Method and apparatus for applicable functionality processing for wireless communication

Abstract

The present application discloses a method and apparatus for applicable functionality processing for wireless communication. A terminal receives a first RRC reconfiguration message, wherein the first RRC reconfiguration message comprises configuration information of a first candidate cell and an execution condition for the first candidate cell, and the configuration information of the first candidate cell comprises at least one of a C-RNTI and T304 of at least the first node in the first candidate cell; the terminal sends a first RRC message, wherein the first RRC message indicates that a first inference configuration is applicable; upon sending the first RRC message, the terminal applies the configuration information of the first candidate cell; and in response to applying the configuration information of the first candidate cell, the terminal sends a first RRC reconfiguration complete message, wherein the configuration information of the first candidate cell comprises the first inference configuration, and the applying the configuration information of the first candidate cell comprises applying the first inference configuration.

Description

A method and apparatus for applicable functional processing in wireless communication

[0001] This application claims priority to Chinese Patent Application No. 202411948672.5, filed on December 25, 2024, entitled "A Method and Apparatus for Applicable Functional Processing in Wireless Communication", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to methods and apparatus for handling applicable functions during handover. Background Technology

[0003] In NR Release 18, research on AI (Artificial Intelligence) / ML (Machine Learning) technologies was initiated to explore their impact on system performance and design. 3GPP Release 19 launched the WI: "AI (Artificial Intelligence) / ML (Machine Learning) for NR Air Interface," supporting a general AI / ML architecture for one-sided AI / ML models. Compared to traditional processing methods, AI / ML offers advantages such as training-based and deployment-required features. Furthermore, AI / ML is a key candidate technology for future 6G communication. Regarding LCM (Life Cycle Management) for UE-side models, the following consensus was reached at RAN2 meeting 128: reporting applicable functionality is supported in handover scenarios.

[0004] Since the specifications of AI models may extend beyond the scope of 3GPP (except for reference models used for performance calibration), the specific implementation of AI / ML training and AI / ML inference may be determined by the hardware equipment vendors themselves. It may be based on classic models such as Transformer architecture, RNN (Recurrent Neural Network), CNN (Conventional Neural Networks), or a hybrid model composed of multiple models. Summary of the Invention

[0005] The applicant's research found that currently, when a UE (User Equipment) performs a handover, it is allowed to carry inference configuration and / or network-side additional conditions in the handover command and report the applicable functions after the handover is completed. Considering that the inference configuration and / or network-side additional conditions can be configured to the terminal along with the target cell configuration, the applicable functions of the target cell can be evaluated when the target cell configuration is applied. If the applicable functions of the current serving cell are still applicable in the target cell, how to make full use of the existing configuration and avoid repeated training is the problem that this application needs to solve.

[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 applicable functions, this application is also applicable to other solutions, such as traditional information reporting solutions. It should also be noted that although the initial purpose of this application was to address the issue of handling applicable functions during handover, this application is also applicable to other scenarios, such as handling applicable functions when a wireless link fails, achieving similar effects to handover-time applicable function handling. Furthermore, using a unified solution across different scenarios helps reduce hardware complexity and cost. Where there is no conflict, the embodiments and features in the terminals of this application can be applied to any 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] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS38 series.

[0008] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS28 series.

[0009] It should be noted that, unless otherwise specified, the embodiments and features in any node of this application can be applied to any other node. Furthermore, unless otherwise specified, the embodiments and features in any embodiment of this application can be arbitrarily combined with each other.

[0010] This application discloses a method used in a terminal for wireless communication, comprising:

[0011] Receive a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the terminal's C-RNTI and T304 in the first candidate cell;

[0012] The above method reuses the existing conditional switching protocol.

[0013] Send a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable;

[0014] The above method indicates that the first inference configuration is applicable when no handover is performed, thereby improving the robustness of candidate configurations when the first inference configuration is applied during handover.

[0015] After the first RRC message is sent, the configuration information of the first candidate cell is applied as a response to the execution conditions of the first candidate cell being met.

[0016] In response to the application of the configuration information of the first candidate cell, a first RRC reconfiguration complete message is sent;

[0017] Wherein, the configuration information of the first candidate cell includes the first inference configuration; the configuration information of applying the first candidate cell includes applying the first inference configuration.

[0018] The above method directly applies the first inference configuration when applying the first candidate cell, reducing signaling interaction and RRC reconfiguration, which can effectively improve the utilization rate of resource allocation.

[0019] According to one aspect of this application, the first inference configuration includes K1 associated identifiers, at least one of the K1 associated identifiers being associated with at least one RS resource of the first candidate cell; wherein K1 is a positive integer.

[0020] The above method uses association identifiers to link inference configuration and RS resources. Considering the differences in RS resource configuration among different cells, it helps to unify the resource configuration of different cells, make reasonable use of RS resources of candidate cells, reduce reconfiguration time, and improve the inference efficiency of AIML models.

[0021] According to one aspect of this application, at least one of the K1 associated identifiers is associated with at least one RS resource of at least one serving cell.

[0022] When the inference configuration is applied by the serving cell, the inference configuration and the serving cell's RS resources are associated using the association identifier. Considering the differences in RS resources between different cells, this is beneficial for the coordination between the terminal and the base station.

[0023] According to one aspect of this application, it includes:

[0024] The application of the first inference configuration includes: restoring the first inference configuration; wherein the first inference configuration is suspended.

[0025] The above method takes into account the different applicability of inference configuration in different cells. By suspending the inference configuration during handover, the terminal has time to determine whether the inference configuration is applicable, thereby improving the configuration fault tolerance rate.

[0026] The above method reduces the need for inference configuration reconfiguration by restoring the inference configuration, which helps to reduce signaling interactions.

[0027] According to one aspect of this application, the configuration information of the first candidate cell indicates whether the first inference configuration is activated.

[0028] The above method indicates whether to activate the first inference configuration by using the configuration information of the first candidate cell, which is beneficial for quickly utilizing the inference configuration, reducing inference interruption time, and making the interaction between the terminal and the network smoother.

[0029] According to one aspect of this application, the first RRC reconfiguration completion message indicates that the first inference configuration is not applicable; wherein, the first inference configuration is not applicable.

[0030] The above method takes into account the case where the first inference configuration is not applicable to the first candidate cell. By using the RRC reconfiguration completion message indication, the network can be made aware of the configuration more quickly and conveniently, and no new signaling needs to be designed, thus reducing complexity.

[0031] This application discloses a method used in a base station for wireless communication, comprising:

[0032] Send a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the terminal's C-RNTI and T304 in the first candidate cell;

[0033] Receive a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable;

[0034] Receive the first RRC reconfiguration complete message;

[0035] Wherein, after sending the first RRC message, the sender of the first RRC message applies the configuration information of the first candidate cell as a response to the execution condition of the first candidate cell being met; as a response to applying the configuration information of the first candidate cell, the sender of the first RRC message sends the first RRC reconfiguration complete message; the configuration information of the first candidate cell includes the first inference configuration; applying the configuration information of the first candidate cell includes applying the first inference configuration.

[0036] According to one aspect of this application, the first inference configuration includes K1 associated identifiers, at least one of the K1 associated identifiers being associated with at least one RS resource of the first candidate cell; wherein K1 is a positive integer.

[0037] According to one aspect of this application, at least one of the K1 associated identifiers is associated with at least one RS resource of at least one serving cell.

[0038] According to one aspect of this application, it includes:

[0039] The application of the first inference configuration includes: restoring the first inference configuration; wherein the first inference configuration is suspended.

[0040] According to one aspect of this application, the configuration information of the first candidate cell indicates whether the first inference configuration is activated.

[0041] According to one aspect of this application, the first RRC reconfiguration completion message indicates that the first inference configuration is not applicable; wherein, the first inference configuration is not applicable.

[0042] This application discloses a terminal used for wireless communication, comprising:

[0043] A first processor receives a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the terminal's C-RNTI and T304 in the first candidate cell;

[0044] A first processor sends a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable;

[0045] The first processor, after sending the first RRC message, applies the configuration information of the first candidate cell as a response to the execution conditions of the first candidate cell being met;

[0046] The first processor, in response to the application of the configuration information of the first candidate cell, sends a first RRC reconfiguration complete message;

[0047] Wherein, the configuration information of the first candidate cell includes the first inference configuration; the configuration information of applying the first candidate cell includes applying the first inference configuration.

[0048] This application discloses a base station used for wireless communication, comprising:

[0049] The second processor sends a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the terminal's C-RNTI and T304 in the first candidate cell;

[0050] The second processor receives a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable;

[0051] The second processor receives the first RRC reconfiguration complete message;

[0052] Wherein, after sending the first RRC message, the sender of the first RRC message applies the configuration information of the first candidate cell as a response to the execution condition of the first candidate cell being met; as a response to applying the configuration information of the first candidate cell, the sender of the first RRC message sends the first RRC reconfiguration complete message; the configuration information of the first candidate cell includes the first inference configuration; applying the configuration information of the first candidate cell includes applying the first inference configuration. Attached Figure Description

[0053] 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:

[0054] Figure 1 shows a flowchart of the transmission of a terminal according to an embodiment of this application;

[0055] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0056] 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;

[0057] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0058] Figure 5 shows a flowchart of wireless signal transmission according to an embodiment of this application;

[0059] Figure 6 illustrates a schematic diagram of the first inference configuration according to an embodiment of this application, which includes K1 associated identifiers;

[0060] Figure 7 shows a schematic diagram of K1 associated identifiers according to an embodiment of this application;

[0061] Figure 8 shows a schematic diagram of the application of the first inference configuration according to another embodiment of this application;

[0062] Figure 9 shows a schematic diagram of the configuration information of the first candidate cell according to an embodiment of this application;

[0063] Figure 10 shows a structural block diagram of a processing device for a terminal according to an embodiment of the present application;

[0064] Figure 11 shows a structural block diagram of a processing apparatus for a base station according to an embodiment of the present application;

[0065] Figure 12 shows a schematic diagram of an AI / ML model according to an embodiment of this application;

[0066] Figure 13 shows a schematic diagram of the deployment of UE smart functions according to an embodiment of this application. Detailed Implementation

[0067] The technical solution of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0068] Example 1

[0069] Example 1 illustrates a flowchart of terminal transmission according to an embodiment of this application, as shown in Figure 1. In Figure 1, each box represents a step, and it is particularly important to emphasize that the order of the boxes in the figure does not represent the temporal sequence of the steps represented.

[0070] In Embodiment 1, the terminal in this application receives a first RRC reconfiguration message in step 101; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of C-RNTI and T304 of the terminal in the first candidate cell; in step 102, a first RRC message is sent; wherein the first RRC message indicates that a first inference configuration is applicable; in step 103, after sending the first RRC message, the configuration information of the first candidate cell is applied as a response to the execution conditions of the first candidate cell being met; in step 104, a first RRC reconfiguration complete message is sent as a response to the application of the configuration information of the first candidate cell;

[0071] Wherein, the configuration information of the first candidate cell includes the first inference configuration; the configuration information of applying the first candidate cell includes applying the first inference configuration.

[0072] As an example, the first RRC reconfiguration message includes configuration information of multiple candidate cells, including at least the first candidate cell.

[0073] As an example, the first RRC reconfiguration message includes configuration information and execution conditions for multiple candidate cells, including at least the first candidate cell.

[0074] As an example, the first RRC reconfiguration message includes an RRCReconfiguration message, which includes the configuration information of the first candidate cell.

[0075] As an example, the first RRC reconfiguration message is an RRCReconfiguration message, which includes the configuration information of the first candidate cell.

[0076] As an example, the first RRC reconfiguration message includes a ReconfigurationWithSync field, which includes the configuration information of the first candidate cell.

[0077] As an example, the first RRC reconfiguration message includes a CondReconfigToAddMod IE, wherein the CondReconfigToAddMod IE includes the configuration information of the first candidate cell.

[0078] As an example, the first RRC reconfiguration message includes an LTM-Candidate IE, which includes the configuration information of the first candidate cell.

[0079] As an example, the first RRC reconfiguration message includes a first candidate configuration, which includes configuration information of a first candidate cell.

[0080] As an example, the first candidate configuration is a CHO candidate configuration, and the first candidate cell is a CHO candidate cell.

[0081] As an example, the first candidate configuration is an LTM candidate configuration, and the first candidate cell is an LTM candidate cell.

[0082] As an example, the first candidate configuration is a C-LTM candidate configuration, and the first candidate cell is an LTM candidate cell.

[0083] As an example, the first candidate cell is PCell.

[0084] As an example, the first candidate cell is at least PCell.

[0085] As an example, the configuration information of the first candidate cell includes at least the C-RNTI of the terminal in the first candidate cell.

[0086] As an example, the configuration information of the first candidate cell includes at least T304 in the first candidate cell.

[0087] As an example, the configuration information of the first candidate cell includes at least the random access information of the first candidate cell.

[0088] As one embodiment, the random access information includes: time and frequency resources for random access.

[0089] As one embodiment, the random access information includes: timing advance information.

[0090] As one embodiment, the random access information includes: quasi-co-address information of the reference signal.

[0091] As an example, the configuration information of the first candidate cell includes at least the cell identifier of the first cell.

[0092] As an example, the cell identifier is a logical identifier.

[0093] As an example, the cell identifier is a bit string.

[0094] As an example, the cell identifier includes PCI.

[0095] As an example, the cell identifier includes the cell's servingCellId.

[0096] As an example, the cell identifier includes the PLMN (Public Land Mobile Network) to which the cell belongs.

[0097] As one example, the cell identifier includes the SNPN (Stand-alone Non-Public Network) to which the cell belongs.

[0098] As an example, the cell identifier includes TAC (Tracking Area Code) and / or TAI.

[0099] As one example, the cell identifier includes GCI (Global Cell Identifier).

[0100] As one example, the cell identifier includes NGCI (NR Cell Global Identifier).

[0101] As one example, the cell identifier includes the LCID logical cell identifier.

[0102] As an example, the cell identifier includes NCI.

[0103] As one example, the cell identifier includes the gNB ID.

[0104] As one example, the cell identifier includes the global gNB ID.

[0105] As an example, the cell identifier includes GCI and TAC.

[0106] As one example, the cell identifier includes the PCI and the carrier frequency.

[0107] As one example, the cell identifier includes PLMN and CGI.

[0108] As an example, the cell identifier includes SNPN and CGI.

[0109] As an example, the cell identifier uniquely indicates the first candidate cell within a tracking area.

[0110] As an example, the cell identifier uniquely indicates the first candidate cell within multiple tracking areas.

[0111] As an example, the cell identifier uniquely indicates the first candidate cell within a PLMN.

[0112] As an example, the cell identifier uniquely indicates the first candidate cell within multiple PLMNs.

[0113] As an example, the cell identifier uniquely indicates the first candidate cell within a SNPN.

[0114] As an example, the cell identifier uniquely indicates the first candidate cell within multiple SNPNs.

[0115] As an example, the cell identifier includes the GCI, if available; otherwise, the cell identifier includes the PCI and the cell's carrier frequency.

[0116] As an example, the cell identifier includes GCI and TAC, if available; otherwise, the cell identifier includes PCI.

[0117] As an example, the cell identifier includes GCI and TAC, if available; otherwise, the cell identifier includes PCI and the cell's carrier frequency.

[0118] As one embodiment, the cell identifier includes GCI, or the cell identifier includes PCI and the cell's carrier frequency.

[0119] As an example, the configuration information of the first candidate cell includes the first inference configuration.

[0120] As an example, the configuration information of the first candidate cell includes network-side additional conditions for the first candidate cell.

[0121] As an example, the configuration information of the first candidate cell includes the inference configuration of the first candidate cell.

[0122] As an example, the configuration information of the first candidate cell includes the report configuration of the first candidate cell.

[0123] As an example, the configuration information of the first candidate cell includes additional UE-side conditions for activating the terminal.

[0124] As an example, the additional conditions on the UE side are determined by the terminal based on the terminal's available storage resources.

[0125] As an example, the additional conditions on the UE side are determined by the terminal based on the terminal's power consumption.

[0126] As an example, the additional conditions on the UE side are determined by the terminal based on the terminal's movement speed.

[0127] As one embodiment, the additional conditions on the UE side are determined by the terminal; wherein, the determination can be made automatically or based on the UE implementation.

[0128] As an example, the portion of the additional conditions on the UE side is determined by the terminal, and the portion of the additional conditions on the UE side is predefined.

[0129] As one embodiment, in response to the receipt of the first RRC reconfiguration message, the execution conditions of the first candidate cell are evaluated, and in response to the execution conditions of the first candidate cell being met, the configuration information of the first candidate cell is applied; wherein, the first RRC message includes the execution conditions of the first candidate cell.

[0130] As an example, the execution conditions of the first candidate cell depend on at least one RS resource.

[0131] As an example, the at least one RS resource does not belong to the first inference configuration.

[0132] As an example, the at least one RS resource is not associated with the first inference configuration.

[0133] As an example, the at least one RS resource is used for switching.

[0134] As an example, the at least one RS resource is associated with a reporting resource.

[0135] As an example, the at least one RS resource is associated with a reporting configuration.

[0136] As an example, the measurement result of the at least one RS resource is an L3 measurement result.

[0137] As an example, the measurement result of the at least one RS resource is an L1 measurement result.

[0138] As an example, after the first RRC reconfiguration message is received, a MAC CE is received, and in response to the receipt of the MAC CE, the configuration information of the first candidate cell is applied; wherein the MAC CE indicates the first candidate cell.

[0139] As an example, the MAC CE indicates the first candidate cell.

[0140] As an example, the MAC CE includes an index of the first candidate cell.

[0141] As an example, the MAC CE includes the timing advance information of the first candidate cell.

[0142] As an example, the MAC CE is an LTM Cell Switch Command.

[0143] As an example, the MAC CE includes an LTM Cell Switch Command.

[0144] As an example, the first RRC message is an RRCReconfigurationComplete message.

[0145] As an example, the first RRC message is a UEAssistanceInformation message.

[0146] As an example, the first RRC message includes an RRCReconfigurationComplete message.

[0147] As an example, the first RRC message includes a UEAssistanceInformation message.

[0148] As an example, the first RRC message is a message indicating that the RRC process has been completed.

[0149] As an example, the first RRC message explicitly indicates the first inference configuration.

[0150] As an example, the first RRC message implicitly indicates the first inference configuration.

[0151] As an example, the first RRC message indicates the status of the first inference configuration.

[0152] As an example, the first RRC message indicates that the first inference configuration is applicable.

[0153] As an example, the first RRC message includes the first inference configuration.

[0154] As an example, the first RRC message includes an index of the first inference configuration.

[0155] As an example, the first RRC message includes at least the first inference configuration.

[0156] As an example, the first RRC message indicates all applicable inference configurations.

[0157] As an example, the first RRC message indicates that any inference configuration in the terminal changes from applicable to inapplicable.

[0158] As an example, the first RRC message is triggered when any inference configuration in the terminal changes from applicable to inapplicable.

[0159] As an example, the first RRC message is triggered as a response to the application of the first inference configuration.

[0160] As an example, in response to an applicable inference configuration, the first RRC message is triggered, indicating all applicable inference configurations.

[0161] As an example, the first RRC message is a measurement report.

[0162] As an example, the first RRC message includes a measurement report.

[0163] As an example, the first RRC message indicates whether the inference configuration of the candidate cell is applicable.

[0164] As an example, the first RRC message indicates whether the inference configuration of the neighboring cell is applicable.

[0165] As an example, the first RRC message indicates whether all configured inference configurations are applicable.

[0166] As an example, when at least the first set of conditions is satisfied, the first RRC message indicates that the first inference configuration is applicable.

[0167] As an example, the at least first condition set includes the first condition set and at least one condition other than the first condition set, the at least one condition being determined by the terminal.

[0168] As an example, the first set of conditions depends on network configuration.

[0169] As an example, the network configuration refers to configuration by an RRC reconfiguration message.

[0170] As an example, the network configuration refers to configuration by a system message.

[0171] As an example, the network configuration refers to configuration by a broadcast message.

[0172] As an example, the first set of conditions is the default.

[0173] As an example, a second RRC reconfiguration message is received before the first RRC message is sent.

[0174] As an example, the second RRC reconfiguration message is for AI / ML model inference.

[0175] As an example, the second RRC reconfiguration message is for AI / ML model training.

[0176] As one example, the second RRC reconfiguration message includes multiple inference configurations, including at least a first inference configuration.

[0177] As one embodiment, the multiple inference configurations, including at least the first inference configuration, are for the current serving cell.

[0178] As an example, the currently serving cell is not the first candidate cell.

[0179] As an example, the currently serving cell is a PCell.

[0180] As an example, the currently serving cell belongs to an MCG.

[0181] As one embodiment, the first message is sent along with receiving the second RRC reconfiguration message.

[0182] As an example, the first message is sent after the second RRC reconfiguration message is received.

[0183] As an example, the second RRC reconfiguration message does not include configuration information for a cell other than the currently serving cell.

[0184] As an example, the second RRC reconfiguration message does not include the configuration information of the candidate cell.

[0185] As an example, the candidate cell is at least one of CHO candidate cells, LTM candidate cells, and / or C-LTM candidate cells.

[0186] As an example, the candidate cell is a candidate PCell.

[0187] As an example, the candidate cell is an MCG.

[0188] As one embodiment, the second RRC reconfiguration message includes the first set of conditions.

[0189] As an example, the second RRC reconfiguration message includes at least one inference configuration, including the first inference configuration.

[0190] As an example, the at least one inference configuration refers to multiple inference configurations.

[0191] As one example, the inference configuration includes a set of inference parameters.

[0192] As an example, the inference configuration is an inference parameter set.

[0193] As one example, the second RRC reconfiguration message includes additional network-side conditions.

[0194] As an example, the network-side additional conditions depend on at least one inference configuration.

[0195] As an example, the network-side additional conditions include at least one inference configuration.

[0196] As one embodiment, the second RRC reconfiguration message includes a first identifier.

[0197] As one example, the network-side additional conditions include the first identifier.

[0198] As an example, the network-side additional condition is the first identifier.

[0199] As an example, the network-side additional conditions are associated with the first identifier.

[0200] As one embodiment, the first inference configuration includes the first identifier.

[0201] As an example, the first inference configuration is associated with the first identifier.

[0202] As one embodiment, at least one reasoning configuration including the first reasoning configuration is associated with the first identifier.

[0203] As one example, the second RRC reconfiguration message includes at least one report configuration, including a first report configuration.

[0204] As one embodiment, the first inference configuration includes the first report configuration.

[0205] As an example, the first inference configuration and the first report configuration are associated.

[0206] As one example, the network-side additional conditions include the first report configuration.

[0207] As an example, the network-side additional conditions include the first report configuration and the first inference configuration.

[0208] As one embodiment, the first inference configuration includes a first function.

[0209] As an example, the first inference configuration configures the first function.

[0210] As an example, the first inference is configured for the first function.

[0211] As an example, the first inference configuration belongs to the first function.

[0212] As an example, the first function is a function supported by the terminal.

[0213] As one embodiment, the first function is the function of the terminal reporting.

[0214] As an example, the first function is an applicable function.

[0215] As an example, the first function is a type of applicable function.

[0216] As an example, the first function is the function that is indicated to be applicable.

[0217] As an example, the first function is the activated function.

[0218] As an example, when the execution conditions of the first candidate cell are met, the configuration information of the first candidate cell is applied.

[0219] As an example, when the first candidate cell is indicated by a MAC CE, the configuration information of the first candidate cell is applied.

[0220] As one embodiment, applying the configuration information of the first candidate cell includes: performing synchronous reconfiguration on the first candidate cell.

[0221] As an example, the configuration information of the first candidate cell is used to start downlink synchronization to the first candidate cell.

[0222] As one embodiment, the configuration information of the first candidate cell includes: connecting to the first candidate cell.

[0223] As one embodiment, the configuration information of the first candidate cell includes: switching to the first candidate cell.

[0224] As one embodiment, applying the configuration information of the first candidate cell includes: performing random access to the first candidate cell.

[0225] As an example, the configuration information of the first candidate cell is used to enable the timer T304.

[0226] As an example, applying the configuration information of the first candidate cell includes: evaluating whether the inference configuration configured on the terminal is applicable.

[0227] As an example, applying the configuration information of the first candidate cell includes: evaluating whether the inference configuration configured for the first candidate cell by the terminal is applicable.

[0228] As an example, applying the configuration information of the first candidate cell includes applying the at least first candidate configuration.

[0229] As an example, when the configuration information of the first candidate cell is completed, the first RRC reconfiguration completion message is sent.

[0230] As an example, the configuration information of the first candidate cell is completed by stopping the timer T304.

[0231] As an example, the completion of the configuration information of the first candidate cell includes the completion of the synchronization information of the first candidate cell.

[0232] As an example, the configuration information of the first candidate cell is completed by the terminal applying the C-RNTI of the first candidate cell.

[0233] As an example, the configuration information of the first candidate cell is completed to include access to the first candidate cell.

[0234] As an example, the configuration information of the first candidate cell is fully included in the data transmission on the first candidate cell.

[0235] As an example, once the configuration information of the first candidate cell is completed, the first RRC reconfiguration completion message is sent.

[0236] As an example, once the configuration information of the first candidate cell is completed, the first RRC reconfiguration completion message is sent.

[0237] As an example, the first RRC reconfiguration message is an RRCReconfiguration message, and the first RRC reconfiguration completion message is an RRCReconfigurationComplete message.

[0238] As an example, the first RRC reconfiguration message includes an RRCReconfiguration message, and the first RRC reconfiguration completion message includes an RRCReconfigurationComplete message.

[0239] As an example, the first RRC reconfiguration completion message includes a first indication.

[0240] As an example, the first indication indicates that the terminal supports at least the first inference configuration.

[0241] As an example, the first indication indicates that at least the first inference configuration applies.

[0242] As an example, the first instruction indicates that the first inference configuration is applied.

[0243] As an example, the first indication indicates that the first inference configuration is activated.

[0244] As one embodiment, applying the first inference configuration includes: replacing the current inference configuration with the first inference configuration.

[0245] As one embodiment, applying the first inference configuration includes: performing inference according to the first inference configuration.

[0246] As an example, applying the first inference configuration includes: activating the first inference configuration.

[0247] As an example, applying the first inference configuration includes: outputting the result obtained according to the first inference configuration.

[0248] Example 2

[0249] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2. Figure 2 illustrates 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 future 3GPP network architecture; 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 and other nodes 204. Node 203 provides user and control plane protocol termination toward UE 201. Node 203 can 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, 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, wireless unit, remote unit, mobile device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless 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 (Authentication Management Field) / SMF (Session Management Function) 211, other MMEs / AMFs / SMFs 214, an S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that handles signaling between the UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF 213 is connected to the Internet service 230. Internet services 230 include operator-compliant Internet protocol services, which may specifically include the Internet, intranets, IMS (IP Multimedia Subsystem), and packet-switched streaming services.

[0250] As an example, the UE201 corresponds to the terminal described in this application.

[0251] As an example, the terminal in this application includes the UE201.

[0252] As an example, the terminal in this application includes the UE201 and an OTT server.

[0253] As an example, the terminal in this application includes the UE201 and a cloud server.

[0254] As an example, the UE201 is a user equipment (UE).

[0255] As an example, the UE201 is a relay device.

[0256] As an example, the UE201 is an IoT terminal.

[0257] As an example, the UE201 supports AI / ML models.

[0258] As an example, the UE201 supports AI / ML functions.

[0259] As an example, the UE201 supports AI / ML inference.

[0260] As an example, the UE201 supports AI / ML training.

[0261] As an example, the UE201 supports the applicable functions described in this application.

[0262] As an example, the UE201 supports the first inference configuration in this application.

[0263] As an example, node 203 corresponds to the base station in this application.

[0264] As an example, the base station in this application includes the node 203.

[0265] As an example, the base station in this application includes the node 203 and a core network node.

[0266] As an example, the base station in this application includes the node 203 and an OAM node.

[0267] As an example, the base station in this application includes the node 203 and an OTT server.

[0268] As one example, node 203 is a base station device.

[0269] As an example, node 203 is a gNB.

[0270] Example 3

[0271] 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 in three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (Physical Layer) signal processing functions. The L1 layer will be referred to herein as PHY 301. Layer 2 (L2 layer) 305 is above PHY 301 and includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. The PDCP sublayer 304 also provides security through encrypted data packets and provides cross-area mobility support. RLC sublayer 303 provides upper-layer packet segmentation and reassembly, retransmission of lost packets, and packet reordering to compensate for out-of-order reception caused by HARQ (Hybrid Automatic Repeat Request). MAC sublayer 302 provides multiplexing between the logical and transport channels. MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) within a cell. MAC sublayer 302 is also responsible for HARQ operations. RRC (Radio Resource Control) sublayer 306 in Layer 3 (L3) of the control plane 300 is responsible for acquiring radio resources (i.e., radio bearers) and using RRC signaling to configure the lower layers. The radio protocol architecture of user plane 350 includes Layer 1 (L1 layer) and Layer 2 (L2 layer). In user plane 350, the radio protocol architecture 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 is largely the same as the corresponding layers and sublayers in control plane 300. 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.

[0272] As an example, the wireless protocol architecture in Figure 3 is applicable to the terminal described in this application.

[0273] As an example, the wireless protocol architecture in Figure 3 is applicable to the base station described in this application.

[0274] As an example, the first RRC reconfiguration message in this application is generated in RRC306.

[0275] As an example, the first RRC message in this application is generated in RRC306.

[0276] As an example, the first RRC reconfiguration completion message in this application is generated in RRC306.

[0277] As an example, the UECapabilityInformation message in this application is generated in the RRC306.

[0278] As an example, the UECapabilityEnqiry message in this application is generated in the RRC306.

[0279] Example 4

[0280] Embodiment 4 illustrates a schematic diagram of a first communication device and a second communication device according to this application, as shown in Figure 4. Figure 4 is a block diagram of a first communication device 450 and a second communication device 410 communicating with each other in an access network.

[0281] The first communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0282] The second communication device 410 includes a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0283] In the transmission from the second communication device 410 to the first communication device 450, at the second 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 the transmission from the second communication device 410 to the first communication device 450, the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the first communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for retransmitting lost packets and signaling to the first communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for the L1 layer (i.e., the physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 410, and mapping of signal clusters based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), M-Phase Shift Keying (M-PSK), M-QAM). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based and non-codebook-based precoding, and beamforming processing, generating one or more spatial streams. Transmit processor 416 then maps each spatial stream to subcarriers, multiplexes it with a reference signal (e.g., a pilot) in the time and / or frequency domains, and subsequently uses inverse fast Fourier transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol 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 the multi-antenna transmitter processor 471 into an radio frequency stream, which is then provided to different antennas 420.

[0284] In the transmission from the second communication device 410 to the first communication device 450, at the first 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 spatial stream destined for the first communication device 450. Symbols on each spatial stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted by the second communication device 410 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of Layer 2. 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 transmission from the second communication device 410 to the first communication device 450, the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transport and logical channels to recover upper-layer data packets from the core network. The upper-layer data packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 for Layer 3 processing.

[0285] In the transmission from the first communication device 450 to the second communication device 410, at the first 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 second communication device 410 described in the transmission from the second communication device 410 to the first communication device 450, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocation, implementing L2 layer functions for the user plane and control plane. The controller / processor 459 is also responsible for retransmitting lost packets and signaling to the second 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 spatial 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.

[0286] In the transmission from the first communication device 450 to the second communication device 410, the function at the second communication device 410 is similar to the receiving function at the first communication device 450 described in the transmission from the second communication device 410 to the first 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. In the transmission from the first communication device 450 to the second communication device 410, the controller / processor 475 provides multiplexing between the transmission and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover upper-layer data packets from the UE 450. Upper-layer packets from the controller / processor 475 can be provided to the core network.

[0287] As one embodiment, the first 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, and the first communication device 450 at least: receives a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of C-RNTI and T304 of the terminal in the first candidate cell; sends a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable; after sending the first RRC message, as a response to the execution conditions of the first candidate cell being met, applies the configuration information of the first candidate cell; as a response to applying the configuration information of the first candidate cell, sends a first RRC reconfiguration completion message; wherein the configuration information of the first candidate cell includes the first inference configuration; applying the configuration information of the first candidate cell includes applying the first inference configuration.

[0288] As one embodiment, the first communication device 450 includes: receiving a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of C-RNTI and T304 of the terminal in the first candidate cell; sending a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable; after sending the first RRC message, applying the configuration information of the first candidate cell as a response to the execution conditions of the first candidate cell being met; and sending a first RRC reconfiguration completion message as a response to applying the configuration information of the first candidate cell; wherein the configuration information of the first candidate cell includes the first inference configuration; and applying the configuration information of the first candidate cell includes applying the first inference configuration.

[0289] As one embodiment, the second 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 second communication device 410 at least: sends a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of C-RNTI and T304 of the terminal in the first candidate cell; receives a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable; receives a first RRC reconfiguration complete message; wherein, after sending the first RRC message, the sender of the first RRC message applies the configuration information of the first candidate cell as a response to the execution conditions of the first candidate cell being met; as a response to applying the configuration information of the first candidate cell, the sender of the first RRC message sends the first RRC reconfiguration complete message; the configuration information of the first candidate cell includes the first inference configuration; applying the configuration information of the first candidate cell includes applying the first inference configuration.

[0290] As one embodiment, the second communication device 410 includes: a memory storing a computer-readable instruction program, the computer-readable instruction program generating actions when executed by at least one processor, the actions including: sending a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of C-RNTI and T304 of the terminal in the first candidate cell; receiving a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable; receiving a first RRC reconfiguration complete message; wherein, after sending the first RRC message, the sender of the first RRC message applies the configuration information of the first candidate cell as a response to the execution conditions of the first candidate cell being met; as a response to applying the configuration information of the first candidate cell, the sender of the first RRC message sends the first RRC reconfiguration complete message; the configuration information of the first candidate cell includes the first inference configuration; the application of the configuration information of the first candidate cell includes applying the first inference configuration.

[0291] As one embodiment, at least one of the antenna 452, the receiver 454, the receiver processor 456, and the controller / processor 459 is used to receive the first RRC reconfiguration message.

[0292] As an example, at least one of the antenna 420, the transmitter 418, the transmitter processor 416, and the controller / processor 475 is used to transmit a first RRC reconfiguration message.

[0293] As an example, at least one of the antenna 452, the transmitter 454, the transmitter processor 468, and the controller / processor 459 is used to transmit the first RRC message.

[0294] As an example, at least one of the antenna 420, the receiver 418, the receiving processor 470, and the controller / processor 475 is used to receive the first RRC message.

[0295] As an example, at least one of the antenna 452, the transmitter 454, the transmitter processor 468, and the controller / processor 459 is used to send a first RRC reconfiguration complete message.

[0296] As an example, at least one of the antenna 420, the receiver 418, the receiver processor 470, and the controller / processor 475 is used to receive a first RRC reconfiguration complete message.

[0297] As an example, the first communication device 450 corresponds to the terminal in this application.

[0298] As an example, the terminal in this application includes the first communication device 450.

[0299] As an example, the second communication device 410 corresponds to the terminal in this application.

[0300] As an example, the terminal in this application includes the second communication device 410.

[0301] As an example, the first communication device 450 is a user equipment.

[0302] As an example, the first communication device 450 is a base station device.

[0303] As an example, the first communication device 450 is a relay device.

[0304] As one embodiment, the second communication device 410 is a user equipment.

[0305] As one embodiment, the second communication device 410 is a base station device.

[0306] As one embodiment, the second communication device 410 is a relay device.

[0307] Example 5

[0308] Example 5 illustrates a wireless signal transmission flowchart according to an embodiment of this application, as shown in Figure 5. It should be noted that the order in this example does not limit the signal transmission order or the order of implementation in this application.

[0309] For terminal U01, in step S5101, a first RRC reconfiguration message is received; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of C-RNTI and T304 of the terminal in the first candidate cell; in step S5102, a first RRC message is sent; the first RRC message indicates that a first inference configuration is applicable; in step S5103, after sending the first RRC message, as a response to the execution conditions of the first candidate cell being met, the configuration information of the first candidate cell is applied; in step S5104, as a response to the application of the configuration information of the first candidate cell, a first RRC reconfiguration completion message is sent.

[0310] For base station N02, in step S5201, the first RRC reconfiguration message is sent; in step S5202, the first RRC message is received; and in step S5203, the first RRC reconfiguration completion message is received.

[0311] In Example 5, the configuration information of the first candidate cell includes the first inference configuration; applying the configuration information of the first candidate cell includes applying the first inference configuration.

[0312] As an example, the terminal U01 is a UE.

[0313] As an example, the terminal U01 includes a UE.

[0314] As one embodiment, the terminal U01 includes a UE and an OTT (over the top) server.

[0315] As one example, the base station N02 includes a base station.

[0316] As one embodiment, the base station N02 includes a base station and a core network device.

[0317] As one embodiment, the base station N02 includes a base station and an OAM.

[0318] As one embodiment, the base station N02 includes a base station and an OTT server.

[0319] As one embodiment, the terminal U01 includes a UE, and the base station N02 includes a base station.

[0320] As an example, step S5101 is performed after step S5102.

[0321] As an example, step S5101 occurs before step S5102.

[0322] As an example, steps S5101 and S5102 are performed simultaneously.

[0323] As an example, the terminal receives the second RRC reconfiguration message before sending the first RRC message.

[0324] As an example, before receiving the second RRC reconfiguration message, a UECapabilityInformation message is sent, which indicates the UE capabilities of the terminal U01; the first RRC reconfiguration message depends on the UECapabilityInformation message.

[0325] As an example, the first processor sends the UECapabilityInformation message.

[0326] As an example, the UECapabilityInformation message indicates that the terminal U01 supports AI / ML.

[0327] As an example, the UECapabilityInformation message indicates the functions supported by the terminal U01.

[0328] As an example, the terminal U01 supports AI / ML functions.

[0329] As an example, the terminal U01 supports AI / ML functions.

[0330] As an example, the terminal U01 supports functions including a first type of function.

[0331] As an example, the first type of functionality includes supporting data collection.

[0332] As an example, the first type of functionality includes support for inference.

[0333] As an example, the first type of functionality includes inference configuration.

[0334] As an example, the first type of functionality includes a set of inference parameters.

[0335] As an example, the first type of functionality includes CSI report configuration.

[0336] As an example, the terminal U01 supports multiple types of functions; wherein, the transmission of the second RRC reconfiguration message depends on the UECapabilityInformation message indicating that the terminal U01 supports a first type of function; wherein, the first type of function is one of the multiple types of functions.

[0337] As a sub-implementation of the above embodiments, one of the multiple functions is for beam prediction inference.

[0338] As a sub-implementation of the above embodiments, one of the multiple functions is for CSI prediction inference.

[0339] As a sub-implementation of the above embodiments, one of the multiple functions is for CSI compression inference.

[0340] As a sub-implementation of the above embodiments, one of the multiple functions is for beam management inference; wherein, the inference for beam management includes at least one of beam prediction inference, CSI prediction inference, or CSI compression inference.

[0341] As a sub-implementation of the above embodiments, one of the multiple functions is for inference of RLF prediction.

[0342] As a sub-implementation of the above embodiments, one of the multiple functions is for HOF prediction inference.

[0343] As a sub-implementation of the above embodiments, one of the multiple functions is for RRM prediction inference.

[0344] As a sub-implementation of the above embodiments, one of the multiple functions is for the reasoning of event prediction in the measurement report.

[0345] As a sub-implementation of the above embodiments, one of the multiple functions is mobility-related reasoning; the mobility-related reasoning includes at least one of RLF prediction reasoning, HOF prediction reasoning, RRM prediction reasoning, or event prediction reasoning for measurement reports.

[0346] As an example, the UECapabilityInformation message indicates that the terminal U01 supports the reporting of applicable functions.

[0347] As an example, the UECapabilityInformation message indicates that the terminal U01 supports the reporting of applicable functions of the first type of function.

[0348] As an example, the UECapabilityInformation message indicates that the terminal U01 supports the reporting of applicable functions for multiple types of functions.

[0349] As an example, before sending the UECapabilityInformation message, a UECapabilityEnqiry message is received, which requests the UE capabilities of the terminal U01.

[0350] As an example, in response to the fulfillment of the execution conditions of the first candidate cell, the configuration information of the first candidate cell is applied.

[0351] As an example, in response to the application of the configuration information of the first candidate cell, the first RRC reconfiguration complete message is sent.

[0352] As an example, applying the configuration information of the first candidate cell means that the configuration information of the first candidate cell is successfully applied.

[0353] As an example, applying the configuration information of the first candidate cell means that the configuration information of the first candidate cell has been applied.

[0354] As an example, applying the configuration information of the first candidate cell means that the first inference configuration in the configuration information of the first candidate cell is successfully applied.

[0355] As an example, the first RRC reconfiguration completion message includes the inference configuration applicable to the terminal.

[0356] As an example, the inference configuration applicable to the terminal is the inference configuration applicable to the first candidate cell.

[0357] As an example, the inference configuration applicable to the terminal is an inference configuration applicable to both the serving cell and the first candidate cell.

[0358] As one embodiment, the inference configuration applicable to the terminal includes the inference configuration configured in the serving cell but applicable to the first candidate cell.

[0359] As an example, the first RRC reconfiguration completion message includes inference configurations that are not applicable to the terminal.

[0360] As an example, the inapplicable inference configuration for the terminal is the inapplicable inference configuration for the first candidate cell.

[0361] As an example, the inapplicable inference configuration for the terminal is an inference configuration that is applicable to the serving cell but not applicable to the first candidate cell.

[0362] As an example, the first RRC reconfiguration complete message includes an index of the first inference configuration indicating that the first inference configuration is applicable.

[0363] As an example, the first RRC reconfiguration completion message does not include an index indicating that the first inference configuration is applicable, and the first RRC reconfiguration completion message indicates an inapplicable inference configuration.

[0364] As an example, the first RRC reconfiguration complete message includes a third field indicating whether the first inference configuration is applicable.

[0365] As an example, the third domain is configured for the first inference.

[0366] As an example, the presence of the third domain indicates that the first inference configuration is applicable.

[0367] As an example, the third field is set to indicate that the first inference configuration applies.

[0368] As one embodiment, the third field is set to a third value to indicate that the first inference configuration is applicable; the third field is set to a fourth value to indicate that the first inference configuration is not applicable.

[0369] As an example, in response to the application of the configuration information of the first candidate cell, if the first inference configuration is not applicable, the first RRC reconfiguration complete message indicates that the first inference configuration is not applicable.

[0370] As an example, in response to the application of the configuration information of the first candidate cell, if the first inference configuration is applicable, the first RRC reconfiguration complete message indicates that the first inference configuration is applicable.

[0371] Example 6

[0372] Example 6 illustrates a schematic diagram of the first inference configuration according to an embodiment of the present application, which includes K1 associated identifiers, as shown in Figure 6.

[0373] In Example 6, the first inference configuration includes K1 associated identifiers, at least one of the K1 associated identifiers being associated with at least one RS resource of the first candidate cell; K1 is a positive integer.

[0374] As one example, the associated identifier includes a physical identifier.

[0375] As one example, the associated identifier includes a logical identifier.

[0376] As an example, the associated identifier is a logical identifier.

[0377] As an example, the associated identifier is the associated ID.

[0378] As an example, the association identifier is a non-negative integer.

[0379] As an example, the associated identifier is a positive integer.

[0380] As an example, the association identifier is associated with at least one RS resource.

[0381] As an example, the association identifier indicates at least one RS resource.

[0382] As an example, the association identifier indicates that at least one RS resource is used by the first inference configuration.

[0383] As an example, the association identifier includes an index of at least one RS resource.

[0384] As an example, the association identifier is an index of at least one RS resource.

[0385] As an example, the association identifier indicates the RS resources that the first inference configuration can use.

[0386] As an example, the association identifier is related to the purpose of the first inference configuration.

[0387] As an example, different association identifiers indicate the purpose of the first inference configuration.

[0388] As an example, the associated RS resource is related to the purpose of the first inference configuration.

[0389] As an example, the associated identifier indicates the purpose of the first inference configuration by referring to the different RS resources associated with it.

[0390] As one example, the purpose of the first inference configuration includes beam management.

[0391] As one example, the first inference configuration may be used for CSI compression.

[0392] As one example, the purpose of the first inference configuration includes positioning.

[0393] As an example, the association identifier is not based on cell configuration.

[0394] As an example, the associated identifier is not cell-specific.

[0395] As an example, at least one of the K1 associated identifiers is associated with at least one RS resource of a candidate cell other than the first candidate cell.

[0396] As an example, K1 is 1.

[0397] As an example, K1 is 2.

[0398] As an example, K1 is greater than 1.

[0399] As an example, K1 is the default.

[0400] As an example, K1 is fixed.

[0401] As an example, K1 is variable.

[0402] As an example, K1 is selected based on the network side.

[0403] As an example, the configuration information of the first candidate cell includes K2 RS resource configurations.

[0404] As an example, K2 is a positive integer.

[0405] As an example, K2 is greater than 1.

[0406] As an example, K2 is greater than K1.

[0407] As an example, K2 is less than or equal to K1.

[0408] As an example, K2 and K1 are independent.

[0409] As an example, at least one of the K1 association identifiers indicates at least one of the K2 RS resource configurations.

[0410] Example 7

[0411] Example 7 illustrates a schematic diagram of K1 associated identifiers according to an embodiment of this application, as shown in Figure 7.

[0412] In Example 7, at least one of the K1 associated identifiers is associated with at least one RS resource of at least one serving cell.

[0413] As an example, the at least one serving cell is a PCell.

[0414] As an example, the at least one serving cell includes at least PCell.

[0415] As an example, the at least one serving cell includes at least a PSCell.

[0416] As an example, the at least one serving cell supports AI / ML.

[0417] As an example, the at least one serving cell supports AI / ML inference.

[0418] As an example, the at least one serving cell supports at least a first inference configuration.

[0419] As an example, before the first RRC reconfiguration message is received, inference for the first function is performed using the at least one RS resource of the at least one serving cell; after the configuration information of the first candidate cell is applied, inference for the first function is performed using the at least one RS resource of the first candidate cell.

[0420] As an example, the first inference configuration configures the first function.

[0421] As an example, the first inference configuration activates the first function.

[0422] As an example, the first inference configuration updates the first function.

[0423] As an example, the first inference configuration is the first function.

[0424] As an example, the first function is for beam management.

[0425] As an example, the first function is for wireless link failure.

[0426] As an example, the first function is for positioning.

[0427] As an example, the first function is for CSI feedback.

[0428] As an example, the first function is for mobility management.

[0429] As an example, the first function is one of the functions in the first class of functions.

[0430] As an example, the first function is the first type of function.

[0431] As one example, the first function includes training.

[0432] As one example, the first function includes prediction.

[0433] As one example, the first function includes monitoring.

[0434] As one example, the first function includes reasoning.

[0435] As an example, the first function includes at least one inference configuration.

[0436] As one embodiment, the first function includes the first inference configuration.

[0437] As an example, the first function is the first inference configuration.

[0438] As one embodiment, the first function includes the first reporting configuration.

[0439] As one example, the first function includes a CSI reporting configuration.

[0440] As an example, the first function includes at least one function.

[0441] As an example, the first function is a type of function.

[0442] As an example, the first function includes a set of inference parameters.

[0443] As an example, the first function is a set of inference parameters.

[0444] As an example, the first function is associated with a model.

[0445] As an example, the first function is at least one function applicable to the serving cell.

[0446] As an example, the first function is at least one function activated by the serving cell.

[0447] As an example, the first function is at least one function applicable to the first candidate cell.

[0448] As an example, the first function is at least one function activated by the first candidate cell.

[0449] Example 8

[0450] Example 8 illustrates a schematic diagram of applying the first inference configuration according to another embodiment of this application, as shown in Figure 8.

[0451] In Example 8, applying the first inference configuration includes: restoring the first inference configuration; wherein the first inference configuration is suspended.

[0452] As an example, in response to the execution conditions of the first candidate cell being met, the first inference configuration is suspended before the configuration information of the first candidate cell is applied.

[0453] As an example, upon receiving the MAC CE indication to switch to the first candidate cell, the first inference configuration is suspended before applying the configuration information of the first candidate cell.

[0454] As an example, when the cell group to which the first serving cell belongs is detected to have an RLF response, the first inference configuration is suspended.

[0455] As an example, when the cell group to which the first serving cell belongs is detected to receive an RLF response, an RRC connection re-establishment process is executed. During the RRC connection re-establishment process, the first inference configuration is suspended. During the RRC connection re-establishment process, the execution conditions of the first candidate cell are met.

[0456] As an example, when the cell group to which the first serving cell belongs is detected to receive an RLF response, an RRC connection re-establishment process is executed. During the RRC connection re-establishment process, the first inference configuration is suspended. During the RRC connection re-establishment process, the first candidate cell is selected.

[0457] As one embodiment, suspending the first inference configuration includes stopping the execution of inference for the first inference configuration.

[0458] As one example, suspending the first inference configuration includes stopping the monitoring of the first inference configuration.

[0459] As one embodiment, suspending the first inference configuration includes deactivating the first inference configuration.

[0460] As an example, the first inference configuration is activated when it is suspended.

[0461] As an example, the first inference configuration is applicable when the first inference configuration is suspended.

[0462] As an example, the first inference configuration is valid when it is suspended.

[0463] As an example, restoring the first inference configuration means assuming that the first inference configuration is applicable.

[0464] As an example, restoring the first inference configuration means activating the first inference configuration.

[0465] As an example, restoring the first inference configuration means retraining the first inference configuration.

[0466] As an example, restoring the first inference configuration means performing inference using the first inference configuration.

[0467] As an example, restoring the first inference configuration means monitoring the first inference configuration.

[0468] As an example, in response to the completion of the application of the configuration information of the first candidate cell, the first inference configuration is restored.

[0469] As an example, once the configuration information of the first candidate cell has been applied, the first inference configuration is restored.

[0470] As an example, after the first inference configuration is restored, if the first inference configuration is not applicable in the first candidate cell, a first report is sent indicating that the first inference configuration is not applicable.

[0471] As an example, when the first inference configuration is restored, if the first inference configuration is not applicable in the first candidate cell, the terminal does not automatically reactivate the first inference configuration.

[0472] As an example, when the first inference configuration is restored, if the first inference configuration is not applicable in the first candidate cell, the terminal does not automatically release the first inference configuration.

[0473] As an example, restoring the first inference configuration depends on the first inference configuration being applicable in the first candidate cell.

[0474] As an example, in response to the fulfillment of the execution conditions of the first candidate cell, if the first inference configuration is applicable, the first inference configuration is restored.

[0475] As an example, in response to the execution conditions of the first candidate cell being met, if the first inference configuration is applicable to the first candidate cell, the first inference configuration is restored.

[0476] As an example, in response to the execution conditions of the first candidate cell being met, if the configuration information of the first candidate cell includes the first inference configuration, the first inference configuration is restored.

[0477] As an example, the configuration information of the first candidate cell including the first inference configuration refers to the inference configuration in the configuration information of the first candidate cell indicating the applicable configuration in the first candidate cell.

[0478] As an example, the configuration information of the first candidate cell including the first inference configuration means that the configuration information of the first candidate cell indicates whether the inference configuration of the current serving cell is applicable, and the inference configuration of the current serving cell is the first inference configuration.

[0479] As an example, in response to the completion of the application of the configuration information of the first candidate cell, if the first inference configuration is applicable, the first inference configuration is restored.

[0480] As an example, in response to the completion of the application of the configuration information of the first candidate cell, if the first inference configuration is applicable to the first candidate cell, the first inference configuration is restored.

[0481] As an example, in response to the successful restoration of the first inference configuration, the first inference configuration is applied.

[0482] As an example, in response to the failure to recover the first inference configuration, a second report is sent, indicating that the recovery of the first inference configuration has failed.

[0483] As an example, the failure to recover the first inference configuration includes the first inference configuration not being applicable in the first candidate cell.

[0484] As an example, the failure to recover the first inference configuration includes situations where the model associated with the first inference configuration is not applicable.

[0485] As an example, the failure to recover the first inference configuration includes a degradation in the monitoring performance of the first inference configuration exceeding a threshold.

[0486] As an example, the failure to restore the first inference configuration includes the first inference configuration being invalid.

[0487] Example 9

[0488] Example 9 illustrates a schematic diagram of the configuration information of the first candidate cell according to an embodiment of this application, as shown in Figure 9.

[0489] In Example 9, the configuration information of the first candidate cell indicates whether the first inference configuration is activated.

[0490] As an example, applying the first inference configuration includes: activating the first inference configuration if the configuration information of the first candidate cell indicates that the first inference configuration should be activated.

[0491] As an example, the configuration information of the first candidate cell explicitly indicates whether the first inference configuration is activated.

[0492] As an example, the configuration information of the first candidate cell implicitly indicates whether the first inference configuration is activated.

[0493] As an example, the first field in the configuration information of the first candidate cell indicates whether the first inference configuration is activated.

[0494] As an example, the first field in the configuration information of the first candidate cell includes an index indicating the activation of the first inference configuration.

[0495] As one embodiment, the first field in the configuration information of the first candidate cell is set to a first value to indicate that the first inference configuration is activated; the first field in the configuration information of the first candidate cell is not set to indicate that the first inference configuration is not activated.

[0496] As one embodiment, the first field in the configuration information of the first candidate cell is set to indicate that the first inference configuration is activated; the first field in the configuration information of the first candidate cell is not set to indicate that the first inference configuration is not activated.

[0497] As an example, the first field in the configuration information of the first candidate cell is set to a first value to indicate that the first inference configuration is activated; the first field in the configuration information of the first candidate cell is set to a second value to indicate that the first inference configuration is not activated; wherein the first value and the second value are different.

[0498] Example 10

[0499] Example 10 illustrates a structural block diagram of a processing device in a terminal according to an embodiment of the present application; as shown in Figure 10. In Figure 10, the processing device 1000 in the terminal includes a first processor 1001.

[0500] A first processor 1001 receives a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the terminal's C-RNTI and T304 in the first candidate cell;

[0501] The first processor 1001 sends a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable;

[0502] After sending the first RRC message, the first processor 1001 applies the configuration information of the first candidate cell as a response to the execution conditions of the first candidate cell being met.

[0503] The first processor 1001, in response to the application of the configuration information of the first candidate cell, sends a first RRC reconfiguration complete message;

[0504] In Example 10, the configuration information of the first candidate cell includes the first inference configuration; the application of the configuration information of the first candidate cell includes the application of the first inference configuration.

[0505] As one embodiment, the terminal includes: one or more processors and memory;

[0506] The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the terminal to perform the method as described in any one of claims 1-7.

[0507] As an example, the first inference configuration includes K1 associated identifiers, at least one of the K1 associated identifiers being associated with at least one RS resource of the first candidate cell; K1 is a positive integer.

[0508] As an example, at least one of the K1 associated identifiers is associated with at least one RS resource of at least one serving cell.

[0509] As one embodiment, the first processor 1001, the application of the first inference configuration includes: restoring the first inference configuration; wherein the first inference configuration was suspended.

[0510] As an example, the configuration information of the first candidate cell indicates whether the first inference configuration is activated.

[0511] As an example, the first RRC reconfiguration complete message indicates that the first inference configuration is not applicable; wherein, the first inference configuration is not applicable.

[0512] As one embodiment, the first processor 1001 includes a first receiver.

[0513] As one embodiment, the first processor 1001 includes a first transmitter.

[0514] As an example, the first processor 1001 has a training function.

[0515] As an example, the first processor 1001 has inference capabilities.

[0516] As one embodiment, the first receiver includes at least one of the following in Figure 4 of this application: antenna 452, receiver 454, multi-antenna receiver processor 458, receiver processor 456, controller / processor 459, memory 460, or data source 467.

[0517] As one embodiment, the first receiver includes at least an antenna 452 and a receiver 454 as shown in Figure 4 of this application.

[0518] As one embodiment, the first transmitter includes at least one of the following in Figure 4 of this application: antenna 452, transmitter 454, multi-antenna transmitter processor 457, transmitter processor 468, controller / processor 459, memory 460, or data source 467.

[0519] As one embodiment, the first transmitter includes at least an antenna 452 and a transmitter 454 as shown in Figure 4 of this application.

[0520] As one example, the terminal includes a UE.

[0521] As an example, the terminal is a UE.

[0522] Example 11

[0523] Example 11 illustrates a structural block diagram of a processing apparatus in a base station according to an embodiment of the present application; as shown in Figure 11. In Figure 11, the processing apparatus 1100 in the base station includes a second processor 1101.

[0524] The second processor 1101 sends a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the terminal's C-RNTI and T304 in the first candidate cell;

[0525] The second processor 1101 receives a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable;

[0526] The second processor 1101 receives the first RRC reconfiguration complete message;

[0527] Wherein, after sending the first RRC message, the sender of the first RRC message applies the configuration information of the first candidate cell as a response to the execution condition of the first candidate cell being met; as a response to applying the configuration information of the first candidate cell, the sender of the first RRC message sends the first RRC reconfiguration complete message; the configuration information of the first candidate cell includes the first inference configuration; applying the configuration information of the first candidate cell includes applying the first inference configuration.

[0528] As one embodiment, the base station includes: one or more processors and a memory;

[0529] The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the base station to perform the method as described in any one of claims 8-13.

[0530] As an example, the first inference configuration includes K1 associated identifiers, at least one of the K1 associated identifiers being associated with at least one RS resource of the first candidate cell; K1 is a positive integer.

[0531] As an example, at least one of the K1 associated identifiers is associated with at least one RS resource of at least one serving cell.

[0532] As one embodiment, applying the first inference configuration includes: restoring the first inference configuration; wherein the first inference configuration was suspended.

[0533] As an example, the configuration information of the first candidate cell indicates whether the first inference configuration is activated.

[0534] As an example, the first RRC reconfiguration complete message indicates that the first inference configuration is not applicable; wherein, the first inference configuration is not applicable.

[0535] As one embodiment, the second processor 1101 has a training function.

[0536] As one embodiment, the second processor 1101 has a data collection function.

[0537] As an example, the second processor 1101 has AI / ML model deployment capabilities.

[0538] As one embodiment, the second processor 1101 includes a second receiver.

[0539] As one embodiment, the second processor 1101 includes a second transmitter.

[0540] As one embodiment, the second processor 1101 includes a second receiver.

[0541] As one embodiment, the second transmitter includes at least one of the following: antenna 420, transmitter 418, multi-antenna transmitter processor 471, transmitter processor 416, controller / processor 475, or memory 476 as shown in Figure 4 of this application.

[0542] As one embodiment, the second transmitter includes at least an antenna 420 and a transmitter 418 as shown in Figure 4 of this application.

[0543] As one embodiment, the second receiver includes at least one of the following: antenna 420, receiver 418, multi-antenna receiver processor 472, receiver processor 470, controller / processor 475, or memory 476 as shown in Figure 4 of this application.

[0544] As one embodiment, the second receiver includes at least an antenna 420 and a receiver 418 as shown in Figure 4 of this application.

[0545] Example 12

[0546] Example 12 illustrates a schematic diagram of an AI / ML model according to an embodiment of this application, as shown in Figure 12. Figure 12 includes a first module, a second module, a third module, a fourth module, and a fifth module.

[0547] In Example 12, in the AI / ML model shown in Figure 12, the first module sends a first dataset to the second module, the first module sends a second dataset to the third module, the first module sends a third dataset to the fifth module, the fifth module sends a first type of parameter group to the second module, the fifth module sends a second type of parameter group to the third module, the fifth module sends a third type of parameter group to the fourth module, the second module sends a fourth type of parameter group to the fourth module, and the fourth module sends a fifth type of parameter group to the third module.

[0548] As an example, at least one of the first module, the second module, the third module, the fourth module, and the fifth module in an AI / ML model belongs to the terminal described in this application.

[0549] As an example, at least one of the first module, the second module, the third module, the fourth module, and the fifth module in an AI / ML model belongs to the terminal in this application; and at least one of the first module, the second module, the third module, the fourth module, and the fifth module belongs to the base station in this application.

[0550] The above method balances the hardware complexity of the terminal with the transmission latency.

[0551] As an example, the fourth module belongs to the terminal described in this application.

[0552] As an example, the first module is used for data collection; specifically, the first module is responsible for data collection; specifically, the first module has data collection functions.

[0553] As one embodiment, the second module has a training function, which is used for AI / ML model training; specifically, the training function is responsible for AI / ML model training; specifically, the training function has AI / ML model training capabilities; specifically, the training function performs AI / ML model training.

[0554] As one example, the second module performs validation and / or testing; specifically, the second module generates AI / ML model performance metrics.

[0555] As one embodiment, the second module is responsible for data preparation; specifically, the data preparation includes at least one of data pre-processing, cleaning, formatting, or transformation.

[0556] As an example, the second module belongs to the terminal described in this application.

[0557] As an example, the second module performs the training described in this application.

[0558] As an example, the third module is used for inference; specifically, the third module has inference function; specifically, the inference function is responsible for inference.

[0559] As an example, the third module belongs to the terminal described in this application.

[0560] As an example, the third module performs reasoning for the activated applicable functions in this application.

[0561] As an example, the third module performs reasoning for the activated first type of applicable function in this application.

[0562] As one embodiment, the fourth module is used for AI / ML model storage; specifically, the fourth module has AI / ML model storage function; specifically, the fourth module is responsible for storing trained AI / ML models; specifically, the fourth module is responsible for storing trained AI / ML models that can be used to perform inference processing.

[0563] As an example, the fourth module stores the AI / ML model corresponding to the first type of applicable function in this application.

[0564] As an example, the fourth module stores the first type of applicable functions in this application.

[0565] As an example, the storage resources described in this application belong to the fourth module.

[0566] As an example, the storage resources in this application include the storage resources in the fourth module.

[0567] As an example, the fifth module is used for management; specifically, the fifth module is responsible for management; specifically, the fifth module has management functions; specifically, the fifth module manages AI / ML models.

[0568] As an example, the first dataset is training data, and the first dataset is the input of the second module.

[0569] As an example, the first dataset is configured by the network.

[0570] As an example, the first dataset is determined by the terminal.

[0571] As an example, the first dataset includes the terminal's stored data; the stored data may come from the network, the terminal's logs, or other RAN nodes.

[0572] As an example, the second dataset is inference data, which is the input of the third module.

[0573] As an example, the second dataset is configured by the network.

[0574] As an example, the second dataset is determined by the terminal.

[0575] As one embodiment, the second dataset includes the terminal's stored data; the stored data may come from the network, the terminal's logs, or other RAN nodes.

[0576] As an example, the third dataset is monitoring data, which is the input of the fifth module.

[0577] As an example, the third dataset is configured by the network.

[0578] As an example, the third dataset is determined by the terminal.

[0579] As an example, the third dataset is determined by the base station.

[0580] As an example, the third dataset includes the terminal's stored data; the stored data may come from the network, the terminal's logs, or other RAN nodes.

[0581] As an example, the first type of parameter group includes monitoring output.

[0582] As one embodiment, the second type of parameter group includes management instructions; specifically, the second type of parameter group is used for fine-tuning operations of the inference function; specifically, the second type of parameter group includes the identifier of the AI / ML model; specifically, the second type of parameter group is used for selecting, and / or switching, and / or activating / deactivating, and / or reverting the AI / ML model.

[0583] As an example, the third type of parameter group includes AI / ML model transfer requests and / or AI / ML model delivery requests.

[0584] As an example, the fourth parameter group includes trained AI / ML models and / or updated AI / ML models; specifically, the fourth parameter group indicates the identifier of the AI / ML model.

[0585] As an example, the fifth parameter group includes AI / ML model transfer and / or AI / ML model delivery; specifically, the fifth parameter group indicates the identifier of the AI / ML model.

[0586] As an example, the second module sends the first type of output to the fifth module.

[0587] As an example, the first type of output includes monitoring output.

[0588] As an example, the second type of output includes inference output.

[0589] As an example, the second type of output is used by the fifth module to monitor the performance of the AI / ML model.

[0590] As an example, the third module sends the second type of output to the fifth module.

[0591] As an example, Example 12 is only intended to illustrate that this application can be used in AI / ML models. This example does not limit the application of this application to non-AI / ML operations, nor does it limit the application of this application to other types of AI / ML models to achieve effects comparable to the AI / ML model shown in Figure 12.

[0592] Example 13

[0593] Example 13 illustrates a schematic diagram of UE smart function deployment according to one embodiment of this application; as shown in Figure 13. The RAN domain training function 1805 in Figure 13 is optional.

[0594] The UE intelligent function 1804 is deployed in the terminal of this application. The UE intelligent function 1804 includes an inference function 1806. The inference function 1806 uses an AI / ML model (also known as an AI model, or an ML model, or an AI / ML model) for inference. An AI / ML model is usually trained before it is used for AI / ML inference.

[0595] As an example, the UE intelligent function 1804 includes a RAN domain training function 1805, which runs training data through an AI / ML model to obtain a relevant loss and adjusts the parameters of the AI / ML model based on the calculated loss; the training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0596] 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.

[0597] Optionally, the UE intelligent function 1804 also includes a CN domain training function (not shown in Figure 13).

[0598] Optionally, the UE intelligent function 1804 also includes an intelligent deployment function—not shown in Figure 13—for loading AI / ML models and data.

[0599] As an example, the terminal indicates whether it supports training functions (RAN domain or CN domain) through capability reporting. The capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0600] As an example, the AI / ML model and related metadata are loaded by the terminal from a network device or a remote server.

[0601] Optionally, the UE intelligent function 1804 is an MnS (Management Service) producer that provides data to the CN domain MnF (Management Function) 1801, and / or the RAN domain MnF 1802, and / or the cross-domain management system 1803 for management or analysis (as shown by double arrow 1807).

[0602] Optionally, the UE intelligent function 1804 is an MnS consumer that loads data from the CN domain MnF1801, and / or the RAN domain MnF1802, and / or the cross-domain management system 1803 for AI / ML-related management, such as managing data requests, AI / ML model activation, and / or AI / ML model training (as shown by double arrow 1807).

[0603] As an example, the AI / ML model is based on a neural network.

[0604] As an example, the AI / ML model is based on CNN (Conventional Neural Networks).

[0605] As an example, the AI / ML model is based on the Transformer architecture.

[0606] As an example, the terminal in this application includes the training function 1805 of the RAN domain shown in Figure 13.

[0607] As an example, the terminal in this application includes the inference function 1806 shown in Figure 13.

[0608] As an example, the UE201 in Figure 2 of this application includes the inference function 1806 in Figure 13.

[0609] As an example, the UE201 in Figure 2 of this application includes the training function 1805 of the RAN domain in Figure 13.

[0610] As an example, the first communication device 450 in Figure 4 of this application includes the reasoning function 1806 in Figure 13.

[0611] As an example, the first processor 1001 in Figure 10 of this application includes the inference function 1806 in Figure 13.

[0612] As an example, the first processor 1001 in Figure 10 of this application includes the training function 1805 of the RAN domain in Figure 13.

[0613] As an example, the third module in Figure 12 of this application includes the reasoning function 1806 in Figure 13.

[0614] As an example, the second module in Figure 12 of this application includes the training function 1805 of the RAN domain in Figure 13.

[0615] As an example, the terminal in this application includes the MnF1802 shown in Figure 13.

[0616] As an example, the terminal in this application includes the RAN domain MnF1802 shown in Figure 13.

[0617] As an example, node 211 in Figure 2 of this application includes the CN domain MnF1801 / RAN domain MnF1802 / cross-domain management system 1803 in Figure 13.

[0618] 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 devices, wireless sensors, internet cards, IoT terminals, RFID terminals, NB-IoT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base station or system equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, home base stations, relay base stations, gNB (NR Node B), TRP (Transmitter Receiver Point), and other wireless communication equipment.

[0619] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method used in a terminal, characterized in that, include: Receive a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the first node's C-RNTI and T304 in the first candidate cell; Send a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable; After the first RRC message is sent, the configuration information of the first candidate cell is applied as a response to the execution conditions of the first candidate cell being met. In response to the application of the configuration information of the first candidate cell, a first RRC reconfiguration complete message is sent; Wherein, the configuration information of the first candidate cell includes the first inference configuration; the configuration information of applying the first candidate cell includes applying the first inference configuration.

2. The method according to claim 1, characterized in that, The first inference configuration includes K1 associated identifiers, at least one of which is associated with at least one RS resource of the first candidate cell; K1 is a positive integer.

3. The method according to claim 2, characterized in that, At least one of the K1 associated identifiers is associated with at least one RS resource of at least one serving cell.

4. The method according to any one of claims 1-3, characterized in that, The method includes: The application of the first inference configuration includes: restoring the first inference configuration; wherein the first inference configuration is suspended.

5. The method according to any one of claims 1-4, characterized in that, The configuration information of the first candidate cell indicates whether the first inference configuration is activated.

6. The method according to any one of claims 1-5, characterized in that, The first RRC reconfiguration complete message indicates that the first inference configuration is not applicable; wherein, the first inference configuration is not applicable.

7. A terminal, characterized in that, The terminal includes: one or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the terminal to perform the method as described in any one of claims 1-6.

8. A method used in a base station, characterized in that, include: Send a first RRC reconfiguration message; wherein the first RRC reconfiguration message includes configuration information and execution conditions of a first candidate cell; wherein the configuration information of the first candidate cell includes at least one of the first node's C-RNTI and T304 in the first candidate cell; Receive a first RRC message; wherein the first RRC message indicates that a first inference configuration is applicable; Receive the first RRC reconfiguration complete message; Wherein, after sending the first RRC message, the sender of the first RRC message applies the configuration information of the first candidate cell as a response to the execution condition of the first candidate cell being met; as a response to applying the configuration information of the first candidate cell, the sender of the first RRC message sends the first RRC reconfiguration complete message; the configuration information of the first candidate cell includes the first inference configuration; applying the configuration information of the first candidate cell includes applying the first inference configuration.

9. The method according to claim 8, characterized in that, The first inference configuration includes K1 associated identifiers, at least one of which is associated with at least one RS resource of the first candidate cell; K1 is a positive integer.

10. The method of claim 9, wherein, At least one of the K1 associated identifiers is associated with at least one RS resource of at least one serving cell.

11. The method according to any one of claims 8-10, characterized in that, The method includes: The application of the first inference configuration includes: restoring the first inference configuration; wherein the first inference configuration is suspended.

12. The method according to any one of claims 8-11, characterized in that, The configuration information of the first candidate cell indicates whether the first inference configuration is activated.

13. The method according to any one of claims 8-12, characterized in that, The first RRC reconfiguration complete message indicates that the first inference configuration is not applicable; wherein, the first inference configuration is not applicable.

14. A base station, characterized by The base station includes: one or more processors and a memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the base station to perform the method as described in any one of claims 8-13.

Images