Method and apparatus applied to node in wireless communication and artificial intelligence

Abstract

Disclosed in the present application are a method and apparatus applied to a node in wireless communication and artificial intelligence. The method comprises: a first node receiving M configuration messages, wherein the M configuration messages respectively indicate M RS resource groups, and any one of the M RS resource groups comprises one or more RS resources, M being a positive integer greater than 1; and for each of the M configuration messages, calculating a first parameter, wherein the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message, the first configuration message is one of the M configuration messages, and a calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one of the M configuration messages other than the first configuration message. The present application monitors performance changes of an AI / ML model and adjusts the monitoring frequency in a timely manner, thereby reducing calculation and resource consumption, and improving the network intelligence level.

Description

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

[0001] This application claims priority to the Chinese patent application No. 202411254239.1, filed on September 6, 2024, entitled "A method and apparatus in a node used for wireless communication and artificial intelligence", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

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

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

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

[0005] The LCM of an AI / ML model is the management of an AI / ML model from creation to end, and the LCM of an AI / ML model in Rel-18 includes one or more of data collection, model training, model registration, model deployment, model configuration, model inference operation, model selection / switching / activation / deactivation / fallback operation, model monitoring, model update, and model transfer; wherein, in the AI / ML model monitoring, how to quickly identify the decline of the inference performance of the AI / ML model and the corresponding response mechanism after the decline of the inference performance of the AI / ML model are technical problems to be solved at present.

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

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

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

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

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

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

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

[0013] Receiving M configuration messages, each of the M configuration messages indicating an RS resource group, any RS resource group of the M RS resource groups comprising one or more RS resources, M being a positive integer greater than 1;

[0014] For each of the M configuration messages, calculating a first parameter; the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message;

[0015] Wherein, the first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages and other than the first configuration message.

[0016] As an embodiment, the problem to be solved by the present application includes: how to improve the reliability of AI / ML model inference.

[0017] As an embodiment, the problem to be solved by the present application includes: how to enhance the measurement reporting mechanism to promote the deep integration of AI / ML and communication.

[0018] As an embodiment, the problem to be solved by the present application includes: how to quickly identify the decline of AI / ML model inference performance in AI / ML model monitoring.

[0019] As an embodiment, the characteristics of the above method include: in the present application, the first node performs measurement, model inference prediction according to the measurement resource and reporting resource configured by the network device, and calculates the KPI of the AI / ML model according to the measurement result and the prediction result, thereby realizing timely monitoring of the inference performance of the AI / ML model and quickly identifying whether the inference performance of the AI / ML model declines.

[0020] As an embodiment, the characteristics of the above method include: in the present application, the M configuration messages respectively configure M RS resource groups for AI / ML model inference, the first node receives and measures the M RS resource groups according to the configuration of the M configuration messages, and simultaneously infers the inference results corresponding to the M RS resource groups based on the collected RS resource data, and the first node calculates the first parameters of the M RS resource groups based on the measurement results of the M RS resource groups and the inference results corresponding to the M RS resource groups, thereby realizing measurement and inference based on AI / ML model through enhanced RS resource configuration.

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

[0022] As an embodiment, the characteristics of the above method include: the first parameter is the KPI of the AI / ML model.

[0023] As an embodiment, the characteristics of the above method include: the signaling carrying the M configuration messages simultaneously indicates the AI / ML model or AI / ML entity associated with the M configuration messages.

[0024] As an embodiment, the characteristics of the above method include: the calculation time of the first parameter includes the period of the first node calculating the first parameter.

[0025] As an embodiment, the characteristics of the above method include: the calculation time of the first parameter includes the period of the first node receiving or measuring the M RS resource groups.

[0026] As an embodiment, the characteristics of the above method include: the calculation time of the first parameter corresponding to the first configuration message includes the calculation delay.

[0027] As an embodiment, the benefits of the above method include: AI and communication are deeply integrated in the present application, improving the adaptability and intelligence level of the communication system, and thus improving the performance, efficiency and user experience of the communication system.

[0028] As an embodiment, the benefits of the above method include: timely identification of AI / ML model inference performance changes.

[0029] As an embodiment, the benefits of the above method include: improving the reliability and robustness of model inference.

[0030] As an embodiment, the benefits of the above method include: improving the quality of business decision-making.

[0031] As an embodiment, the benefits of the above method include: improving the flexibility and adaptability of the system.

[0032] According to an aspect of the present application, the above method is characterized in that the calculation time refers to the CPU occupation time.

[0033] As an embodiment, the features of the above method include: the calculation time refers to the channel state information calculation occupation time.

[0034] As an embodiment, the features of the above method include: the calculation time refers to the CSI processing unit occupation time.

[0035] As an embodiment, the features of the above method include: the calculation time refers to the central processing unit occupation time.

[0036] As an embodiment, the benefits of the above method include: fully considering the impact of computing power delay.

[0037] According to an aspect of the present application, the above method is characterized in that it includes:

[0038] For each of the M configuration messages, the corresponding first parameter is sent.

[0039] As an embodiment, the problem to be solved by the present application includes: in AI / ML model monitoring, how to quickly identify the decline of AI / ML model inference performance.

[0040] As an embodiment, the features of the above method include: in the present application, the terminal transmits the M first parameters obtained by calculation to the network through the air interface signal, and the network realizes performance monitoring of the AI / ML model deployed in the terminal based on the received M first parameters, timely identifies the performance change of the AI / ML model, and thus solves the above problem.

[0041] As an embodiment, the method has the feature that the terminal physical layer measures and calculates M first parameters for the M configuration messages, and sends the M first parameters to a higher layer, and the terminal can implement performance monitoring of the AI / ML model based on the M first parameters, thereby solving the above problems.

[0042] As an embodiment, the method has the feature that the first node sends M first parameters, and the M first parameters are all KPIs of the same type of AI / ML model.

[0043] As an embodiment, the method has the benefit that the application supports the working mode of the network monitoring the AI / ML model deployed on the terminal side, has low requirements on the terminal, reduces the cost of the terminal, and enables the network to obtain more information about the performance change of the model to assist the model selection / switching / activation / deactivation / rollback operation.

[0044] As an embodiment, the method has the benefit that the application supports the working mode of the terminal monitoring the AI / ML model deployed on the terminal side, and the terminal can optionally send the reporting information when the performance change of the AI / ML model meets a given condition or a given set of conditions, thereby avoiding repeated sending of redundant information to occupy too much air interface resource, saving energy resources, and improving the endurance time of the terminal.

[0045] According to an aspect of the application, the method has the feature that it comprises:

[0046] According to the reporting configuration of each of the M configuration messages, calculating or sending predicted channel information;

[0047] The predicted channel information depends on the measurement on the RS resource group indicated by the corresponding configuration message, and the calculation of the first parameter depends on the predicted channel information associated with the corresponding configuration message.

[0048] As an embodiment, the method has the feature that the first node calculates predicted channel information according to the reporting configuration of each of the M configuration messages, and calculates the first parameter according to the predicted channel information and the measured channel information.

[0049] As an embodiment, the method has the feature that the first parameter comprises real CSI.

[0050] As an embodiment, the method has the feature that the first parameter comprises the Euclidean metric between the predicted channel information and the measured channel information.

[0051] As an embodiment, the benefits of the above method include: improving the accuracy of model monitoring, verifying the reliability of reasoning.

[0052] As an embodiment, the benefits of the above method include: timely discovery of overfitting and underfitting of the model.

[0053] As an embodiment, the benefits of the above method include: the terminal can implement performance monitoring of the model based on the predicted channel information and the measurement results in a relevant manner, which helps to identify model abnormalities in a timely manner and enhances the robustness of the model.

[0054] According to an aspect of the present application, the above method is characterized in that the M configuration messages are associated with a first entity, the first entity is used for AI / ML-based prediction, and the first entity includes at least one of the following features:

[0055] - an AI / ML model;

[0056] - associated with an AI / ML model ID;

[0057] - associated with a Functionality ID;

[0058] - associated with a data set;

[0059] - corresponding to an Associated ID.

[0060] As an embodiment, the ID in the present application refers to: IDentify, proof.

[0061] As an embodiment, the ID in the present application refers to: IDentification, identity proof.

[0062] As an embodiment, the ID in the present application refers to: IDentity, identity or identification.

[0063] As an embodiment, the ID in the present application refers to: IDentifier, identifier.

[0064] As an embodiment, the ID in the present application refers to: InDex, index.

[0065] As an embodiment, the problem to be solved in the present application includes: how to enhance the measurement reporting mechanism to promote the deep integration of AI / ML and communication.

[0066] As an embodiment, the method has the feature that the first entity is introduced in the application, and optionally, the first entity performs AI / ML related operations such as construction of a training data set, model training, and the like, thereby realizing the function of supporting AI / ML models in a wireless network.

[0067] As an embodiment, the method has the feature that the M configuration messages correspond to M first parameters for the first entity, and the M first parameters are used to monitor KPIs of the first entity.

[0068] As an embodiment, the method has the feature that the first entity calculates predicted channel information according to the reporting configuration of each of the M configuration messages.

[0069] As an embodiment, the method has the feature that the first entity is an AI / ML model.

[0070] As an embodiment, the method has the feature that the first entity is an AI / ML entity.

[0071] As an embodiment, the method has the benefit of facilitating the deep integration of AI and communication networks and improving compatibility.

[0072] As an embodiment, the method has the benefit of improving network topology capabilities and enhancing user experience.

[0073] As an embodiment, the method has the benefit of improving network efficiency and resource utilization based on performance monitoring and optimization of AI / ML entities.

[0074] According to an aspect of the application, the method has the feature that the M configuration messages correspond to M different target predictions, and the M different target predictions include at least one of the following:

[0075] - prediction of RSRP for L1;

[0076] - prediction of RSRP for L3;

[0077] - prediction for cell switching;

[0078] - prediction for mobility.

[0079] As an embodiment, the method has the feature that the target refers to a measurement object, and the M configuration messages are respectively configured or associated to the M measurement objects.

[0080] As an embodiment, the method has the feature that the prediction of the M different targets is based on a measurement result.

[0081] As an embodiment, the method has the benefit that the present application supports a single AI / ML entity to handle multiple different measurement tasks simultaneously, and optionally, the multi-task parallel processing allows the entity to dynamically adjust resource allocation strategies, improving the flexibility and adaptability of the system.

[0082] As an embodiment, the method has the benefit that it is suitable for a wider range of measurement scenarios, reducing system complexity and maintenance costs.

[0083] As an embodiment, the method has the benefit of improving the level of network intelligence.

[0084] According to an aspect of the present application, the method has the feature that the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message other than the first configuration message among the M configuration messages, which includes: when the first parameter corresponding to at least one configuration message other than the first configuration message is not less than a first threshold value, the calculation time of the first parameter is equal to a first time value; when the first parameter corresponding to at least one configuration message other than the first configuration message is less than a first threshold value, the calculation time of the first parameter is equal to a second time value; the first time value and the second time value are different.

[0085] As an embodiment, the present application addresses the problem of how to determine the calculation time of the first parameter.

[0086] As an embodiment, the method has the feature that the first node determines the calculation time of the first parameter corresponding to the first configuration message according to the calculation result of the first parameter corresponding to one configuration message other than the first configuration message, thereby solving the above problem.

[0087] As an embodiment, the method has the feature that the signaling carrying the M configuration messages simultaneously indicates the first time value and the second time value.

[0088] As an embodiment, the method has the feature that the second time value is greater than the first time value, and model monitoring is performed at a more sparse frequency after the AI / ML model performance is identified to have declined.

[0089] As an embodiment, the method has the benefit that monitoring at a more sparse frequency after the model performance is identified to have declined can significantly reduce calculation and resource consumption, thereby improving the priority of other tasks and reducing the burden of invalid monitoring.

[0090] As an embodiment, the benefits of the above method include: reducing the impact of noise in AI / ML model inference and monitoring process, and obtaining changes in model performance based on longer time granularity.

[0091] According to an aspect of the present application, the above method is characterized in that the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to the second configuration message among the M configuration messages and other than the first configuration message, and the first configuration message and the second configuration message are consistent; the consistency includes at least one of the following:

[0092] - the RS resource group indicated by the first configuration message and the RS resource group indicated by the second configuration message are QCL;

[0093] - the speed applicable to the first configuration message and the speed applicable to the second configuration message are the same;

[0094] - the first configuration message and the second configuration message indicate the same RS resource group;

[0095] - the first configuration message and the second configuration message correspond to the same spatial parameter.

[0096] As an embodiment, the features of the above method include: how the first node determines the second configuration message.

[0097] As an embodiment, the features of the above method include: the inference performance of AI / ML is closely related to input data, and when the noise in the input data of the AI / ML model is too large, it will affect the model inference accuracy, in this application, the monitoring frequency of the AI / ML model of the two different configuration messages associated with the input data is associated, thereby solving the above problem.

[0098] As an embodiment, the benefits of the above method include: reducing the impact on model inference performance due to excessive noise in input data, i.e., reducing the quality of communication link channel.

[0099] As an embodiment, the benefits of the above method include: reducing computation and resource consumption, reducing redundant data processing, and improving overall system response speed.

[0100] According to an aspect of the present application, the above method is characterized in that the measurement includes measurement for at least one of RSRP, RSRQ, RSSI, or SNR.

[0101] As an embodiment, the benefits of the above method include: good compatibility.

[0102] As an embodiment, the benefits of the above method include: easy to implement.

[0103] According to an aspect of the present application, the above method is characterized in that the first node is a user equipment.

[0104] According to an aspect of the present application, the above method is characterized in that the first node is a terminal.

[0105] The present application discloses a method in a second node for wireless communication and artificial intelligence, comprising:

[0106] transmitting M configuration messages, the M configuration messages respectively indicating M RS resource groups, any RS resource group of the M RS resource groups comprising one or more RS resources, M being a positive integer greater than 1;

[0107] wherein the receiver of the M configuration messages is a first node; for each configuration message of the M configuration messages, the first node calculates a first parameter; the calculation of the first parameter depends on the measurement of the RS resource group indicated for the corresponding configuration message; the first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message.

[0108] As an embodiment, the above method is characterized in that the second node is a network device, the network device comprising at least one of a core network device and an access network device.

[0109] As an embodiment, the above method is characterized in that the second node is a device providing wireless communication function service, which can communicate with a terminal device and is usually located at the network side.

[0110] As an embodiment, the above method is characterized in that the second node is a base station.

[0111] As an embodiment, the above method is characterized in that the second node is an eNB.

[0112] As an embodiment, the above method is characterized in that the second node is a gNB.

[0113] As an embodiment, the above method is characterized in that the second node comprises a base station.

[0114] As an embodiment, the above method is characterized in that the second node comprises a core network.

[0115] As an embodiment, the above method is characterized in that the second node comprises a base station and a core network.

[0116] As one embodiment, the method has the feature that the second node comprises an entity for deploying the AI / ML model.

[0117] As one embodiment, the method has the feature that the second node comprises a node for deploying the AI / ML model.

[0118] As one embodiment, the method has the feature that the base station in the present application comprises a core network.

[0119] As one embodiment, the method has the feature that the base station in the present application comprises a core network device.

[0120] As one embodiment, the method has the feature that the base station in the present application comprises an entity for deploying the AI / ML model.

[0121] As one embodiment, the method has the feature that the base station in the present application comprises a node for deploying the AI / ML model.

[0122] According to one aspect of the present application, the method has the feature that the calculation time refers to the occupation time of the CPU.

[0123] According to one aspect of the present application, the method has the feature that it comprises:

[0124] For each of the M configuration messages, a corresponding first parameter is received.

[0125] According to one aspect of the present application, the method has the feature that it comprises:

[0126] According to the reporting configuration of each of the M configuration messages, predicted channel information is received;

[0127] Wherein the predicted channel information depends on the measurement on the RS resource group indicated by the corresponding configuration message; the calculation of the first parameter depends on the predicted channel information associated with the corresponding configuration message.

[0128] According to one aspect of the present application, the method has the feature that the M configuration messages are associated to a first entity, the first entity is used for AI / ML-based prediction, and the first entity comprises at least one of the following features:

[0129] - an AI / ML model;

[0130] - associated to an AI / ML model ID;

[0131] - associated to a Functionality ID;

[0132] - association to a data set;

[0133] - correspondence to an Associated ID.

[0134] According to an aspect of the present application, the above method is characterized in that the M configuration messages respectively correspond to M different target predictions, and the M different target predictions include at least one of the following:

[0135] - prediction of RSRP for L1;

[0136] - prediction of RSRP for L3;

[0137] - prediction for cell switching;

[0138] - prediction for mobility.

[0139] According to an aspect of the present application, the above method is characterized in that the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages and other than the first configuration message, and the meaning of the consistency includes at least one of the following:

[0140] According to an aspect of the present application, the above method is characterized in that the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message in the M configuration messages and other than the first configuration message, and the first configuration message and the second configuration message are consistent; and the meaning of the consistency includes at least one of the following:

[0141] - the RS resource group indicated by the first configuration message and the RS resource group indicated by the second configuration message are QCL;

[0142] - the speed applicable to the first configuration message and the speed applicable to the second configuration message are the same;

[0143] - the first configuration message and the second configuration message indicate the same RS resource group;

[0144] - the first configuration message and the second configuration message correspond to the same spatial parameter.

[0145] According to an aspect of the present application, the above method is characterized in that the measurement comprises measurement for at least one of RSRP, RSRQ, RSSI or SNR.

[0146] According to an aspect of the present application, the above method is characterized in that the second node is a base station.

[0147] The present application discloses a device for a first node in wireless communication and artificial intelligence, comprising:

[0148] A first receiver receives M configuration messages, each of which indicates M RS resource groups, any of which comprises one or more RS resources, and M is a positive integer greater than 1.

[0149] A first processor calculates a first parameter for each of the M configuration messages, and the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message.

[0150] Among them, the first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages other than the first configuration message.

[0151] The present application discloses a device for a second node in wireless communication and artificial intelligence, comprising:

[0152] A first transmitter transmits M configuration messages, each of which indicates M RS resource groups, any of which comprises one or more RS resources, and M is a positive integer greater than 1.

[0153] Among them, the receiver of the M configuration messages is the first node; for each of the M configuration messages, the first node calculates a first parameter; the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message; the first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages other than the first configuration message.

[0154] As an embodiment, compared with the conventional scheme, the present application has the following advantages, but is not limited to:

[0155] In the present application, AI and communication are deeply integrated to improve the adaptability and intelligence level of the communication system, and thus the performance, efficiency and user experience of the communication system are improved.

[0156] The application supports a single AI / ML entity to handle multiple different measurement tasks simultaneously. Optionally, multi-task parallel processing allows the entity to dynamically adjust resource allocation strategies, improving the flexibility and adaptability of the system.

[0157] Recognizing model performance degradation allows for significantly reduced computation and resource consumption at a more sparse monitoring frequency, thereby improving the priority of other tasks and reducing the burden of ineffective monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0158] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0159] Figure 1 shows a flowchart of a first node transmission according to one embodiment of the application;

[0160] Figure 2 shows a schematic diagram of a network architecture according to one embodiment of the application;

[0161] Figure 3 shows a schematic diagram of an embodiment of a wireless protocol architecture of the user plane and control plane according to one embodiment of the application;

[0162] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to one embodiment of the application;

[0163] Figure 5 shows a flowchart of a transmission between a first node and a second node according to one embodiment of the application;

[0164] Figure 6 shows a flowchart of a first node transmitting a first parameter according to one embodiment of the application;

[0165] Figure 7 shows a flowchart of a first node calculating or transmitting predicted channel information according to one embodiment of the application;

[0166] Figure 8 shows a schematic diagram of a first entity according to one embodiment of the application;

[0167] Figure 9 shows a schematic diagram of a configuration message and a target prediction according to one embodiment of the application;

[0168] Figure 10 shows a schematic diagram of a calculation time of a first parameter corresponding to a first configuration message according to one embodiment of the application;

[0169] Figure 11 shows a schematic diagram of RAN domain AI / ML function deployment according to one embodiment of the application;

[0170] Figure 12 shows a schematic diagram of AI / ML function deployment of a UE according to one embodiment of the application;

[0171] FIG. 13 shows a schematic diagram of an artificial intelligence or machine learning based processing system according to an embodiment of the present application;

[0172] FIG. 14 shows a schematic diagram of artificial intelligence or machine learning according to an embodiment of the present application;

[0173] FIG. 15 shows a structural block diagram of a processing device for use in a first node according to an embodiment of the present application;

[0174] FIG. 16 shows a structural block diagram of a processing device for use in a second node according to an embodiment of the present application. DETAILED DESCRIPTION

[0175] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily without conflict. Based on performance, flexibility, complexity, overhead and compatibility, etc., the person skilled in the art has the motivation to flexibly combine the embodiments in different drawings without conflict, including but not limited to the embodiments in FIG. 1 and the embodiments in FIGS. 5-16, the embodiments in FIG. 5 and the embodiments in FIGS. 6-16, etc.

[0176] Embodiment 1

[0177] Embodiment 1 illustrates a flowchart of a first node transmission according to an embodiment of the present application, as shown in FIG. 1. In FIG. 1, each block represents a step. In particular, the order of the steps in the blocks does not represent a specific time sequence between the steps.

[0178] The first node receives M configuration messages in step 101, the M configuration messages respectively indicate M RS resource groups, any RS resource group in the M RS resource groups includes one or more RS resources, and M is a positive integer greater than 1; in step 102, a first parameter is calculated for each of the M configuration messages; the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message.

[0179] In embodiment 1, the first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages other than the first configuration message.

[0180] As an embodiment, the RS refers to Reference Signal, reference signal.

[0181] As an embodiment, the first node is a user equipment (UE).

[0182] As an embodiment, the first node is a terminal.

[0183] As an embodiment, the first node is the first node as described in the present application.

[0184] As an embodiment, the M is a positive integer greater than 1.

[0185] As an embodiment, the M is not greater than 128.

[0186] As an embodiment, the M is not greater than 64.

[0187] As an embodiment, the first node receives the M configuration messages.

[0188] As an embodiment, any of the M configuration messages is transmitted through higher layer signaling.

[0189] As an embodiment, any of the M configuration messages is carried by RRC (Radio Resource Control) layer signaling.

[0190] As an embodiment, any of the M configuration messages is transmitted through RRC signaling.

[0191] As an embodiment, any of the M configuration messages is transmitted through an RRC message.

[0192] As an embodiment, any of the M configuration messages includes RRC signaling.

[0193] As an embodiment, any of the M configuration messages includes one or more RRC IEs (Information Elements).

[0194] As an embodiment, any of the M configuration messages includes one or more fields in one RRC IE.

[0195] As an embodiment, any of the M configuration messages includes one or more fields in each of a plurality of RRC IEs.

[0196] As an embodiment, the M configuration messages are carried by the same RRC signaling.

[0197] As one embodiment, the M configuration messages belong to a list included in one RRC IE.

[0198] As one sub-embodiment of this embodiment, the M configuration messages correspond to one and the same field of the one RRC IE.

[0199] As one sub-embodiment of this embodiment, the M configuration messages correspond to M elements of the one list.

[0200] As one sub-embodiment of this embodiment, the name of the list carrying the M configuration messages comprises: Add.

[0201] As one sub-embodiment of this embodiment, the name of the list carrying the M configuration messages comprises: Mod.

[0202] As one sub-embodiment of this embodiment, the name of the list carrying the M configuration messages comprises: ToAddModList.

[0203] As one embodiment, any of the M configuration messages comprises a ServingCellConfig IE.

[0204] As one embodiment, any of the M configuration messages comprises one or more fields in a ServingCellConfig IE.

[0205] As one embodiment, any of the M configuration messages comprises a CSI-MeasConfig IE.

[0206] As one embodiment, any of the M configuration messages comprises one or more fields in a CSI-MeasConfig IE.

[0207] As one embodiment, any of the M configuration messages comprises a NZP-CSI-RS-Resource IE.

[0208] As one embodiment, any of the M configuration messages comprises one or more fields in a NZP-CSI-RS-Resource IE.

[0209] As one embodiment, any of the M configuration messages comprises a CSI-RS-ResourceMapping IE.

[0210] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-RS-ResourceMapping IE.

[0211] As one embodiment, any of the M configuration messages includes the CSI-FrequencyOccupation IE.

[0212] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-FrequencyOccupation IE.

[0213] As one embodiment, any of the M configuration messages includes the CSI-ResourcePeriodicityAndOffset IE.

[0214] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-ResourcePeriodicityAndOffset IE.

[0215] As one embodiment, any of the M configuration messages includes the NZP-CSI-RS-ResourceSet IE.

[0216] As one embodiment, any of the M configuration messages includes one or more fields in the NZP-CSI-RS-ResourceSet IE.

[0217] As one embodiment, any of the M configuration messages includes the CSI-IM-Resource IE.

[0218] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-IM-Resource IE.

[0219] As one embodiment, any of the M configuration messages includes the CSI-IM-ResourceSet IE.

[0220] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-IM-ResourceSet IE.

[0221] As one embodiment, any of the M configuration messages includes the CSI-SSB-ResourceSet IE.

[0222] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-SSB-ResourceSet IE.

[0223] As one embodiment, any of the M configuration messages includes the CSI-ResourceConfig IE.

[0224] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-ResourceConfig IE.

[0225] As one embodiment, any of the M configuration messages includes the CSI-RS-ResourceConfigMobility IE.

[0226] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-RS-ResourceConfigMobility IE.

[0227] As one embodiment, any of the M configuration messages includes the CSI-ReportConfig IE.

[0228] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-ReportConfig IE.

[0229] As one embodiment, any of the M configuration messages includes the CSI-AperiodicTriggerStateList IE.

[0230] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-AperiodicTriggerStateList IE.

[0231] As one embodiment, any of the M configuration messages includes the CSI-AperiodicTriggerState IE.

[0232] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-AperiodicTriggerState IE.

[0233] As one embodiment, any of the M configuration messages includes the CSI-AssociatedReportConfigInfo IE.

[0234] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-AssociatedReportConfiglnfo IE.

[0235] As one embodiment, any of the M configuration messages includes the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0236] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0237] As one embodiment, any of the M configuration messages includes the CSI-SemiPersistentOnPUSCH-TriggerState IE.

[0238] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-SemiPersistentOnPUSCH-TriggerState IE.

[0239] As one embodiment, any of the M configuration messages includes the CSI-ReportSubConfigTriggerList IE.

[0240] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-ReportSubConfigTriggerList IE.

[0241] As one embodiment, any of the M configuration messages includes the CSI-ReportSubConfig IE.

[0242] As one embodiment, any of the M configuration messages includes one or more fields in the CSI-ReportSubConfig IE.

[0243] As one embodiment, any of the M configuration messages includes the LTM-CSI-ReportConfig IE.

[0244] As one embodiment, any of the M configuration messages includes one or more fields in the LTM-CSI-ReportConfig IE.

[0245] As one embodiment, the name of the RRC signaling used to transmit any of the M configuration messages comprises CSI.

[0246] As one embodiment, the name of the RRC signaling used to transmit any of the M configuration messages comprises CSI-RS.

[0247] As one embodiment, the name of the RRC signaling used to transmit any of the M configuration messages comprises Report.

[0248] As one embodiment, the name of the RRC signaling used to transmit any of the M configuration messages comprises Config.

[0249] As one embodiment, the M configuration messages are all used for prediction.

[0250] As one embodiment, the M configuration messages are all used for AI / ML inference.

[0251] As one embodiment, the M configuration messages are M prediction configuration messages, respectively.

[0252] As one embodiment, the M configuration messages are M parameters set messages, respectively.

[0253] As one embodiment, the M configuration messages are M beam configuration messages, respectively.

[0254] As one embodiment, the M configuration messages indicate the M RS resource groups, respectively.

[0255] As one embodiment, the M configuration messages configure the M RS resource groups, respectively.

[0256] As one embodiment, the M configuration messages correspond to the M RS resource groups one-to-one.

[0257] As one embodiment, any of the M configuration messages indicates one RS resource group.

[0258] As one embodiment, any of the M configuration messages configures one RS resource group.

[0259] As one embodiment, any of the M configuration messages indicates one of the M RS resource groups.

[0260] As an embodiment, any of the M configuration messages configures one of the M RS resource groups.

[0261] As an embodiment, the M RS resource groups respectively correspond to M beams.

[0262] As an embodiment, the M RS resource groups respectively correspond to M RS resource sets.

[0263] As an embodiment, each of the M configuration messages indicates a period of measurement of the corresponding RS resource group.

[0264] As an embodiment, each of the M configuration messages indicates a period of measurement of each RS resource in the corresponding RS resource group.

[0265] As an embodiment, each of the M configuration messages indicates RS resources included in the corresponding RS resource group.

[0266] As an embodiment, each of the M configuration messages indicates configuration information of RS resources included in the corresponding RS resource group.

[0267] As an embodiment, the configuration information of the RS resource in the present application includes some or all of time domain resource, frequency domain resource, CDM (Code Division Multiplexing) type, CDM group, RS sequence, scrambling code, period, slot offset, QCL relationship, TCI (Transmission Configuration Indicator) state, density, or CSI-RS (Channel State Information Reference Signal) port quantity.

[0268] As an embodiment, each of the M configuration messages includes one reporting configuration.

[0269] As an embodiment, the M configuration messages respectively indicate M reporting configurations.

[0270] As an embodiment, each of the M configuration messages indicates a reporting configuration for RS resources included in the corresponding RS resource group.

[0271] As an embodiment, the reporting configuration of the RS resource in the present application includes one or more of the following: a time domain resource, a frequency domain resource, a codebook, a channel occupied, a CSI type.

[0272] As a sub-embodiment of the embodiment, the candidate of the CSI type includes one or more of the following: L1-RSRP, CRI, RI, PMI, CQI, LI, SSB-Index, SSBRI, SINR, L1-SINR, Capability Index, Capability Set Index.

[0273] As an embodiment, any of the M RS resource groups includes one or more RS resources.

[0274] As an embodiment, at least one of the M RS resource groups includes only one RS resource, and at least one of the M RS resource groups includes multiple RS resources.

[0275] As an embodiment, the RS resource group includes only one RS resource.

[0276] As an embodiment, the RS resource group includes multiple RS resources.

[0277] As an embodiment, at least one of the M RS resource groups includes only one RS resource.

[0278] As an embodiment, at least one of the M RS resource groups includes multiple RS resources.

[0279] As one subembodiment of the embodiment, the multiple RS resources included in the one RS resource group belong to different RS resource sets.

[0280] As one subembodiment of the embodiment, there are at least two RS resources in the multiple RS resources included in the one RS resource group corresponding to different NZP-CSI-RS-ResourceSetId.

[0281] As one subembodiment of the embodiment, the multiple RS resources included in the one RS resource group belong to the same RS resource set.

[0282] As one subembodiment of the embodiment, the multiple RS resources included in the one RS resource group correspond to the same NZP-CSI-RS-ResourceSetId.

[0283] As one embodiment, the RS resources included in any RS resource group of the M RS resource groups belong to one RS resource set.

[0284] As one embodiment, the RS resource in the present application is periodic.

[0285] As one embodiment, the RS resource in the present application is semi-persistent.

[0286] As one embodiment, the RS resource in the present application includes an antenna port.

[0287] As one embodiment, the RS resource in the present application includes a reference signal port.

[0288] As one embodiment, the RS resource in the present application includes a CSI-RS port.

[0289] As one embodiment, the RS resource in the present application is one of a CSI-RS resource or an SSB.

[0290] As one embodiment, the RS resource in the present application includes a CSI-RS resource.

[0291] As one embodiment, the RS resource in the present application is a CSI-RS resource.

[0292] As one embodiment, the RS resource in the present application includes a NZP (Non-Zero Power) CSI-RS resource.

[0293] As one embodiment, the RS resource in the present application is a NZP CSI-RS resource.

[0294] As an embodiment, one RS resource in the present application corresponds to one CSI-RS resource ID.

[0295] As an embodiment, one RS resource in the present application corresponds to one NZP-CSI-RS-Resource ID.

[0296] As an embodiment, the RS resource in the present application includes SSB.

[0297] As an embodiment, the RS resource in the present application is SSB.

[0298] As an embodiment, one RS resource in the present application corresponds to one SSB-Index.

[0299] As an embodiment, one RS resource in the present application corresponds to one ssb-Index.

[0300] As an embodiment, the SSB in the present application refers to Synchronization Signal Block.

[0301] As an embodiment, the SSB in the present application refers to SS (Synchronization Signal) / PBCH (Physical Broadcast Channel) block.

[0302] Typically, the receiving occasions of the PBCH, PSS (Primary Synchronization Signal) and SSS (Secondary Synchronization Signal) are in consecutive symbols, and form an SS / PBCH block.

[0303] As an embodiment, when the RS resources included in the RS resource group are CSI-RS resources or SSBs, the above method has good forward compatibility; however, in order to adapt to the performance requirements of future wireless networks such as 6G, the signals included in the RS resource group may also be other types of RSs to better meet the performance requirements of measurement reporting.

[0304] As an embodiment, the RS resources included in each of the M RS resource groups are one of CSI-RS resources or SSBs.

[0305] As one embodiment, any of the M RS resource groups is a CSI-RS resource group or is a SSB group.

[0306] As one embodiment, any of the M RS resource groups is a CSI-RS resource group.

[0307] As one embodiment, any of the M RS resource groups is a SSB group.

[0308] As one embodiment, the first node computes the first parameter for each of the M configuration messages.

[0309] As one embodiment, the first node computes M first parameters, the M first parameters being for the M configuration messages, respectively.

[0310] As one sub-embodiment of this embodiment, the M first parameters are used for M predicted performance monitoring corresponding to the M configuration messages, respectively.

[0311] As one sub-embodiment of this sub-embodiment, the M predictions correspond to M prediction sub-models, respectively.

[0312] As one sub-embodiment of this sub-embodiment, the M predictions correspond to M prediction functions of one model, respectively.

[0313] As one sub-embodiment of this sub-embodiment, the M predictions correspond to M prediction targets of one model, respectively.

[0314] As one sub-embodiment of this sub-embodiment, the M predictions correspond to M prediction tasks of one model, respectively.

[0315] As one embodiment, the first parameter corresponds to a performance metric.

[0316] As one embodiment, the first parameter corresponds to a KPI (Key Performance Indicator).

[0317] As one embodiment, the first parameter is an intermediate KPI.

[0318] As one embodiment, the first parameter is an eventual KPI.

[0319] As one embodiment, the first parameter is used for performance monitoring of one of the M configuration messages.

[0320] As one embodiment, the first parameter is used for performance monitoring of measurements indicated by one of the M configuration messages.

[0321] As one embodiment, signaling carrying the M configuration messages indicates the first parameter.

[0322] As one embodiment, each of the M configuration messages indicates the first parameter.

[0323] As one embodiment, candidates of the first parameter include one or more of GCS (Generalized Cosine Similarity), SGSC (Squared Generalized Cosine Similarity), NMSE (Normalized Mean Squared Error), truth ground CSI, equivalent MSE (equivalent Mean Squared Error), and numerical spectral efficiency gap.

[0324] As one embodiment, candidates of the first parameter include one or more of throughput, BLER (Block Error Rate), hypothetical BLER.

[0325] As one embodiment, the first parameter is NMSE.

[0326] As one embodiment, the first parameter is SGCS.

[0327] As one embodiment, the first parameter is truth ground CSI.

[0328] As one embodiment, any of the M configuration messages indicates measurements for the corresponding RS resource group.

[0329] As one embodiment, computation of the first parameter relies on measurements for the RS resource group indicated by the corresponding configuration message.

[0330] As one embodiment, the measurements comprise measurements for at least one of RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), RSSI (Received Signal Strength Indicator) and SNR (Signal To Noise Ratio).

[0331] As one embodiment, the measurements comprise measurements for RSRP.

[0332] As one embodiment, the measurements comprise measurements for RSRQ.

[0333] As one embodiment, the measurements comprise measurements for RSSI.

[0334] As one embodiment, the measurements comprise measurements for SNR.

[0335] As one embodiment, the first node performs the calculation of the first parameter in relation.

[0336] As one embodiment, the first node obtains the first parameter by comparing results of measurements for the RS resource sets indicated by the respective configuration messages and prediction results resulting from the respective configuration messages.

[0337] As one embodiment, the first node obtains the first parameter by calculating a difference between results of measurements for the RS resource sets indicated by the respective configuration messages and prediction results resulting from the respective configuration messages.

[0338] As one embodiment, the first node obtains the first parameter by calculating a Euclidean metric between results of measurements for the RS resource sets indicated by the respective configuration messages and prediction results resulting from the respective configuration messages.

[0339] As one embodiment, the first configuration message is one of the M configuration messages.

[0340] As one embodiment, the M configuration messages comprise the first configuration message.

[0341] As one embodiment, a calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message.

[0342] As an embodiment, the computation time comprises a measurement period of the RS resource group indicated by the corresponding configuration message.

[0343] As an embodiment, the computation time comprises a period of measurement result computation of the RS resource group according to the corresponding configuration message.

[0344] As an embodiment, the computation time comprises a period of computation.

[0345] As an embodiment, the computation time comprises an occupation time of computing power.

[0346] As an embodiment, the computation time comprises an occupation time of CPU.

[0347] As an embodiment, the computation time comprises an occupation time of APU.

[0348] As an embodiment, the computation time comprises an occupation time of NPU (Neural Processing Unit).

[0349] As an embodiment, the CPU in the present application refers to CSI Processing Unit.

[0350] As an embodiment, the CPU in the present application refers to Central Processing Unit.

[0351] As an embodiment, the APU in the present application refers to AI Processing Unit.

[0352] As an embodiment, the APU in the present application refers to Accelerated Processing Unit.

[0353] As an embodiment, the computation time of the first parameter corresponding to the first configuration message depends on the first configuration message.

[0354] As an embodiment, the computation time of the first parameter corresponding to the first configuration message depends on which one of the candidates of the first parameter in the present application the first parameter is.

[0355] As an embodiment, the computation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to the first configuration message and one configuration message other than the first configuration message.

[0356] As an embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the calculation result of the first parameter corresponding to the first configuration message and one configuration message other than the first configuration message.

[0357] As an embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message other than the first configuration message in the M configuration messages, and the first configuration message and the second configuration message are consistent; the consistency includes at least one of the following:

[0358] -the RS resource group indicated by the first configuration message and the RS resource group indicated by the second configuration message are QCL;

[0359] -the speed applied by the first configuration message and the speed applied by the second configuration message are the same;

[0360] -the first configuration message and the second configuration message indicate the same RS resource group;

[0361] -the first configuration message and the second configuration message correspond to the same spatial parameter.

[0362] As an embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message other than the first configuration message in the M configuration messages, and the RS resource group indicated by the first configuration message and the RS resource group indicated by the second configuration message are QCL.

[0363] As an embodiment, the QCL in the present application refers to Quasi Co-Location.

[0364] As an embodiment, the QCL in the present application refers to Quasi Co-Located.

[0365] As an embodiment, the QCL in the present application includes QCL parameters.

[0366] As an embodiment, the QCL in the present application includes QCL assumptions.

[0367] As an embodiment, the QCL type in the present application includes TypeA, TypeB, TypeC and TypeD.

[0368] As an embodiment, the QCL parameters of the QCL Type A in the present application comprise at least one of Doppler shift, Doppler spread, average delay, delay spread, spatial Tx parameter or spatial Rx parameter.

[0369] As an embodiment, the QCL parameters of the QCL Type A in the present application comprise at least one of Doppler shift, Doppler spread, average delay, delay spread, spatial Tx parameter or spatial Rx parameter.

[0370] As an embodiment, the Type A, the Type B, the Type C and the Type D in the present application are defined in clause 5.1.5 of 3GPP TS 38.214.

[0371] As an embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message among the M configuration messages and other than the first configuration message, and the speed range to which the first configuration message applies is the same as the speed range to which the second configuration message applies.

[0372] As a sub-embodiment of the embodiment, the speed corresponds to a given speed.

[0373] As a sub-embodiment of the embodiment, the speed corresponds to a given speed range, and the speed range comprises an upper limit speed and a lower limit speed.

[0374] As an embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message among the M configuration messages and other than the first configuration message, and the first configuration message and the second configuration message indicate the same RS resource group.

[0375] As one embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message among the M configuration messages and other than the first configuration message, the first configuration message and the second configuration message correspond to the same spatial parameter.

[0376] As one sub-embodiment of this embodiment, the spatial parameter includes a spatial reception parameter.

[0377] As one sub-embodiment of this embodiment, the spatial parameter includes a spatial transmission parameter.

[0378] As one sub-embodiment of this embodiment, the spatial parameter includes a TCI.

[0379] As one sub-embodiment of this embodiment, the spatial parameter includes a TCI State.

[0380] As one sub-embodiment of this embodiment, the spatial parameter includes a TCI-StateId.

[0381] Embodiment 2

[0382] Embodiment 2 illustrates a schematic diagram of a network architecture according to one embodiment of the present application, as shown in FIG. 2.

[0383] FIG. 2 illustrates a network architecture 200. The network architecture 200 is a network architecture for LTE (Long-Term Evolution), LTE-A (Long-Term Evolution Advanced), 5G systems, 5G-Advanced, and future 6G systems. The network architecture for LTE, LTE-A, 5G systems, 5G-Advanced, and future 6G systems is referred to as EPS (Evolved Packet System). The 5G NR or LTE network architecture can be referred to as 5GS (5G System) / EPS or some other suitable terminology; the 6G network architecture can be referred to as 6GS (6G System) / EPS or some other suitable terminology. The network architecture 200 can include one or more UEs 201, a RAN (Next Generation Radio Access Network) 202, a core network 210, a HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet services 230. The network architecture 200 can be interconnected with other access networks, but these entities / interfaces are not shown for simplicity. As shown in FIG. 2, the network architecture 200 provides packet-switched services, however, those skilled in the art will readily appreciate that the various concepts presented throughout this application are amenable to use with networked systems providing circuit-switched services. The RAN 202 includes Node Bs 203 and other nodes 204. The Node Bs 203 provide user and control plane protocol terminations toward the UEs 201. The Node Bs 203 can be connected to the other nodes 204 via an Xn interface (e.g., backhaul). The Node Bs 203 can also be referred to as base stations, base transceiver stations, radio base stations, radio transceivers, transceiver functions, basic service sets (BSSs), extended service sets (ESSs), TRPs (Transmitter Receiver Points), or some other suitable terminology. The Node Bs 203 provide access points to the core network 210 for the UEs 201; the core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or alternatively, the core network 210 is a 6GC.Examples of a UE 201 include a cellular phone, a smart phone, a Session Initiation Protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., MP3 player), a camera, a game console, a drone, a flying vehicle, a narrowband physical web device, a machine type communication device, a land transport vehicle, a car, a wearable device, or any other similar functional device. Those skilled in the art will also The node 203 is connected by an SI / NG interface to the core network 210. The core network 210 includes a MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MME / AMF / SMF 214, a S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that processes the signaling between the UE 201 and the 5G-CN / EPC 210. The MME / AMF / SMF 211 generally provides bearer and connection management. All user Internet Protocol (IP) packets are transferred through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation as well as other functions. The P-GW / UPF 213 is connected to the Internet services 230. The Internet services 230 include operator- correspondent Internet Protocol services, which can specifically include the Internet, intranet, IMS (IP Multimedia Subsystem), and packet-switched services.

[0384] As one embodiment, the first node described in this application includes the UE 201.

[0385] As one embodiment, the second node described in the present application comprises the node 203.

[0386] As one embodiment, the node 203 is a Macro Cell base station.

[0387] As one embodiment, the node 203 is a Micro Cell base station.

[0388] As one embodiment, the node 203 is a Pico Cell base station.

[0389] As one embodiment, the node 203 is a Femto Cell base station.

[0390] As one embodiment, the node 203 is a base station device supporting large latency difference.

[0391] As one embodiment, the node 203 is a flying platform device.

[0392] As one embodiment, the node 203 is a satellite device.

[0393] As one embodiment, the node 203 is a test device (e.g. a transceiver simulating part of the functions of a base station, a signaling tester).

[0394] As one embodiment, the UE 201 comprises a mobile phone.

[0395] As one embodiment, the UE 201 comprises a vehicle, including a car.

[0396] As one embodiment, the wireless link from the UE 201 to the node 203 is an uplink, which is used to perform uplink transmission.

[0397] As one embodiment, the wireless link from the node 203 to the UE 201 is a downlink, which is used to perform downlink transmission.

[0398] As one embodiment, the wireless link between the node 203 and the UE 201 comprises a cellular network link.

[0399] As one embodiment, the node 203 and the UE 201 are connected through a Uu air interface.

[0400] As one embodiment, the sender of the M configuration messages described in the present application comprises the node 203.

[0401] As an embodiment, the receiver of the M configuration messages in the present application comprises the UE 201.

[0402] As an embodiment, the sender of the first parameter in the present application comprises the UE 201.

[0403] As an embodiment, the receiver of the first parameter in the present application comprises the node 203.

[0404] As an embodiment, the sending of the first parameter in the present application is implemented inside the UE 201.

[0405] As an embodiment, the sender of the predicted channel information in the present application comprises the UE 201.

[0406] As an embodiment, the receiver of the predicted channel information in the present application comprises the node 203.

[0407] As an embodiment, the node 203 supports the deployment of a Network-side (NW-side) AI / ML model.

[0408] As an embodiment, the UE 201 supports the deployment of a UE-side AI / ML model.

[0409] As an embodiment, the UE 201 supports a 5G system.

[0410] As an embodiment, the node 203 supports a 5G system.

[0411] As an embodiment, the UE 201 supports at least a 6G system.

[0412] As an embodiment, the node 203 supports at least a 6G system.

[0413] Embodiment 3

[0414] Embodiment 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture of a user plane and a control plane according to an embodiment of the present application, as shown in FIG. 3.

[0415] Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300, Figure 3 shows the radio protocol architecture for the control plane 300 between a first communication node device (UE or RSU (Road Side Unit) in V2X (Vehicle to Everything), a vehicle mounted device or a vehicle mounted communication module) and a second node device (gNB, UE or RSU in V2X, a vehicle mounted device or a vehicle mounted communication module), or between two UEs, using three layers: Layer 1 (L1), Layer 2 (L2) and Layer 3 (L3). L1 is the lowest layer and implements various PHY (PHYsical layer) signal processing functions. L1 will be referred to as the PHY 301 herein. Layer 2 305 is above the PHY 301 and is responsible for the link between the first node device and the second node device, or between two UEs, through the PHY 301. Layer 2 305 includes a MAC (Medium Access Control) sublayer 302, a RLC (Radio Link Control) sublayer 303 and a PDCP (Packet Data Convergence Protocol) sublayer 304, which are terminated at the second node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. The PDCP sublayer 304 also provides security, by encrypting data packets, and handover support for the first communication node device between second communication node devices. The RLC sublayer 303 provides segmentation and reassembly of upper layer data packets, retransmission of lost data packets, and reordering of data packets to compensate for out-of-order reception due to HARQ (Hybrid Automatic Repeat reQuest). The MAC sublayer 302 provides multiplexing between logical and transport channels. The MAC sublayer 302 is also responsible for allocating the various radio resources (e.g., resource blocks) in one cell among the UEs. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in Layer 3 in the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second communication node device and the first communication node device.The radio protocol architecture of the user plane 350 includes Layer 1 (L1) and Layer 2 (L2), which are substantially the same as the corresponding layers and sublayers in the control plane 300 for the first communication node device and the second communication node device, for the physical layer 351, the PDCP sublayer 354 in L2 355, the RLC sublayer 353 in L2 355, and the MAC sublayer 352 in L2 355, but the PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead. Also included in L2 355 in the user plane 350 is the SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between QoS (Quality of Service) flows and data radio bearers (DRBs) to support diverse traffic types. Although not illustrated, the first communication node device can have several upper layers above L2 355, including a network layer (e.g., IP (Internet Protocol) layer) that terminates at the P-GW on the network side and an application layer that terminates at the other end of the connection (e.g., a remote UE, a server, etc.).

[0416] As one embodiment, the radio protocol architecture in FIG. 3 is applicable to the first node in the present application.

[0417] As one embodiment, the radio protocol architecture in FIG. 3 is applicable to the second node in the present application.

[0418] As one embodiment, the M configuration messages in the present application are generated at the RRC 306.

[0419] As one embodiment, the M first parameters in the present application are generated at the MAC 302 or the MAC 352.

[0420] As one embodiment, the M first parameters in the present application are generated at the PHY 301 or the PHY 351.

[0421] As one embodiment, the higher layer in the present application refers to a layer above the physical layer.

[0422] As one embodiment, the higher layer in the present application includes the RRC layer.

[0423] As one embodiment, the higher layer signaling in the present application includes the RRC IE.

[0424] As one embodiment, the higher layer signaling in the present application includes the RRC message.

[0425] As one embodiment, the higher layer described in the present application comprises a MAC layer.

[0426] As one embodiment, the higher layer signaling described in the present application comprises a MAC CE.

[0427] Embodiment 4

[0428] Embodiment 4 illustrates a schematic diagram of a first communication device and a second communication device according to one embodiment of the present application, as shown in FIG. 4. FIG. 4 is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0429] The first communication device 410 comprises a controller / processor 475, a memory 476, a receive processor 470, a transmit processor 416, a multi-antenna receive processor 472, a multi-antenna transmit processor 471, a transmitter / receiver 418 and an antenna 420.

[0430] The second communication device 450 comprises a controller / processor 459, a memory 460, a data source 467, a transmit processor 468, a receive processor 456, a multi-antenna transmit processor 457, a multi-antenna receive processor 458, a transmitter / receiver 454 and an antenna 452.

[0431] In transmissions from the first communication device 410 to the second communication device 450, at the first communication device 410, upper layer packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements functionality of L2. In DL, the controller / processor 475 provides header compression, ciphering, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocations for second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the second communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for Ll (i.e., physical layer). The transmit processor 416 implements coding and interleaving to facilitate forward error correction (FEC) at the second communication device 450 and mapping onto signal constellations based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-ary phase shift keying (M-PSK), M-ary quadrature amplitude modulation (M-QAM)). The multi-antenna transmit processor 471 performs digital spatial pre-coding of the coded and modulated symbols, including codebook-based and non-codebook-based pre-coding and beamforming processing, to generate one or more parallel streams. The transmit processor 416 then maps to each of the parallel streams to subcarriers, multiplexes the modulated symbols in time domain and / or frequency domain with reference signals (e.g., pilot) and then performs an inverse fast Fourier transform (IFFT) to generate time domain multicarrier symbol streams. The multi-antenna transmit processor 471 then performs transmit analog pre-coding / beamforming operations on the time domain multicarrier symbol streams. Each transmitter 418 converts the baseband multicarrier symbol streams provided by the multi-antenna transmit processor 471 into radio frequency signals that are transmitted via the corresponding antennas 420.

[0432] In transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its respective antenna 452. Each receiver 454 recovers information modulated onto an RF carrier and converts the RF stream into a baseband multi-carrier symbol stream that provides to the receive processor 456. The receive processor 456 and the multi-antenna receive processor 458 implement various signal processing functions of the LI. The multi-antenna receive processor 458 performs receive analog precoding / beamforming operation on the baseband multi-carrier symbol stream from the receivers 454. The receive processor 456 converts the baseband multi-carrier symbol stream from the receive analog precoding / beamforming operation from the time domain to the frequency domain using a Fast Fourier Transform (FFT). In the frequency domain, the physical layer data signals and the reference signals are demultiplexed by the receive processor 456, where the reference signals will be used for channel estimation, and the data signals are recovered after multi-antenna detection in the multi-antenna receive processor 458 for any parallel streams destined to the second communication device 450. The symbols on each parallel stream are demodulated and recovered in the receive processor 456 and generate soft decisions. The receive processor 456 then decodes and de-interleaves the soft decisions to recover the upper layer data and control signals transmitted by the first communication device 410 on the physical channels. The upper layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of the L2. The controller / processor 459 can be associated with a memory 460 that stores program codes and data. The memory 460 can be referred to as a computer-readable medium. In the DL, the controller / processor 459 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer data packets from the core network. The upper layer data packets are then provided to all protocol layers above the L2. Various control signals can also be provided to the L3 for L3 processing. The controller / processor 459 is also responsible for error detection using an ACK and / or negative ACK (NACK) protocol to support HARQ operations.

[0433] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper layer packets to a controller / processor 459. The data source 467 represents all protocol layers above L2. Similar to the transmit function described at the first communication device 410 in the DL, the controller / processor 459 implements header compression, ciphering, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocations for the first communication device 410, implements L2 layer functionality for the user plane and control plane. The controller / processor 459 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the first communication device 410. A transmit processor 468, in conjunction with a multi-antenna transmit processor 457, performs modulation mapping, channel coding processing, digital multi-antenna spatial pre-coding including codebook-based and non-codebook-based precoding, and beamforming processing, and then the transmit processor 468 generates parallel streams of symbols that are modulated onto different carriers, and the modulated symbol streams are then provided to different antennas 452 via transmitters 454 after analog pre-coding / beamforming operations in the multi-antenna transmit processor 457. Each transmitter 454 converts a baseband symbol stream into a radio frequency signal that is transmitted via the corresponding antenna 452.

[0434] In the transmission from the second communication device 450 to the first communication device 410, the functionality at the first communication device 410 is similar to the functionality described in connection with the reception at the second communication device 450 in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives a radio frequency signal through its respective antenna 420, converts the received radio frequency signal into a baseband signal, and provides the baseband signal to a multi-antenna receive processor 472 and a receive processor 470. The receive processor 470 and the multi-antenna receive processor 472 together implement L1 functionality. A controller / processor 475 implements L2 functionality. The controller / processor 475 can be associated with a memory 476 that stores program codes and data. The memory 476 can be referred to as a computer-readable medium. The controller / processor 475 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer packets from the second communication device 450. Upper layer packets from the controller / processor 475 can be provided to a core network. The controller / processor 475 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.

[0435] As one embodiment, the second communication device 450 comprises: at least one processor and at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the performance of the following actions. The second communication device 450 is configured to receive at least the M configuration messages as described in the present application, the M configuration messages respectively indicating M RS resource groups, any of the M RS resource groups comprising one or more RS resources, the M being a positive integer greater than 1; for each of the M configuration messages, compute the first parameter as described in the present application; the computation of the first parameter relies on the measurement of the RS resource group indicated for the respective configuration message; the first configuration message is one of the M configuration messages; the computation time of the first parameter corresponding to the first configuration message relies on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message.

[0436] As one embodiment, the second communication device 450 comprises: a memory storing a computer readable program of instructions which, when executed by at least one processor, causes the performance of the following actions. The actions comprise: receiving at least the M configuration messages as described in the present application; for each of the M configuration messages, computing the first parameter as described in the present application.

[0437] As one embodiment, the first communication device 410 comprises: at least one processor and at least one memory including computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the performance of the following actions. The first communication device 410 is configured to transmit at least the M configuration messages as described in the present application, the M configuration messages respectively indicating M RS resource groups, any of the M RS resource groups comprising one or more RS resources, the M being a positive integer greater than 1; the receiver of the M configuration messages is the second communication device 450; for each of the M configuration messages, the second communication device 450 is configured to compute a first parameter; the computation of the first parameter relies on the measurement of the RS resource group indicated for the respective configuration message; the first configuration message is one of the M configuration messages; the computation time of the first parameter corresponding to the first configuration message relies on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message.

[0438] As one embodiment, the first communication device 410 comprises a memory that stores a program of computer readable instructions to produce an action when executed by at least one processor, the action comprising transmitting the M configuration messages in the present application.

[0439] As one embodiment, the first node in the present application comprises the second communication device 450.

[0440] As one embodiment, the second node in the present application comprises the first communication device 410.

[0441] As one embodiment, at least one of {the antenna 420, the transmitter 418, the transmit processor 416, the multi-antenna transmit processor 471, the controller / processor 475, the memory 476} is configured to transmit the M configuration messages in the present application; at least one of {the antenna 452, the receiver 454, the receive processor 456, the multi-antenna receive processor 458, the controller / processor 459, the memory 460, the data source 467} is configured to receive the M configuration messages in the present application.

[0442] As one embodiment, at least one of {the antenna 452, the transmitter / receiver 454, the transmit processor 468, the receive processor 456, the multi-antenna transmit processor 457, the multi-antenna receive processor 458, the controller / processor 459, the memory 460, the data source 467} is configured to compute the first parameter in the present application for the each of the M configuration messages;

[0443] As one embodiment, at least one of {the antenna 452, the transmitter / receiver 454, the transmit processor 468, the receive processor 456, the multi-antenna transmit processor 457, the multi-antenna receive processor 458, the controller / processor 459, the memory 460, the data source 467} is configured to transmit the first parameter in the present application for the each of the M configuration messages; at least one of {the antenna 420, the receiver 418, the receive processor 470, the multi-antenna receive processor 472, the controller / processor 475, the memory 476} is configured to receive the first parameter in the present application for the each of the M configuration messages.

[0444] As an embodiment, at least one of {the antenna 452, the transmitter / receiver 454, the transmit processor 468, the receive processor 456, the multi-antenna transmit processor 457, the multi-antenna receive processor 458, the controller / processor 459, the memory 460, the data source 467} is configured to calculate the predicted channel information according to the reporting configuration of each of the M configuration messages.

[0445] As an embodiment, at least one of {the antenna 452, the transmitter / receiver 454, the transmit processor 468, the receive processor 456, the multi-antenna transmit processor 457, the multi-antenna receive processor 458, the controller / processor 459, the memory 460, the data source 467} is configured to transmit the predicted channel information according to the reporting configuration of each of the M configuration messages; at least one of {the antenna 420, the receiver 418, the receive processor 470, the multi-antenna receive processor 472, the controller / processor 475, the memory 476} is configured to receive the predicted channel information according to the reporting configuration of each of the M configuration messages.

[0446] Embodiment 5

[0447] Embodiment 5 illustrates a flowchart of the transmission between the first node and the second node according to an embodiment of the present application, as shown in FIG. 5. In FIG. 5, the first node U1 communicates with the second node N2 through a wireless link. It is particularly explained that the sequence in this embodiment does not limit the sequence of signal transmission and implementation in the present application.

[0448] For the first node U1, M configuration messages are received in step S510; for each of the M configuration messages, a first parameter is calculated in step S511.

[0449] For the second node N2, the M configuration messages are transmitted in step S520.

[0450] In embodiment 5, the M configuration messages respectively indicate M RS resource groups, any RS resource group of the M RS resource groups includes one or more RS resources, the M is a positive integer greater than 1; the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message; the first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages and other than the first configuration message.

[0451] As one embodiment, the first node U1 is the first node as described in the present application.

[0452] As one embodiment, the second node N2 is the second node as described in the present application.

[0453] As one embodiment, the air interface between the second node N2 and the first node U1 comprises a wireless interface between a base station device and a user equipment device.

[0454] As one embodiment, the air interface between the second node N2 and the first node U1 comprises a wireless interface between a relay node device and a user equipment device.

[0455] As one embodiment, the air interface between the second node N2 and the first node U1 comprises a wireless interface between a user equipment device and a user equipment device.

[0456] As one embodiment, the second node N2 and the first node U1 communicate over a Uu interface.

[0457] As one embodiment, the second node N2 is a serving cell maintaining base station of the first node U1.

[0458] As one embodiment, the transport channel occupied by the M configuration messages comprises a DL-SCH (DownLink-Shared CHannel).

[0459] As one embodiment, the physical layer channel occupied by the M configuration messages comprises a PDSCH (Physical Downlink Shared CHannel).

[0460] As one embodiment, the M configuration messages occupy at least one PDSCH.

[0461] As one embodiment, the M configuration messages occupy one PDSCH.

[0462] As one embodiment, the M configuration messages are transmitted on one PDSCH, and the step S510 comprises receiving the one PDSCH.

[0463] As one embodiment, the M configuration messages are transmitted on multiple PDSCHs, and the step S510 comprises receiving the multiple PDSCHs.

[0464] As one embodiment, the step S510 precedes the step S511.

[0465] Embodiment 6

[0466] Embodiment 6 illustrates a flowchart of a first node sending a first parameter according to an embodiment of the present application, as shown in FIG. 6. In FIG. 6, each block represents a step.

[0467] The first node sends the first parameter corresponding to each of the M configuration messages in step 601.

[0468] As one embodiment, the first node sends M first parameters, which are respectively for the M configuration messages.

[0469] As one embodiment, the first node sends the first parameter only when the first parameter meets a given condition.

[0470] As one sub-embodiment of this embodiment, the first parameter meeting a given condition means that the performance corresponding to the first parameter is worse than a given threshold.

[0471] As one sub-embodiment of this embodiment, the first parameter meeting a given condition means that the first parameter is less than the first threshold in the present application.

[0472] As one sub-embodiment of this embodiment, the first parameter meeting a given condition means that the performance corresponding to the first parameter is worse than a given threshold and the duration of the performance reaching a preset duration; the preset duration is predefined or the preset duration is preconfigured.

[0473] As one sub-embodiment of this embodiment, the first parameter meeting a given condition means that the first parameter is less than the first threshold in the present application and the duration of the performance reaching a preset duration; the preset duration is predefined or the preset duration is preconfigured.

[0474] As one sub-embodiment of this embodiment, the first parameter meeting a given condition means that the performance corresponding to the first parameter is worse than a given threshold for a number of times reaching a target value; the target value is a positive integer, the target value is predefined or the target value is preconfigured.

[0475] As one sub-embodiment of this embodiment, the first parameter meeting a given condition means that the performance corresponding to the first parameter is worse than the first threshold in the present application for a number of times reaching a target value; the target value is a positive integer, the target value is predefined or the target value is preconfigured.

[0476] As a sub-embodiment of the embodiment, the meaning that the first parameters satisfy the given condition includes that the number of the first parameters in the M first parameters which are worse than the given threshold reaches a given value; the given value is a positive integer, and the given value is predefined or the target value is preconfigured.

[0477] As a sub-embodiment of the embodiment, the meaning that the first parameters satisfy the given condition includes that the number of the first parameters in the M first parameters which are worse than the given threshold reaches a given value; the given value is a positive integer, and the given value is predefined or the target value is preconfigured.

[0478] As an embodiment, the sending of the corresponding first parameters means sending the corresponding first parameters from a lower layer to a higher layer.

[0479] As an embodiment, the sending of the corresponding first parameters means sending the corresponding first parameters from a lower layer to a MAC entity.

[0480] As an embodiment, the sending of the corresponding first parameters means sending the corresponding first parameters from a lower layer to a MAC layer.

[0481] As an embodiment, the sending of the corresponding first parameters means sending the corresponding first parameters by a report.

[0482] As a sub-embodiment of the embodiment, the receiver of the report is the second node in the application.

[0483] As a sub-embodiment of the embodiment, the transmission channel occupied by the report includes an UL-SCH (UpLink-Shared CHannel).

[0484] As an embodiment, the sending of the corresponding first parameters means sending the corresponding first parameters by an air interface signal.

[0485] As a sub-embodiment of the embodiment, the physical layer channel occupied by the air interface signal includes a PUSCH (Physical Uplink Shared CHannel).

[0486] As a sub-embodiment of the embodiment, the physical layer channel occupied by the air interface signal includes a PUCCH (Physical Uplink Control CHannel).

[0487] As one sub embodiment of the embodiment, the M first parameters occupy at least one PUSCH.

[0488] As one sub embodiment of the embodiment, the M first parameters occupy at least one PUCCH.

[0489] As one sub embodiment of the embodiment, the M first parameters occupy one PUSCH.

[0490] As one sub embodiment of the embodiment, the M first parameters occupy one PUCCH.

[0491] As one sub embodiment of the embodiment, the M first parameters are transmitted on one PUSCH, and the step S601 comprises sending the one PUSCH.

[0492] As one sub embodiment of the embodiment, the M first parameters are transmitted on one PUCCH, and the step S601 comprises sending the one PUCCH.

[0493] As one sub embodiment of the embodiment, the M first parameters are transmitted on multiple PUSCHs, and the step S601 comprises sending the multiple PUSCHs.

[0494] As one sub embodiment of the embodiment, the M first parameters are transmitted on multiple PUCCHs, and the step S601 comprises sending the multiple PUCCHs.

[0495] As one embodiment, the M configuration messages respectively correspond to M IDs.

[0496] As one embodiment, the M configuration messages respectively correspond to M indexes.

[0497] As one embodiment, the M configuration messages respectively correspond to M identities.

[0498] As one embodiment, the first node sends an ID of a configuration message corresponding to the first parameters.

[0499] As one embodiment, the first node sends the first parameters and an ID of a configuration message corresponding to the first parameters.

[0500] As one embodiment, the step 601 is after the step S511 in FIG. 5.

[0501] Embodiment 7

[0502] Embodiment 7 illustrates a flowchart of a first node computing or sending predicted channel information according to an embodiment of the present application, as shown in FIG. 7. In FIG. 7, each block represents a step.

[0503] The first node computes or sends predicted channel information according to the reporting configuration of each of the M configuration messages in step 701.

[0504] In Embodiment 7, the predicted channel information depends on measurements on RS resource groups indicated by the corresponding configuration messages; the computation of the first parameter depends on the predicted channel information associated with the corresponding configuration message.

[0505] As one embodiment, the predicted channel information is predicted by AI / ML.

[0506] As one embodiment, the predicted channel information is reported by the report corresponding to the reporting configuration.

[0507] As one embodiment, the first node computes predicted channel information according to the reporting configuration of each of the M configuration messages.

[0508] As one embodiment, the first node sends predicted channel information according to the reporting configuration of each of the M configuration messages.

[0509] As one embodiment, the first node computes and sends predicted channel information according to the reporting configuration of each of the M configuration messages.

[0510] As one embodiment, the measurement on the RS resource group includes receiving RSs in the RS resource group to obtain RSRP corresponding to the RSs.

[0511] As one embodiment, the measurement on the RS resource group includes receiving RSs in the RS resource group to obtain RSRQ corresponding to the RSs.

[0512] As one embodiment, the measurement on the RS resource group includes receiving RSs in the RS resource group to obtain RSSI corresponding to the RSs.

[0513] As one embodiment, the measurement on the RS resource group includes receiving RSs in the RS resource group to obtain SNR corresponding to the RSs.

[0514] As one embodiment, the measurement on the RS resource group includes receiving RSs in the RS resource group to obtain compressed CSI corresponding to the RSs.

[0515] As an embodiment, the calculation of the first parameter relies on the predicted channel information associated with the respective configuration message and the measurement on the RS resource set indicated by the respective configuration message.

[0516] As an embodiment, the first parameter is equal to the NMSE between the predicted channel information associated with the respective configuration message and the measured channel information on the RS resource set indicated by the respective configuration message.

[0517] As an embodiment, the first parameter is equal to the SGCS between the predicted channel information associated with the respective configuration message and the measured channel information on the RS resource set indicated by the respective configuration message.

[0518] As an embodiment, the first parameter is equal to the Euclidean metric between the predicted channel information associated with the respective configuration message and the measured channel information on the RS resource set indicated by the respective configuration message.

[0519] As an embodiment, the first parameter is equal to the truth ground CSI corresponding to the predicted channel information associated with the respective configuration message.

[0520] As an embodiment, the step 701 is before the step S511 in FIG. 5.

[0521] As an embodiment, the step 701 is after the step S510 in FIG. 5.

[0522] Embodiment 8

[0523] Embodiment 8 illustrates a schematic diagram of a first entity according to an embodiment of the present application, as shown in FIG. 8. In FIG. 8, a communication system includes a first entity 801, a base station 802, a terminal 803 and a terminal device 804; wherein the terminal 803 and the terminal 804 can access the base station 802 respectively and communicate with the base station 802; it is worth noting that the present application embodiment does not limit the specific implementation of the first entity, the first entity 801 can be located at the network side and interact with network devices such as base stations, or be located inside the network device; it can also be located at the user side and interact with terminals, or be located inside the terminal.

[0524] In embodiment 8, the first entity in the present application includes the first entity 801 in FIG. 8, and the second node in the present application includes the base station 802.

[0525] As an embodiment, the M configuration messages are associated to the first entity.

[0526] As one embodiment, the first entity comprises the M configuration messages.

[0527] As one embodiment, the M configuration messages are all used to configure the first entity.

[0528] As one sub-embodiment of this embodiment, the M configuration messages are respectively used to configure M prediction sub-models comprised by the first entity.

[0529] As one sub-embodiment of this embodiment, the M configuration messages are respectively used to configure M prediction functionalities comprised by the first entity.

[0530] As one sub-embodiment of this embodiment, the M configuration messages are respectively used to configure M prediction targets comprised by the first entity.

[0531] As one sub-embodiment of this embodiment, the M configuration messages are respectively used to configure M prediction tasks comprised by the first entity.

[0532] As one embodiment, the first entity is used for AI / ML-based prediction, and the first entity comprises at least one of the following features:

[0533] - is an AI / ML model (model);

[0534] - is associated to an AI / ML model ID (model-Id);

[0535] - is associated to a Functionality ID;

[0536] - is associated to a data set;

[0537] - corresponds to an Associated ID.

[0538] As one embodiment, the ID in the present application refers to IDentify, proof.

[0539] As one embodiment, the ID in the present application refers to IDentification, identity proof.

[0540] As one embodiment, the ID in the present application refers to IDentity, identity or identifier.

[0541] As one embodiment, the ID in the present application refers to IDentifier, identifier.

[0542] As one embodiment, the ID in the present application refers to InDex, index.

[0543] As an embodiment, the first entity is an AI / ML model.

[0544] As an embodiment, the first entity is a model.

[0545] As an embodiment, the first entity is associated to an AI / ML model ID.

[0546] As an embodiment, the AI / ML model identified by the AI / ML model ID in this application can be logical, and the mapping relationship from the logical AI / ML model to the physical AI / ML model is usually implemented by the device manufacturer; and the AI / ML model ID corresponding to the same AI / ML model in different stages of LCM can be different, that is, the AI / ML model ID in this application can not be globally unique.

[0547] As an embodiment, the first entity is associated to a Functionality ID.

[0548] As an embodiment, the Functionality in this application refers to an AI / ML-enabled feature or Feature Group (FG) enabled by configuration, wherein the configuration is supported according to the UE capability indication.

[0549] As an embodiment, the first entity is associated to a data set.

[0550] As an embodiment, the first entity is associated to a training data set.

[0551] As an embodiment, the base station forwards the data related to the AI / ML model collected by itself or reported by the terminal to the first entity, and the first entity performs AI / ML-related operations such as construction of the training data set and model training, and the output of the AI / ML-related operations such as the trained AI / ML model, model evaluation, and test results are forwarded to each terminal through the base station.

[0552] As an embodiment, the terminal forwards the data related to the AI / ML model collected by itself or issued by the base station to the first entity, and the first entity performs AI / ML-related operations such as construction of the training data set and model training, and the output of the AI / ML-related operations such as the trained AI / ML model, model evaluation, and test results are forwarded to the base station through the terminal.

[0553] As an embodiment, the first entity corresponds to an Associated ID.

[0554] As an embodiment, in order to support AI / ML function in a wireless network, an AI / ML network element or module can be introduced in the network. If an AI / ML network element is introduced, it corresponds to a separate network element; if an AI / ML module is introduced, it can be located inside a certain network element, such as inside a terminal device or a network device, etc.

[0555] As an embodiment, the first entity is located inside a base station.

[0556] As an embodiment, the first entity is a module or function of a base station.

[0557] As an embodiment, the first entity is located inside a terminal.

[0558] As an embodiment, the first entity is a module or function of a terminal.

[0559] As an embodiment, one possible implementation of the first entity in the present application is that the first entity is deployed in a server or a cloud device of an Over The Top (OTT) system, and optionally, the cloud device is located in one or more of a user equipment side, a network equipment side, or a core network side.

[0560] Embodiment 9

[0561] Embodiment 9 illustrates a schematic diagram of configuration messages and target prediction according to an embodiment of the present application, as shown in FIG. 9. In FIG. 9, the M configuration messages correspond to the prediction of M different targets respectively.

[0562] In embodiment 9, the prediction of the M different targets includes at least one of the following:

[0563] - prediction of RSRP for L1;

[0564] - prediction of RSRP for L3;

[0565] - prediction for cell handover;

[0566] - prediction for mobility.

[0567] As an embodiment, the L1 refers to Layer 1.

[0568] As an embodiment, the L3 refers to Layer 3.

[0569] As an embodiment, the cell handover includes handover (HO).

[0570] As one embodiment, the cell handover comprises L1 / L2 Triggered Mobility (LTM).

[0571] As one embodiment, the M configuration messages respectively correspond to predictions of M different targets.

[0572] As one embodiment, the M configuration messages respectively indicate predictions of M different targets.

[0573] As one embodiment, the M configuration messages respectively indicate predictions for M different measurement objects.

[0574] As one embodiment, the predictions of the M different targets comprise predictions of RSRP for L1.

[0575] As one embodiment, the predictions of RSRP for L1 comprise predictions of SS-RSRP (Synchronization Signal Reference Signal Received Power).

[0576] As one embodiment, the predictions of RSRP for L1 comprise predictions of CSI-RSRP.

[0577] As one embodiment, the predictions of the M different targets comprise predictions of RSRP for L3.

[0578] As one embodiment, the predictions of RSRP for L3 comprise higher layer filtered RSRP.

[0579] As one embodiment, the predictions of the M different targets comprise predictions of RSRP for L1 and predictions of RSRP for L3.

[0580] As one embodiment, the predictions of the M different targets comprise predictions for RLF (Radio Link Failure).

[0581] As one embodiment, the predictions of the M different targets comprise predictions for RRM (Radio Resource Management).

[0582] As one embodiment, the predictions of the M different targets comprise predictions for cell handover.

[0583] As one embodiment, the predictions of the M different targets comprise predictions for mobility.

[0584] As one embodiment, the prediction of the M different targets comprises a prediction for cell handover and mobility.

[0585] As one embodiment, the prediction of the M different targets comprises a prediction for triggering of an Event.

[0586] As one sub-embodiment of this embodiment, the prediction of the event triggering comprises a prediction of sending of a measurement report.

[0587] Embodiment 10

[0588] Embodiment 10 illustrates a diagram of calculation time of a first parameter corresponding to a first configuration message according to one embodiment of the present application, as shown in FIG. 10.

[0589] In embodiment 10, when the first parameter corresponding to at least one configuration message other than the first configuration message is not lower than a first threshold, the calculation time of the first parameter is equal to a first time value; when the first parameter corresponding to at least one configuration message other than the first configuration message is lower than the first threshold, the calculation time of the first parameter is equal to a second time value; the first time value and the second time value are different.

[0590] As one embodiment, when the first parameter corresponding to at least one configuration message other than the first configuration message is not lower than a first threshold, the calculation time of the first parameter is equal to a first time value; when the first parameter corresponding to at least one configuration message other than the first configuration message is lower than the first threshold, the calculation time of the first parameter is equal to a second time value; the first time value and the second time value are different.

[0591] As one embodiment, the first threshold is fixed.

[0592] As one embodiment, the first threshold is predefined.

[0593] As one embodiment, the first threshold is configured by RRC signaling.

[0594] As one sub-embodiment of this embodiment, the signaling configuring the first entity in the present application simultaneously indicates the first threshold.

[0595] As one sub-embodiment of this embodiment, the signaling carrying the M configuration messages simultaneously indicates the first threshold.

[0596] As one sub-embodiment of this embodiment, the M configuration messages respectively indicate M first thresholds.

[0597] As an embodiment, the first parameter is confidence, and the first threshold corresponds to a number between 0 and 100.

[0598] As an embodiment, the first node periodically calculates the first parameter, and the first node receives at least one configuration message other than the first configuration message corresponding to the first parameter lower than the first threshold within the calculation time of the first parameter corresponding to the first configuration message, and the first node calculates the next first parameter calculation time to become the second time value.

[0599] As an embodiment, the period of the first node calculating the first parameter is the first time value, and when the first node receives at least one configuration message other than the first configuration message corresponding to the first parameter lower than the first threshold, the period of the first node calculating the first parameter corresponding to the first configuration message becomes the second time value.

[0600] As an embodiment, the second time value is not less than the first time value.

[0601] As an embodiment, the calculation time is the occupation time of CPU, and the second time value is equal to the first time value multiplied by a positive integer greater than 1.

[0602] As an embodiment, the calculation time is the occupation time of APU, and the second time value is equal to the first time value multiplied by a positive integer greater than 1.

[0603] As an embodiment, the calculation time is the occupation time of NPU, and the second time value is equal to the first time value multiplied by a positive integer greater than 1.

[0604] As an embodiment, the calculation time is the measurement period, and the first time value is equal to the second time value multiplied by a positive integer greater than 1.

[0605] As an embodiment, the calculation time is the period of measuring the calculation result, and the first time value is equal to the second time value multiplied by a positive integer greater than 1.

[0606] As an embodiment, the first time value is directly configured by the base station, and the second time value is predefined or implicitly indicated by base station signaling; a non-limiting implementation is:

[0607] The first node receives the RS resource sent by the second node in the present application and performs measurement and model inference on the corresponding RS resource. When the first parameter corresponding to at least one configuration message other than the first configuration message is lower than the first threshold value, the first node can set the calculation time for the first parameter to a second time value, the second time value is K times of the first time value K, the K is a positive integer greater than 1, the K is indicated by base station signaling, or the K is predefined, or the K is related to the implementation of the first node. The above scheme can save air interface resources, allow the terminal to adaptively adjust the measurement time of the first parameter, and optionally, the first node sets the calculation time of the first parameter to the first time value when it is monitored that the M first parameters corresponding to the M configuration messages are not lower than the first threshold value.

[0608] Another non-limiting implementation is that in the case that the first node sends the first parameter or sends information indicating the first parameter, the network, including the second node, simultaneously sets the period of the RS resource in the RS resource group corresponding to the first configuration message to a second time value, the second time value is not less than the first time value. The above scheme allows flexible configuration of the second time value, while establishing a consensus between the base station and the terminal. The base station can obtain more model performance information based on the air interface signal, which assists the base station to perform model selection / switching / activation / deactivation / backoff operation.

[0609] Embodiment 11

[0610] Embodiment 11 illustrates a schematic diagram of RAN domain AI / ML function deployment according to an embodiment of the present application, as shown in FIG. 11. In FIG. 11, gNB can be replaced by network devices such as eNB, or 6G base station, etc.

[0611] In embodiment 11, the management of the ML inference function of multiple base stations is completed by the RAN domain management function 1102, that is, data interaction is performed with the RAN domain MnS (Management Service) consumer / cross-domain management 1101 (as shown by the dashed arrow in FIG. 11). The RAN domain ML training function 1103 is located in the RAN domain management function 1102; while the ML inference function is located in the base station, that is, the AI / ML inference function 1104 is located in the gNB 1105, the AI / ML inference function 1106 is located in the gNB 1107, and so on.

[0612] AI / ML related functions include ML training function (also referred to as AI training, or AI / ML training), ML testing function, ML inference function (also referred to as AI inference, or AI / ML inference), etc. ML training function, ML testing function, ML inference function can be deployed independently, or co-located. Deployment of AI / ML related functions can be implemented by software, such as downloading and / or running of executable files; or by software combined with hardware, such as acceleration of specific computing units by hardware to improve operation speed or save power consumption.

[0613] For ML training function, it can be deployed in a cross-domain management system, or a domain-specific management system for managing RAN domain or CN (Core Network) domain. For example, ML training function 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), i.e. ML training function is MTLF (Model Training Logical Function).

[0614] For ML inference function, it can also be deployed in a cross-domain management system, or a domain-specific management system; for example, ML inference function is MDAF, or ML inference function is AnLF (Analytics Logical Function) in NWDAF.

[0615] Similarly, ML testing function can also be deployed in a cross-domain management system, or a domain-specific management system.

[0616] Optionally, management of ML inference function can also be completed by the base station itself, i.e. each base station can independently interact with RAN domain MnS consumer / cross-domain management 1101 for data.

[0617] It is noted that Embodiment 11 is just one non-limiting implementation; alternatively, the ML training function of the RAN domain can also be deployed at the base station; or alternatively, some base stations deploy both the ML inference function and the ML training function of the RAN domain, while some base stations only deploy the ML inference function.

[0618] As one embodiment, one gNB (or base station) in Embodiment 11 is the second node of the present application.

[0619] Embodiment 12

[0620] Embodiment 12 illustrates a schematic diagram of AI / ML function deployment of a UE according to one embodiment of the present application, as shown in FIG. 12. In FIG. 12, the RAN domain ML training function 1204 is optional.

[0621] The UE function 1203 is deployed in the first node of the present application, and the UE function 1203 includes the AI / ML inference function 1205; the AI / ML inference function 1205 uses a ML model (also referred to as an AI model) for inference; one ML model is usually trained before being used for AI / ML inference.

[0622] As one embodiment, the UE function 1203 includes the RAN domain ML training function 1204, which runs training data through a ML model to derive a related loss, and adjusts parameters of the ML model based on the calculated loss; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0623] The above embodiments can reduce the complexity of the base station, or save the air interface resources caused by reporting training data; however, the above embodiments put higher requirements on the processing capability of the UE side.

[0624] Alternatively, the UE function 1203 also includes a CN domain ML training function (not included in FIG. 12).

[0625] Alternatively, the UE function 1203 also includes an AI / ML deployment function (not included in FIG. 12) for loading ML models and data.

[0626] As one embodiment, the first node indicates whether the ML training function (RAN domain or CN domain) is supported through capability reporting, and the capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0627] As one embodiment, the ML model, and related metadata, is loaded by the first node from a network device or a remote server.

[0628] Optionally, the UE function 1203 is a MnS producer providing data to a CN domain MnF and / or a RAN domain MnF and / or a cross-domain management system 1201 for management or analytics (as indicated by double arrow 1202).

[0629] Optionally, the UE function 1203 is a MnS consumer loading data from a CN domain MnF and / or a RAN domain MnF and / or a cross-domain management system 1201 for AI / ML related management, e.g., management data requests, ML model activation, and / or ML training, etc. (as indicated by double arrow 1202).

[0630] As one embodiment, the ML model is based on NN (Neural Networks).

[0631] As one embodiment, the ML model is based on ANN (Artificial Neural Networks).

[0632] As one embodiment, the ML model is based on CNN (Convolutional Neural Networks).

[0633] As one embodiment, the ML model is based on LLM (Large Language Model) architecture.

[0634] As one embodiment, the ML model is based on Transformer architecture.

[0635] As one embodiment, the ML model is based on GPT (Generative Pre-Trained) architecture.

[0636] As one embodiment, the ML model is based on LSTM (Long Short-Term Memory).

[0637] As one embodiment, the ML model is based on MLP (MultiLayer Perceptron).

[0638] As one embodiment, the ML model is based on GAN (Generative Adversarial Nets).

[0639] As one embodiment, the ML model is based on a light-weight neural network.

[0640] As one sub-embodiment of this embodiment, the light-weight neural network includes one or more of MobileNet, ShuffleNet, and SqueezeNet.

[0641] Embodiment 13

[0642] Embodiment 13 illustrates a schematic diagram of an artificial intelligence or machine learning based processing system according to one embodiment of the present application, as shown in FIG. 13. In FIG. 13, the artificial intelligence or machine learning based processing system includes a first processing machine, a second processing machine, a third processing machine, and a fourth processing machine.

[0643] In embodiment 13, the first processing machine sends a first data set to the second processing machine, and sends a second data set to the third processing machine; the second processing machine generates a target first-type parameter group according to the first data set, and sends the generated target first-type parameter group to the third processing machine; the third processing machine processes the second data set using the target first-type parameter group to obtain a first-type output, and optionally, the third processing machine sends the first-type output to the fourth processing machine. In FIG. 13, a first-type feedback and a second-type feedback are optional; the second processing machine includes an ML training function; and the third processing machine includes an ML inference function.

[0644] As one embodiment, the fourth processing machine includes an ML testing function.

[0645] As one embodiment, the fourth processing machine includes performance monitoring / evaluation of the ML model.

[0646] As one embodiment, the third processing machine sends a first-type feedback to the second processing machine; the first-type feedback is used to trigger re-computation or update of the target first-type parameter group, i.e., trigger ML initial training or ML re-training.

[0647] As one embodiment, the fourth processing machine sends a second-type feedback to the first processing machine; the second-type feedback is used to generate the first data set or the second data set, or the second-type feedback is used to trigger sending of the first data set or sending of the second data set.

[0648] As an embodiment, the third processor belongs to the first node, and the fourth processor belongs to the second node.

[0649] As an embodiment, the third processor belongs to the first node.

[0650] As an embodiment, the first data set comprises training data.

[0651] As an embodiment, the second processor is configured to train an ML model, and the trained model is described by the target first-type parameter group.

[0652] As an embodiment, the second processor belongs to the first node; the above method avoids transmitting the first data set to the second node.

[0653] As an embodiment, the second processor belongs to the second node in the present application; the above method supports joint training and optimizes system performance.

[0654] As an embodiment, the second processor belongs to the core network; the above method supports network-wide joint training and further optimizes system performance.

[0655] As an embodiment, the second data set comprises inference data.

[0656] As an embodiment, the third processor constructs a model according to the target first-type parameter group, and then inputs the second data set into the constructed model to obtain the first-type output.

[0657] As an embodiment, the output of the third processor comprises the first parameter.

[0658] As an embodiment, the second data set comprises the M configuration messages.

[0659] As an embodiment, the second data set comprises the M RS resource groups.

[0660] As an embodiment, at least one of the first processor, the second processor, the third processor and the fourth processor is associated with the first entity in the present application.

[0661] As an embodiment, the first-type feedback comprises the first parameter.

[0662] As an embodiment, the second processor is associated with the first entity.

[0663] As one embodiment, the third processor generates a recovery data set from the first type of output, and an error of the recovery data set from the second data set is used to generate the first type of feedback.

[0664] As one embodiment, the first type of feedback is used to reflect performance of the trained model; when the performance of the trained model cannot meet the requirement, the second processor recalculates the target first type of parameter set.

[0665] As one embodiment, the performance of the trained model is considered to be unable to meet the requirement when the error is too large or the update is not performed for too long a time.

[0666] As one embodiment, the target first type of parameter set includes one or more of a convolution kernel, a pool core, a pooling function, an activation function, a parameter of the pooling function, or a parameter of the activation function.

[0667] As one embodiment, the target first type of parameter set includes one or more of a convolution kernel size, a convolution layer number, a convolution step, a pool core size, a pool core step, a pooling function, an activation function, or a feature map number.

[0668] Embodiment 14

[0669] Embodiment 14 illustrates an AI / ML based schematic diagram according to one embodiment of the present application, as shown in FIG. 14. In FIG. 14, the first operation and the second operation belong to a first stage, the third operation belongs to a second stage, the fourth operation belongs to a third stage, and the fifth operation belongs to a fourth stage; a line with an arrow indicates the order of the flow.

[0670] As one embodiment, 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.

[0671] 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.

[0672] As an embodiment, the first stage includes AI / ML model training.

[0673] As an embodiment, the first stage includes AI / ML model training and AI / ML testing.

[0674] As an embodiment, the AI / ML model training includes initial training and re-training of one or a set of AI / ML entities.

[0675] As an embodiment, the AI / ML model training relies on training data.

[0676] As an embodiment, the AI / ML model training includes AI / ML entity validation.

[0677] As an embodiment, the AI / ML entity validation is used to evaluate the performance of the AI / ML entity.

[0678] As an embodiment, the AI / ML entity validation relies on validation data.

[0679] As an embodiment, if the result of AI / ML entity validation does not meet the expectation, the AI / ML model will be re-trained.

[0680] As an embodiment, the AI / ML testing includes testing the validated AI / ML entity to evaluate the performance of the trained AI / ML model.

[0681] As an embodiment, if the result of AI / ML testing meets the expectation, the AI / ML entity proceeds to the next stage; otherwise, the AI / ML model will be re-trained.

[0682] As an embodiment, the AI / ML testing relies on testing data.

[0683] As an embodiment, the second stage includes AI / ML simulation, which simulates the inference of the AI / ML entity in a simulation environment.

[0684] As an embodiment, the AI / ML simulation is to evaluate the performance of the inference of the AI / ML entity in a simulation environment before using the AI / ML entity.

[0685] As an embodiment, the second stage is optional.

[0686] As one embodiment, the third stage includes AI / ML entity loading for obtaining trained AI / ML entity for desired AI / ML inference function.

[0687] As one embodiment, the third stage is optional.

[0688] As one embodiment, the third stage is not needed when training function and inference function are co-located.

[0689] As one embodiment, the fourth stage includes AI / ML inference.

[0690] Embodiment 15

[0691] Embodiment 15 illustrates a structural block diagram of a processing apparatus in a first node according to one embodiment of the present application, as shown in FIG. 15. In FIG. 15, the processing apparatus 1500 in the first node includes a first receiver 1501 and a first processor 1502.

[0692] In embodiment 15, the first receiver 1501 receives M configuration messages, the M configuration messages respectively indicate M RS resource groups, any RS resource group of the M RS resource groups includes one or more RS resources, the M is a positive integer greater than 1; for each configuration message of the M configuration messages, the first processor 1502 calculates a first parameter; the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message;

[0693] In embodiment 15, the first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message.

[0694] As one embodiment, the calculation time refers to the occupation time of CPU.

[0695] As one embodiment, the first processor 1502 transmits the corresponding first parameter for each configuration message of the M configuration messages.

[0696] As one embodiment, the first processor 1502 calculates or transmits predicted channel information according to the reporting configuration of each configuration message of the M configuration messages; the predicted channel information depends on the measurement on the RS resource group indicated by the corresponding configuration message; the calculation of the first parameter depends on the predicted channel information associated with the corresponding configuration message.

[0697] As an embodiment, the M configuration messages are associated to a first entity, the first entity is used for AI / ML based prediction, the first entity comprises at least one of the following features:

[0698] - is an AI / ML model;

[0699] - is associated to an AI / ML model ID;

[0700] - is associated to a Functionality ID;

[0701] - is associated to a data set;

[0702] - corresponds to an Associated ID.

[0703] As an embodiment, the M configuration messages respectively correspond to M different target predictions, the M different target predictions comprise at least one of the following:

[0704] - prediction of RSRP for L1;

[0705] - prediction of RSRP for L3;

[0706] - prediction for cell switching;

[0707] - prediction for mobility.

[0708] As an embodiment, the calculation time of a first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message among the M configuration messages and other than the first configuration message, the consistency between the first configuration message and the at least one configuration message comprises at least one of the following:

[0709] As an embodiment, the calculation time of a first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message among the M configuration messages and other than the first configuration message, the first configuration message and the second configuration message are consistent; the consistency comprises at least one of the following:

[0710] - RS resource groups indicated by the first configuration message and RS resource groups indicated by the second configuration message are QCL;

[0711] - speeds applicable to the first configuration message and speeds applicable to the second configuration message are the same;

[0712] - the first configuration message and the second configuration message indicate same RS resource group;

[0713] - the first configuration message and the second configuration message correspond same spatial parameter.

[0714] As one embodiment, the measurement comprises measurement for at least one of RSRP, RSRQ, RSSI, or SNR.

[0715] As one embodiment, the M configuration messages respectively indicate prediction for M different measurement targets.

[0716] As one embodiment, each of the M configuration messages indicates reporting configuration for RS resources included in a corresponding RS resource group.

[0717] As one embodiment, the first parameter corresponds one performance indicator.

[0718] As one embodiment, the first parameter corresponds one KPI.

[0719] As one embodiment, the calculation time is a period of measuring and calculating result, and the first time value is equal to a positive integer multiple of the second time value which is greater than 1.

[0720] As one embodiment, the first node 1500 is a user equipment.

[0721] As one embodiment, the first node 1500 is a terminal.

[0722] As one embodiment, the first node 1500 is a relay node equipment.

[0723] As one embodiment, the first receiver 1501 comprises at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, the data source 467} in embodiment 4.

[0724] As one embodiment, the first processor 1502 comprises at least one of {the antenna 452, the transmitter / receiver 454, the transmitting processor 468, the receiving processor 456, the multi-antenna transmitting processor 457, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, the data source 467} in embodiment 4.

[0725] Embodiment 16

[0726] Embodiment 16 illustrates a structural block diagram of a processing apparatus in a second node according to an embodiment of the present application, as shown in FIG. 16. In FIG. 16, the processing apparatus 1600 in the second node includes a first transmitter 1601 and a second receiver 1602.

[0727] In Embodiment 16, the first transmitter 1601 transmits M configuration messages, the M configuration messages respectively indicate M RS resource groups, any RS resource group of the M RS resource groups includes one or more RS resources, and M is a positive integer greater than 1.

[0728] In Embodiment 16, the receiver of the M configuration messages is a first node; for each of the M configuration messages, the first node calculates a first parameter; the calculation of the first parameter depends on the measurement of the RS resource group indicated by the corresponding configuration message; a first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages and other than the first configuration message.

[0729] As an embodiment, the calculation time refers to the CPU occupation time.

[0730] As an embodiment, the second receiver 1602 receives the corresponding first parameter for each of the M configuration messages.

[0731] As an embodiment, the second receiver 1602 receives predicted channel information according to the reporting configuration of each of the M configuration messages; the predicted channel information depends on the measurement on the RS resource group indicated by the corresponding configuration message; the calculation of the first parameter depends on the predicted channel information associated with the corresponding configuration message.

[0732] As an embodiment, the M configuration messages are associated to a first entity, the first entity is used for AI / ML-based prediction, and the first entity includes at least one of the following features:

[0733] - an AI / ML model;

[0734] - associated to an AI / ML model ID;

[0735] - associated to a Functionality ID;

[0736] - associated to a data set;

[0737] - corresponds to an Associated ID.

[0738] As one embodiment, the M configuration messages respectively correspond to M different targets of prediction, the M different targets of prediction include at least one of:

[0739] - a prediction of RSRP for L1;

[0740] - a prediction of RSRP for L3;

[0741] - a prediction for cell switching;

[0742] - a prediction for mobility.

[0743] As one embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message among the M configuration messages and other than the first configuration message, the meaning of the consistency includes: when the first parameter corresponding to at least one configuration message other than the first configuration message is not lower than a first threshold value, the calculation time of the first parameter is equal to a first time value; when the first parameter corresponding to at least one configuration message other than the first configuration message is lower than a first threshold value, the calculation time of the first parameter is equal to a second time value; the first time value and the second time value are different.

[0744] As one embodiment, the calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message among the M configuration messages and other than the first configuration message, the first configuration message and the second configuration message are consistent; the meaning of the consistency includes at least one of:

[0745] - the RS resource group indicated by the first configuration message and the RS resource group indicated by the second configuration message are QCL;

[0746] - the speed applicable to the first configuration message and the speed applicable to the second configuration message are the same;

[0747] - the first configuration message and the second configuration message indicate the same RS resource group;

[0748] - the first configuration message and the second configuration message correspond to the same spatial parameter.

[0749] As one embodiment, the measurement includes measurement for at least one of RSRP, RSRQ, RSSI, or SNR.

[0750] As one embodiment, the measurement includes measurement for at least one of RSRP, RSRQ, RSSI, or SNR.

[0751] As an embodiment, the M configuration messages respectively indicate predictions for M different measurement targets.

[0752] As an embodiment, each of the M configuration messages indicates a reporting configuration for RS resources included in a corresponding RS resource group.

[0753] As an embodiment, the first parameter corresponds to a performance indicator.

[0754] As an embodiment, the first parameter corresponds to a KPI.

[0755] As an embodiment, the calculation time is a period of measuring a calculation result, and the first time value is equal to a positive integer multiple of the second time value greater than 1.

[0756] As an embodiment, the second node 1600 is a base station device.

[0757] As an embodiment, the second node 1600 is a user equipment.

[0758] As an embodiment, the second node 1600 is a TRP.

[0759] As an embodiment, the first transmitter 1601 includes at least one of {the antenna 420, the transmitter 418, the transmit processor 416, the multi-antenna transmit processor 471, the controller / processor 475, the memory 476} in Embodiment 4.

[0760] As an embodiment, the second receiver 1602 includes at least one of {the antenna 420, the receiver 418, the receive processor 470, the multi-antenna receive processor 472, the controller / processor 475, the memory 476} in Embodiment 4.

[0761] Those skilled in the art can understand that all or part of the steps in the foregoing method can be instructed by programs to related hardware, and the programs can be stored in a computer readable storage medium, such as a read-only memory, a hard disk, an optical disk or the like. Alternatively, all or part of the steps of the foregoing embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module unit in the foregoing embodiments can be implemented in the form of hardware or in the form of a software function module, and the present application is not limited to any specific form of combination of software and hardware. The user equipment, terminal and UE in the present application include but are not limited to unmanned aerial vehicles, communication modules on unmanned aerial vehicles, remote control aircraft, aircraft, small aircraft, mobile phones, tablet computers, notebook computers, vehicle-mounted communication devices, vehicles, vehicles, RSUs, wireless sensors, network cards, Internet of Things terminals, RFID (Radio Frequency Identification) terminals, NB-IoT (Narrow Band Internet of Things) terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, network cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablet computers and other wireless communication devices. The base station or system device in the present application includes but is not limited to macro cellular base stations, micro cellular base stations, small cellular base stations, home base stations, relay base stations, eNB (evolved Node B), gNB, TRP, GNSS (Global Navigation Satellite System), relay satellites, satellite base stations, air base stations, RSUs, unmanned aerial vehicles, test equipment such as wireless communication devices that simulate part of the functions of base stations or signaling testers, and the like.

[0762] Those skilled in the art will understand that the application can be implemented by other specified forms without departing from the core or essential characteristics thereof. Therefore, the presently disclosed embodiments should in no way be considered as descriptive rather than limiting. The scope of the application is determined by the appended claims rather than the preceding description, and all modifications within the equivalent meaning and range of the claims are considered to be included therein.

Claims

1. A method in a terminal for wireless communication with artificial intelligence, characterized by, Comprising: receiving M configuration messages, the M configuration messages respectively indicating M RS resource groups, any RS resource group of the M RS resource groups comprising one or more RS resources, the M being a positive integer greater than 1; for each configuration message of the M configuration messages, calculating a first parameter; the calculation of the first parameter relying on a measurement on the RS resource group indicated by the corresponding configuration message; wherein a first configuration message is one of the M configuration messages; the calculation time of the first parameter corresponding to the first configuration message relying on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message.

2. The method of claim 1, wherein, The calculation time refers to the CPU occupation time.

3. The method according to claim 1 or 2, characterized in that, Comprising: for each configuration message of the M configuration messages, sending the corresponding first parameter.

4. The method according to any one of claims 1 to 3, characterized in that, Comprising: calculating or sending predicted channel information according to the reporting configuration of each configuration message of the M configuration messages; wherein the predicted channel information relies on a measurement on the RS resource group indicated by the corresponding configuration message; the calculation of the first parameter relying on the predicted channel information associated with the corresponding configuration message.

5. The method according to any one of claims 1 to 4, characterized in that, The M configuration messages are associated to a first entity, the first entity being used for AI / ML based prediction, the first entity comprising at least one of the following features: - being an AI / ML model; - being associated to an AI / ML model ID; - being associated to a Functionality ID; - being associated to a data set; - corresponding to an Associated ID.

6. The method according to any one of claims 1 to 5, characterized in that, The M configuration messages respectively correspond to M different target predictions, the M different target predictions comprising at least one of the following: - a prediction of L1 RSRP; - a prediction of L3 RSRP; - a prediction for cell handover; - a prediction for mobility.

7. The method according to any one of claims 1 to 6, characterized in that, The calculation time of the first parameter corresponding to the first configuration message relying on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message means that when the first parameter corresponding to at least one configuration message other than the first configuration message is not lower than a first threshold, the calculation time of the first parameter equals to a first time value; when the first parameter corresponding to at least one configuration message other than the first configuration message is lower than the first threshold, the calculation time of the first parameter equals to a second time value; the first time value and the second time value are different.

8. The method according to any one of claims 1 to 7, characterized in that, The calculation time of the first parameter corresponding to the first configuration message relying on the first parameter corresponding to a second configuration message of the M configuration messages and other than the first configuration message, the first configuration message and the second configuration message being consistent; the consistency means at least one of the following ： - the RS resource group indicated by the first configuration message and the RS resource group indicated by the second configuration message are QCL; - the speed applicable to the first configuration message and the speed applicable to the second configuration message are the same; - the first configuration message and the second configuration message indicate same RS resource groups; - the first configuration message and the second configuration message correspond to same spatial parameters.

9. The method according to any one of claims 1 to 8, characterized in that, The measurement includes measurement for at least one of RSRP, RSRQ, RSSI, or SNR.

10. A terminal, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes including computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the terminal to perform the method according to any one of claims 1-9.

11. A method in a base station for wireless communication with artificial intelligence, characterized by, comprising: sending M configuration messages, the M configuration messages respectively indicating M RS resource groups, any RS resource group of the M RS resource groups including one or more RS resources, M being a positive integer greater than 1; wherein a receiver of the M configuration messages is a terminal; for each configuration message of the M configuration messages, the terminal calculates a first parameter; the calculation of the first parameter relies on measurement for the RS resource group indicated by the corresponding configuration message; a first configuration message is one of the M configuration messages; a calculation time of the first parameter corresponding to the first configuration message relies on the first parameter corresponding to at least one configuration message of the M configuration messages and other than the first configuration message.

12. The method of claim 11, wherein, The calculation time refers to the CPU occupation time.

13. The method according to claim 11 or 12, characterized in that, comprising: for each configuration message of the M configuration messages, receiving the corresponding first parameter.

14. The method of any one of claims 11-13, wherein, comprising: receiving predicted channel information according to the reporting configuration of each configuration message of the M configuration messages; wherein the predicted channel information relies on measurement on the RS resource group indicated by the corresponding configuration message; the calculation of the first parameter relies on the predicted channel information associated with the corresponding configuration message.

15. The method according to any one of claims 11 to 14, characterized in that, The M configuration messages are associated to a first entity, the first entity being used for AI / ML based prediction, the first entity including at least one of the following features: - being an AI / ML model; - being associated to an AI / ML model ID; - being associated to a Functionality ID; - being associated to a data set; - corresponding to an Associated ID.

16. The method according to any one of claims 11 to 15, characterized in that, The M configuration messages respectively correspond to prediction of M different targets, the prediction of the M different targets including at least one of the following: - prediction of RSRP for L1; - prediction of RSRP for L3; - prediction for cell switching; - prediction for mobility.

17. The method of any one of claims 11 to 16, wherein, The calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to at least one configuration message in the M configuration messages and other than the first configuration message, which includes: when the first parameter corresponding to at least one configuration message other than the first configuration message is not lower than a first threshold value, the calculation time of the first parameter is equal to a first time value; when the first parameter corresponding to at least one configuration message other than the first configuration message is lower than the first threshold value, the calculation time of the first parameter is equal to a second time value; the first time value and the second time value are different.

18. The method of any one of claims 11-17, wherein, The calculation time of the first parameter corresponding to the first configuration message depends on the first parameter corresponding to a second configuration message in the M configuration messages and other than the first configuration message, and the first configuration message and the second configuration message are consistent; the consistency includes at least one of the following: The RS resource groups indicated by the first configuration message and the second configuration message are QCL; The speed applied by the first configuration message and the speed applied by the second configuration message are the same; The first configuration message and the second configuration message indicate the same RS resource group; The first configuration message and the second configuration message correspond to the same spatial parameter.

19. The method of any one of claims 11-18, wherein, The measurement includes measurement of at least one of RSRP, RSRQ, RSSI or SNR.

20. A base station, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes including computer instructions, and the one or more processors are configured to invoke the computer instructions to enable the base station to perform the method according to any one of claims 11-19.

Images