Method and apparatus for wireless communications

Abstract

A method and apparatus for wireless communications. The method comprises: a first node receiving a first information block, which indicates a channel data type and a first performance requirement; and sending a second information block, which comprises a first dataset. The indication of the first information block is dependent on a first inference configuration being applicable to a first node; performance monitoring that the first node executes on the first inference configuration is dependent on a second performance requirement; the first dataset is an output result of the first node executing the first inference configuration after receiving the first information block; a type of data in the first dataset is the channel data type; the indication of the second information block is dependent on a first set of conditions being met; the first set of conditions comprises a first performance meeting the first performance requirement; and the first performance is performance of the first node executing the first inference configuration. The present application enables an increase in the utilization rate of a first dataset.

Description

Methods and apparatus used for wireless communication Technical Field

[0001] This application relates to methods and apparatus in wireless communication systems, and more particularly to schemes and apparatus related to transmitting output results obtained from inference configuration in wireless communication systems. Background Technology

[0002] In traditional wireless communication, the UE (User Equipment) reports various auxiliary information obtained through measurements of downlink signals and / or channels, such as channel status information, beam management-related auxiliary information, and positioning-related auxiliary information. With the adoption of new technologies, the increase in the number of antennas, the diversification of application scenarios, and the increasing demands on system performance, traditional measurement and reporting methods incur significant redundancy overhead. Therefore, in NR (New Radio) Rel-18 (Release-18), research on AI (Artificial Intelligence) / ML (Machine Learning) technologies was initiated to explore their impact on system performance and system design.

[0003] Compared to traditional processing methods, AI / ML offers advantages such as training-based and deployment-required features. Based on current research advancements, AI / ML models can be deployed in either the UE or network nodes. Considering the potentially limited computing power / resources of the UE, the UE's AI / ML model can be trained independently by the UE, or trained by a dedicated server on the UE side and then transferred to the UE. The UE then uses the trained AI / ML model for inference based on the inference configuration indicated by the network. In other words, the UE's inference configuration can be associated with a specific AI / ML model or function. For network nodes that have deployed AI / ML models, the inference configuration of the AI / ML model is typically determined by the network node itself, without needing to receive additional signaling instructions.

[0004] In future 6G communications, AI / ML technologies may also play an important role. According to 3GPP (3rd Generation Partnership Project) standard TS (Technical Specification) 38.300, AI / ML models and algorithms are beyond the scope of 3GPP. Summary of the Invention

[0005] The applicant's research revealed that whether the output obtained through the execution of inference configuration can be utilized by other nodes after the introduction of AI / ML functions is an urgent problem to be solved.

[0006] To address the aforementioned problems, this application discloses a solution. It should be noted that while many embodiments of this application are focused on AI / ML, this application is also applicable to other solutions, such as edge computing, V2X (Vehicle to Everything), ISAC (Integrated Sensing and Communication), near-field communication (e.g., NFC), and IoT (Internet of Things). Although the specification of this application involves descriptions of some AI / ML models, those skilled in the art will understand that these descriptions are not essential or irreplaceable for solutions related to wireless cellular communication. Furthermore, adopting a unified solution for different scenarios helps reduce hardware complexity and cost. Where there is no conflict, the embodiments and features in the embodiments of the first node of this application can be applied to the second node, and vice versa. Where there is no conflict, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0007] Where necessary, the interpretation of terms in this application shall refer to the definitions of the 3GPP TS38 series of specifications; or, the definitions of the 3GPP TS37 series of specifications; or, the definitions of the 3GPP TS28 series of specifications; or, the definitions of the 3GPP TS23 series of specifications; or, the definitions of the 3GPP TS24 series of specifications; or, the definitions of the 3GPP TS22 series of specifications.

[0008] This application discloses a method used in a first node for wireless communication, characterized by comprising:

[0009] Receive a first information block, the first information block indicating the channel data type and a first performance requirement;

[0010] Send a second information block, the second information block including the first data set;

[0011] Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the first node; the performance monitoring of the first node executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance that satisfies the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

[0012] In the above method, the indication of the first information block helps to improve the relevance of the indication content in the second information block and reduce the processing complexity of the first node sending the second information block; in addition, the sending of the second information block helps the receiver of the second information block to obtain the first data set that meets the requirements indicated earlier (i.e. the first performance requirement), which provides the possibility of improving the utilization rate of the first data set.

[0013] Specifically, according to one aspect of this application, the above method is characterized in that the first data set is used for training or performance monitoring of the second inference configuration; the second inference configuration is different from the first inference configuration.

[0014] In the above aspects, the first data set can be used as training data or performance monitoring data for the second inference configuration, which is beneficial to improving the utilization rate of the first data set in other inference configurations besides the first inference configuration, and can help improve the performance of the second inference configuration.

[0015] Specifically, according to one aspect of this application, the above method is characterized in that the first performance is the performance of the first node performing the first inference configuration before receiving the first information block.

[0016] The above aspects can avoid the first node having to calculate and execute the first inference configuration performance after receiving the first information block, which is beneficial to saving the power consumption of the first node.

[0017] Specifically, according to one aspect of this application, the above method is characterized in that the first performance is the performance of the first node in executing the first inference configuration after receiving the first information block.

[0018] In the above aspects, the first performance is more timely than the performance of the first node performing the first inference configuration before receiving the first information block, which is beneficial to improving the degree of matching of the first data set with the first performance requirements.

[0019] Specifically, according to one aspect of this application, the above method is characterized by comprising:

[0020] In response to the commencement of calculations for the first performance, a first timer is started;

[0021] The first condition set includes the fact that the first timer has not expired.

[0022] The above aspects can avoid the situation where the storage and computing resources of the first node are occupied due to the long execution of the first inference configuration, improve the resource utilization of the first node, and help reduce the latency and complexity of the first node sending the second information block.

[0023] Specifically, according to one aspect of this application, the above method is characterized in that the first set of conditions includes the first performance simultaneously satisfying both the first performance requirement and the second performance requirement.

[0024] In the above aspects, the first performance also needs to meet the performance monitoring requirements of executing the first inference configuration, which helps to avoid including poor-performing data obtained by executing the first inference configuration in the first data set if the first inference configuration may not be applicable, and is conducive to improving the reliability of the first data set.

[0025] Specifically, according to one aspect of this application, the above method is characterized by comprising:

[0026] Send a third information block, which indicates a second data set;

[0027] Wherein, the indication of the third information block depends on the first condition set not being satisfied; the second data set is the measurement result after the first node enters the fallback mode, or the second data set is the output result of the first node executing the third inference configuration; the data type in the second data set is the channel data type.

[0028] The above aspects help to improve the flexibility of the first node in generating the second data set when the first condition set is not met, thereby helping to ensure that the receiver of the third information block obtains data that meets the channel data type requirements.

[0029] This application discloses a method used in a second node for wireless communication, characterized by comprising:

[0030] Send a first information block, which indicates the channel data type and a first performance requirement;

[0031] Receive a second information block, the second information block including a first data set;

[0032] Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the receiver of the first information block; the performance monitoring of the receiver of the first information block executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the receiver of the first information block executing the first inference configuration.

[0033] Specifically, according to one aspect of this application, the above method is characterized in that the first data set is used for training or performance monitoring of the second inference configuration; the second inference configuration is different from the first inference configuration.

[0034] Specifically, according to one aspect of this application, the above method is characterized in that the first performance is the performance of the recipient of the first information block performing the first inference configuration before receiving the first information block.

[0035] Specifically, according to one aspect of this application, the above method is characterized in that the first performance is the performance of the recipient of the first information block performing the first inference configuration after receiving the first information block.

[0036] Specifically, according to one aspect of this application, the above method is characterized in that the first condition set includes the first timer not having expired; and the recipient of the first information block starts the first timer in response to the commencement of calculation of the first performance.

[0037] Specifically, according to one aspect of this application, the above method is characterized in that the first set of conditions includes the first performance simultaneously satisfying both the first performance requirement and the second performance requirement.

[0038] Specifically, according to one aspect of this application, the above method is characterized by comprising:

[0039] Receive a third information block, the third information block indicating a second data set;

[0040] Wherein, the indication of the third information block depends on the first condition set not being satisfied; the second data set is the measurement result after the sender of the third information block enters the fallback mode, or the second data set is the output result of the sender of the third information block executing the third inference configuration; the data type in the second data set is the channel data type.

[0041] This application discloses a first node used for wireless communication, characterized in that it includes:

[0042] A first receiver receives a first information block, the first information block indicating the channel data type and a first performance requirement;

[0043] A first transmitter sends a second information block, the second information block including a first data set;

[0044] Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the first node; the performance monitoring of the first node executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance that satisfies the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

[0045] This application discloses a second node used for wireless communication, characterized by comprising:

[0046] The second transmitter sends a first information block, which indicates the channel data type and the first performance requirements.

[0047] A second receiver receives a second information block, the second information block including a first data set;

[0048] Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the receiver of the first information block; the performance monitoring of the receiver of the first information block executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the receiver of the first information block executing the first inference configuration. Attached Figure Description

[0049] 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:

[0050] Figure 1 shows a flowchart of communication of a first node according to an embodiment of this application;

[0051] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0052] 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;

[0053] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0054] Figure 5 illustrates a transmission flowchart between a first node N1 and a second node N2 according to an embodiment of this application;

[0055] Figure 6 shows a schematic diagram illustrating that a first performance requirement is met according to an embodiment of the present application;

[0056] Figure 7 shows a flowchart of a first node starting a first timer according to an embodiment of this application;

[0057] Figure 8 illustrates a flowchart of performance monitoring of a first node executing a first inference configuration depending on a second performance requirement according to an embodiment of this application;

[0058] Figure 9 shows a transmission flowchart of the first node N1 sending the third information block according to an embodiment of this application;

[0059] Figure 10 shows a schematic diagram of RAN domain AI / ML function deployment according to an embodiment of this application;

[0060] Figure 11 shows a schematic diagram of the AI / ML function deployment of a UE according to an embodiment of this application;

[0061] Figure 12 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0062] Figure 13 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application;

[0063] Figure 14 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0064] Figure 15 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of this application. Detailed Implementation

[0065] 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 5-15, the embodiments in Figure 5 and the embodiments in Figures 6-15, etc.

[0066] Example 1

[0067] Example 1 illustrates a flowchart of communication of a first node according to an embodiment of this application, as shown in Figure 1.

[0068] In Embodiment 1, the first node 100 receives a first information block in step 101, the first information block indicating the channel data type and the first performance requirements; and sends a second information block in step 102, the second information block including the first data set.

[0069] In Embodiment 1, the indication of the first information block depends on the applicability of the first inference configuration to the first node; the performance monitoring of the first node executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

[0070] As an example, the first information block explicitly indicates the channel data type.

[0071] As a sub-example of the above embodiments, the channel data type includes CSI (Channel Status Information).

[0072] As a sub-example of the above embodiments, the channel data type includes the compression result of CSI.

[0073] As a sub-implementation of the above embodiments, the channel data type includes at least one of RSRP (Reference Signal Received Power), beam index, and UE location information.

[0074] As a sub-example of the above embodiments, the channel data type includes a precoding matrix.

[0075] As a sub-example of the above embodiments, the channel data type includes an eigenvector.

[0076] As a sub-example of the above embodiments, the channel data type includes the raw channel matrix.

[0077] Typically, but not limitingly, the first information block includes a first bitmap; whether the first bit value of the first bitmap is "1" indicates whether the information data type includes CSI type; whether the second bit value of the first bitmap is "1" indicates whether the information data type includes RSRP; whether the third bit value of the first bitmap is "1" indicates whether the information data type includes beam index; and whether the fourth bit value of the first bitmap is "1" indicates whether the information data type includes UE location information.

[0078] Typically, but not limitingly, the first information block includes at least one enumerated value; the at least one enumerated value indicates the contents included in the channel data type.

[0079] As an example, the first information block implicitly indicates the channel data type.

[0080] As a sub-implementation of the above embodiments, the first information block includes at least one associated ID; the channel data type includes data of the AI / ML model corresponding to the at least one associated ID.

[0081] As a sub-implementation of the above embodiments, the first information block includes at least one AI / ML model ID; the channel data type includes data of the AI / ML model corresponding to the at least one AI / ML model ID.

[0082] As a sub-implementation of the above embodiments, the first information block includes at least one AI / ML function / feature ID; the channel data type includes data of the AI / ML model corresponding to the at least one AI / ML function ID.

[0083] As a sub-implementation of the above embodiment, the first information block includes at least one dataset ID; the channel data type includes the data corresponding to the at least one dataset ID.

[0084] As an example, the data of the AI / ML model includes at least one of the input of the AI / ML model and the output of the AI / ML model.

[0085] As an example, the data of the AI / ML model includes at least one of the training data and inference data of the AI / ML model; wherein the inference data is used for performance monitoring of the AI / ML model.

[0086] As an example, the AI / ML function relies on network-side additional conditions (NW-side Additional Condition).

[0087] As an example, the AI / ML functionality relies on a network configuration parameter set.

[0088] As an example, the AI / ML functions include at least one of the following: CSI compression / feedback; CSI prediction; beam management; positioning.

[0089] As an example, the AI / ML function is associated with at least one AI / ML model.

[0090] As an example, the ID mentioned in this application refers to IDentify (proof).

[0091] As an example, the ID mentioned in this application refers to: IDentification.

[0092] As an example, the ID mentioned in this application refers to: IDentity (identity or identifier).

[0093] As an example, the ID mentioned in this application refers to: Identifier.

[0094] As an example, the ID mentioned in this application refers to: InDex (index).

[0095] As an example, the ID mentioned in this application refers to: InDicator.

[0096] As an example, the first inference configuration is pre-configured.

[0097] As an example, the first inference configuration is indicated.

[0098] As an example, the first inference configuration includes the configuration of at least one RS resource.

[0099] As a sub-example of the above embodiments, the first data set is the output result of taking data measured on some or all of the at least one RS resource as input and executing the first inference configuration.

[0100] As an example, the at least one RS resource includes a DMRS (Demodulation Reference Signal) resource.

[0101] As an example, the at least one RS resource includes an SSB (SS / PBCH Block, Synchronization Signal Physical Broadcast Channel Block) resource.

[0102] As an example, the SSB mentioned in this application refers to: Synchronization Signal Block.

[0103] As an example, the SSB mentioned in this application refers to: Synchronization Signal / Physical Broadcast Channel Block (SS (Synchronization Signal) / PBCH (Physical Broadcast Channel) Block).

[0104] As an example, the at least one RS resource includes a PRS (Positioning Reference Signal) resource.

[0105] As an example, the at least one RS resource includes a TRS (Tracking Reference Signal) resource.

[0106] As an example, the at least one RS resource includes a PTRS (Phase Tracking Reference Signal) resource.

[0107] As an example, the at least one RS resource includes a CSI-RS (Channel State Information Reference Signal) resource.

[0108] As an example, the at least one RS resource includes an SRS (Sounding Reference Signal) resource.

[0109] As an example, the first inference configuration includes a format for the output result of executing the first inference configuration.

[0110] As an example, the format of the output result of executing the first inference configuration includes a compressed result of type CSI.

[0111] As an example, the format of the output of the first inference configuration includes predicted values ​​of type CSI.

[0112] As an example, the format of the output of the first inference configuration includes at least one of the predicted beam index, predicted location information, and predicted RSRP.

[0113] As an example, the format of the output of the first inference configuration includes at least one of the compressed result of the precoding matrix and the predicted value.

[0114] As an example, the format of the output of the first inference configuration includes at least one of the compressed result of the feature vector and the predicted value.

[0115] As an example, the format of the output of the first inference configuration includes at least one of the compressed result of the original channel matrix and the predicted value.

[0116] As an example, the first inference configuration is associated with at least one association ID.

[0117] As an example, the first inference configuration is associated with at least one AI / ML model ID.

[0118] As an example, the first inference configuration is associated with at least one AI / ML function ID.

[0119] As an example, the first inference configuration is used to configure at least one AI / ML model.

[0120] As an example, the first inference configuration is used to configure at least one AI / ML function.

[0121] As an example, the first inference configuration is used to activate at least one AI / ML model.

[0122] As an example, the first inference configuration is used to activate at least one AI / ML function.

[0123] As an example, activation as described in this application refers to: applying AI / ML models / functions for inference.

[0124] As one embodiment, the indication of the first information block depends on whether the first inference configuration is applicable to the first node, including that the AI / ML model associated with the first inference configuration is available / applicable before the first node receives the first information block.

[0125] As one embodiment, the indication of the first information block depends on the applicability of the first inference configuration to the first node, including that the AI / ML model associated with the first inference configuration is activated before the first node receives the first information block.

[0126] As one embodiment, the indication that the first information block depends on the applicability of the first inference configuration to the first node includes: the receipt of the first information block is conditional on the sender of the first information block knowing that the AI / ML model associated with the first inference configuration is available to the first node.

[0127] As one embodiment, the indication that the first information block depends on the applicability of the first inference configuration to the first node includes: the receipt of the first information block is conditional on the sender of the first information block knowing that the AI / ML model associated with the first inference configuration is activated for the first node.

[0128] As an example, executing the first inference configuration means: applying the AI / ML model associated with the first inference configuration to perform inference.

[0129] As an example, executing the first inference configuration means applying the parameters in the first inference configuration to the AI / ML model associated with the first inference configuration for inference.

[0130] As an example, the first data set being the output result of the first node executing the first inference configuration after receiving the first information block means that the first data set is all the output results of the first node executing the first inference configuration after receiving the first information block.

[0131] As an example, the first data set being the output result of the first node executing the first inference configuration after receiving the first information block means that the first data set is a compressed result of the output result of the first node executing the first inference configuration after receiving the first information block.

[0132] As an example, the first data set being the output result of the first node executing the first inference configuration after receiving the first information block means that the first data set is the reconstruction result of the output of the first node executing the first inference configuration after receiving the first information block.

[0133] As an example, the first performance is used to measure the quality of the AI / ML model associated with the first inference configuration.

[0134] As an example, the first performance is used to measure whether the output of executing the first inference configuration meets expectations.

[0135] As an example, the first performance metric includes at least one of the following: AI / ML model complexity, accuracy, precision, recall, F1 score, cosine similarity, mean square error, and mean absolute error.

[0136] As an example, the complexity includes floating-point operations.

[0137] As an example, when the AI / ML function corresponding to the AI / ML model is localization, the accuracy includes at least one of horizontal accuracy and vertical accuracy.

[0138] As an example, the cosine similarity includes at least one of generalized cosine similarity and squared generalized cosine similarity.

[0139] As an example, the mean square error includes at least one of normalized mean square error, root mean square error, and equivalent mean square error.

[0140] As an example, the first performance metric includes response time.

[0141] As an example, the measure of the first performance includes convergence speed.

[0142] As an example, the measure of the first performance includes the numerical spectral efficiency gap.

[0143] As an example, the first performance metric includes throughput.

[0144] As an example, the first performance metric includes at least one of BLER (Block Error Rate) and hypothetical BLER.

[0145] As an example, the measure of the first performance includes the output of executing the first inference configuration.

[0146] As an example, the first performance is calculated based on the output of executing the first inference configuration and the label / ground truth of the output.

[0147] As an example, the first performance is obtained during the inference phase when the first inference configuration is executed on the first node.

[0148] As one example, the first performance requirement includes at least a first threshold.

[0149] As an example, the first threshold corresponds to a first measurement value; wherein the first measurement value is one of at least one measurement value of the first performance.

[0150] Typically, but not limitingly, the first metric includes complexity, and the first threshold corresponds to a complexity value.

[0151] Typically, but not limitingly, the first metric includes accuracy, and the first threshold corresponds to an accuracy value.

[0152] Typically, but not limitingly, the first measure includes precision, and the first threshold corresponds to a precision value.

[0153] Typically, but not limitingly, the first metric includes recall, with the first threshold corresponding to a recall value.

[0154] Typically, but not limitingly, the first measure includes an F1 value, and the first threshold corresponds to an F1 value.

[0155] Typically, but not limitingly, the first metric includes cosine similarity, and the first threshold corresponds to a cosine similarity value.

[0156] Typically, but not limitingly, the first measure includes mean squared error, and the first threshold corresponds to a mean squared error value.

[0157] Typically, but not limitingly, the first measure includes the squared absolute error, and the first threshold corresponds to a squared absolute error value.

[0158] Typically, but not limitingly, the first metric includes response time, and the first threshold corresponds to a response time value.

[0159] Typically, but not limitingly, the first metric includes convergence rate, and the first threshold corresponds to a convergence rate value.

[0160] Typically, but not limitingly, the first metric includes the numerical spectral efficiency gap, and the first threshold corresponds to a numerical spectral efficiency gap value.

[0161] Typically, but not limitingly, the first metric includes throughput, and the first threshold corresponds to a throughput value.

[0162] Typically, but not limitingly, the first metric includes BLER, and the first threshold corresponds to a BLER value.

[0163] Typically, but not limitingly, the first metric includes the output of executing the first inference configuration, and the first threshold corresponds to an output value of executing the first inference configuration.

[0164] As an example, the first performance meeting the first performance requirement includes: the first metric value being better than the first threshold.

[0165] As a sub-implementation of the above embodiments, the first measurement value being better than the first threshold means that the magnitude of the first measurement value is greater than the first threshold.

[0166] As a sub-implementation of the above embodiments, the first measurement value being better than the first threshold means that the magnitude of the first measurement value is less than the first threshold.

[0167] As an example, the first performance meeting the first performance requirement includes: the first metric value is not worse than the first threshold.

[0168] As a sub-implementation of the above embodiments, the first measured value is not worse than the first threshold means that the magnitude of the first measured value is not greater than the first threshold.

[0169] As a sub-implementation of the above embodiments, the first measured value is not worse than the first threshold means that the magnitude of the first measured value is not less than the first threshold.

[0170] As an example, the second performance requirement can be referred to as an example of the first performance requirement.

[0171] As an example, the second performance requirement differs from the first performance requirement.

[0172] As one embodiment, the first information block includes AS (Access Stratum) signaling.

[0173] As one embodiment, the first information block includes RRC (Radio Resource Control) signaling.

[0174] As an example, the first information block includes one or more RRC IEs (Information Elements).

[0175] As an example, the first information block includes one or more fields in an RRC IE.

[0176] As one embodiment, the first information block includes SIB (System Information Block) signaling.

[0177] As one embodiment, the first information block includes SIB signaling for positioning.

[0178] As one embodiment, the first information block includes non-AS signaling.

[0179] As an example, the first information block includes LPP (LTE Positioning Protocol) signaling.

[0180] As one embodiment, the first information block includes one or more LPP IEs.

[0181] As an example, the first information block includes one or more fields in an LPP IE.

[0182] As an example, the signaling name of the first information block includes "Data".

[0183] As an example, the signaling name of the first information block includes Collection.

[0184] As an example, the signaling name of the first information block includes Request.

[0185] As an example, the signaling name of the first information block includes Performance.

[0186] As one embodiment, the second information block includes AS signaling.

[0187] As one embodiment, the second information block includes RRC signaling.

[0188] As one embodiment, the second information block includes one or more RRC IEs.

[0189] As one example, the second information block includes one or more fields in an RRC IE.

[0190] As one embodiment, the second information block includes MAC (Medium Access Control) and CE (Control Element).

[0191] As one embodiment, the second information block includes UCI (Uplink Control Information).

[0192] As an example, the second information block is transmitted on the PUCCH (Physical Uplink Control Channel).

[0193] As an example, the second information block is transmitted on PUSCH (Physical Uplink Shared Channel).

[0194] As one embodiment, the second information block includes non-AS signaling.

[0195] As one embodiment, the second information block includes LPP signaling.

[0196] As one embodiment, the second information block includes one or more LPP IEs.

[0197] As one embodiment, the second information block includes one or more fields in an LPP IE.

[0198] As an example, the signaling / IE / domain name of the second information block includes Report.

[0199] As an example, the signaling / IE / domain name of the second information block includes Data.

[0200] Furthermore, the following provides some non-limiting implementations of the first inference configuration, the channel data type, the first data set, and the first performance for ease of understanding. These different implementations may be applicable to different application scenarios.

[0201] As an example, the first inference configuration includes at least one CSI-RS configuration; the channel data type is a CSI compression result.

[0202] As a sub-example of the above embodiments, the first data set includes compressed results of CSI measurement results.

[0203] As a sub-implementation of the above embodiments, the first inference configuration is CSI-Reportconfig.

[0204] As a sub-implementation of the above embodiments, the first inference configuration includes at least one of the following: an associated ID and at least one of the report types of the output of executing the first inference configuration.

[0205] As a sub-example of the above embodiments, the report type of the output of the first inference configuration includes at least one of aperiodic report, periodic report, and semi-persistent report.

[0206] As a sub-implementation of the above embodiments, the CSI measurement results include at least one of CRI (CSI-RS Resource Indicator), RI (Rank Indicator), PMI (Precoding Matrix Indicator), CQI (Channel Quality Indicator), L1-RSRP, CRI-RSRP, SSB-Index-RSRP, beam index (e.g., CSI-RS-Index, SSB-Index, etc.), precoding matrix, eigenvector, and original channel matrix.

[0207] As a sub-implementation of the above embodiments, the first performance is the squared generalized cosine similarity (SGCS) or the normalized mean square error (NMSE).

[0208] The above embodiments are particularly suitable for CSI compression scenarios.

[0209] As an example, the first inference configuration includes at least one CSI-RS configuration; the channel data type is a CSI measurement result.

[0210] As a sub-example of the above embodiments, the first data set includes predicted CSI measurement results.

[0211] As a sub-implementation of the above embodiments, the first inference configuration is CSI-Reportconfig.

[0212] As a sub-implementation of the above embodiments, the first inference configuration includes at least one of the following: an associated ID and at least one of the report types of the output of executing the first inference configuration.

[0213] As a sub-implementation of the above embodiments, an example of the report type of the output of the first inference configuration is given in the example in the previous embodiment.

[0214] As a sub-example of the above embodiment, the CSI measurement results are provided in the example of the previous embodiment.

[0215] As a sub-implementation of the above embodiments, the first performance is an example from the previous embodiment.

[0216] The above embodiments are particularly suitable for CSI prediction scenarios.

[0217] As one embodiment, the first inference configuration includes at least a first CSI-RS resource configuration and a second CSI-RS resource configuration, wherein the CSI measurement results on the first CSI-RS resource are used as input for executing the first inference configuration to predict the CSI measurement results on the second CSI-RS resource; the channel data type is RSRP and beam index.

[0218] As a sub-implementation of the above embodiments, the prediction includes at least one of spatial-domain correlation and temporal-domain correlation.

[0219] As a sub-implementation of the above embodiments, the first data set is the predicted RSRP and the predicted beam index.

[0220] As a sub-implementation of the above embodiments, the first inference configuration is CSI-Reportconfig.

[0221] As a sub-implementation of the above embodiments, the first inference configuration includes at least one of the following: an associated ID, a report type of the output of executing the first inference configuration, and a time instance of measurement or prediction.

[0222] As a sub-implementation of the above embodiments, an example of the report type of the output of the first inference configuration is given in the example in the previous embodiment.

[0223] As a sub-example of the above embodiment, the CSI measurement results are provided in the example of the previous embodiment.

[0224] As a sub-implementation of the above embodiments, the RSRP includes at least one of L1-RSRP, CRI-RSRP, and SSB-Index-RSRP.

[0225] As a sub-implementation of the above embodiments, the beam index includes at least one of CSI-RS-Index and SSB-Index.

[0226] As a sub-implementation of the above embodiments, the first performance is CRI (Resource Indicator) or SSBRI.

[0227] The above embodiments are particularly suitable for beam management scenarios.

[0228] As an example, the first inference configuration includes at least one DL PRS resource configuration; the channel data type is UE location information.

[0229] As a sub-implementation of the above embodiments, the first data set includes at least one of the predicted UE location information, the quality identifier of the predicted UE location information, and the timestamp of the predicted UE location information.

[0230] As a sub-implementation of the above embodiments, the first inference configuration is NR-DL-PRS-Assistance Data.

[0231] As a sub-implementation of the above embodiments, the first inference configuration is NR-DL-PRS-BeamInfo.

[0232] As a sub-implementation of the above embodiments, the first inference configuration is NR-DL-PRS-Info.

[0233] As a sub-implementation of the above embodiments, the timestamp is NR-TimeStamp.

[0234] As a sub-implementation of the above embodiments, the UE location information includes at least one of location coordinates, velocity, and location error.

[0235] As a sub-implementation of the above embodiments, the first performance includes at least one of horizontal accuracy and vertical accuracy.

[0236] The above embodiments are particularly suitable for positioning scenarios.

[0237] Example 2

[0238] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0239] Figure 2 illustrates the network architecture 200. The network architecture 200 is a 5G NR (New Radio) / LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution Advanced) system, or a 5G+ network architecture, or a 6G network architecture, or a network architecture adopted in the future evolution of 3GPP; the network architecture 200 may be referred to as 5GS (5G System) / EPS (Evolved Packet System), or 6GS (6G System); the network architecture 200 includes at least one of UE (User Equipment) 201, RAN (Radio Access Network) 202, core network 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet service 230. The network architecture 200 can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown, the network architecture 200 provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN includes node 203. The RAN may also include other nodes 204. Node 203 provides user and control plane protocol termination toward UE 201. Node 203 may be connected to other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. Node 203 may also be referred to as a base station, base transceiver station, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), TRP (transmitter-receiver node), or some other suitable term. The core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC; node 203 provides UE 201 with an access point to the core network 210.Examples of UE201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, non-terrestrial base station communications, satellite mobile communications, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband IoT devices, machine-type communication devices, land vehicles, automobiles, wearable devices, mobile terminals (MTs) in relay equipment, or any other similar functional devices. Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio 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. Node 203 is connected to the core network 210 via an S1 / NG interface. The core network 210 includes an MME (Mobility Management Entity) / AMF (Access and Mobility Management Function) / 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, as well as other nodes not shown in Figure 2. 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 / UPF213 provides UE IP address allocation and other functions. The P-GW / UPF213 connects to Internet service 230. Internet service 230 includes operator-compliant Internet protocol services, specifically including Internet, intranet, IMS (IP Multimedia Subsystem), and packet switching services.

[0240] As one embodiment, the first node includes the UE201, and the second node includes the node203.

[0241] As one embodiment, the first node includes the node 203, and the second node includes the UE 201.

[0242] As one embodiment, the first node includes the UE201, and the second node includes the core network 210.

[0243] As one embodiment, the first node includes the core network 210, and the second node includes the UE 201.

[0244] As one embodiment, the first node includes the node 203, and the second node includes the core network 210.

[0245] As one embodiment, the first node includes the core network 210, and the second node includes the node 203.

[0246] As an example, the UE201 is a terminal.

[0247] As one example, node 203 is a base station.

[0248] As one embodiment, the node 203 is a relay node device.

[0249] As one embodiment, the core network 210 includes LMF (Location Management Function).

[0250] As an example, the wireless link between the UE201 and the node203 includes a cellular link.

[0251] Example 3

[0252] 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.

[0253] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and control plane according to this application, as shown in Figure 3. Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300. Figure 3 shows the radio protocol architecture for the control plane 300 between a first communication device (gNB or LMF) and a second communication device (UE) using four layers: Layer 1, Layer 2, Layer 3, and the NAS (Non-Access Stratum) layer. Layer 1 (L1 layer) is the lowest layer and implements various PHY (Physical Layer) signal processing functions. The L1 layer will be referred to herein as PHY 301. Layer 2 (L2 layer) 305 is above PHY 301 and is responsible for the link between the first communication device and the second communication device. Layer L2 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the first communication 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 first and second communication devices. 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. 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 second communication devices. Furthermore, the MAC sublayer 302 handles HARQ operations. The Radio Resource Control (RRC) sublayer 306 in Layer 3 (L3) of the control plane 300 is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second and first communication devices. The NAS sublayer 307 in the control plane 300 is used for the transmission of non-access stratum signaling between the first and second communication devices; this signaling transmission is transparent and invisible to the base station.The radio protocol architecture of user plane 350 includes Layer 1 (L1 layer) and Layer 2 (L2 layer). The radio protocol architecture for the first and second communication 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 L2 layer 355, RLC sublayer 353 in L2 layer 355, and MAC sublayer 352 in L2 layer 355. However, PDCP sublayer 354 also provides header compression for upper layer packets to reduce radio transmission overhead. L2 layer 355 in user plane 350 also includes SDAP (Service Data Adaptation Protocol) sublayer 356. SDAP sublayer 356 is responsible for mapping between QoS streams and Data Radio Bearers (DRBs) to support service diversity. Although not illustrated, the second communication device may have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) terminating at the P-GW / UPF on the network side and an application layer terminating at the other end of the connection (e.g., remote UE, server, etc.).

[0254] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node.

[0255] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node.

[0256] As an example, the first information block is generated in at least one of the NAS sublayer 307 or the RRC sublayer 306.

[0257] As an example, the second information block is generated in at least one of the NAS sublayer 307 or the RRC sublayer 306.

[0258] As an example, the third information block is generated in at least one of the NAS sublayer 307 or the RRC sublayer 306.

[0259] Example 4

[0260] 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.

[0261] The first communication device 410 includes at least one of 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.

[0262] The second communication device 450 includes at least one of 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.

[0263] As an example, the first communication device 410 is a core network device, and the first communication device 410 includes at least one of a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, and a transmitter / receiver 418.

[0264] As an example, the first communication device 410 is an access network device, and some specific implementation methods are given below.

[0265] 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 layer functionality. In DL (Downlink), 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 layer (i.e., physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and constellation mapping based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), 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. 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 O-stream. 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 multi-antenna transmit processor 471 into an RF stream, which is then provided to different antennas 420.

[0266] 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 signal processing functions of the L1 layer. 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 over the physical channel by the first communication device 410. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of Layer 2 (L2). 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 (Layered Logic), 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 Layer 2. Various control signals may also be provided to Layer 3 (L3) for L3 processing. The controller / processor 459 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0267] 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 the L2 layer. 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 layer 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.

[0268] 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 layer functions. The controller / processor 475 implements the L2 layer functions. The controller / processor 475 may be associated with a memory 476 that stores 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.

[0269] 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 means at least: receiving a first information block, the first information block indicating a channel data type and a first performance requirement; transmitting a second information block, the second information block including a first data set; wherein the indication of the first information block depends on the applicability of a first inference configuration to the first node; performance monitoring of the first node executing the first inference configuration depends on a second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the type of data in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of a first set of conditions; the first set of conditions includes a first performance satisfying the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

[0270] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: receiving a first information block, the first information block indicating a channel data type and a first performance requirement; transmitting a second information block, the second information block including a first data set; wherein the indication of the first information block depends on the applicability of a first inference configuration to the first node; performance monitoring of the first node executing the first inference configuration depends on a second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of a first set of conditions; the first set of conditions includes a first performance requirement satisfying the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

[0271] 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 means at least: transmitting a first information block, the first information block indicating a channel data type and a first performance requirement; receiving a second information block, the second information block including a first data set; wherein the indication of the first information block depends on a first inference configuration being applicable to the receiver of the first information block; performance monitoring of the receiver of the first information block executing the first inference configuration depends on a second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the type of data in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of a first set of conditions; the first set of conditions includes a first performance satisfying the first performance requirement; the first performance is the performance of the receiver of the first information block executing the first inference configuration.

[0272] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: transmitting a first information block, the first information block indicating a channel data type and a first performance requirement; receiving a second information block, the second information block including a first data set; wherein the indication of the first information block depends on the applicability of a first inference configuration to a receiver of the first information block; performance monitoring of the receiver of the first information block executing the first inference configuration depends on a second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the type of data in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of a first set of conditions; the first set of conditions includes a first performance satisfying the first performance requirement; the first performance is the performance of the receiver of the first information block executing the first inference configuration.

[0273] As an example, the first node in this application includes the second communication device 450, and the second node includes the first communication device 410.

[0274] As a sub-implementation of the above embodiment, some or all of the following are used to transmit the first information block: {the antenna 420, the transmitter 418, the transmission processor 416, the multi-antenna transmission processor 471, the controller / processor 475, and the memory 476}.

[0275] As a sub-implementation of the above embodiments, some or all of the following are used to transmit the second information block: {the antenna 452, the transmitter 454, the transmitter processor 468, the multi-antenna transmitter processor 457, the controller / processor 459, the memory 460, and the data source 467}.

[0276] As a sub-implementation of the above embodiments, some or all of the following are used to transmit the third information block: {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}.

[0277] As an example, the first node in this application includes the first communication device 410, and the second node includes the second communication device 450.

[0278] As a sub-implementation of the above embodiments, some or all of the following are used to transmit the first information block: {the antenna 452, the transmitter 454, the transmitter processor 468, the multi-antenna transmitter processor 457, the controller / processor 459, the memory 460, and the data source 467}.

[0279] As a sub-implementation of the above embodiment, some or all of the following are used to transmit the second information block: {the antenna 420, the transmitter 418, the transmission processor 416, the multi-antenna transmission processor 471, the controller / processor 475, and the memory 476}.

[0280] As a sub-implementation of the above embodiment, some or all of the following are used to transmit the third information block: {the antenna 420, the transmitter 418, the transmission processor 416, the multi-antenna transmission processor 471, the controller / processor 475, and the memory 476}.

[0281] Example 5

[0282] Example 5 illustrates a transmission flowchart between a first node N1 and a second node N2 according to an embodiment of this application, as shown in Figure 5. The steps in block F0 and the dashed lines are optional. It should be noted that, for ease of explanation, Example 5 and subsequent embodiments are only examples of a positioning scenario and do not limit the application of this application to scenarios other than positioning.

[0283] For the second node N2, in step S5201, a first information block is sent, indicating a channel data type and a first performance requirement; in step S5202, a second information block is received, the second information block including a first data set; wherein, the indication of the first information block depends on the applicability of a first inference configuration to the receiver of the first information block; performance monitoring of the receiver of the first information block executing the first inference configuration depends on a second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of a first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the receiver of the first information block executing the first inference configuration;

[0284] For the first node N1, in step S5101, a first information block is received, the first information block indicating a channel data type and a first performance requirement; in step S5102, a second information block is sent, the second information block including a first data set; wherein, the indication of the first information block depends on the applicability of a first inference configuration to the first node; the performance monitoring of the first node executing the first inference configuration depends on a second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of a first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

[0285] As an example, the first information block indicates a data collection request for the channel data type.

[0286] In one embodiment, the second information block is triggered by the first information block.

[0287] As a sub-implementation of the above embodiment, the first information block instructs the first node N1 to send the second information block in response to satisfying the first set of conditions.

[0288] As an example, the first set of conditions is pre-configured for the first node N1.

[0289] As an example, the first set of conditions is indicated to the first node N1.

[0290] As a sub-implementation of the above embodiments, the first condition set is included in the first information block.

[0291] As an example, the indication of the first information block being applicable to the first inference configuration for the first node means that the second node N2 sends the first information block on the condition that it receives indication information #1 from the first node N1; wherein, the indication information #1 indicates that at least one AI / ML model in the first node N1 is available; the at least one AI / ML model is associated with the first inference configuration.

[0292] As an example, the indication that the first information block depends on the first inference configuration is applicable to the first node means that the second node N2 sends the first information block depending on the first inference configuration.

[0293] As a sub-example of the above embodiment, the second node N2 sends the first information block on the condition that the first inference configuration has been sent to the first node N1.

[0294] As a sub-implementation of the above embodiments, the first information block is included in the first inference configuration.

[0295] In the above embodiment, the second node N2 can send the first information block to the first node N1 when it knows that the AI / ML model associated with the first inference configuration is applicable to the first node N1, thereby avoiding unnecessary transmission of the first information block and reducing the power consumption of the second node N2.

[0296] As a non-limiting embodiment, the first node N1 and the second node N2 are a user equipment and a core network equipment, respectively.

[0297] As a sub-example of the above embodiment, the second node N2 is the service core network device of the first node N1.

[0298] As a sub-implementation of the above embodiment, the second node N2 is a network element or functional entity in the core network device.

[0299] As a sub-implementation of the above embodiment, the second node N2 is an LMF.

[0300] As a sub-implementation of the above embodiments, the first inference configuration is LPP signaling.

[0301] As a sub-implementation of the above embodiments, the first inference configuration is a request capabilities signaling; or, the first inference configuration is one or more IEs / domains in the request capabilities signaling.

[0302] As a sub-implementation of the above embodiments, the first inference configuration is to provide Assistance Data signaling; or, the first inference configuration is to provide one or more IEs / domains in the Assistance Data signaling.

[0303] As a sub-implementation of the above embodiments, the first inference configuration is a RequestLocation Information signaling; or, the first inference configuration is one or more IEs / domains in the RequestLocation Information signaling.

[0304] As a sub-implementation of the above embodiments, the first inference configuration is NR-DL-PRS-Assistance Data.

[0305] As a sub-implementation of the above embodiments, the first inference configuration is NR-DL-PRS-BeamInfo.

[0306] As a sub-implementation of the above embodiments, the first inference configuration is NR-DL-PRS-Info.

[0307] As a sub-implementation of the above embodiments, the first information block and the second information block are LPP signaling.

[0308] As a sub-implementation of the above embodiments, the first information block is a request for location information signaling or one or more IEs / domains in the request for location information signaling, and the second information block is a provide location information signaling or one or more IEs / domains in the provide location information signaling.

[0309] As a sub-implementation of the above embodiments, the first information block is a request capability signaling or one or more IEs / domains in the request capability signaling, and the second information block is a provide capability signaling or one or more IEs / domains in the provide capability signaling.

[0310] As a sub-implementation of the above embodiments, the first information block is providing auxiliary data signaling or providing one or more IEs / domains in auxiliary data signaling, and the second information block is providing location information signaling or providing one or more IEs / domains in location information signaling.

[0311] As a non-limiting embodiment, the executing entities of the first node N1 and the second node N2 in the above embodiment can be interchanged, that is, the first node N1 and the second node N2 are a core network device and a user equipment, respectively.

[0312] As a sub-example of the above embodiment, the first node N1 is the serving core network device of the second node N2.

[0313] As a sub-implementation of the above embodiments, the first node N1 is a network element or functional entity in the core network device.

[0314] As a sub-implementation of the above embodiment, the first node N1 is an LMF.

[0315] As a sub-implementation of the above embodiments, the first information block and the second information block are LPP signaling.

[0316] As a sub-implementation of the above embodiments, the first information block is one or more IEs / domains in Request Assistance Data signaling or Request Assistance Data signaling, and the second information block is one or more IEs / domains in Provide Assistance Data signaling or Provide Assistance Data signaling.

[0317] As a sub-implementation of the above embodiments, the first information block is providing capability signaling or one or more IEs / domains in the provision capability signaling, and the second information block is providing auxiliary data signaling or one or more IEs / domains in the provision auxiliary data signaling.

[0318] As an example, for the second node N2, a first signaling is sent in step S52021, the first signaling instructing the first node N1 to send the second information block; correspondingly, for the first node N1, a first signaling is received in step S51021, the first signaling instructing the first node N1 to send the second information block.

[0319] As a sub-implementation of the above embodiment, step S5102 includes: in response to receiving the first signaling, the first node N1 sends the second information block.

[0320] As a sub-implementation of the above embodiment, the second node N2 receives a second signaling from the first node N1, the second signaling indicating that the first condition set is satisfied; wherein, the first signaling is triggered by the second signaling.

[0321] As a sub-implementation of the above embodiment, the second node N2 receives a second signaling from the first node N1, the second signaling indicating that the output result of the first node executing the first inference configuration meets the conditions for use in training or performance monitoring; typically, but not limitingly, the second signaling indicating that the first set of conditions is met can be regarded as an implicit indication that the second signaling indicates that the output result of the first node executing the first inference configuration meets the conditions for use in training or performance monitoring.

[0322] As a sub-implementation of the above embodiments, please refer to the signaling example of the first information block for an example of the first signaling.

[0323] As a sub-implementation of the above embodiments, please refer to the signaling example of the second information block for an example of the second signaling.

[0324] As a sub-implementation of the above embodiments, the first information block is included in the first signaling.

[0325] The above sub-implementation is beneficial to improving the flexibility of the first information block indication, and is especially suitable for scenarios that dynamically request data collection.

[0326] As a sub-implementation of the above embodiments, the first condition set is included in the first signaling.

[0327] As an example, the first information block is generated by the second node N2.

[0328] As an example, the content in the first information block is indicated to the second node N2 by the third node N3.

[0329] As a sub-implementation of the above embodiments, the first node N1 is a user equipment, the second node N2 is a core network device, and the third node N3 is a user equipment.

[0330] As a sub-example of the above embodiments, the first node N1 is a user equipment, the second node N2 is a core network device, and the third node N3 is an access network device.

[0331] As a sub-example of the above embodiments, the first node N1 is a core network device, the second node N2 is a user equipment, and the third node N3 is an access network device.

[0332] As a sub-implementation of the above embodiments, the first node N1 is a core network device, the second node N2 is a user equipment, and the third node N3 is a user equipment.

[0333] As a sub-implementation of the above embodiment, step S5201 includes: receiving information block #1 from the third node N3; wherein, information block #1 indicates the content in the first information block; the first information block is triggered by information block #1.

[0334] As a sub-implementation of the above embodiment, step S52021 includes: receiving signaling #1 from the third node N3; wherein, signaling #1 indicates a request for data collection of the channel data type; the first signaling is triggered by signaling #1.

[0335] As a sub-implementation of the above sub-implementation, the signaling #1 includes the information block #1.

[0336] As an example, the indication that the second information block depends on the first condition set being satisfied means that the sending of the second information block is triggered by the first condition set being satisfied.

[0337] As a sub-implementation of the above embodiments, the step of sending the second information block being triggered by the first condition set being met includes: the second signaling indicating that the first condition set is met; wherein, the first signaling is triggered by the second signaling.

[0338] As a sub-implementation of the above embodiment, the step of sending the second information block triggered by the first condition set being met includes: step S5102 includes sending the second information block as a response to the first condition set being met.

[0339] As an example, the indication that the second information block depends on the first set of conditions being satisfied means that the second information block includes indication information that the first set of conditions is satisfied.

[0340] As a sub-implementation of the above embodiments, the second information block including the first data set can be regarded as an implicit indication that the first condition set is satisfied.

[0341] As an example, the indication that the second information block depends on the first set of conditions being satisfied means that the second information block includes the first performance.

[0342] As one example, how the second node N2 applies the second information block is typically implementation-dependent or determined by the vendor of the second node N2; some non-limiting implementations are given below.

[0343] As one example, the first dataset is used for training or performance monitoring of the second inference configuration; the second inference configuration is different from the first inference configuration.

[0344] As a sub-implementation of the above embodiments, the use of the first data set for training the second inference configuration includes: the first data set being used to train at least one AI / ML model associated with the second inference configuration.

[0345] As a sub-implementation of the above embodiments, the use of the first data set for training the second inference configuration includes: the first data set being training data of at least one AI / ML model associated with the second inference configuration.

[0346] As a sub-implementation of the above embodiments, the performance monitoring of the first data set for the second inference configuration includes: the first data set being used for the inference phase of at least one AI / ML model associated with the second inference configuration.

[0347] As a sub-implementation of the above embodiments, the performance monitoring of the first data set for the second inference configuration includes: the first data set being inference data of at least one AI / ML model associated with the second inference configuration.

[0348] As a sub-implementation of the above embodiments, the performance monitoring of the first data set used for the second inference configuration includes: the first data set is the label / true value of the output result obtained by executing the second inference configuration.

[0349] As a sub-implementation of the above embodiment, the second inference configuration is the configuration in the second node N2.

[0350] As a sub-implementation of the above embodiment, the second inference configuration is indicated to the second node N2.

[0351] As a sub-implementation of the above embodiments, the second inference configuration is associated with at least one AI / ML model in the second node N2.

[0352] As a sub-example of the above embodiment, the second inference configuration is the configuration in the third node N3.

[0353] As a sub-implementation of the above embodiment, the second inference configuration is instructed to the third node N3.

[0354] As a sub-example of the above embodiment, the second inference configuration is associated with at least one AI / ML model in the third node N3.

[0355] As a sub-implementation of the above embodiment, step S5202 includes: in response to receiving the second information block, sending information block #2 to the third node N3; wherein, the information block #2 includes the first data set.

[0356] Example 6

[0357] Example 6 illustrates a schematic diagram of a first performance requirement satisfying a first performance requirement according to an embodiment of the present application, as shown in Figure 6, including three possible implementation methods.

[0358] As an example, the first performance is the performance of the first node executing the first inference configuration before receiving the first information block (i.e., the before-and-after timing example 1).

[0359] As a sub-example of the above embodiment, the first performance is the performance of the first node in the most recent performance monitoring before receiving the first information block.

[0360] As a sub-implementation of the above embodiments, step S5101 in embodiment 5 includes: in response to receiving the first information block and the first performance meeting the first performance requirement, executing the first inference configuration to output the first data set.

[0361] As a sub-example of the above embodiments, the first data set includes the output results obtained by the first inference configuration being executed for the first node to calculate the first performance.

[0362] The above sub-implementation is beneficial for reducing the power consumption and memory occupied by the first node, and improving the efficiency of the first node in generating the first data set.

[0363] As one embodiment, the first performance is the performance of the first node in executing the first inference configuration after receiving the first information block; some non-limiting implementation methods are given below for this embodiment.

[0364] Typically, but not limitingly, the first performance refers to the performance of the first node executing the first inference configuration and outputting the first data set (i.e., the before-and-after time series example 2).

[0365] As a sub-implementation of the above embodiments, step S5101 in embodiment 5 includes: in response to receiving the first information block, executing the first inference configuration to output the first data set.

[0366] As a sub-implementation of the above embodiments, the first performance is calculated based on the first data set.

[0367] As a sub-implementation of the above embodiments, the data included in the first data set all meet the first performance requirements.

[0368] As a sub-example of the above embodiments, step S5101 in embodiment 5 includes: saving the output result obtained by executing the first inference configuration that satisfies the first performance requirement; wherein, the first data set includes the output result.

[0369] Typically, but not limitingly, the first performance refers to the performance of the first node executing the first inference configuration after receiving the first information block and before outputting the first data set (i.e., the before-and-after timing example 3).

[0370] As a sub-example of the above embodiments, step S5101 in embodiment 5 includes: calculating the first performance in response to receiving the first information block.

[0371] As a sub-implementation of the above embodiments, calculating the first performance includes executing the first inference configuration.

[0372] As a sub-example of the above embodiments, step S5101 in embodiment 5 includes: storing the output result of executing the first inference configuration after the first performance meets the first performance requirement; wherein, the first data set includes the output result.

[0373] Example 6 provides multiple implementation methods for determining the first performance of the first node, which helps to improve the flexibility of the first node in generating the first data set.

[0374] Example 7

[0375] Example 7 illustrates a flowchart of a first node starting a first timer according to an embodiment of this application, as shown in Figure 7. In Example 7, the first performance is the performance of the first node executing the first inference configuration after receiving the first information block.

[0376] For the first node, please refer to the relevant descriptions of steps S5101 and S5102 in Embodiment 5 for steps S701 and S702; in step S7011, as a response to start calculating the first performance, a first timer is started; wherein, the first condition set includes the first timer not expiring.

[0377] As an example, the first timer is pre-configured for the first node.

[0378] As an example, the first timer is instructed to the first node.

[0379] As a sub-implementation of the above embodiments, the first timer is included in the first information block.

[0380] As a sub-implementation of the above embodiments, the first timer is included in the first signaling.

[0381] In either of the two sub-implementations described above, the triggering and configuration of the first timer are controlled by the second node, which facilitates flexible configuration of the first timer and avoids the first node receiving unnecessary signaling.

[0382] As a sub-implementation of the above embodiments, the first timer is included in the first inference configuration.

[0383] In the above sub-implementation, the first timer is saved as prior knowledge of the first node, which helps to reduce the complexity of the first node starting the first timer and improve the efficiency of starting the first timer.

[0384] As a sub-implementation of the above embodiment, the third node sends the information block #1 and the first time value to the second node, or the third node sends the signaling #1 and the first time value to the second node; wherein, the value of the first timer depends on the first time value.

[0385] In the above sub-implementation, the value of the first timer is determined based on the first time value indicated by the third node, which helps to increase the likelihood that the first data set will be used by the third node.

[0386] As an example, the start time of the first timer corresponds to the time when the calculation of the first performance begins.

[0387] As a sub-implementation of the above embodiment, the moment when the calculation of the first performance begins refers to the moment when the first node receives the first information block.

[0388] As a sub-implementation of the above embodiments, the moment when the calculation of the first performance begins refers to the moment when the first node starts executing the first inference configuration after receiving the first information block.

[0389] As an example, the expiration of the first timer means that the initial value of the first timer is 0, and the first timer increments to the second time value.

[0390] As an example, the expiration of the first timer means that the initial value of the first timer is the second time value, and the first timer counts down to 0.

[0391] As an example, if the first timer expires, the first node sends indication information #2 to the second node; wherein, the indication information #2 indicates that the reason for the failure to obtain the first data set is timeout.

[0392] As a sub-implementation of the above embodiment, the indication information #2 indicates the reason value for the timeout of obtaining the first data set.

[0393] As a sub-implementation of the above embodiments, the reason value for obtaining the timeout of the first data set includes at least one of the first node low power and the first node low memory / buffer.

[0394] The above embodiments help the second node make decisions based on the reasons for the failure to obtain the first data set, and provide the possibility for the first node to receive the first information block again in the future.

[0395] Example 8

[0396] Example 8 illustrates a flowchart of a first node executing a first inference configuration according to an embodiment of this application, showing a performance monitoring process dependent on a second performance requirement, as shown in Figure 8. It should be noted that in Example 8, there may be no dependency between steps S801 and S802; for example, either step S801 or step S802 may be executed independently. Furthermore, the execution result of step S801 may not affect the execution of step S802, and vice versa.

[0397] For the first node, in step S801, it is determined whether the first performance meets the second performance requirement. If the first performance meets the second performance requirement, it is determined that the first inference configuration is applicable to the first node. If the first performance does not meet the second performance requirement, it is determined that the first inference configuration is not applicable to the first node. In step S802, it is determined whether the first performance meets the first performance requirement. If the first performance meets the first performance requirement, it is further determined whether other conditions in the first condition set are met. If the first performance does not meet the first performance requirement, it is determined that the second information block will not be sent.

[0398] As an example, the performance monitoring of the first node executing the first inference configuration depending on the second performance requirement means that the performance monitoring of the first node executing the first inference configuration does not depend on the first performance requirement.

[0399] As a sub-implementation of the above embodiments, the first performance requirement is different from the second performance requirement.

[0400] As a sub-implementation of the above embodiments, the first performance requirement is higher than the second performance requirement.

[0401] As a sub-implementation of the above embodiments, the first performance requirement is lower than the second performance requirement.

[0402] As a sub-implementation of the above embodiments, the first performance requirement is more stringent than the second performance requirement.

[0403] As a sub-implementation of the above embodiments, the first performance requirement is less stringent than the second performance requirement.

[0404] As a sub-implementation of the above embodiments, whether the first performance meets the first performance requirement does not affect the performance monitoring of the first node executing the first inference configuration.

[0405] As an example, the performance monitoring of the first node executing the first inference configuration depends on the second performance requirement, which means that the conditions under which the first inference configuration is not applicable include the first node's performance in executing the first inference configuration not meeting the second performance requirement.

[0406] As a sub-implementation of the above embodiments, performance monitoring of the first node executing the first inference configuration is used to determine whether the first inference configuration is applicable.

[0407] As a sub-implementation of the above embodiments, in response to the first performance not meeting the second performance requirement, the first node determines that the first inference configuration is not applicable.

[0408] As a sub-implementation of the above embodiment, the first node sends indication information #3 to the second node, the indication information #3 indicating the first performance, or the indication information #3 indicating that the first performance does not meet the second performance requirement; the second node sends indication information #4 to the first node, the indication information #4 indicating that the first inference configuration is not applicable; typically, but not limitingly, the indication information #3 is included in the second information block.

[0409] As a sub-example of the above embodiments, the first inference configuration is applicable when the first performance does not meet the first performance requirement but meets the second performance requirement.

[0410] As a sub-example of the above embodiments, step S5102 in embodiment 5 includes: sending the second information block when the first performance meets the first performance requirement but does not meet the second performance requirement.

[0411] As an example, the first set of conditions includes the first performance simultaneously satisfying both the first performance requirement and the second performance requirement.

[0412] As a sub-implementation of the above embodiments, step S5102 in embodiment 5 includes: sending the second information block as a response that the first performance simultaneously meets the first performance requirement and the second performance requirement.

[0413] As a sub-implementation of the above embodiments, the second information block indicates that the first performance simultaneously meets both the first performance requirement and the second performance requirement.

[0414] As a sub-example of the above embodiments, step S5101 in embodiment 5 includes: in response to receiving the first information block, performing the performance monitoring of the first inference configuration.

[0415] The above sub-implementation examples are helpful for the first node to determine whether the first performance meets the second performance requirements.

[0416] As a sub-example of the above embodiments, step S5101 in embodiment 5 includes: determining whether the first performance meets the first performance requirement as a response to the first performance meeting the second performance requirement.

[0417] As a sub-example of the above embodiments, step S5101 in embodiment 5 includes: starting the first timer as a response that the first performance meets the second performance requirement.

[0418] As a sub-implementation of the above embodiments, step S5101 in embodiment 5 includes: in response to the first performance meeting the second performance requirement, executing the first inference configuration to output the first data set.

[0419] Example 9

[0420] Example 9 illustrates a transmission flowchart of a first node N1 sending a third information block according to an embodiment of this application, as shown in Figure 9, where the steps in block F1 are optional.

[0421] For the second node N2, the first information block is sent in step S9201; a third information block is received in step S9202, the third information block indicating a second data set; wherein, the indication of the third information block depends on the first condition set not being satisfied; the second data set is the measurement result after the sender of the third information block enters the fallback mode, or, the second data set is the output result of the sender of the third information block performing a third inference configuration; the data type in the second data set is the channel data type;

[0422] For the first node N1, the first information block is received in step S9101; a third information block is sent in step S9102, the third information block indicating a second data set; wherein, the indication of the third information block depends on the first condition set not being satisfied; the second data set is the measurement result after the first node N1 enters the fallback mode, or the second data set is the output result of the first node N1 executing the third inference configuration; the data type in the second data set is the channel data type.

[0423] As an example, please refer to the example of the second information block for an example of the third information block.

[0424] As an example, the indication of the third information block depending on the first condition set not being satisfied means that step S9102 includes sending the third information block as a response to the first condition set not being satisfied.

[0425] As an example, the indication of the third information block depending on the first condition set not being satisfied means that the third information block indicates that the first condition set is not satisfied.

[0426] As an example, the indication of the third information block depending on the first condition set not being satisfied means that step S9101 includes, as a response to the first condition set not being satisfied, the first node N1 entering a fallback mode and measuring or executing the third inference configuration.

[0427] As an example, the fallback mode means that the first inference configuration is no longer applicable to the first node N1.

[0428] As an example, the fallback mode means that the first node N1 no longer executes the first inference configuration.

[0429] As an example, the fallback mode refers to the following: the first node N1 generates data of the information data type using a method other than inference configuration / training.

[0430] As an example, the fallback mode refers to the following: the first node N1 uses a method other than AI / ML to generate data of the information data type.

[0431] As a sub-example of the above embodiments, for scenarios involving CSI prediction, CSI compression / feedback, and beam management, the fallback mode includes measurement on at least one RS resource; the at least one RS resource is configured.

[0432] As a sub-example of the above embodiments, for a positioning scenario, the back-off mode includes conventional positioning methods; typically, but not limitingly, the conventional positioning methods include the positioning methods described in Section 8 of TS 38.305V18.1.0.

[0433] As an example, please refer to the example of the first inference configuration for an example of the third inference configuration.

[0434] As an example, the first set of conditions not being met includes the first performance not meeting the first performance requirement, the first timer expiring, and the first performance not being able to simultaneously meet at least one of the first performance requirement and the second performance requirement.

[0435] As an example, for the first node N1, in step S91021, a fourth information block is sent, indicating that the first condition set is not satisfied; in step S91022, a fifth information block is received, indicating the entry into fallback mode or the third inference configuration; wherein, the fifth information block is triggered by the fourth information block, and the third information block is triggered by the fifth information block; correspondingly, for the second node N2, in step S92021, a fourth information block is received, indicating that the first condition set is not satisfied; in step S92022, a fifth information block is sent, indicating the entry into fallback mode or the third inference configuration; wherein, the fifth information block is triggered by the fourth information block, and the third information block is triggered by the fifth information block.

[0436] As a sub-implementation of the above embodiments, an example of the fourth information block is provided in the example of the second information block, and an example of the fifth information block is provided in the example of the first information block.

[0437] As a sub-implementation of the above embodiment, the fifth information block instructs the execution of the third inference configuration to output the second data set.

[0438] As a sub-implementation of the above embodiment, the fourth information block includes the reason value for why the first condition set is not satisfied.

[0439] The above sub-implementation helps the second node make decisions based on the reasons why the first condition set is not satisfied, thereby increasing the likelihood that the second node will obtain data that satisfies the channel data type.

[0440] As a sub-implementation of the above sub-implementation, the cause value includes at least one of the following: the first performance does not meet the first performance requirement, the first timer expires, and the first performance cannot simultaneously meet the first performance requirement and the second performance requirement.

[0441] As a sub-implementation of the above sub-implementation, in the case of the first timer expiring, the fourth information block includes the indication information #2.

[0442] Example 10

[0443] Example 10 illustrates a schematic diagram of RAN (Radio Access Network) domain AI / ML function deployment according to an embodiment of this application, as shown in Figure 10. The gNB in ​​Example 10 can be replaced with, for example, an eNB, or a network device such as a 6G base station.

[0444] 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.

[0445] 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 (MDA 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).

[0446] 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.

[0447] Similarly, ML testing functionality can also be deployed in cross-domain management systems or domain-specific management systems.

[0448] In Example 10, the RAN domain ML training function 1002 is located in the RAN domain management function 1003; while the ML inference function is located in the base station, that is, the AI / ML inference function 1004 is located in gNB 1005, the AI / ML inference function 1006 is located in gNB 1007, and so on.

[0449] In Figure 10, the management of ML inference functions of multiple base stations is completed by RAN domain management function 1003, that is, data interaction with RAN domain MnS (Mangement Service) consumer / cross-domain management 1001 (as shown by the dashed arrow in Figure 10).

[0450] 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 1001.

[0451] It should be noted that Embodiment 10 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.

[0452] As an example, one of the gNBs (or base stations) in Example 10 is the second node of this application.

[0453] Example 11

[0454] Example 11 illustrates a schematic diagram of the deployment of AI / ML functionality in a UE according to one embodiment of this application; as shown in Figure 11. The RAN domain ML training function 1105 in Figure 11 is optional.

[0455] UE function 1104 is deployed in the first node of this application, and the UE function 1104 includes AI / ML inference function 1106; the AI / ML inference function 1106 uses an ML model (also known as an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[0456] As an example, the UE function 1104 includes a RAN domain ML training function 1105, 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.

[0457] 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.

[0458] Optionally, the UE function 1104 also includes a CN domain ML training function (not shown in Figure 11).

[0459] Optionally, the UE function 1104 also includes an AI / ML deployment function—not shown in Figure 11—for loading ML models and data.

[0460] 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.

[0461] As an example, the ML model and the associated metadata are loaded by the first node from a network device or a remote server.

[0462] Optionally, the UE function 1104 is an MnS (Management Service) producer that provides data to the CN domain MnF (Management Function) 1101, and / or the RAN domain MnF 1102, and / or the cross-domain management system 1103 for management or analysis (as shown by double arrow 1107).

[0463] Optionally, the UE function 1104 is an MnS consumer that loads data from the CN domain MnF (Management Function) 1101, and / or the RAN domain MnF 1102, and / or the cross-domain management system 1103 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1107).

[0464] As an example, the first performance in this application is obtained by inference using an ML model (also known as an AI model) via the AI / ML inference function 1106.

[0465] As an example, at least one of the first receiver and the first transmitter includes a RAN domain ML training function 1105 in Figure 11.

[0466] As an example, at least one of the first receiver and the first transmitter includes an AL / ML inference function 1106 in Figure 11.

[0467] As an example, the ML model is a model based on NN (Neural Networks).

[0468] As an example, the ML model is based on an ANN (Artificial Neural Networks) model.

[0469] As an example, the ML model is based on a CNN (Conventional Neural Networks) model.

[0470] As an example, the ML model is based on a GNN (Graph Neural Network) model.

[0471] As an example, the ML model is based on the LLM (Large Language Model) architecture.

[0472] As an example, the ML model is based on the Transformer architecture.

[0473] As an example, the ML model is based on the GPT (Generative Pre-Trained) architecture.

[0474] As an example, the ML model is based on an LSTM (Long Short-Term Memory) network.

[0475] As an example, the ML model is based on an MLP (MultiLayer Perceptron) model.

[0476] As an example, the ML model is based on GAN (Generative Adversarial Nets).

[0477] As an example, the ML model is based on a lightweight neural network.

[0478] As an example, the lightweight neural network includes one or more of MobileNet, ShuffleNet, and SqueezeNet.

[0479] Example 12

[0480] Example 12 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application, as shown in Figure 12. In Figure 12, the processing system based on artificial intelligence or machine learning includes a first processor, a second processor, a third processor, and a fourth processor.

[0481] In Example 12, 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 12, 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.

[0482] As one embodiment, the fourth processor includes ML testing functionality.

[0483] As one embodiment, the fourth processor includes performance monitoring / evaluation of the ML model.

[0484] As one embodiment, the third processor sends a first type of feedback to the second processor; the first type of feedback is used to trigger the recalculation or update of the target first type of parameter set, that is, to trigger ML initial training or ML retraining.

[0485] 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.

[0486] As one embodiment, the first processor generates the first dataset and the second dataset based on the measurement of the reference signal.

[0487] As an example, both the first processor and the second processor belong to the first node.

[0488] As an example, the second processor belongs to the first node; the above method avoids passing the first dataset to the second node.

[0489] As one embodiment, the third processor belongs to the first node, and the fourth processor belongs to the second node.

[0490] As an example, both the third processor and the fourth processor belong to the first node.

[0491] As an example, the first dataset includes training data.

[0492] 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.

[0493] As an example, the second dataset includes inference data.

[0494] 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.

[0495] As an example, the target first type of parameter group includes at least one AI / ML model associated with the first inference configuration in this application.

[0496] As an example, the first type of output includes the first data set in this application.

[0497] As an example, the output of the third processor includes the first performance described in this application.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] Example 13

[0504] Example 13 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application, as shown in Figure 13. In Figure 13, 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 the process.

[0505] 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.

[0506] 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.

[0507] As an example, the first stage includes AI / ML model training.

[0508] As an example, the first stage includes AI / ML model training and AI / ML testing.

[0509] As an example, the AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[0510] As an example, the training of the AI / ML model depends on training data.

[0511] As an example, the AI / ML model training includes AI / ML entity validation.

[0512] As an example, the AI / ML entity verification is used to evaluate the performance of the AI / ML entity.

[0513] As an example, the AI / ML entity verification relies on verification data.

[0514] As an example, if the AI / ML entity verification results do not meet expectations, the AI / ML model will be retrained.

[0515] As an example, the AI / ML testing includes testing the validated AI / ML entities to estimate the performance of the trained AI / ML model.

[0516] 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.

[0517] As an example, the AI / ML test relies on test data.

[0518] As one embodiment, the second stage includes AI / ML simulation, which performs AI / ML entity reasoning in a simulation environment.

[0519] As an example, the AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using AI / ML entities.

[0520] As one embodiment, the second stage is optional.

[0521] 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.

[0522] As an example, the third stage is optional.

[0523] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[0524] As an example, the fourth stage includes AI / ML inference.

[0525] Example 14

[0526] Example 14 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of this application; as shown in Figure 14. In Figure 14, the processing apparatus 1400 in the first node includes a first receiver 1401 and a first transmitter 1402.

[0527] The first receiver 1401 receives a first information block, the first information block indicating the channel data type and the first performance requirements; the first transmitter 1402 transmits a second information block, the second information block including a first data set;

[0528] In Example 14, the indication of the first information block depends on the applicability of the first inference configuration to the first node; the performance monitoring of the first node executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

[0529] As one example, the first dataset is used for training or performance monitoring of the second inference configuration; the second inference configuration is different from the first inference configuration.

[0530] As an example, the first performance is the performance of the first node executing the first inference configuration before receiving the first information block.

[0531] As an example, the first performance is the performance of the first node executing the first inference configuration after receiving the first information block.

[0532] As one embodiment, the first receiver 1401 starts a first timer in response to begin calculating the first performance; wherein the first condition set includes the first timer not expiring.

[0533] As an example, the first set of conditions includes the first performance simultaneously satisfying both the first performance requirement and the second performance requirement.

[0534] As an example, the first transmitter 1402 transmits a third information block, the third information block indicating a second data set; wherein, the indication of the third information block depends on the first condition set not being satisfied; the second data set is the measurement result after the first node enters the fallback mode, or the second data set is the output result of the first node performing a third inference configuration; the data type in the second data set is the channel data type.

[0535] As one example, the first node is a user equipment.

[0536] As a sub-example of the above embodiments, the user equipment is a terminal.

[0537] As a sub-implementation of the above embodiments, the first receiver 1401 includes at least one of the following in embodiment 4: {antenna 452, receiver 454, receiver processor 456, multi-antenna receiver processor 458, controller / processor 459, memory 460, data source 467}.

[0538] As a sub-implementation of the above embodiments, the first transmitter 1402 includes at least one of the following in embodiment 4: {antenna 452, transmitter 454, transmission processor 468, multi-antenna transmission processor 457, controller / processor 459, memory 460, data source 467}.

[0539] As one example, the first node is an access network device or a core network device.

[0540] As a sub-example of the above embodiments, the access network device is a base station device.

[0541] As a sub-example of the above embodiments, the access network device is a relay node device.

[0542] As a sub-implementation of the above embodiments, the first node is a network element in the core network device.

[0543] As a sub-implementation of the above embodiments, the first node is a functional entity in the core network device.

[0544] As a sub-implementation of the above embodiments, the first receiver 1401 includes at least one of the following in embodiment 4: {antenna 420, receiver 418, receiver processor 470, multi-antenna receiver processor 472, controller / processor 475, memory 476}.

[0545] As a sub-example of the above embodiments, the first transmitter 1402 includes at least one of the following in embodiment 4: {antenna 420, transmitter 418, transmission processor 416, multi-antenna transmission processor 471, controller / processor 475, memory 476}.

[0546] Example 15

[0547] Example 15 illustrates a structural block diagram of a processing apparatus for a second node according to an embodiment of this application; as shown in Figure 15. In Figure 15, the processing apparatus 1500 in the second network device includes a second receiver 1501 and a second transmitter 1502.

[0548] The second transmitter 1502 transmits a first information block, the first information block indicating the channel data type and the first performance requirements; the second receiver 1501 receives a second information block, the second information block including a first data set.

[0549] In Example 15, the indication of the first information block depends on the applicability of the first inference configuration to the receiver of the first information block; the performance monitoring of the receiver of the first information block executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the receiver of the first information block executing the first inference configuration.

[0550] As one example, the first dataset is used for training or performance monitoring of the second inference configuration; the second inference configuration is different from the first inference configuration.

[0551] As an example, the first performance is the performance of the recipient of the first information block performing the first inference configuration before receiving the first information block.

[0552] As an example, the first performance is the performance of the receiver of the first information block performing the first inference configuration after receiving the first information block.

[0553] As one embodiment, the first condition set includes the first timer not having expired; the recipient of the first information block starts the first timer in response to begin calculating the first performance.

[0554] As an example, the first set of conditions includes the first performance simultaneously satisfying both the first performance requirement and the second performance requirement.

[0555] As one embodiment, the second receiver 1501 receives a third information block, the third information block indicating a second data set; wherein, the indication of the third information block depends on the first condition set not being satisfied; the second data set is the measurement result after the sender of the third information block enters the fallback mode, or, the second data set is the output result of the sender of the third information block performing a third inference configuration; the data type in the second data set is the channel data type.

[0556] In one embodiment, the second node is a user equipment.

[0557] As a sub-example of the above embodiments, the user equipment is a terminal.

[0558] As a sub-implementation of the above embodiments, the second receiver 1501 includes at least one of the following in embodiment 4: {antenna 452, receiver 454, receiver processor 456, multi-antenna receiver processor 458, controller / processor 459, memory 460, data source 467}.

[0559] As a sub-example of the above embodiments, the second transmitter 1502 includes at least one of the following in embodiment 4: {antenna 452, transmitter 454, transmission processor 468, multi-antenna transmission processor 457, controller / processor 459, memory 460, data source 467}.

[0560] As one embodiment, the second node is an access network device or a core network device.

[0561] As a sub-example of the above embodiments, the access network device is a base station device.

[0562] As a sub-example of the above embodiments, the access network device is a relay node device.

[0563] As a sub-implementation of the above embodiments, the second node is a network element in the core network device.

[0564] As a sub-implementation of the above embodiments, the second node is a functional entity in the core network device.

[0565] As a sub-implementation of the above embodiments, the second receiver 1501 includes at least one of the following in embodiment 4: {antenna 420, receiver 418, receiver processor 470, multi-antenna receiver processor 472, controller / processor 475, memory 476}.

[0566] As a sub-example of the above embodiments, the second transmitter 1502 includes at least one of the following in embodiment 4: {antenna 420, transmitter 418, transmission processor 416, multi-antenna transmission processor 471, controller / processor 475, memory 476}.

[0567] 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 access cards, IoT terminals, RFID terminals, NB-IoT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet access 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, eNBs, gNBs, TRPs (Transmitter Receiver Points), GNSS, relay satellites, satellite base stations, airborne base stations, RSUs (Road Side Units), drones, and testing equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[0568] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A first node for wireless communication, the first node comprising: include: A first receiver receives a first information block, the first information block indicating the channel data type and a first performance requirement; A first transmitter sends a second information block, the second information block including a first data set; Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the first node; the performance monitoring of the first node executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance that satisfies the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

2. The first node of claim 1, characterized in that, The first dataset is used for training or performance monitoring of the second inference configuration; the second inference configuration is different from the first inference configuration.

3. The first node of claim 1 or 2, wherein, The first performance is the performance of the first node executing the first inference configuration before receiving the first information block.

4. The first node of claim 1 or 2, characterized by, The first performance refers to the performance of the first node in executing the first inference configuration after receiving the first information block.

5. The first node of claim 4, wherein, include: The first receiver, in response to the start of calculating the first performance, starts a first timer; The first condition set includes the fact that the first timer has not expired.

6. The first node of any of claims 1 to 5, wherein, The first set of conditions includes the first performance simultaneously satisfying both the first performance requirement and the second performance requirement.

7. The first node of any of claims 1 to 6, wherein, include: The first transmitter sends a third information block, the third information block indicating a second data set; Wherein, the indication of the third information block depends on the first condition set not being satisfied; the second data set is the measurement result after the first node enters the fallback mode, or the second data set is the output result of the first node executing the third inference configuration; the data type in the second data set is the channel data type.

8. A second node for use in wireless communication, characterized by include: The second transmitter sends a first information block, which indicates the channel data type and the first performance requirements. A second receiver receives a second information block, the second information block including a first data set; Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the receiver of the first information block; the performance monitoring of the receiver of the first information block executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance satisfying the first performance requirement; the first performance is the performance of the receiver of the first information block executing the first inference configuration.

9. A method in a first node used for wireless communication, characterized by, include: Receive a first information block, the first information block indicating the channel data type and a first performance requirement; Send a second information block, the second information block including the first data set; Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the first node; the performance monitoring of the first node executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the first node executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance that satisfies the first performance requirement; the first performance is the performance of the first node executing the first inference configuration.

10. A method, in a second node, for wireless communication, characterized by, include: Send a first information block, which indicates the channel data type and a first performance requirement; Receive a second information block, the second information block including a first data set; Wherein, the indication of the first information block depends on the applicability of the first inference configuration to the receiver of the first information block; the performance monitoring of the receiver of the first information block executing the first inference configuration depends on the second performance requirement; the first data set is the output result of the receiver of the first information block executing the first inference configuration after receiving the first information block; the data type in the first data set is the channel data type; the indication of the second information block depends on the satisfaction of the first condition set; the first condition set includes a first performance requirement satisfying the first performance requirement; The first performance is the performance of the receiver of the first information block executing the first inference configuration.

Images