Method and apparatus for node used for wireless communication and artificial intelligence

Abstract

The present application discloses a method and apparatus for a node used for wireless communication and artificial intelligence. The node receives a first information block, wherein the first information block configures training data collections for a first cell set and a second cell set; the maximum cache size of the node for the collections is a first size, and the sizes of the training data collections for the first cell set and the second cell set of the node are a first target size and a second target size, respectively; the first target size plus the second target size is greater than the first size; the node reports training data for the first cell set and the second cell set with reference to a first reference size and a second reference size, respectively; the second reference size is equal to the smaller of a candidate size and the second target size; and the first reference size is equal to the first size minus the second reference size. The present application improves data diversity.

Description

A method and apparatus for use in nodes for wireless communication and artificial intelligence Technical Field

[0001] This application relates to signal transmission methods and apparatus in wireless communication systems, and more particularly to methods and apparatus for collecting and reporting training data. Background Technology

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

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

[0004] Training data collection is a crucial step for the effective application of AI / ML in wireless communication networks. Consequently, the contradiction between the massive training data required by AI / ML algorithms and the limited storage of user devices is a problem that needs to be solved.

[0005] To address the aforementioned issues, this application discloses a solution. It should be noted that while this application is initially intended for AI / ML scenarios, it can also be applied to other non-AI / ML scenarios. Furthermore, adopting 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, short-range communication systems, NTN (Non-Terrestrial Network), IoT (Internet of Things), and URLLC (Ultra-Reliable Low-Latency Communication) networks) helps reduce hardware complexity and cost. Where there is no conflict, embodiments and features in any node of this application can be applied to any other node. Where there is no conflict, embodiments and features in any embodiment of this application can be arbitrarily combined with each other.

[0006] In particular, the interpretation of terms, nouns, functions, and variables in this application (unless otherwise specified) can be found in the definitions of the TS38 and TS37 series of 3GPP (3rd Generation Partnership Project) Technical Specifications (TS). Where necessary, reference can be made to TS38.211, TS38.212, TS38.213, TS38.214, TS38.215, TS38.300, TS38.304, TS38.305, TS38.321, TS38.331, TS37.355, and TS38.423 in the 3GPP technical specifications to aid in understanding this application.

[0007] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS38 series.

[0008] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS37 series.

[0009] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-17.

[0010] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-18.

[0011] This application discloses a method for a first node in wireless communication and artificial intelligence, comprising:

[0012] Receive a first information block, wherein the first information block configures the collection of training data for a first cell set and the collection of training data for a second cell set;

[0013] Wherein, the maximum cache size for training data collection by the first node is a first size; the size of the training data collection by the first node for the first cell set is a first target size; and the size of the training data collection by the first node for the second cell set is a second target size. The sum of the first target size and the second target size is greater than the first size. The first target size is not greater than the first size. The first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size. The second reference size is equal to the smaller of the candidate size and the second target size. The first reference size is equal to the difference between the first size and the second reference size. The candidate size is predefined or configurable.

[0014] As an example, the problem this application aims to solve includes: how to resolve the contradiction between massive training data and limited UE storage.

[0015] As an example, the problem this application aims to solve includes: how to improve model performance by enhancing training data collection.

[0016] As an example, the problem this application aims to solve includes: cache usage by the UE when collecting training data.

[0017] As an example, the problem this application aims to solve includes scenarios where two cells or sets of cells serving a UE cannot quickly exchange data.

[0018] As an example, the features of the above method include: In this application, when the sender of the first information block indicates that the size of the training data of the first cell set and the second cell set that the first node needs to collect exceeds the cache size of the first node, the first node determines the size of the data reported by the first cell set and the second cell set according to the size of the training size and the candidate size that the second cell set needs to collect, thereby solving the above problem.

[0019] As an example, the features of the above method include: In this application, when the sender of the first information block indicates that the size of the training data to be collected by the first node exceeds the cache size of the first node, by defining a candidate size, it is ensured that the first node can collect training data for the first cell set and training data for the second cell set at the same time, thereby ensuring the generalization of training data to improve model performance, thus solving the above problem.

[0020] As an example, the feature of the above method includes: the second reference size is not larger than the candidate size.

[0021] As an example, the feature of the above method includes: the sum of the candidate size and the first target size is greater than the first size.

[0022] As an example, the advantages of the above method include: this application supports the deep integration of AI and communication, improves the adaptability and intelligence level of the communication system, and thus enhances the performance, efficiency and user experience of the communication system.

[0023] As an example, the advantages of the above method include: improving the diversity and representativeness of training data by reasonably allocating cache, thereby enhancing the generalization ability of the model.

[0024] As an example, the advantages of the above method include: optimizing storage resource utilization, avoiding excessive use of cache by the first cell set leading to insufficient data collection in the second cell set due to insufficient cache, thereby reducing model bias caused by imbalanced training data.

[0025] As an example, the advantages of the above method include: introducing candidate sizes can avoid overflow caused by collecting too much training data for the second cell set when the cache is limited, thus overwriting the training data collected for the first cell set, and ensuring that all cell sets can store a certain amount of training data.

[0026] According to one aspect of this application, the above method is characterized in that the first target size is based on prediction, or the first target size is based on actual training data collection for the first cell set; the second target size is based on prediction, or the second target size is based on actual training data collection for the second cell set.

[0027] As an example, the features of the above method include: the first information block configures the first node to collect training data for the first cell set, the size of the training data being the first target size; the first information block configures the first node to collect training data for the second cell set, the size of the training data being the second target size.

[0028] As an example, the features of the above method include: the first target size is predicted by the first node based on the configuration of the training data collected by the first node regarding the first cell set; the second target size is predicted by the first node based on the configuration of the training data collected by the first node regarding the second cell set.

[0029] As an example, the features of the above method include: when the cache capacity of the first node is sufficient, the first node will collect training data for the first target size and the second target size for the first cell set and the second cell set, respectively.

[0030] As an example, the advantages of the above method include: predicting in advance the amount of training data to be collected for each cell set can optimize the allocation of storage resources.

[0031] As an example, the benefits of the above method include: helping base stations to more accurately adjust bandwidth allocation and network resource allocation when performing resource scheduling.

[0032] As an example, the benefits of the above method include: improving the efficiency of collaboration between network devices and user equipment.

[0033] According to one aspect of this application, the above method is characterized by comprising:

[0034] Send a first signal and a second signal, wherein the first signal and the second signal respectively include the training data for the first cell set and the training data for the second cell set;

[0035] Wherein, the first signal is referenced to the first reference size, and the second signal is referenced to the second reference size.

[0036] As an example, the features of the above method include: the size of the training data carried by the first signal for the first cell set does not exceed the first reference size; and the size of the training data carried by the second signal for the second cell set does not exceed the second reference size.

[0037] As an example, the features of the above method include: this application does not limit whether the first signal and the second signal are sent simultaneously.

[0038] As an example, the features of the above method include: after the first node sends the first signal and the second signal, it clears the cache storing the training data for the first cell set and the cache storing the training data for the second cell set, respectively.

[0039] As an example, the advantages of the above method include reducing redundant information transmission between user equipment and network equipment.

[0040] As an example, the advantages of the above method include: user equipment can intelligently manage cache resources.

[0041] As an example, the advantages of the above method include: timely reporting of training data when the cache reaches its maximum size can ensure the real-time nature of the training data, and new training data can be collected again by clearing the cache in a timely manner after reporting.

[0042] According to one aspect of this application, the above method is characterized by comprising:

[0043] Send the second information block;

[0044] The second information block indicates that the maximum cache size used by the first node for training data collection has been reached or will be reached.

[0045] As an example, the features of the above method include: the second information block indicates that the cache of the first node used for training data collection is full or about to be full.

[0046] As an example, the features of the above method include: the second information block indicates that the ratio of the occupied cache in the cache of the first node used for training data collection to the first size exceeds a given threshold, the given threshold being a real number between 0 and 1, and the given threshold being predefined or configurable.

[0047] As an example, the features of the above method include: the second information block includes a training data reporting request.

[0048] As an example, the advantages of the above method include: when the UE reports a low storage status, the network device can activate an optimization strategy for data uploading, prioritizing the processing of data that needs to be uploaded in a timely manner.

[0049] As an example, the advantages of the above method include: the network device can perform load balancing based on the cache status of multiple UEs, thereby improving the overall resource utilization.

[0050] As an example, the advantages of the above method include: optimizing data storage strategy, allowing network devices to appropriately reallocate resources, coordinating the load of cell groups, and preventing some terminals from being unable to collect data normally due to memory shortages.

[0051] According to one aspect of this application, the above method is characterized by comprising:

[0052] A first coefficient is received, which is used to determine the candidate size.

[0053] As an example, the feature of the above method includes: the product of the first coefficient and the first size is the candidate size.

[0054] As an example, the features of the above method include: the difference between the first size and the first coefficient multiplied by the first size is the candidate size.

[0055] As an example, the feature of the above method includes that the candidate size is configurable.

[0056] As an example, the advantages of the above method include: configurable candidate sizes allow the network to adjust the proportion of training data collected from different cell sets according to model capabilities, thereby improving the accuracy of the model.

[0057] As an example, the advantages of the above method include: configuring the scaling factor can hide the hardware differences between different user devices, reduce the difficulty of standardization, and improve standard compatibility.

[0058] As an example, the advantages of the above method include: configurable candidate sizes can establish consensus between network devices and user devices, avoiding redundancy or omissions in training data due to information asymmetry between the two parties.

[0059] According to one aspect of this application, the above method is characterized in that the first cell set corresponds to MCG and the second cell set corresponds to SCG; or, the first cell set corresponds to 6G cells and the second cell set corresponds to 5G cells.

[0060] As an example, the features of the above method include: the cells included in the first cell set all belong to the MCG; the cells included in the second cell set all belong to the SCG.

[0061] As an example, the features of the above method include: the cells included in the first cell set are all 6G cells; the cells included in the second cell set are all 5G cells.

[0062] As an example, the features of the above method include: the 6G cell refers to the cell whose radio access mode is 6G, and the 5G cell refers to the cell whose radio access mode is NR.

[0063] As an example, the benefits of the above method include improving the quality and diversity of training data.

[0064] As an example, the advantages of the above method include: reducing the steps of training data preprocessing, facilitating the establishment of labels for training data, and improving model performance.

[0065] As an example, the advantages of the above method include: ensuring that the training data can reflect different network topologies, interference conditions and bandwidth conditions, improving the generalization ability of the training model, and enabling it to better adapt to network optimization and AI applications in different environments.

[0066] According to one aspect of this application, the above method is characterized in that the first information block configures a set of parameters for the training data collection for the first cell set and for the training data collection for the second cell set, the set of parameters including at least one of the time-frequency resources occupied by the reporting of the training data and the conditions satisfied to trigger the reporting of the training data.

[0067] As an example, the characteristics of the above method include: the parameter set belongs to the CSI framework.

[0068] As an example, the features of the above method include: the parameter set is used to configure higher-level parameters for AI / ML training data collection.

[0069] As an example, the features of the above method include: the reporting of the training data is configured by the sender of the second information block.

[0070] As an example, the advantages of the above method include: optimizing the utilization efficiency of wireless resource networks and reducing collisions and interference.

[0071] As an example, the advantages of the above method include: improving the reliability and quality of training data upload.

[0072] According to one aspect of this application, the above method is characterized in that the training data collection for the first cell set preferentially occupies a cache other than the candidate size in the maximum cache of the first node used for training data collection.

[0073] As an example, the features of the above method include: when the second reference size is equal to the second target size, the first node will only occupy the cache for training data collection for the first cell set in the candidate size when all caches outside the candidate size are occupied.

[0074] As an example, the features of the above method include: when the second reference size is equal to the second target size, and the cache outside the candidate size is not fully occupied, the training data collection for the first cell set will not occupy the cache for training data collection for the first cell set in the candidate size.

[0075] As an example, the features of the above method include: when the second reference size is equal to the candidate size, the training data collection for the first cell set only occupies the cache other than the candidate size in the maximum cache of the first node used for training data collection.

[0076] As an example, the benefits of the above method include: reducing the impact of the first cell set on the second cell set, improving cache utilization efficiency, and enhancing data diversity and quality.

[0077] As an example, the advantages of the above method include: cache reservation can be implemented in a way specified by hardware or software, reducing the difficulty of implementation.

[0078] As an example, the advantages of the above method include: avoiding cache overflow and improving cache utilization.

[0079] As an example, the benefits of the above method include: enhancing resource sharing and coordination capabilities across cell groups.

[0080] According to one aspect of this application, the above method is characterized in that the first node is a user equipment.

[0081] According to one aspect of this application, the above method is characterized in that the first node is a terminal.

[0082] This application discloses a method for a second node in wireless communication and artificial intelligence, comprising:

[0083] Send a first information block, the first information block configuring training data collection for a first cell set and training data collection for a second cell set;

[0084] Wherein, the receiver of the first information block is the first node; the maximum cache size for training data collection by the first node is a first size, the size of the training data collection by the first node for the first cell set is a first target size, and the size of the training data collection by the first node for the second cell set is a second target size; the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size; the second reference size is equal to the smaller of the candidate size and the second target size; the first reference size is equal to the difference between the first size and the second reference size; the candidate size is predefined, or the candidate size is configurable.

[0085] As an example, the features of the above method include: the second node includes a base station and a core network.

[0086] As an example, the features of the above method include: the second node includes a core network.

[0087] As an example, the features of the above method include: the second node includes an entity for deploying AI / ML models.

[0088] As an example, the features of the above method include: the second node includes a node for deploying AI / ML models.

[0089] As an example, the features of the above method include: the second node includes a base station.

[0090] As an example, the features of the above method include: the second node is a base station.

[0091] As an example, the features of the above method include: the second node is an LMF.

[0092] As an example, the features of the above method include: the second node is OAM.

[0093] As an example, the features of the above method include: the second node is a gNB.

[0094] As an example, the features of the above method include: the second node is a network device, which includes at least one of a core network device and an access network device.

[0095] As an example, the features of the above method include: the second node is a device that provides wireless communication function services, can communicate with terminal devices, and is usually located on the network side.

[0096] As an example, the features of the above method include: the base station in this application includes a core network.

[0097] As an example, the features of the above method include: the base station in this application includes core network equipment.

[0098] As an example, the features of the above method include: the base station in this application includes an entity for deploying AI / ML models.

[0099] As an example, the features of the above method include: the base station in this application includes nodes for deploying AI / ML models.

[0100] According to one aspect of this application, the above method is characterized in that the first target size is based on prediction, or the first target size is based on actual training data collection for the first cell set; the second target size is based on prediction, or the second target size is based on actual training data collection for the second cell set.

[0101] According to one aspect of this application, the above method is characterized by comprising:

[0102] Receive a first signal and a second signal, wherein the first signal and the second signal respectively include the training data for the first cell set and the training data for the second cell set;

[0103] Wherein, the first signal is referenced to the first reference size, and the second signal is referenced to the second reference size.

[0104] According to one aspect of this application, the above method is characterized by comprising:

[0105] Receive the second information block;

[0106] The second information block indicates that the maximum cache size used by the first node for training data collection has been reached or will be reached.

[0107] According to one aspect of this application, the above method is characterized by comprising:

[0108] A first coefficient is sent, which is used to determine the candidate size.

[0109] According to one aspect of this application, the above method is characterized in that the first cell set corresponds to MCG and the second cell set corresponds to SCG; or, the first cell set corresponds to 6G cells and the second cell set corresponds to 5G cells.

[0110] According to one aspect of this application, the above method is characterized in that the first information block configures a set of parameters for the training data collection for the first cell set and for the training data collection for the second cell set, the set of parameters including at least one of the time-frequency resources occupied by the reporting of the training data and the conditions satisfied to trigger the reporting of the training data.

[0111] According to one aspect of this application, the above method is characterized in that the training data collection for the first cell set preferentially occupies a cache other than the candidate size in the maximum cache of the first node used for training data collection.

[0112] According to one aspect of this application, the method described above is characterized in that the second node is a base station.

[0113] This application discloses a device for a first node in wireless communication and artificial intelligence, comprising:

[0114] A first receiver receives a first information block, wherein the first information block is configured to collect training data for a first cell set and collect training data for a second cell set.

[0115] Wherein, the maximum cache size for training data collection by the first node is a first size; the size of the training data collection by the first node for the first cell set is a first target size; and the size of the training data collection by the first node for the second cell set is a second target size. The sum of the first target size and the second target size is greater than the first size. The first target size is not greater than the first size. The first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size. The second reference size is equal to the smaller of the candidate size and the second target size. The first reference size is equal to the difference between the first size and the second reference size. The candidate size is predefined or configurable.

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

[0117] The second transmitter transmits a first information block, which is configured to collect training data for a first cell set and collect training data for a second cell set.

[0118] Wherein, the receiver of the first information block is the first node; the maximum cache size for training data collection by the first node is a first size, the size of the training data collection by the first node for the first cell set is a first target size, and the size of the training data collection by the first node for the second cell set is a second target size; the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size; the second reference size is equal to the smaller of the candidate size and the second target size; the first reference size is equal to the difference between the first size and the second reference size; the candidate size is predefined, or the candidate size is configurable.

[0119] As an example, compared with conventional solutions, this application has the following advantages, but is not limited to:

[0120] This application supports the deep integration of AI and communication to improve the adaptability and intelligence of communication systems, thereby enhancing the performance, efficiency, and user experience of communication systems.

[0121] This application reasonably allocates the cache size corresponding to the collection of training data for two cell sets, so as to avoid the problem that the collection of training data for one cell set will occupy the terminal's cache and cause the training data for the other cell to be unable to be collected.

[0122] This application addresses scenarios where latency-free and bandwidth-unrestricted interaction is impossible between two cell sets, which is closer to real-world scenarios and facilitates engineering implementation.

[0123] This application makes full use of the performance gains that AI / ML models bring to the terminal, and is relatively easy to implement, and can balance resources to avoid waste and overuse. Attached Figure Description

[0124] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0125] Figure 1 illustrates a flowchart of the first node transmission according to an embodiment of this application;

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

[0127] Figure 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application;

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

[0129] Figure 5 shows a first flowchart of the transmission between a first node and a second node according to an embodiment of this application;

[0130] Figure 6 illustrates a second flowchart of the transmission between a first node and a second node according to an embodiment of this application;

[0131] Figure 7 shows a first schematic diagram of a first reference dimension and a second reference dimension according to an embodiment of this application;

[0132] Figure 8 shows a second schematic diagram of a first reference dimension and a second reference dimension according to an embodiment of this application;

[0133] Figure 9 shows a schematic diagram of a first target size and a second target size according to an embodiment of this application;

[0134] Figure 10 shows a first schematic diagram of a first cell set and a second cell set according to an embodiment of this application;

[0135] Figure 11 shows a second schematic diagram of a first cell set and a second cell set according to an embodiment of this application;

[0136] Figure 12 shows a schematic diagram of a parameter set according to an embodiment of this application;

[0137] Figure 13 illustrates a schematic diagram of RAN domain AI / ML function deployment according to an embodiment of this application;

[0138] Figure 14 shows a schematic diagram of the deployment of AI / ML functions of a UE according to an embodiment of this application;

[0139] Figure 15 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0140] Figure 16 illustrates a schematic diagram of artificial intelligence or machine learning according to an embodiment of this application;

[0141] Figure 17 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0142] Figure 18 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0143] The technical solutions of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Considering performance, flexibility, complexity, overhead, and compatibility, those skilled in the art are motivated to flexibly combine the embodiments in different drawings without conflict, including but not limited to the embodiments in Figure 1 and the embodiments in Figures 5-18, the embodiments in Figure 5 and the embodiments in Figures 6-18, etc.

[0144] Example 1

[0145] Example 1 illustrates a flowchart of the first node transmission according to an embodiment of this application, as shown in Figure 1. In Figure 1, each block represents a step. In particular, the order of the steps in the blocks does not represent a specific temporal sequence between the steps.

[0146] The first node receives a first information block in step 101, the first information block configuring training data collection for a first cell set and training data collection for a second cell set.

[0147] In Embodiment 1, the maximum cache size for training data collection by the first node is a first size; the size of the training data collection by the first node for the first cell set is a first target size; and the size of the training data collection by the first node for the second cell set is a second target size. The sum of the first target size and the second target size is greater than the first size. The first target size is not greater than the first size. The first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size. The second reference size is equal to the smaller of the candidate size and the second target size. The first reference size is equal to the difference between the first size and the second reference size. The candidate size is predefined or configurable.

[0148] As one example, the first node is a user equipment (UE).

[0149] As one example, the first node is a terminal.

[0150] As an example, the first node is the first node in this application.

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

[0152] As one example, the first information block is transmitted via higher-level signaling.

[0153] As an example, the first information block is transmitted via an RRC (Radio Resource Control) message.

[0154] As an example, the first information block is transmitted via RRC signaling.

[0155] As an example, the first information block includes one or more RRC IEs (Information Elements).

[0156] As an example, the first information block includes one or more fields in an RRC IE.

[0157] As one embodiment, the first information block includes one or more fields of each of the plurality of RRC IEs.

[0158] As one example, the first information block indicates higher-level parameters.

[0159] As one embodiment, the first information block is transmitted by dynamic signaling.

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

[0161] As an example, the first information block is transmitted via Layer 2 (L2) signaling.

[0162] As one embodiment, the first information block includes MAC (Media Access Control) layer signaling.

[0163] As an example, the first information block includes a MAC CE (Control Element).

[0164] As an example, the first information block is transmitted via Layer 1 (L1) signaling.

[0165] As one embodiment, the first information block includes physical layer signaling.

[0166] As one embodiment, the first information block includes physical layer control signaling.

[0167] As an example, the first information block is indicated by DCI (Downlink Control Information).

[0168] As one embodiment, the first information block is jointly carried by RRC layer signaling and MAC layer signaling.

[0169] As one embodiment, the first information block is jointly carried by RRC layer signaling and physical layer signaling.

[0170] As an example, the first information block configures the reference signal (RS) resources of the first cell set.

[0171] As an example, the first information block configures the RS resources of each cell in the first cell set.

[0172] As an example, the first information block configures the RS resources of the second cell set.

[0173] As an example, the first information block configures the RS resources of each cell in the second cell set.

[0174] As a sub-implementation of the above four embodiments, the first node receives and measures the RS resources to obtain the training data.

[0175] As a sub-implementation of the above four embodiments, the first node receives and measures the RS resources to obtain part of the training data.

[0176] As a sub-implementation of the above four embodiments, the first node receives and measures the RS resources, and the first node collects the measurement results of a portion of the RS resources to generate the training data.

[0177] As one embodiment, the first information block is configured to collect training data for the first cell set and collect training data for the second cell set.

[0178] As an example, the first information block triggers the collection of training data for the first cell set and the collection of training data for the second cell set.

[0179] As an example, the first information block activates the training data collection for the first cell set and the training data collection for the second cell set.

[0180] As an example, the first information block enables the collection of training data for the first cell set and the collection of training data for the second cell set.

[0181] As one embodiment, the first information block schedules the uploading of training data for the first cell set and the uploading of training data for the second cell set.

[0182] As an example, in response to receiving the first information block, the first node begins collecting the training data for the first cell set and the training data for the second cell set.

[0183] As an example, in response to receiving the first information block, the first node initializes a cache for the training data for the first cell set and a cache for the training data for the second cell set.

[0184] As an example, in response to receiving the first information block, the first node clears the cache of the training data for the first cell set and the cache of the training data for the second cell set.

[0185] As an example, in this application, the second node instructs the first node to begin collecting the training data for the first cell set and the training data for the second cell set.

[0186] As an example, in this application, the second node instructs the first node to begin collecting the training data for the first cell set.

[0187] As an example, in this application, the second node instructs the first node to begin collecting the training data for the second cell set.

[0188] As an example, this application does not limit whether the first node starts collecting training data for the first cell set and training data for the second cell set simultaneously.

[0189] As an example, the first cell set includes at least one cell.

[0190] As an example, the first cell set includes one cell.

[0191] As one example, the first cell set includes multiple cells.

[0192] As an example, the cells included in the first cell set are all serving cells of the first node.

[0193] As an example, at least one cell in the first cell set is the serving cell of the first node.

[0194] As one example, the second cell set includes at least one cell.

[0195] As an example, the second cell set includes one cell.

[0196] As one example, the second cell set includes multiple cells.

[0197] As an example, the cells included in the second cell set are all serving cells of the first node.

[0198] As an example, at least one cell in the second cell set is the serving cell of the first node.

[0199] As an example, the cells included in the second cell set are all candidate cells of the first node.

[0200] As an example, at least one cell in the second cell set is a candidate cell of the first node.

[0201] As an example, the cells included in the first cell set and the second cell set are orthogonal.

[0202] As one embodiment, the first cell set includes the serving cells of the first node, and the second cell set includes the non-serving cells of the first node.

[0203] As an example, the cells included in the first cell set and the second cell set are both serving cells of the first node.

[0204] As one embodiment, the first cell set includes the primary cell (PCell) of the first node; the second cell set includes the secondary cells (SCell) of the first node.

[0205] As a sub-implementation of this embodiment, the PCell includes a special cell (SpCell).

[0206] As a sub-implementation of this embodiment, the PCell includes a primary secondary cell (PSCell).

[0207] As one embodiment, the first cell set includes the serving cells of the first node, and the second cell set includes the candidate cells of the first node.

[0208] As one embodiment, the first cell set includes the serving cell of the first node, and the second cell set includes the neighboring cells of the first node.

[0209] As an example, the training data includes at least measurement results.

[0210] As an example, the training data includes at least measurement information.

[0211] As an example, the training data includes at least RLF (Radio Link Failure).

[0212] As an example, the training data includes at least HOF (HandOver Failure).

[0213] As one example, the training data includes a functionality ID.

[0214] As an example, the Functionality described in this application refers to a feature or feature group (FG) that supports AI / ML (Artificial Intelligence / Machine Learning) through configuration, wherein the configuration is supported according to conditions indicated by the UE capability.

[0215] As an example, the training data includes associated IDs.

[0216] As an example, the associated ID described in this application is used to indicate the generalization ability of the model.

[0217] As an example, the associated ID described in this application is used to ensure the consistency of network-side (NW-side) additional conditions during model training and model inference.

[0218] As an example, the training data includes L1-RSRP (Layer 1-Reference Signal Received Power) obtained by measuring the reference signal.

[0219] As one example, the training data includes beam indication.

[0220] As an example, the beam indicator described in this application includes at least one of CRI (CSI-RS Resource Indicator) and SSBRI (SS / PBCH Block Resource Indicator).

[0221] As an example, the beam indication described in this application includes beam order.

[0222] As an example, the training data is used in an AI / ML model.

[0223] As an example, the training data is used for AI / ML model training.

[0224] As an example, the training data is used for AI / ML model validation.

[0225] As an example, the training data is used for AI / ML model testing.

[0226] As an example, the training data is used for AI / ML model retraining.

[0227] As an example, the training data is used for AI / ML functions.

[0228] As an example, the training data is used for AI / ML function training.

[0229] As an example, the training data was used for AI / ML function validation.

[0230] As an example, the training data was used for AI / ML function testing.

[0231] As an example, the training data is used for AI / ML function retraining.

[0232] As an example, the training includes supervised learning training.

[0233] As an example, the training includes training using semi-supervised learning.

[0234] As an example, the training includes unsupervised learning training.

[0235] As an example, the training includes training using self-supervised learning.

[0236] As an example, the training includes reinforcement learning training.

[0237] As an example, the training is performed by the second node side in this application.

[0238] As an example, the training is performed on a node other than the first node in this application.

[0239] As an example, the training is performed by the network side.

[0240] As an example, the training is performed by a UE server.

[0241] As an example, the training is performed by an AI entity.

[0242] As an example, the second node in this application forwards the AI / ML model-related data it collects or the data reported by the first node to the AI ​​entity in this application. The AI ​​entity then performs AI / ML-related operations such as constructing the training dataset and training the model. The output of the trained AI / ML model, model evaluation, test results, and other AI / ML-related operations is forwarded to each terminal through the second node in this application.

[0243] As an example, the first node forwards the AI / ML model-related data it collects or the data issued by the second node in this application to the AI ​​entity in this application. The AI ​​entity then performs AI / ML-related operations such as constructing the training dataset and training the model. The first node forwards the output of the AI / ML-related operations, such as the trained AI / ML model, model evaluation, and test results, to the second node in this application.

[0244] As an example, to support AI / ML functions in a wireless network, AI / ML network elements or modules can be introduced into the network. If an AI / ML network element is introduced, the AI ​​entity described in this application corresponds to an independent network element; if an AI / ML module is introduced, the second node in this application can be located inside a network element, such as inside a terminal device or network device.

[0245] As an example, the AI ​​entity described in this application is located inside a base station.

[0246] As an example, the AI ​​entity described in this application is a module or function of a base station.

[0247] As an example, the AI ​​entity described in this application is located inside the terminal.

[0248] As an example, the AI ​​entity described in this application is a module or function of a terminal.

[0249] As an example, one possible implementation of the AI ​​entity described in this application is that the AI ​​entity is deployed in a server or cloud device of an Over-The-Top (OTT) system. Optionally, the cloud device is located on one or more of the user equipment side, network equipment side, or core network side.

[0250] As an example, the training data for the first cell set and the training data for the second cell set are used simultaneously in an AI / ML model.

[0251] As an example, the training data for the first cell set and the training data for the second cell set are respectively used in two AI / ML models.

[0252] As one embodiment, the training data for the first cell set and the training data for the second cell set are used simultaneously in a single function.

[0253] As one embodiment, the training data for the first cell set and the training data for the second cell set are used simultaneously for different functionalities.

[0254] As an example, the training data for the first cell set and the training data for the second cell set are simultaneously trained by a network-side AI / ML model.

[0255] As an example, the training data for the first cell set and the training data for the second cell set are simultaneously trained by the UE-side AI / ML model.

[0256] As an example, the training data for the first cell set and the training data for the second cell set are simultaneously trained by the network-side AI / ML model and the UE-side AI / ML model.

[0257] As an example, the maximum buffer size for the first node to collect training data is the first size.

[0258] As one embodiment, the size of the cache used by the first node to store training data is at most the first size.

[0259] As one embodiment, the maximum size of the storage resource used by the first node to store training data is the first size.

[0260] As an example, the cache belongs to a UE variable.

[0261] As an example, the cache is a UE variable of an RRC sublayer.

[0262] As an example, the cache is VarLogMeasReport.

[0263] As an example, the cache is VarMeasReportList.

[0264] As an example, the cache is VarMeasReport.

[0265] As an example, the cache is VarMeasIdleReport.

[0266] As an example, the cache belongs to VarLogMeasReport.

[0267] As an example, the cache belongs to VarMeasReportList.

[0268] As an example, the cache belongs to VarMeasReport.

[0269] As an example, the cache belongs to VarMeasIdleReport.

[0270] As an example, the cache is a UE variable of a protocol layer above an RRC sublayer.

[0271] As an example, the cache is an AS (Access Stratum) buffer.

[0272] As an example, the cache belongs to the AS layer.

[0273] As an example, the cache is a NAS (Non-Access Stratum) buffer.

[0274] As an example, the cache is a memory.

[0275] As an example, the cache is a register.

[0276] As an example, the cache is implemented in software.

[0277] As one example, the cache is implemented in hardware.

[0278] As an example, the cache is readable and writable.

[0279] As an example, the cache is erasable.

[0280] As an example, the unit corresponding to the maximum cache size is MB (MegaByte).

[0281] As an example, the unit corresponding to the maximum cache size is GB (Gigabyte).

[0282] As an example, the unit corresponding to the first size is MB.

[0283] As an example, the unit corresponding to the first size is GB.

[0284] As one example, the first size depends on the feature combination of the first node.

[0285] As an example, the first size depends on the FeatureCombination of the first node.

[0286] As one example, the first size depends on the capabilities of the first node.

[0287] As an example, the first size depends on the UECapabilityInformation of the first node.

[0288] As an example, the first size is reported to the second node in this application via a UECapabilityInformation message.

[0289] As an example, the first size depends on the UAI (UE Assistance Information) of the first node.

[0290] As an example, the first dimension is reported to the second node in this application via UAI.

[0291] As an example, the first size depends on the UEInformationResponse of the first node.

[0292] As an example, the first size is reported to the second node in this application via a UEInformationResponse message.

[0293] As an example, the first size depends on the UEAssistanceInformation of the first node.

[0294] As an example, the first size is reported to the second node in this application via a UEAssistanceInformation message.

[0295] As an example, the first size depends on the RRCReconfigurationComplete of the first node.

[0296] As an example, the first dimension is reported to the second node in this application via an RRCReconfigurationComplete message.

[0297] As an example, the size of the training data collected by the first node for the first cell set is the first target size.

[0298] As an example, the size of the training data collection for the first cell set predicted by the first node is the first target size.

[0299] As an example, the first node collects training data of the first target size for the first cell set.

[0300] As an example, the first node prediction will collect training data of the first target size for the first cell set.

[0301] As an example, the first node will collect training data of the first target size for the first cell set.

[0302] As one embodiment, the first information block configures the first node to collect training data for the first cell set; the size of the training data is the first target size.

[0303] As one embodiment, the first information block configures the first node to collect training data of the first target size for the first cell set.

[0304] As an example, the unit corresponding to the first target size is MB.

[0305] As an example, the unit corresponding to the first target size is GB.

[0306] As an example, the size of the training data collected by the first node for the second cell set is the second target size.

[0307] As an example, the first node collects training data for the second target size for the second cell set.

[0308] As an example, the first node prediction will collect training data for the second target size for the second cell set.

[0309] As an example, the first node will collect training data for the second target size for the second cell set.

[0310] As one embodiment, the first information block configures the first node to collect training data for the second cell set; the size of the training data is the second target size.

[0311] As one embodiment, the first information block configures the first node to collect training data of the second target size for the second cell set.

[0312] As an example, the unit corresponding to the second target size is MB.

[0313] As an example, the unit corresponding to the second target size is GB.

[0314] As an example, the sum of the first target size and the second target size is greater than the first size.

[0315] As one example, the first size is smaller than the sum of the first target size and the second target size.

[0316] As an example, the first target size is not larger than the first size.

[0317] As an example, the first target size is smaller than the first size.

[0318] As an example, the first target size is equal to the first size.

[0319] As an example, the first node reports the training data for the first cell set with reference to the first reference size.

[0320] As an example, the first reference size is the size referenced by the first node in the training data reported for the first cell set.

[0321] As an example, the training data reported by the first node for the first cell set at one time is no larger than the first reference size.

[0322] As an example, the first reference size is the size corresponding to the training data for the first cell set actually reported by the first node.

[0323] As an example, the first reference size is the size corresponding to the training data for the first cell set that the first node retains and is ready to report.

[0324] As an example, the unit corresponding to the first reference size is MB.

[0325] As an example, the unit corresponding to the first reference size is GB.

[0326] As an example, the first node reports the training data for the second cell set with reference to the second reference size.

[0327] As one embodiment, the second reference size is the size referenced by the first node in the training data reported for the second cell set.

[0328] As an example, the training data reported by the first node for the second cell set at one time is no larger than the second reference size.

[0329] As one embodiment, the second reference size is the size corresponding to the training data for the second cell set actually reported by the first node.

[0330] As one embodiment, the second reference size is the size corresponding to the training data for the second cell set that the first node retains and is ready to report.

[0331] As an example, the unit corresponding to the second reference dimension is MB.

[0332] As an example, the unit corresponding to the second reference size is GB.

[0333] As an example, the second reference size is equal to the smaller of the candidate size and the second target size.

[0334] As one embodiment, the first reference dimension is equal to the difference between the first dimension and the second reference dimension.

[0335] As one embodiment, the sum of the first reference dimension and the second reference dimension is equal to the first dimension.

[0336] As one example, the candidate size is predefined or the candidate size is configurable.

[0337] As an example, the unit corresponding to the candidate size is MB.

[0338] As an example, the unit corresponding to the candidate size is GB.

[0339] As an example, the candidate size is predefined.

[0340] As an example, the candidate size is fixed.

[0341] As an example, the candidate size is implementation-dependent.

[0342] As an example, the ratio of the candidate size to the first size is predefined.

[0343] As one embodiment, the ratio of the difference between the first size and the candidate size to the first size is predefined.

[0344] As an example, the candidate size is configurable.

[0345] As an example, the candidate size is configured by the network.

[0346] As one example, the candidate size is configured by the base station.

[0347] As one example, the candidate size is configured by the first node.

[0348] As an example, the candidate size is indicated by the first node.

[0349] As an example, the candidate size is configured in the second node of this application.

[0350] As an example, the candidate size is indicated by the second node in this application.

[0351] As an example, higher-layer signaling configures the candidate size.

[0352] As an example, the first information block configures the candidate size.

[0353] As one embodiment, the ratio of the candidate size to the first size is configurable.

[0354] As an example, the ratio of the candidate size to the first size is configured by the network.

[0355] As one example, the ratio of the candidate size to the first size is configured by the base station.

[0356] As one embodiment, the ratio of the candidate size to the first size is configured in the first node.

[0357] As an example, the ratio of the candidate size to the first size is indicated by the first node.

[0358] As an example, the ratio of the candidate size to the first size is configured in the second node of this application.

[0359] As an example, the ratio of the candidate size to the first size is indicated by the second node in this application.

[0360] As an example, higher-layer signaling configures the ratio of the candidate size to the first size.

[0361] As an example, the first information block configures the ratio of the candidate size to the first size.

[0362] As one embodiment, the ratio of the difference between the first size and the candidate size to the first size is configurable.

[0363] As one embodiment, the ratio of the difference between the first size and the candidate size to the first size is configured by the network.

[0364] As one embodiment, the ratio of the difference between the first size and the candidate size to the first size is configured by the base station.

[0365] As an example, the ratio of the difference between the first size and the candidate size to the first size is configured in the first node.

[0366] As an example, the ratio of the difference between the first size and the candidate size to the first size is indicated by the first node.

[0367] As an example, the ratio of the difference between the first size and the candidate size to the first size is configured in the second node of this application.

[0368] As an example, the ratio of the difference between the first size and the candidate size to the first size is indicated by the second node in this application.

[0369] As an example, the higher-level signaling configuration is the ratio of the difference between the first size and the candidate size to the first size.

[0370] As an example, the first information block is configured to be the ratio of the difference between the first size and the candidate size to the first size.

[0371] Example 2

[0372] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0373] Figure 2 illustrates network architecture 200. Network architecture 200 is the network architecture for LTE (Long-Term Evolution), LTE-A (Long-Term Evolution Advanced), 5G systems, 5G-Advanced, and future 6G systems. The network architectures for LTE, LTE-A, 5G systems, 5G-Advanced, and future 6G systems are referred to as EPS (Evolved Packet System). The 5G NR or LTE network architecture may be referred to as 5GS (5G System) / EPS or some other suitable terminology; the 6G network architecture may be referred to as 6GS (6G System) / EPS or some other suitable terminology.

[0374] The network architecture 200 may include one or more UEs 201, a RAN (Radio Access Network) 202, a core network 210, an HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and an Internet service 230. The network architecture 200 may interconnect with other access networks, but these entities / interfaces are not shown for simplicity.

[0375] As shown in Figure 2, the network architecture 200 provides packet switching services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN 202 includes Node B 203 and other nodes 204. Node B 203 provides user and control plane protocol termination toward the UE 201. Node B 203 may be connected to other nodes 204 via an Xn interface (e.g., backhaul). Node B 203 may also be referred to as eNB (evolved Node B), gNB, base station, base transceiver station, radio base station, radio transceiver, transceiver function, Basic Service Set (BSS), Extended Service Set (ESS), TRP (Transmitter Receiver Point), or some other suitable term. Node B 203 provides UE 201 with an access point to the core network 210; the core network 210 is a 5GC (5G Core network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC (6G Core network). Examples of the UE 201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, GPS devices, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband physical network devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to the UE 201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, radio terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. The Node B 203 is connected to the core network 210 via an S1 / NG interface.The core network 210 includes an MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MMEs / AMFs / SMFs 214, an 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 handles signaling between the UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF 213 is connected to the Internet service 230. The Internet service 230 includes operator-compliant Internet protocol services, specifically including the Internet, intranet, IMS (IP Multimedia Subsystem), and packet-switched streaming services.

[0376] As an example, the first node in this application includes the UE 201.

[0377] As an example, the second node in this application includes node B 203.

[0378] As an example, node B 203 is a macrocell base station.

[0379] As an example, node B 203 is a microcell base station.

[0380] As an example, node B 203 is a pico cell base station.

[0381] As an example, node B 203 is a femtocell.

[0382] As an example, node B 203 is a base station device that supports large latency differences.

[0383] As an example, node B 203 is a flight platform device.

[0384] As an example, node B 203 is a satellite device.

[0385] As one embodiment, the node B 203 is a test device (e.g., a transceiver device simulating part of the functions of a base station, a signaling tester).

[0386] As an example, the UE 201 includes a mobile phone.

[0387] As an example, the UE 201 is a vehicle including a car.

[0388] As an example, the wireless link from the UE 201 to the node B 203 is an uplink, which is used to perform uplink transmissions.

[0389] As an example, the radio link from the node B 203 to the UE 201 is a downlink, which is used to perform downlink transmissions.

[0390] As an example, the wireless link between the node B 203 and the UE 201 includes a cellular link.

[0391] As an example, the node B 203 and the UE 201 are connected via the Uu air interface.

[0392] As an example, the sender of the first information block in this application includes the node B 203.

[0393] As an example, the recipient of the first information block in this application includes the UE 201.

[0394] As an example, the sender of the first signal in this application includes the UE 201.

[0395] As an example, the receiver of the first signal in this application includes the node B 203.

[0396] As an example, the sender of the second signal in this application includes the UE 201.

[0397] As an example, the receiver of the second signal in this application includes the node B 203.

[0398] As an example, the sender of the second information block in this application includes the UE 201.

[0399] As an example, the recipient of the second information block in this application includes the node B 203.

[0400] As an example, the sender of the first coefficient in this application includes the node B 203.

[0401] As an example, the recipient of the first coefficient in this application includes the UE 201.

[0402] As an example, the node B 203 supports the deployment of network-side (NW-side) AI / ML models.

[0403] As an example, the UE 201 supports the deployment of UE-side AI / ML models.

[0404] As an example, the UE 201 supports a 5G system.

[0405] As an example, the node B 203 supports a 5G system.

[0406] As an example, the UE 201 supports at least a 6G system.

[0407] As an example, the node B 203 supports at least a 6G system.

[0408] Example 3

[0409] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in Figure 3.

[0410] Figure 3 is a schematic diagram illustrating an embodiment of the wireless protocol architecture for the user plane 350 and the control plane 300. Figure 3 shows the wireless protocol architecture for the control plane 300 between a first communication node device (UE or RSU in V2X, on-board equipment or on-board communication module) and a second node device (gNB, RSU in UE or V2X, on-board equipment or on-board 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 herein as PHY 301. L2305 is above PHY 301 and is responsible for the link between the first node device and the second node device, or between two UEs, through PHY 301. L2305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. It also provides security through encrypted data packets and supports cross-cell mobility between the second communication node devices and the first communication node device. The RLC sublayer 303 provides upper-layer packet segmentation and reassembly, retransmission of lost packets, and packet reordering to compensate for out-of-order reception due to HARQ (Hybrid Automatic Repeat Request). The MAC sublayer 302 provides multiplexing between logical and transport channels. It is also responsible for allocating various radio resources (e.g., resource blocks) within a cell between the first communication node devices. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in L3 of the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and using RRC signaling between the second communication node device and the first communication node device to configure the lower layer.The wireless protocol architecture of user plane 350 includes Layer 1 (L1) and Layer 2 (L2). The wireless protocol architecture for the first and second communication node devices in user plane 350 is largely the same as the corresponding layers and sublayers in control plane 300 for Physical Layer 351, PDCP sublayer 354 in L2355, RLC sublayer 353 in L2355, and MAC sublayer 352 in L2355. However, PDCP sublayer 354 also provides header compression for upper-layer packets to reduce wireless transmission overhead. L2355 in user plane 350 also includes SDAP (Service Data Adaptation Protocol) sublayer 356. SDAP sublayer 356 is responsible for mapping between QoS (Quality of Service) streams and Data Radio Bearer (DRB) to support service diversity. Although not illustrated, the first communication node device may have several upper layers above L2355, including a network layer (e.g., IP (Internet Protocol) layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., remote UE, server, etc.).

[0411] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node in this application.

[0412] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node in this application.

[0413] As an example, in this application, the first information block is generated in the RRC 306.

[0414] As an example, in this application, the first information block is generated in the MAC sublayer 302 or the MAC sublayer 352.

[0415] As an example, in this application, the first information block is generated in the PHY 301 or the PHY 351.

[0416] As an example, in this application, the first signal is generated in the RRC 306.

[0417] As an example, in this application, the first signal is generated on a layer above the RRC 306.

[0418] As an example, the second signal in this application is generated in the RRC 306.

[0419] As an example, in this application, the second signal is generated on a layer above the RRC 306.

[0420] As an example, the first coefficient in this application is generated in the RRC 306.

[0421] As an example, the second information block in this application is generated in the RRC 306.

[0422] As an example, in this application, the second information block is generated in the MAC sublayer 302 or the MAC sublayer 352.

[0423] As an example, the second information block in this application is generated in the PHY 301 or the PHY 351.

[0424] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0425] As an example, the higher layer described in this application includes the RRC layer.

[0426] As an example, the higher-layer signaling described in this application includes RRC IE.

[0427] As an example, the higher-level signaling described in this application includes RRC messages.

[0428] As an example, the higher layer described in this application includes the MAC layer.

[0429] As an example, the higher-layer signaling described in this application includes MAC CE.

[0430] Example 4

[0431] Example 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of this application, as shown in Figure 4. Figure 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.

[0432] The first communication device 410 includes a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0433] The second communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0434] In the transmission from the first communication device 410 to the second communication device 450, at the first communication device 410, upper-layer data packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements L2 functionality. In the DL, the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ operation, 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 L1 (i.e., the physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and mapping of signal clusters based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), M-PSK, and M-Quadrature Amplitude Modulation (M-QAM)). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, generating one or more parallel streams. The transmit processor 416 then maps each parallel stream to a subcarrier, multiplexes the modulated symbols with a reference signal (e.g., a pilot) in the time and / or frequency domains, and then uses an inverse fast fourier transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol stream. The multi-antenna transmit processor 471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multi-antenna transmit processor 471 into an RF stream, which is then provided to a different antenna 420.

[0435] In the transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 456. The receiver processor 456 and the multi-antenna receiver processor 458 implement various L1 signal processing functions. The multi-antenna receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 454. The receiver processor 456 uses a Fast Fourier Transform (FFT) to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 456, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 458 after multi-antenna detection to recover any parallel stream destined for the second communication device 450. Symbols on each parallel stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted by the first communication device 410 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements L2 functionality. The controller / processor 459 may be associated with a memory 460 storing program code and data. The memory 460 may be referred to as computer-readable media. In the DL, the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer packets from the core network. The upper-layer packets are then provided to all protocol layers above L2. Various control signals may also be provided to L3 for L3 processing. The controller / processor 459 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0436] 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 data packets to the controller / processor 459. The data source 467 represents all protocol layers above L2. Similar to the transmission functions at the first communication device 410 described in the DL, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on the radio resource allocation of the first communication device 410, implementing L2 functions 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. Transmit processor 468 performs modulation mapping and channel coding processing, while multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming processing. Subsequently, transmit processor 468 modulates the generated parallel stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 457, the stream is provided to different antennas 452 via transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by multi-antenna transmit processor 457 into a radio frequency symbol stream before providing it to antenna 452.

[0437] In the transmission from the second communication device 450 to the first communication device 410, the function at the first communication device 410 is similar to the receiving function at the second communication device 450 described in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 472 and the receiving processor 470. The receiving processor 470 and the multi-antenna receiving processor 472 jointly implement the L1 function. The controller / processor 475 implements the L2 function. The controller / processor 475 may be associated with a memory 476 storing program code and data. The memory 476 may be referred to as computer-readable media. The controller / processor 475 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer data packets from the second communication device 450. The upper-layer data packets from the controller / processor 475 may be provided to the core network. The controller / processor 475 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0438] As one embodiment, the second communication device 450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second communication device 450 receives at least the first information block in this application, the first information block being configured for training data collection for the first cell set and training data collection for the second cell set in this application; the maximum buffer size of the second communication device 450 for training data collection is a first size, the size of the training data collection of the second communication device 450 for the first cell set is a first target size, and the size of the training data collection of the second communication device 450 for the second cell set is a second target size; the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the reporting of training data for the first cell set by the second communication device 450 references a first reference size, and the reporting of training data for the second cell set by the second communication device 450 references a second reference size; the second reference size is equal to the smaller of the candidate size and the second target size; the first reference size is equal to the difference between the first size and the second reference size; the candidate size is predefined, or the candidate size is configurable.

[0439] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that produces an action when executed by at least one processor, the action including: receiving the first information block in this application.

[0440] As one embodiment, the first communication device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The first communication device 410 transmits at least the first information block in this application, wherein the first information block is configured for training data collection for the first cell set and for training data collection for the second cell set in this application; the receiver of the first information block is the second communication device 450; the maximum buffer size of the second communication device 450 for training data collection is a first size, the size of the training data collection of the second communication device 450 for the first cell set is a first target size, and the size of the training data collection of the second communication device 450 for the second cell set is a second target size; the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the reporting of the training data of the second communication device 450 for the first cell set references a first reference size, and the reporting of the training data of the second cell set references a second reference size; the second reference size is equal to the smaller of the candidate size and the second target size; the first reference size is equal to the difference between the first size and the second reference size; the candidate size is predefined or the candidate size is configurable.

[0441] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that produces an action when executed by at least one processor, the action including: sending the first information block in this application.

[0442] As an example, the first node in this application includes the second communication device 450.

[0443] As an example, the second node in this application includes the first communication device 410.

[0444] As an example, at least one of {the antenna 420, the transmitter 418, the transmitter processor 416, the multi-antenna transmitter processor 471, the controller / processor 475, and the memory 476} is used to transmit the first information block in this application; at least one of {the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first information block in this application.

[0445] As an example, at least one of {the antenna 420, the transmitter 418, the transmitter processor 416, the multi-antenna transmitter processor 471, the controller / processor 475, and the memory 476} is used to transmit the first coefficient in this application; at least one of {the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first coefficient in this application.

[0446] As an example, at least one of {the antenna 452, the transmitter / receiver 454, the transmission processor 468, the multi-antenna transmission processor 457, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the second information block in this application; at least one of {the antenna 420, the receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the controller / processor 475, and the memory 476} is used to receive the second information block in this application.

[0447] As an example, at least one of {the antenna 452, the transmitter / receiver 454, the transmitting processor 468, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467} is used to transmit the first signal and the second signal in this application; at least one of {the antenna 420, the receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the controller / processor 475, and the memory 476} is used to receive the first signal and the second signal in this application.

[0448] Example 5

[0449] Example 5 illustrates a first flowchart of transmission between a first node and a second node according to an embodiment of this application, as shown in Figure 5. In Figure 5, the first node U1 and the second node N2 communicate via a wireless link, and the steps in blocks F51 and F52 are optional. It should be noted that the order in this embodiment does not limit the signal transmission order or the order of implementation in this application.

[0450] For the first node U1, the first information block is received in step S510; the second information block is sent in step S5110; and the first signal and the second signal are sent in step S5120.

[0451] For the second node N2, a first information block is sent in step S520; a second information block is received in step S5210; and a first signal and a second signal are received in step S5220.

[0452] In Embodiment 5, the maximum cache size for training data collection by the first node U1 is a first size; the size of the training data collection by the first node U1 for the first cell set is a first target size; and the size of the training data collection by the first node U1 for the second cell set is a second target size. The sum of the first target size and the second target size is greater than the first size. The first target size is not greater than the first size. The reporting of training data by the first node U1 for the first cell set references a first reference size, and the reporting of training data by the first node U1 for the second cell set references a second reference size. The second reference size is equal to the smaller of the candidate size and the second target size. The first reference size is equal to the difference between the first size and the second reference size. The candidate size is predefined or configurable.

[0453] As an example, the first node U1 is the first node in this application.

[0454] As an example, the second node N2 is the second node in this application.

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

[0456] As one embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between the relay node device and the user equipment.

[0457] As one embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between user equipment and user equipment.

[0458] As one example, the second node N2 and the first node U1 communicate via the Uu interface.

[0459] As one example, the second node N2 is the maintenance base station of the serving cell of the first node U1.

[0460] As one example, the second node N2 is a maintenance base station of the serving cell of the first node U1.

[0461] As an example, the logical channel occupied by the first information block includes DCCH (Dedicated Control Channel).

[0462] As an example, the first information block is carried by SRB1 (Signalling Radio Bearer 1).

[0463] As an example, the first information block is carried by SRB3 (Signalling Radio Bearer 3).

[0464] As an example, the transmission channel occupied by the first information block includes DL-SCH (DownLink-Shared Channel).

[0465] As an example, the physical layer channel occupied by the first information block includes PDSCH (Physical Downlink Shared Channel).

[0466] As an example, the physical layer channel occupied by the first information block includes the PDCCH (Physical Downlink Control Channel).

[0467] As an embodiment, the steps in box 51 of Figure 5 exist, and the method applied to the first node in this application includes: sending a second information block; the second information block indicates that the maximum cache size for the first node to collect training data has been reached or will be reached.

[0468] As one example, the second information block is transmitted via MAC layer signaling.

[0469] As an example, the second information block is transmitted via MAC CE.

[0470] As one embodiment, the second information block is transmitted via physical layer signaling.

[0471] As one embodiment, the second information block is transmitted via physical layer control signaling.

[0472] As an example, the second information block is transmitted via UCI (Uplink Control Information).

[0473] As an example, the second node receives the second information block and determines that the maximum cache size used by the first node for training data collection has been reached or will be reached.

[0474] As an example, the second information block includes a bit that directly indicates that the maximum cache size for the first node to collect training data has been reached or will be reached.

[0475] As a sub-implementation of this embodiment, the bit is 0, the bit indicates that the maximum cache size for the first node to collect training data will be reached; the bit is 1, the bit indicates that the maximum cache size for the first node to collect training data has been reached.

[0476] As a sub-implementation of this embodiment, the bit being 1 indicates that the maximum cache size for the first node to collect training data will be reached; the bit being 0 indicates that the maximum cache size for the first node to collect training data has been reached.

[0477] As a sub-implementation of this embodiment, the bit is 0, indicating that the size of the training data collection for the first node for the first cell set has been reached or will be reached; the bit is 1, indicating that the size of the training data collection for the second cell set has been reached or will be reached.

[0478] As a sub-implementation of this embodiment, the bit is 1, indicating that the size of the training data collection for the first node for the first cell set has been reached or will be reached; the bit is 0, indicating that the size of the training data collection for the second cell set has been reached or will be reached.

[0479] As an example, the second information block includes two bits that directly indicate that the maximum cache size for the first node to collect training data has been reached or will be reached.

[0480] As a sub-implementation of this embodiment, the two bits are 00, indicating that the maximum cache size for the first node to collect training data will be reached; the two bits are 11, indicating that the maximum cache size for the first node to collect training data has been reached.

[0481] As a sub-implementation of this embodiment, the two bits are 01, indicating that the size of the training data collected by the first node for the first cell set has been reached or will be reached; the two bits are 10, indicating that the size of the training data collected by the first node for the second cell set has been reached or will be reached.

[0482] As a sub-implementation of this embodiment, the two bits are 10, indicating that the size of the training data collected by the first node for the first cell set has been reached or will be reached; the two bits are 01, indicating that the size of the training data collected by the first node for the second cell set has been reached or will be reached.

[0483] As an example, the second information block indicates that the maximum cache size for the first node to collect training data has been reached.

[0484] As one example, the second information block indicates that the cache of the first node used for training data collection is full.

[0485] As an example, the statement that the maximum cache size for the first node to collect training data has been reached means that the storage resources of the first node used for collecting training data have been fully occupied.

[0486] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the storage resources already occupied in the storage resources of the first node for training data collection is a first size.

[0487] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the unoccupied storage resources in the storage resources used by the first node for training data collection is 0.

[0488] As one example, the second information block indicates that the maximum cache size for the first node to collect training data will be reached.

[0489] As one example, the second information block indicates that the cache of the first node used for training data collection is about to be full.

[0490] As an example, the maximum cache size to be reached by the first node for training data collection means that the storage resources of the first node for training data collection will be fully occupied.

[0491] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the unoccupied storage resources in the storage resources used by the first node for training data collection will be 0.

[0492] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the storage resources already occupied in the storage resources of the first node for training data collection is not less than or greater than a first threshold, wherein the first threshold is predefined, configurable, or implementation-related.

[0493] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the unoccupied storage resources in the storage resources used by the first node for training data collection is not greater than or less than a second threshold, which is predefined, configurable, or implementation-related.

[0494] As an example, the maximum cache size to be reached for the first node in training data collection means that the ratio of the size of the storage resources already occupied in the storage resources for training data collection of the first node to the first size is greater than a first ratio, which is predefined, configurable, or implementation-dependent.

[0495] As an example, the maximum cache size to be reached for the first node in training data collection means that the ratio of the size of the unoccupied storage resources in the storage resources used by the first node for training data collection to the first size is less than a second ratio, which is predefined, configurable, or implementation-dependent.

[0496] As one example, the second information block indicates the candidate size.

[0497] As one embodiment, the second information block carries a training data reporting request.

[0498] As one embodiment, the second information block carries a training data reporting indicator, which indicates that the first node is about to transmit the first signal and the second signal.

[0499] As one embodiment, the transmission channel occupied by the second information block includes UL-SCH (UpLink-Shared Channel).

[0500] As an example, the second information block is transmitted via PUCCH (Physical Uplink Control Channel).

[0501] As an example, the second information block is transmitted via PUSCH (Physical Uplink Shared Channel).

[0502] As an example, the steps in box 51 of Figure 5 are present, with step S5110 following step S510 and step S5210 following step S520.

[0503] As an example, the step in box 51 of Figure 5 is not present.

[0504] As an embodiment, the steps in box 52 of Figure 5 are present, and the method applied to the first node in this application includes: sending a first signal and a second signal, the first signal and the second signal respectively including the training data for the first cell set and the training data for the second cell set; the first signal refers to the first reference size, and the second signal refers to the second reference size.

[0505] As an example, the first signal is a baseband signal.

[0506] As an example, the first signal is a radio frequency signal.

[0507] As one example, the first signal includes a UEInformationResponse message.

[0508] As one embodiment, the second signal includes a UEInformationResponse message.

[0509] As an example, the first node sends the first signal.

[0510] As one embodiment, the first node sends the first signal, the first signal including the training data for the first cell set.

[0511] As one example, the first node sends the second signal.

[0512] As one embodiment, the first node sends the second signal, the second signal including the training data for the second set of cells.

[0513] As an example, this application does not limit whether the first signal and the second signal are sent simultaneously.

[0514] As an example, this application does not limit the timing order of the first signal and the second signal.

[0515] As an example, the first signal is associated with the first information block.

[0516] As one embodiment, the second signal is associated with the first information block.

[0517] As an example, the first signal is referenced to the first reference dimension.

[0518] As one embodiment, the meaning of the first signal referencing the first reference size includes: the training data of the first cell set occupies the buffer of the first reference signal size in the buffer used to collect training data, and the first signal transmits the training data in the buffer of the first reference signal size.

[0519] As an example, the meaning of "the first signal refers to the first reference size" includes: the size of the training data carried by the first signal is not greater than the first reference size.

[0520] As an example, the meaning of "the first signal refers to the first reference size" includes: the size of the training data carried by the first signal is at most the first reference size.

[0521] As one embodiment, the meaning of the first signal referencing the first reference size includes: the first signal generates a corresponding transport block based on training data of the first reference size.

[0522] As one embodiment, the first signal includes part or all of the training data for the first cell set, with a size equal to the first reference size.

[0523] As one embodiment, the second signal is referenced to the second reference dimension.

[0524] As one embodiment, the second signal referencing the second reference size means that: the training data of the second cell set occupies the buffer of the second reference signal size in the buffer used to collect training data, and the second signal transmits the training data in the buffer of the second reference signal size.

[0525] As one embodiment, the meaning of "the second signal refers to the second reference size" includes: the size of the training data carried by the second signal is not greater than the second reference size.

[0526] As one embodiment, the meaning of "the second signal refers to the second reference size" includes: the size of the training data carried by the second signal is at most the second reference size.

[0527] As one embodiment, the meaning of the second signal referencing the second reference size includes: the second signal generates a corresponding transport block based on training data of the second reference size.

[0528] As one embodiment, the second signal includes part or all of the training data for the second cell set, with a size equal to the second reference size.

[0529] As an example, the first signal is carried by the SRB.

[0530] As one embodiment, the second signal is carried by the SRB.

[0531] As an example, the first signal is carried by SRBx, where x is a positive integer not less than 4.

[0532] As an example, the second signal is carried by SRBx, where x is a positive integer not less than 4.

[0533] As a sub-example of the two embodiments described above, x equals 4.

[0534] As a sub-example of the two embodiments described above, x equals 5.

[0535] As an example, the transmission channel occupied by the first signal includes UL-SCH.

[0536] As an example, the physical layer channel occupied by the first signal includes PUSCH.

[0537] As one embodiment, the transmission channel occupied by the second signal includes UL-SCH.

[0538] As an example, the physical layer channel occupied by the second signal includes PUSCH.

[0539] As an example, the steps in box 52 of Figure 5 are present, with step S5120 following step S510 and step S5220 following step S520.

[0540] As an example, the step in box 52 of Figure 5 is not present.

[0541] As an example, the steps in boxes 51 and 52 of Figure 5 are both present, with the steps in box 52 following the steps in box 51.

[0542] As an example, the steps in boxes 51 and 52 of Figure 5 are not present.

[0543] Example 6

[0544] Example 6 illustrates a second flowchart of transmission between a first node and a second node according to an embodiment of this application, as shown in Figure 6. In Figure 6, the first node U3 and the second node N4 communicate via a wireless link. It should be noted that the order in this embodiment does not limit the signal transmission order or the order of implementation in this application.

[0545] For the first node U3, the first coefficient is received in step S630.

[0546] For the second node N4, the first coefficient is sent in step S640.

[0547] In Example 6, the first coefficient is used by the first node U3 to determine the candidate size.

[0548] As an example, the first node U3 is the first node in this application.

[0549] As an example, the second node N4 is the second node in this application.

[0550] As one embodiment, the air interface between the second node N4 and the first node U3 includes a wireless interface between the base station equipment and the user equipment.

[0551] As one embodiment, the air interface between the second node N4 and the first node U3 includes a wireless interface between the relay node device and the user equipment.

[0552] As one embodiment, the air interface between the second node N4 and the first node U3 includes a wireless interface between user equipment and user equipment.

[0553] As one example, the second node N4 and the first node U3 communicate via the Uu interface.

[0554] As one example, the second node N4 is the sustaining base station for the serving cell of the first node U3.

[0555] As one example, the second node N4 is a maintenance base station of the serving cell of the first node U3.

[0556] As an example, the first coefficient is a percentage between 0% and 100%.

[0557] As an example, the first coefficient is a real number between 0 and 1.

[0558] As an example, the first coefficient is equal to 0.

[0559] As an example, the first coefficient is equal to 1.

[0560] As an example, the first coefficient is predetermined.

[0561] As an example, the first coefficient is fixed.

[0562] As an example, the first coefficient is configurable.

[0563] As an example, the first coefficient is configured by the network.

[0564] As an example, the first coefficient is configured by the base station.

[0565] As an example, the first coefficient is configured by the second node U3.

[0566] As an example, the first coefficient is indicated by the second node U3.

[0567] As an example, the first coefficient is indicated by higher-level signaling.

[0568] As an example, the first coefficient is indicated via an RRC message.

[0569] As an example, the first coefficient is indicated via RRC signaling.

[0570] As an example, the first coefficient is indicated by the first information block in this application.

[0571] As an example, the first information block includes a first field, which directly indicates the first coefficient.

[0572] As an example, the first coefficient is indicated by MAC CE.

[0573] As an example, the first coefficient is indicated by physical layer signaling.

[0574] As an example, the first coefficient is indicated by physical layer control signaling.

[0575] As an example, the first coefficient is indicated by PDCCH.

[0576] As an example, the first coefficient is indicated by DCI.

[0577] As an example, the first coefficient is used by the first node U3 to determine the candidate size.

[0578] As an example, the candidate size is equal to the product of the first size and the first coefficient.

[0579] As an example, the candidate size is equal to the first size minus the difference between the product of the first size and the first coefficient.

[0580] As an example, step S630 follows step S510 in Figure 5; step S640 follows step S520 in Figure 5.

[0581] As an example, step S630 precedes step S510 in Figure 5; step S640 precedes step S520 in Figure 5.

[0582] As an example, the first coefficient is carried by the first information block, and step S630 occurs simultaneously with step S510 in Figure 5; step S640 occurs simultaneously with step S520 in Figure 5.

[0583] As an example, steps S630 and S640 are performed before the steps in block 51 of Figure 5.

[0584] As an example, steps S630 and S640 precede the steps in block 52 of Figure 5.

[0585] As an example, the logical channel occupied by the signaling transmitting the first coefficient includes DCCH.

[0586] As an example, the signaling for transmitting the first coefficient is carried by SRB1.

[0587] As an example, the signaling for transmitting the first coefficient is carried by SRB3.

[0588] As an example, the transmission channel occupied by the signaling transmitting the first coefficient includes DL-SCH.

[0589] As an example, the physical layer channel occupied by the signaling transmitting the first coefficient includes PDSCH.

[0590] As an example, the physical layer channel occupied by the signaling transmitting the first coefficient includes PDCCH.

[0591] Example 7

[0592] Example 7 illustrates a first schematic diagram of a first reference size and a second reference size according to an embodiment of this application, as shown in Figure 7. In Figure 7, the rectangles with thick outlines represent the cache for training data collection of the first node, the size of which is the first size, wherein the rectangles filled with diamond crosses represent the cache of the first reference size, and the rectangles filled with crosses represent the cache of the second reference size.

[0593] In embodiment 7, the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the smaller of the candidate size and the second target size is the second target size; the second reference size is equal to the second target size, and the first reference size is equal to the difference between the first size and the second target size.

[0594] As an example, the smaller of the candidate size and the second target size is the second target size; the second reference size is equal to the second target size, and the first reference size is equal to the difference between the first size and the second target size.

[0595] As an example, the sum of the first target size and the candidate size is greater than the first size.

[0596] As an example, the training data collection for the first cell set preferentially occupies the cache outside the candidate size in the maximum cache of the first node used for training data collection.

[0597] As an example, the training data collection for the second cell set only occupies a portion of the candidate size in the maximum cache of the first node used for training data collection.

[0598] As an example, in Figure 7, the training data collection for the first cell set occupies the cache of the first node for training data collection in a left-to-right order.

[0599] As a sub-example of this embodiment, the meaning of occupying the cache of the first node for training data collection from left to right includes: the first node will only occupy the cache for training data collection for the first cell set in the candidate size when all caches outside the candidate size are occupied.

[0600] As a sub-implementation of this embodiment, the meaning of occupying the cache of the first node for training data collection from left to right includes: when the cache other than the candidate size is not fully occupied, the training data collection for the first cell set will not occupy the cache for training data collection for the first cell set in the candidate size.

[0601] Example 8

[0602] Example 8 illustrates a second schematic diagram of a first reference size and a second reference size according to an embodiment of this application, as shown in Figure 8. In Figure 8, the rectangles with thick outlines represent the cache for training data collection of the first node, the size of which is the first size, wherein the rectangles filled with diamond crosses represent the cache of the first reference size, and the rectangles filled with cross crosses represent the cache of the second reference size.

[0603] In embodiment 8, the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the smaller of the candidate size and the second target size is the candidate size; the second reference size is equal to the candidate size, and the first reference size is equal to the difference between the first size and the candidate size.

[0604] As an example, the sum of the first target size and the candidate size is greater than the first size.

[0605] As an example, the smaller of the candidate size and the second target size is the candidate size; the second reference size is equal to the candidate size, and the first reference size is equal to the difference between the first size and the candidate size.

[0606] As an example, the training data collection for the first cell set preferentially occupies the cache outside the candidate size in the maximum cache of the first node used for training data collection.

[0607] As an example, the training data collection for the first cell set only uses the cache outside the candidate size in the maximum cache of the first node used for training data collection.

[0608] As an example, the training data collection for the first cell set only occupies the candidate size cache in the maximum cache of the first node used for training data collection.

[0609] As an example, when the second reference size is equal to the candidate size, the training data collection for the first cell set only occupies the cache other than the candidate size in the maximum cache of the first node used for training data collection.

[0610] Example 9

[0611] Example 9 illustrates a schematic diagram of a first target size and a second target size according to an embodiment of this application, as shown in Figure 9. In Figure 9, the first target size is based on prediction, or the first target size is based on actual training data collection for the first cell set; the second target size is based on prediction, or the second target size is based on actual training data collection for the second cell set.

[0612] As one embodiment, the first target size is based on prediction, or the first target size is based on the actual training data collection for the first cell set.

[0613] As an example, the first target size is predicted based on the first node.

[0614] As an example, the first target size is predicted by the first node based on the configuration of the training data collected by the first node regarding the first cell set.

[0615] As an example, the first target size is the size of the cache required by the first node for collecting training data for the first cell set at a future time point after receiving the first information block.

[0616] As an example, the first target size is the size of the training data for the first cell set that the first node will collect.

[0617] As an example, the first target size is the size of the training data for the first cell set that the first node would collect without pruning.

[0618] As an example, the first target size is based on the actual training data collection for the first cell set.

[0619] As an example, the first target size is based on the actual size of the cache required for collecting the training data for the first cell set.

[0620] As an example, the first target size is based on the size of the cache required for the current collection of training data for the first cell set.

[0621] As one embodiment, the second target size is based on prediction, or the second target size is based on the actual training data collection for the second cell set.

[0622] As one example, the second target size is predicted based on the first node.

[0623] As one embodiment, the second target size is predicted by the first node based on the configuration of the training data collected by the first node regarding the second cell set.

[0624] As an example, the second target size is the size of the cache required by the first node for collecting training data for the second cell set at a future time point after receiving the first information block.

[0625] As an example, the second target size is the size of the training data that the first node will collect for the second cell set.

[0626] As an example, the second target size is the size of the training data for the second cell set that would be collected by the first node without pruning.

[0627] As one embodiment, the second target size is based on the size of the cache required for the actual collection of training data for the second cell set.

[0628] As one embodiment, the second target size is based on the size of the cache required for the current collection of training data for the second cell set.

[0629] Example 10

[0630] Example 10 illustrates a first schematic diagram of a first cell set and a second cell set according to an embodiment of this application, as shown in Figure 10. In Figure 10, the MCG includes one PCell and at least one SCell, and the SCG includes one PSCell and at least one SCell.

[0631] In Example 10, the first cell set corresponds to the MCG, and the second cell set corresponds to the SCG.

[0632] As an example, MCG refers to Master Cell Group.

[0633] As an example, SCG refers to Secondary Cell Group.

[0634] As an example, PCell in Figure 10 refers to Primary Cell.

[0635] As an example, SCell in Figure 10 refers to Secondary Cell.

[0636] As an example, PSCell in Figure 10 refers to Primary Secondary Cell.

[0637] As an example, the first cell set corresponds to the MCG, and the second cell set corresponds to the SCG.

[0638] As one embodiment, the first cell set is the MCG of the first node; the second cell set is the SCG of the first node.

[0639] As one embodiment, the first cell set includes at least one serving cell in the MCG of the first node; the second cell set includes at least one serving cell in the SCG of the first node.

[0640] As an example, the serving cells included in the first cell set all belong to the MCG of the first node; the serving cells included in the second cell set all belong to the SCG of the first node.

[0641] As an example, the cells included in the MCG are all 6G cells.

[0642] As an example, the cells included in the MCG are all 6G cells, and the cells included in the SCG are all 5G cells.

[0643] As an example, both the cells included in the MCG and the cells included in the SCG are 5G cells.

[0644] As an example, both the cells included in the MCG and the cells included in the SCG are 6G cells.

[0645] Example 11

[0646] Example 11 illustrates a second schematic diagram of a first cell set and a second cell set according to an embodiment of this application, as shown in Figure 11. In Figure 11, the first cell set corresponds to 6G cells, and the second cell set corresponds to 5G cells.

[0647] As an example, the 6G cell is a cell that supports 6G services.

[0648] As an example, the 6G cell refers to a cell whose radio access mode is 6G.

[0649] As an example, the 5G cell is a cell that supports 5G services.

[0650] As an example, the 5G cell is a cell that supports NR (New Radio) services.

[0651] As an example, the 5G cell refers to a cell whose radio access mode is NR.

[0652] As an example, the first cell set corresponds to 6G cells, and the second cell set corresponds to 5G cells.

[0653] As an example, the first set of cells includes 6G cells; the second set of cells includes 5G cells.

[0654] As one embodiment, the first cell set includes the 6G serving cells of the first node; the second cell set includes the 5G serving cells of the first node.

[0655] As one embodiment, the first cell set is the MCG of the first node, and the cells included in the MCG are 6G cells; the second cell set is the SCG of the second node, and the cells included in the SCG are 5G cells.

[0656] As an example, the first cell set corresponds to the serving cell of the first node and the neighboring cells of the serving cell of the first node.

[0657] Example 12

[0658] Example 12 illustrates a schematic diagram of a parameter set according to an embodiment of this application, as shown in Figure 12. In Figure 12, the parameter set includes at least one of the time-frequency resources occupied by the reporting of the training data and the conditions that trigger the reporting of the training data.

[0659] In embodiment 12, the first information block configures the training data collection for the first cell set and the parameter set for the training data collection for the second cell set.

[0660] As an example, the first information block configures a set of parameters for the training data collection for the first cell set and for the training data collection for the second cell set. The set of parameters includes at least one of the time-frequency resources occupied by the reporting of the training data and the conditions that trigger the reporting of the training data.

[0661] As an example, the first information block configures the parameter sets for the training data collection for the first cell set and the training data collection for the second cell set.

[0662] As an example, the parameter set includes at least one of the time-frequency resources occupied by the reporting of the training data and the conditions that are met to trigger the reporting of the training data.

[0663] As an example, the parameter set includes the time-frequency resources occupied by the reporting of the training data and the conditions that must be met to trigger the reporting of the training data.

[0664] As one embodiment, the parameter set includes the time-frequency resources occupied by the reporting of the training data.

[0665] As an example, the parameter set includes the temporal resources occupied by the reporting of the training data.

[0666] As an example, the parameter set configures the time-domain resources occupied by the first signal.

[0667] As an example, the parameter set includes the offset value between the temporal domain resources occupied by the reporting of the training data and the second information block.

[0668] As an example, the parameter set includes the starting time slot of the time domain resources occupied by the reporting of the training data.

[0669] As an example, the parameter set includes the start symbol of the time-domain resources occupied by the reporting of the training data.

[0670] As one embodiment, the parameter set includes the frequency domain resources occupied by the reporting of the training data.

[0671] As an example, the parameter set configures the frequency domain resources occupied by the first signal.

[0672] As one embodiment, the parameter set includes the conditions that trigger the reporting of the training data.

[0673] As an example, the condition for triggering the reporting of the training data is: the first node sends the second information block.

[0674] As an example, the condition for triggering the reporting of the training data is that the maximum cache size of the first node for collecting training data has been reached.

[0675] As an example, the condition for triggering the reporting of the training data is that the maximum cache size of the first node for collecting training data will be reached.

[0676] As an example, the condition for triggering the reporting of the training data is that the remaining power of the first node is low.

[0677] As an example, the condition for triggering the reporting of the training data is: the remaining power of the first node is lower than or not higher than a given threshold, wherein the given threshold is predefined or implementation-related.

[0678] As an example, the condition for triggering the reporting of the training data is: periodic reporting.

[0679] As an example, the condition for triggering the reporting of the training data is: semi-continuous reporting.

[0680] As an example, the condition for triggering the reporting of the training data is: non-periodic reporting.

[0681] As an example, the condition for triggering the reporting of the training data is: event-triggered.

[0682] As an example, the condition for triggering the reporting of the training data is: on-demand reporting.

[0683] Example 13

[0684] Example 13 illustrates a schematic diagram of RAN domain AI / ML function deployment according to one embodiment of this application, as shown in Figure 13. In Figure 13, the gNB can be replaced with, for example, an eNB, or a network device such as a 6G base station.

[0685] In Example 13, the management of ML inference functions of multiple base stations is completed by RAN domain management function 1302, that is, data interaction with RAN domain MnS (Management Service) consumers / cross-domain management 1301 (as shown by the dashed arrows in Figure 13). RAN domain ML training function 1303 is located in RAN domain management function 1302; while ML inference functions are located in the base stations, that is, AI / ML inference function 1304 is located in gNB 1305, AI / ML inference function 1306 is located in gNB 1307, and so on.

[0686] AI / ML related functions include ML training (also known as AI training or AI / ML training), ML testing, and ML inference (also known as AI inference or AI / ML inference), etc. ML training, ML testing, and ML inference functions can be deployed independently or co-located. Deployment of AI / ML related functions can be implemented through software, such as downloading and / or running executable files; or it can be implemented through a combination of software and hardware, such as accelerating specific computing units through hardware to improve computing speed or save power.

[0687] ML training functions can be deployed in a cross-domain management system or a domain-specific management system; the domain-specific management system is used to manage the RAN domain or the CN (Core Network) domain. For example, ML training functions for MDA (Management Data Analytics) can be deployed in MDAF (Management Data Analytic Function); ML training for network data analytics can be deployed in NWDAF (Network Data Analytics Function), meaning the ML training function is an MTLF (Model Training Logical Function).

[0688] The ML inference function can also be deployed in a cross-domain management system or a domain-specific management system; for example, the ML inference function is MDAF, or the ML inference function is AnLF (Analytics Logical Function) located in NWDAF.

[0689] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[0690] Optionally, the management of ML inference function can also be completed by the base station itself, that is, each base station can independently interact with the RAN domain MnS consumer / cross-domain management 1301.

[0691] It should be noted that Embodiment 13 is merely a non-limiting implementation method; optionally, the ML training function of the RAN domain may also be deployed in the base station; or optionally, some base stations may deploy both the ML inference function and the ML training function of the RAN domain, while some base stations may only deploy the ML inference function.

[0692] As an example, one of the gNBs (or base stations) in Example 13 is the second node of this application.

[0693] Example 14

[0694] Example 14 illustrates a schematic diagram of the deployment of AI / ML functions in a UE according to one embodiment of this application, as shown in Figure 14. In Figure 14, the RAN domain ML training function 1404 is optional.

[0695] UE function 1403 is deployed in the first node of this application, and the UE function 1403 includes AI / ML inference function 1405; the AI / ML inference function 1405 uses an ML model (also called an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[0696] As an example, the UE function 1403 includes a RAN domain ML training function 1404, which runs training data through an ML model to obtain a relevant loss and adjusts the parameters of the ML model based on the calculated loss; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0697] The above embodiments can reduce the complexity of the base station, or save air interface resources caused by reporting training data; however, the above embodiments place high demands on the processing capabilities of the UE side.

[0698] Optionally, the UE function 1403 also includes a CN domain ML training function (not shown in Figure 14).

[0699] Optionally, the UE function 1403 also includes an AI / ML deployment function—not shown in Figure 14—for loading ML models and data.

[0700] As an example, the first node indicates whether it supports ML training function (RAN domain or CN domain) through capability reporting. The capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0701] As an example, the ML model and the associated metadata are loaded by the first node from a network device or a remote server.

[0702] Optionally, the UE function 1403 is an MnS producer that provides data to the CN domain MnF (Management Function) and / or the RAN domain MnF and / or the cross-domain management system 1401 for management or analysis (as shown by the double arrow 1402).

[0703] Optionally, the UE function 1403 is an MnS consumer that loads data from the CN domain MnF and / or RAN domain MnF and / or cross-domain management system 1401 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1402).

[0704] As an example, the ML model is based on NN (Neural Networks).

[0705] As an example, the ML model is based on ANN (Artificial Neural Networks).

[0706] As an example, the ML model is based on CNN (Convolutional Neural Networks).

[0707] As an example, the ML model is based on the LLM (Large Language Model) architecture.

[0708] As an example, the ML model is based on the Transformer architecture.

[0709] As an example, the ML model is based on the GPT (Generative Pre-Trained) architecture.

[0710] As an example, the ML model is based on LSTM (Long Short-Term Memory network).

[0711] As an example, the ML model is based on MLP (MultiLayer Perceptron).

[0712] As an example, the ML model is based on GAN (Generative Adversarial Networks).

[0713] As an example, the ML model is based on a lightweight neural network.

[0714] As a sub-example of this embodiment, the lightweight neural network includes one or more of MobileNet, ShuffleNet, and SqueezeNet.

[0715] Example 15

[0716] Example 15 illustrates a schematic diagram of an artificial intelligence or machine learning-based processing system according to an embodiment of this application, as shown in Figure 15. In Figure 15, the artificial intelligence or machine learning-based processing system includes a first processor, a second processor, a third processor, and a fourth processor.

[0717] In Example 15, the first processor sends a first dataset to the second processor and a second dataset to the third processor; the second processor generates a target first-class parameter set based on the first dataset, and sends the generated target first-class parameter set to the third processor; the third processor processes the second dataset using the target first-class parameter set to obtain a first-class output, optionally sending the first-class output to the fourth processor. In Figure 15, the first-class feedback and the second-class feedback are optional; the second processor includes ML training functionality; the third processor includes ML inference functionality.

[0718] As one embodiment, the fourth processor includes ML testing functionality.

[0719] As one embodiment, the fourth processor includes performance monitoring / evaluation of the ML model.

[0720] As an example, the third processor sends a first type of feedback to the second processor; the first type of feedback is used to trigger the recalculation or update of the target first type of parameter set, that is, to trigger ML initial training or ML retraining.

[0721] As one embodiment, the fourth processor sends a second type of feedback to the first processor; the second type of feedback is used to generate the first dataset or the second dataset, or the second type of feedback is used to trigger the sending of the first dataset or the sending of the second dataset.

[0722] As one embodiment, the first processor generates the first dataset and the second dataset based on the measurement of the reference signal.

[0723] As one embodiment, the third processor belongs to the first node, and the fourth processor belongs to the second node.

[0724] As an example, the third processor belongs to the first node.

[0725] As an example, the first dataset includes training data.

[0726] As one embodiment, the first dataset includes the training data for the first cell set collected by the first node.

[0727] As an example, the first dataset includes the training data collected by the first node for the second set of cells.

[0728] As one embodiment, the first dataset includes the training data collected by the first node for the first cell set and the training data for the second cell set.

[0729] As one embodiment, the second processor is used to train an ML model, and the trained model is described by the target first class of parameter sets.

[0730] As an example, the second processor belongs to the first node; the above method avoids passing the first dataset to the second node.

[0731] As an example, the second processor belongs to the second node in this application; the above method supports joint training and optimizes system performance.

[0732] As an example, the second processor belongs to the core network; the above method supports network-wide joint training, further optimizing system performance.

[0733] As an example, the second dataset includes inference data.

[0734] As an example, the third processor constructs a model based on the target first type of parameter group, and then inputs the second dataset into the constructed model to obtain the first type of output.

[0735] As an example, the third processor generates a recovery dataset based on the first type of output, and the error between the recovery dataset and the second dataset is used to generate the first type of feedback.

[0736] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the second processing opportunity will recalculate the target first type of parameter set.

[0737] As an example, when the error is too large or the update has not been performed for too long, the performance of the trained model is considered to be unsatisfactory.

[0738] As an example, the target first type of parameter group includes one or more of the following: convolution kernel, pooling kernel, pooling function, activation function, parameters of the pooling function, or parameters of the activation function.

[0739] As an example, the target first type of parameter group includes one or more of the following: convolution kernel size, number of convolution layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[0740] Example 16

[0741] Example 16 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application, as shown in Figure 16. In Figure 16, the first and second operations 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; the arrowed lines indicate the sequence of processes.

[0742] As an example, the first operation includes AI / ML training, the second operation includes AI / ML testing, the third operation includes AI / ML emulation, the fourth operation includes AI / ML entity loading, and the fifth operation includes AI / ML inference.

[0743] 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.

[0744] As an example, the first stage includes AI / ML model training.

[0745] As an example, the training data for the first cell set is used in the first phase.

[0746] As an example, the training data for the second cell set is used in the first phase.

[0747] As an example, the first stage includes AI / ML model training and AI / ML testing.

[0748] As an example, the AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[0749] As an example, the training of the AI / ML model depends on training data.

[0750] As an example, the AI / ML model training includes AI / ML entity validation.

[0751] As an example, the AI / ML entity verification is used to evaluate the performance of the AI / ML entity.

[0752] As an example, the AI / ML entity verification relies on verification data.

[0753] As an example, if the AI / ML entity verification results do not meet expectations, the AI / ML model will be retrained.

[0754] As an example, the AI / ML testing includes testing the validated AI / ML entities to estimate the performance of the trained AI / ML model.

[0755] As an example, if the AI / ML test results meet expectations, the AI / ML entity proceeds to the next stage; otherwise, the AI / ML model will be retrained.

[0756] As an example, the AI / ML test relies on test data.

[0757] As one embodiment, the second stage includes AI / ML simulation, which performs AI / ML entity reasoning in a simulation environment.

[0758] As an example, the AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using AI / ML entities.

[0759] As one embodiment, the second stage is optional.

[0760] As an example, the third stage includes AI / ML entity loading, which is to obtain trained AI / ML entities to obtain the desired AI / ML inference function.

[0761] As an example, the third stage is optional.

[0762] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[0763] As an example, the fourth stage includes AI / ML inference.

[0764] Example 17

[0765] Example 17 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of this application, as shown in Figure 17. In Figure 17, the processing apparatus 1700 in the first node includes a first receiver 1701 and a first transmitter 1702, wherein the first transmitter 1702 is optional.

[0766] In embodiment 17, the first receiver 1701 receives a first information block, the first information block being configured for training data collection for a first cell set and training data collection for a second cell set;

[0767] In Example 17, the maximum cache size for training data collection by the first node is a first size; the size of the training data collection by the first node for the first cell set is a first target size; and the size of the training data collection by the first node for the second cell set is a second target size. The sum of the first target size and the second target size is greater than the first size. The first target size is not greater than the first size. The first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size. The second reference size is equal to the smaller of the candidate size and the second target size. The first reference size is equal to the difference between the first size and the second reference size. The candidate size is predefined or configurable.

[0768] As one embodiment, the first target size is based on prediction, or the first target size is based on actual training data collection for the first cell set; the second target size is based on prediction, or the second target size is based on actual training data collection for the second cell set.

[0769] As one embodiment, the first transmitter 1702 transmits a first signal and a second signal, the first signal and the second signal respectively including training data for the first cell set and training data for the second cell set; the first signal references the first reference size, and the second signal references the second reference size.

[0770] As an example, the first transmitter 1702 sends a second information block; the second information block indicates that the maximum buffer size for the first node to collect training data has been reached or will be reached.

[0771] As an example, the first receiver 1701 receives a first coefficient, which is used to determine the candidate size.

[0772] As one example, the first cell set corresponds to MCG, and the second cell set corresponds to SCG; or, the first cell set corresponds to 6G cells, and the second cell set corresponds to 5G cells.

[0773] As an example, the first information block configures a set of parameters for the training data collection for the first cell set and for the training data collection for the second cell set. The set of parameters includes at least one of the time-frequency resources occupied by the reporting of the training data and the conditions that trigger the reporting of the training data.

[0774] As an example, the training data collection for the first cell set preferentially occupies the cache outside the candidate size in the maximum cache of the first node used for training data collection.

[0775] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the storage resources already occupied in the storage resources of the first node for training data collection is not less than or greater than a first threshold, wherein the first threshold is predefined, configurable, or implementation-related.

[0776] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the unoccupied storage resources in the storage resources used by the first node for training data collection is not greater than or less than a second threshold, which is predefined, configurable, or implementation-related.

[0777] As an example, the maximum cache size to be reached for the first node in training data collection means that the ratio of the size of the storage resources already occupied in the storage resources for training data collection of the first node to the first size is greater than a first ratio, which is predefined, configurable, or implementation-dependent.

[0778] As an example, the maximum cache size to be reached for the first node in training data collection means that the ratio of the size of the unoccupied storage resources in the storage resources used by the first node for training data collection to the first size is less than a second ratio, which is predefined, configurable, or implementation-dependent.

[0779] As one example, the second information block indicates the candidate size.

[0780] As one embodiment, the second information block carries a training data reporting request.

[0781] As one embodiment, the second information block carries a training data reporting indicator, which indicates that the first node is about to transmit the first signal and the second signal.

[0782] As an example, the first node 1700 is a user equipment.

[0783] As an example, the first node 1700 is a terminal.

[0784] As an example, the first node 1700 is a relay node device.

[0785] As an example, the first receiver 1701 includes at least one of the following in embodiment 4: the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467.

[0786] As an example, the first transmitter 1702 includes at least one of the following in embodiment 4: the antenna 452, the transmitter 454, the transmission processor 468, the multi-antenna transmission processor 457, the controller / processor 459, the memory 460, and the data source 467.

[0787] Example 18

[0788] Example 18 illustrates a structural block diagram of a processing apparatus for a second node according to an embodiment of this application, as shown in Figure 18. In Figure 18, the processing apparatus 1800 in the second node includes a second transmitter 1801 and a second receiver 1802, wherein the second receiver 1802 is optional.

[0789] In embodiment 18, the second transmitter 1801 transmits a first information block, the first information block being configured for training data collection for a first cell set and training data collection for a second cell set;

[0790] In embodiment 18, the receiver of the first information block is a first node; the maximum cache size for training data collection by the first node is a first size, the size of the training data collection by the first node for the first cell set is a first target size, and the size of the training data collection by the first node for the second cell set is a second target size; the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size; the second reference size is equal to the smaller of the candidate size and the second target size; the first reference size is equal to the difference between the first size and the second reference size; the candidate size is predefined, or the candidate size is configurable.

[0791] As one embodiment, the first target size is based on prediction, or the first target size is based on actual training data collection for the first cell set; the second target size is based on prediction, or the second target size is based on actual training data collection for the second cell set.

[0792] As one embodiment, the second receiver 1802 receives a first signal and a second signal, the first signal and the second signal respectively including the training data for the first cell set and the training data for the second cell set;

[0793] Wherein, the first signal is referenced to the first reference size, and the second signal is referenced to the second reference size.

[0794] As one embodiment, the second receiver 1802 receives a second information block; the second information block indicates that the maximum buffer size for the first node to collect training data has been reached or will be reached.

[0795] As an example, the second transmitter 1801 transmits a first coefficient, which is used to determine the candidate size.

[0796] As one example, the first cell set corresponds to MCG, and the second cell set corresponds to SCG; or, the first cell set corresponds to 6G cells, and the second cell set corresponds to 5G cells.

[0797] As an example, the first information block configures a set of parameters for the training data collection for the first cell set and for the training data collection for the second cell set. The set of parameters includes at least one of the time-frequency resources occupied by the reporting of the training data and the conditions that trigger the reporting of the training data.

[0798] As an example, the training data collection for the first cell set preferentially occupies the cache outside the candidate size in the maximum cache of the first node used for training data collection.

[0799] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the storage resources already occupied in the storage resources of the first node for training data collection is not less than or greater than a first threshold, wherein the first threshold is predefined, configurable, or implementation-related.

[0800] As an example, the maximum cache size to be reached by the first node for training data collection means that the size of the unoccupied storage resources in the storage resources used by the first node for training data collection is not greater than or less than a second threshold, which is predefined, configurable, or implementation-related.

[0801] As an example, the maximum cache size to be reached for the first node in training data collection means that the ratio of the size of the storage resources already occupied in the storage resources for training data collection of the first node to the first size is greater than a first ratio, which is predefined, configurable, or implementation-dependent.

[0802] As an example, the maximum cache size to be reached for the first node in training data collection means that the ratio of the size of the unoccupied storage resources in the storage resources used by the first node for training data collection to the first size is less than a second ratio, which is predefined, configurable, or implementation-dependent.

[0803] As one example, the second information block indicates the candidate size.

[0804] As one embodiment, the second information block carries a training data reporting request.

[0805] As one embodiment, the second information block carries a training data reporting indicator, which indicates that the first node is about to transmit the first signal and the second signal.

[0806] As one example, the second node 1800 is a base station device.

[0807] As one embodiment, the second node 1800 is a user equipment.

[0808] As an example, the second node 1800 is a TRP.

[0809] As one embodiment, the second transmitter 1801 includes at least one of the following in embodiment 4: the antenna 420, the transmitter 418, the transmission processor 418, the multi-antenna transmission processor 471, the controller / processor 475, and the memory 476.

[0810] As one embodiment, the second receiver 1802 includes at least one of the following in embodiment 4: the antenna 420, the receiver 418, the receiver processor 470, the multi-antenna receiver processor 472, the controller / processor 475, and the memory 476.

[0811] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The user equipment, terminal, and UE in this application include, but are not limited to, drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablets, laptops, vehicle-mounted communication equipment, vehicles, RSUs, wireless sensors, internet cards, IoT 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, internet cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base stations or system equipment in this application include, but are not limited to, macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNB (evolved Node B), gNB, TRP, GNSS (Global Navigation Satellite System), relay satellites, satellite base stations, airborne base stations, RSUs, unmanned aerial vehicles, and test equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[0812] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A first node used in wireless communication and artificial intelligence, characterized in that, include: A first receiver receives a first information block, wherein the first information block is configured to collect training data for a first cell set and collect training data for a second cell set. Wherein, the maximum cache size for training data collection by the first node is a first size; the size of the training data collection by the first node for the first cell set is a first target size; and the size of the training data collection by the first node for the second cell set is a second target size. The sum of the first target size and the second target size is greater than the first size. The first target size is not greater than the first size. The first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size. The second reference size is equal to the smaller of the candidate size and the second target size. The first reference size is equal to the difference between the first size and the second reference size. The candidate size is predefined or configurable.

2. The first node according to claim 1, characterized in that, The first target size is based on prediction, or the first target size is based on actual training data collection for the first cell set; the second target size is based on prediction, or the second target size is based on actual training data collection for the second cell set.

3. The first node according to claim 1 or 2, characterized in that, include: A first transmitter transmits a first signal and a second signal, the first signal and the second signal respectively including training data for the first cell set and training data for the second cell set; Wherein, the first signal is referenced to the first reference size, and the second signal is referenced to the second reference size.

4. The first node according to any one of claims 1 to 3, characterized in that, include: The first transmitter sends the second information block; The second information block indicates that the maximum cache size used by the first node for training data collection has been reached or will be reached.

5. The first node according to any one of claims 1 to 4, characterized in that, include: The first receiver receives a first coefficient, which is used to determine the candidate size.

6. The first node according to any one of claims 1 to 5, characterized in that, The first cell set corresponds to MCG, and the second cell set corresponds to SCG; or, the first cell set corresponds to 6G cells, and the second cell set corresponds to 5G cells.

7. The first node according to any one of claims 1 to 6, characterized in that, The first information block configures a set of parameters for the training data collection for the first cell set and for the training data collection for the second cell set. The set of parameters includes at least one of the time-frequency resources occupied by the reporting of the training data and the conditions that are met to trigger the reporting of the training data.

8. The first node according to any one of claims 1 to 7, characterized in that, The training data collection for the first cell set preferentially occupies the cache outside the candidate size in the maximum cache of the first node used for training data collection.

9. A second node used in wireless communication and artificial intelligence, characterized in that, include: The second transmitter transmits a first information block, which is configured to collect training data for a first cell set and collect training data for a second cell set. Wherein, the receiver of the first information block is the first node; the maximum cache size for training data collection by the first node is a first size, the size of the training data collection by the first node for the first cell set is a first target size, and the size of the training data collection by the first node for the second cell set is a second target size; the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size; the second reference size is equal to the smaller of the candidate size and the second target size; the first reference size is equal to the difference between the first size and the second reference size; the candidate size is predefined, or the candidate size is configurable.

10. A method for use as a first node in wireless communication and artificial intelligence, characterized in that, include: Receive a first information block, wherein the first information block configures the collection of training data for a first cell set and the collection of training data for a second cell set; Wherein, the maximum cache size for training data collection by the first node is a first size; the size of the training data collection by the first node for the first cell set is a first target size; and the size of the training data collection by the first node for the second cell set is a second target size. The sum of the first target size and the second target size is greater than the first size. The first target size is not greater than the first size. The first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size. The second reference size is equal to the smaller of the candidate size and the second target size. The first reference size is equal to the difference between the first size and the second reference size. The candidate size is predefined or configurable.

11. A method for a second node used in wireless communication and artificial intelligence, characterized in that, include: Send a first information block, the first information block configuring training data collection for a first cell set and training data collection for a second cell set; Wherein, the receiver of the first information block is the first node; the maximum cache size for training data collection by the first node is a first size, the size of the training data collection by the first node for the first cell set is a first target size, and the size of the training data collection by the first node for the second cell set is a second target size; the sum of the first target size and the second target size is greater than the first size; the first target size is not greater than the first size; the first node reports training data for the first cell set with reference to a first reference size, and the first node reports training data for the second cell set with reference to a second reference size; the second reference size is equal to the smaller of the candidate size and the second target size; the first reference size is equal to the difference between the first size and the second reference size; the candidate size is predefined, or the candidate size is configurable.

Images