, the L2 is a total number of the first type of resources occupied on one serving cell after the first signaling.

[0482] As one embodiment, the L2 is a total number of the first type of resources occupied on all carriers after the first signaling.

[0483] As one embodiment, the L2 is a total number of the first type of resources occupied on all serving cells after the first signaling.

[0484] As one embodiment, the L2 is a number of the first type of resources occupied by one operation after the first signaling, the one operation comprising reasoning.

[0485] As one embodiment, the L2 is a number of the first type of resources occupied by one function after the first signaling, the one function relying on reasoning.

[0486] As one embodiment, the L2 is a total number of the first type of resources occupied by a plurality of operations after the first signaling, each operation of the plurality of operations comprising reasoning.

[0487] As one embodiment, the L2 is a total number of the first type of resources occupied by a plurality of functions after the first signaling, each function of the plurality of functions relying on reasoning.

[0488] Embodiment 8

[0489] Embodiment 8 illustrates a diagram of L2 according to one embodiment of the present application; as shown in FIG. 8. In Embodiment 8, the L2 is equal to a sum of L3 and the P1, the L3 is a positive integer.

[0490] As one embodiment, the L3 is a positive integer not greater than the L0.

[0491] As one embodiment, the L3 is a number of the first type of resources previously occupied.

[0492] As one embodiment, the L3 is equal to the L0 minus the L1.

[0493] As one embodiment, the L3 is a number of the first type of resources occupied before the first signaling.

[0494] As one embodiment, the L3 is a total number of the first type of resources occupied on one carrier before the first signaling.

[0495] As one embodiment, the L3 is the total number of first-type resources occupied before the first signaling on all carriers.

[0496] As one embodiment, the L3 is the total number of first-type resources occupied before the first signaling on one serving cell.

[0497] As one embodiment, the L3 is the total number of first-type resources occupied before the first signaling on all serving cells.

[0498] As one embodiment, the L3 is the number of first-type resources occupied before the second report.

[0499] As one embodiment, the L3 is the total number of first-type resources occupied before the second report on one carrier.

[0500] As one embodiment, the L3 is the total number of first-type resources occupied before the second report on all carriers.

[0501] As one embodiment, the L3 is the total number of first-type resources occupied before the second report on one serving cell.

[0502] As one embodiment, the L3 is the total number of first-type resources occupied before the second report on all serving cells.

[0503] As one embodiment, the L3 is the number of first-type resources occupied by one operation before the first signaling, the one operation including reasoning.

[0504] As one embodiment, the L3 is the number of first-type resources occupied by one function before the first signaling, the one function depending on reasoning.

[0505] As one embodiment, the L3 is the number of first-type resources occupied by no later than one execution of one operation before the first signaling, the one operation including reasoning.

[0506] As one embodiment, the L3 is the number of first-type resources occupied by no later than one implementation of one function before the first signaling, the one function depending on reasoning.

[0507] As one embodiment, the L3 is the number of first-type resources occupied by no later than the most recent execution of one operation before the first signaling, the one operation including reasoning.

[0508] As one embodiment, the L3 is a number of the first type of resources occupied by one function not later than a most recent implementation of the first signaling, the one function relying on inference.

[0509] As one embodiment, the L3 is a total number of the first type of resources occupied by a plurality of operations before the first signaling, each of the plurality of operations including inference.

[0510] As one sub-embodiment of the above embodiment, any two of the plurality of operations overlap in time in occupying the first type of resources.

[0511] As one sub-embodiment of the above embodiment, the L3 is a total number of the first type of resources occupied by the plurality of operations within a time window, any two of the plurality of operations overlapping in time in occupying the first type of resources within the time window, a start time of the first time window being earlier than a start symbol of the first signaling.

[0512] As one embodiment, the L3 is a total number of the first type of resources occupied by a plurality of functions before the first signaling, each of the plurality of functions relying on inference.

[0513] As one sub-embodiment of the above embodiment, any two of the plurality of functions overlap in time in occupying the first type of resources.

[0514] As one sub-embodiment of the above embodiment, the L3 is a total number of the first type of resources occupied by the plurality of functions within a time window, any two of the plurality of functions overlapping in time in occupying the first type of resources within the time window, a start time of the first time window being earlier than a start symbol of the first signaling.

[0515] As one embodiment, the L3 is a number of the first type of resources occupied by one operation before the second reporting, the one operation including inference.

[0516] As one embodiment, the L3 is a number of the first type of resources occupied by one function before the second reporting, the one function relying on inference.

[0517] As one embodiment, the L3 is a number of the first type of resources occupied by one operation not later than a most recent execution of the second reporting, the one operation including inference.

[0518] As one embodiment, the L3 is a number of the first type of resources occupied by one function not later than a most recent implementation of the second reporting, the one function relying on inference.

[0519] As one embodiment, the L3 is the total number of the first type of resources occupied by the plurality of operations or the plurality of functions before the second report.

[0520] As one embodiment, the L3 is the number of the first type of resources occupied in the first time pool.

[0521] As one embodiment, the first time pool is one symbol.

[0522] As one embodiment, the first time pool is one slot.

[0523] As one embodiment, the first time pool depends on the first signaling.

[0524] As one embodiment, the first time pool depends on the time domain resource of the first signaling.

[0525] As one embodiment, the first signaling indicates the first time pool.

[0526] The benefits of the above method include increasing the scheduling flexibility of the network side and further optimizing the performance.

[0527] As one embodiment, the first time pool depends on the second report.

[0528] As one embodiment, the first time pool depends on the time domain resource of the second report.

[0529] As one embodiment, the second report indicates the first time pool.

[0530] The benefits of the above method include increasing the flexibility of the terminal.

[0531] As one embodiment, the L3 is unknown to the sender of the first signaling.

[0532] As one embodiment, the benefits of the above method include better adaptation to different terminals and reduced air interface overhead.

[0533] As one embodiment, the L2 is the number of the first type of resources occupied after the first signaling, and the L3 is the number of the first type of resources occupied before the first signaling.

[0534] As one embodiment, the L2 is the number of the first type of resources occupied after the first signaling, and the L3 is the number of the first type of resources occupied before the second report.

[0535] As an embodiment, the L2 is the total number of the first type of resources occupied by the first operation after the first signaling, and the L3 is the total number of the first type of resources occupied by the first operation before the first signaling.

[0536] As an embodiment, the L2 is the number of the first type of resources occupied by the first operation after the first signaling, and the L3 is the number of the first type of resources occupied by the first operation before the first signaling.

[0537] As an embodiment, the L2 is the number of the first type of resources occupied by the first function after the first signaling, and the L3 is the number of the first type of resources occupied by the first function before the first signaling.

[0538] Embodiment 9

[0539] Embodiment 9 illustrates a diagram of L2 according to an embodiment of the present application; as shown in FIG. 9. In Embodiment 9, the L2 is the minimum one of the plurality of candidate values that is not less than the sum of L3 and P1, and the L3 is a positive integer.

[0540] Embodiment of L3 is seen in Embodiment 8.

[0541] As an embodiment, any one of the plurality of candidate values is a positive integer.

[0542] As an embodiment, any one of the plurality of candidate values is a positive integer that is not greater than L0.

[0543] As an embodiment, the plurality of candidate values is configurable.

[0544] As an embodiment, the plurality of candidate values depends on the configuration of a higher layer parameter.

[0545] As an embodiment, the plurality of candidate values is unknown to the sender of the first signaling.

[0546] As an embodiment, the plurality of candidate values depends on the capability of the first node.

[0547] As an embodiment, the plurality of candidate values is the M values.

[0548] As an embodiment, the plurality of candidate values is the number of the first type of resources occupied by the P candidate operations respectively.

[0549] As an embodiment, the plurality of candidate values is P candidate values, and the P candidate values are respectively the number of the first type of resources occupied by the P candidate operations.

[0550] As one embodiment, the L2 is the number of first-type resources occupied by a first operation, and determining the L2 refers to determining the number of first-type resources occupied by the first operation as the L2.

[0551] As one embodiment, the first node determines the number of first-type resources occupied by a current execution of the first operation as the L2.

[0552] As one embodiment, the first node determines the number of first-type resources occupied by a next execution of the first operation as the L2.

[0553] As one embodiment, the L2 is the number of first-type resources occupied by a first function, and determining the L2 refers to determining the number of first-type resources occupied by the first function as the L2.

[0554] As one embodiment, the first node determines the number of first-type resources occupied by a candidate operation used to implement the first function as the L2.

[0555] As one embodiment, the first node determines the number of first-type resources currently occupied by a candidate operation used to implement the first function as the L2.

[0556] As one embodiment, the first node determines the number of first-type resources next occupied by a candidate operation used to implement the first function as the L2.

[0557] Embodiment 10

[0558] Embodiment 10 illustrates a diagram of L2 first-type resources occupied by a first operation according to one embodiment of the present application; as shown in FIG. 10.

[0559] As one embodiment, the first operation occupies the L2 first-type resources after the first signaling.

[0560] As one embodiment, a first execution of the first operation after the first signaling occupies the L2 first-type resources.

[0561] As one embodiment, a first execution of the first operation after Q symbols after the first signaling occupies the L2 first-type resources, and the Q is a positive integer.

[0562] As one embodiment, the L2 is the number of first-type resources occupied by the first operation after the first signaling.

[0563] As an embodiment, the L2 is a number of the first type of resources occupied by a first execution of the first operation after a first signaling of the first signaling.

[0564] As an embodiment, the L2 is a number of the first type of resources occupied by a first execution of the first operation after a first signaling of the first signaling.

[0565] As an embodiment, the Q is configurable.

[0566] As an embodiment, the Q is dependent on a configuration of a higher layer parameter.

[0567] As an embodiment, the Q is configured to the first node.

[0568] As an embodiment, the Q is dependent on a capability of the first node.

[0569] As an embodiment, the Q is reported by the first node.

[0570] As an embodiment, the Q is reported by the first node through a UE capability IE.

[0571] As an embodiment, the Q is fixed.

[0572] As an embodiment, the first node determines the L2 based on the P1.

[0573] As an embodiment, the L2 is a minimum value of the M values that is not less than a sum of L3 and the P1, the L3 being a positive integer.

[0574] As an embodiment, the L2 is a value of the M values that has a minimum absolute value of a difference of (L3+the P1), the L3 being a positive integer.

[0575] As an embodiment, the first node randomly selects a value of the M values that is not less than a sum of L3 and the P1 as the L2.

[0576] As an embodiment, the first node alternately selects a value of the M values that is not less than a sum of L3 and the P1 as the L2.

[0577] As an embodiment, the L3 is a number of the first type of resources occupied by the first operation before the first signaling.

[0578] As an embodiment, the L3 is a number of the first type of resources occupied by a latest execution of the first operation before the first signaling.

[0579] As one embodiment, the L3 is the number of first-type resources occupied by the first operation no later than the most recent execution of the first signaling.

[0580] As one embodiment, the L3 is the number of first-type resources occupied by the first operation before the second reporting.

[0581] As one embodiment, the L3 is the number of first-type resources occupied by the first operation no later than one execution of the second reporting.

[0582] As one embodiment, the L3 is the number of first-type resources occupied by the first operation no later than the most recent execution of the second reporting.

[0583] As one embodiment, the L3 is the number of first-type resources occupied by the first operation in the first time pool.

[0584] Embodiments of the first time pool are seen in embodiment 8.

[0585] As one embodiment, the first operation is based on training.

[0586] As one embodiment, the first operation is obtained through training.

[0587] As one embodiment, the models of the first operation are all obtained through training.

[0588] As one embodiment, the training of the first operation is performed by the first node.

[0589] As one embodiment, the training of the first operation is performed by a serving cell of the first node.

[0590] As one embodiment, the training of the first operation is performed by a core network.

[0591] As one embodiment, the training of the first operation is performed by an MDA function.

[0592] As one embodiment, the training of the first operation is performed by a NWDAF.

[0593] As one embodiment, the training of the first operation is performed by an MDAS producer.

[0594] As one embodiment, the training of the first operation is performed by an MnS (Management Service) producer.

[0595] As one embodiment, the first operation includes inference.

[0596] As one embodiment, the first operation is inference.

[0597] As one embodiment, the first operation includes an AI entity.

[0598] As one embodiment, the first operation includes a portion of an AI entity for inference.

[0599] As one embodiment, the first operation is performed by an AI entity or an AI function.

[0600] As one embodiment, the first operation is performed by an AI entity or an AI function deployed at the first node.

[0601] As one embodiment, the AI function includes an AI inference function.

[0602] As one embodiment, the AI function includes an AI training function.

[0603] As one embodiment, the AI function includes an AI management function.

[0604] As one embodiment, the AI includes ML (Machine Learning).

[0605] As one embodiment, the AI includes AI and ML.

[0606] As one embodiment, the AI includes AI or ML.

[0607] As one embodiment, the first operation is based on artificial intelligence or machine learning.

[0608] As one embodiment, the first operation is based on a neural network.

[0609] As one embodiment, the first operation is used for generation, prediction, or compression of CSI (Channel State Information).

[0610] As one embodiment, the first operation is used for data reception.

[0611] As one embodiment, the first operation is used for positioning.

[0612] As one embodiment, the first operation is used for scheduling.

[0613] As one embodiment, the first operation is used for semantic-based error correction.

[0614] As one embodiment, the output of the first operation includes channel information.

[0615] As one embodiment, the channel information includes CSI.

[0616] As one embodiment, the channel information includes one or more of CQI (Channel Quality Indicator), PMI (Precoding Matrix Indicator), CRI (CSI-RS Resource Indicator), LI (Layer Indicator), RI (Rank Indicator), SSBRI (SS / PBCH Block Resource Indicator), RSRP (Reference Signal received power), SINR (Signal-to-Interference and Noise Ratio), Capability Index, and TDCP (Time Domain Channel Properties).

[0617] As one embodiment, the channel information includes compressed CSI.

[0618] As one embodiment, the channel information includes predicted CSI.

[0619] As one embodiment, the channel information includes a channel matrix.

[0620] As one embodiment, the channel information includes a precoding matrix.

[0621] As one embodiment, the output of the first operation includes positioning information.

[0622] As one embodiment, the output of the first operation includes recovered TBs (Transport Blocks) or CBs (Code Blocks).

[0623] As one embodiment, the output of the first operation includes scheduling results.

[0624] As one embodiment, the first operation is deployment requiring.

[0625] As one embodiment, the first operation is obtained by load.

[0626] As one embodiment, the first operation is not deployment requiring.

[0627] As one embodiment, the first type of resource is used to perform the first operation.

[0628] As one embodiment, at least one of the L0 first type of resources is used to perform the first operation.

[0629] As one embodiment, any of the L0 first type of resources can be used to perform the first operation.

[0630] As one embodiment, the first operation’s performance occupies the first type of resource.

[0631] As one embodiment, the first operation’s performance occupies at least one of the L0 first type of resources.

[0632] As one embodiment, the first signaling indicates the first operation.

[0633] As one embodiment, the first signaling indicates that the number of the first type of resources occupied by the first operation is adjusted by the P1.

[0634] As one embodiment, the first signaling indicates a first identity, the first operation is associated to the first identity.

[0635] As one embodiment, the first signaling indicates the first operation by indicating the first identity.

[0636] As one embodiment, an operation being associated to an identity includes that the operation is identified by the identity.

[0637] As one embodiment, an operation being associated to an identity includes that a model of the operation is identified by the identity.

[0638] The above method has the benefits of simplifying the design and unifying the understanding of different AI operations or AI models among different nodes.

[0639] As one embodiment, an operation being associated to an identity includes that an AI entity or AI function to which the operation belongs is identified by the identity.

[0640] As one embodiment, an operation being associated to an identity includes that an AI function or AI entity performing the operation is identified by the one identity.

[0641] The benefits of the above method include that the design is simplified and the understanding of different AI entities or AI functions is unified among different nodes.

[0642] As one embodiment, an operation being associated to an identity includes that a training of the operation is identified by the one identity.

[0643] As one embodiment, an operation being associated to an identity includes that a training data set of the operation is identified by the one identity.

[0644] The benefits of the above method include that the design is further simplified by establishing a consensus among different AI functions through identifying an AI training or an AI training data set to recognize the inference generated by this AI training or AI training data set.

[0645] Embodiment 11

[0646] Embodiment 11 illustrates an example of the number of first-type resources occupied by a first operation according to one embodiment of the present application; as shown in FIG. 11. In embodiment 11, the candidates of the number of first-type resources occupied by the first operation include M values.

[0647] As one embodiment, the first operation includes a plurality of sub-operations, one execution of the first operation can include the execution of all or part of the plurality of sub-operations, and when one execution of the first operation includes the execution of different sub-operations in the plurality of sub-operations, the number of first-type resources occupied by the one execution is different values in the M values.

[0648] As one embodiment, the more sub-operations included in one execution of the first operation, the greater the number of first-type resources occupied by the one execution.

[0649] As one embodiment, when one execution of the first operation includes the execution of different sub-operations in the plurality of sub-operations, the performance achieved by the one execution is different.

[0650] As one embodiment, when one execution of the first operation includes the execution of different numbers of sub-operations, the performance achieved by the one execution is different.

[0651] As one embodiment, the more sub-operations included in one execution of the first operation, the better the performance achieved by the one execution.

[0652] As one embodiment, the performance of inference is significantly improved with the increase of the number of parameters of the AI or ML model, and the more the number of parameters, the more the amount of computation and storage space required for inference; therefore, there is a mutual constraint relationship between the performance of inference and resource occupation; the above method provides a selection of different inference performance and resource occupation for the first operation, making the system more flexible, more efficient and more robust.

[0653] As one embodiment, the plurality of sub-operations includes a given sub-operation, and each execution of the first operation must include execution of the given sub-operation.

[0654] As one embodiment, one of the plurality of sub-operations includes at least one convolutional layer.

[0655] As one embodiment, one of the plurality of sub-operations includes at least one encoding layer.

[0656] As one embodiment, two of the plurality of sub-operations respectively include a fully connected layer and at least one encoding layer.

[0657] As one embodiment, an encoding layer includes at least one convolutional layer and a pooling layer.

[0658] As one embodiment, in the convolutional layer, at least one convolutional kernel is used to convolve the input of the first operation to generate a corresponding feature map, and at least one feature map output by the convolutional layer is reshaped into a vector input to the fully connected layer; the fully connected layer converts the one vector into the output of the first operation.

[0659] As one embodiment, at least two of the plurality of sub-operations respectively include at least one convolutional layer or respectively include at least one encoding layer.

[0660] As one sub-embodiment of the above embodiment, each execution of the first operation must include part or all of the at least two sub-operations.

[0661] As one sub-embodiment of the above embodiment, one execution of the first operation can include only part of the at least two sub-operations.

[0662] As one embodiment, one of the plurality of sub-operations includes a fully connected layer, and each execution of the first operation must include the sub-operation including the fully connected layer.

[0663] As one embodiment, determining L2 includes determining which sub-operation or sub-operations of the plurality of sub-operations are included in the execution of the first operation.

[0664] As one embodiment, the first node determines, in association with determining the L2, which one or more of the plurality of sub-operations the execution of the first operation comprises.

[0665] As one embodiment, the M values respectively correspond to M sub-operation combinations, any one of the M sub-operation combinations comprises at least one of the plurality of sub-operations; one execution of the first operation comprises execution of a first sub-operation combination of the M sub-operation combinations; and the first sub-operation combination occupies a number of first-type resources equal to the L2.

[0666] As one embodiment, the M sub-operation combinations respectively occupy a number of first-type resources equal to the M values.

[0667] As one embodiment, the first node determines the first sub-operation combination based on the P1.

[0668] As one embodiment, one execution of the first operation after the first signaling comprises execution of the first sub-operation combination.

[0669] As one embodiment, the first execution of the first operation after the first signaling comprises execution of the first sub-operation combination.

[0670] As one embodiment, the first execution of the first operation after Q symbols after the first signaling comprises execution of the first sub-operation combination.

[0671] As one embodiment, the first sub-operation combination is a sub-operation combination corresponding to a minimum one of the M values that is not less than a sum of L3 and the P1.

[0672] As one embodiment, the first sub-operation combination is a sub-operation combination corresponding to a minimum one of the M values that has a minimum absolute value of a difference between (L3 + the P1).

[0673] As one embodiment, the first node randomly selects the first sub-operation combination from all of the M sub-operation combinations corresponding to a value that is not less than a sum of L3 and the P1.

[0674] As one embodiment, the first node alternately selects, as the first sub-operation combination, a sub-operation combination of the M sub-operation combinations corresponding to a value that is not less than a sum of L3 and the P1.

[0675] As one embodiment, the L3 is a number of first-type resources occupied by a sub-operation combination comprised by one execution of the first operation no later than the first signaling.

[0676] As one embodiment, the L3 is the number of first-type resources occupied by a combination of sub-operations of the first operation included in no later than one execution of the first signaling.

[0677] As one embodiment, the L3 is the number of first-type resources occupied by a combination of sub-operations of the first operation included in one execution of the second reporting.

[0678] As one embodiment, the L3 is the number of first-type resources occupied by a combination of sub-operations of the first operation included in no later than one execution of the second reporting.

[0679] As one embodiment, the L3 is the number of first-type resources occupied by a combination of sub-operations of the first operation included in one execution of the first operation overlapping in time domain and a first time pool.

[0680] Embodiments of the first time pool are seen in embodiment 8.

[0681] Embodiment 12

[0682] Embodiment 12 illustrates a diagram of L2 first-type resources occupied by a first function according to one embodiment of the present application; as shown in FIG. 12.

[0683] As one embodiment, the first function includes an AI or ML based function.

[0684] As one embodiment, the first function includes a function that can be implemented with inference.

[0685] As one embodiment, the first function is based on AI or ML.

[0686] As one embodiment, the first function is based on inference.

[0687] As one embodiment, the first function is implemented with inference.

[0688] As one embodiment, the first function is implemented by inference.

[0689] As one embodiment, the first function can be implemented by inference, and can also be implemented by a scheme that does not include inference.

[0690] As one embodiment, candidates of the scheme adopted by the first function include AI or ML based schemes.

[0691] As one embodiment, candidates of the scheme adopted by the first function include inference.

[0692] As one embodiment, candidates of the scheme adopted by the first function include inference, and also include schemes other than inference.

[0693] As one embodiment, the first function comprises CSI generation, update or computation.

[0694] As one embodiment, the first function comprises one or more of CSI compression, CSI prediction or beam management.

[0695] As one embodiment, the first function comprises data reception.

[0696] As one embodiment, the first function comprises PDSCH reception.

[0697] As one embodiment, the first function comprises one or more of channel estimation, MIMO reception, demodulation, channel decoding and CRC check.

[0698] As one embodiment, the first function comprises positioning.

[0699] As one embodiment, the first function comprises scheduling.

[0700] As one embodiment, the first function comprises semantic based error correction.

[0701] As one embodiment, the first node and the sender of the first signaling have consensus on the first function.

[0702] As one embodiment, the first function is identified by a first identity.

[0703] As one embodiment, the benefit of the above method comprises facilitating consensus on the first function by different nodes.

[0704] As one embodiment, the first function comprises a combination of all or part of a plurality of candidate sub-functions, the combination being identified by a first identity.

[0705] As one sub-embodiment of the above embodiment, the first node and the sender of the first signaling have consensus on the plurality of candidate sub-functions.

[0706] As one sub-embodiment of the above embodiment, the plurality of candidate sub-functions are configured by higher layer signaling.

[0707] As one sub-embodiment of the above embodiment, the plurality of candidate sub-functions are dependent on configuration of higher layer signaling.

[0708] As one sub-embodiment of the above embodiment, the plurality of candidate sub-functions are dependent on capability of the first node.

[0709] As one subembodiment of the above embodiment, the plurality of candidate sub-functions are reported by the first node through a UE capability IE.

[0710] As one subembodiment of the above embodiment, the plurality of candidate sub-functions are predefined.

[0711] As one subembodiment of the above embodiment, different combinations of the plurality of candidate sub-functions are identified by different identities.

[0712] As one reference embodiment of the above subembodiment, the first node and the sender of the first signaling have consensus on the different combinations and corresponding identities.

[0713] As one embodiment, the above method has benefits including more flexible design, adapting to different terminals and application scenarios.

[0714] As one embodiment, the above method has benefits including good forward compatibility.

[0715] As one embodiment, the first signaling indicates the first function.

[0716] As one embodiment, the first signaling indicates that the number of first-type resources occupied by the first function is adjusted by the P1.

[0717] As one embodiment, the first signaling indicates a first identity, the first function being identified by the first identity.

[0718] As one embodiment, the first signaling indicates the first function by indicating the first identity.

[0719] As one embodiment, the number of first-type resources occupied by the first function after the first signaling is the L2.

[0720] As one embodiment, the number of first-type resources occupied by the first function in the first implementation after the first signaling is the L2.

[0721] As one embodiment, the number of first-type resources occupied by the first function in the first implementation after Q symbols after the first signaling is the L2, the Q being a positive integer.

[0722] As one embodiment, the L2 first-type resources are occupied by a candidate operation for implementing the first function after the first signaling.

[0723] As one embodiment, the L2 first-type resources are occupied by the first candidate operation for implementing the first function after the first signaling.

[0724] As one embodiment, the first candidate operation used to implement the first function occupies the L2 first type resources.

[0725] Embodiment 13

[0726] Embodiment 13 illustrates a diagram of P candidate operations of a first function according to one embodiment of the present application; as shown in FIG. 13. In embodiment 13, the first function has P candidate operations, the L2 is the number of first type resources occupied by a first candidate operation, and the first candidate operation is a candidate operation of the P candidate operations used for the first function.

[0727] As one embodiment, any candidate operation of the P candidate operations can be used for the first function.

[0728] As one embodiment, any candidate operation of the P candidate operations is used for the first function.

[0729] As one embodiment, any candidate operation of the P candidate operations can be used to implement the first function.

[0730] As one embodiment, any candidate operation of the P candidate operations is used to implement the first function.

[0731] As one embodiment, the first node can use any candidate operation of the P candidate operations to implement the first function.

[0732] As one embodiment, the first node uses any candidate operation of the P candidate operations to implement the first function.

[0733] As one embodiment, any candidate operation of the P candidate operations is trained.

[0734] As one embodiment, any candidate operation of the P candidate operations is obtained through training.

[0735] As one embodiment, the model of any candidate operation of the P candidate operations is obtained through training.

[0736] As one embodiment, the training of at least one candidate operation of the P candidate operations is performed by the first node.

[0737] As one embodiment, the training of at least one candidate operation of the P candidate operations is performed by the sender of the first signaling.

[0738] As one embodiment, the training of at least one of the P candidate operations is performed by a core network.

[0739] As one embodiment, the training of at least one of the P candidate operations is performed by an MDA function.

[0740] As one embodiment, the training of at least one of the P candidate operations is performed by a NWDAF.

[0741] As one embodiment, the training of at least one of the P candidate operations is performed by an MDAS producer.

[0742] As one embodiment, the training of at least one of the P candidate operations is performed by an MnS producer.

[0743] As one embodiment, any of the P candidate operations comprises an inference.

[0744] As one embodiment, any of the P candidate operations is an inference.

[0745] As one embodiment, any of the P candidate operations comprises an AI entity.

[0746] As one embodiment, any of the P candidate operations comprises a portion of an AI entity used for inference.

[0747] As one embodiment, any of the P candidate operations is performed by an AI entity or an AI function.

[0748] As one embodiment, any of the P candidate operations is performed by an AI entity or an AI function deployed at the first node.

[0749] As one embodiment, any of the P candidate operations is based on artificial intelligence or machine learning.

[0750] As one embodiment, any of the P candidate operations is based on a neural network.

[0751] As one embodiment, an output of any of the P candidate operations comprises channel information.

[0752] As one embodiment, an output of any of the P candidate operations comprises positioning information.

[0753] As one embodiment, the output of any of the P candidate operations comprises a recovered TB or CB.

[0754] As one embodiment, the output of any of the P candidate operations comprises a scheduling result.

[0755] As one embodiment, at least one of the P candidate operations is deployment- requiring.

[0756] As one embodiment, at least one of the P candidate operations is obtained by load.

[0757] As one embodiment, at least one of the P candidate operations is obtained by load from a serving cell of the first node.

[0758] As one embodiment, at least one of the P candidate operations is obtained by load from a core network.

[0759] As one embodiment, at least one of the P candidate operations is deployment- non-requiring.

[0760] As one embodiment, any of the P candidate operations is deployment- non-requiring.

[0761] As one embodiment, at least two of the P candidate operations occupy different amounts of the first type of resource.

[0762] As one embodiment, any two of the P candidate operations occupy different amounts of the first type of resource.

[0763] As one embodiment, at least two of the P candidate operations, when executed, occupy different amounts of the first type of resource.

[0764] As one embodiment, any two of the P candidate operations, when executed, occupy different amounts of the first type of resource.

[0765] As one embodiment, at least two of the P candidate operations achieve different performances.

[0766] As one embodiment, any two of the P candidate operations achieve different performances.

[0767] As one embodiment, at least two of the P candidate operations occupy different amounts of the first type of resource and achieve different performances.

[0768] As an example, any two of the P candidate operations occupy different amounts of the first type of resources and achieve different performance.

[0769] As an example, the performance of inference is significantly improved as the number of parameters of the AI / ML model increases, and the greater the number of parameters, the greater the amount of computation and storage space required for inference; therefore, there is a mutual constraint relationship between the performance of inference and resource occupation; in the above method, the P candidate operations provide different inference performance and resource occupation for the selection of the first function, making the system more flexible, more efficient and more robust.

[0770] As an example, the first report indicates the amount of the first type of resources occupied by each of the P candidate operations.

[0771] As an example, the first report indicates the minimum and maximum of the amount of the first type of resources respectively occupied by the P candidate operations.

[0772] As an example, the first report indicates the maximum of the amount of the first type of resources respectively occupied by the P candidate operations.

[0773] As an example, the benefits of the above method include that more information facilitates the network side to further optimize scheduling.

[0774] As an example, the amount of the first type of resources occupied by at least one of the P candidate operations is unknown to the sender of the first signaling.

[0775] As an example, the amount of the first type of resources occupied by any of the P candidate operations is unknown to the sender of the first signaling.

[0776] As an example, the benefits of the above method include that different terminals are more flexibly supported.

[0777] As an example, the benefits of the above method include that air interface overhead is saved.

[0778] As an example, the first report indicates the P candidate operations.

[0779] As an example, the first report indicates P identities, and the P candidate operations are respectively associated to the P identities.

[0780] As an example, the benefits of the above method include that more information facilitates the network side to further optimize scheduling.

[0781] As an embodiment, at least one of the P candidate operations is unknown to a sender of the first signaling.

[0782] As an embodiment, the P candidate operations are unknown to a sender of the first signaling.

[0783] As an embodiment, benefits of the above method include more flexible support of different terminals.

[0784] As an embodiment, benefits of the above method include saving air interface overhead.

[0785] As an embodiment, the first report indicates a maximum value among quantities of first type resources occupied by the P candidate operations respectively, the P candidate operations being unknown to a sender of the first signaling.

[0786] As an embodiment, a quantity of first type resources occupied by any of the P candidate operations is unknown to a sender of the first signaling, the P candidate operations being unknown to the sender of the first signaling.

[0787] As an embodiment, the first candidate operation is a candidate operation of the P candidate operations used to implement the first function.

[0788] As an embodiment, the first candidate operation is a candidate operation used to implement the first function after the first signaling.

[0789] As an embodiment, the first candidate operation is a first candidate operation used to implement the first function after the first signaling.

[0790] As an embodiment, the first candidate operation is a first candidate operation used to implement the first function after the first signaling and after Q symbols.

[0791] As an embodiment, the Q is configurable.

[0792] As an embodiment, the Q depends on configuration of a higher layer parameter.

[0793] As an embodiment, the Q is configured to the first node.

[0794] As an embodiment, the Q depends on capability of the first node.

[0795] As an embodiment, the Q is reported by the first node.

[0796] As an embodiment, the Q is fixed.

[0797] As one embodiment, the L2 is a number of the first type of resources occupied by one execution of the first candidate operation.

[0798] As one embodiment, determining the L2 comprises determining the first candidate operation.

[0799] As one embodiment, the first node determines the first candidate operation along with determining the L2.

[0800] As one embodiment, the first node determines the first candidate operation based on the P1.

[0801] As one embodiment, the first candidate operation is one of the P candidate operations whose number of the first type of resources occupied is smallest among the numbers of the first type of resources occupied by the P candidate operations which are not less than a sum of L3 and the P1, the L3 being a positive integer.

[0802] As one embodiment, the first candidate operation is one of the P candidate operations whose absolute value of a difference between the number of the first type of resources occupied and (L3+P1) is smallest, the L3 being a positive integer.

[0803] As one embodiment, the first node randomly selects one of the P candidate operations whose number of the first type of resources occupied is not less than a sum of L3 and the P1 as the first candidate operation.

[0804] As one embodiment, the first node selects one of the P candidate operations whose number of the first type of resources occupied is not less than a sum of L3 and the P1 as the first candidate operation in turn.

[0805] As one embodiment, the L3 is a number of the first type of resources occupied by a second candidate operation, the second candidate operation being one of the P candidate operations.

[0806] As one embodiment, the L3 is a number of the first type of resources occupied by one execution of the second candidate operation.

[0807] As one embodiment, the second candidate operation is different from the first candidate operation.

[0808] As one embodiment, the second candidate operation is a candidate operation used to implement the first function before the first signaling.

[0809] As one embodiment, the second candidate operation is a candidate operation used to implement the first function last before the first signaling.

[0810] As one embodiment, the second candidate operation is a candidate operation used to implement the first function before the second report.

[0811] As one embodiment, the second candidate operation is the last candidate operation used to implement the first function before the second report.

[0812] As one embodiment, the first signaling indicates the second candidate operation.

[0813] As one embodiment, the second report indicates the second candidate operation.

[0814] As one embodiment, the second candidate operation is a candidate operation used to implement the first function in a first time pool.

[0815] Embodiment of the first time pool is embodiment 8.

[0816] Embodiment 14

[0817] Embodiment 14 illustrates a diagram of receiving K1 candidate schemes on a first physical layer channel according to one embodiment of the present application; as shown in FIG. 14. In embodiment 14, at least two candidate schemes of the K1 candidate schemes occupy different number of first type resources.

[0818] As one embodiment, the first node determines the scheme adopted by the receiving on the first physical layer channel from the K1 candidate schemes according to the P1.

[0819] As one embodiment, at least one candidate scheme of the K1 candidate schemes includes inference.

[0820] As one embodiment, each candidate scheme of the K1 candidate schemes includes inference.

[0821] As one embodiment, any two candidate schemes of the K1 candidate schemes occupy different number of first type resources.

[0822] As one embodiment, at least two candidate schemes of the K1 candidate schemes achieve different performance.

[0823] As one embodiment, any two candidate schemes of the K1 candidate schemes achieve different performance.

[0824] As one embodiment, any two candidate schemes of the K1 candidate schemes occupy different number of first type resources and achieve different performance.

[0825] As an embodiment, the performance achieved by any of the K1 candidate schemes includes one or more of: a block error probability, a bit error probability, a channel estimation error, a modulation symbol error probability, a maximum MCS (Modulation and Coding Scheme) that can be supported without a block error probability below a given threshold, a throughput, and a number of retransmissions.

[0826] As an embodiment, the performance achieved by any of the K1 candidate schemes includes one or more of: a bit error probability, a channel estimation error, a modulation symbol error probability, a block error probability that is not lower than a given threshold, a maximum MCS (Modulation and Coding Scheme) that can be supported, a throughput, and a number of retransmissions.

[0827] As an embodiment, the performance of inference is significantly improved as the number of parameters of the AI / ML model increases, and the larger the number of parameters, the larger the amount of computation and storage space required for inference; therefore, there is a mutual constraint relationship between the performance of inference and resource occupation; in the above method, the K1 candidate schemes provide a trade-off between different performance and resource occupation for the reception on the first physical layer channel, making the system more flexible, more efficient and more robust.

[0828] As an embodiment, the scheme adopted by the reception on the first physical layer channel is the one with the smallest number of first-type resources occupied among the K1 candidate schemes whose number of first-type resources occupied is not less than the sum of L3 and the P1.

[0829] As an embodiment, the scheme adopted by the reception on the first physical layer channel is the one with the smallest absolute value of the difference between the number of first-type resources occupied and (L3+the P1) among the K1 candidate schemes.

[0830] As an embodiment, the first node randomly selects the scheme adopted by the reception on the first physical layer channel from the K1 candidate schemes whose number of first-type resources occupied is not less than the sum of L3 and the P1.

[0831] As an embodiment, the first node alternately selects the scheme adopted by the reception on the first physical layer channel from the K1 candidate schemes whose number of first-type resources occupied is not less than the sum of L3 and the P1.

[0832] As a preferred embodiment, the L3 is the number of first-type resources occupied by the reception on a second physical layer channel.

[0833] As an embodiment, the first signaling indicates that the number of first-type resources occupied by the reception on the first physical layer channel is adjusted by the P1 compared to the number of first-type resources occupied by the reception on a second physical layer channel.

[0834] As one embodiment, the first signaling indicates that the number of first type of resources occupied by the reception on the first physical layer channel is adjusted by at least the Pi compared to the number of first type of resources occupied by the reception on the second physical layer channel.

[0835] As one embodiment, the first signaling indicates that the number of first type of resources occupied by the reception on the first physical layer channel is adjusted by at most the Pi compared to the number of first type of resources occupied by the reception on the second physical layer channel.

[0836] As one embodiment, the second physical layer channel is a PDSCH.

[0837] As one embodiment, the second physical layer channel is a PDCCH.

[0838] As one embodiment, the second physical layer channel carries at least one transport block or code block.

[0839] As one embodiment, the first physical layer channel is a PDSCH, and the second type of physical layer channel is a PDSCH.

[0840] As one embodiment, the second physical layer channel is a PDSCH before the first signaling.

[0841] As one embodiment, the second physical layer channel is a PDSCH before the first signaling, and the first physical layer channel is a PDSCH after the first signaling.

[0842] As one embodiment, the second physical layer channel is a latest PDSCH before the first signaling.

[0843] As one embodiment, the second physical layer channel is a PDSCH before the second report.

[0844] As one embodiment, the second physical layer channel is a latest PDSCH before the second report.

[0845] As one embodiment, the first signaling indicates the second physical layer channel.

[0846] As one embodiment, the second report indicates the second physical layer channel.

[0847] As one embodiment, the second physical layer channel and the first physical layer channel are transmitted on a same cell.

[0848] As one embodiment, the second physical layer channel and the first physical layer channel are transmitted on a same carrier.

[0849] As one embodiment, the second physical layer channel and the first physical layer channel are transmitted on the same BWP (Bandwidth Part).

[0850] As one embodiment, the second physical layer channel and the first physical layer channel are transmitted on different cells.

[0851] As one sub-embodiment of the above embodiment, the different cells belong to one cell group.

[0852] As one sub-embodiment of the above embodiment, the different cells belong to one frequency band or frequency band combination.

[0853] As one embodiment, the scheme adopted for the reception on the second physical layer channel is one of the K1 candidate schemes.

[0854] As one embodiment, when the P1 is greater than 0, the number of first type resources occupied by the scheme adopted for the reception on the first physical layer channel is greater than the number of first type resources occupied by the scheme adopted for the reception on the second physical layer channel.

[0855] As one embodiment, when the P1 is less than 0, the number of first type resources occupied by the scheme adopted for the reception on the first physical layer channel is less than the number of first type resources occupied by the scheme adopted for the reception on the second physical layer channel.

[0856] As one embodiment, when the P1 is equal to 0, the scheme adopted for the reception on the first physical layer channel is the scheme adopted for the reception on the second physical layer channel.

[0857] As one embodiment, when the P1 is greater than 0 or less than 0, the scheme adopted for the reception on the first physical layer channel is different from the scheme adopted for the reception on the second physical layer channel.

[0858] As one embodiment, when the P1 is greater than 0, the number of first type resources occupied by the scheme adopted for the reception on the first physical layer channel is greater than the number of first type resources occupied by the scheme adopted for the reception on the second physical layer channel, and the performance achieved is superior to the scheme adopted for the reception on the second physical layer channel.

[0859] As one embodiment, when the P1 is less than 0, the number of the first type of resources occupied by the scheme employed by the receiving on the first physical layer channel is less than the number of the first type of resources occupied by the scheme employed by the receiving on the second physical layer channel, and the performance achieved is worse than the performance achieved by the scheme employed by the receiving on the second physical layer channel.

[0860] As one embodiment, in the above method, the sender of the first signaling can increase or decrease the number of the first type of resources occupied by the receiving on the first physical layer channel according to the actual performance indication, for example, in the case where the performance is already good, the occupation of the first type of resources can be reduced by appropriately reducing the performance, or in the case where the performance is poor, the performance can be improved by occupying more first type of resources, so that the whole system is more efficient and robust.

[0861] As one embodiment, the scheme employed by the receiving on the first physical layer channel occupies L2 first type of resources.

[0862] As one embodiment, the number of the first type of resources occupied by the scheme employed by the receiving on the first physical layer channel is the L2.

[0863] As one embodiment, determining the L2 comprises determining the scheme employed by the receiving on the first physical layer channel.

[0864] As one embodiment, determining the L2 comprises determining the scheme employed by the receiving on the first physical layer channel from the K1 candidate schemes.

[0865] As one embodiment, the number of the first type of resources occupied by the scheme employed by the receiving on the first physical layer channel is the L2; determining the L2 comprises determining the scheme employed by the receiving on the first physical layer channel.

[0866] As one embodiment, the number of the first type of resources occupied by the receiving on the first physical layer channel is the L2, and the number of the first type of resources occupied by the receiving on the second physical layer channel is the L3.

[0867] Embodiment 15

[0868] Embodiment 15 illustrates a schematic diagram of the first operation being used for receiving on a first physical layer channel according to one embodiment of the present application; as shown in FIG. 15.

[0869] As one embodiment, the input of the first operation comprises a signal received on the first physical layer channel.

[0870] As one embodiment, the input of the first operation comprises part or all of the signal received on the first physical layer channel.

[0871] As one embodiment, the input of the first operation comprises part or all of the pre-processed signal received on the first physical layer channel.

[0872] As one embodiment, the pre-processing comprises one or more of matrix decomposition, domain transformation, DFT (Discrete Fourier Transform), quantization, shortening, puncturing.

[0873] As one embodiment, the domain transformation comprises one or more of angle domain to space domain transformation, space domain to angle domain transformation, time domain to frequency domain transformation, frequency domain to time domain transformation, delay domain to frequency domain transformation, frequency domain to delay domain transformation, Doppler domain to time domain transformation and time domain to Doppler domain transformation.

[0874] As one embodiment, the output of the first operation comprises recovered transport blocks or code blocks.

[0875] As one embodiment, the output of the first operation comprises recovered transport blocks or code blocks carried by the first physical layer channel.

[0876] As one embodiment, the output of the first operation comprises channel estimation results.

[0877] As one embodiment, the output of the first operation comprises recovered modulation symbols.

[0878] As one embodiment, the K1 is equal to the M, and the number of first type resources occupied by the K1 candidate schemes respectively are the M values.

[0879] As one embodiment, the first operation comprises a plurality of sub-operations, one execution of the first operation can comprise execution of all or part of the plurality of sub-operations, the M values respectively correspond to M sub-operation combinations, any one of the M sub-operation combinations comprises at least one of the plurality of sub-operations; a first sub-operation combination of the M sub-operation combinations is used for the receiving on the first physical layer channel; which of the M sub-operation combinations is the first sub-operation combination depends on the P1.

[0880] Embodiments of the plurality of sub-operations are seen in embodiment 11.

[0881] As one embodiment, the number of first type resources occupied by the M sub-operation combinations respectively are the M values.

[0882] As an embodiment, the M combinations of sub-operations are candidates of the scheme employed by the receiving on the first physical layer channel.

[0883] As an embodiment, the first node determines the first combination of sub-operations according to the P1.

[0884] As an embodiment, the first node determines the first combination of sub-operations from the M combinations of sub-operations according to the P1.

[0885] As an embodiment, the first combination of sub-operations is the one corresponding to the minimum one of the M values that is not less than the sum of L3 and the P1.

[0886] As an embodiment, the first combination of sub-operations is the one corresponding to the one of the M values that has the minimum absolute value of difference from (L3+the P1).

[0887] As an embodiment, the first node randomly selects the first combination of sub-operations from all the combinations of sub-operations whose corresponding values are not less than the sum of L3 and the P1.

[0888] As an embodiment, the first node selects the combinations of sub-operations whose corresponding values are not less than the sum of L3 and the P1 from the M combinations of sub-operations in turn as the first combination of sub-operations.

[0889] As an embodiment, the L3 is the number of first type of resources occupied by the receiving on a second physical layer channel.

[0890] Embodiment 14 is for the second physical layer channel.

[0891] Embodiment 16

[0892] Embodiment 16 illustrates a diagram of a first function including receiving on a first physical layer channel according to an embodiment of the present application; as shown in FIG. 16.

[0893] As an embodiment, the scheme employed by the receiving on the first physical layer channel is one of the P candidate operations.

[0894] As an embodiment, the P candidate operations are candidates of the scheme employed by the receiving on the first physical layer channel.

[0895] As an embodiment, the K1 is equal to the P, and the K1 candidate schemes are the P candidate operations.

[0896] As an embodiment, a first candidate operation of the P candidate operations is used for the receiving on the first physical layer channel, which one of the P candidate operations depends on the P1.

[0897] As an embodiment, the first node determines the first candidate operation according to the P1.

[0898] As an embodiment, the first node determines the first candidate operation from the P candidate operations according to the P1.

[0899] As an embodiment, the first candidate operation is one of the P candidate operations whose number of occupied first type resources is smallest among all candidate operations whose number of occupied first type resources is no less than a sum of L3 and the P1.

[0900] As an embodiment, the first candidate operation is one of the P candidate operations whose absolute value of difference between its number of occupied first type resources and (L3+P1) is smallest.

[0901] As an embodiment, the first node randomly selects the first candidate operation from all candidate operations of the P candidate operations whose number of occupied first type resources is no less than a sum of L3 and the P1.

[0902] As an embodiment, the first node selects the candidate operation of the P candidate operations whose number of occupied first type resources is no less than a sum of L3 and the P1 as the first candidate operation in turn.

[0903] As an embodiment, the L3 is a number of first type resources occupied by receiving on a second physical layer channel.

[0904] Embodiment of the second physical layer channel is seen in embodiment 14.

[0905] Embodiment 17

[0906] Embodiment 17 illustrates a schematic diagram of K2 candidate schemes of calculation of the first CSI according to an embodiment of the present application; as shown in FIG. 17. In embodiment 17, at least two of the K2 candidate schemes have different number of occupied first type resources.

[0907] As an embodiment, the first node determines the scheme adopted by the calculation of the first CSI from the K2 candidate schemes according to the P1.

[0908] As an embodiment, at least one of the K2 candidate schemes includes inference.

[0909] As one embodiment, each of the K2 candidate schemes includes an inference.

[0910] As one embodiment, any two of the K2 candidate schemes differ in the number of first-type resources occupied.

[0911] As one embodiment, at least two of the K2 candidate schemes differ in the performance achieved.

[0912] As one embodiment, any two of the K2 candidate schemes differ in the performance achieved.

[0913] As one embodiment, any two of the K2 candidate schemes differ in the number of first-type resources occupied and the performance achieved.

[0914] As one embodiment, the performance achieved by any of the K2 candidate schemes includes one or more of: throughput, Squared Generalized Cosine Similarity (SGCS), Normalized Mean Square Error (NMSE), CSI prediction accuracy, and hypothetical BLER (Block Error Rate).

[0915] As one embodiment, the CSI prediction accuracy includes RSRP accuracy, beam prediction accuracy, success rate of correct prediction, or various combinations thereof.

[0916] As one embodiment, the beam prediction accuracy includes at least one of: probability that the first (top-1) strongest beam is the first (top-1) predicted beam, probability that the first (top-1) strongest beam is one of the top-K (top-K) predicted beams, probability that the first (top-1) predicted beam is one of the top-K (top-K) strongest beams.

[0917] As one embodiment, the RSRP accuracy includes at least one of: average of the difference between the RSRP of the first (top-1) predicted beam and the RSRP of the first (top-1) strongest beam, CDF (Cumulative Distribution Function) of the difference between the RSRP of the first (top-1) predicted beam and the RSRP of the first (top-1) strongest beam.

[0918] As an embodiment, the correct prediction comprises at least one of a difference between a RSRP of a first (top-1) predicted beam and a RSRP of a strongest beam is no more than x dB, and a difference between a maximum RSRP of a top-K (top-K) predicted beam and the RSRP of the strongest beam is no more than x dB.

[0919] As a sub-embodiment of the above embodiment, the x is configurable.

[0920] As a sub-embodiment of the above embodiment, the x is dependent on measurement accuracy.

[0921] As an embodiment, the performance of inference is significantly improved with an increase in the number of parameters of the AI / ML model, and the greater the number of parameters, the greater the amount of computation and storage space required for inference; therefore, there is a mutual constraint relationship between the performance of inference and resource occupation; in the above method, the K2 candidate schemes provide a trade-off between different performance and resource occupation for the calculation of the first CSI, making the system more flexible, more efficient and more robust.

[0922] As an embodiment, the scheme adopted for the calculation of the first CSI is the one with the smallest number of first-type resources occupied among the K2 candidate schemes whose number of first-type resources occupied is no less than the sum of L3 and P1.

[0923] As an embodiment, the scheme adopted for the calculation of the first CSI is the one with the smallest absolute value of the difference between the number of first-type resources occupied and (L3+P1) among the K2 candidate schemes.

[0924] As an embodiment, the first node randomly selects the scheme adopted for the calculation of the first CSI from the candidate schemes whose number of first-type resources occupied is no less than the sum of L3 and P1 among the K2 candidate schemes.

[0925] As an embodiment, the first node alternately selects the candidate scheme whose number of first-type resources occupied is no less than the sum of L3 and P1 among the K2 candidate schemes as the scheme adopted for the calculation of the first CSI.

[0926] As a preferred embodiment, the L3 is the number of first-type resources occupied for the calculation of the second CSI.

[0927] As an embodiment, the first signaling indicates that the number of first-type resources occupied for the calculation of the first CSI is adjusted by P1 compared to the number of first-type resources occupied for the calculation of the second CSI.

[0928] As one embodiment, the first signaling indicates that the number of first type of resources occupied by the calculation of the first CSI is adjusted by at least the P1 compared to the number of first type of resources occupied by the calculation of the second CSI.

[0929] As one embodiment, the first signaling indicates that the number of first type of resources occupied by the calculation of the first CSI is adjusted by at most the P1 compared to the number of first type of resources occupied by the calculation of the second CSI.

[0930] As one embodiment, the scheme adopted by the calculation of the second CSI is one of the K2 candidate schemes.

[0931] As one embodiment, the second CSI is a CSI reporting before the first signaling.

[0932] As one embodiment, the second CSI is the most recent CSI reporting before the first signaling.

[0933] As one embodiment, the second CSI is a CSI reporting before the second reporting.

[0934] As one embodiment, the second CSI is the most recent CSI reporting before the second reporting.

[0935] As one embodiment, the first signaling indicates the second CSI.

[0936] As one embodiment, the second reporting indicates the second CSI.

[0937] As one preferred embodiment, the first CSI and the second CSI are for the same CSI reporting configuration.

[0938] As one sub-embodiment of the above embodiment, the second CSI is a CSI reporting for the same CSI reporting configuration before the first signaling.

[0939] As one sub-embodiment of the above embodiment, the second CSI is the most recent CSI reporting for the same CSI reporting configuration before the first signaling.

[0940] As one sub-embodiment of the above embodiment, the second CSI is a CSI reporting for the same CSI reporting configuration before the second reporting.

[0941] As one sub-embodiment of the above embodiment, the second CSI is the most recent CSI reporting for the same CSI reporting configuration before the second reporting.

[0942] As a sub-embodiment of the above embodiment, the second CSI is one CSI reporting for the same CSI reporting configuration before the first signaling, and the first CSI is one CSI reporting for the same CSI reporting configuration after the first signaling.

[0943] As an embodiment, the first CSI and the second CSI are for different CSI reporting configurations.

[0944] As an embodiment, the first CSI and the second CSI are for the same cell.

[0945] As an embodiment, the first CSI and the second CSI are transmitted on the same carrier.

[0946] As an embodiment, the first CSI and the second CSI are for the same BWP.

[0947] As an embodiment, the first CSI and the second CSI are for different cells.

[0948] As a sub-embodiment of the above embodiment, the different cells belong to one cell group.

[0949] As a sub-embodiment of the above embodiment, the different cells belong to one frequency band or frequency band combination.

[0950] As a preferred embodiment, the same one or more RS (Reference Signal) resources are used to obtain channel measurements for calculating the first CSI and channel measurements for calculating the second CSI.

[0951] As an embodiment, different RS resources are used to obtain channel measurements for calculating the first CSI and channel measurements for calculating the second CSI.

[0952] As a sub-embodiment of the above embodiment, the different RS resources are configured to the same cell.

[0953] As a sub-embodiment of the above embodiment, the different RS resources are located in the same BWP.

[0954] As a sub-embodiment of the above embodiment, the different RS resources are configured to different cells.

[0955] As an embodiment, when the P1 is greater than 0, the number of first type resources occupied by the scheme adopted for calculating the first CSI is greater than the number of first type resources occupied by the scheme adopted for calculating the second CSI.

[0956] As an embodiment, when the P1 is less than 0, the first CSI is calculated by a scheme occupying a number of first type resources less than a number of first type resources occupied by a scheme for calculating the second CSI.

[0957] As an embodiment, when the P1 is equal to 0, the first CSI is calculated by a scheme identical to a scheme for calculating the second CSI.

[0958] As an embodiment, when the P1 is greater than 0 or less than 0, the first CSI is calculated by a scheme different from a scheme for calculating the second CSI.

[0959] As an embodiment, when the P1 is greater than 0, the first CSI is calculated by a scheme occupying a number of first type resources greater than a number of first type resources occupied by a scheme for calculating the second CSI, and achieving a performance superior to a performance achieved by the scheme for calculating the second CSI.

[0960] As an embodiment, when the P1 is less than 0, the first CSI is calculated by a scheme occupying a number of first type resources less than a number of first type resources occupied by a scheme for calculating the second CSI, and achieving a performance inferior to a performance achieved by the scheme for calculating the second CSI.

[0961] As an embodiment, in the above method, the sender of the first signaling can indicate an increase or decrease in a number of first type resources occupied by CSI calculation according to actual performance, for example, in a case where performance is already good, the occupation of first type resources can be reduced by appropriately reducing performance, or in a case where performance is poor, performance can be improved by occupying more first type resources; making the entire system more efficient and robust.

[0962] As an embodiment, the scheme for calculating the first CSI occupies L2 first type resources.

[0963] As an embodiment, the number of first type resources occupied by the scheme for calculating the first CSI is the L2.

[0964] As an embodiment, determining the L2 comprises determining the scheme for calculating the first CSI.

[0965] As an embodiment, determining the L2 comprises determining the scheme for calculating the first CSI from the K2 candidate schemes.

[0966] As an example, the number of the first type of resources occupied by the scheme employed by the calculation of the first CSI is the L2; determining the L2 comprises determining the scheme employed by the calculation of the first CSI.

[0967] As an example, the number of the first type of resources occupied by the calculation of the first CSI is the L2, and the number of the first type of resources occupied by the calculation of the second CSI is the L3.

[0968] Embodiment 18

[0969] Embodiment 18 illustrates a schematic diagram of the first operation being used for the calculation of the first CSI according to an embodiment of the present application; as shown in FIG. 18.

[0970] As an example, the input of the first operation comprises channel measurement obtained based on RS.

[0971] As an example, the input of the first operation comprises interference measurement obtained based on RS or IM (Interference Measurement) resource.

[0972] As an example, the input of the first operation comprises the result of the measurement of RS after pre-processing.

[0973] As an example, the output of the first operation comprises channel information.

[0974] As an example, the K2 is equal to the M, and the number of the first type of resources occupied by the K2 candidate schemes respectively is the M values.

[0975] As an example, the first operation comprises a plurality of sub-operations, one execution of the first operation can comprise execution of all or part of the plurality of sub-operations, the M values respectively correspond to M sub-operation combinations, any sub-operation combination in the M sub-operation combinations comprises at least one sub-operation in the plurality of sub-operations; a first sub-operation combination in the M sub-operation combinations is used for the calculation of the first CSI; which one of the M sub-operation combinations is the first sub-operation combination depends on the P1.

[0976] Embodiments of the plurality of sub-operations are seen in Embodiment 11.

[0977] As an example, the number of the first type of resources occupied by the M sub-operation combinations respectively is the M values.

[0978] As an example, the M sub-operation combinations are candidates of the scheme employed by the calculation of the first CSI.

[0979] As an example, the first node determines the first sub-operation combination according to the P1.

[0980] As an example, the first node determines the first sub-operation combination from the M sub-operation combinations according to the P1.

[0981] As an example, the first sub-operation combination is the one corresponding to the minimum one of the M values that is not less than the sum of L3 and the P1.

[0982] As an example, the first sub-operation combination is the one corresponding to the one of the M values that has the minimum absolute value of the difference from (L3+the P1).

[0983] As an example, the first node randomly selects the first sub-operation combination from all the sub-operation combinations corresponding to the values that are not less than the sum of L3 and the P1.

[0984] As an example, the first node selects the sub-operation combinations corresponding to the values that are not less than the sum of L3 and the P1 from the M sub-operation combinations in turn as the first sub-operation combination.

[0985] As an example, the L3 is the number of the first type of resources occupied by the calculation of the second CSI.

[0986] Embodiment of the second CSI is shown in embodiment 17.

[0987] Embodiment 19

[0988] Embodiment 19 shows a schematic diagram of the first function including the calculation of the first CSI according to an embodiment of the present application; as shown in FIG. 19.

[0989] As an example, the scheme adopted by the calculation of the first CSI is one of the P candidate operations.

[0990] As an example, the P candidate operations are candidates of the scheme adopted by the calculation of the first CSI.

[0991] As an example, the K2 is equal to the P, and the K2 candidate schemes are the P candidate operations.

[0992] As an example, a first candidate operation in the P candidate operations is used for the calculation of the first CSI, and the first candidate operation is which one of the P candidate operations depends on the P1.

[0993] As an example, the first node determines the first candidate operation according to the P1.

[0994] As an embodiment, the first node determines the first candidate operation from the P candidate operations according to the P1.

[0995] As an embodiment, the first candidate operation is one of the P candidate operations whose number of occupied first-type resources is the smallest among all candidate operations whose number of occupied first-type resources is no less than the sum of L3 and the P1.

[0996] As an embodiment, the first candidate operation is one of the P candidate operations whose absolute value of difference between its number of occupied first-type resources and (L3+P1) is the smallest.

[0997] As an embodiment, the first node randomly selects the first candidate operation from all candidate operations whose number of occupied first-type resources is no less than the sum of L3 and the P1.

[0998] As an embodiment, the first node selects, as the first candidate operation, candidate operations whose number of occupied first-type resources is no less than the sum of L3 and the P1 in turn.

[0999] As an embodiment, the L3 is the number of occupied first-type resources in the calculation of the second CSI.

[1000] Embodiment of the second CSI is shown in embodiment 17.

[1001] Embodiment 20

[1002] Embodiment 20 shows a schematic diagram of at least one of the L0 first-type resources including one or more first-type sub-resources and one or more second-type sub-resources according to an embodiment of the present application; as shown in FIG. 20.

[1003] As an embodiment, each of the L0 first-type resources includes one or more first-type sub-resources and one or more second-type sub-resources.

[1004] As an embodiment, at least one of the L0 first-type resources includes a number of first-type sub-resources and a number of second-type sub-resources which are not equal.

[1005] As an embodiment, one first-type resource being occupied means that at least one first-type sub-resource or at least one second-type sub-resource included in the one first-type resource is occupied; one first-type resource not being occupied means that each first-type sub-resource and each second-type sub-resource included in the one first-type resource is not occupied.

[1006] As an embodiment, one first-type resource is occupied means that all first-type sub-resources and all second-type sub-resources included in the one first-type resource are occupied; one first-type resource is not occupied means that at least one first-type sub-resource or at least one second-type sub-resource included in the one first-type resource is not occupied.

[1007] As an embodiment, the first-type sub-resource is used for computation or processing.

[1008] As an embodiment, the first-type sub-resource is used for computation or processing required by inference.

[1009] As an embodiment, the first-type sub-resource is used for storage.

[1010] As an embodiment, the first-type sub-resource includes storage resource.

[1011] As an embodiment, the first-type sub-resource is used for storage required by inference.

[1012] As an embodiment, the second-type sub-resource is used for storage.

[1013] As an embodiment, the second-type sub-resource is used for storage required by inference.

[1014] As an embodiment, the second-type sub-resource is CSI processing unit.

[1015] As an embodiment, the second-type sub-resource includes storage unit or storage space.

[1016] As an embodiment, the second-type sub-resource includes storage resource.

[1017] As an embodiment, the second-type sub-resource includes memory.

[1018] As an embodiment, the second-type sub-resource includes video memory.

[1019] As an embodiment, the second-type sub-resource is used for storing part or all parameters of AI model or ML model.

[1020] As an embodiment, the second-type sub-resource is used for storing part or all intermediate results of inference.

[1021] As an embodiment, the second-type sub-resource is used for storing part or all outputs of inference.

[1022] As an embodiment, the second type of sub-resource is used to store part or all of parameters of the AI model or the ML model and part or all of intermediate results of the inference.

[1023] As an embodiment, the second type of sub-resource is used to store part or all of parameters of the AI model or the ML model, part or all of intermediate results of the inference, and part or all of outputs of the inference.

[1024] As an embodiment, the parameters of the AI model or the ML model include 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, and a feature map number.

[1025] As an embodiment, the parameters of the AI model or the ML model include one or more 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.

[1026] As an embodiment, both the first type of sub-resource and the second type of sub-resource are used for the inference.

[1027] As an embodiment, the first type of sub-resource is used for computation or processing, and the second type of sub-resource is used for storage.

[1028] As an embodiment, the first type of sub-resource is used for computation or processing required by the inference, and the second type of sub-resource is used for storage required by the inference.

[1029] As an embodiment, the benefit of the above method includes better meeting the requirements of the inference and giving full play to the advantages of AI or ML technology.

[1030] As an embodiment, only the first type of sub-resource of the first type of sub-resource and the second type of sub-resource is used for the inference.

[1031] As an embodiment, the first type of sub-resource is used for the inference, and the second type of sub-resource is used for processing that does not include the inference.

[1032] As an embodiment, the first type of sub-resource is used for the inference, and the second type of sub-resource is a CSI processing unit.

[1033] As an embodiment, the benefit of the above method includes making full use of the existing CSI processing unit and improving the utilization rate.

[1034] As an embodiment, the first type of sub-resource is used for storage, and the second type of sub-resource is used for CSI computation or CSI processing.

[1035] As one embodiment, the first type of sub-resources are used for inference, and the second type of sub-resources are used for CSI computation or CSI processing.

[1036] As one embodiment, benefits of the above method include, making full use of existing CSI processing units, and improving utilization.

[1037] As one embodiment, the number of first type of sub-resources included in each of the L0 first type of resources and the number of second type of sub-resources included in each of the L0 first type of resources are unknown to the sender of the first signaling.

[1038] As one embodiment, the first report indicates the number of first type of sub-resources included in each of at least part of the L0 first type of resources and the number of second type of sub-resources included in each of the at least part of the L0 first type of resources.

[1039] As one embodiment, the first report indicates the number of first type of sub-resources included in each of the L0 first type of resources and the number of second type of sub-resources included in each of the L0 first type of resources.

[1040] As one embodiment, one first type of sub-resource being occupied includes that the one first type of sub-resource is not idle.

[1041] As one embodiment, one first type of sub-resource being occupied includes that the one first type of sub-resource has been used for inference.

[1042] As one embodiment, one first type of sub-resource being occupied includes that the one first type of sub-resource has been used for computation or processing.

[1043] As one embodiment, one first type of sub-resource being occupied includes that the one first type of sub-resource has been used for storage.

[1044] As one embodiment, one first type of sub-resource not being occupied includes that the one first type of sub-resource is idle.

[1045] As one embodiment, one first type of sub-resource not being occupied includes that the one first type of sub-resource has not been used for inference.

[1046] As one embodiment, one first type of sub-resource not being occupied includes that the one first type of sub-resource has not been used for computation or processing.

[1047] As one embodiment, one first type of sub-resource not being occupied includes that the one first type of sub-resource has not been used for storage.

[1048] As one embodiment, one second type of sub-resource being occupied includes that the one second type of sub-resource is not idle.

[1049] As one embodiment, one second-type sub-resource being occupied includes that the one second-type sub-resource has been used for storing.

[1050] As one embodiment, one second-type sub-resource being occupied includes that the one second-type sub-resource has been used for CSI processing.

[1051] As one embodiment, one second-type sub-resource not being occupied includes that the one second-type sub-resource is idle.

[1052] As one embodiment, one second-type sub-resource not being occupied includes that the one second-type sub-resource has not been used for storing.

[1053] As one embodiment, one second-type sub-resource not being occupied includes that the one second-type sub-resource has not been used for CSI processing.

[1054] As one embodiment, the first signaling indicates that the number of first-type sub-resources being occupied is adjusted by P2, and the P2 is an integer.

[1055] As one embodiment, the P2 is greater than 0, and the adjusting by P2 includes: increasing the P2.

[1056] As one embodiment, the P2 is less than 0, and the adjusting by P2 includes: decreasing the absolute value of the P2.

[1057] As one embodiment, the P2 is greater than 0, and the adjusting by P2 includes: increasing at least the P2.

[1058] As one embodiment, the P2 is less than 0, and the adjusting by P2 includes: decreasing at most the absolute value of the P2.

[1059] As one embodiment, the P2 is equal to 0, and the adjusting by P2 includes: keeping unchanged.

[1060] As one embodiment, the first signaling indicates that the total number of first-type sub-resources being occupied on one carrier or one serving cell is adjusted by the P2.

[1061] As one embodiment, the first signaling indicates that the total number of first-type sub-resources being occupied on all carriers or all serving cells is adjusted by the P2.

[1062] As one embodiment, the first signaling indicates that the number of first-type sub-resources being occupied by the first operation is adjusted by the P2.

[1063] As one embodiment, the first signaling indicates that the number of first-type sub-resources being occupied by the first function is adjusted by the P2.

[1064] As one embodiment, the scheme employed by the receiving on the first physical layer channel depends on the P2.

[1065] As one embodiment, the first signaling indicates that the number of first type of sub-resources occupied by the receiving on the first physical layer channel is adjusted by the P2 compared to the number of first type of sub-resources occupied by the receiving on the second physical layer channel.

[1066] As one embodiment, the scheme employed by the calculating of the first CSI depends on the P2.

[1067] As one embodiment, the first signaling indicates that the number of first type of sub-resources occupied by the calculating of the first CSI is adjusted by the P2 compared to the number of first type of sub-resources occupied by the calculating of the second CSI.

[1068] As one embodiment, the first signaling indicates that the number of second type of sub-resources occupied is adjusted by P3, the P3 is an integer.

[1069] As one embodiment, the P3 is greater than 0, the adjusting P3 comprises: increasing the P3.

[1070] As one embodiment, the P3 is less than 0, the adjusting P3 comprises: decreasing the absolute value of the P3.

[1071] As one embodiment, the P3 is greater than 0, the adjusting P3 comprises: increasing at least the P3.

[1072] As one embodiment, the P3 is less than 0, the adjusting P3 comprises: decreasing at most the absolute value of the P3.

[1073] As one embodiment, the P3 is equal to 0, the adjusting P3 comprises: keeping unchanged.

[1074] As one embodiment, the first signaling indicates that the total number of second type of sub-resources occupied on one carrier or one serving cell is adjusted by the P3.

[1075] As one embodiment, the first signaling indicates that the total number of second type of sub-resources occupied on all carriers or all serving cells is adjusted by the P3.

[1076] As one embodiment, the first signaling indicates that the number of second type of sub-resources occupied by the first operation is adjusted by the P3.

[1077] As one embodiment, the first signaling indicates that the number of second type of sub-resources occupied by the first function is adjusted by the P3.

[1078] As one embodiment, the scheme employed by the receiving on the first physical layer channel depends on the P3.

[1079] As one embodiment, the first signaling indicates that the number of second-type sub-resources occupied by the receiving on the first physical layer channel is adjusted by the P3 compared to the number of second-type sub-resources occupied by the receiving on the second physical layer channel.

[1080] As one embodiment, the scheme employed by the calculation of the first CSI depends on the P3.

[1081] As one embodiment, the first signaling indicates that the number of second-type sub-resources occupied by the calculation of the first CSI is adjusted by the P3 compared to the number of second-type sub-resources occupied by the calculation of the second CSI.

[1082] As one embodiment, the first signaling indicates that the number of first-type resources occupied is maintained unchanged, while indicating that the number of first-type sub-resources occupied is adjusted by P2 or the number of second-type sub-resources occupied is adjusted by P3.

[1083] As one sub-embodiment of the above-mentioned embodiment, the first signaling indicates that the total number of first-type sub-resources occupied in all the occupied first-type resources is adjusted by the P2, or the first signaling indicates that the total number of second-type sub-resources occupied in all the occupied first-type resources is adjusted by the P3.

[1084] Embodiment 21

[1085] Embodiment 21 illustrates a schematic of deploying a given operation according to one embodiment of the present application, as shown in FIG. 21; in embodiment 21, the given operation is the first operation or one of the P candidate operations, the first node makes a request to a first producer for loading the given operation, and obtains the given operation from the first producer.

[1086] As one embodiment, the given operation is the first operation.

[1087] As one embodiment, the given operation is one of the P candidate operations.

[1088] As one embodiment, the given operation is needed to be deployed.

[1089] As one embodiment, the deployment includes obtaining the given operation.

[1090] As one embodiment, the deployment includes obtaining an AI entity.

[1091] As one embodiment, the deploying comprises obtaining an AI entity that performs the given operation.

[1092] As one embodiment, the deploying comprises obtaining an AI entity that comprises an AI function that performs the given operation.

[1093] As one embodiment, the deploying comprises obtaining an AI function.

[1094] As one embodiment, the deploying comprises obtaining an AI function that performs the given operation.

[1095] As one embodiment, the deploying comprises loading the given operation.

[1096] As one embodiment, the deploying comprises making a request to load the given operation.

[1097] As one embodiment, the request in Figure 21 is a request to load the given operation made by the first node.

[1098] As one embodiment, the response in Figure 21 is a response to the request to load the given operation made by the first node.

[1099] As one embodiment, the first node obtains the given operation through the response in Figure 21.

[1100] As one embodiment, the first node obtains a model of the given operation through the response in Figure 21.

[1101] As one embodiment, the first node obtains an AI entity that comprises an AI function that performs the given operation through the response in Figure 21.

[1102] As one embodiment, the first node obtains an AI function that performs the given operation through the response in Figure 21.

[1103] As one embodiment, the first producer provides the given operation to the first node through the response in Figure 21.

[1104] As one embodiment, the first producer provides a model of the given operation to the first node through the response in Figure 21.

[1105] As one embodiment, the first producer provides an AI entity that comprises an AI function that performs the given operation to the first node through the response in Figure 21.

[1106] As one embodiment, the first producer provides the first node with an AI function to perform the given operation via the response in FIG. 21.

[1107] As one embodiment, the deployment is done by an AI function.

[1108] As one embodiment, the deployment is done by an AI function deployed at the first node.

[1109] As one embodiment, the deployment is done by an AI deployment function.

[1110] As one embodiment, the deployment is done by an AI deployment function deployed at the first node.

[1111] As one embodiment, the deployment is done by an AI inference function.

[1112] As one embodiment, the deployment is done by an AI inference function deployed at the first node.

[1113] As one embodiment, the deployment is done by an AI entity.

[1114] As one embodiment, the deployment is done by an AI entity deployed at the first node.

[1115] As one embodiment, the deployment is done by an AI entity with a deployment function.

[1116] As one embodiment, the deployment is done by an AI entity with a deployment function deployed at the first node.

[1117] As one embodiment, the deployment is done by an AI entity with an inference function.

[1118] As one embodiment, the deployment is done by an AI entity with an inference function deployed at the first node.

[1119] As one embodiment, the deployment includes obtaining the given operation from a first producer.

[1120] As one embodiment, the deployment includes making a request to a first producer to load the given operation.

[1121] As one embodiment, the deploying includes loading the given operation from a first producer.

[1122] As one embodiment, the first producer generates and provides an AI model.

[1123] As one embodiment, the first producer generates and provides an AI entity.

[1124] As one embodiment, the first producer generates and provides an AI function.

[1125] As one embodiment, the first producer is a producer of the given operation.

[1126] As one embodiment, the first producer is a trained producer of the given operation.

[1127] As one embodiment, the first producer includes an AI entity producer.

[1128] As one embodiment, the first producer includes an AI function producer.

[1129] As one embodiment, the first producer includes an AI deployment producer.

[1130] As one embodiment, the first producer includes an AI loading producer.

[1131] As one embodiment, the first producer includes an AI training producer.

[1132] As one embodiment, the first producer includes an AI inference producer.

[1133] As one embodiment, the first producer includes a trained producer of an AI model.

[1134] As one embodiment, the first producer includes an MnS (Management Service) producer.

[1135] As one embodiment, the first producer is a serving cell of the first node.

[1136] As one embodiment, the first producer is a maintaining base station of the serving cell of the first node.

[1137] As one embodiment, the first producer is a core network.

[1138] As an embodiment, the training of the given operation is performed by the first producer.

[1139] Embodiment 22

[1140] Embodiment 22 illustrates a schematic diagram of an artificial intelligence or machine learning based processing system according to an embodiment of the present application; as shown in FIG. 22. In embodiment 22, the second processing machine sends a first data set to the third processing machine, and sends a second data set to the fourth processing machine; the third processing machine generates a target first type parameter group according to the first data set, and sends the generated target first type parameter group to the fourth processing machine; the fourth processing machine 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 fifth processing machine. In FIG. 22, the first type feedback and the second type feedback are optional; the third processing machine comprises an ML training function; and the fourth processing machine comprises an ML inference function.

[1141] As an embodiment, the fifth processing machine comprises an ML test function.

[1142] As an embodiment, the fifth processing machine comprises performance monitoring / evaluation of the ML model.

[1143] As an embodiment, the fourth processing machine sends a first type feedback to the third processing machine, and the first type feedback is used to trigger recalculation or update of the target first type parameter group, i.e. trigger ML initial training or ML retraining.

[1144] As an embodiment, the fifth processing machine sends a second type feedback to the second processing machine, 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.

[1145] As an embodiment, the second processing machine generates the first data set and the second data set according to measurement of a reference signal.

[1146] As an embodiment, the fourth processing machine belongs to the first node.

[1147] As an embodiment, the fifth processing machine belongs to the first node or the second node.

[1148] As an embodiment, the fourth processing machine performs the first operation.

[1149] As an embodiment, the fourth processing machine performs the first candidate operation.

[1150] As an embodiment, the second data set comprises measurements on reference signals.

[1151] As an embodiment, the second data set comprises reception of PDSCH.

[1152] As an embodiment, the first data set comprises training data.

[1153] As an embodiment, the third processor is configured to train an ML model, and the trained model is described by the target first-type parameter set.

[1154] As an embodiment, the third processor is located at the first node.

[1155] The above embodiment avoids transmitting the first data set to the second node.

[1156] As an embodiment, the third processor is located at the second node.

[1157] The above embodiment supports joint training, and optimizes system performance.

[1158] As an embodiment, the third processor is located at the core network.

[1159] The above embodiment supports network-wide joint training, and further optimizes system performance.

[1160] As an embodiment, the second data set comprises inference data.

[1161] As an embodiment, the fourth processor is located at the first node.

[1162] As an embodiment, the fourth processor constructs a model according to the target first-type parameter set, and then inputs the second data set into the constructed model to obtain the first-type output.

[1163] As an embodiment, the fourth processor compares real data with the first-type output, and the error obtained is used to generate the first-type feedback.

[1164] As an embodiment, the fourth processor generates the first-type feedback through performance monitoring.

[1165] As an embodiment, the first-type feedback is used to reflect the performance of the trained model; when the performance of the trained model cannot meet the requirements, the third processor will recalculate the target first-type parameter set.

[1166] As one embodiment, the fifth handler compares the real data with the first type of output, and the error obtained is used to generate the second type of feedback.

[1167] As one embodiment, the fifth handler generates the second type of feedback through performance monitoring.

[1168] As one embodiment, the second type of feedback is used to reflect the performance of the trained model; when the performance of the trained model cannot meet the requirements, the second handler sends the first data set to trigger or assist the third handler to recalculate the target first type of parameter group.

[1169] As one embodiment, the performance of the trained model is considered to be unable to meet the requirements when the error is too large or has not been updated for too long a time.

[1170] As one embodiment, the target first type of parameter group includes one or more of the following: convolution kernel size, convolution layer number, convolution step length, pooling kernel size, pooling kernel step length, pooling function, activation function, or feature map number.

[1171] As one embodiment, the target first type of parameter group includes one or more of the following: convolution kernel, pooling kernel, pooling function, activation function, parameters of the pooling function, or parameters of the activation function.

[1172] As one embodiment, the ML includes AI.

[1173] As one embodiment, the ML includes ML and AI.

[1174] Embodiment 23

[1175] Embodiment 23 illustrates a schematic diagram based on artificial intelligence or machine learning according to one embodiment of the present application; as shown in FIG. 23. FIG. 23 includes a second operation, a third operation, a fourth operation, a fifth operation, and a sixth operation. In embodiment 23, the second operation and the third operation belong to the first stage, the fourth operation belongs to the second stage, the fifth operation belongs to the third stage, and the sixth operation belongs to the fourth stage. In FIG. 23, the line with an arrow represents the order of the flow.

[1176] As one embodiment, the second operation includes ML training, the third operation includes ML testing, the fourth operation includes ML emulation, the fifth operation includes ML entity loading, and the sixth operation includes AI inference.

[1177] As an embodiment, the first phase comprises a training phase, the second phase comprises an emulation phase, the third phase comprises a deployment phase, and the fourth phase comprises an inference phase.

[1178] As an embodiment, the first phase comprises ML model training.

[1179] As an embodiment, the first phase comprises ML model training and ML testing.

[1180] As an embodiment, the ML model training comprises initial training and re-training of one or a set of ML models.

[1181] As an embodiment, the ML model training relies on training data.

[1182] As an embodiment, the ML model training comprises ML entity validation.

[1183] As an embodiment, the ML entity validation is used to evaluate the performance of the ML entity.

[1184] As an embodiment, the ML entity validation relies on validation data.

[1185] As an embodiment, if the result of the ML entity validation does not meet the expectation, the ML model will be re-trained.

[1186] As an embodiment, the ML testing comprises testing the validated ML entity to evaluate the performance of the trained ML model.

[1187] As an embodiment, if the result of the ML testing meets the expectation, the ML entity proceeds to the next phase; otherwise, the ML model will be re-trained.

[1188] As an embodiment, the ML testing relies on testing data.

[1189] As an embodiment, the second phase comprises ML emulation, which performs inference of the ML entity in an emulation environment.

[1190] As an embodiment, the ML emulation estimates the performance of the inference of the ML entity in an emulation environment before the ML entity is used.

[1191] As one embodiment, the second stage is optional.

[1192] As one embodiment, the third stage includes ML entity loading for obtaining trained ML entity for desired AI inference function.

[1193] As one embodiment, the third stage is optional.

[1194] As one embodiment, the third stage is not needed when training function and inference function are co-located.

[1195] As one embodiment, the fourth stage includes AI inference.

[1196] As one embodiment, the ML includes AI.

[1197] As one embodiment, the AI includes ML.

[1198] Embodiment 24

[1199] Embodiment 24 illustrates a diagram of AI function deployment according to one embodiment of the application; as shown in FIG. 24.

[1200] In embodiment 24, AI training function of RAN (Radio Access Network) domain is located in 3GPP RAN domain-specific management function, while AI inference function is located in UE.

[1201] In embodiment 24, RAN domain-specific management function provides AI training function management capability and AI inference function management capability.

[1202] Embodiment 25

[1203] Embodiment 25 illustrates a diagram of AI function deployment according to one embodiment of the application; as shown in FIG. 25.

[1204] In embodiment 25, AI training function is located in RAN domain-specific management function, while AI inference function is located in UE locally.

[1205] In embodiment 25, the management capability of the AI training function is provided by a RAN domain specific management function, and the management capability of the AI inference is provided locally by the UE.

[1206] In FIG. 25, MnF refers to Management Function.

[1207] Embodiment 26

[1208] Embodiment 26 illustrates a schematic diagram of AI function deployment according to one embodiment of the present application; as shown in FIG. 26.

[1209] In embodiment 26, the AI training function and the AI inference function are both located in the UE, wherein the UE provides the capability of training and inference.

[1210] In embodiment 26, the RAN domain specific management function provides the management capability of the AI training function and the management capability of the AI inference function.

[1211] Embodiment 27

[1212] Embodiment 27 illustrates a schematic diagram of AI function deployment according to one embodiment of the present application; as shown in FIG. 27.

[1213] In embodiment 27, the AI training function and the AI inference function are both located in the UE.

[1214] In embodiment 27, the management capability of the AI training function and the management capability of the AI inference function are both provided locally by the UE.

[1215] In FIG. 27, MnF refers to Management Function.

[1216] Embodiment 28

[1217] Embodiment 28 illustrates a structural block diagram of a processing apparatus in a first node according to one embodiment of the present application; as shown in FIG. 28. In FIG. 28, the processing apparatus 2800 in the first node includes a first transmitter 2801 and a first processor 2802.

[1218] In embodiment 28, the first transmitter 2801 transmits a first report, and the first processor 2802 receives a first signaling.

[1219] In embodiment 28, the first report indicates L0 first type resources, wherein L0 is a positive integer; the first signaling indicates that the number of occupied first type resources is adjusted by P1, wherein P1 is an integer; and the L0 first type resources are used for inference.

[1220] As an embodiment, the first report comprises UE capability information, and the first signaling is DCI.

[1221] As an embodiment, the first transmitter 2801 transmits a second report; wherein the second report indicates that L1 first-type resources are not occupied, and L1 is a positive integer.

[1222] As a sub-embodiment of the above-mentioned embodiment, the second report is carried by a MAC CE.

[1223] As a sub-embodiment of the above-mentioned embodiment, L1 is not greater than L0, and P1 is not greater than L1.

[1224] As an embodiment, the first processor 2802 determines L2, and L2 is a positive integer; wherein L2 first-type resources are occupied, and L2 depends on P1.

[1225] As a sub-embodiment of the above-mentioned embodiment, L2 and P1 are linearly related, and the linear coefficient between L2 and P1 is 1.

[1226] As a sub-embodiment of the above-mentioned embodiment, L2 is the smallest one of a plurality of candidate values that is not less than the sum of L3 and P1, and L3 is the number of first-type resources occupied before L2 is determined.

[1227] As an embodiment, L2 first-type resources are occupied by a first operation; the candidate of the number of first-type resources occupied by the first operation comprises M values, M is a positive integer greater than 1, the M values are positive integers respectively, and L2 is one of the M values.

[1228] As a sub-embodiment of the above-mentioned embodiment, the first operation is obtained through training.

[1229] As a sub-embodiment of the above-mentioned embodiment, the first operation comprises inference.

[1230] As a sub-embodiment of the above-mentioned embodiment, the first signaling indicates that the number of first-type resources occupied by the first operation is adjusted by P1.

[1231] As an embodiment, L2 first-type resources are occupied by a first function, the first function has P candidate operations, P is a positive integer greater than 1, L2 is the number of first-type resources occupied by a first candidate operation, and the first candidate operation is a candidate operation used for the first function among the P candidate operations.

[1232] As one subembodiment of the above embodiment, any of the P candidate operations is obtained through training.

[1233] As one subembodiment of the above embodiment, any of the P candidate operations includes inference.

[1234] As one subembodiment of the above embodiment, the first signaling indicates that the number of the first type of resources occupied by the first function is adjusted by the P1.

[1235] As one embodiment, the first processor 2802 receives on a first physical layer channel; wherein a scheme employed by the receiving on the first physical layer channel depends on the P1.

[1236] As one subembodiment of the above embodiment, the first physical layer channel is PDSCH.

[1237] As one embodiment, the first transmitter 2801 transmits first CSI; wherein a scheme employed by the calculation of the first CSI depends on the P1.

[1238] As one embodiment, at least one of the L0 first type of resources includes one or more first type of sub-resources and one or more second type of sub-resources; at least the first type of sub-resources of the first type of sub-resources and the second type of sub-resources are used for inference.

[1239] As one subembodiment of the above embodiment, the first type of sub-resources are used for computation or processing required by inference, and the second type of sub-resources are used for storage required by inference.

[1240] As one subembodiment of the above embodiment, the first type of sub-resources are used for inference, and the second type of sub-resources are CSI processing units.

[1241] As one embodiment, the first node is a terminal.

[1242] As one embodiment, the first node is a user equipment.

[1243] As one embodiment, the first node is a relay node device.

[1244] As one embodiment, the first transmitter 2801 includes at least one of {antenna 452, transmitter 454, transmit processor 468, multi-antenna transmit processor 457, controller / processor 459, memory 460, data source 467} in embodiment 4.

[1245] As one embodiment, the first processor 2802 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.

[1246] Embodiment 29

[1247] Embodiment 29 illustrates a structural block diagram of a processing apparatus in a second node according to an embodiment of the present application; as shown in Figure 29. In Figure 29, the processing apparatus 2900 in the second node includes a first receiver 2901 and a second transmitter 2902.

[1248] In embodiment 29, the first receiver 2901 receives a first report; the second transmitter 2902 transmits a first signaling.

[1249] In embodiment 29, the first report indicates L0 first-type resources, the L0 being a positive integer; the first signaling indicates that the number of occupied first-type resources is adjusted by P1, the P1 being an integer; the L0 first-type resources are used for inference.

[1250] As one embodiment, the first report includes UE capability information, and the first signaling is DCI.

[1251] As one embodiment, the first receiver 2901 receives a second report; wherein the second report indicates that L1 first-type resources are not occupied, the L1 being a positive integer.

[1252] As one sub-embodiment of the above-mentioned embodiment, the second report is carried by a MAC CE.

[1253] As one sub-embodiment of the above-mentioned embodiment, the L1 is not greater than the L0, and the P1 is not greater than the L1.

[1254] As one embodiment, a sender of the first report determines L2, the L2 being a positive integer; wherein L2 first-type resources are occupied, and the L2 depends on the P1.

[1255] As one sub-embodiment of the above-mentioned embodiment, the L2 and the P1 are linearly related, and the linear coefficient between the L2 and the P1 is 1.

[1256] As one sub-embodiment of the above-mentioned embodiment, the L2 is the smallest one of a plurality of candidate values that is not less than the sum of L3 and the P1, the L3 being the number of occupied first-type resources before the L2 is determined.

[1257] As one embodiment, the L2 first-type resources are occupied by a first operation; candidates of the number of first-type resources occupied by the first operation include M values, the M is a positive integer greater than 1, the M values are positive integers respectively, and the L2 is one of the M values.

[1258] As one sub-embodiment of the above embodiment, the first operation is obtained through training.

[1259] As one sub-embodiment of the above embodiment, the first operation includes inference.

[1260] As one sub-embodiment of the above embodiment, the first signaling indicates that the number of first-type resources occupied by the first operation is adjusted by the P1.

[1261] As one embodiment, the L2 first-type resources are occupied by a first function, the first function has P candidate operations, P is a positive integer greater than 1, the L2 is the number of first-type resources occupied by a first candidate operation, and the first candidate operation is a candidate operation used for the first function among the P candidate operations.

[1262] As one sub-embodiment of the above embodiment, any candidate operation in the P candidate operations is obtained through training.

[1263] As one sub-embodiment of the above embodiment, any candidate operation in the P candidate operations includes inference.

[1264] As one sub-embodiment of the above embodiment, the first signaling indicates that the number of first-type resources occupied by the first function is adjusted by the P1.

[1265] As one embodiment, the second transmitter 2902 transmits on a first physical layer channel; wherein a scheme adopted by a target receiver of the first physical layer channel for receiving on the first physical layer channel depends on the P1.

[1266] As one sub-embodiment of the above embodiment, the first physical layer channel is a PDSCH.

[1267] As one embodiment, the first receiver 2901 receives first CSI; wherein a scheme adopted by the first receiver 2901 for calculating the first CSI depends on the P1.

[1268] As one embodiment, a sender of the first CSI adopts a scheme for calculating the first CSI depending on the P1.

[1269] As one embodiment, at least one of the L0 first-type resources comprises one or more first-type sub-resources and one or more second-type sub-resources; at least the first-type sub-resources of the first-type sub-resources and the second-type sub-resources are used for inference.

[1270] As one subembodiment of the above embodiment, the first-type sub-resources are used for computation or processing required for inference, and the second-type sub-resources are used for storage required for inference.

[1271] As one subembodiment of the above embodiment, the first-type sub-resources are used for inference, and the second-type sub-resources are CSI processing units.

[1272] As one embodiment, the second node is a base station.

[1273] As one embodiment, the second node is a base station device.

[1274] As one embodiment, the second node is a user equipment.

[1275] As one embodiment, the second node is a relay node device.

[1276] As one embodiment, the first receiver 2901 comprises at least one of {antennas 420, receivers 418, receive processors 470, multi-antenna receive processors 472, controller / processor 475, memory 476} in Embodiment 4.

[1277] As one embodiment, the second transmitter 2902 comprises at least one of {antennas 420, transmitters 418, transmit processors 416, multi-antenna transmit processors 471, controller / processor 475, memory 476} in Embodiment 4.

[1278] Those skilled in the art can understand that all or part of the steps in the foregoing method can be instructed by programs to the relevant 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, vehicles, vehicles, RSUs, 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, small cellular base stations, home base stations, relay base stations, eNBs, gNBs, TRPs (Transmitter Receiver Points), GNSSs, relay satellites, satellite base stations, air base stations, RSUs (Road Side Units), unmanned aerial vehicles, test equipment such as wireless communication devices that simulate part of the functions of base stations or signaling testers, and the like.

[1279] Those skilled in the art will understand that the application can be implemented by other specified forms without departing from the core or essential characteristics thereof. Therefore, the presently disclosed embodiments should in no way be considered as descriptive rather than limiting. The scope of the application is determined by the appended claims rather than the preceding description, and all modifications within the equivalent meaning and range of the claims are considered to be included therein.

Claims

A first node for wireless communication, characterized in that Comprising: a first transmitter that transmits a first report, the first report indicating L0 first-type resources, L0 being a positive integer; a first processor that receives first signaling, the first signaling indicating that a number of occupied first-type resources is adjusted by P1, P1 being an integer; wherein the L0 first-type resources are used for inference. The first node according to claim 1, characterized in that the first transmitter transmits a second report; wherein the second report indicates that L1 first-type resources are not occupied, L1 being a positive integer. The first node according to claim 1 or 2, characterized in that, the first processor determines L2, L2 being a positive integer; wherein L2 first-type resources are occupied, L2 depending on P1. The first node according to claim 3, characterized in that the L2 first-type resources are occupied by a first operation; candidates of a number of first-type resources occupied by the first operation include M values, M being a positive integer greater than 1, the M values being positive integers respectively, L2 being one of the M values. The first node according to claim 3, characterized in that the L2 first-type resources are occupied by a first function, the first function having P candidate operations, P being a positive integer greater than 1, L2 being a number of first-type resources occupied by a first candidate operation, the first candidate operation being a candidate operation of the P candidate operations used for the first function. The first node according to any of claims 1 to 5, characterized in that the first processor receives on a first physical layer channel; wherein a scheme adopted by the receiving on the first physical layer channel depends on P1. The first node according to any of claims 1 to 6, characterized in that the first transmitter transmits first CSI; wherein a scheme adopted by a calculation of the first CSI depends on P1. The first node according to any one of claims 1 to 7, characterized in that at least one of the L0 first-type resources includes one or more first-type sub-resources and one or more second-type sub-resources; at least the first-type sub-resources of the first-type sub-resources and the second-type sub-resources are used for inference. A second node for wireless communication, characterized in that Comprising: a first receiver that receives a first report, the first report indicating L0 first-type resources, L0 being a positive integer; a second transmitter that transmits first signaling, the first signaling indicating that a number of occupied first-type resources is adjusted by P1, P1 being an integer; wherein the L0 first-type resources are used for inference. The second node according to claim 9, characterized by the first receiver receives a second report; wherein the second report indicates that L1 first-type resources are not occupied, L1 being a positive integer. The second node according to claim 9 or 10, characterized in that a sender of the first report determines L2, L2 being a positive integer; wherein L2 first-type resources are occupied, L2 depending on P1. The second node according to claim 11, characterized by the L2 first-type resources are occupied by a first operation; candidates of a number of first-type resources occupied by the first operation include M values, M being a positive integer greater than 1, the M values being positive integers respectively, L2 being one of the M values. The second node according to claim 11, characterized by the L2 first-type resources are occupied by a first function, the first function having P candidate operations, P being a positive integer greater than 1, L2 being a number of first-type resources occupied by a first candidate operation, the first candidate operation being a candidate operation of the P candidate operations used for the first function. The second node according to any of claims 9 to 13, characterized by The second transmitter transmits on a first physical layer channel; wherein a scheme employed by a target receiver on the first physical layer channel for receiving on the first physical layer channel depends on the P1. The second node according to any of claims 9 to 14, characterized by The first receiver receives a first CSI; wherein a scheme employed for computing the first CSI depends on the P1. The second node according to any of claims 9 to 15, characterized by At least one of the L0 first-type resources comprises one or more first-type sub-resources and one or more second-type sub-resources; at least the first-type sub-resources among the first-type sub-resources and the second-type sub-resources are used for inference. A method used in a first node for wireless communication, characterized by Comprising: Transmitting a first report, the first report indicating L0 first-type resources, L0 being a positive integer; Receiving a first signaling, the first signaling indicating that a number of occupied first-type resources is adjusted by P1, P1 being an integer; wherein the L0 first-type resources are used for inference. The method in a first node according to claim 17, characterized by Comprising: Transmitting a second report; wherein the second report indicates that L1 first-type resources are not occupied, L1 being a positive integer. The method in a first node according to claim 17 or 19, characterized by Comprising: Determining L2, L2 being a positive integer; wherein L2 first-type resources are occupied, L2 depending on the P1. The method in a first node according to claim 19, characterized by The L2 first-type resources are occupied by a first operation; candidates of a number of first-type resources occupied by the first operation comprise M values, M being a positive integer greater than 1, the M values being positive integers respectively, L2 being one of the M values. The method in a first node according to claim 19, characterized by The L2 first-type resources are occupied by a first function, the first function having P candidate operations, P being a positive integer greater than 1, L2 being a number of first-type resources occupied by a first candidate operation, the first candidate operation being a candidate operation used for the first function among the P candidate operations. The method in a first node according to any of claims 17-21, characterized by Comprising: Receiving on a first physical layer channel; wherein a scheme employed by the receiving on the first physical layer channel depends on the P1. The method in a first node according to any of claims 17-22, characterized by Comprising: Transmitting a first CSI; wherein a scheme employed for computing the first CSI depends on the P1. The method in a first node according to any of claims 17-23, characterized by At least one of the L0 first-type resources comprises one or more first-type sub-resources and one or more second-type sub-resources; at least the first-type sub-resources among the first-type sub-resources and the second-type sub-resources are used for inference. A method used in a second node for wireless communication, characterized by Comprising: Receiving a first report, the first report indicating L0 first-type resources, L0 being a positive integer; Transmitting a first signaling, the first signaling indicating that a number of occupied first-type resources is adjusted by P1, P1 being an integer; wherein the L0 first-type resources are used for inference. The method in a second node according to claim 25, characterized by Comprising: Receiving a second report; wherein the second report indicates that L1 first-type resources are not occupied, L1 being a positive integer. The method in a second node according to claim 25 or 26, characterized by A transmitter of the first report determines L2, L2 being a positive integer; wherein L2 first-type resources are occupied, L2 depending on the P1. The method in a second node according to claim 27, characterized by The L2 first-type resources are occupied by a first operation; candidates of a number of first-type resources occupied by the first operation comprise M values, M being a positive integer greater than 1, the M values being positive integers respectively, L2 being one of the M values. The method in a second node according to claim 27, characterized by The L2 first-type resources are occupied by a first function, the first function has P candidate operations, P is a positive integer greater than 1, L2 is the number of first-type resources occupied by a first candidate operation, and the first candidate operation is a candidate operation of the P candidate operations used for the first function. The method in a second node according to any of claims 25-29, characterized by Comprise: Transmit on a first physical layer channel; Wherein, a scheme adopted by a target receiver of the first physical layer channel for receiving on the first physical layer channel depends on the P1. The method in a second node according to any of claims 25-30, characterized by Comprise: Receive first CSI; Wherein, a scheme adopted by a target receiver of the first physical layer channel for receiving on the first physical layer channel depends on the P1. The method in a second node according to any of claims 25-31, characterized by At least one first-type resource of the L0 first-type resources comprises one or more first-type sub-resources and one or more second-type sub-resources; at least the first-type sub-resource of the first-type sub-resource and the second-type sub-resource is used for inference.

Images