A method and apparatus in a node for wireless communication

Abstract

The application discloses a method and device in a node for wireless communication. The node transmits a first report, the first report indicating a recommended configuration; transmits a first signal; the recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, a maximum output power value of the first signal depends on a first maximum power backoff value, the AI-inference-based maximum power backoff value is one of a plurality of candidate values of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, the first time window is configured or indicated by the first report. The application is beneficial to improve the performance of uplink transmission.

Description

Technical Field

[0001] This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to AI (Artificial Intelligence) or ML (Machine Learning) schemes and apparatus in wireless communication. Background Technology

[0002] Leveraging AI / ML (Artificial Intelligence / Machine Learning) technologies to improve 5G network performance is a crucial component of achieving deep integration of 5G and AI / ML and building intelligent dimensions for 5G-Advanced (5.5G) networks. Starting with 5G Rel-17 (Release 17), the 3GPP (3rd Generation Partnership Project) RAN (Radio Access Networks) has been researching the AI / ML functional framework and typical high-level use cases for AI / ML, including Network Energy Saving (NES), load balancing, and mobility enhancement. Rel-18 further investigated AI / ML physical layer use cases, including AI / ML-based localization, AI / ML-based beam management, and AI / ML-based CSI (Channel State Information) prediction and compression, and standardized high-level AI / ML use cases (NES, load balancing, mobility enhancement). Rel-19 will complete the standardization of AI / ML-related physical layer use cases and further explore new use cases of AI / ML in RAN L2 / L3 (Layer 2 / Layer 3), such as AI / ML-based network slicing, AI / ML-based coverage, and AI / ML-based mobility.

[0003] It is foreseeable that AI / ML will be one of the most pervasive core technologies in future 6G, involving all levels of air interface, network, protocol, and algorithm, and will also profoundly impact network functions such as sensing, communication, computing, and control. Currently, the development of AI / ML has entered the large-scale model stage. Large-scale communication models can realize autonomous networks and intelligent services, support network operation optimization, and improve network efficiency. The deep integration of communication and AI is an important direction for the future evolution of communication. AI will empower the development and upgrade from 5G and 5.5G to 6G, bringing new management models such as automated management of frequency bands and traffic, real-time analysis of user data and network load, and prediction of network status. Summary of the Invention

[0004] In existing networks, base station scheduling decisions primarily rely on user-reported measurement reports (such as CSI). These reports are typically generated based on predefined rules and static configurations, making it difficult to dynamically adapt to complex wireless environments and diverse service requirements. This traditional approach often exhibits insufficient flexibility and low resource utilization efficiency when facing highly dynamic, high-density, and diverse network scenarios. To address this issue, introducing AI for reasoning, enabling the UE (User Equipment) to analyze its own location and service requirements based on real-time data and historical information, and generate waveform or power backoff information to assist base station scheduling, has become a possible solution.

[0005] This application discloses a solution to the problem of reporting recommended waveforms or power back-off based on AI inference. It should be noted that the AI / ML scenario described in this application is merely a typical application scenario or example; this application is also applicable to 6G networks or other scenarios facing similar problems (e.g., non-AI / ML scenarios, or other scenarios where UEs recommend configurations to base stations, or for different application scenarios such as eMBB, URLLC, non-terrestrial networks, sensor-integrated networks, smart metasurfaces, and terahertz networks), achieving similar technical effects. Furthermore, adopting a unified solution for different scenarios (including but not limited to eMBB, URLLC, non-terrestrial networks, sensor-integrated networks, smart metasurfaces, and terahertz networks) helps reduce hardware complexity and cost. Where there is no conflict, the embodiments and features described in the first node of this application can be applied to the second node, and vice versa.

[0006] This application discloses a method used in a first node of wireless communication, characterized by comprising:

[0007] Send a first report, which indicates the recommended configuration;

[0008] Send the first signal;

[0009] The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[0010] It should be noted that sending (or receiving) the first report and sending (or receiving) the first signal are common expressions in the art, respectively meaning sending (or receiving) the content of the first report, and sending (or receiving) the information (e.g., modulation symbols, bits) on the first signal. The above expressions are beneficial to maintain consistency with the general expressions in the art.

[0011] As an example, AI is used to infer recommended waveforms or maximum power backoff values ​​over a period of time based on factors including but not limited to user location, reference signal measurement, and uplink data quality, and these values ​​are then reported to the base station to assist in base station scheduling, improve uplink performance, and increase resource utilization.

[0012] According to one aspect of this application, the above method is characterized by comprising:

[0013] Receive the first reference signal;

[0014] The recommended configuration indicated in the first report depends on a first inference, the input of which depends on a measurement of the first reference signal.

[0015] According to one aspect of this application, the above method is characterized in that the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, and the first encoder is applied to the encoding of data on the first logical channel, the first encoder being based on AI.

[0016] According to one aspect of this application, the above method is characterized by comprising:

[0017] Receive a first information block, the first information block indicating a first condition;

[0018] Send a second information block, which indicates that the first AI function is applicable;

[0019] Wherein, the first AI function applies under the first condition, and the recommended configuration indicated by the first report depends on the first AI function.

[0020] According to one aspect of this application, the above method is characterized by comprising:

[0021] Send a second report;

[0022] The second report indicates that the second AI function is not applicable, and the recommended configuration indicated by the first report depends on the second AI function; the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[0023] According to one aspect of this application, the above method is characterized in that the triggering condition for the first report includes at least one of the following:

[0024] The change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold, which is configured or predefined;

[0025] The waveform based on AI reasoning is different from the waveform indicated in the previous report.

[0026] According to one aspect of this application, the above method is characterized in that the first report is triggered when a first timer expires, wherein the first timer is configured or predefined.

[0027] This application discloses a method used in a second node for wireless communication, characterized by comprising:

[0028] Receive the first report, which indicates the recommended configuration;

[0029] Receive the first signal;

[0030] The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[0031] According to one aspect of this application, the above method is characterized by comprising:

[0032] Send the first reference signal;

[0033] The recommended configuration indicated in the first report depends on a first inference, the input of which depends on a measurement of the first reference signal.

[0034] According to one aspect of this application, the above method is characterized in that the recommended configuration indicated by the first report is inferred by the sender of the first report based on a first logical channel, and a first encoder is applied to the encoding of data on the first logical channel, the first encoder being based on AI.

[0035] According to one aspect of this application, the above method is characterized by comprising:

[0036] Send a first information block, which indicates a first condition;

[0037] Receive a second information block, which indicates that the first AI function is applicable;

[0038] Wherein, the first AI function applies under the first condition, and the recommended configuration indicated by the first report depends on the first AI function.

[0039] According to one aspect of this application, the above method is characterized by comprising:

[0040] Receive the second report;

[0041] The second report indicates that the second AI function is not applicable, and the recommended configuration indicated by the first report depends on the second AI function; the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[0042] According to one aspect of this application, the above method is characterized in that the triggering condition for the first report includes at least one of the following:

[0043] The change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold, which is configured or predefined;

[0044] The waveform based on AI reasoning is different from the waveform indicated in the previous report.

[0045] According to one aspect of this application, the above method is characterized in that the first report is triggered when a first timer expires, wherein the first timer is configured or predefined.

[0046] This application discloses a first node used for wireless communication, characterized in that it comprises:

[0047] The first transceiver sends a first report, which indicates the recommended configuration.

[0048] The first transceiver sends a first signal;

[0049] The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[0050] This application discloses a second node used for wireless communication, characterized in that it comprises:

[0051] The second transceiver receives the first report, which indicates the recommended configuration.

[0052] The second transceiver receives the first signal;

[0053] The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[0054] As an example, compared with conventional solutions, this application has the following advantages:

[0055] Improved uplink transmission performance;

[0056] Improved resource utilization;

[0057] This improves the robustness of the system. Attached Figure Description

[0058] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0059] Figure 1 A flowchart of the first node transmission according to an embodiment of this application is shown;

[0060] Figure 2 A schematic diagram of a network architecture according to an embodiment of this application is shown;

[0061] Figure 3A schematic diagram of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application is shown;

[0062] Figure 4 A schematic diagram of a first node and a second node according to an embodiment of this application is shown;

[0063] Figure 5 A flowchart illustrating the transmission between the first node and the second node according to an embodiment of this application is shown;

[0064] Figure 6 A schematic diagram of a first reference signal according to an embodiment of this application is shown;

[0065] Figure 7 A schematic diagram illustrating the relationship between a first encoder, a first logical channel, and a recommended configuration according to an embodiment of this application is shown.

[0066] Figure 8 A schematic diagram illustrating the relationship between a first information block, a second information block, a first condition, and a first AI function according to an embodiment of this application is shown.

[0067] Figure 9 A schematic diagram illustrating the relationship between a first time window and a second report according to an embodiment of this application is shown;

[0068] Figure 10 A schematic diagram illustrating the triggering conditions of a first report according to an embodiment of this application is shown;

[0069] Figure 11 A schematic diagram illustrating the relationship between a first timer and a first report according to an embodiment of this application is shown;

[0070] Figure 12 A schematic diagram illustrating the deployment of RAN domain AI / ML functionality according to an embodiment of this application is shown;

[0071] Figure 13 A schematic diagram illustrating the deployment of AI / ML functions in a UE according to an embodiment of this application is shown;

[0072] Figure 14 A schematic diagram of an artificial intelligence or machine learning-based processing system according to an embodiment of this application is shown;

[0073] Figure 15 A schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application is shown;

[0074] Figure 16 A structural block diagram of a processing apparatus for a first node according to an embodiment of this application is shown;

[0075] Figure 17 A structural block diagram of a processing apparatus for a second node according to an embodiment of this application is shown. Detailed Implementation

[0076] The technical solution of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0077] Example 1

[0078] Example 1 illustrates a flowchart 100 of a first node transmission according to an embodiment of this application, as shown in the attached diagram. Figure 1 As shown. In the appendix Figure 1 In the diagram, each box represents a step. It is particularly important to emphasize that the order of the boxes in the diagram does not restrict the chronological order of the steps they represent.

[0079] In Embodiment 1, the first node in this application sends a first report in step 101, the first report indicating a recommended configuration; and sends a first signal in step 102; the recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, the first time window being configured or indicated by the first report.

[0080] As one example, the first node is a user equipment.

[0081] As an example, the first node supports AI.

[0082] As an example, the first node supports AI functionality.

[0083] As an example, the first node supports AI-based inference.

[0084] As an example, the sender of the first report is the first node.

[0085] As an example, the first report is a report from a higher layer.

[0086] As an example, the first report is generated at a higher level.

[0087] As one embodiment, the first report is a MAC (Medium Access Control) layer report. As a supplementary embodiment, using a MAC layer report results in lower signaling overhead.

[0088] As an example, the first report is a report generated at the MAC layer.

[0089] As an example, the first report is a MAC (medium access control) CE (control element).

[0090] As an example, the first report is transmitted in a MAC PDU (Protocol Data Unit).

[0091] As one example, the first report belongs to the PHR (Power Headroom Report). As a supplementary example, the recommended configuration instructions are added to the existing report with minimal standard changes.

[0092] As one example, the first report is a completely new 6G report. As a supplementary example, a new report is introduced to indicate the recommended configuration, providing greater flexibility.

[0093] As an example, the first report is an RCR (recommended configuration report).

[0094] As an example, the first report is a report from the first node recommending configurations to the network side.

[0095] As an example, the first report is transmitted on UL-SCH (Uplink Shared Channel).

[0096] As one embodiment, the first report is a physical layer report. As a supplementary embodiment, physical layer reporting is used to reduce latency.

[0097] As an example, the first report is carried by an uplink signal from the physical layer.

[0098] As an example, the first report is carried by PUSCH.

[0099] As an example, the first report precedes the first signal.

[0100] As an example, the first report follows the first signal.

[0101] As an example, the first report is carried by the first signal.

[0102] As an example, the recommended configuration is the configuration desired by the first node.

[0103] As an example, the recommended configuration is applicable for some time to come.

[0104] As an example, the recommended configuration is based on configurations generated by AI / ML.

[0105] As an example, the recommended configuration is the configuration generated by the first node based on AI / ML.

[0106] As an example, the recommended configuration is inferred by an AI / ML model.

[0107] As an example, the recommended configuration is the configuration for auxiliary base station scheduling recommended by the user equipment to the network side.

[0108] As an example, the specific method for generating the recommended configuration is related to the UE implementation.

[0109] As an example, the recommended configuration is obtained by the user equipment based on its own location and predictions of its future location.

[0110] As an example, the recommended configuration is obtained by the user equipment based on predictions of future uplink data volume.

[0111] As an example, the recommended configuration is obtained by the user equipment based on its understanding of the data on the logical channel.

[0112] As an example, the recommended configuration is obtained by the user equipment based on the data characteristics on the logical channel.

[0113] As an example, the recommended configuration is obtained by the user equipment based on measurements of a reference signal and predictions of future measurement results.

[0114] As one embodiment, the first report indicating the recommended configuration includes: the first report carrying the recommended configuration.

[0115] As one embodiment, the first report indicating a recommended configuration includes: the first report explicitly or implicitly indicating the recommended configuration.

[0116] As one embodiment, the first report indicating the recommended configuration includes: the first report being used to determine the recommended configuration.

[0117] As one embodiment, the first report indicating the recommended configuration includes: the first report is a MAC CE, and at least one bit or one byte in the first report indicates the recommended configuration.

[0118] As one embodiment, the first report indicating the recommended configuration includes: the first report is a MAC CE, and one bit in the first report indicates the waveform based on AI inference; bit "0" represents DFT-S-OFDM, and bit "1" represents CP-OFDM; or, bit "1" represents DFT-S-OFDM, and bit "0" represents CP-OFDM. As a supplementary embodiment, using one bit to indicate the recommended waveform is simple in design and saves signaling overhead.

[0119] As one embodiment, the first report indicating recommended configuration includes: a field in the first report indicating the index corresponding to the maximum power backoff value based on AI inference. As a supplementary embodiment, using an index to indicate the maximum power backoff value based on AI inference quantizes continuous values ​​into discrete values, saving signaling overhead.

[0120] As an example, the first signal is a baseband signal or a radio frequency signal.

[0121] As an example, the first signal is a reference signal.

[0122] As an example, the first signal is a physical channel.

[0123] As an example, the first signal is a physical layer signal.

[0124] As an example, the first signal is PUSCH (Physical Uplink Shared Channel).

[0125] As an example, the first signal is an SRS (Sounding Reference Signal).

[0126] As an example, the first signal is PUCCH (Physical Uplink Control Channel).

[0127] As an example, the first signal is PRACH (physical random access channel).

[0128] As one embodiment, the first signal includes PUSCH and demodulation reference signal (DMRS).

[0129] As an example, the first signal is a new reference signal or physical channel introduced by 6G.

[0130] As an example, the first signal is the physical channel mapped by UL-SCH (Uplink Shared Channel).

[0131] As an example, the first signal carries at least one of CSI (Channel State Information) or UL-SCH.

[0132] As an example, when the recommended configuration indicated by the first report only includes the maximum power back-off value based on AI inference, the first signal includes an uplink physical channel and an uplink reference signal, wherein the uplink physical channel includes at least one of PUSCH, PUCCH, SRS, and PRACH.

[0133] As an example, when the recommended configuration indicated by the first report includes the AI-based inference waveform, the first signal includes an uplink physical channel, which includes PUSCH or PUCCH.

[0134] As an example, the recommended configuration indicated by the first report includes at least one of the following: the waveform based on AI inference and the maximum power back-off value based on AI inference.

[0135] As an example, the recommended configuration indicated by the first report includes at least one of the following: the waveform based on AI inference and the maximum power backoff value based on AI inference.

[0136] As an example, the recommended configuration indicated by the first report includes at least one of the following: the waveform based on AI inference and the maximum power backoff value based on AI inference.

[0137] As an example, the recommended configuration indicated by the first report includes at least one of the following: the waveform based on AI inference and the maximum power backoff value based on AI inference. The recommended configuration indicated by the first report includes only the waveform based on AI inference and the maximum power backoff value based on AI inference.

[0138] As an example, the recommended configuration indicated in the first report may also include other recommended configurations.

[0139] As an example, the recommended configuration indicated in the first report may also include other scheduling-related recommended configurations.

[0140] As an example, the recommended configuration indicated by the first report also includes the MCS (Modulation and Coding Scheme) index recommended by the first node.

[0141] As an example, the recommended configuration indicated by the first report also includes the modulation scheme recommended by the first node.

[0142] As an example, the recommended configuration indicated by the first report also includes the modulation order recommended by the first node.

[0143] As an example, the recommended configuration indicated in the first report also includes a time window in which the recommended configuration takes effect.

[0144] As an example, the recommended configuration indicated by the first report also includes a time window for the recommended configuration to be applied.

[0145] As an example, the recommended configuration indicated by the first report also includes the first time window.

[0146] As an example, the reasoning corresponds to "inference".

[0147] As an example, the reasoning means prediction.

[0148] As an example, the meaning of the reasoning includes obtaining.

[0149] As an example, the reasoning includes recommendation.

[0150] As an example, the meaning of the reasoning includes assumption.

[0151] As an example, the meaning of "reasoning" includes generation.

[0152] As an example, the AI-based reasoning includes: ML (Machine Learning) based reasoning.

[0153] As an example, the AI-based reasoning includes reasoning based on AI (Artificial Intelligence) or ML (Machine Learning).

[0154] As an example, the AI-based reasoning includes reasoning based on neural networks.

[0155] As an example, the AI-based reasoning includes: AI-based prediction.

[0156] As an example, the AI-based reasoning includes: AI / ML-based prediction.

[0157] As an example, the AI-based reasoning is implemented in the UE.

[0158] As an example, the AI-based reasoning includes: obtaining information based on at least one AI / ML algorithm.

[0159] As an example, the AI-based reasoning includes: reasoning based on AI models.

[0160] As an example, the AI-based reasoning includes: the first node using AI-based reasoning.

[0161] As an example, the AI-based reasoning includes: the first node employing an AI model for reasoning.

[0162] As an example, the AI-based reasoning includes: further processing or quantification of the reasoning results based on the AI ​​model.

[0163] As an example, the AI-based inference includes: UE-sided model inference.

[0164] As an example, the AI-based inference includes: user part inference based on a two-sided model.

[0165] As an example, the output of the AI ​​inference or AI model is related to the UE implementation.

[0166] As an example, the input to the AI ​​inference or AI model is related to the UE implementation.

[0167] As an example, how AI inference is performed or which AI model is used is related to the UE implementation and is not defined in the standard.

[0168] As an example, the AI / ML model used by the first node is determined by the hardware equipment manufacturer.

[0169] As an example, the waveform based on AI inference is a waveform obtained through AI inference.

[0170] As an example, the waveform based on AI inference is the output of at least one AI model.

[0171] As an example, the AI-based inference waveform depends on parameters output by at least one AI model.

[0172] As an example, the waveform based on AI inference is obtained by further corresponding or mapping the parameters output by at least one AI model.

[0173] As an example, the AI-based inference waveform includes whether transform precoding is enabled.

[0174] As an example, the AI-inference-based waveform includes whether AI-inference-based transform precoding is enabled.

[0175] As an example, the waveform based on AI inference is obtained by the AI ​​model inferring the measurement results of the reference signal.

[0176] As an example, the waveform based on AI reasoning is obtained by the AI ​​model through reasoning and prediction of location information.

[0177] As an example, the waveform based on AI reasoning is obtained by the AI ​​model inferring its own position information and movement speed.

[0178] As an example, the waveform based on AI inference is obtained by the AI ​​model's understanding of the data on the logical channel.

[0179] As an example, the waveform based on AI reasoning is obtained by the AI ​​model from reasoning about other information.

[0180] As an example, the maximum power backoff value based on AI inference is the maximum power backoff value obtained through AI inference.

[0181] As an example, the maximum power backoff value based on AI inference is greater than or equal to 0.

[0182] As an example, the maximum power reduction value based on AI inference is the MPR (Maximum power reduction) value.

[0183] As an example, the maximum power backoff value based on AI inference is MPR. C value.

[0184] As an example, the maximum power backoff value based on AI inference is the A-MPR (additional maximum power reduction) value.

[0185] As an example, the maximum power reduction value based on AI inference is the P-MPR (power management maximum power reduction) value.

[0186] As an example, the unit of the maximum power backoff value based on AI inference is dBm (millidecibels).

[0187] As an example, the unit of the maximum power backoff value based on AI inference is Bm (decibels).

[0188] As an example, the unit of the maximum power backoff value based on AI inference is watts or milliwatts.

[0189] As an example, the maximum power backoff value based on AI inference is the output of at least one AI model.

[0190] As an example, the maximum power fallback value based on AI inference is obtained by quantizing, calculating or processing the output of an AI model.

[0191] As an example, the maximum power backoff value based on AI inference is obtained by further corresponding or mapping the parameters output by at least one AI model.

[0192] As an example, the maximum power backoff value based on AI inference is obtained by the AI ​​model through inference of the measurement results of the reference signal.

[0193] As an example, the maximum power backoff value based on AI inference is obtained by the AI ​​model through inference and prediction of location information.

[0194] As an example, the maximum power fallback value based on AI inference is obtained by the AI ​​model through inference of its own position information and movement speed.

[0195] As an example, the maximum power backoff value based on AI inference is obtained by the AI ​​model's understanding of the data in the logical channel.

[0196] As an example, the maximum power backoff value based on AI inference is obtained by the AI ​​model from inferences about other information.

[0197] As an example, the maximum power backoff value based on AI inference is based on an actual transmission.

[0198] As an example, the maximum power backoff value based on AI inference is based on a reference transmission.

[0199] As an example, the maximum power backoff value based on AI inference is based on a virtual transmission.

[0200] As an example, the maximum power backoff value based on AI inference is the maximum power backoff value inferred for an actual PUSCH.

[0201] As an example, the maximum power backoff value based on AI inference is the maximum power backoff value inferred for a reference PUSCH.

[0202] As an example, the maximum power backoff value based on AI inference is the maximum power backoff value inferred for a virtual PUSCH.

[0203] As an example, the maximum power backoff value based on AI inference is based on an actual transmission or based on a reference transmission.

[0204] As one embodiment, the maximum power back-off value based on AI inference is the maximum power back-off value corresponding to an assumed PUSCH transmission where all other conditions are the same except for the transform precoding state in an actual PUSCH transmission. As a supplementary embodiment, the transform precoding state is based on the AI ​​inference.

[0205] As one embodiment, the maximum power backoff value based on AI inference is the maximum power backoff value corresponding to an assumed PUSCH transmission under the condition that all other conditions are the same in an actual PUSCH transmission, except for the waveform. As a supplementary embodiment, the waveform of the assumed PUSCH is inferred based on AI. As a supplementary embodiment, the maximum power backoff value calculated using the waveform inferred by AI, and the other conditions for calculating the maximum power backoff value based on a known actual PUSCH, facilitate consensus between the base station and the user, helping the base station utilize the recommended configuration.

[0206] As one embodiment, the maximum power back-off value based on AI inference is the assumed maximum power back-off value corresponding to a PUSCH under the condition that all other conditions are the same in an actual PUSCH transmission except for the waveform and modulation order. As a supplementary embodiment, the waveform and modulation order are inferred based on AI. As a supplementary embodiment, calculating the maximum power back-off value through the waveform and modulation order inferred by AI helps the base station obtain information on the waveform and modulation order recommended by the user, thus assisting the base station in scheduling.

[0207] As a sub-example of the above embodiments, the other conditions include resource block allocation (RBallocation) type.

[0208] As a sub-example of the above embodiments, the other conditions include whether the resource block allocation type is edge resource block allocations, outer resource block allocations, or inner resource block allocations.

[0209] As a sub-example of the above embodiments, the actual transmission includes actual PUSCH transmission.

[0210] As a sub-implementation of the above embodiments, the actual transmission includes the actual uplink physical signal transmission.

[0211] As a sub-example of the above embodiments, the actual transmission includes the transmission of an uplink physical signal carrying the first report.

[0212] As a sub-example of the above embodiments, the actual transmission includes uplink physical signal transmission earlier than the first report.

[0213] As a sub-example of the above embodiments, the actual PUSCH transmission includes a PUSCH transmission carrying the first report.

[0214] As a sub-example of the above embodiments, the actual PUSCH transmission includes PUSCH transmissions earlier than the first reported transmission.

[0215] As an example, the candidate waveforms of the first signal include DFT-s-OFDM (Discrete Fourier Transform Spread Orthogonal Frequency Division Multiplexing) waveforms.

[0216] As an example, the candidate waveforms of the first signal include CP-OFDM (Cyclic Prefix Orthogonal Frequency Division Multiplexing) waveforms.

[0217] As an example, the candidate waveforms of the first signal include DFT-s-OFDM waveforms and CP-OFDM waveforms.

[0218] As an example, the candidate waveforms of the first signal include W-OFDM (Wideband Orthogonal Frequency Division Multiplexing) waveforms.

[0219] As an example, the candidate waveforms of the first signal include SC-FDMA (Single Carrier-Frequency Division Multiple Access).

[0220] As an example, the candidate waveforms of the first signal include FDMA (Frequency Division Multiple Access).

[0221] As an example, the candidate waveforms of the first signal include F-OFDM (Filtered OFDM) waveforms.

[0222] As an example, the candidate waveforms of the first signal include CPS-OFDM (Circularly Pulse Shaped-Orthogonal Frequency Division Multiplexing).

[0223] As one embodiment, the multiple candidate waveforms of the first signal include FB-OFDM (Filter Bank-Orthogonal Frequency Division Multiplexing).

[0224] As an example, the candidate waveforms of the first signal include orthogonal time-frequency space (OTFS) waveforms.

[0225] As an example, the multiple candidate waveforms of the first signal include waveforms generated by windowing based on OFDM.

[0226] As an example, the multiple candidate waveforms of the first signal include waveforms generated by filtering based on OFDM.

[0227] As one example, the multiple candidate waveforms of the first signal include waveforms after filtering or processing OFDM using AI.

[0228] As an example, multiple candidate waveforms of the first signal are used to generate the baseband signal or radio frequency signal of the uplink physical channel.

[0229] As an example, the candidate waveforms of the first signal are waveforms used for uplink transmission.

[0230] As an example, the candidate waveforms of the first signal are candidate waveforms for uplink transmission.

[0231] As an example, the multiple candidate waveforms of the first signal are the waveforms of the baseband signal or radio frequency signal used by the modulation symbols to generate the physical channel.

[0232] As one embodiment, the modulation symbol is passed through one of a plurality of candidate waveforms of the first signal to generate a baseband signal or radio frequency signal for PUSCH.

[0233] As an example, the AI-inference-based waveform being one of a plurality of candidate waveforms of the first signal includes: the AI-inference-based waveform being a possible waveform of the first signal.

[0234] As an example, the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, including: the AI-inference-based waveform is a configurable waveform of the first signal.

[0235] As an example, the AI-inference-based waveform being one of a plurality of candidate waveforms of the first signal includes: the candidate waveform of the AI-inference-based waveform being a candidate waveform of the first signal.

[0236] As an example, the unit of the maximum output power value of the first signal is dBm (millidecibels).

[0237] As an example, the unit of the maximum output power value of the first signal is dB (decibels).

[0238] As an example, the unit of the maximum output power value of the first signal is watts or milliwatts.

[0239] As an example, the maximum output power value of the first signal is greater than 0.

[0240] As an example, the maximum output power value of the first signal is the maximum output power allowed per carrier.

[0241] As an example, the maximum output power value of the first signal is the maximum output power configured by the first node (UE configured maximum output power).

[0242] As an example, the maximum output power value of the first signal is configured per carrier.

[0243] As an example, the maximum output power value of the first signal is configured per cell.

[0244] As an example, the maximum output power value of the first signal is configured per transmission occasion.

[0245] As an example, the maximum output power value of the first signal is the maximum output power configured for the first node.

[0246] As an example, the maximum output power value of the first signal is the configured maximum output power of the first node in the carrier occupied by the serving cell to which the first signal belongs and in the transmission opportunity to which the first signal belongs in the time domain.

[0247] As an example, the maximum output power value of the first signal is the maximum transmission power that the first signal can achieve.

[0248] As an example, the maximum output power value of the first signal is the P value corresponding to the first signal. CMAX The value of .

[0249] As an example, the maximum output power value of the first signal is the P value corresponding to the first signal. CMAX,f,c The value of (i).

[0250] As an example, the maximum output power value of the first signal is the user-configured maximum output power value P in transmission opportunity i of carrier f in serving cell c. CMAX,f,c (i).

[0251] As an example, the maximum output power value of the first signal is within a certain range.

[0252] As an example, the maximum output power value of the first signal is within a closed interval.

[0253] As an example, the maximum output power value of the first signal is configured or determined by the first node within the range of the maximum output power value of the first signal.

[0254] As an example, the maximum output power value of the first signal also depends on the power level of the first node.

[0255] As an example, the range of the maximum output power value of the first signal depends on the power level of the first node.

[0256] As an example, at least one parameter for calculating the range of the maximum output power value of the first signal depends on the power level of the first node.

[0257] As an example, the first maximum power back-off value is MPR. C .

[0258] As an example, the first maximum power back-off value is A-MPR. C .

[0259] As an example, the first maximum power back-off value is ΔMPR. c .

[0260] As an example, the first maximum power back-off value is P-MPR. c .

[0261] As an example, the unit of the first maximum power back-off value is dBm (millidecibels).

[0262] As an example, the unit of the first maximum power back-off value is Bm (decibels).

[0263] As an example, the unit of the first maximum power back-off value is watts or milliwatts.

[0264] As an example, the first maximum power backoff value is greater than or equal to 0.

[0265] As an example, the first maximum power backoff value depends on the power class.

[0266] As an example, the first maximum power backoff value depends on the power level of the first node.

[0267] As an example, the first maximum power backoff value is per power class.

[0268] As an example, the first maximum power backoff value has corresponding values ​​under different power classes.

[0269] As an example, the first maximum power back-off value depends on the operating band number to which the frequency band occupied by the first signal belongs.

[0270] As an example, the first maximum power back-off value depends on the modulation scheme of the first signal.

[0271] As a sub-example of this embodiment, the modulation method of the first signal includes at least one of Pi / 2BPSK (Binary Phase Shift Keying) modulation, QPSK (Quadrature Phase Shift Keying) modulation, 16QAM (Quadrature Amplitude Modulation) modulation, 64QAM modulation, 256QAM modulation, and 1024QAM modulation.

[0272] As a sub-example of this embodiment, the modulation method of the first signal further includes modulation based on AI / ML methods or constellation mapping.

[0273] As a sub-example of this embodiment, the modulation method of the first signal also includes modulation methods other than those described above.

[0274] As an example, the first maximum power back-off value has corresponding values ​​under different modulation methods.

[0275] As an example, the first maximum power back-off value depends on the waveform of the first signal.

[0276] As an example, the first maximum power back-off value also depends on the position of the first signal in the frequency domain.

[0277] As an example, the first maximum power backoff value also depends on the position of the first signal in the maximum channel bandwidth.

[0278] As an example, the first maximum power backoff value also depends on the resource block allocation type of the first signal.

[0279] As a sub-example of this embodiment, the resource block allocation type of the first signal includes at least one of edge resource block allocations, outer resource block allocations, and inner resource block allocations.

[0280] As one embodiment, the maximum output power value of the first signal depending on the first maximum power back-off value includes: the maximum output power value of the first signal is related to the first maximum power back-off value.

[0281] As one embodiment, the maximum output power value of the first signal depends on a first maximum power back-off value, including: the first maximum power back-off value is used to determine the maximum output power value of the first signal.

[0282] As one embodiment, the maximum output power value of the first signal depends on a first maximum power backoff value, including: the first maximum power backoff value is used to calculate the maximum output power value of the first signal.

[0283] As one embodiment, the maximum output power value of the first signal depends on the first maximum power back-off value, including: the range of the maximum output power value of the first signal depends on the first maximum power back-off value.

[0284] As one embodiment, the maximum output power value of the first signal depends on the first maximum power back-off value, including: the setting range of the maximum output power value of the first signal depends on the first maximum power back-off value.

[0285] As one embodiment, the maximum output power value of the first signal depending on the first maximum power backoff value includes: the upper limit or lower limit of the maximum output power value of the first signal depending on the first maximum power backoff value.

[0286] As an example, the maximum output power value of the first signal depends on a first maximum power backoff value, which includes: the lower limit of the maximum output power value of the first signal is an expression, and the first maximum power backoff value is a parameter for calculating the lower limit of the maximum output power value of the first signal.

[0287] As an example, the maximum output power value of the first signal depends on a first maximum power back-off value, including: the maximum output power is P. CMAX,f,c P CMAX_L,f,c ≤P CMAX,f,c ≤P CMAX_H,f,c ,in

[0288] P CMAX_L,f,c =MIN{P EMAX,c -ΔT C,c , (P PowerClass -ΔP PowerClass )-MAX(MAX(MPR c +ΔMPR c A-MPR c )+ΔT IB,c +ΔT C,c +ΔT RxSRS P-MPR c )},

[0289] P CMAX_H,f,c =MIN{P EMAX,c P PowerClass -ΔP PowerClass},

[0290] P EMAX,c The value indicated by the high-level parameter, P PowerClass It is the maximum terminal power, obtained according to a predefined table per band per power level, ΔP PowerClass It is the offset of the maximum terminal power, which depends on user capabilities, network-side configuration, number of symbols transmitted uplink, power level of the sender of the first PRDCH, modulation scheme, waveform, etc., ΔT IB,c It is the additional tolerance of the serving cell, ΔT C,c It is the power lower limit offset, MPR c It is the maximum power reduction (A-MPR). c It is the additional maximum allowable power reduction, ΔMPR c It is the maximum power reduction offset, ΔT RxSRS It is the offset during SRS transmission, P-MPR cIt is the maximum power reduction in power management (MPR). c ΔMPR c P-MPR c and A-MPR c One of them is the first maximum output power backoff value.

[0291] As an example, the maximum output power value of the first signal depends on a first maximum power back-off value, including: the maximum output power is P. CMAX,f,c P CMAX_L,f,c ≤P CMAX,f,c ≤P CMAX_H,f,c ,in

[0292] P CMAX_L,f,c =MIN{P EMAX,c -ΔT C,c , (P PowerClass -ΔP PowerClass )-MAX(MAX(MPR c +ΔMPR c A-MPR c )+ΔT IB,c +ΔT C,c +ΔT RxSRS P-MPRc )},

[0293] P CMAX_H,f,c =MIN{P EMAX,c P PowerClass -ΔP PowerClass},

[0294] P EMAX,c The value indicated by the high-level parameter, P PowerClass It is the maximum terminal power, obtained according to a predefined table per band per power level, ΔT PowerClass It is the offset of the maximum terminal power, which depends on user capabilities, network-side configuration, number of symbols transmitted uplink, power level of the sender of the first PRDCH, modulation scheme, waveform, etc., ΔT IB,c It is the additional tolerance of the serving cell, ΔT C,c It is the power lower limit offset, MPR c It is the first maximum power back-off value, A-MPR c It is the additional maximum allowable power reduction, ΔMPR c It is the maximum power reduction offset, ΔT RxSRS It is the offset during SRS transmission, P-MPR cIt is the maximum power reduction in power management.

[0295] As an example, the maximum power backoff value based on AI inference being one of a plurality of candidate values ​​of the first maximum power backoff value includes: the maximum power backoff value based on AI inference being a possible value of the first maximum power backoff value.

[0296] As an example, the maximum power backoff value based on AI inference being one of several candidate values ​​of the first maximum power backoff value includes: the maximum power backoff value based on AI inference and the first maximum power backoff value being two identical or different values ​​of the same parameter.

[0297] As an example, the maximum power backoff value based on AI inference being one of a plurality of candidate values ​​of the first maximum power backoff value includes: the maximum power backoff value based on AI inference being a parameter for determining the maximum output power of the uplink signal.

[0298] As an example, the maximum power backoff value based on AI inference being one of a plurality of candidate values ​​of the first maximum power backoff value includes: the maximum power backoff value based on AI inference being the value of the parameter corresponding to the first maximum power backoff value based on AI inference.

[0299] As one embodiment, the maximum power backoff value based on AI inference being one of a plurality of candidate values ​​of the first maximum power backoff value includes: the maximum power backoff value based on AI inference being one of a plurality of candidate values ​​of the first maximum power backoff value.

[0300] As an example, the recommended configuration indicated by the first report for a first time window includes: the recommended configuration indicated by the first report taking effect within the first time window.

[0301] As an example, the recommended configuration indicated by the first report for a first time window includes: the recommended configuration indicated by the first report is generated by the first node for the first time window.

[0302] As an example, the recommended configuration indicated by the first report for the first time window includes: the recommended configuration indicated by the first report is the configuration recommended by the first node for the first time window.

[0303] As an example, the recommended configuration indicated by the first report for a first time window includes: the recommended configuration indicated by the first report is applied to the first time window.

[0304] As an example, the recommended configuration indicated by the first report for a first time window includes: both the recommended configuration indicated by the first report and the first time window are the outputs of an AI / ML model.

[0305] As an example, the recommended configuration indicated by the first report for a first time window includes: the time window for the recommended application of the recommended configuration indicated by the first report is the first time window.

[0306] As an example, the recommended configuration indicated by the first report for a first time window includes: the recommended configuration indicated by the first report is a recommended configuration for scheduling within the first time window.

[0307] As an example, the recommended configuration indicated by the first report for a first time window includes: the recommended configuration indicated by the first report is the recommended configuration for scheduling the second node in this application within the first time window.

[0308] As an example, the recommended configuration indicated by the first report for the first time window includes: the recommended configuration indicated by the first report is the configuration that the second node expects or recommends when scheduling uplink transmission within the first time window.

[0309] As one embodiment, the recommended configuration indicated by the first report for a first time window includes: the first report indicating a recommended waveform for uplink transmission within the first time window.

[0310] As an example, the recommended configuration indicated by the first report for a first time window includes: the waveform based on AI inference recommended by the first node for uplink transmission within the first time window, as indicated by the first report.

[0311] As an example, the recommended configuration indicated by the first report for a first time window includes: the first report indicating a recommended maximum power back-off value for uplink transmission within the first time window.

[0312] As an example, the recommended configuration indicated by the first report for a first time window includes: the maximum power backoff value based on AI inference recommended by the first node for uplink transmission within the first time window, as indicated by the first report.

[0313] As an example, the recommended configuration indicated by the first report for a first time window includes: the first report indicating the recommended maximum power backoff value and waveform for uplink transmission within the first time window.

[0314] As an example, the first time window is a time window based on AI inference.

[0315] As an example, the first time window is inferred by AI.

[0316] As an example, the first time window is the time window inferred by the first node.

[0317] As an example, both the first time window and the recommended configuration are outputs of the AI ​​model.

[0318] As an example, the first time window is a time window inferred by the first node through AI.

[0319] As an example, the first time window includes the start time inferred by the first node through AI and the duration inferred by the first node through AI.

[0320] As an example, the first time window is a time window configured on the network side.

[0321] As an example, the first time window is a future time window.

[0322] As an example, the first time window includes at least a period of time that is in the future.

[0323] As one embodiment, the first time window comprises a continuous period of time.

[0324] As one embodiment, the first time window comprises a continuous absolute time period.

[0325] As one embodiment, the first time window includes a continuous time slot, frame, or subframe.

[0326] As an example, the length of the first time window is measured in seconds or milliseconds.

[0327] As an example, the unit of the time window length of the first time window is a frame, a subframe, or a time slot.

[0328] As an example, the start time of the first time window is the current time.

[0329] As an example, the start time of the first time window depends on the time when the first report was generated.

[0330] As one embodiment, the start time of the first time window depends on the transmission time of the wireless signal carrying the first report.

[0331] As an example, the start time of the first time window depends on the time when the first report is submitted to the lower protocol layer.

[0332] As an example, the start time of the first time window depends on the latest measurement time window associated with the first time window.

[0333] As an example, the start time of the first time window depends on a time offset.

[0334] As one example, the start time of the first time window depends on the time of the reference signal.

[0335] As an example, the start time of the first time window depends on the time of the reference signal associated with the recommended configuration.

[0336] As an example, the start time of the first time window depends on the time window in which the first node obtains the latest measurement reference signal of the recommended configuration.

[0337] As an example, the start time of the first time window depends on the reference time and the first time offset.

[0338] As a sub-implementation of this embodiment, the reference time includes at least one of the time when the first report was generated, the time when the wireless signal carrying the first report was transmitted, and the latest measurement time window associated with the first time window.

[0339] As a sub-implementation of this embodiment, the reference time is one of the following: the time when the first report was generated, the time when the wireless signal carrying the first report was transmitted, and the latest measurement time window associated with the first time window.

[0340] As a sub-implementation of this embodiment, the start time of the first time window is determined jointly by the time the first report was generated and the first time offset.

[0341] As a sub-implementation of this embodiment, the start time of the first time window is a first time offset after the reference time.

[0342] As a sub-implementation of this embodiment, the start time of the first time window is later than the reference time by a first time offset.

[0343] As a sub-implementation of this embodiment, the first time window begins from the time length after the reference time when the first time offset is calculated.

[0344] As a sub-implementation of this embodiment, the start time of the first time window is the reference time plus the first time offset.

[0345] As a sub-implementation of this embodiment, the first time window starts from the reference time plus the first time offset.

[0346] As a sub-implementation of this embodiment, the unit of the first time offset is seconds or milliseconds.

[0347] As a sub-implementation of this embodiment, the unit of the first time offset is a frame, a subframe, or a time slot.

[0348] As an example, the start time of the first time window is determined based on AI inference.

[0349] As an example, the length of the first time window is determined based on AI inference.

[0350] As an example, the first time window is the SLIV (start and length indicator value) corresponding to a continuous time-domain resource.

[0351] As one embodiment, the first time window is configured, or as indicated by the first report, the first time window is configured. As a supplementary embodiment, the network side configures the first time window to reduce signaling overhead.

[0352] As an example, the first time window is configured or indicated by the first report, including: the first time window is explicitly or implicitly configured by higher-layer signaling or higher-layer parameters.

[0353] As one embodiment, the first time window is configured or indicated by the first report, including: the first time window is configured on the network side.

[0354] As an example, the first time window is configured or indicated by the first report, including: the first time window is configured by higher-level signaling or higher-level parameters.

[0355] As an example, the first time window is configured or indicated by the first report, including: the first time window is configured by RRC layer parameters or RRC layer signaling.

[0356] As an example, the first time window is configured or indicated by the first report, including: the duration of the first time window is configured.

[0357] As an example, the first time window is configured or indicated by the first report, including: the start time of the first time window is configured.

[0358] As an example, the first time window is configured or indicated by the first report, including: the start time of the first time window relative to a reference time is configured as a time offset.

[0359] As an example, the first time window is configured or indicated by the first report, including that the start time and duration of the first time window are configured by high-level parameters.

[0360] As an example, the first time window is configured or indicated by the first report, including: the start time of the first time window is a predefined offset time relative to a reference time, and the length of the first time window is configured by higher-layer parameters or higher-layer signaling.

[0361] As an example, the first time window is configured or indicated by the first report to include: the start time of the first time window is an offset time relative to a reference time configured by higher-level parameters, and the length of the first time window is predefined.

[0362] As one embodiment, the first time window is configured or indicated by the first report, including: the first time window is indicated by the first report. As a supplementary embodiment, the first report indicates the first time window, which can be adjusted according to the user's own situation or reasoning, making it more flexible.

[0363] As an example, the first time window is configured or indicated by the first report, including: the first report explicitly or implicitly configuring the first time window.

[0364] As an example, the first time window is configured or indicated by the first report, including at least one field included in the first report indicating the first time window.

[0365] As an example, the first time window is configured or indicated by the first report, including: at least one field included in the first report indicating the start time of the first time window or the duration of the first time window.

[0366] As an example, the first time window is configured or indicated by the first report, including at least one field in the first report indicating the index corresponding to the first time window.

[0367] As an example, the first time window is configured or indicated by the first report, including: the first report indicating the SLIV value corresponding to the first time window.

[0368] As one embodiment, the first time window is configured or indicated by the first report, including: the first time window is jointly determined by the network-side configuration and the indication of the first report.

[0369] As one embodiment, the first time window is configured or indicated by the first report, including: the first time window depends on the network-side configuration and the indication of the first report.

[0370] As one embodiment, the first time window is configured or indicated by the first report, including: the candidate time windows of the first time window are configured, and the first report indicates the index corresponding to the first time window from the candidate time windows of the first time window.

[0371] As one embodiment, the first time window is configured or indicated by the first report, including: the candidate time length of the first time window is configured, and the first report indicates the index corresponding to the first time window from the candidate time length of the first time window.

[0372] As one embodiment, the first time window is configured or indicated by the first report, including: the candidate start time of the first time window is configured, and the first report indicates the index corresponding to the first time window from the candidate start times of the first time window.

[0373] As an example, the first time window is configured or indicated by the first report, including: the candidate length and candidate start time of the first time window are both configured, and the first report indicates the index corresponding to the first time window from the candidate start time and candidate time length of the first time window, respectively.

[0374] Example 2

[0375] Example 2 illustrates a schematic diagram of a network architecture according to this application, as shown in the attached diagram. Figure 2 As shown. (Attached) Figure 2This diagram illustrates the network architecture 200 for 6G, 5G NR, 5G-Advanced, LTE (Long-Term Evolution), and LTE-A (Long-Term Evolution Advanced) systems. The 6G, 5G NR, or LTE network architecture 200 may be referred to as 6GS (6G System) / 5GS (5G System) / EPS (Evolved Packet System) 200 or some other suitable terminology. The 6GS / 5GS / EPS 200 may include one or more UEs (User Equipment) 201, NG-RAN (Next Generation Radio Access Network) 202, 6GC (6G Core Network) / 5GC (5G Core Network) / EPC (Evolved Packet Core) 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet services 230. The 6GS / 5GS / EPS can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown in the figure, the 6GS / 5GS / EPS provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The NG-RAN includes network node 203 and other network nodes 204. Network node 203 provides user and control plane protocol termination toward UE 201. Network node 203 can connect to other network nodes 204 via backhaul. Network node 203 may also be referred to as eNB, gNB, base station, ground station, satellite base station, aircraft base station, base transceiver station, radio base station, radio transceiver, transceiver function, Basic Services Set (BSS), Extended Services Set (ESS), TRP (Transmitter Receiver Node), or some other suitable term. Network node 203 provides UE 201 with an access point to 6GC / 5GC / EPC210. ​​Examples of UE 201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, non-terrestrial communications, satellite mobile communications, GPS, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, IoT devices, machine-type communication devices, land vehicles, automobiles, wearable devices, test equipment, RFID devices, electronic tags, sensor devices, test instruments, test tools, or any other similar functional devices.Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, radio terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. Network node 203 is connected to 6GC / 5GC / EPC210 via the S1 / NG interface. 6GC / 5GC / EPC210 includes MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MME / AMF / SMF 214, S-GW (Service Gateway) / UPF (User Plane Function) 212, and P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF211 is the control node that handles signaling between UE201 and 6GC / 5GC / EPC210. ​​Essentially, the MME / AMF / SMF211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF212, which is itself connected to the P-GW / UPF213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF213 is connected to Internet service 230. Internet service 230 includes operator-compliant Internet Protocol services, specifically including the Internet, intranet, IMS (IP Multimedia Subsystem), and packet-switched streaming services.

[0376] As an example, the UE201 corresponds to the first node in this application.

[0377] As an example, the UE201 supports AI functionality.

[0378] As an example, the gNB(eNB)201 corresponds to the second node in this application.

[0379] As an example, the gNB (eNB) 201 supports AI functionality.

[0380] Example 3

[0381] Example 3 illustrates a schematic diagram of a wireless protocol architecture for a user plane and a control plane according to this application, as shown in the attached diagram. Figure 3 As shown. Figure 3 This is a schematic diagram illustrating an embodiment of a radio protocol architecture for the user plane 350 and the control plane 300. Figure 3The radio protocol architecture for the control plane 300 between the first node (UE or gNB) and the second node (gNB or UE) is illustrated using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (Physical Layer) signal processing functions. L1 layer will be referred to as PHY301 in this document. Layer 2 (L2 layer) 305 sits above PHY301 and is responsible for the link between the first and second nodes via PHY301. L2 layer 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second node. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. The PDCP sublayer 304 also provides security through encrypted data packets and supports cross-regional mobility between the second and first nodes. RLC sublayer 303 provides upper-layer packet segmentation and reassembly, retransmission of lost packets, and packet reordering to compensate for out-of-order reception due to HARQ. MAC sublayer 302 provides multiplexing between the logical and transport channels. MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) within a cell among the first nodes. MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in Layer 3 (L3) of the control plane 300 is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layer using RRC signaling between the second and first nodes. The radio protocol architecture of user plane 350 includes Layer 1 (L1 layer) and Layer 2 (L2 layer). The radio protocol architecture for the first and second nodes in user plane 350 is largely the same as the corresponding layers and sublayers in control plane 300 for Physical Layer 351, PDCP sublayer 354 in L2 layer 355, RLC sublayer 353 in L2 layer 355, and MAC sublayer 352 in L2 layer 355. However, PDCP sublayer 354 also provides header compression for upper layer packets to reduce radio transmission overhead. L2 layer 355 in user plane 350 also includes SDAP (Service Data Adaptation Protocol) sublayer 356. SDAP sublayer 356 is responsible for mapping between QoS streams and Data Radio Bearers (DRBs) to support service diversity.Although not illustrated, the first node may have several upper layers above L2 layer 355, including a network layer (e.g., IP layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., remote UE, server, etc.).

[0382] As an example, Appendix Figure 3 The wireless protocol architecture described herein is applicable to the first node in this application.

[0383] As an example, Appendix Figure 3 The wireless protocol architecture described herein is applicable to the second node in this application.

[0384] As an example, the first report in this application is generated by MAC302, or MAC352, or PHY301, or PHY351.

[0385] As an example, the first signal in this application is generated by the RRC306, or MAC302, or MAC352, or PHY301, or PHY351.

[0386] As an example, the first reference signal in this application is generated in the PHY301 or PHY351.

[0387] As an example, the first information block in this application is generated in RRC306, or MAC302, or MAC352, or PHY301, or PHY351.

[0388] As an example, the second information block in this application is generated in RRC306, or MAC302, or MAC352, or PHY301, or PHY351.

[0389] As an example, the second report in this application is generated by the RRC306, or the MAC302, or the MAC352, or the PHY301, or the PHY351.

[0390] Example 4

[0391] Example 4 illustrates a schematic diagram of a first node and a second node according to an embodiment of this application, as shown in the attached diagram. Figure 4 As shown.

[0392] The first node (450) may include a controller / processor 490, a data source / buffer 480, a receiver processor 452, a transmitter / receiver 456 and a transmitter processor 455, the transmitter / receiver 456 including an antenna 460.

[0393] The second node (410) may include a controller / processor 440, a data source / buffer 430, a receiver processor 412, a transmitter / receiver 416 and a transmitter processor 415, wherein the transmitter / receiver 416 includes an antenna 420.

[0394] In the transmission from the second node (410) to the first node (450), upper-layer packets are provided to the controller / processor 440. The controller / processor 440 implements functions of Layer 2 and above. The controller / processor 440 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the first node 450 based on various priority metrics. The controller / processor 440 is also responsible for HARQ operation, retransmission of lost packets, and higher-layer signaling to the first node 450. The higher-layer information carried by the first information block in this application is generated in the controller / processor 440. The transmit processor 415 implements various signal processing functions for Layer 1 (i.e., physical layer), including encoding, interleaving, scrambling, modulation, power control / allocation, precoding, and physical layer control signaling generation, such as the physical layer signal carrying the first information block in this application and the first reference signal in this application, which are completed in the transmit processor 415. The generated modulation symbols are divided into parallel streams, and each stream is mapped to a corresponding multicarrier subcarrier and / or multicarrier symbol. These are then transmitted by the transmit processor 415 via the transmitter 416 to the antenna 420 as radio frequency (RF) signals. At the receiver, each receiver 456 receives the RF signal through its corresponding antenna 460. Each receiver 456 recovers the baseband information modulated onto the RF carrier and provides the baseband information to the receive processor 452. The receive processor 452 implements various signal reception processing functions at Layer 1. These signal reception processing functions include demodulating the physical layer signal of the first information block and the first reference signal in this application using multicarrier symbols in the multicarrier symbol stream based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK)), followed by descrambling, decoding, and deinterleaving to recover the data or control transmitted by the second node device 410 on the physical channel. The data and control signals are then provided to the controller / processor 490. The controller / processor 490 is responsible for the L2 layer and above, and interprets higher-level information, including the higher-level information carried in the first information block. The controller / processor may be associated with a memory 480 that stores program code and data. The memory 480 may be referred to as computer-readable media.

[0395] In the transmission from the first node (450) to the second node (410), similar to the transmission from the second node (410) to the first node (450), the higher-layer information includes the second information block of this application, the first report of this application, the second report of this application, and the first signal of this application (if carrying higher-layer information). After being generated by the controller / processor 490, the first signal is processed by the transmitter processor 455 to perform various signal transmission processing functions for the L1 layer (i.e., the physical layer). The physical layer signal carrying the second information block of this application, the physical layer signal carrying the first report of this application, and the physical layer signal carrying the second report of this application are also included. The first signal of this application is mapped by the transmitter processor 455 to the antenna 460 via the transmitter 456 and transmitted as a radio frequency signal. The receiver 416 receives the radio frequency signal through its corresponding antenna 420. Each receiver 416 recovers the baseband information modulated onto the radio frequency carrier and provides the baseband information to the receiver processor 412. The receiver processor 412 implements various signal receiving and processing functions for the L1 layer (i.e., the physical layer), including receiving and processing physical layer signals carrying the second information block of this application, physical layer signals carrying the first report of this application, and physical layer signals carrying the second report of this application. The first signal of this application subsequently provides data and / or control signals to the controller / processor 440. The controller / processor 440 implements L2 layer functions, including interpreting higher-layer information such as the second information block of this application, the first report of this application, the second report of this application, and the first signal of this application (e.g., carrying higher-layer information). The controller / processor may be associated with a buffer 430 that stores program code and data. The buffer 430 may be a computer-readable medium.

[0396] As one embodiment, the first node 450 device includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor, and the first node 450 device at least: sends a first report, the first report indicating a recommended configuration; sends a first signal; wherein the recommended configuration indicated by the first report includes at least one of an AI inference-based waveform and an AI inference-based maximum power backoff value; the AI ​​inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, the AI ​​inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, the first time window being configured or indicated by the first report.

[0397] As one embodiment, the first node 450 device includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: sending a first report indicating a recommended configuration; and sending a first signal; wherein the recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[0398] As one embodiment, the second node device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second node device 410 at least: receives a first report indicating a recommended configuration; receives a first signal; wherein the recommended configuration indicated by the first report includes at least one of an AI inference-based waveform and an AI inference-based maximum power backoff value; the AI ​​inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, the AI ​​inference-based maximum power backoff value being one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, the first time window being configured or indicated by the first report.

[0399] As one embodiment, the second node 410 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: receiving a first report indicating a recommended configuration; receiving a first signal; wherein the recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, the AI-inference-based maximum power backoff value being one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[0400] As an example, the first node 450 is a user equipment (UE).

[0401] As an example, the first node 450 is a user device that supports AI / ML functions.

[0402] As one embodiment, the second node 410 is a base station device (gNB / eNB).

[0403] As an example, the second node 410 is a base station device that supports AI / ML functions.

[0404] As one embodiment, receiver 456 (including antenna 460), receiver processor 452 and controller / processor 490 are used to receive the first information block in this application.

[0405] As one embodiment, receiver 456 (including antenna 460), receiver processor 452 and controller / processor 490 are used to receive the first reference signal in this application.

[0406] As one embodiment, transmitter 456 (including antenna 460), transmitter processor 455 and controller / processor 490 are used to transmit the second information block in this application.

[0407] As one embodiment, transmitter 456 (including antenna 460), transmitter processor 455 and controller / processor 490 are used to transmit the first report in this application.

[0408] As one embodiment, transmitter 456 (including antenna 460), transmitter processor 455 and controller / processor 490 are used to transmit the first signal in this application.

[0409] As one embodiment, transmitter 456 (including antenna 460), transmitter processor 455 and controller / processor 490 are used to transmit the second report in this application.

[0410] As one embodiment, a transmitter 416 (including an antenna 420), a transmitter processor 415, and a controller / processor 440 are used to transmit the first information block in this application.

[0411] As one embodiment, transmitter 416 (including antenna 420), transmitter processor 415 and controller / processor 440 are used to transmit the first reference signal in this application.

[0412] As one embodiment, receiver 416 (including antenna 420), receiver processor 412 and controller / processor 440 are used to receive the second information block in this application.

[0413] As one embodiment, receiver 416 (including antenna 420), receiver processor 412 and controller / processor 440 are used to receive the first report in this application.

[0414] As one embodiment, receiver 416 (including antenna 420), receiver processor 412 and controller / processor 440 are used to receive the first signal in this application.

[0415] As one embodiment, receiver 416 (including antenna 420), receiver processor 412 and controller / processor 440 are used to receive the second report in this application.

[0416] Example 5

[0417] Example 5 illustrates a flowchart of the transmission between the first node and the second node according to an embodiment of this application, as shown in the attached diagram. Figure 5 As shown. In the appendix Figure 5 In this example, the second node N500 is the sustaining base station for the serving cell of the first node U550. It should be noted that the order in this example does not limit the signal transmission order or the implementation order in this application.

[0418] for Second node N500 In step S501, a first information block is sent; in step S502, a second information block is received; in step S503, a first reference signal is sent; in step S504, a first report is received; in step S505, a first signal is received; and in step S506, a second report is received.

[0419] for First node U550 In step S551, a first information block is received; in step S552, a second information block is sent; in step S553, a first reference signal is received; in step S554, a first report is sent; in step S555, a first signal is sent; and in step S556, a second report is sent.

[0420] In Example 5, the first report indicates a recommended configuration; the recommended configuration indicated by the first report includes at least one of an AI-based inference waveform and an AI-based inference maximum power backoff value; the AI-based inference waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-based inference maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report. The recommended configuration indicated by the first report depends on first inference, the input of which depends on a measurement of the first reference signal. The first information block indicates a first condition; the second information block indicates that a first AI function is applicable; the first AI function is applicable under the first condition, and the recommended configuration indicated by the first report depends on the first AI function. The second report indicates that a second AI function is not applicable, and the recommended configuration indicated by the first report depends on the second AI function; the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[0421] As an example, the first signal precedes the first information block.

[0422] As an example, the first signal is later than the first information block.

[0423] As an example, the first signal precedes the second information block.

[0424] As an example, the first signal is later than the second information block.

[0425] As one embodiment, the first signal carries the second information block.

[0426] As an example, the first signal precedes the first reference signal.

[0427] As an example, the first signal is later than the first reference signal.

[0428] As an example, the first signal precedes the first report.

[0429] As an example, the first signal is later than the first report.

[0430] As an example, the first signal carries the first report.

[0431] As an example, the first signal precedes the second report.

[0432] As an example, the first signal is later than the second report.

[0433] As one embodiment, the first signal carries the second report.

[0434] Example 6

[0435] Example 6 illustrates a schematic diagram of a first reference signal according to an embodiment of this application, as shown in the attached diagram. Figure 6 As shown. In the appendix Figure 6 In the diagram, the horizontal axis represents time, and the rectangle filled with diagonal lines represents the first reference signal.

[0436] In Example 6, the recommended configuration indicated by the first report depends on a first inference, the input of which depends on a measurement of the first reference signal.

[0437] As an example, the location of the UE or its position in the cell is predicted in the future based on the current and historical measurement results of the reference signal, and then the waveform or maximum power backoff value is recommended, which improves the base station scheduling efficiency and enhances the robustness of the system.

[0438] As an example, the first reference signal is a downlink reference signal.

[0439] As an example, the first reference signal is periodic.

[0440] As an example, the first reference signal is semi-persistent.

[0441] As an example, the first reference signal is aperiodic.

[0442] As an example, the first reference signal includes CSI-RS (Channel State Information Reference Signal).

[0443] As one embodiment, the first reference signal includes an SSB (Synchronization Signal Block).

[0444] As one embodiment, the first reference signal includes a PRS (positioning reference signal).

[0445] As one embodiment, the first reference signal includes DMRS.

[0446] As an example, the first reference signal occupies at least one reference signal resource.

[0447] As an example, the first reference signal occupies one reference signal resource.

[0448] As one embodiment, the first reference signal occupies multiple reference signal resources.

[0449] As an example, the first reference signal is a CSI-RS that occupies one reference signal resource.

[0450] As one embodiment, the first reference signal is part or all of a set of reference signal resources.

[0451] As one embodiment, the first reference signal is a plurality of SSBs corresponding to the same index.

[0452] As an example, the first inference is an AI inference or an ML inference.

[0453] As an example, the first inference is inference performed using an AI model or an ML model.

[0454] As an example, the first reasoning is an implementation of the AI-based reasoning described in this application.

[0455] As an example, the first reasoning is the AI-based reasoning described in this application.

[0456] As an example, the first reasoning corresponds to a function.

[0457] As an example, the first inference corresponds to an AI function.

[0458] As an example, the first inference is an AI / ML model.

[0459] As an example, the first reasoning is to obtain an AI model included in the AI ​​functions of the recommended configuration.

[0460] As an example, the output of the first inference is a waveform.

[0461] As an example, the output of the first inference is a maximum power backoff value.

[0462] As an example, the output of the first inference is a waveform and a maximum power backoff value.

[0463] As an example, the output of the first inference is processed to obtain at least one of either a waveform or a maximum power backoff value.

[0464] As an example, the recommended configuration indicated by the first report depends on the first inference, including that the recommended configuration indicated by the first report is related to the first inference.

[0465] As one embodiment, the recommended configuration indicated by the first report depends on a first inference, which includes: the first inference being used to determine the recommended configuration indicated by the first report.

[0466] As one embodiment, the recommended configuration indicated by the first report depends on a first inference, which includes: the first inference being used to generate the recommended configuration indicated by the first report.

[0467] As an example, the recommended configuration indicated by the first report depends on the first inference, including: at least one configuration or parameter included in the recommended configuration indicated by the first report depends on the first inference.

[0468] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the recommended configuration indicated by the first report is the output of the first inference.

[0469] As an example, the recommended configuration indicated by the first report depends on the first inference, including at least one configuration or parameter included in the recommended configuration indicated by the first report being the output of the first inference.

[0470] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the recommended configuration indicated by the first report is obtained by processing or quantizing the output of the first inference.

[0471] As an example, the recommended configuration indicated by the first report depends on the first inference, including at least one of the waveform based on AI inference in this application and the maximum power back-off value based on AI inference in this application depending on the first inference.

[0472] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the waveform of the AI-based inference in this application is the output of the first inference.

[0473] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the waveform based on AI inference in this application is obtained by processing or quantizing the output of the first inference.

[0474] As an example, the recommended configuration indicated by the first report depends on the first inference, which includes: the output of the first inference is a value, and the output of the first inference is mapped to the waveform of the AI-based inference in this application according to a predefined table.

[0475] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the output of the first AI inference is a first value; when the first value is greater than a first set value, the waveform based on AI inference in this application is a waveform; otherwise, the waveform based on AI inference is another waveform; the first set value is configured, predefined, or related to the UE implementation.

[0476] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the maximum power backoff value based on AI inference in this application depends on the first inference.

[0477] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the maximum power backoff value based on AI inference in this application is the output of the first inference.

[0478] As an example, the recommended configuration indicated by the first report depends on the first inference, including: the maximum power backoff value based on AI inference in the application is obtained by processing or quantizing the output of the first inference.

[0479] As an example, the recommended configuration indicated by the first report depends on a first inference including: the output of the first inference is a first value, which is mapped to the maximum power backoff value of the AI-based inference in this application according to a predefined table.

[0480] As one embodiment, the measurement of the first reference signal includes: the measurement of the first reference signal (RS) by the first node in this application.

[0481] As one embodiment, the measurement of the first reference signal includes: the measurement of the first node in this application on at least one RS resource corresponding to the first reference signal.

[0482] As one embodiment, the measurement of the first reference signal includes: the measurement of the first node in this application on a plurality of RS resources corresponding to the first reference signal.

[0483] As one embodiment, the measurement of the first reference signal includes: the measurement of the first node of this application on RS resources of the first reference signal over a period of time.

[0484] As one embodiment, the measurement of the first reference signal includes: measuring the first reference signal within a time window.

[0485] As one embodiment, the measurement of the first reference signal includes: measuring the first reference signal within SMTC (SS / PBCHBlock Measurement Time Configuration).

[0486] As one embodiment, the measurement of the first reference signal includes: the first node in this application performing a measurement on the reference signal resource corresponding to the first reference signal.

[0487] As an example, the measurement of the first reference signal includes: the first node in this application measures one or more of RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), RSSI (Received Signal Strength Indicator), and SNR (Signal To Noise Ratio) on the reference signal resource corresponding to the first reference signal.

[0488] As an example, the measurement process for the measurement of the first reference signal is implemented in a related manner.

[0489] As an example, the measurement of the first reference signal is based on a channel estimation algorithm.

[0490] As one embodiment, the measurement of the first reference signal is based on difference or filtering.

[0491] As one embodiment, the input to the first inference depending on the measurement of the first reference signal includes: the input to the first inference being related to the measurement of the first reference signal.

[0492] As one embodiment, the input to the first inference depends on a measurement of the first reference signal, which is used to determine the input to the first inference.

[0493] As one embodiment, the input to the first inference depends on a measurement of the first reference signal, which is used by the first node in the application to determine the input to the first inference.

[0494] As one embodiment, the input to the first inference depends on a measurement of the first reference signal, which includes the measurement of the first reference signal being used as the input to the first inference by the first node in the application.

[0495] As one embodiment, the input of the first inference depending on the measurement of the first reference signal includes: the input of the first inference depending on the result of the measurement of the first reference signal by the first node in this application.

[0496] As one embodiment, the input to the first inference, which depends on the measurement for the first reference signal, includes: the inference dataset for the first inference being derived from the measurement for the first reference signal.

[0497] As one embodiment, the input to the first inference, which depends on measurements of the first reference signal, includes: the input to the first inference depends on the L1 (layer 1) measurement results of the first node in this application for the first reference signal. As a supplementary embodiment, prediction based on the L1 measurement results can yield a recommended waveform or maximum power backoff value for the future based on the current beam, enabling the base station to obtain the optimal waveform for the current beam within this time period, thereby improving uplink transmission performance.

[0498] As one embodiment, the input to the first inference, which depends on measurements of the first reference signal, includes: the input to the first inference depends on the L3 (layer 3) measurement results of the first node in this application for the first reference signal. As a supplementary embodiment, prediction based on the L3 measurement results can determine whether the current user will be at the cell edge or cell center in the current cell for a future period, thereby recommending waveforms, improving uplink transmission performance, enhancing cell-level performance, and increasing system robustness.

[0499] As one embodiment, the input to the first inference that depends on the measurement of the first reference signal includes: the input to the first inference that depends on the RSRP (Reference Signal Received Power) measured by the first node of this application for the first reference signal.

[0500] As one embodiment, the input to the first inference that depends on the measurement for the first reference signal includes: the input to the first inference that depends on the L1-RSRP (Reference Signal Received Power) measured by the first node in this application for the first reference signal.

[0501] As one embodiment, the input to the first inference that depends on the measurement for the first reference signal includes: the input to the first inference that depends on the L3-RSRP (Reference Signal Received Power) measured by the first node in this application for the first reference signal.

[0502] As one embodiment, the input to the first inference that depends on the measurement of the first reference signal includes: the input to the first inference that depends on the RSRQ (Reference Signal Received Quality) measured by the first node of this application for the first reference signal.

[0503] As one embodiment, the input to the first inference, which depends on the measurement of the first reference signal, includes: the input to the first inference is the RSRP (Reference Signal Received Power) measured by the first node for the first reference signal.

[0504] As one embodiment, the input to the first inference, which depends on measurements of the first reference signal, includes: the input to the first inference being measurements of the first node of the first reference signal over a historical period.

[0505] As one embodiment, the input to the first inference, which depends on measurements of the first reference signal, includes: the input to the first inference being the measurement results of the first node over a past period of time of the first reference signal.

[0506] As one embodiment, the input to the first inference, which depends on measurements of the first reference signal, includes: the input to the first inference being the measurement results of the first node for the first reference signal over the current and past periods.

[0507] As an example, the input to the first inference, which depends on measurements for the first reference signal, includes: the input to the first inference being the RSRP measurement results of the first node for the first reference signal over the current and past periods.

[0508] As an example, the input to the first inference depends on measurements for the first reference signal, including: the input to the first inference is one or more of the following measurements of the first node on the reference signal resource corresponding to the first reference signal over the current and past periods: RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), RSSI (Received Signal Strength Indicator), and SNR (Signal To Noise Ratio).

[0509] As an example, the input to the first inference also includes the movement speed of the first node in this application.

[0510] As an example, the inputs to the first reasoning may also include other factors or data.

[0511] Example 7

[0512] Example 7 illustrates a schematic diagram illustrating the relationship between a first encoder, a first logical channel, and a recommended configuration according to an embodiment of this application, as shown in the attached diagram. Figure 7 As shown. In the appendix Figure 7 In this process, the first encoder is used to encode data on the first logical channel, and a recommended configuration is inferred based on the first logical channel.

[0513] In Example 7, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, and the first encoder is applied to the encoding of data on the first logical channel, the first encoder being based on AI.

[0514] As an example, statistical characteristics, contextual information, or semantic information of data on a logical channel can be used to recommend transmission waveforms or maximum power backoff values ​​to assist base station scheduling, reduce resource waste, improve spectrum efficiency, and enhance the reliability and robustness of data transmission.

[0515] As an example, the first logical channel is a channel between the MAC sublayer and the RLC sublayer.

[0516] As an example, the first logical channel is CCCH (Common Control Channel).

[0517] As one embodiment, the first logical channel is a DTCH (Dedicated Traffic Channel). As a supplementary embodiment, the UE predicts the recommended waveform or maximum power backoff value for a future time period based on its own service information, thereby improving system performance.

[0518] As an example, the first logical channel is DCCH (Dedicated Control Channel).

[0519] As an example, the first logical channel is mapped to the uplink transport channel.

[0520] As an example, the first logical channel is mapped to an uplink shared channel (UL-SCH).

[0521] As one embodiment, the first logical channel is mapped to an uplink shared channel (UL-SCH) and then transmitted on the uplink physical channel.

[0522] As an example, the first logical channel is mapped to the Uplink Shared Channel (UL-SCH) and then transmitted on the PUSCH.

[0523] As an example, the transmission mode of the first logical channel is TM (Transparent Mode).

[0524] As an example, the transmission mode of the first logical channel is UM (Unacknowledged Mode).

[0525] As an example, the transmission mode of the first logical channel is AM (Acknowledged Mode).

[0526] As an example, the first logical channel is identified by a LogicalChannelIdentity.

[0527] As an example, the first logical channel is identified by an RRC IE whose name includes LogicalChannelIdentity.

[0528] As one example, the data on the first logical channel comes from the NAS (Non-access stratum) or the core network.

[0529] As an example, the first logical channel is associated with a protocol layer.

[0530] As one example, the first logical channel is associated with multiple protocol layers.

[0531] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the recommended configuration indicated by the first report depends on the first logical channel.

[0532] As one embodiment, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the first logical channel is used by the first node to infer the recommended configuration indicated by the first report.

[0533] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the recommended configuration indicated by the first report is inferred by the first node using AI based on the first logical channel.

[0534] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the recommended configuration indicated by the first report is inferred by the first node using an AI model based on the first logical channel.

[0535] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the recommended configuration indicated by the first report is inferred by the first node when it applies the first encoder for encoding.

[0536] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the recommended configuration indicated by the first report is inferred by the first node based on the statistical characteristics of the data on the first logical channel.

[0537] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the first node infers the recommended configuration indicated by the first report based on the characteristics of the data on the first logical channel.

[0538] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the recommended configuration indicated by the first report is inferred by the first node based on the characteristics of the data on the first logical channel.

[0539] As a sub-implementation of the above embodiments, the characteristics of the data on the first logical channel are determined by the first node.

[0540] As a sub-example of the above embodiments, the characteristics of the data on the first logical channel are determined by the first node itself or based on the UE implementation.

[0541] As a sub-example of the above embodiments, the characteristics of the data on the first logical channel are determined by the first node through calculation or statistics.

[0542] As a sub-example of the above embodiments, the characteristics of the data on the first logical channel are determined by the first node through AI / ML.

[0543] As a sub-implementation of the above embodiments, the characteristics of the data on the first logical channel include the amount of data on the first logical channel.

[0544] As a sub-implementation of the above embodiments, the characteristics of the data on the first logical channel include statistical characteristics on the first logical channel.

[0545] As a sub-example of the above embodiments, the characteristics of the data on the first logical channel include the autocorrelation, cross-correlation, or stationarity of the data on the first logical channel.

[0546] As a sub-implementation of the above embodiments, the characteristics of the data on the first logical channel include the redundancy of the data on the first logical channel.

[0547] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, including: the recommended configuration indicated by the first report depends on the parameters associated with the first encoder.

[0548] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the encoding of data transmitted on the first logical channel by the first node using the first encoder.

[0549] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the first encoder being associated with the first logical channel.

[0550] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the first encoder performing source encoding on the data mapped to the first logical channel.

[0551] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the first encoder performing source compression on the data mapped to the first logical channel.

[0552] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the output of the first encoder being transmitted on the first logical channel.

[0553] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the input of the first encoder is a data block of the first protocol layer, and the output of the first encoder is transmitted on the first logical channel.

[0554] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the input of the first encoder is a data block of the first protocol layer, and the output of the first encoder is a PDU (Protocol Data Unit) of the first protocol layer mapped to the first logical channel.

[0555] As a sub-implementation of this embodiment, the first protocol layer is a layer above the MAC layer.

[0556] As a sub-implementation of this embodiment, the first protocol layer includes an RLC layer.

[0557] As a sub-implementation of this embodiment, the first protocol layer includes a PDCP layer.

[0558] As a sub-implementation of this embodiment, the first protocol layer includes an application layer.

[0559] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the input of the first encoder is the data transmitted on the first logical channel.

[0560] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the data transmitted on the first logical channel is the input of the first encoder, and the output of the first encoder is transmitted in the UL-SCH layer.

[0561] As one embodiment, the encoding of data on the first logical channel by the first encoder includes: the data transmitted on the first logical channel is the input of the first encoder, and the output of the first encoder is a PDU or SDU (Service Data Unit) of the MAC layer.

[0562] As an example, the first encoder is implemented in software.

[0563] As one example, the first encoder is implemented in hardware.

[0564] As an example, the first encoder is implemented based on the UE.

[0565] As an example, there is a first decoder on the network side, which is the inverse operation of the first encoder.

[0566] As an example, the first encoder is an applicable functionality, which is used for encoding.

[0567] As an example, the first encoder is an applicable function used for source coding.

[0568] As an example, the first encoder is an applicable function used for joint source-channel coding.

[0569] As an example, the first encoder is an applicable function used for AI encoding.

[0570] As an example, the first encoder is an applicable function, and the model corresponding to the applicable function is a two-sided mode.

[0571] As an example, the first encoder performs source coding.

[0572] As an example, the first encoder performs source compression.

[0573] As one example, the first encoder is at the application layer.

[0574] As an example, the first encoder is at the PDCP (Packet Data Convergence Protocol) layer.

[0575] As an example, the first encoder is in the RLC (Radio Link Control) sublayer.

[0576] As an example, the first encoder is at the MAC layer.

[0577] As one example, the input to the first encoder is a data block from a protocol layer above the MAC layer.

[0578] As an example, the first encoder is a two-sided mode.

[0579] As an example, the number of bits at the input of the first encoder is less than or equal to the number of bits at the output of the first encoder.

[0580] As one embodiment, the first encoder based on AI includes: the first encoder is based on an AI / ML model.

[0581] As one embodiment, the first encoder based on AI includes: the first encoder is based on at least one AI model.

[0582] As one embodiment, the first encoder based on AI includes: the first encoder is based on at least one of training, inference, or reinforcement learning.

[0583] As one embodiment, the first encoder based on AI includes: the first encoder is an AI-based source encoder.

[0584] As one embodiment, the first encoder based on AI includes: the first encoder is an AI-based source compression encoder.

[0585] As one embodiment, the first encoder based on AI includes: the first encoder is a two-sided mode user part (UE part).

[0586] As an example, the first node supports the first encoder.

[0587] As an example, the first node supports the functions associated with the first encoder.

[0588] As an example, the functionality associated with the first encoder is available on the first node.

[0589] Example 8

[0590] Example 8 illustrates a schematic diagram of the relationship between a first information block, a second information block, a first condition, and a first AI function according to an embodiment of this application, as shown in the attached diagram. Figure 8 As shown. In the appendix Figure 8 In the diagram, the left box indicates the first information block, the right box indicates the second information block, the arrows indicate the corresponding relationships, the first AI function corresponds to the first condition, and the first AI function is applicable under the first condition.

[0591] In Example 8, the first information block indicates a first condition; the second information block indicates that a first AI function is applicable; the first AI function is applicable under the first condition, and the recommended configuration indicated by the first report depends on the first AI function.

[0592] As an example, by indicating additional conditions on the network side, the applicability of the first AI function is determined, ensuring the consistency of model training and inference conditions on the UE side and guaranteeing the performance of AI inference.

[0593] As one embodiment, the first information block is transmitted via an air interface or a wireless interface.

[0594] As one embodiment, the first information block includes all or part of a higher-layer signaling or physical-layer signaling.

[0595] As one embodiment, the first information block includes all or part of an RRC (Radio Resource Control) layer signaling or a MAC (Medium Access Control) layer signaling.

[0596] As one embodiment, the first information block includes an RRC (Radio Resource Control) layer signaling. As a supplementary embodiment, RRC layer parameters or signaling are used to indicate additional network-side conditions. This has the advantage of saving signaling overhead and maintaining good compatibility.

[0597] As one embodiment, the first information block includes multiple sub-information blocks, each of which is an IE (Information Element) or a field in the RRC signaling to which the first information block belongs; one or more sub-information blocks included in the first information block indicate the first condition.

[0598] As one embodiment, the first information block includes an RRC reconfiguration message.

[0599] As one embodiment, the first information block includes some or all of the fields in the IE “RRCReconfiguration”.

[0600] As one example, the first information block includes some or all of the domains in IE's "OtherConfig".

[0601] As an example, the first information block is carried via PDSCH (Physical Downlink Shared Channel).

[0602] As one embodiment, the first information block is either cell-specific or user equipment-specific.

[0603] As one embodiment, the first information block is cell-specific. As a supplementary embodiment, the cell level indicates additional network-side conditions to reduce complexity.

[0604] As one embodiment, the first information block is UE-specific. As a supplementary embodiment, indicating additional network-side conditions at the user level can take into account the capabilities of the UE and is more flexible.

[0605] As an example, the first information block is transmitted on the downlink physical channel.

[0606] As an example, the first information block is transmitted on the PDSCH (Physical Downlink Control Channel).

[0607] As one example, the first information block indicates the configuration of the first AI function.

[0608] As an example, the first information block configures the first AI function.

[0609] As one example, the first information block indicates the inference configuration of the first AI function.

[0610] As an example, the first information block indicates the inference parameters of the first AI function.

[0611] As an example, the first information block indicates that the first node in this application provides the applicable functions of the first node.

[0612] As an example, the first information block indicates that the first node in this application allows the provision of the applicable functions of the first node.

[0613] As an example, the first information block and the second information block are used for LCM (life cycle management).

[0614] As an example, the first information block and the second information block are used for the LCM of the AI ​​model or ML model.

[0615] As an example, the first information block and the second information block are used for the LCM of the same one or more AI models or ML models.

[0616] As an example, the first information block and the second information block are used for the LCM of the first AI function.

[0617] As an example, the first condition is an additional condition on the network side.

[0618] As a sub-implementation of this embodiment, the additional conditions on the network side include at least one of the following: transmit beam, mapping of physical antenna to antenna port, configuration of reference signal, and tilt angle of physical antenna.

[0619] As an example, the first condition is associated with an identification (ID).

[0620] As an example, the first condition is identified by an index.

[0621] As one example, the first condition includes multiple sub-conditions.

[0622] As an example, the first condition applies to the first AI function.

[0623] As an example, the first condition is associated with the first AI function.

[0624] As an example, the first condition is the condition under which the first AI function is available.

[0625] As an example, the first condition is the condition that the AI ​​model associated with the first AI function is available.

[0626] As an example, the first condition is a condition associated with the availability of at least one AI model for the first AI function.

[0627] As an example, the first condition is an additional condition on the network side for the first AI function.

[0628] As an example, the first condition is the network-side configuration.

[0629] As an example, the first condition is applied to the first AI function.

[0630] As an example, the first condition is used by the first node in this application to determine whether the first AI function is available.

[0631] As one embodiment, the first information block indicating the first condition includes: the first information block explicitly or implicitly indicating the first condition.

[0632] As one embodiment, the first information block indicating the first condition includes: the first information block carrying the first condition.

[0633] As one embodiment, the first information block indicating the first condition includes: the first information block being determined by the first node in this application to be the first condition.

[0634] As one embodiment, the first information block indicating the first condition includes: the first information block indicating additional conditions on the network side corresponding to each of the multiple AI functions, wherein the first condition is an additional condition on the network side corresponding to the first AI function.

[0635] As one embodiment, the first information block indicating the first condition includes: the first information block indicating the identifier or index associated with the first condition.

[0636] As one embodiment, the first information block indicating the first condition includes: at least one domain or at least one IE included in the first information block indicating the first condition.

[0637] As an example, the first AI function is the AI ​​function reported by the first node in this application.

[0638] As an example, the first AI function is the supported functionality of the first node in this application.

[0639] As an example, the first AI function is an AI function supported by the first node in this application.

[0640] As an example, the first AI function corresponds to a "Functionality".

[0641] As an example, the first AI function is an AI / ML-based function.

[0642] As an example, the first AI function is a function accomplished through AI / ML.

[0643] As an example, the first AI function includes at least one AI model.

[0644] As an example, the first AI function includes an AI model.

[0645] As an example, the first AI function includes multiple AI models.

[0646] As an example, the first AI function includes at least one AI model that implements the first AI function.

[0647] As an example, the first AI function is implemented through at least one AI model.

[0648] As an example, the first AI function is a function implemented through AI model reasoning.

[0649] As an example, the first AI function is the function implemented based on AI reasoning as described in this application.

[0650] As one embodiment, the first AI function includes a reasoning configuration that implements the first AI function.

[0651] As an example, the first AI function is associated with at least one IE in the RRC layer.

[0652] As an example, the first AI function belongs to an AI function set, which includes at least one of BM (Beam Management) Case-1, BM Case-2, CSI prediction, CSI compression, positioning accuracy enhancement, and mobility.

[0653] As an example, the first AI function is associated with an identifier or index.

[0654] As an example, how to implement the first AI function is related to the UE implementation.

[0655] As an example, the AI ​​model included in the first AI function is related to the UE implementation.

[0656] As an example, the first AI function is configured for the AI-based reasoning described in this application.

[0657] As an example, "applicable" means: available.

[0658] As an example, "applicable" means "enabled".

[0659] As an example, "applicable" means "activated".

[0660] As an example, the first AI function is applicable to: at least one AI model included in the first AI function is applicable.

[0661] As an example, the first AI function is applicable to: at least one AI model that implements the first AI function is applicable.

[0662] As one embodiment, the first AI function is applicable including: the first AI function being enabled.

[0663] As an example, the first AI function is applicable to situations where the first node in this application is ready to apply the first AI function.

[0664] As an example, the first AI function is applicable to: the first node in this application is ready to apply at least one AI model included in the first AI function for inference.

[0665] As one embodiment, the first AI function is applicable to the first node in this application.

[0666] As one embodiment, the second information block is transmitted via an air interface or a wireless interface.

[0667] As one embodiment, the second information block includes all or part of a higher-layer signaling or physical-layer signaling.

[0668] As one embodiment, the second information block includes all or part of an RRC (Radio Resource Control) layer signaling or a MAC (Medium Access Control) layer signaling.

[0669] As one embodiment, the second information block includes all or part of the IE (Information Element) in an RRC (Radio Resource Control) message. As a supplementary embodiment, using RRC messages or signaling to report available functions saves signaling overhead.

[0670] As one embodiment, the second information block includes UAI (UEAssistance Information).

[0671] As one embodiment, the second information block includes at least one IE or at least one domain in the IE "UL-DCCH-Message".

[0672] As one embodiment, the second information block includes at least one IE or at least one domain in the IE "UEAssistanceInformation".

[0673] As one embodiment, the second information block includes at least one IE or at least one domain in IE "RRCReconfigurationComplete".

[0674] As an example, the second information block is mapped onto a logical channel (DCCH, Dedicated Control Channel).

[0675] As one embodiment, the second information block is UE-specific.

[0676] As one example, the second information block is transmitted on the uplink physical channel.

[0677] As one embodiment, the second information block is carried by an uplink physical signal.

[0678] As an example, the second information block is transmitted on the PUSCH.

[0679] As one embodiment, the second information block is a MAC layer message. As a supplementary embodiment, MAC layer messages are used to report availability, reducing latency.

[0680] As an example, the second information block is a MAC (medium access control) CE (control element).

[0681] As an example, the second information block is transmitted in a MAC PDU (Protocol Data Unit).

[0682] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block indicating that the first AI function is available.

[0683] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block explicitly indicating that the first AI function is applicable.

[0684] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block implicitly indicating that the first AI function is applicable.

[0685] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block indicating the identifier or index corresponding to the first AI function.

[0686] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second report indicating the applicability of multiple AI functions, wherein the first AI function is one of the multiple AI functions.

[0687] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block carrying multiple applicable AI functions, wherein the first AI function is one of the multiple applicable AI functions.

[0688] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block indicating a list of available AI functions of the first node in this application, wherein the first AI function belongs to the list of available AI functions of the first node.

[0689] As one embodiment, the second information block indicating the applicability of the first AI function includes: at least one sub-information block included in the second information block indicating the applicability of the first AI function.

[0690] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block indicating the set of AI functions applicable to the first node in this application, wherein the first AI function belongs to the set of AI functions applicable to the first node.

[0691] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block indicating that at least one AI model included in the first AI function is available.

[0692] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block indicating that at least one AI model associated with the first AI function is available.

[0693] As one embodiment, the second information block indicating the applicability of the first AI function includes: the second information block indicating that the UE-side model included in the first AI function is available.

[0694] As one embodiment, the second information block indicating the applicability of the first AI function includes: at least one domain or at least one IE included in the second information block indicating the applicability of the first AI function.

[0695] As one embodiment, the applicability of the first AI function under the first condition includes: the applicability of the first AI function depends on the first condition.

[0696] As an example, the application of the first AI function under the first condition includes: the conditions under which the first AI function is applicable include the first condition.

[0697] As an example, the application of the first AI function under the first condition includes: the application conditions of the first AI function include multiple conditions, and the first condition is one of them.

[0698] As an example, the first AI function being applicable under the first condition includes: the first condition being a condition under which the first AI function is applicable.

[0699] As an example, the application of the first AI function under the first condition includes: when the first condition is met, the first AI function is applied.

[0700] As one embodiment, the application of the first AI function under the first condition includes: the first AI function is applied only when the first condition is met.

[0701] As one embodiment, the application of the first AI function under the first condition includes: the first AI function may only be applied when the first condition is met.

[0702] As one embodiment, the application of the first AI function under the first condition includes: when the first condition is not met, the first AI function is not applicable.

[0703] As one embodiment, the application of the first AI function under the first condition includes: the first condition being a necessary and sufficient condition for the application of the first AI function.

[0704] As one embodiment, the application of the first AI function under the first condition includes: the first condition being a necessary but not sufficient condition for the application of the first AI function.

[0705] As one embodiment, the first AI function being applicable under the first condition includes: the first condition being a condition applicable to the first AI function.

[0706] As one embodiment, the application of the first AI function under the first condition includes: the first condition being an additional network-side condition for the first AI function.

[0707] As an example, the first AI function is applicable under the first condition as follows: the first condition corresponds to a first associated identifier, and the identifier corresponding to at least one AI model included in the first AI function is the same as the first associated identifier.

[0708] As an example, the first AI function being applicable under the first condition includes: the first AI function being applicable when the first node in this application complies with the first condition.

[0709] As an example, the conditions under which the first AI function applies also include the conditions of the first node itself in this application.

[0710] As an example, the conditions under which the first AI function applies also include additional user-side conditions.

[0711] As a sub-implementation of the above embodiments, the user-side additional conditions are conditions known to the user internally.

[0712] As a sub-implementation of the above embodiments, the additional conditions on the user side depend on the user's implementation.

[0713] As a sub-implementation of the above embodiments, the additional conditions on the user side depend on the user's state.

[0714] As a sub-implementation of the above embodiments, the additional conditions on the user side depend on the user's capabilities.

[0715] As a sub-example of the above embodiments, the additional conditions on the user side include one or more of the following: user hardware configuration or capabilities, user battery level, user software configuration, user antenna configuration, and user movement speed.

[0716] As an example, the applicability of the first AI function also includes the availability of the user device model.

[0717] As an example, the first AI function is applicable based on the first condition, additional UE-side conditions, and the availability of the user equipment model.

[0718] As an example, the first node in this application confirms the applicability of the first AI function and reports it after receiving the first condition and verifying the user-side additional conditions and the availability of the user equipment model.

[0719] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the recommended configuration indicated by the first report is related to the first AI function.

[0720] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the recommended configuration indicated by the first report is generated based on the first AI function.

[0721] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the recommended configuration indicated by the first report is the output of the first AI function.

[0722] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the recommended configuration indicated by the first report is the output of at least one AI model included in the first AI function.

[0723] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the recommended configuration indicated by the first report is the inference result of at least one AI model included in the first AI function.

[0724] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the recommended configuration indicated by the first report is obtained by processing or quantizing the output of at least one AI model included in the first AI function.

[0725] As an example, the recommended configuration indicated by the first report depends on the first AI function, including at least one of the waveform based on AI inference in this application and the maximum power backoff value based on AI inference in this application.

[0726] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the waveform based on AI inference in this application depends on the first AI function.

[0727] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the waveform based on AI inference in this application is the output of the first AI function.

[0728] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the waveform based on AI inference in this application is the inference result of at least one AI model included in the first AI function.

[0729] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the waveform based on AI inference in this application is obtained by processing or quantizing the output of at least one AI model included in the first AI function.

[0730] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the output of at least one AI model included in the first AI function is a first value, which is mapped to the waveform based on AI inference in this application according to a predefined table.

[0731] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the output of at least one AI model included in the first AI function is a first value; when the first value is greater than a first set value, the waveform based on AI inference in this application is a waveform; otherwise, the waveform based on AI inference is another waveform; the first set value is configured, predefined, or related to the UE implementation.

[0732] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the output of at least one AI model included in the first AI function is the waveform based on AI inference described in this application.

[0733] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the maximum power backoff value based on AI inference in this application depends on the first AI function.

[0734] As an example, the recommended configuration indicated by the first report depends on the first AI function, including: the maximum power backoff value based on AI inference in this application is the output of the first AI function.

[0735] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the maximum power backoff value based on AI inference in this application is the inference result of at least one AI model included in the first AI function.

[0736] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the maximum power backoff value based on AI inference in this application is obtained by processing or quantizing the output of at least one AI model included in the first AI function.

[0737] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the output of at least one AI model included in the first AI function is a first value, which is mapped to the maximum power backoff value based on AI inference in this application according to a predefined table.

[0738] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the output of at least one AI model included in the first AI function is a first value, and the first value is further processed, quantized, or transformed to obtain the maximum power backoff value based on AI inference in this application.

[0739] As an example, the recommended configuration indicated by the first report depends on the first AI function including: the output of at least one AI model included in the first AI function is the maximum power backoff value based on AI inference in this application.

[0740] Example 9

[0741] Example 9 illustrates a schematic diagram of the relationship between a first time window and a second report according to an embodiment of this application, as shown in the attached diagram. Figure 9 As shown. In the appendix Figure 9 In the diagram, the rectangle filled with diagonal lines represents the reference signal, the horizontal axis represents time, the second report is later than the first time window, and the triggering of the second report depends on the measurement within the first time window.

[0742] In Example 9, the second report indicates that the second AI function is not applicable, and the recommended configuration indicated by the first report depends on the second AI function; the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[0743] As an example, the availability of the second AI function is monitored based on the actual measurement results, and the base station is notified in a timely manner that the AI ​​function is unavailable when the performance monitoring does not meet the requirements. This prevents inaccurate recommendations from affecting performance when the AI ​​function is unavailable, and timely reporting is beneficial for retraining the AI ​​model or reconfiguring it, and ensures that the base station and the user have the same understanding of the availability of the AI ​​function.

[0744] In one embodiment, the sender of the second report is the first node.

[0745] As an example, the second report is a higher-layer report.

[0746] As an example, the second report is generated at a higher level.

[0747] As an example, the second report is a report from the RRC layer.

[0748] As an example, the second report is a report generated at the RRC layer.

[0749] As an example, the second report is UAI (UEAssistance Information).

[0750] As an example, the second report is an IE or a domain in UAI.

[0751] As an example, the second report includes at least one IE or at least one domain of IE "UEAssistanceInformation".

[0752] As an example, the second report is a report from the MAC (Medium Access Control) layer.

[0753] As an example, the second report is a report generated at the MAC layer.

[0754] As an example, the second report is a MAC (medium access control) CE (control element).

[0755] As an example, the second report is transmitted in a MAC PDU (Protocol Data Unit).

[0756] As an example, the second report is transmitted on UL-SCH (Uplink Shared Channel).

[0757] As one embodiment, the second report is carried by an uplink signal from the physical layer.

[0758] As an example, the second report is carried by PUSCH.

[0759] As one embodiment, the second AI function is the same AI function as the first AI function in this application. As a supplementary embodiment, this approach offers the advantage of simple design.

[0760] As one embodiment, the second AI function and the first AI function in this application are two different AI functions. As a supplementary embodiment, this approach offers the advantage of greater flexibility.

[0761] As an example, the second AI function is the AI ​​function reported by the first node in this application.

[0762] As an example, the second AI function is a supported functionality supported by the first node in this application.

[0763] As an example, the second AI function is an AI function supported by the first node in this application.

[0764] As an example, the second AI function corresponds to a "Functionality".

[0765] As an example, the second AI function is an AI / ML-based function.

[0766] As an example, the second AI function is a function accomplished through AI / ML.

[0767] As an example, the second AI function includes at least one AI model.

[0768] As an example, the second AI function includes an AI model.

[0769] As one example, the second AI function includes multiple AI models.

[0770] As one example, the second AI function includes at least one AI model that implements the first AI function.

[0771] As an example, the second AI function is implemented through at least one AI model.

[0772] As an example, the second AI function is a function implemented through AI model reasoning.

[0773] As an example, the second AI function is the function implemented based on AI reasoning as described in this application.

[0774] As one embodiment, the second AI function includes a reasoning configuration for implementing the second AI function.

[0775] As an example, the second AI function is associated with at least one IE in the RRC layer.

[0776] As an example, the second AI function belongs to an AI function set, which includes at least one of BM (Beam Management) Case-1, BM Case-2, CSI prediction, CSI compression, positioning accuracy enhancement, and mobility.

[0777] As one example, the second AI function is associated with an identifier or index.

[0778] As an example, how to implement the second AI function is related to the UE implementation.

[0779] As an example, the AI ​​model included in the second AI function is related to the UE implementation.

[0780] As an example, the second AI function is configured for the AI-based inference described in this application.

[0781] As one example, the second AI function not being applicable includes: the second AI function changing from applicable to non-applicable.

[0782] As an example, the second AI function not being applicable includes: at least one AI model included in the second AI function is not applicable.

[0783] As an example, the second AI function not being applicable includes: the AI ​​model corresponding to the additional conditions on the network side included in the second AI function is not applicable.

[0784] As an example, the second AI function not being applicable includes: the AI ​​model for the associated ID indicated by the network side included in the second AI function is not applicable.

[0785] As an example, the second AI function not being applicable includes: all AI models included in the second AI function are not applicable.

[0786] As one example, the second AI function not being applicable includes: the second AI function being disabled.

[0787] As one example, the second AI function not being applicable includes: the second AI function is temporarily not applicable.

[0788] As an example, the second AI function not being applicable includes: the second AI function not being applicable during the LCM process.

[0789] As one example, the second AI function not being applicable includes: the performance of the second AI function not meeting the requirements.

[0790] As an example, the inapplicability of the second AI function includes: performance monitoring of the second AI function does not meet the requirements.

[0791] As an example, the second AI function not being applicable includes: the second AI function requiring retraining.

[0792] As one example, the second AI function not being applicable includes: the second AI function requiring reconfiguration.

[0793] As one embodiment, the second AI function not being applicable includes: the second AI function being disabled by the first node in this application.

[0794] As one embodiment, the second AI function not being applicable includes: the second AI function not being applied by the first node in this application.

[0795] As an example, the second AI function not being applicable includes: the second AI function being deactivated by the first node in this application.

[0796] As one embodiment, the second AI function not being applicable includes: the second AI function is not applicable or is temporarily not applicable to the first node in this application.

[0797] As one example, the second report indicating that the second AI function is not applicable includes: the second report indicating that the second AI function is unavailable.

[0798] As one embodiment, the second report indicating that the second AI function is not applicable includes: the second report explicitly indicating that the second AI function is non-applicable.

[0799] As one embodiment, the second report indicating that the second AI function is not applicable includes: the second report implicitly indicating that the second AI function is non-applicable.

[0800] As one embodiment, the second report indicating that the second AI function is not applicable includes: the second report indicating the identifier or index corresponding to the second AI function.

[0801] As one embodiment, the second report indicating that the second AI function is not applicable includes: the second report indicating that multiple AI functions are not applicable, and the second AI function is one of the multiple AI functions.

[0802] As one embodiment, the second report indicating that the second AI function is not applicable includes: the second report indicating that the second AI function changes from applicable to non-applicable.

[0803] As one embodiment, the second report indicating that the second AI function is not applicable includes: the second report indicating that multiple AI functions change from applicable to inapplicable, and the second AI function belongs to the multiple AI functions.

[0804] As one embodiment, the second report indicating that the second AI function is not applicable includes: at least one domain or at least one IE included in the second report indicating that the second AI function is not applicable.

[0805] As one embodiment, the second report indicating that the second AI function is not applicable includes: at least one bit included in the second report indicating that the second AI function is not applicable.

[0806] As one example, the second report indicating that the second AI function is not applicable includes: the IE "UEAssistanceInformation" included in the second report indicating that the second AI function is not applicable.

[0807] As one example, the second report indicating that the second AI function is not applicable includes: the second report indicating that all AI models included in the second AI function are not applicable.

[0808] As one example, the second report indicating that the second AI function is not applicable includes: the second report indicating that the model of the additional conditions associated with the network side included in the second AI function is not applicable.

[0809] As one embodiment, the second report indicating that the second AI function is not applicable includes: at least one field or at least one bit included in the second report indicating that the second AI function is not applicable.

[0810] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the recommended configuration indicated by the first report is related to the second AI function.

[0811] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the recommended configuration indicated by the first report is generated based on the second AI function.

[0812] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the recommended configuration indicated by the first report is the output of the second AI function.

[0813] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the recommended configuration indicated by the first report is the output of at least one AI model included in the second AI function.

[0814] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the recommended configuration indicated by the first report is the inference result of at least one AI model included in the second AI function.

[0815] As an example, the recommended configuration indicated by the first report depends on the second AI function, which includes: the recommended configuration indicated by the first report is obtained by processing or quantizing the output of at least one AI model included in the second AI function.

[0816] As an example, the recommended configuration indicated by the first report depends on the second AI function, including at least one of the waveform based on AI inference in this application and the maximum power backoff value based on AI inference in this application.

[0817] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the waveform based on AI inference in this application depends on the second AI function.

[0818] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the waveform based on AI inference in this application is the output of the second AI function.

[0819] As an example, the recommended configuration indicated by the first report depends on the second AI function including: the waveform based on AI inference in this application is the inference result of at least one AI model included in the second AI function.

[0820] As an example, the recommended configuration indicated by the first report depends on the second AI function, which includes: the waveform based on AI inference in this application is obtained by processing or quantizing the output of at least one AI model included in the second AI function.

[0821] As an example, the recommended configuration indicated by the first report depends on the second AI function including: the output of at least one AI model included in the second AI function is a first value, which is mapped to the waveform of the AI-based inference in this application according to a predefined table.

[0822] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the output of at least one AI model included in the second AI function is a first value; when the first value is greater than a first set value, the waveform based on AI inference in this application is a waveform; otherwise, the waveform based on AI inference is another waveform; the first set value is configured, predefined, or related to the UE implementation.

[0823] As an example, the recommended configuration indicated by the first report depends on the second AI function including: the output of at least one AI model included in the second AI function is the waveform based on AI inference described in this application.

[0824] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the maximum power backoff value based on AI inference in this application depends on the second AI function.

[0825] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the maximum power backoff value based on AI inference in this application is the output of the second AI function.

[0826] As an example, the recommended configuration indicated by the first report depends on the second AI function including: the maximum power backoff value based on AI inference in this application is the inference result of at least one AI model included in the second AI function.

[0827] As an example, the recommended configuration indicated by the first report depends on the second AI function, including: the maximum power backoff value based on AI inference in this application is obtained by processing or quantizing the output of at least one AI model included in the second AI function.

[0828] As an example, the recommended configuration indicated by the first report depends on the second AI function including: the output of at least one AI model included in the second AI function is a first value, which is mapped to the maximum power backoff value based on AI inference in this application according to a predefined table.

[0829] As an example, the recommended configuration indicated by the first report depends on the second AI function, which includes: the output of at least one AI model included in the second AI function is a first value, which is then processed, quantized, or transformed in a predefined manner to obtain the maximum power backoff value based on AI inference in this application.

[0830] As an example, the recommended configuration indicated by the first report depends on the second AI function including: the output of at least one AI model included in the second AI function is the maximum power backoff value based on AI inference in this application.

[0831] As an example, the measurement within the first time window includes: the measurement of the first node in this application within the first time window.

[0832] As one embodiment, the measurement within the first time window includes: the measurement of the reference signal by the first node in this application within the first time window.

[0833] As an example, the measurement within the first time window includes: the measurement of the downlink reference signal by the first node in this application within the first time window.

[0834] As one embodiment, the measurement within the first time window includes: the measurement of downlink DMRS by the first node in this application within the first time window.

[0835] As one embodiment, the measurement within the first time window includes: the measurement of SSB by the first node in this application within the first time window.

[0836] As one embodiment, the measurement within the first time window includes: the measurement of CSI-RS by the first node in this application within the first time window.

[0837] As one embodiment, the measurement within the first time window includes: the measurement of PRS by the first node in this application within the first time window.

[0838] As one embodiment, the measurement within the first time window includes: the first node in this application performing measurements on the RS resources associated with the reference signal within the first time window.

[0839] As one embodiment, the measurement within the first time window includes: the first node in this application performing a measurement on the reference signal resource corresponding to the reference signal.

[0840] As an example, the measurement of the first reference signal includes: the first node in this application measures one or more of RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), RSSI (Received Signal Strength Indicator), and SNR (Signal To Noise Ratio) on the reference signal resource corresponding to the reference signal.

[0841] As one embodiment, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including: the triggering event of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[0842] As one embodiment, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including whether to send the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[0843] As one embodiment, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including: the relationship between the recommended configuration and the measurement within the first time window is determined by the first node in this application to determine whether to send the second report.

[0844] As one example, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including: the triggering of the second report depends on the relationship between the recommended configuration and the L1 measurement result within the first time window.

[0845] As one example, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including: the triggering of the second report depends on the relationship between the recommended configuration and the L1 RSRP measurement results within the first time window.

[0846] As one example, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including: the triggering of the second report depends on the relationship between the recommended configuration and the L3 measurement results within the first time window.

[0847] As one example, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including: the triggering of the second report depends on the relationship between the recommended configuration and the L3 RSRP measurement results within the first time window.

[0848] As one embodiment, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including whether the result of the measurement within the first time window is within a target interval, the target interval depending on the recommended configuration.

[0849] As one embodiment, the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window, including: the triggering of the second report depends on whether the RSRP obtained from the measurement within the first time window is within a target interval, the target interval depending on the recommended configuration.

[0850] As a sub-example of the above embodiments, the target range is the value range corresponding to the recommended configuration.

[0851] As a sub-example of the above embodiments, the target interval is an interval corresponding to the recommended configuration based on a predefined table or mapping relationship.

[0852] As a sub-example of the above embodiments, when the recommended configuration includes the AI-inference-based waveform in this application, the AI-inference-based waveform corresponds to the target interval.

[0853] As a sub-example of the above embodiments, when the recommended configuration includes the AI-based inference waveform in this application, the target range is different when the inference-based waveform is different.

[0854] As a sub-implementation of the above embodiments, when the recommended configuration includes the maximum power backoff value based on AI inference in this application, the maximum power backoff value based on AI inference corresponds to different target ranges according to a predefined table or mapping rule.

[0855] As a sub-implementation of the above embodiment, the second report is triggered when the measurement result or RSRP obtained within the first time window is outside the target interval.

[0856] As a sub-implementation of the above embodiment, when the measurement result or RSRP within the first time window is within the target interval, the second report is not sent.

[0857] As one example, "the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window" includes: the triggering of the second report depends on whether the waveform based on AI inference is equal to a first waveform, where the first waveform is a waveform corresponding to or mapped from the measurement result obtained within the first time window.

[0858] As one embodiment, "the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window" includes: the second report is triggered when the waveform based on AI inference is different from the first waveform; the first waveform is a waveform corresponding to or mapped to the measurement result obtained within the first time window.

[0859] As an example, "the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window" includes: the triggering of the second report depends on whether the maximum power backoff value based on AI inference differs from the target maximum power backoff value by more than a certain threshold, wherein the target maximum power backoff value is the maximum power backoff value corresponding to the measurement result obtained within the first time window, and the certain threshold is predefined, configured, or dependent on the UE implementation.

[0860] As an example, "the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window" includes: triggering the second report when the difference between the maximum power backoff value based on AI inference and the target maximum power backoff value is greater than a certain threshold; the target maximum power backoff value is the maximum power backoff value corresponding to the measurement result obtained within the first time window, and the certain threshold is predefined, configured, or dependent on the UE implementation.

[0861] Example 10

[0862] Example 10 illustrates a schematic diagram of the triggering conditions for a first report according to an embodiment of this application, as shown in the attached diagram. Figure 10 As shown. In the appendix Figure 10 In case A, the vertical axis represents power, and the rectangle filled with diagonal lines represents the power value. The difference between the maximum power backoff value indicated by the previous report and the maximum power backoff value based on AI inference is greater than a first threshold, triggering the first report. In case B, the arrows indicate the indication relationship. The previous report indicates waveform A, while the AI ​​inference indicates waveform B, triggering the first report.

[0863] In Example 10, the triggering condition for the first report includes at least one of the following: the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold, the first threshold being configured or predefined; the waveform based on AI inference is different from the waveform indicated in the previous report.

[0864] As an example, when the predicted waveform is different from the previously predicted and reported waveform, or when the difference between the predicted maximum power backoff value and the previously predicted and reported maximum power backoff value is greater than a certain threshold, the first report is triggered, thus avoiding frequent reporting of the predicted waveform or maximum power backoff value and saving signaling overhead.

[0865] As an example, the maximum power backoff value indicated in the previous report is also based on AI inference.

[0866] As an example, the maximum power backoff value indicated in the previous report is based on the previous inference by the AI.

[0867] As an example, the maximum power backoff value indicated in the previous report is based on prior AI reasoning.

[0868] As an example, the waveform indicated in the previous report was also based on AI inference.

[0869] As an example, the waveform indicated by the previous report is based on the previous inference by AI.

[0870] As an example, the waveform indicated in the previous report is based on prior AI reasoning.

[0871] As an example, the previous report corresponds to "the last report".

[0872] As an example, the previous report is the latest report that precedes the first report.

[0873] As an example, the previous report is the latest report of the same type that precedes the first report.

[0874] As an example, the previous report is a report of the same type preceding the first report.

[0875] As an example, the triggering condition for the first report includes the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report being greater than a first threshold.

[0876] As an example, a sufficient condition for triggering the first report is that the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold.

[0877] As an example, the necessary condition for triggering the first report is that the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold.

[0878] As an example, the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report being greater than a first threshold includes: the difference between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report being greater than the first threshold.

[0879] As an example, the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report being greater than a first threshold includes: the absolute value of the difference between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report being greater than the first threshold.

[0880] As an example, the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report being greater than a first threshold includes: the maximum power backoff value based on AI inference is X, the maximum power backoff value indicated in the previous report is Y, |XY|>Z, Z is the first threshold, and || represents the absolute value.

[0881] As an example, the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report being greater than a first threshold includes: the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report are not in the same interval, the maximum power backoff value is divided into multiple intervals, and the interval is one of the multiple intervals.

[0882] As an example, the triggering condition for the first report includes that the waveform based on AI inference is different from the waveform indicated in the previous report.

[0883] As an example, the fact that the waveform based on AI inference is different from the waveform indicated in the previous report is a sufficient condition for triggering the first report.

[0884] As an example, the fact that the waveform based on AI inference is different from the waveform indicated in the previous report is a necessary condition for triggering the first report.

[0885] As an example, the difference between the waveform based on AI inference and the waveform indicated in the previous report includes: the waveform based on AI inference and the waveform indicated in the previous report are two different waveforms.

[0886] As an example, the difference between the waveform based on AI inference and the waveform indicated in the previous report includes: the waveform based on AI inference is CP-OFDM, while the waveform indicated in the previous report is DFT-s-OFDM.

[0887] As an example, the difference between the waveform based on AI inference and the waveform indicated in the previous report includes: the waveform based on AI inference is DFT-S-OFDM, while the waveform indicated in the previous report is CP-OFDM.

[0888] As an example, the difference between the waveform based on AI inference and the waveform indicated in the previous report includes: the transform precoder of the waveform based on AI inference is enabled, while the transform precoder of the waveform indicated in the previous report is disabled.

[0889] As an example, the difference between the waveform based on AI inference and the waveform indicated in the previous report includes: the transformation precoding of the waveform based on AI inference is not enabled, while the transformation precoding of the waveform indicated in the previous report is enabled.

[0890] As an example, the triggering conditions for the first report include the change in the maximum power backoff value based on AI inference from the maximum power backoff value indicated in the previous report being greater than a first threshold and the waveform based on AI inference being different from the waveform indicated in the previous report.

[0891] As an example, the first report is triggered when at least one of the following conditions is met: the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold, or the waveform based on AI inference is different from the waveform indicated in the previous report.

[0892] As an example, the triggering conditions for the first report include multiple conditions. The first report is triggered when any one of the conditions is met. The two conditions are that the change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold and that the waveform based on AI inference is different from the waveform indicated in the previous report.

[0893] As an example, the first threshold is greater than 0.

[0894] As an example, the first threshold is greater than or equal to 0.

[0895] As an example, the first threshold is a non-negative integer.

[0896] As an example, the first threshold can be a decimal.

[0897] As an example, the unit of the first threshold is dBm.

[0898] As an example, the unit of the first threshold is dB.

[0899] As an example, the unit of the first threshold is watt or milliwatt.

[0900] As one embodiment, the first threshold being configured or predefined includes: the first threshold being configured. As a supplementary embodiment, the network side configures the first threshold, thereby affecting the reporting frequency, providing greater flexibility.

[0901] As one embodiment, the first threshold being configured or predefined includes: the first threshold being configured by high-level parameters.

[0902] As one embodiment, the first threshold being configured or predefined includes: the first threshold being configured on the network side.

[0903] As one embodiment, the first threshold being configured or predefined includes: the first threshold being configured by the signaling or domain of the RRC layer.

[0904] As one embodiment, the first threshold is configured or predefined, including: the first threshold is indicated by signaling from the MAC layer.

[0905] As one embodiment, the first threshold being configured or predefined includes: the first threshold being configured by the higher-layer signaling associated with the reporting of the first report.

[0906] As one embodiment, the first threshold being configured or predefined includes: the first threshold being predefined. As a supplementary embodiment, the first threshold is a predefined value; the advantage of doing so is reduced standard complexity and saved signaling overhead.

[0907] As one embodiment, the first threshold being configured or predefined includes: the first threshold being hard-coded in the standard.

[0908] As one embodiment, the first timer is configured or predefined, including that the first threshold is fixed.

[0909] Example 11

[0910] Example 11 illustrates a schematic diagram of the relationship between a first timer and a first report according to an embodiment of this application, as shown in the attached diagram. Figure 11 As shown. In the appendix Figure 11 In the diagram, the horizontal axis represents time, and the rectangle filled with diagonal lines represents the first report. The first timer starts when the current report is sent, and the first report is triggered when the first timer expires.

[0911] In Example 11, the first report is triggered when the first timer expires, and the first timer is configured or predefined.

[0912] As an example, periodically reporting the predicted waveform or maximum power backoff value ensures that a prediction report will be made at least once every certain period of time, thus improving the robustness of the system.

[0913] As an example, the first node starts the first timer when the previous report of the first report is sent.

[0914] As an example, when the previous report of the first report is sent, the first timer is started or restarted.

[0915] As an example, when the previous report of the first report is generated, the first node starts the first timer.

[0916] As an example, when the previous report of the first report is generated, the first timer is started or restarted.

[0917] As an example, when the previous report of the first report is submitted to the lower protocol layer, the first node starts the first timer.

[0918] As an example, when the previous report of the first report is submitted to the lower protocol layer, the first timer is started or restarted.

[0919] As an example, the first timer starts timing after a time offset has elapsed since the previous report of the first report was sent. The time offset is configured or predefined.

[0920] As an example, the unit of the first timer is seconds or milliseconds.

[0921] As one embodiment, the unit of the first timer is a frame, a subframe, or a slot.

[0922] As an example, the first timer is incremented.

[0923] As an example, the first timer is decremented.

[0924] As one example, the first timer is a counter.

[0925] As an example, the first timer is a periodic timer.

[0926] As an example, the first timer is a MAC layer timer.

[0927] As an example, the first timer is a physical layer timer.

[0928] As an example, the first timer is a timer for the periodic reporting of the first report.

[0929] As an example, the first timer is configured by the IE "RCR-config".

[0930] As an example, the first timer is configured in IE "PHR-Config".

[0931] As an example, the first timer is configured in the domain "phr-PeriodicTimer".

[0932] As one example, triggering the first report when the first timer expires includes: the first report being triggered when the first timer expires.

[0933] As one example, triggering the first report when the first timer expires includes: the sending of the first report depends on the expiration of the first timer.

[0934] As an example, triggering the first report when the first timer expires includes: the expiration of the first timer being a condition for triggering the first report.

[0935] As an example, triggering the first report when the first timer expires includes: triggering the first report has multiple conditions, and the expiration of the first timer is one of the multiple conditions.

[0936] As one embodiment, triggering the first report when the first timer expires includes: the expiration of the first timer being a sufficient condition for triggering the first report.

[0937] As one example, triggering the first report when the first timer expires includes: the expiration of the first timer is a necessary condition for triggering the first report.

[0938] As one embodiment, the first timer being configured or predefined includes: the first timer being configured. As a supplementary embodiment, configuring the first timer on the network side provides greater flexibility.

[0939] As one embodiment, the first timer is configured or predefined, including: the first timer is configured by higher-level parameters.

[0940] As one embodiment, the first timer being configured or predefined includes: the first timer being configured on the network side.

[0941] As one embodiment, the first timer is configured or predefined, including: the first timer is configured by the signaling or domain of the RRC layer.

[0942] As one embodiment, the first timer is configured or predefined, including: the first timer is configured by the higher-layer signaling associated with the reporting of the first report.

[0943] As one embodiment, the first timer is configured or predefined, including: the first timer is predefined. As a supplementary embodiment, the first timer has a predefined time length, which has the advantage of reducing standard complexity and saving signaling overhead.

[0944] As one embodiment, the first timer is configured or predefined, including: the first timer is hard-coded in the standard.

[0945] As one embodiment, the first timer being configured or predefined includes: the value of the first timer or the duration of the first timer being predefined.

[0946] As one embodiment, the first timer is configured or predefined, including: the value of the first timer or the duration of the first timer is fixed.

[0947] Example 12

[0948] Example 12 illustrates a schematic diagram of RAN domain AI / ML function deployment according to an embodiment of this application, as shown in the attached diagram. Figure 12 As shown. In the appendix Figure 12 In this context, gNB can be replaced with network equipment such as eNB or 6G base stations.

[0949] In Example 12, the management of the ML inference functions of multiple base stations is completed by the RAN domain management function 1202, that is, data interaction with the RAN domain MnS (Management Service) consumer / cross-domain management 1201 (as shown in the attached figure). Figure 12 (As shown by the dashed arrow in the diagram). The RAN domain ML training function 1203 is located in the RAN domain management function 1202; while the ML inference function is located in the base station, that is, the AI / ML inference function 1204 is located in gNB 1205, the AI / ML inference function 1206 is located in gNB 1207, and so on.

[0950] AI / ML related functions include ML training (also known as AI training or AI / ML training), ML testing, and ML inference (also known as AI inference or AI / ML inference), etc. ML training, ML testing, and ML inference functions can be deployed independently or co-located. Deployment of AI / ML related functions can be implemented through software, such as downloading and / or running executable files; or it can be implemented through a combination of software and hardware, such as accelerating specific computing units through hardware to improve computing speed or save power.

[0951] ML training functions can be deployed in a cross-domain management system or a domain-specific management system; the domain-specific management system is used to manage the RAN domain or the CN (Core Network) domain. For example, ML training functions for MDA (Management Data Analytics) can be deployed in MDAF (Management Data Analytic Function); ML training for network data analytics can be deployed in NWDAF (Network Data Analytics Function), meaning the ML training function is an MTLF (Model Training Logical Function).

[0952] The ML inference function can also be deployed in a cross-domain management system or a domain-specific management system; for example, the ML inference function is MDAF, or the ML inference function is AnLF (Analytics Logical Function) located in NWDAF.

[0953] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[0954] Optionally, the management of ML inference function can also be completed by the base station itself, that is, each base station can independently interact with the RAN domain MnS consumer / cross-domain management 1201.

[0955] It should be noted that Example 12 is merely a non-limiting implementation; optionally, the ML training function of the RAN domain may also be deployed at the base station; or optionally, some base stations may deploy both the ML inference function and the ML training function of the RAN domain, while some base stations may only deploy the ML inference function.

[0956] As an example, one of the gNBs (or base stations) in Example 12 is the second node of this application.

[0957] As one example, the ML includes AI.

[0958] As one example, the AI ​​includes ML.

[0959] Example 13

[0960] Example 13 illustrates a schematic diagram of the deployment of AI / ML functions in a UE according to an embodiment of this application, as shown in the attached diagram. Figure 13 As shown. In the appendix Figure 13 In this context, the RAN domain ML training function 1304 is optional.

[0961] UE function 1303 is deployed in the first node of this application, and the UE function 1303 includes AI / ML inference function 1305; the AI / ML inference function 1305 uses an ML model (also called an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[0962] As an example, the UE function 1303 includes a RAN domain ML training function 1304, which runs training data through an ML model to obtain a relevant loss and adjusts the parameters of the ML model based on the calculated loss; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0963] The above embodiments can reduce the complexity of the base station, or save air interface resources caused by reporting training data; however, the above embodiments place high demands on the processing capabilities of the UE side.

[0964] Optionally, the UE function 1303 also includes a CN domain ML training function ( Figure 13 (Not included in the text).

[0965] Optionally, the UE function 1303 also includes an AI / ML deployment function. Figure 13It is not included in the list, which is used to load ML models and data.

[0966] As an example, the first node indicates whether it supports ML training function (RAN domain or CN domain) through capability reporting. The capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0967] As an example, the first node instructs the AI / ML inference function 1305 for the applicable configuration for inference via UAI.

[0968] As an example, the ML model and the associated metadata are loaded by the first node from a network device or a remote server.

[0969] Optionally, the UE function 1303 is an MnS producer that provides data to the CN domain MnF (Management Function) and / or the RAN domain MnF and / or the cross-domain management system 1301 for management or analysis (as shown by the double arrow 1302).

[0970] Optionally, the UE function 1303 is an MnS consumer that loads data from the CN domain MnF and / or RAN domain MnF and / or cross-domain management system 1301 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1302).

[0971] As an example, the AI-based inference waveform described in this application is obtained through inference by the AI / ML inference function 1305.

[0972] As an example, the maximum power backoff value based on AI inference in this application is obtained through inference by the AI / ML inference function 1305.

[0973] As an example, the maximum power backoff value indicated in the previous report in this application is obtained through inference by the AI / ML inference function 1305.

[0974] As an example, the waveform indicated in the previous report in this application is obtained through inference by the AI / ML inference function 1305.

[0975] As an example, the first time window in this application is obtained through inference by the AI / ML inference function 1305.

[0976] As an example, the ML model is based on NN.

[0977] As an example, the ML model is based on ANN.

[0978] As an example, the ML model is based on CNN.

[0979] As an example, the ML model is based on the Transformer architecture.

[0980] As an example, the ML model is based on LSTM.

[0981] As an example, the ML model is based on MLP.

[0982] As an example, the ML model is based on GAN.

[0983] As an example, the ML model is based on a lightweight neural network.

[0984] As a sub-example of this embodiment, the lightweight neural network includes one or more of MobileNet, ShuffleNet, and SqueezeNet.

[0985] As one example, the ML includes AI.

[0986] As one example, the AI ​​includes ML.

[0987] Example 14

[0988] Example 14 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application, as shown in the attached diagram. Figure 14 As shown. In the appendix Figure 14 In this context, the processing system based on artificial intelligence or machine learning includes a first processor, a second processor, a third processor, and a fourth processor.

[0989] In Example 14, the first processor sends a first dataset to the second processor and a second dataset to the third processor; the second processor generates a target first-class parameter set based on the first dataset, and sends the generated target first-class parameter set to the third processor; the third processor processes the second dataset using the target first-class parameter set to obtain a first-class output, optionally, the third processor sends the first-class output to the fourth processor. (See Appendix...) Figure 14 In this configuration, the first type of feedback and the second type of feedback are optional; the second processor includes ML training functionality; and the third processor includes ML inference functionality.

[0990] As one embodiment, the fourth processor includes ML testing functionality.

[0991] As one embodiment, the fourth processor includes performance monitoring / evaluation of the ML model.

[0992] As one embodiment, the third processor sends a first type of feedback to the second processor; the first type of feedback is used to trigger the recalculation or update of the target first type of parameter set, that is, to trigger ML initial training or ML retraining.

[0993] As one embodiment, the fourth processor sends a second type of feedback to the first processor; the second type of feedback is used to generate the first dataset or the second dataset, or the second type of feedback is used to trigger the sending of the first dataset or the sending of the second dataset.

[0994] As one embodiment, the first processor generates the first dataset and the second dataset based on the measurement of the reference signal.

[0995] As one embodiment, the third processor belongs to the first node, and the fourth processor belongs to the second node.

[0996] As an example, the third processor belongs to the first node.

[0997] As an example, the first dataset includes training data.

[0998] As one embodiment, the second processor is used to train an ML model, and the trained model is described by the target first class of parameter sets.

[0999] As an example, the second processor belongs to the first node; the above method avoids passing the first dataset to the second node.

[1000] As an example, the second processor belongs to the second node in this application; the above method supports joint training and optimizes system performance.

[1001] As an example, the second processor belongs to the core network; the above method supports network-wide joint training, further optimizing system performance.

[1002] As an example, the second dataset includes inference data.

[1003] As an example, the third processor constructs a model based on the target first type of parameter group, and then inputs the second dataset into the constructed model to obtain the first type of output.

[1004] As an example, the second dataset includes the measurements of the first reference signal described in this application.

[1005] As an example, the second dataset includes the L1 measurement results obtained from the measurement of the first reference signal as described in this application.

[1006] As an example, the second dataset includes the L3 measurement results obtained from the measurement of the first reference signal as described in this application.

[1007] As one embodiment, the second dataset includes data on the first logical channel in this application.

[1008] As one embodiment, the second dataset includes features of the data on the first logical channel in this application.

[1009] As an example, the first type of output includes the recommended configuration indicated by the first report in this application.

[1010] As an example, the first type of output includes the recommended configuration described in this application.

[1011] As an example, the first type of output includes the AI-based inference waveform described in this application.

[1012] As an example, the first type of output includes the maximum power backoff value based on AI inference described in this application.

[1013] As an example, the third processor generates a recovery dataset based on the first type of output, and the error between the recovery dataset and the second dataset is used to generate the first type of feedback.

[1014] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the second processing opportunity will recalculate the target first type of parameter set.

[1015] As an example, when the error is too large or the update has not been performed for too long, the performance of the trained model is considered to be unsatisfactory.

[1016] As an example, 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.

[1017] As an example, the target first type of parameter group includes one or more of the following: convolution kernel size, number of convolution layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[1018] Example 15

[1019] Example 15 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application, as shown in the attached diagram. Figure 15 As shown. In the appendix Figure 15 In this process, the first and second operations belong to the first stage, the third operation belongs to the second stage, the fourth operation belongs to the third stage, and the fifth operation belongs to the fourth stage; the arrowed lines indicate the sequence of the process.

[1020] As an example, the first operation includes AI / ML training, the second operation includes AI / ML testing, the third operation includes AI / ML emulation, the fourth operation includes AI / ML entity loading, and the fifth operation includes AI / ML inference.

[1021] As one embodiment, the first stage includes a training phase, the second stage includes an emulation phase, the third stage includes a deployment phase, and the fourth stage includes an inference phase.

[1022] As an example, the first stage includes AI / ML model training.

[1023] As an example, the first stage includes AI / ML model training and AI / ML testing.

[1024] As an example, the AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[1025] As an example, the training of the AI / ML model depends on training data.

[1026] As an example, the AI / ML model training includes AI / ML entity validation.

[1027] As an example, the AI / ML entity verification is used to evaluate the performance of the AI / ML entity.

[1028] As an example, the AI / ML entity verification relies on verification data.

[1029] As an example, if the AI / ML entity verification results do not meet expectations, the AI / ML model will be retrained.

[1030] As an example, the AI / ML testing includes testing the validated AI / ML entities to estimate the performance of the trained AI / ML model.

[1031] As an example, if the AI / ML test results meet expectations, the AI / ML entity proceeds to the next stage; otherwise, the AI / ML model will be retrained.

[1032] As an example, the AI / ML test relies on test data.

[1033] As one embodiment, the second stage includes AI / ML simulation, which performs AI / ML entity reasoning in a simulation environment.

[1034] As an example, the AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using AI / ML entities.

[1035] As one embodiment, the second stage is optional.

[1036] As an example, the third stage includes AI / ML entity loading, which is to obtain trained AI / ML entities to obtain the desired AI / ML inference function.

[1037] As an example, the third stage is optional.

[1038] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[1039] As an example, the fourth stage includes AI / ML inference.

[1040] Example 16

[1041] Example 16 illustrates a structural block diagram of a processing device for a first node according to an embodiment, as shown in the attached diagram. Figure 16 As shown. In the appendix Figure 16 In the first node, the processing device 1600 includes a first transceiver 1601. The first transceiver 1601 includes the components specified in the appendix of this application. Figure 4 The transmitter / receiver 456 (including antenna 460), receiver processor 452, transmitter processor 455 and controller / processor 490 are included.

[1042] In embodiment 16, a first transceiver 1601 sends a first report indicating a recommended configuration; the first transceiver 1601 sends a first signal; wherein the recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[1043] As one embodiment, a first transceiver 1601 receives a first reference signal; wherein the recommended configuration indicated by the first report depends on a first inference, the input of which depends on a measurement of the first reference signal.

[1044] As an example, the recommended configuration indicated by the first report is inferred by the first node based on the first logical channel, and the first encoder is applied to the encoding of data on the first logical channel, the first encoder being based on AI.

[1045] As one embodiment, a first transceiver 1601 receives a first information block indicating a first condition; the first transceiver 1601 sends a second information block indicating that a first AI function is applicable; wherein, the first AI function is applicable under the first condition, and the recommended configuration indicated by the first report depends on the first AI function.

[1046] As an example, the first transceiver 1601 sends a second report; the second report indicates that the second AI function is not applicable, and the recommended configuration indicated by the first report depends on the second AI function; the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[1047] As an example, the triggering conditions for the first report include at least one of the following:

[1048] The change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold, which is configured or predefined;

[1049] The waveform based on AI reasoning is different from the waveform indicated in the previous report.

[1050] As an example, the first report is triggered when the first timer expires, and the first timer is configured or predefined.

[1051] Example 17

[1052] Example 17 illustrates a structural block diagram of a processing device for a second node according to an embodiment, as shown in the attached diagram. Figure 17 As shown. In the appendix Figure 17 In the second node, the processing device 1700 includes a second transceiver 1701. The second transceiver 1701 includes the components outlined in the appendix to this application. Figure 4 The transmitter / receiver 416 (including antenna 420), receiver processor 412, transmitter processor 415 and controller / processor 440 are included.

[1053] In embodiment 17, the second transceiver 1701 receives a first report indicating a recommended configuration; the second transceiver 1701 receives a first signal; wherein the recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

[1054] As one embodiment, the second transceiver 1701 transmits a first reference signal; wherein the recommended configuration indicated by the first report depends on a first inference, the input of which depends on a measurement of the first reference signal.

[1055] As an example, the recommended configuration indicated by the first report is inferred by the sender of the first report based on the first logical channel, and the first encoder is applied to the encoding of data on the first logical channel, the first encoder being based on AI.

[1056] As one embodiment, the second transceiver 1701 sends a first information block indicating a first condition; the second transceiver 1701 receives a second information block indicating that a first AI function is applicable; wherein, the first AI function is applicable under the first condition, and the recommended configuration indicated by the first report depends on the first AI function.

[1057] As an example, the second transceiver 1701 receives a second report; the second report indicates that the second AI function is not applicable, and the recommended configuration indicated by the first report depends on the second AI function; the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

[1058] As an example, the triggering conditions for the first report include at least one of the following:

[1059] The change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold, which is configured or predefined;

[1060] The waveform based on AI reasoning is different from the waveform indicated in the previous report.

[1061] As an example, the first report is triggered when the first timer expires, and the first timer is configured or predefined.

[1062] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The first node or second node or UE or terminal in this application includes, but is not limited to, mobile phones, tablets, laptops, network cards, low-power devices, eMTC devices, NB-IoT devices, vehicle communication devices, aircraft, airplanes, drones, remote-controlled airplanes, testing devices, testing equipment, testing instruments, etc. The base station equipment or base station or network-side equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, home base stations, relay base stations, eNBs, gNBs, Transmitter Receiver Nodes (TRPs), relay satellites, satellite base stations, airborne base stations, testing devices, testing equipment, testing instruments, etc.

[1063] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A first node for wireless communication, the first node comprising: include: The first transceiver sends a first report, which indicates the recommended configuration. The first transceiver sends a first signal; The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

2. The first node of claim 1, characterized in that, include: The first transceiver receives the first reference signal; The recommended configuration indicated in the first report depends on a first inference, the input of which depends on a measurement of the first reference signal.

3. The first node according to claim 1 or 2, characterized in that, The recommended configuration indicated in the first report is inferred by the first node based on the first logical channel, and the first encoder is applied to the encoding of data on the first logical channel, and the first encoder is based on AI.

4. The first node according to any one of claims 1 to 3, characterized in that, include: The first transceiver receives a first information block, the first information block indicating a first condition; The first transceiver sends a second information block, the second information block indicating that the first AI function is applicable; Wherein, the first AI function applies under the first condition, and the recommended configuration indicated by the first report depends on the first AI function.

5. The first node according to any one of claims 1 to 4, characterized in that, include: The first transceiver sends the second report; The second report indicates that the second AI function is not applicable, and the recommended configuration indicated by the first report depends on the second AI function; the triggering of the second report depends on the relationship between the recommended configuration and the measurement within the first time window.

6. The first node according to any one of claims 1 to 5, characterized in that, The triggering conditions for the first report include at least one of the following: The change between the maximum power backoff value based on AI inference and the maximum power backoff value indicated in the previous report is greater than a first threshold, which is configured or predefined; The waveform based on AI reasoning is different from the waveform indicated in the previous report.

7. The first node according to any one of claims 1 to 6, characterized in that, The first report is triggered when the first timer expires, and the first timer is either configured or predefined.

8. A second node for wireless communication, characterized in that, include: The second transceiver receives the first report, which indicates the recommended configuration. The second transceiver receives the first signal; The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

9. A method for a first node in wireless communication, characterized in that, include: Send a first report, which indicates the recommended configuration; Send the first signal; The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

10. A method for a second node in wireless communication, characterized in that, include: Receive the first report, which indicates the recommended configuration; Receive the first signal; The recommended configuration indicated by the first report includes at least one of an AI-inference-based waveform and an AI-inference-based maximum power backoff value; the AI-inference-based waveform is one of a plurality of candidate waveforms of the first signal, the maximum output power value of the first signal depends on a first maximum power backoff value, and the AI-inference-based maximum power backoff value is one of a plurality of candidate values ​​of the first maximum power backoff value; the recommended configuration indicated by the first report is for a first time window, which is configured or indicated by the first report.

Images