Method and device for radio link failure prediction

Abstract

The present application discloses a method and device for radio link failure prediction. The method comprises: a terminal receiving first signaling, the first signaling indicating a first threshold; if a first counter reaches the first threshold, starting a first timer; if the first timer expires, determining a radio link failure; and if the first counter reaches a second threshold, executing radio link failure prediction, the first threshold being different from the second threshold. The method provided by the present application reduces the impact of radio link failure prediction on a terminal.

Description

A method and apparatus for radio link failure prediction

[0001] The present application claims priority from the Chinese patent application No. 2024107082025, filed on May 31, 2024, and entitled "A method and apparatus for radio link failure prediction", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to a transmission method and apparatus in a wireless communication system, and in particular to a method and apparatus for radio link failure (RLF) prediction. BACKGROUND

[0003] For existing services or future services (e.g., XR), when the mobility of a UE (User Equipment) is high or moves between high-density cells, it will cause more unexpected problems such as handover failure (HOF), radio link failure, ping-pong phenomenon, throughput loss, or early / late handover. Considering that the mechanism based on AI (Artificial Intelligence) / ML (Machine Learning) algorithm has the potential to implement the proactive scheme and based on the related progress of RAN1 and RAN3 in AI / ML, the 3GPP (the 3rd Generation Partnership Project) has passed the SI (Study Item) of "Study on AI / ML for mobility in NR (New Radio)", which studies and evaluates the potential benefits and gains of AI / ML assisted mobility for network triggered L3 based handover, including RLF prediction or HOF prediction. SUMMARY

[0004] The inventors have found that, since RLF prediction is performed at the UE (User Equipment) side, RLF prediction improves mobility performance while also bringing additional overhead in terms of power consumption, signaling, etc. to the UE. Therefore, how to reduce the impact of RLF prediction on the UE needs to be further enhanced.

[0005] To solve the above problems, the present application provides a solution. In the description of the above problems, the NR system is taken as an example, and the present application is also applicable to scenarios such as LTE (Long-Term Evolution) or LTE-A (Long-Term Evolution Advanced) or 5G+ or 6G system, and similar technical effects of the NR system are obtained; further, although the present application gives a specific implementation for RLF, the present application can also be used in scenarios such as HOF, and similar technical effects of RLF are obtained. Further, the unified design scheme for different scenarios also helps to reduce hardware complexity and cost. Further, although the original intention of the present application is to target the Uu air interface, the present application can also be used for the PC5 interface, and similar technical effects of the Uu air interface are obtained. Further, although the original intention of the present application is to target the terminal and base station scenario, the present application is also applicable to the V2X (Vehicle-to-Everything) scenario, the communication scenario between the terminal and the relay, and the communication scenario between the relay and the base station, and similar technical effects in the terminal and base station scenario are obtained. Further, although the original intention of the present application is to target the terminal and base station scenario, the present application is also applicable to the IAB (Integrated Access and Backhaul) communication scenario, and similar technical effects in the terminal and base station scenario are obtained. Further, although the original intention of the present application is to target the TN (Terrestrial Network) scenario, the present application is also applicable to the NTN (Non-Terrestrial Network) communication scenario, and similar technical effects in the TN scenario are obtained. In addition, the unified solution for different scenarios also helps to reduce hardware complexity and cost.

[0006] As an embodiment, the explanation of the terminology in the present application refers to the definition of the specification agreement TS36 series of 3GPP.

[0007] As an embodiment, the explanation of the terminology in the present application refers to the definition of the specification agreement TS38 series of 3GPP.

[0008] As an embodiment, the explanation of the terminology in the present application refers to the definition of the specification agreement TS37 series of 3GPP.

[0009] As an embodiment, the explanation of the terminology in the present application refers to the definition of the specification agreement 6G series of 3GPP.

[0010] It should be noted that the embodiments in any node and the features in the embodiments of the present application can be applied to any other node without conflict. The embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0011] The present application discloses a method used in a terminal, comprising:

[0012] receiving first signaling; wherein the first signaling indicates a first threshold; if a first counter reaches the first threshold, starting a first timer; if the first timer expires, determining RLF;

[0013] wherein if the first counter reaches a second threshold, performing RLF prediction; the first threshold and the second threshold are different.

[0014] As an embodiment, the problem to be solved by the present application includes: how to reduce the impact of RLF prediction on UE; the above method solves the above problem by introducing the execution condition of RLF prediction.

[0015] As an embodiment, the problem to be solved by the present application includes: how to trigger RLF prediction; the above method solves the above problem by triggering the execution of RLF prediction when the first counter reaches the second threshold.

[0016] As an embodiment, the problem to be solved by the present application includes: what features does the first counter have; in the above method, if the first counter reaches the first threshold, the first timer is started; if the first timer expires, RLF is determined, thereby solving the above problem.

[0017] As an embodiment, the above method is simple to implement.

[0018] As an embodiment, the above method reduces the standardization work.

[0019] As an embodiment, the above method reduces the impact of RLF prediction on UE.

[0020] As an embodiment, the above method makes the trigger condition more reasonable.

[0021] According to an aspect of the present application, when the first counter reaches the second threshold, a first notification is sent; the first notification is received;

[0022] wherein the first notification triggers the execution of RLF prediction.

[0023] As an embodiment, the problem to be solved by the application includes: how to trigger the execution of RLF prediction when the first counter reaches the second threshold; the above method, in which the terminal sends and receives the first notification, solves the above problem.

[0024] As an embodiment, the above method introduces the first notification inside the terminal, which is simple to implement.

[0025] As an embodiment, the above method is conducive to standardization.

[0026] As an embodiment, the above method is conducive to the separation of RLF detection and RLF prediction.

[0027] According to an aspect of the application, the method comprises:

[0028] In response to the first condition being met, the RLF prediction is aborted;

[0029] The first condition depends on at least one of measurement or prediction.

[0030] As an embodiment, the first condition depends on measurement.

[0031] As an embodiment, the first condition depends on prediction.

[0032] As an embodiment, the first condition depends on measurement and prediction.

[0033] As an embodiment, the problem to be solved by the application includes: how to reduce unnecessary RLF prediction; the above method solves the above problem by aborting the RLF prediction.

[0034] As an embodiment, the problem to be solved by the application includes: how to abort the RLF prediction; the above method solves the above problem by aborting the RLF prediction when the first condition is met.

[0035] As an embodiment, the problem to be solved by the application includes: how to determine the first condition; the above method, in which the first condition depends on measurement or prediction, solves the above problem.

[0036] As an embodiment, the above method allows the RLF prediction to be aborted according to the first condition during the RLF prediction process.

[0037] As an embodiment, the above method further reduces the impact of RLF prediction on the UE.

[0038] As an embodiment, the above method determines the first condition by at least one of measurement or prediction, making the condition for aborting the RLF prediction more reasonable.

[0039] According to an aspect of the present application, the method comprises:

[0040] sending a second notification when the first condition is met; receiving the second notification;

[0041] wherein the second notification triggers the aborting of the RLF prediction.

[0042] As one embodiment, the problem to be solved by the present application includes: how to trigger the aborting of the RLF prediction when the first condition is met; in the above method, the terminal sends and receives a second notification, thereby solving the above problem.

[0043] As one embodiment, the above method introduces a second notification inside the terminal, which is simple to implement.

[0044] As one embodiment, the above method is conducive to standardization.

[0045] As one embodiment, the above method is conducive to the separation of RLF detection and RLF prediction.

[0046] According to an aspect of the present application, the method comprises:

[0047] operating at least one of the first counter or the first timer in response to predicting the RLF.

[0048] As one embodiment, the problem to be solved by the present application includes: how to operate after predicting the RLF; the above method solves the above problem by operating at least one of the first counter or the first timer.

[0049] As one embodiment, the operation of at least one of the first counter or the first timer makes it easier to detect the RLF.

[0050] As one embodiment, the above method avoids detecting the RLF too late by operating at least one of the first counter or the first timer.

[0051] As one embodiment, the operation of at least one of the first counter or the first timer makes it more difficult to detect the RLF.

[0052] As one embodiment, the above method avoids detecting the RLF too early by operating at least one of the first counter or the first timer.

[0053] As one embodiment, the operation of at least one of the first counter or the first timer makes it impossible to detect the RLF through the first counter.

[0054] As one embodiment, the method avoids detecting RLF too late by operating at least one of the first counter or the first timer.

[0055] As one embodiment, the operating at least one of the first counter or the first timer is operating the first counter.

[0056] As one embodiment, the operating at least one of the first counter or the first timer is operating the first timer.

[0057] As one embodiment, the operating at least one of the first counter or the first timer is operating the first counter and the first timer.

[0058] According to one aspect of the present application, the method comprises:

[0059] In response to predicting RLF, initiating RRC connection reestablishment.

[0060] As one embodiment, the problem to be solved by the present application includes how to operate after predicting RLF; the method solves the problem by initiating RRC connection reestablishment.

[0061] As one embodiment, the method avoids detecting RLF too late by initiating RRC connection reestablishment.

[0062] As one embodiment, the method improves mobility robustness.

[0063] As one embodiment, the method improves service continuity.

[0064] As one embodiment, the method shortens interruption delay.

[0065] According to one aspect of the present application, the method comprises:

[0066] As one embodiment, the method avoids detecting RLF too late by operating at least one of the first counter or the first timer.

[0067] As one embodiment, the problem to be solved by the present application includes how to operate after predicting RLF; the method solves the problem by operating at least one of the first counter or the first timer or initiating RRC connection reestablishment.

[0068] As an embodiment, the problem to be solved by the present application includes: how to determine whether to operate at least one of the first counter or the first timer or to initiate RRC connection reestablishment after predicting RLF, the method solves the problem by operating the first counter or initiating RRC connection reestablishment depending on the predicted time of occurrence of RLF.

[0069] As an embodiment, the method adaptively adjusts the UE behavior after predicting RLF, which can avoid detecting RLF too early or too late.

[0070] As an embodiment, the method considers the impact of the predicted time of occurrence of RLF, thereby selecting a more appropriate UE behavior.

[0071] According to an aspect of the present application, the method comprises:

[0072] receiving at least a first reference signal;

[0073] wherein the RLF prediction depends on the at least first reference signal.

[0074] As an embodiment, the problem to be solved by the present application includes: how to perform RLF prediction; in the method, the RLF prediction depends on the at least first reference signal, thereby solving the problem.

[0075] As an embodiment, the method facilitates the combination of RLF prediction and RLF detection.

[0076] As an embodiment, the method reduces standardization work.

[0077] As an embodiment, the method is simple to implement.

[0078] According to an aspect of the present application, the prediction of RLF depends on at least one of the number of predicted in-sync indications or the number of predicted out-of-sync indications within a first time window; the predicted in-sync indications or the predicted out-of-sync indications depend on the at least first reference signal.

[0079] As an embodiment, the problem to be solved by the present application includes: how to determine to predict RLF; in the method, the prediction of RLF depends on at least one of the number of predicted in-sync indications or the number of predicted out-of-sync indications within a first time window, thereby solving the problem.

[0080] As an embodiment, the method improves the accuracy of prediction.

[0081] The present application discloses a method used in a base station, comprising:

[0082] sending a first signaling; wherein the first signaling indicates a first threshold; if the first counter reaches the first threshold, a recipient of the first signaling starts a first timer; if the first timer expires, the recipient of the first signaling determines an RLF;

[0083] wherein if the first counter reaches a second threshold, an RLF prediction is performed; the first threshold and the second threshold are different.

[0084] According to an aspect of the present application, when the first counter reaches the second threshold, the recipient of the first signaling sends a first notification; the recipient of the first signaling receives the first notification; wherein the first notification triggers the performing of the RLF prediction.

[0085] According to an aspect of the present application, in response to the first condition being satisfied, the recipient of the first signaling suspends the RLF prediction; wherein the first condition depends on at least one of a measurement or a prediction.

[0086] According to an aspect of the present application, when the first condition is satisfied, the recipient of the first signaling sends a second notification; the recipient of the first signaling receives the second notification; wherein the second notification triggers the suspending of the RLF prediction.

[0087] According to an aspect of the present application, in response to predicting an RLF, the recipient of the first signaling operates at least one of the first counter or the first timer.

[0088] According to an aspect of the present application, in response to predicting an RLF, the recipient of the first signaling initiates an RRC connection reestablishment.

[0089] According to an aspect of the present application, at least a first reference signal is sent;

[0090] wherein the RLF prediction depends on the at least first reference signal.

[0091] According to an aspect of the present application, the first signaling indicates the second threshold.

[0092] According to an aspect of the present application, the first condition comprises the first counter reaching a third threshold; the first signaling indicates the third threshold.

[0093] The present application discloses a terminal comprising:

[0094] The terminal comprises one or more processors and a memory;

[0095] The memory is coupled to the one or more processors, and the memory is configured to store computer program codes including computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the terminal to perform the method.

[0096] The application discloses a base station, comprising:

[0097] The base station comprises one or more processors and a memory;

[0098] The memory is coupled to the one or more processors, and the memory is configured to store computer program codes including computer instructions, and the one or more processors are configured to invoke the computer instructions to cause the base station to perform the method. BRIEF DESCRIPTION OF DRAWINGS

[0099] Fig. 1 shows a flowchart of a terminal according to one embodiment of the application;

[0100] Fig. 2 shows a schematic diagram of a network architecture according to one embodiment of the application;

[0101] Fig. 3 shows a schematic diagram of an embodiment of a wireless protocol architecture of a user plane and a control plane according to one embodiment of the application;

[0102] Fig. 4 shows a schematic diagram of a first communication device and a second communication device according to one embodiment of the application;

[0103] Fig. 5 shows a flowchart of a wireless signal transmission according to one embodiment of the application;

[0104] Fig. 6 shows a flowchart of a wireless signal transmission according to another embodiment of the application;

[0105] Fig. 7 shows a flowchart of a wireless signal transmission according to yet another embodiment of the application;

[0106] Fig. 8 shows a flowchart of a wireless signal transmission according to still another embodiment of the application;

[0107] Fig. 9 shows a schematic diagram of predicting RLF according to one embodiment of the application;

[0108] Fig. 10 shows a schematic diagram of a first counter according to one embodiment of the application;

[0109] Fig. 11 shows a schematic diagram of a first counter according to another embodiment of the application;

[0110] Fig. 12 shows a structural block diagram of a processing device for use in a terminal according to one embodiment of the application;

[0111] Figure 13 shows a structural block diagram of a processing device in a base station according to an embodiment of the present application.

[0112] Figure 14 shows a flowchart of a first state according to an embodiment of the present application.

[0113] Figure 15 shows a schematic diagram of transmission of a first notification and a second notification according to an embodiment of the present application.

[0114] Figure 16 shows a schematic diagram of an intelligent model according to an embodiment of the present application.

[0115] Figure 17 shows a schematic diagram of intelligent function deployment of a RAN domain according to an embodiment of the present application.

[0116] Figure 18 shows a schematic diagram of intelligent function deployment of a UE according to an embodiment of the present application.

[0117] Figure 19 shows a flowchart based on artificial intelligence or machine learning according to an embodiment of the present application. DETAILED DESCRIPTION

[0118] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily without conflict.

[0119] Embodiment 1

[0120] Embodiment 1 shows a flowchart of a terminal according to an embodiment of the present application, as shown in Figure 1. In Figure 1, each block represents a step, and it is particularly emphasized that the order of the blocks in the figure does not represent the time sequence between the represented steps.

[0121] In embodiment 1, the terminal in the present application receives a first signaling in step 101; wherein the first signaling indicates a first threshold; starts a first timer if a first counter reaches the first threshold; determines an RLF if the first timer expires; wherein performs an RLF prediction if the first counter reaches a second threshold; the first threshold and the second threshold are different.

[0122] As an embodiment, the first signaling indicating the first threshold means that the first signaling explicitly indicates the first threshold.

[0123] As an embodiment, the first signaling indicating the first threshold means that the first signaling implicitly indicates the first threshold.

[0124] As an embodiment, the first signaling indicates the first threshold by configuring the first threshold.

[0125] As an embodiment, the first signaling indicates the first threshold by enabling the first threshold.

[0126] As an embodiment, the first signaling is cell common.

[0127] As an embodiment, the first signaling is UE specific.

[0128] As an embodiment, the first signaling is RRC (Radio Resource Control) signaling.

[0129] As an embodiment, the first signaling comprises RRC signaling and MAC (Medium Access Control) CE (Control Element).

[0130] As an embodiment, the first signaling comprises RRC signaling and DCI (Downlink Control Information).

[0131] As an embodiment, the first signaling comprises one RRC signaling, the one RRC signaling configuring the first threshold.

[0132] As an embodiment, the first signaling comprises one RRC signaling and one MAC CE, the one RRC signaling configuring a plurality of thresholds, the one MAC CE indicating the first threshold from the plurality of thresholds.

[0133] As an embodiment, the first signaling comprises one RRC signaling and one DCI, the one RRC signaling configuring a plurality of thresholds, the one DCI indicating the first threshold from the plurality of thresholds.

[0134] As an embodiment, one beamFailureInstanceMaxCount in the first signaling indicates the first threshold; the first counter is BFI_COUNTER.

[0135] As an embodiment, one n311 in the first signaling indicates the first threshold; the first counter is N311.

[0136] As an embodiment, the first threshold is a constant N310, the first timer is T310, and the first counter is counter N310.

[0137] As one embodiment, one n310 in the first signaling indicates the first threshold; the first timer is T310; and the first counter is N310.

[0138] As one embodiment, the first counter counts a number of first type indications from a physical layer.

[0139] As one embodiment, the first counter counts a number of first type indications from a physical layer for a PCell.

[0140] As one embodiment, the first counter counts a number of first type indications from a physical layer for a PSCell.

[0141] As one embodiment, the first type indication is an in-sync indication.

[0142] As one embodiment, the first counter is N311.

[0143] As one embodiment, the first type indication is an out-of-sync indication.

[0144] As one embodiment, the first counter is N310.

[0145] As one embodiment, the first type indication is a beam failure instance indication.

[0146] As one embodiment, the first counter is BFI_COUNTER.

[0147] As one embodiment, a candidate of the first counter depends on RRC configuration.

[0148] As one embodiment, a candidate of the first counter depends on a UE implementation of the terminal.

[0149] As one embodiment, a candidate of the first counter is determined by the terminal itself.

[0150] As one embodiment, the first counter reaching a second threshold means that the first counter is not less than the second threshold; and the first counter reaching a first threshold means that the first counter is not less than the first threshold.

[0151] As one sub-embodiment of the above embodiment, the not less than is greater than.

[0152] As one sub-embodiment of the above embodiment, the not less than is equal to.

[0153] As a sub-example of the above embodiment, the not less than is equal to or greater than.

[0154] As an example, the first threshold is less than the second threshold.

[0155] As a sub-example of the above embodiment, the first counter reaches the first of the first threshold and the second threshold.

[0156] As a sub-example of the above embodiment, the "start the first timer if the first counter reaches the first threshold" is not affected by the RLF prediction.

[0157] As a sub-example of the above embodiment, the above method reduces the impact on existing protocols.

[0158] As a sub-example of the above embodiment, the first timer is started as soon as the first counter reaches the first threshold; wherein the T300, T301, T304, T311, T316 and T319 are not running when the first counter reaches the first threshold.

[0159] As a sub-example of the above embodiment, the first timer is running when the first counter reaches the second threshold.

[0160] As a sub-example of the above embodiment, the RLF prediction is performed if the first timer is running and the first counter reaches the second threshold.

[0161] As a sub-example of the above embodiment, the "start the first timer if the first counter reaches the first threshold" is affected by whether the terminal supports the RLF prediction.

[0162] As a sub-example of the above embodiment, the above method avoids the first timer triggering RLF too early due to expiration.

[0163] As a sub-example of the above embodiment, the first timer is started if the terminal does not support the RLF prediction when the first counter reaches the first threshold; the first timer is not started if the terminal supports the RLF prediction.

[0164] As a sub-example of the above embodiment, the "start the first timer if the first counter reaches the first threshold" is affected by whether the terminal is enabled for the RLF prediction.

[0165] As a sub-example of the above embodiment, the above method avoids the first timer triggering RLF too early due to expiration.

[0166] As a sub-example of the above embodiment, the first timer is started if the RLF prediction is not enabled when the first counter reaches the first threshold; the first timer is not started if the RLF prediction is enabled.

[0167] As a sub-example of the above embodiment, the first timer is not running when the first counter reaches the second threshold.

[0168] As an example, the first threshold is greater than the second threshold.

[0169] As a sub-example of the above embodiment, the first counter reaches the second threshold of the second threshold and the first threshold.

[0170] As a sub-example of the above embodiment, the "start the first timer if the first counter reaches the first threshold" is not affected by the performing RLF prediction.

[0171] As a sub-example of the above embodiment, the first timer is started as long as the first counter reaches the first threshold; wherein the first counter reaches the first threshold, T300, T301, T304, T311, T316 and T319 are not running.

[0172] As a sub-example of the above embodiment, the method reduces the impact on the existing protocol.

[0173] As a sub-example of the above embodiment, the "start the first timer if the first counter reaches the first threshold" is affected by the performing RLF prediction.

[0174] As a sub-example of the above embodiment, the first timer is started if the RLF prediction is not enabled when the first counter reaches the first threshold; the first timer is not started if the RLF prediction is enabled.

[0175] As a sub-example of the above embodiment, the method avoids the first timer expired triggering RLF during RLF prediction.

[0176] As an example, the second threshold is indicated by RRC signaling.

[0177] As an example, the second threshold is indicated by the relevant information of the predicted RLF.

[0178] As an example, the second threshold is determined by the terminal.

[0179] As one embodiment, the second threshold is default.

[0180] As one embodiment, the second threshold is dedicated for the RLF prediction.

[0181] As one embodiment, the second threshold is dedicated for an intelligent model used for the RLF prediction.

[0182] As one embodiment, the second threshold is equal to a product of a maximum value of the first counter and a first ratio.

[0183] As one embodiment, the second threshold is equal to a product of the first threshold and a first ratio.

[0184] As one embodiment, the first ratio is configurable.

[0185] As one embodiment, the first ratio is greater than 0 and less than 1.

[0186] As one embodiment, the first ratio is greater than 1.

[0187] As one embodiment, the first ratio is fixed.

[0188] As one embodiment, the first ratio is indicated by RRC signaling.

[0189] As one embodiment, the first ratio is indicated by related information of the predicted RLF.

[0190] As one embodiment, the first ratio is determined by the terminal.

[0191] As one embodiment, the first ratio is default.

[0192] As one embodiment, the first offset is dedicated for the RLF prediction.

[0193] As one embodiment, the first offset is dedicated for an intelligent model used for the RLF prediction.

[0194] As one embodiment, the first offset is equal to a difference between the first threshold and a first offset.

[0195] As one embodiment, the first offset is equal to a difference between a maximum value of the first counter and a first offset.

[0196] As one embodiment, the first offset is configurable.

[0197] As one embodiment, the first offset is fixed.

[0198] As an embodiment, the first offset is indicated by RRC signaling.

[0199] As an embodiment, the first offset is indicated by the related information of the predicted RLF.

[0200] As an embodiment, the first offset is determined by the terminal.

[0201] As an embodiment, the first offset is default.

[0202] As an embodiment, the first offset is dedicated for the RLF prediction.

[0203] As an embodiment, the first offset is dedicated for the intelligent model for the RLF prediction.

[0204] As an embodiment, the determining RLF means detecting RLF.

[0205] As an embodiment, the determining RLF means detecting MCG RLF.

[0206] As an embodiment, the determining RLF means considering MCG detecting RLF.

[0207] As an embodiment, the first counter is for PCell (Primary Cell) or MCG (Master Cell Group); the RLF prediction is performed for PCell or MCG.

[0208] As an embodiment, the determining RLF means considering SCG detecting RLF.

[0209] As an embodiment, the determining RLF means detecting SCG RLF.

[0210] As an embodiment, the first counter is for PSCell (Primary SCG Cell) or SCG (Secondary Cell Group); the RLF prediction is performed for PSCell or SCG.

[0211] As an embodiment, when the first counter reaches the second threshold, how the terminal determines the performing RLF prediction depends on UE implementation.

[0212] As an embodiment, when the first counter reaches the second threshold, how the terminal notifies the intelligent module 1501 in embodiment 14 depends on UE implementation.

[0213] As one embodiment, the RLF prediction is performed by the terminal based on a UE implementation.

[0214] As one embodiment, the RLF prediction is performed by the terminal based on a UE implementation.

[0215] As one embodiment, the RLF prediction is performed by the terminal based on a network configuration.

[0216] As one embodiment, the RLF prediction is performed by the terminal based on a UE implementation and a network configuration.

[0217] As one embodiment, the RLF prediction is based on recent measurements.

[0218] As one embodiment, the RLF prediction is based on previous measurements.

[0219] As one embodiment, the RLF prediction is based on information stored by the terminal.

[0220] As one embodiment, the RLF prediction is based on information provided by the network.

[0221] As one embodiment, the RLF prediction includes inference.

[0222] As one embodiment, the RLF prediction includes training.

[0223] As one embodiment, the RLF prediction includes training and inference.

[0224] As one embodiment, the RLF prediction includes predicting link quality.

[0225] As one embodiment, the RLF prediction includes predicting synchronization indication.

[0226] As one embodiment, the RLF prediction includes predicting out-of-sync indication.

[0227] As one embodiment, the RLF prediction includes predicting whether a timer has expired.

[0228] As one embodiment, the RLF prediction refers to predicting whether an RLF will occur.

[0229] As one embodiment, the RLF prediction refers to predicting a probability of an RLF occurring.

[0230] As one embodiment, the RLF prediction refers to predicting a time of an RLF occurring.

[0231] As one embodiment, the RLF prediction refers to predicting a time interval in which an RLF will not occur.

[0232] As one embodiment, the RLF prediction refers to predicting a probability of occurrence of RLF over time.

[0233] As one embodiment, for the terminal, AS security is activated, and at least one of SRB2 or at least one DRB or at least one multicast MRB is configured; the performing RLF prediction is for MCG.

[0234] As one embodiment, for the terminal, T316 is not configured, or SCG transmission is suspended, or SCG is deactivated; the performing RLF prediction is for MCG.

[0235] As one embodiment, for the terminal, MCG transmission is suspended; the performing RLF prediction is for SCG.

[0236] As one embodiment, during running of the first timer, T312 is not started.

[0237] As one embodiment, when the first timer is running, T312 is started.

[0238] As one embodiment, when the first timer is running, a measurement report is sent, and along with the measurement report, T312 is started.

[0239] As one embodiment, the T312 and the first timer in the present application are for the same cell or the same cell group.

[0240] Embodiment 2

[0241] Embodiment 2 illustrates a diagram of a network architecture according to one embodiment of the application, as shown in FIG. 2. FIG. 2 illustrates a 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 the network architecture 200 is a 5G+ network architecture, or the network architecture 200 is a 6G network architecture, or the network architecture 200 is a network architecture of future continued evolution of 3GPP; the network architecture 200 can be referred to as a 5GS (5G System) / EPS (Evolved Packet System), or the network architecture 200 can be referred to as a 6GS (6G System); the network architecture 200 includes a UE (User Equipment) 201, a RAN (Radio Access Network) 202, a core network 210, a HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and at least one of an Internet service 230. The network architecture 200 can be interconnected 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 appreciate that the various concepts presented throughout this application are amenable to use with networked or other cellular networked environments providing circuit-switched services. The RAN includes a node 203 and other nodes 204. The node 203 provides user and control plane protocol terminations toward the UE 201. The node 203 can be connected to the other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. The node 203 can also be referred to as a base station, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a TRP (Transmit Receive Point), or some other suitable terminology. The core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC; the node 203 provides an access point to the core network 210 for the UE 201.Examples of UE 201 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptop computers, 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, aerial vehicles, narrowband internet of things devices, machine type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional device. Those skilled in the art will also The node 203 is connected by an S1 / NG interface to the core network 210. The core network 210 includes a MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MME / AMF / SMF 214, a S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that processes the signaling between UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocal) packets are transferred through the S-GW / UPF 212, which itself is connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation as well as other functions. The P-GW / UPF 213 is connected to the Internet services 230. The Internet services 230 include operator corresponding Internet protocol services, which can specifically include the Internet, an intranet, an IMS (IP Multimedia Subsystem), and a packet switched streaming service.

[0242] As one embodiment, the UE 201 corresponds to the terminal in the present application.

[0243] As one embodiment, the UE 201 is a user equipment (UE).

[0244] As one embodiment, the UE 201 is a Base Station (BS).

[0245] As one embodiment, the UE 201 is a Relay device.

[0246] As one embodiment, the UE 201 is a Gateway device.

[0247] As one embodiment, the node 203 corresponds to the base station in the present application.

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

[0249] As one embodiment, the node 203 is a Relay device.

[0250] As one embodiment, the node 203 is a Gateway device.

[0251] As one embodiment, the user equipment supports intelligent functions.

[0252] As one embodiment, the user equipment supports intelligent modules.

[0253] As one embodiment, the user equipment supports intelligent models.

[0254] As one embodiment, the user equipment supports intelligent models for the RLF prediction.

[0255] As one embodiment, the user equipment supports RLF prediction.

[0256] As one embodiment, the user equipment supports 3GPP Release 19.

[0257] As one embodiment, the user equipment supports 5G.

[0258] As one embodiment, the user equipment supports 6G.

[0259] As one embodiment, the user equipment supports Radio Link Monitoring (RLM).

[0260] As one embodiment, the user equipment supports handover.

[0261] As one embodiment, the user equipment supports CHO.

[0262] As one embodiment, the user equipment supports cell selection.

[0263] As an embodiment, the user equipment supports transmission of a non-terrestrial network (NTN).

[0264] As an embodiment, the user equipment supports transmission of a terrestrial network (TN).

[0265] As an embodiment, the user equipment supports dual connection (DC) transmission.

[0266] As an embodiment, the user equipment comprises a device supporting low latency and high reliability transmission.

[0267] As an embodiment, the user equipment can be a mobile terminal, which can be a mobile phone or an iPad or a computer or a watch or a ring; the user equipment can also be a wearable device, which can be a watch or a ring or shoes or a hat or clothing or glasses, etc.; the user equipment can also be a flying device; the user equipment can also be a vehicle terminal; the user equipment can also be a ship terminal; the user equipment can also be an Internet of Things terminal; the user equipment can also be an industrial Internet of Things terminal; the user equipment can also be a test device; the user equipment can also be a signaling tester; the user equipment can also be an IAB (Integrated Access and Backhaul)-MT.

[0268] As an embodiment, the base station equipment supports an intelligent model.

[0269] As an embodiment, the base station equipment supports an intelligent function.

[0270] As an embodiment, the base station equipment supports selection of an intelligent model.

[0271] As an embodiment, the base station equipment supports configuration of an intelligent model.

[0272] As an embodiment, the base station equipment supports configuration of RLF prediction.

[0273] As an embodiment, the base station equipment supports transmission of a non-terrestrial network (NTN).

[0274] As an embodiment, the base station equipment supports transmission of a terrestrial network (TN).

[0275] As an embodiment, the base station equipment comprises a base transceiver station (BTS).

[0276] As an embodiment, the base station device comprises a Node B (NB); the Node B can be a gNB or an eNB or an ng-eNB or an en-gNB; the base station device can comprise a CU (Centralized Unit); the base station device can further comprise a DU (Distributed Unit); the base station device can further comprise a TRP (Transmitter Receiver Point).

[0277] As an embodiment, the base station device can be a Macro Cellular base station or a Micro Cell base station or a Pico Cell base station or a Femto Cell; the base station device can further be a flight platform device or a satellite device; the base station device can further be a test device or a signaling tester; the base station device can further be a gateway device; the base station device can further be an IAB device; the IAB device comprises at least one of an IAB-node or an IAB-donor or an IAB-donor-CU or an IAB-donor-DU or an IAB-DU or an IAB-MT.

[0278] As an embodiment, the relay device can comprise a relay; the relay can be a L3 relay or a L2 relay; the relay device can further comprise a router; the relay device can further comprise a switch; the relay device can further comprise a gateway device; the relay device can further comprise at least part of a user equipment; the relay device can further comprise at least part of a base station device.

[0279] Embodiment 3

[0280] Figure 3 is a diagram illustrating an embodiment of a radio protocol architecture for the user plane 350 and the control plane 300. Figure 3 shows three layers for the radio protocol architecture for the control plane 300: Layer 1, Layer 2, and Layer 3. Layer 1 (LI layer) is the lowest layer and implements various PHY (Physical layer) signal processing functions. The LI layer will be referred to as the PHY 301 herein. Layer 2 (L2 layer) 305 is above the PHY 301 and includes a MAC (Medium Access Control) sublayer 302, a 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 functions, such as ciphering / de-ciphering, and header compression / de-compression. The RLC sublayer 303 provides segmentation and reassembly of upper layer data packets, retransmission of lost data packets, and reordering of data packets to compensate for out-of-order reception due to HARQ. The MAC sublayer 302 provides multiplexing between logical and transport channels. The MAC sublayer 302 is also responsible for allocating the various radio resources (e.g., resource blocks) in one cell. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in Layer 3 (L3 layer) in the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and using RRC signaling to configure the lower layers. The radio protocol architecture for the user plane 350 includes Layer 1 (LI layer) and Layer 2 (L2 layer), which are substantially the same as the corresponding layers and sublayers in the control plane 300 for the physical layer 351, the PDCP sublayer 354 in the L2 layer 355, the RLC sublayer 353 in the L2 layer 355, and the MAC sublayer 352 in the L2 layer 355, but the PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead. Also included in the L2 layer 355 in the user plane 350 is the SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between QoS flows and data radio bearers (DRBs) to support diverse service

[0281] As one embodiment, the wireless protocol architecture in FIG. 3 is applicable to the terminal in the present application.

[0282] As one embodiment, the wireless protocol architecture in FIG. 3 is applicable to the base station in the present application.

[0283] As one embodiment, the first signaling in the present application is generated at the RRC 306.

[0284] As one embodiment, the first signaling in the present application is generated at the MAC 302 or the MAC 352.

[0285] As one embodiment, the first signaling in the present application is generated at the PHY 301 or the PHY 351.

[0286] As one embodiment, the at least first reference signal in the present application is generated at the PHY 301 or the PHY 351.

[0287] As one embodiment, the first notification is sent at a first designated protocol layer of the terminal.

[0288] As one embodiment, the second notification is sent at a first designated protocol layer of the terminal.

[0289] As one embodiment, the third notification is received at a first designated protocol layer of the terminal.

[0290] As one embodiment, the fourth notification is received at a first designated protocol layer of the terminal.

[0291] As one embodiment, the first designated protocol layer is one of the protocol layers shown in FIG. 3.

[0292] As one embodiment, the first designated protocol layer is the RRC 306.

[0293] As one embodiment, the first notification is received at a second designated protocol layer of the terminal.

[0294] As one embodiment, the second notification is received at a second designated protocol layer of the terminal.

[0295] As one embodiment, the third notification is sent at a second designated protocol layer of the terminal.

[0296] As one embodiment, the fourth notification is sent at a second designated protocol layer of the terminal.

[0297] As one embodiment, the second designated protocol layer is one of the protocol layers shown in FIG. 3.

[0298] As an embodiment, the second designated protocol layer is a protocol layer other than the protocol layers shown in Figure 3 (not included in Figure 3).

[0299] Embodiment 4

[0300] Embodiment 4 shows a schematic diagram of a first communication device and a second communication device according to the present 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.

[0301] The first communication device 450 comprises a controller / processor 459, a memory 460, a data source 467, a transmit processor 468, a receive processor 456, a multi-antenna transmit processor 457, a multi-antenna receive processor 458, a transmitter / receiver 454 and antennas 452.

[0302] The second communication device 410 comprises a controller / processor 475, a memory 476, a receive processor 470, a transmit processor 416, a multi-antenna receive processor 472, a multi-antenna transmit processor 471, a transmitter / receiver 418 and antennas 420.

[0303] In the transmission from the second communication device 410 to the first communication device 450, at the second communication device 410, upper layer packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements functionality of the L2 layer. In the transmission from the second communication device 410 to the first communication device 450, the controller / processor 475 provides header compression, ciphering, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocations for the first communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for retransmission of lost packets, and signaling to the first communication device 450. The transmit processor 416 and the multiple antenna transmit processor 471 implement various signal processing functions for the LI layer (i.e., physical layer). The transmit processor 416 implements coding and interleaving to facilitate forward error correction (FEC) at the second communication device 410, and mapping of coded bits to modulation symbols based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), M-quadrature amplitude modulation (M-QAM)). The multiple antenna transmit processor 471 performs digital spatial pre-coding of the coded and modulated symbols, including codebook-based and non-codebook-based pre-coding, and beamforming processing, to generate one or more spatial streams. The transmit processor 416 then maps to each spatial stream to the subcarriers, multiplexes the stream with reference signals (e.g., pilot) in the time and / or frequency domain, and then performs an inverse fast Fourier transform (IFFT) to generate a time-domain multicarrier symbol stream for the physical channel. The multiple antenna transmit processor 471 then performs transmit analog pre-coding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multiple antenna transmit processor 471 into a radio frequency stream, and then provides the radio frequency stream to the corresponding antenna 420.

[0304] In transmissions 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 respective antenna 452. Each receiver 454 recovers information modulated onto an RF carrier and provides the recovered information at baseband as a stream of symbols to a receive processor 456. The receive processor 456 and a multiple access receiver processor 458 implement various signal processing functions of the Ll layer. The multiple access receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multiple access symbol streams from the receivers 454. The receive processor 456 converts the baseband multiple access symbol streams from the time-domain to the frequency domain using a Fast Fourier Transform (FFT). In the frequency domain, the physical layer data signals and the reference signals are demultiplexed from the received symbol streams, with the reference signals to be used for channel estimation and the data signals to be recovered after multiple access detection in the multiple access receiver processor 458 for any spatial streams destined for the first communication device 450. The symbols on each spatial stream are demodulated and recovered by the receive processor 456 and used to generate soft decisions. The receive processor 456 then decodes and de-interleaves the soft decisions to recover the upper layer data and control signals transmitted by the second communication device 410 on the physical channel. The upper layer data and control signals are then provided to a controller / processor 459. The controller / processor 459 implements the functions of the L2 layer. The controller / processor 459 can be associated with a memory 460 that stores program codes and data. The memory 460 can be referred to as a computer-readable medium. In transmissions from the second communication device 410 to the first communication device 450, the controller / processor 459 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer data packets from the core network. The upper layer data packets are then provided to all protocol layers above the L2 layer. Various control signals can also be provided to the L3 for L3 processing.

[0305] 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 a controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmit function 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, ciphering, packet segmentation and reordering, and multiplexing between logical and transport channels based on radio resource allocations, implements L2 layer functionality for the user plane and control plane. The controller / processor 459 is also responsible for error detection, retransmission of lost packets, and signaling to the second communication device 410. A transmit processor 468 performs modulation mapping, channel coding processing, and a multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, and then the transmit processor 468 modulates the resulting spatial streams into multi-carrier / single-carrier symbol streams, which are then provided to different antennas 452 via transmitters 454 after analog precoding / beamforming operations in the multi-antenna transmit processor 457. Each transmitter 454 first converts the baseband symbol stream provided by the multi-antenna transmit processor 457 into a radio frequency signal, and then provides the radio frequency signal to the antenna 452.

[0306] In the transmission from the first communication device 450 to the second communication device 410, the functions at the second communication device 410 are similar to the receive functions 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 a radio frequency signal through its respective antenna 420, converts the received radio frequency signal into a baseband signal, and provides the baseband signal to a multi-antenna receive processor 472 and a receive processor 470. The receive processor 470 and the multi-antenna receive processor 472 collectively implement the functionality of the L1 layer. A controller / processor 475 implements the functionality of the L2 layer. The controller / processor 475 can be associated with a memory 476 that stores program codes and data. The memory 476 can be referred to as a computer readable medium. In the transmission from the first communication device 450 to the second communication device 410, the controller / processor 475 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover upper layer data packets from the UE 450. Upper layer data packets from the controller / processor 475 can be provided to a core network.

[0307] As one embodiment, the first communication device 450 comprises: at least one processor and at least one memory including a computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the first communication device 450 at least to receive first signaling; wherein the first signaling indicates a first threshold; start a first timer if a first counter reaches the first threshold; determine RLF if the first timer expires; wherein RLF prediction is performed if the first counter reaches a second threshold; the first threshold and the second threshold being different.

[0308] As one embodiment, the first communication device 450 comprises: a memory storing a computer readable program of instructions which, when executed by at least one processor, causes actions comprising: receiving first signaling; wherein the first signaling indicates a first threshold; starting a first timer if a first counter reaches the first threshold; determining RLF if the first timer expires; wherein RLF prediction is performed if the first counter reaches a second threshold; the first threshold and the second threshold being different.

[0309] As one embodiment, the second communication device 410 comprises: at least one processor and at least one memory including a computer program code; the at least one memory and the computer program code configured to, with the at least one processor, cause the second communication device 410 at least to send first signaling; wherein the first signaling indicates a first threshold; a receiver of the first signaling starts a first timer if a first counter reaches the first threshold; the receiver of the first signaling determines RLF if the first timer expires; wherein RLF prediction is performed if the first counter reaches a second threshold; the first threshold and the second threshold being different.

[0310] As one embodiment, the second communication device 410 comprises: a memory storing a computer readable program of instructions which, when executed by at least one processor, causes actions comprising: sending first signaling; wherein the first signaling indicates a first threshold; a receiver of the first signaling starts a first timer if a first counter reaches the first threshold; the receiver of the first signaling determines RLF if the first timer expires; wherein RLF prediction is performed if the first counter reaches a second threshold; the first threshold and the second threshold being different.

[0311] As an embodiment, at least one of the antenna 452, the receiver 454, the receive processor 456, the controller / processor 459 is configured to receive the first signaling.

[0312] As an embodiment, at least one of the antenna 420, the transmitter 418, the transmit processor 416, the controller / processor 475 is configured to transmit the first signaling.

[0313] As an embodiment, at least one of the antenna 452, the transmitter 454, the transmit processor 468, the controller / processor 459 is configured to transmit at least the first reference signal.

[0314] As an embodiment, at least one of the antenna 420, the receiver 418, the receive processor 470, the controller / processor 475 is configured to receive at least the first reference signal.

[0315] As an embodiment, the first communication device 450 corresponds to the terminal in the present application.

[0316] As an embodiment, the second communication device 410 corresponds to the base station in the present application.

[0317] As an embodiment, the first communication device 450 is a user equipment.

[0318] As an embodiment, the first communication device 450 is a base station device.

[0319] As an embodiment, the first communication device 450 is a relay device.

[0320] As an embodiment, the first communication device 450 performs the RLF prediction.

[0321] As an embodiment, optionally, the first communication device 450 comprises the intelligent module 1501 in the attached Figure 14 (not included in Figure 4).

[0322] As an embodiment, optionally, the first communication device 450 comprises the third module in the attached Figure 15 (not included in Figure 4).

[0323] As an embodiment, optionally, the first communication device 450 comprises the inference function 1806 in the attached Figure 17 (not included in Figure 4).

[0324] As an embodiment, the second communication device 410 is a user equipment.

[0325] As an embodiment, the second communication device 410 is a base station device.

[0326] As one embodiment, the second communication device 410 is a relay device.

[0327] As one embodiment, optionally, the second communication device 410 assists in performing the RLF prediction.

[0328] As one embodiment, optionally, the second communication device 410 includes an inference function (not included in FIG. 4) of FIG. 16.

[0329] As one embodiment, optionally, the second communication device 410 includes a RAN domain training function 1805 (not included in FIG. 4) of FIG. 17.

[0330] Embodiment 5

[0331] Embodiment 5 illustrates a wireless signal transmission flowchart according to one embodiment of the present application, as shown in FIG. 5. It is particularly noted that the sequence in this example does not limit the sequence of signal transmission and implementation in the present application.

[0332] For the terminal U01, in step S5101, a first signaling is received; wherein the first signaling indicates a first threshold; in step S5102, at least a first reference signal is received; in step S5103, it is determined whether the first counter reaches a second threshold; if the first counter reaches the second threshold, step S5106 is executed, otherwise, step S5106 is not executed; in step S5104, a first notification is sent when the first counter reaches the second threshold; in step S5105, the first notification is received; wherein the first notification triggers the execution of the RLF prediction; in step S5106, the RLF prediction is executed; in step S5107, it is determined whether a first condition is met; in response to the first condition being met, step S5110 is executed, otherwise, step S5110 is not executed; wherein the first condition depends on at least one of measurement or prediction; in step S5108, a second notification is sent when the first condition is met; in step S5109, the second notification is received; wherein the second notification triggers the aborting of the RLF prediction; in step S5110, the RLF prediction is aborted; in step S5111, it is determined whether the first counter reaches the first threshold; if the first counter reaches the first threshold, step S5112 is executed, otherwise, step S5112 is not executed; in step S5112, a first timer RLF is started; in step S5113, it is determined whether the first timer expires; if the first timer expires, step S5114 is executed, otherwise, step S5114 is not executed; in step S5114, RLF is determined.

[0333] For the base station N02, in step S5201, a first signaling is transmitted; in step S5202, at least a first reference signal is transmitted.

[0334] In embodiment 5, the first threshold and the second threshold are different.

[0335] As one embodiment, the base station N02 is a base station to which a serving cell of the terminal U01 belongs.

[0336] As one embodiment, the base station N02 is a base station to which a PCell of the terminal U01 belongs.

[0337] As one embodiment, the base station N02 is a base station to which a PSCell of the terminal U01 belongs.

[0338] As one embodiment, the base station N02 is a Master Node (MN).

[0339] As one embodiment, the base station N02 is a Secondary Node (SN).

[0340] As one embodiment, the terminal U01 and the base station N02 are connected through a wireless connection.

[0341] As one embodiment, the terminal U01 and the base station N02 are connected through a wired connection.

[0342] As one embodiment, the terminal U01 and the base station N02 are connected through a Uu interface.

[0343] As one embodiment, the terminal U01 and the base station N02 are connected through an IAB interface.

[0344] As one embodiment, the terminal U01 and the base station N02 are connected through a PC5 interface.

[0345] As one embodiment, the first notification is an indication.

[0346] As one embodiment, the first notification is a notification.

[0347] As one embodiment, the first notification is a cross-layer indication.

[0348] As one embodiment, the first notification is a cross-entity indication.

[0349] As one embodiment, the first notification is within the terminal U01.

[0350] As one embodiment, the first notification is sent and received within the terminal U01.

[0351] As one embodiment, the first notification activates a smart model for the RLF prediction.

[0352] As one embodiment, the first notification enables a smart model for the RLF prediction.

[0353] As one embodiment, the first notification indicates parameters of a smart model for the RLF prediction.

[0354] As one embodiment, the parameters of a smart model for the RLF prediction comprise an identification of a smart model for the RLF prediction.

[0355] As one embodiment, the parameters of a smart model for the RLF prediction comprise a type of a smart model for the RLF prediction.

[0356] As one embodiment, the parameters of a smart model for the RLF prediction comprise a current value of the first counter.

[0357] As one embodiment, the first notification triggering the performing the RLF prediction means that the first notification requests the performing the RLF prediction.

[0358] As one embodiment, the first notification triggering the performing the RLF prediction means that the first notification indicates the performing the RLF prediction.

[0359] As one embodiment, the first notification triggering the performing the RLF prediction means that the RLF prediction is performed when the first notification is received.

[0360] As one embodiment, how the terminal U01 determines to abort the RLF prediction when the first condition is fulfilled depends on the UE implementation.

[0361] As one embodiment, how the terminal U01 informs the smart module 1501 in embodiment 14 when the first condition is fulfilled depends on the UE implementation.

[0362] As one embodiment, the aborting is stopping.

[0363] As one embodiment, the aborting is terminating.

[0364] As one embodiment, the aborting is suspending.

[0365] As one embodiment, the aborting is suspending.

[0366] As an embodiment, the first condition depends on the first counter.

[0367] As an embodiment, the first condition depending on the first counter means that the first condition comprises the first counter not reaching the second threshold.

[0368] As an embodiment, the first condition depending on the first counter means that the first condition comprises the first counter reaching a third threshold.

[0369] As an embodiment, the third threshold is a positive integer; the third threshold is greater than the second threshold.

[0370] As an embodiment, the first signaling indicates the third threshold.

[0371] As an embodiment, the terminal determines the third threshold by itself.

[0372] As an embodiment, the predicted information related to the RLF indicates the third threshold.

[0373] As an embodiment, the first condition depending on a prediction means that the first condition depends on an intelligent model for the RLF prediction.

[0374] As an embodiment, the first condition depending on an intelligent model for the RLF prediction means that the first condition comprises the intelligent model for the RLF prediction being updated.

[0375] As an embodiment, the first condition depending on an intelligent model for the RLF prediction means that the first condition comprises the intelligent model for the RLF prediction being reconfigured.

[0376] As an embodiment, the first condition depending on an intelligent model for the RLF prediction means that the first condition comprises the intelligent model for the RLF prediction being deactivated.

[0377] As an embodiment, the first condition depending on a measurement means that the first condition comprises considering that the MCG is detected with the RLF.

[0378] As an embodiment, the first condition depending on a measurement means that the first condition comprises the first timer being stopped.

[0379] As an embodiment, the first condition depending on a measurement means that the first condition comprises the first timer expiring.

[0380] As one embodiment, the first condition dependent measurement means that the first condition comprises T312 being stopped.

[0381] As one embodiment, the first condition dependent measurement means that the first condition comprises initiating a handover procedure.

[0382] As one embodiment, the first condition dependent measurement means that the first condition comprises handover failure.

[0383] As one embodiment, the first condition dependent measurement means that the first condition comprises T304 being stopped.

[0384] As one embodiment, the second notification is an indication.

[0385] As one embodiment, the second notification is a notification.

[0386] As one embodiment, the second notification is a cross-layer indication.

[0387] As one embodiment, the second notification is a cross-entity indication.

[0388] As one embodiment, the second notification is within the terminal U01.

[0389] As one embodiment, the second notification is transmitted and received within the terminal U01.

[0390] As one embodiment, the second notification deactivates an intelligent model for the RLF prediction.

[0391] As one embodiment, the second notification disables an intelligent model for the RLF prediction.

[0392] As one embodiment, the second notification indicates an identity of an intelligent model for the RLF prediction.

[0393] As one embodiment, the second notification indicates a type of an intelligent model for the RLF prediction.

[0394] As one embodiment, the second notification triggering the aborting the RLF prediction means that the second notification requests aborting the performing RLF prediction.

[0395] As one embodiment, the second notification triggering the aborting the RLF prediction means that the second notification indicates aborting the performing RLF prediction.

[0396] As one embodiment, the second notification triggers the suspending of the RLF prediction refers to that the RLF prediction is suspended when the second notification is received.

[0397] As one embodiment, the suspending of the RLF prediction is accompanied by resetting an intelligent model of the RLF prediction.

[0398] As one embodiment, the suspending of the RLF prediction is accompanied by clearing at least part of information of the RLF prediction.

[0399] As one embodiment, the suspending of the RLF prediction is accompanied by clearing at least part of cache of the RLF prediction.

[0400] As one embodiment, the above method avoids impact on subsequent RLF prediction.

[0401] As one embodiment, the transmitter of the at least first reference signal is a maintaining base station of a cell or a cell group to which the first timer is directed.

[0402] As one embodiment, the receiving the at least first reference signal comprises receiving the first reference signal at each available reception occasion of each reference signal in the at least first reference signal.

[0403] As one embodiment, the receiving the at least first reference signal comprises receiving the first reference signal at at least one available reception occasion of each reference signal in the at least first reference signal.

[0404] As one embodiment, an available reception occasion of one reference signal is a time-frequency resource configured to the one reference signal.

[0405] As one embodiment, an available reception occasion of one reference signal is a time-frequency resource configured to the one reference signal and non-overlapping with a specified time-frequency resource.

[0406] As one sub-embodiment of the above embodiment, the specified time-frequency resource comprises an active measurement gap.

[0407] As one sub-embodiment of the above embodiment, a transmission on the specified time-frequency resource has a higher priority than the one reference signal.

[0408] As one embodiment, the transmitter of the at least first reference signal is a cell to which the RLF prediction is directed.

[0409] As one embodiment, the at least first reference signal is a physical layer signal.

[0410] As one embodiment, the at least first reference signal is a Reference Signal.

[0411] As one embodiment, any of the at least first reference signal is used for RLF prediction.

[0412] As one embodiment, any of the at least first reference signal is used for RLM (Radio Link Monitoring).

[0413] As one embodiment, any of the at least first reference signal is used for both RLM and RLF prediction.

[0414] As one embodiment, the at least first reference signal is Downlink (DL).

[0415] As one embodiment, the at least first reference signal is Sidelink (SL).

[0416] As one embodiment, the at least first reference signal is periodic.

[0417] As one embodiment, the at least first reference signal is semi-persistent.

[0418] As one embodiment, the at least first reference signal comprises a Synchronization Signal.

[0419] As one embodiment, each of the at least first reference signal is one SSB (Synchronization Signal Block, or SS / PBCH).

[0420] As one embodiment, the at least first reference signal is a Synchronization Signal.

[0421] As one embodiment, each of the at least first reference signal is one CSI-RS (Channel State Information Reference Signal).

[0422] As one embodiment, the at least first reference signal is indicated by RRC signaling.

[0423] As one embodiment, the at least first reference signal is determined by the terminal U01.

[0424] As one embodiment, the at least first reference signal is the first reference signal.

[0425] As one embodiment, the at least first reference signal is a plurality of reference signals; the plurality of reference signals includes at least the first reference signal.

[0426] As one embodiment, the at least first reference signal is no more than M1 reference signals; the M1 is a positive integer.

[0427] As one embodiment, the M1 depends on L_max in TS 38.213.

[0428] As one embodiment, the M1 is N_RLM in TS 38.213.

[0429] As one embodiment, the M1 is 2 or 4 or 8.

[0430] As one embodiment, the M1 is no more than 8.

[0431] As one embodiment, the M1 is no more than 16.

[0432] As one embodiment, the RLF prediction includes predicting a link quality for the at least first reference signal.

[0433] As one embodiment, the RLF prediction includes predicting a synchronization indication; the synchronization indication depends on the at least first reference signal.

[0434] As one embodiment, the RLF prediction includes predicting a number of synchronization indications; the synchronization indication depends on the at least first reference signal.

[0435] As one embodiment, the RLF prediction includes predicting an out-of-sync indication; the out-of-sync indication depends on the at least first reference signal.

[0436] As one embodiment, the RLF prediction includes predicting a number of out-of-sync indications; the out-of-sync indication depends on the at least first reference signal.

[0437] As one embodiment, the RLF prediction depends on the at least first reference signal.

[0438] As one embodiment, the RLF prediction depends on a measurement result for the at least first reference signal.

[0439] As one embodiment, an input to an intelligent model for the RLF prediction includes a measurement result for the at least first reference signal.

[0440] As one embodiment, an inference of an intelligent model for the RLF prediction depends on a measurement result for the at least first reference signal.

[0441] As one embodiment, the measurement result for the at least first reference signal comprises at least one measurement value for the at least first reference signal.

[0442] As one embodiment, the measurement result for the at least first reference signal comprises at least one measurement value for each of the at least first reference signal.

[0443] As one embodiment, the at least one measurement value is only one measurement value.

[0444] As one embodiment, the at least one measurement value is a plurality of measurement values.

[0445] As one embodiment, the plurality of measurement values are obtained at different times.

[0446] As one embodiment, the plurality of measurement values are obtained at the same time.

[0447] As one embodiment, the measurement value is RSRP (Reference Signal Receiving Power).

[0448] As one embodiment, the measurement value is RSRQ (Reference Signal Receiving Power).

[0449] As one embodiment, the measurement value is SINR (Signal to Interference plus Noise Ratio).

[0450] As one embodiment, the step S5103 is before the step S5111; the first threshold is greater than the second threshold.

[0451] As one sub-embodiment of the above embodiment, the RLF prediction is not performed regardless of the first counter reaching the first threshold.

[0452] As one sub-embodiment of the above embodiment, the first timer is not running regardless of the first condition being met.

[0453] As one embodiment, the step S5103 is after the step S5111; the first threshold is less than the second threshold.

[0454] As one sub-embodiment of the above embodiment, the first timer is running when the first counter reaches the second threshold.

[0455] As a sub-example of the above example, the first timer is running when the first condition is met.

[0456] As an example, the dashed box F5.1 is optional.

[0457] As an example, the dashed box F5.1 is not present.

[0458] As an example, the dashed box F5.1 is present.

[0459] As an example, the step S5107 is optional.

[0460] As an example, the step S5107 is not present.

[0461] As an example, the step S5107 is present.

[0462] As an example, the dashed box F5.2 is optional.

[0463] As an example, the dashed box F5.2 depends on the step S5107.

[0464] As an example, the dashed box F5.2 is not present and the step S5107 is present.

[0465] As an example, the dashed box F5.2 is present and the step S5107 is present.

[0466] As an example, optionally, the terminal U01 sends first UE capability information (not shown in the figure 5); wherein the first UE capability information indicates that the terminal U01 supports RLF prediction.

[0467] As an example, the “performing RLF prediction if the first counter reaches a second threshold” depends on the first UE capability information indicating that the terminal U01 supports RLF prediction.

[0468] As an example, performing RLF prediction if the first counter reaches a second threshold is conditional on the first UE capability information indicating that the terminal U01 supports RLF prediction.

[0469] As an example, the first UE capability information comprises one RRC message; the one RRC message indicates that the terminal U01 supports RLF prediction.

[0470] As an embodiment, the first UE capability information comprises one RRC message and one MAC CE; the one RRC message indicates a plurality of UE capabilities; and the one MAC CE indicates, from the plurality of UE capabilities, that the terminal U01 supports the RLF prediction.

[0471] As an embodiment, the one RRC message is a UECapabilityInformation message.

[0472] As an embodiment, the one RRC message is a UEAssistanceInformation message.

[0473] As an embodiment, the first UE capability information indicates a parameter of at least one intelligent model supported by the terminal U01; optionally, the parameter can be an identification of the intelligent model, can be a type of the intelligent model, can be a function of the intelligent model, etc.

[0474] As a sub-embodiment of the above-mentioned embodiment, one of the at least one intelligent model supported by the terminal U01 is an intelligent model for the RLF prediction.

[0475] As an embodiment, the first UE capability information indicates that the terminal U01 supports the RLF prediction.

[0476] As an embodiment, the first UE capability information indicates, from the RLF prediction and the HOF prediction, the RLF prediction.

[0477] As an embodiment, the first UE capability information indicates, from the RLF prediction and the HOF prediction, both the RLF prediction and the HOF prediction.

[0478] As an embodiment, optionally, the terminal U01 receives a second message (not shown in the FIG. 5); wherein the second message enables the RLF prediction.

[0479] As an embodiment, the “performing the RLF prediction if the first counter reaches a second threshold” relies on the second message enabling the RLF prediction.

[0480] As an embodiment, the RLF prediction is performed if the first counter reaches a second threshold, on the premise that the second message enables the RLF prediction.

[0481] As an embodiment, the second message indicates a parameter of at least one intelligent model enabled; optionally, the parameter can be an identification of the intelligent model, can be a type of the intelligent model, can be a function of the intelligent model, etc.

[0482] As a sub-example of the above example, the second message indicates that one of the at least one enabled intelligent model is an intelligent model for the RLF prediction.

[0483] As an example, the second message comprises an RRC message; the RRC message enables the RLF prediction.

[0484] As an example, the second message comprises a MAC CE; the MAC CE enables the RLF prediction.

[0485] As an example, the second message comprises a DCI; the DCI enables the RLF prediction.

[0486] As an example, the enabling comprises enable.

[0487] As an example, the enabling comprises activate.

[0488] As an example, the enabling comprises enable.

[0489] As an example, the enabling comprises enable.

[0490] As an example, the enabling comprises trigger.

[0491] Example 6

[0492] Example 6 illustrates a wireless signal transmission flow chart according to another example of the present application, as shown in FIG. 6. It is particularly noted that the sequence in this example does not limit the sequence of signal transmission and the sequence of implementation in the present application.

[0493] For the terminal U01, in step S6101, an RLF is predicted; in step S6102, at least one of the first counter or the first timer is operated in response to the prediction of the RLF.

[0494] As an example, the operation of at least one of the first counter or the first timer is: operation of the first counter.

[0495] As an example, the operation of at least one of the first counter or the first timer is: operation of the first timer.

[0496] As an example, the operation of at least one of the first counter or the first timer is: operation of the first counter and the first timer.

[0497] As one embodiment, operating at least one of the first counter or the first timer is contingent upon predicting RLF.

[0498] As one embodiment, operating at least one of the first counter or the first timer is contingent upon predicting RLF.

[0499] As one embodiment, operating at least one of the first counter or the first timer is contingent upon predicting RLF.

[0500] As one embodiment, operating at least one of the first counter or the first timer is contingent upon predicting RLF.

[0501] As one embodiment, the terminal U01 predicts RLF based on UE implementation.

[0502] As one embodiment, the terminal U01 predicts RLF based on protocol specification.

[0503] As one embodiment, the terminal U01 predicts RLF based on intelligent model.

[0504] As one embodiment, the terminal U01 predicts RLF based on intelligent model for RLF prediction.

[0505] As one embodiment, predicting RLF means predicting N310 consecutive out-of-sync indications; N310 is a positive integer.

[0506] As one embodiment, predicting RLF means predicting that the number of consecutive out-of-sync indications will reach N310; N310 is a positive integer.

[0507] As one embodiment, predicting RLF means predicting that the number of consecutive out-of-sync indications within the first time window will reach N310; N310 is a positive integer.

[0508] As one embodiment, predicting RLF means predicting that the first timer will expire.

[0509] As one embodiment, predicting RLF means predicting that T312 will expire.

[0510] As one embodiment, predicting RLF means predicting that any one of the first timer or T312 will expire.

[0511] As one embodiment, predicting RLF means predicting that RLF will occur.

[0512] As one embodiment, the predicting the RLF refers to a first indicator of predicting the RLF reaching a first threshold.

[0513] As one embodiment, the first indicator includes a BLER (Block Error Rate).

[0514] As one embodiment, the first indicator includes a RSRP.

[0515] As one embodiment, the first indicator includes a RSRQ.

[0516] As one embodiment, the first indicator includes a probability.

[0517] As one embodiment, the first indicator includes a confidence.

[0518] As one embodiment, the response to predicting the RLF refers to when the predicting the RLF is predicted.

[0519] As one embodiment, the response to predicting the RLF refers to once the predicting the RLF is predicted.

[0520] As one embodiment, the response to predicting the RLF refers to at least after the predicting the RLF is predicted.

[0521] As one embodiment, the operating the first timer refers to stopping the first timer.

[0522] As one embodiment, the operating the first timer refers to changing a value of the first timer.

[0523] As one sub-embodiment of the above embodiment, the changing is increasing.

[0524] As one sub-embodiment of the above embodiment, the changing is decreasing.

[0525] As one sub-embodiment of the above embodiment, the changing the value of the first timer is according to RRC configuration.

[0526] As one sub-embodiment of the above embodiment, the changing the value of the first timer is according to information related to the predicted RLF.

[0527] As one sub-embodiment of the above embodiment, the changing the value of the first timer means changing a current value of the first timer.

[0528] As one sub-embodiment of the above embodiment, the changing the value of the first timer means changing a value at next start of the first timer.

[0529] As one embodiment, the operation of the first counter is to reset the first counter.

[0530] As one embodiment, the operation of the first counter is to decrease the first counter.

[0531] As one embodiment, the operation of the first counter is to increase the first counter.

[0532] Embodiment 7

[0533] Embodiment 7 illustrates a flow chart of wireless signal transmission according to yet another embodiment of the present application, as shown in FIG. 7. It is particularly noted that the sequence in this example does not limit the sequence of signal transmission and implementation in the present application.

[0534] For terminal U01, in step S7101, RLF is predicted; in step S7102, RRC connection reestablishment is initiated as a response to the prediction of RLF.

[0535] As one embodiment, the prediction of RLF and the response to the prediction of RLF refer to Embodiment 6, which is not repeated here.

[0536] As one embodiment, RRC connection reestablishment is initiated as soon as RLF is predicted.

[0537] As one embodiment, RRC connection reestablishment is initiated if RLF is predicted.

[0538] As one embodiment, RRC connection reestablishment is initiated at least when RLF is predicted.

[0539] As one embodiment, RRC connection reestablishment is initiated as a response to the prediction of RLF regardless of the time of occurrence of the predicted RLF.

[0540] As one embodiment, RLF is determined after the prediction of RLF and before the initiation of RRC connection reestablishment.

[0541] As one embodiment, RLF is not determined after the prediction of RLF and before the initiation of RRC connection reestablishment.

[0542] As one embodiment, no valid event triggering the determination of RLF is detected within the time interval from the prediction of RLF to the initiation of RRC connection reestablishment.

[0543] As one embodiment, the valid event triggering the determination of RLF includes expiration of the first timer.

[0544] As one embodiment, the legitimate event triggering the determination of the RLF comprises expiration of T312.

[0545] As one embodiment, the legitimate event triggering the determination of the RLF comprises receiving a Random Access problem indication from the MCG MAC and none of T300, T301, T304, T311, T316 and T319 are running and a Small Data Transmission (SDT) procedure is not ongoing.

[0546] As one embodiment, the legitimate event triggering the determination of the RLF comprises reaching a RLC maximum number of retransmissions and a SDT procedure is not ongoing.

[0547] As one embodiment, the legitimate event triggering the determination of the RLF comprises receiving a consecutive uplink Listen Before Talk (LBT) failure indication from the MCG MAC.

[0548] As one embodiment, the legitimate event triggering the determination of the RLF comprises expiration of T304 of the MCG.

[0549] Embodiment 8

[0550] Embodiment 8 illustrates a flowchart of wireless signal transmission according to yet another embodiment of the present application, as shown in FIG. 8. It is particularly noted that the sequence in this example does not limit the sequence of signal transmission and the sequence of implementation in the present application.

[0551] For the terminal U01, in step S8101, an RLF is predicted; in step S8102, it is determined whether the occurrence time of the predicted RLF is earlier than a first time; if the occurrence time of the predicted RLF is earlier than the first time, step S8103(a) is executed; otherwise, step S8103(b) is executed; in step S8103(a), an RRC connection reestablishment is initiated; in step S8103(b), at least one of the first counter or the first timer is operated.

[0552] In Embodiment 8, in response to the prediction of the RLF, at least one of the first counter or the first timer is operated or the RRC connection reestablishment is initiated depends on the occurrence time of the predicted RLF.

[0553] As one embodiment, the prediction of the RLF, the operation of at least one of the first counter or the first timer in response to the prediction of the RLF, and the initiation of the RRC connection reestablishment refer to Embodiment 6, which will not be repeated here.

[0554] As one embodiment, the first time is an expiry time of the first timer.

[0555] As one embodiment, the first time is an expiry time of T312.

[0556] As one embodiment, the first timer is the smaller of the first timer and T312; both the first timer and the T312 are running; the first timer is T310.

[0557] As one embodiment, the first time is a time after a specified time interval from a time when the RLF is predicted.

[0558] As one embodiment, the specified time interval is configurable.

[0559] As one embodiment, the specified time interval is indicated by an RRC message.

[0560] As one embodiment, the specified time interval is indicated by the predicted RLF related information.

[0561] As one embodiment, in response to the prediction of the RLF, operating the second statistic or initiating RRC connection reestablishment.

[0562] As one embodiment, if the predicted time of the RLF is later than the first time, operating at least one of the first counter or the first timer; if the predicted time of the RLF is earlier than the first time, initiating RRC connection reestablishment.

[0563] As one embodiment, if the predicted time of the RLF is later than the first time, operating at least one of the first counter or the first timer along with the time when the RLF is predicted.

[0564] As one embodiment, if the predicted time of the RLF is earlier than the first time, initiating RRC connection reestablishment along with the time when the RLF is predicted.

[0565] As one embodiment, if the predicted time of the RLF is earlier than the first time, initiating RRC connection reestablishment along with the predicted time of the RLF.

[0566] As one embodiment, if the predicted time of the RLF is the first time, operating at least one of the first counter or the first timer.

[0567] As one embodiment, if the predicted time of occurrence of the RLF is the first time, initiating RRC connection reestablishment.

[0568] Embodiment 9

[0569] Embodiment 9 illustrates a diagram of predicting RLF according to one embodiment of the present application, as shown in FIG. 9. In the FIG. 9, the horizontal axis represents time, t9.1 is the start time of the first time window, t9.2 is the end time of the first time window, the solid single arrow represents a predicted in-sync indication, the dashed single arrow represents a predicted out-of-sync indication, and every other predicted indication period corresponds to a prediction evaluation occasion.

[0570] In Embodiment 9, the predicting RLF relies on at least one of a number of predicted in-sync indications or a number of predicted out-of-sync indications within the first time window; the predicted in-sync indication or the predicted out-of-sync indication relies on the at least first reference signal.

[0571] As one embodiment, the predicted out-of-sync indication relies on a predicted link quality for the at least first reference signal.

[0572] As one embodiment, the predicted link quality is RSRP.

[0573] As one embodiment, the predicted link quality is RSRQ.

[0574] As one embodiment, the predicted link quality is BLER.

[0575] As one embodiment, the predicted link quality is filtered by L1 or L3.

[0576] As one embodiment, the predicted link quality is unfiltered.

[0577] As one embodiment, the predicted link quality is a new quantity.

[0578] As one embodiment, if the predicted link quality for each of the at least first reference signal is worse than a first predicted out-of-sync threshold within a prediction out-of-sync evaluation period, an out-of-sync indication is predicted.

[0579] As one embodiment, the first predicted out-of-sync threshold is Qout configured by rlmInSyncOutOfSyncThreshold.

[0580] As one embodiment, the first predicted out-of-sync threshold is not Qout configured by rlmInSyncOutOfSyncThreshold.

[0581] As one embodiment, the predicted in-sync indication depends on a predicted link quality for the at least first reference signal.

[0582] As one embodiment, the predicted in-sync indication is predicted if a predicted link quality for at least one of the at least first reference signal is better than a first predicted in-sync threshold within a predicted in-sync evaluation period.

[0583] As one embodiment, the first predicted in-sync threshold is Qin configured by rlmInSyncOutOfSyncThreshold.

[0584] As one embodiment, the first predicted in-sync threshold is not Qin configured by rlmInSyncOutOfSyncThreshold.

[0585] As one embodiment, the predicted evaluation occasion can not exist in practice for clarity.

[0586] As one embodiment, at each predicted evaluation occasion, there is either a predicted in-sync indication or a predicted out-of-sync indication.

[0587] As one embodiment, at a predicted evaluation occasion, there is neither a predicted in-sync indication nor a predicted out-of-sync indication.

[0588] As one embodiment, the length of the predicted in-sync evaluation period is equal to the length of the predicted out-of-sync evaluation period.

[0589] As one embodiment, the length of the predicted in-sync evaluation period is not equal to the length of the predicted out-of-sync evaluation period.

[0590] As one embodiment, the length of the predicted in-sync evaluation period is the length of the in-sync evaluation period.

[0591] As one embodiment, the length of the predicted in-sync evaluation period is not the length of the in-sync evaluation period.

[0592] As one embodiment, the length of the predicted indication period is equal to the length of the indication period.

[0593] As one embodiment, the length of the in-sync evaluation period refers to TEvaluate_in_SSB of TS 38.133.

[0594] As one embodiment, the length of the out-of-sync evaluation period refers to TEvaluate_out_SSB of TS 38.133.

[0595] As an embodiment, the length of the in-sync evaluation period and the length of the out-of-sync evaluation period are equal.

[0596] As an embodiment, the length of the in-sync evaluation period and the length of the out-of-sync evaluation period are not equal.

[0597] As an embodiment, the method above can maintain the continuity of the predicted in-sync indication and / or the predicted out-of-sync indication based on the in-sync indication and / or the out-of-sync indication.

[0598] As an embodiment, the length of the prediction indication period and the length of the indication period are not equal.

[0599] As an embodiment, the method above makes the prediction more flexible independently of the in-sync indication and / or the out-of-sync indication.

[0600] As an embodiment, the embodiment above does not limit the position of the evaluation occasion in the prediction indication period.

[0601] As an embodiment, the prediction evaluation occasion is only for the sake of clarity, which is evaluated every other prediction indication period to determine whether there is a predicted out-of-sync indication or a predicted in-sync indication, and is not specifically limited in actual application.

[0602] As an embodiment, the prediction of the RLF depends on the number of the predicted in-sync indications in a first time window.

[0603] As an embodiment, the absence of at least P2 consecutive predicted in-sync indications in the first time window triggers the prediction of the RLF; the P2 is a positive integer.

[0604] As an embodiment, the method above is simple to implement.

[0605] As an embodiment, the P2 is the difference between N311 and R2; the R2 is the number of consecutive in-sync indications received by the time of the prediction of the RLF.

[0606] As an embodiment, the P2 is less than N311.

[0607] As an embodiment, the method above uses a smaller P2 than N311 to reduce the probability of predicting the RLF.

[0608] As an embodiment, the P2 is greater than N311.

[0609] As an embodiment, the method above uses a larger P2 than N311 to provide a fault tolerance rate of the prediction.

[0610] As an embodiment, the P2 is N321.

[0611] As one embodiment, the ratio of the predicted in-sync indications within the first time window is no more than a threshold triggers the predicting RLF.

[0612] As one sub-embodiment of the above embodiment, the no more than is less than.

[0613] As one sub-embodiment of the above embodiment, the no more than is less than or equal to.

[0614] As one sub-embodiment of the above embodiment, the threshold is configurable.

[0615] As one sub-embodiment of the above embodiment, the threshold is default.

[0616] As one sub-embodiment of the above embodiment, the ratio of the predicted in-sync indications within the first time window refers to the ratio of the number of the predicted in-sync indications within the first time window to the number of predicted indication periods within the first time window.

[0617] As one sub-embodiment of the above embodiment, the ratio of the predicted in-sync indications within the first time window refers to the ratio of the number of the predicted in-sync indications within the first time window to the number of the predicted out-of-sync indications within the first time window.

[0618] As one embodiment, the predicting RLF depends on the number of the predicted out-of-sync indications within a first time window.

[0619] As one embodiment, the presence of at least P1 consecutive predicted out-of-sync indications within the first time window triggers the predicting RLF; the P1 is a positive integer.

[0620] As one embodiment, the P1 is less than N310.

[0621] As one embodiment, the use of a smaller P1 than N310 in the above method facilitates earlier prediction of RLF.

[0622] As one embodiment, the P1 is greater than N310.

[0623] As one embodiment, the use of a larger P1 than N310 in the above method avoids the impact of prediction error.

[0624] As one embodiment, the P1 is N310.

[0625] As one embodiment, the above method is simple to implement.

[0626] As one embodiment, the P1 is N310 minus R1; the R1 is a number of consecutive out-of-sync indications received since the time when the RLF is predicted.

[0627] As one embodiment, the P1 is N320.

[0628] As one embodiment, a ratio of the predicted out-of-sync indications within the first time window is no less than a threshold triggers the prediction of the RLF.

[0629] As one sub-embodiment of the above embodiment, the no less than is greater than.

[0630] As one sub-embodiment of the above embodiment, the no less than is greater than or equal to.

[0631] As one sub-embodiment of the above embodiment, the threshold is configurable.

[0632] As one sub-embodiment of the above embodiment, the threshold is default.

[0633] As one sub-embodiment of the above embodiment, the ratio of the predicted out-of-sync indications within the first time window refers to a ratio of a number of the predicted out-of-sync indications within the first time window and a number of predicted indication periods within the first time window.

[0634] As one sub-embodiment of the above embodiment, the ratio of the predicted out-of-sync indications within the first time window refers to a ratio of a number of the predicted out-of-sync indications within the first time window and a number of the predicted in-sync indications within the first time window.

[0635] As one embodiment, the prediction of the RLF depends on a number of the predicted in-sync indications and a number of the predicted out-of-sync indications within a first time window.

[0636] As one embodiment, a presence of at least P1 consecutive predicted out-of-sync indications within a second time window and a non-presence of at least P2 consecutive predicted in-sync indications within a first time window triggers the prediction of the RLF; the P1 is a positive integer; the P2 is a positive integer; a start time of the first time window depends on an end time of the second time window.

[0637] As one embodiment, the first time window is implemented by a timer.

[0638] As one embodiment, a length of the first time window is indicated by a network.

[0639] As one embodiment, the length of the first time window is determined by the terminal.

[0640] As one embodiment, the length of the first time window is indicated by the related information of the predicted RLF.

[0641] As one embodiment, the first time window includes at least the P1 predicted indication periods.

[0642] As one embodiment, the length of the first time window is not less than (P1-1) predicted indication periods.

[0643] As one embodiment, the length of the first time window is not less than (P1-1) predicted indication periods and not greater than the P1 predicted indication periods.

[0644] As one embodiment, the first time window includes at least the P2 predicted indication periods.

[0645] As one embodiment, the length of the first time window is not less than (P2-1) predicted indication periods.

[0646] As one embodiment, the length of the first time window is not less than (P2-1) predicted indication periods and not greater than the P2 predicted indication periods.

[0647] As one embodiment, the first time window includes at least (P1+P2) predicted indication periods.

[0648] As one embodiment, the first time window is not less than the remaining time of the first counter; the first counter is a timer.

[0649] As one embodiment, the first time window is the remaining time of the first counter; the first counter is a timer.

[0650] As one embodiment, the first time window is greater than the remaining time of the first counter; the first counter is a timer.

[0651] As one embodiment, the first time window includes the remaining time of the first counter and at least one predicted indication period after the expiration time of the first counter; the first counter is a timer.

[0652] As one embodiment, the length of the first time sub-window is equal to the value of the first timer.

[0653] As one embodiment, the first time sub-window is the predicted running time of the first timer.

[0654] As one embodiment, the P2 consecutive predicted in- sync indications correspond to P2 consecutive predicted in-sync evaluation periods.

[0655] As one embodiment, the P1 consecutive predicted out-of-sync indications correspond to P1 consecutive predicted out-of-sync evaluation periods.

[0656] Embodiment 10

[0657] Embodiment 10 illustrates a diagram of a first counter according to one embodiment of the application, as shown in FIG. 10. In the diagram 10, the horizontal axis represents time, and the dashed single-headed arrow represents an out-of-sync indication.

[0658] In embodiment 10, when the RRC sublayer of the terminal receives an out-of-sync indication from the physical layer, the first counter is incremented by 1 if the first timer is not running; the first timer is started if the first counter reaches the first threshold; RLF prediction is performed if the first counter reaches the second threshold; the first timer is T310; the first counter is N310; and the first threshold is less than the second threshold.

[0659] As one embodiment, the first timer is running when the first counter reaches the second threshold.

[0660] As one embodiment, the first timer is not running when the first counter reaches the second threshold.

[0661] As one embodiment, the running time of the first timer and the performing of RLF prediction overlap in time.

[0662] As one embodiment, the running time of the first timer and the performing of RLF prediction do not overlap in time.

[0663] As one embodiment, the out-of-sync indication is dependent on an evaluation of the at least first reference signal.

[0664] As one embodiment, the out-of-sync indication is dependent on an evaluation of a reference signal used for RLM.

[0665] As one embodiment, the physical layer of the terminal sends an out-of-sync indication to the higher layer of the terminal if the link quality evaluated for each of the at least first reference signal in an out-of-sync evaluation period is worse than Qout configured by rlmInSyncOutOfSyncThreshold.

[0666] As an example, if the link quality evaluated for each reference signal used for RLM is worse than Qout configured by rlmInSyncOutOfSyncThreshold during one out-of-sync evaluation period, the physical layer of the terminal sends an out-of-sync indication to the higher layer of the terminal.

[0667] Embodiment 11

[0668] Embodiment 11 illustrates a schematic diagram of a first counter according to another embodiment of the present application, as shown in FIG. 11. In FIG. 11, the horizontal axis represents time, and the dotted single arrow represents an out-of-sync indication.

[0669] In Embodiment 11, when the RRC sublayer of the terminal receives an out-of-sync indication from the physical layer, if the first timer is not running, the first counter is increased by 1; if the first counter reaches the first threshold, the first timer is started; if the first counter reaches the second threshold, an RLF prediction is performed; the first timer is T310; the first counter is N310; the first threshold is greater than the second threshold.

[0670] As an example, the RLF prediction is performed when the first counter reaches the first threshold.

[0671] As an example, the RLF prediction is not performed when the first counter reaches the first threshold.

[0672] As an example, the running time of the first timer and the performing of the RLF prediction overlap in time.

[0673] As an example, the running time of the first timer and the performing of the RLF prediction do not overlap in time.

[0674] Embodiment 12

[0675] Embodiment 12 illustrates a structural block diagram of a processing apparatus in a terminal according to an embodiment of the present application, as shown in FIG. 12. In FIG. 12, the processing apparatus 1200 in the terminal comprises a first receiver 1201 and a first processor 1202.

[0676] The first receiver 1201 receives first signaling; wherein the first signaling indicates a first threshold; if a first counter reaches the first threshold, a first timer is started; if the first timer expires, an RLF is determined.

[0677] In Embodiment 12, if the first counter reaches a second threshold, an RLF prediction is performed; the first threshold and the second threshold are different.

[0678] As one embodiment, the first handler 1202 determines RLF if the first counter reaches a first threshold.

[0679] As one embodiment, the first handler 1202 performs RLF prediction if the first counter reaches a second threshold.

[0680] As one embodiment, the first handler 1202 sends a first notification when the first counter reaches the second threshold; receives the first notification; wherein the first notification triggers the performing RLF prediction.

[0681] As one embodiment, the first handler 1202 aborts the RLF prediction in response to a first condition being satisfied; wherein the first condition depends on at least one of a measurement or a prediction.

[0682] As one embodiment, the first handler 1202 sends a second notification when the first condition is satisfied; receives the second notification; wherein the second notification triggers the aborting the RLF prediction.

[0683] As one embodiment, the first handler 1202 operates at least one of the first counter or the first timer in response to predicting RLF.

[0684] As one embodiment, the first handler 1202 initiates RRC connection reestablishment in response to predicting RLF.

[0685] As one embodiment, the first handler 1202 operates at least one of the first counter or the first timer in response to predicting RLF or initiates RRC connection reestablishment depending on a time of occurrence of the predicted RLF.

[0686] As one embodiment, the first receiver 1201 receives at least a first reference signal; wherein the RLF prediction depends on the at least first reference signal.

[0687] As one embodiment, the predicting RLF depends on at least one of a number of predicted in- sync indications or a number of predicted out-of-sync indications within a first time window; the predicted in-sync indications or the predicted out-of-sync indications depend on the at least first reference signal.

[0688] As one embodiment, the first handler 1202 comprises a first transmitter.

[0689] As one embodiment, the first processor 1202 includes the third module in Figure 16; the third module performs the RLF prediction.

[0690] As one embodiment, the first processor 1202 includes the intelligent module 1501 in Figure 15; the intelligent module 1501 performs the RLF prediction.

[0691] As one embodiment, the first processor 1202 includes the inference function 1806 in Figure 18; the inference function 1806 performs the RLF prediction.

[0692] As one embodiment, the first receiver 1202 includes at least one of the antenna 452 or the receiver 454 or the multi-antenna receive processor 458 or the receive processor 456 or the controller / processor 459 or the memory 460 or the data source 467 in Figure 4.

[0693] As one embodiment, the first receiver 1201 includes at least the antenna 452 and the receiver 454 in Figure 4.

[0694] As one embodiment, the first transmitter includes at least one of the antenna 452 or the transmitter 454 or the multi-antenna transmit processor 457 or the transmit processor 468 or the controller / processor 459 or the memory 460 or the data source 467 in Figure 4.

[0695] As one embodiment, the first transmitter includes at least the antenna 452 and the transmitter 454 in Figure 4.

[0696] As one embodiment, the terminal includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is configured to store computer program codes, the computer program codes include computer instructions, the one or more processors invoke the computer instructions to make the terminal execute the method in the application which is used in the terminal; the one or more processors and the memory include the first receiver 1201 and the first processor 1202.

[0697] Embodiment 13

[0698] Embodiment 13 illustrates a structural block diagram of a processing apparatus for use in a base station according to one embodiment of the present application, as shown in Figure 13. In Figure 13, the processing apparatus 1300 in the base station includes a second transmitter 1301.

[0699] The second transmitter 1301 transmits a first signaling; wherein the first signaling indicates a first threshold; and wherein a receiver of the first signaling starts a first timer if the first counter reaches the first threshold; and wherein the receiver of the first signaling determines an RLF if the first timer expires.

[0700] In embodiment 13, the RLF prediction is performed if the first counter reaches a second threshold; and wherein the first threshold and the second threshold are different.

[0701] In one embodiment, the receiver of the first signaling transmits a first notification when the first counter reaches the second threshold; and wherein the receiver of the first signaling receives the first notification; and wherein the first notification triggers the performing of the RLF prediction.

[0702] In one embodiment, the receiver of the first signaling suspends the RLF prediction in response to a first condition being satisfied; and wherein the first condition depends on at least one of a measurement or a prediction.

[0703] In one embodiment, the receiver of the first signaling transmits a second notification when the first condition is satisfied; and wherein the receiver of the first signaling receives the second notification; and wherein the second notification triggers the suspending of the RLF prediction.

[0704] In one embodiment, the receiver of the first signaling operates at least one of the first counter or the first timer in response to predicting the RLF.

[0705] In one embodiment, the receiver of the first signaling initiates a RRC connection reestablishment in response to predicting the RLF.

[0706] In one embodiment, the second transmitter 1301 transmits at least a first reference signal; and wherein the RLF prediction depends on the at least first reference signal.

[0707] In one embodiment, the first signaling indicates the second threshold.

[0708] In one embodiment, the first condition comprises the first counter reaching a third threshold; and wherein the first signaling indicates the third threshold.

[0709] In one embodiment, the processing device 1300 in the base station comprises a second receiver 1302.

[0710] In one embodiment, the processing device 1300 in the base station comprises a third module in FIG. 16.

[0711] As one embodiment, the processing device 1300 in the base station comprises the training function 1805 of the RAN domain in FIG. 18.

[0712] As one embodiment, the processing device 1300 in the base station comprises the inference function 1806 in FIG. 18.

[0713] As one embodiment, the processing device 1300 in the base station comprises one inference function, 1704 or 1706, in FIG. 17.

[0714] As one embodiment, the second transmitter 1301 comprises at least one of the antenna 420 or the transmitter 418 or the multi-antenna transmit processor 471 or the transmit processor 416 or the controller / processor 475 or the memory 476 in FIG. 4 of this application.

[0715] As one embodiment, the second transmitter 1301 comprises at least the antenna 420 and the transmitter 418 in FIG. 4 of this application.

[0716] As one embodiment, the second receiver 1302 comprises at least one of the antenna 420 or the receiver 418 or the multi-antenna receive processor 472 or the receive processor 470 or the controller / processor 475 or the memory 476 in FIG. 4 of this application.

[0717] As one embodiment, the second receiver 1302 comprises at least the antenna 420 and the receiver 418 in FIG. 4 of this application.

[0718] As one embodiment, the base station comprises: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprise computer instructions, and the one or more processors invoke the computer instructions to cause the base station to perform the method in the base station in this application; the one or more processors and the memory comprise the second transmitter 1301.

[0719] Embodiment 14

[0720] Embodiment 14 illustrates a flowchart of a first state according to one embodiment of the present application, as shown in FIG. 14. Embodiment 14 illustrates a schematic diagram of an intelligent model according to one embodiment of the present application, as shown in FIG. 14.

[0721] For terminal U01, in step S1401, an RLF is predicted; in step S1402, in response to said predicting said RLF, a first status is triggered; in step S1403, any condition in a first set of conditions is met; in step S1404, in response to said any condition in said first set of conditions being met, said first status that is triggered is cancelled.

[0722] As one embodiment, said first status is triggered pending until said first status is cancelled.

[0723] As one embodiment, said pending means triggered and not cancelled.

[0724] As one embodiment, said pending means pending.

[0725] As one embodiment, said pending means set.

[0726] As one embodiment, said pending means stored.

[0727] As one embodiment, dashed box 14.1 is optional.

[0728] As one embodiment, said dashed box 14.1 is not present.

[0729] As one sub-embodiment of the above embodiment, any condition in said first set of conditions is not met.

[0730] As one sub-embodiment of the above embodiment, said first status is not cancelled.

[0731] As one embodiment, said dashed box 14.1 is present.

[0732] As one sub-embodiment of the above embodiment, at least one condition in said first set of conditions is met.

[0733] As one sub-embodiment of the above embodiment, said first status is cancelled.

[0734] As one embodiment, one condition in said first set of conditions comprises said predicted said RLF being predicted to be eliminated.

[0735] As one embodiment, one condition in said first set of conditions comprises initiating a handover procedure.

[0736] As one embodiment, one condition in said first set of conditions comprises entering an RRC_INACTIVE state.

[0737] As one embodiment, one condition in the first set of conditions comprises entering RRC_IDLE state.

[0738] As one embodiment, one condition in the first set of conditions comprises the intelligent model being deactivated.

[0739] As one embodiment, one condition in the first set of conditions comprises the intelligent model being deleted.

[0740] As one embodiment, one condition in the first set of conditions comprises the intelligent model being reconfigured.

[0741] As one embodiment, one condition in the first set of conditions comprises at least one of the predicted RLF being predicted to be eliminated or a handover procedure being initiated or an RRC connection reestablishment being initiated or entering RRC_INACTIVE state or entering RRC_IDLE state or the intelligent model being deactivated or the intelligent model being deleted or the intelligent model being reconfigured.

[0742] As one embodiment, the canceling refers to cancel.

[0743] As one embodiment, the canceling refers to release.

[0744] As one embodiment, the canceling refers to delete.

[0745] As one embodiment, the canceling refers to clear.

[0746] As one embodiment, the canceling refers to no longer storing.

[0747] Embodiment 15

[0748] Embodiment 15 illustrates a diagram of transmission of the first notification and the second notification according to one embodiment of the present application, as shown in FIG. 15. The terminal 1500 comprises an intelligent module 1501 and a legacy module 1502.

[0749] In embodiment 15, the legacy module 1502 of the terminal 1500 sends the first notification when the first counter reaches the second threshold; the intelligent module 1501 of the terminal 1500 receives the first notification; wherein the first notification triggers the performing RLF prediction.

[0750] In Embodiment 15, the legitimate module 1502 of the terminal 1500 sends a second notification when the first condition is satisfied; the smart module 1501 of the terminal 1500 receives the second notification; wherein the second notification triggers the suspension of the RLF prediction.

[0751] As one embodiment, the performing the RLF prediction comprises sending the first notification.

[0752] As one embodiment, the smart module 1501 of the terminal 1500 sends a third notification when the RLF is predicted; the legitimate module 1502 of the terminal 1500 receives the third notification; wherein the third notification indicates the predicted RLF.

[0753] As one embodiment, the performing the RLF prediction comprises sending the first notification and receiving the third notification.

[0754] As one embodiment, the third notification comprises relevant information of the predicted RLF.

[0755] As one embodiment, the smart module 1501 of the terminal 1500 sends a fourth notification; the legitimate module 1502 of the terminal 1500 receives the fourth notification; wherein the fourth notification indicates the predicted RLF is eliminated.

[0756] As one sub-embodiment of the above-mentioned embodiment, the above-mentioned method avoids triggering unreasonable UE behavior by updating prediction information.

[0757] As one sub-embodiment of the above-mentioned embodiment, the above-mentioned method is beneficial to UE decision.

[0758] As one sub-embodiment of the above-mentioned embodiment, the predicted RLF elimination means that RLF will not occur at the predicted time of the predicted RLF.

[0759] As one embodiment, in response to the first notification being received, an indication is sent to a lower layer; the indication is received at the RRC sub-layer.

[0760] As one embodiment, in response to the first notification being received, an indication is sent to an upper layer; the indication is received at the RRC sub-layer.

[0761] As one embodiment, the indication indicates the first notification.

[0762] As one embodiment, the indication comprises the first notification.

[0763] As one embodiment, the legitimate module is logical.

[0764] As one embodiment, the legal module is physical.

[0765] As one embodiment, the legal module determines RLF if the first counter reaches a first threshold.

[0766] As one embodiment, the legal module receives at least a first reference signal.

[0767] As one embodiment, the legal module operates the first counter in response to predicting RLF.

[0768] As one embodiment, the legal module initiates RRC connection reestablishment in response to predicting RLF.

[0769] As one embodiment, the legal module is a protocol entity.

[0770] As one embodiment, the legal module is an RRC protocol entity.

[0771] As one embodiment, the legal module is at an RRC sublayer.

[0772] As one embodiment, the legal module is at an upper layer of an RRC sublayer.

[0773] As one embodiment, the legal module is at a lower layer of an RRC sublayer.

[0774] As one embodiment, the legal module supports 3GPP Release 17.

[0775] As one embodiment, the legal module supports 3GPP Release 18.

[0776] As one embodiment, the legal module does not have either of a training function or an inference function.

[0777] As one embodiment, the legal module is not an intelligent module.

[0778] As one embodiment, the intelligent module is a hardware.

[0779] As one embodiment, the intelligent module is a software.

[0780] As one embodiment, the intelligent module is a program.

[0781] As one embodiment, the intelligent module is a function.

[0782] As one embodiment, the intelligent module is a protocol entity.

[0783] As one embodiment, the smart module is an AI entity.

[0784] As one embodiment, the smart module is an ML entity.

[0785] As one embodiment, the smart module is an AI / ML entity.

[0786] As one embodiment, the smart module is logical.

[0787] As one embodiment, the smart module is physical.

[0788] As one embodiment, the smart module performs RLF prediction.

[0789] As one embodiment, the smart module processes the at least one smart model.

[0790] As one embodiment, the smart module includes at least one of the second module or the third module in the smart model as shown in embodiment 16.

[0791] As one embodiment, the interface between the legal module and the smart module is defined by 3GPP protocol.

[0792] As one embodiment, the interface between the legal module and the smart module is based on UE implementation.

[0793] As one embodiment, the interface between the legal module and the smart module is logical.

[0794] As one embodiment, the interface between the legal module and the smart module is physical.

[0795] Embodiment 16

[0796] Embodiment 16 illustrates a schematic diagram of a smart model according to one embodiment of the present application, as shown in FIG. 16. FIG. 16 includes a first module, a second module, a third module, a fourth module, and a fifth module.

[0797] In embodiment 16, in the smart model as shown in FIG. 16, the first module sends a first data set to the second module, the first module sends a second data set to the third module, the first module sends a third data set to the fifth module, the fifth module sends a first group of parameters to the second module, the fifth module sends a second group of parameters to the third module, the fifth module sends a third group of parameters to the fourth module, the second module sends a fourth group of parameters to the fourth module, and the fourth module sends a fifth group of parameters to the third module.

[0798] As an example, the first module, the second module, the third module, the fourth module and the fifth module in one intelligent model all belong to the terminal.

[0799] The method avoids air interface signaling interaction and shortens transmission delay.

[0800] As an example, any one of the first module, the second module, the third module, the fourth module and the fifth module in one intelligent model does not belong to the terminal.

[0801] The method reduces hardware complexity of the terminal.

[0802] As an example, at least one of the first module, the second module, the third module, the fourth module and the fifth module in one intelligent model belongs to the terminal; and at least one of the first module, the second module, the third module, the fourth module and the fifth module belongs to the network node.

[0803] The method balances hardware complexity of the terminal and transmission delay.

[0804] As an example, the first module is used for data collection.

[0805] As an example, the first module is responsible for data collection.

[0806] As an example, the first module has a data collection function.

[0807] As an example, the second module has a training function.

[0808] As an example, the training function is used for model training.

[0809] As an example, the training function is responsible for model training.

[0810] As an example, the training function has a model training function.

[0811] As an example, the training function performs model training.

[0812] As an example, the second module performs validation.

[0813] As an example, the second module performs testing.

[0814] As an embodiment, the second module generates model performance metrics.

[0815] As an embodiment, the second module is responsible for data preparation.

[0816] As an embodiment, the data preparation includes at least one of data pre-processing or cleaning or formatting or transformation.

[0817] As an embodiment, the third module has an inference function.

[0818] As an embodiment, the inference function is used for inference.

[0819] As an embodiment, the inference function is responsible for inference.

[0820] As an embodiment, the fourth module is used for model storage.

[0821] As an embodiment, the fourth module has a model storage function.

[0822] As an embodiment, the fourth module is responsible for storing trained models.

[0823] As an embodiment, the fourth module is responsible for storing trained models that can be used to perform inference processing.

[0824] As an embodiment, the fifth module is used for management.

[0825] As an embodiment, the fifth module is responsible for management.

[0826] As an embodiment, the fifth module has a management function.

[0827] As an embodiment, the fifth module manages intelligent models.

[0828] As an embodiment, the first data set is training data.

[0829] As an embodiment, the first data set is an input to the second module.

[0830] As an embodiment, the second data set is inference data.

[0831] As an embodiment, the second dataset is an input to the third module.

[0832] As an embodiment, the third dataset is Monitoring Data.

[0833] As an embodiment, the third dataset is an input to the fifth module.

[0834] As an embodiment, the first set of parameters includes Monitoring output.

[0835] As an embodiment, the second set of parameters includes Management Instruction.

[0836] As an embodiment, the second set of parameters is used for fine-tune operation of inference function.

[0837] As an embodiment, the second set of parameters includes identification of a model.

[0838] As an embodiment, the second set of parameters is used for selection of a model.

[0839] As an embodiment, the second set of parameters is used for switching of a model.

[0840] As an embodiment, the second set of parameters is used for activation / deactivation of a model.

[0841] As an embodiment, the second set of parameters is used for fallback of an intelligent model.

[0842] As an embodiment, the third set of parameters includes Model Transfer Request.

[0843] As an embodiment, the third set of parameters includes Model Delivery Request.

[0844] As an embodiment, the fourth set of parameters includes Trained Model.

[0845] As an embodiment, the fourth set of parameters includes Updated Model.

[0846] As an embodiment, the fourth set of parameters indicates identification of a model.

[0847] As one embodiment, the fifth set of parameters includes Model Transfer.

[0848] As one embodiment, the fifth set of parameters includes Model Delivery.

[0849] As one embodiment, the fifth set of parameters indicates an identity of a model.

[0850] As one embodiment, the first type of output is absent.

[0851] As one embodiment, the first type of output is present.

[0852] As one embodiment, the second module sends the first type of output to the fifth module.

[0853] As one embodiment, the first type of output includes a monitoring output.

[0854] As one embodiment, the second type of output is absent.

[0855] As one embodiment, the second type of output is present.

[0856] As one embodiment, the third module sends the second type of output to the fifth module.

[0857] As one embodiment, the second type of output includes an Inference Output.

[0858] As one embodiment, the second type of output is used by the fifth module to monitor performance of an AI / ML model.

[0859] As one embodiment, the second type of output indicates a result of the performing RLF prediction.

[0860] As one embodiment, the second type of output indicates that an RLF is predicted.

[0861] As one embodiment, the second type of output includes information related to the predicted RLF.

[0862] As one embodiment, the second type of output includes the third notification.

[0863] As one embodiment, the second type of output includes the fourth notification.

[0864] As one embodiment, the first dataset in the intelligent model is configured by a network.

[0865] As an embodiment, the first data set in the intelligent model is determined by the terminal.

[0866] As an embodiment, the first data set in the intelligent model comprises storage data of the terminal; the storage data can be from the network, can also be from the log of the terminal, and can also be from other RAN nodes.

[0867] As an embodiment, the first data set in the intelligent model comprises measurement information of the terminal; the measurement information can be the moving state of the terminal, for example, the moving speed, or the number of switched cells in a given time interval, etc.; the measurement information can also be the measurement result for the reference signal, for example, the cell-level measurement result, or the beam-level measurement result, or the time-domain measurement result, or the frequency-domain measurement result, or the spatial-domain measurement result, or the combination thereof, etc.

[0868] As an embodiment, the first data set in the intelligent model comprises the measurement result for the at least first reference signal.

[0869] As an embodiment, the second data set in the intelligent model is configured by the network.

[0870] As an embodiment, the second data set in the intelligent model is determined by the terminal.

[0871] As an embodiment, the second data set in the intelligent model comprises storage data of the terminal; the storage data can be from the network, can also be from the log of the terminal, and can also be from other RAN nodes.

[0872] As an embodiment, the second data set in the intelligent model comprises measurement information of the terminal; the measurement information can be the moving state of the terminal, for example, the moving speed, or the number of switched cells in a given time interval, etc.; the measurement information can also be the measurement result for the reference signal, for example, the cell-level measurement result, or the beam-level measurement result, or the time-domain measurement result, or the frequency-domain measurement result, or the spatial-domain measurement result, or the combination thereof, etc.

[0873] As an embodiment, the second data set in the intelligent model comprises the measurement result for the at least first reference signal.

[0874] As an embodiment, the third data set in the intelligent model is configured by the network.

[0875] As an embodiment, the third data set in the intelligent model is determined by the terminal.

[0876] As an embodiment, the third data set in the intelligent model comprises storage data of the terminal; the storage data can be from the network, can also be from the log of the terminal, and can also be from other RAN nodes.

[0877] As an embodiment, the third data set in the intelligent model comprises measurement information of the terminal; the measurement information can be the moving state of the terminal, such as the moving speed, or the number of switched cells in a given time interval, etc.; the measurement information can also be the measurement result for the reference signal, such as the cell-level measurement result, or the beam-level measurement result, or the time-domain measurement result, or the frequency-domain measurement result, or the spatial-domain measurement result, or a combination thereof, etc.

[0878] As an embodiment, the third data set in the intelligent model comprises the measurement result for the at least first reference signal.

[0879] As an embodiment, the RLF prediction is performed through the intelligent model.

[0880] As an embodiment, the embodiment 16 is only for illustrating that the present application can be applied to the intelligent model, the embodiment does not limit that the present application is applied to the non-intelligent operation, and the embodiment does not limit that the present application is applied to other types of intelligent models to achieve the effect equivalent to the intelligent model shown in the figure 16.

[0881] Embodiment 17

[0882] The embodiment 17 illustrates the schematic diagram of the intelligent function deployment of the RAN (Radio Access Network, wireless access network) domain according to an embodiment of the present application; as shown in the figure 17. The gNB in the embodiment 17 can be replaced by the network device such as the eNB, or the 6G base station, etc.

[0883] The intelligent function of the RAN domain comprises the training (also referred to as the ML training, or the AI training, or the AI / ML training) function, the testing (also referred to as the ML testing, or the AI testing, or the AI / ML testing) function, the inference (also referred to as the ML inference, or the AI inference, or the AI / ML inference) function, etc. The training function, the testing function, and the inference function can be independently deployed, or can be co-located deployed. The deployment of the intelligent function can be realized through the software, such as the download and / or running of the executable file; or can be realized through the software combined with the hardware, such as accelerating the calculation through the hardware to improve the operation speed or save the power consumption.

[0884] For training function, it can be deployed in cross-domain management system, or domain-specific management system; the domain-specific management system is used for managing RAN domain or CN (Core Network, core network) domain. For example, for the training function of MDA (Management Data Analytics, management data analysis) can be deployed in MDAF (MDA function); for the training of network data analysis can be deployed in NWDAF (Network Data Analytics Function, network data function), that is, the training function is MTLF (Model Training logical function, model training logical function).

[0885] For inference function, it can also be deployed in cross-domain management system, or domain-specific management system; for example, the inference function is MDAF, or the inference function is AnLF (Analytics logical function, analysis logical function) in NWDAF.

[0886] Similarly, the test function can also be deployed in cross-domain management system, or domain-specific management system.

[0887] In embodiment 17, the training function 1702 of the RAN domain is located in the management function 1703 of the RAN domain; and the inference function is located in the base station, that is, the inference function 1704 is located in the gNB 1705, the inference function 1706 is located in the gNB 1707, and so on.

[0888] In FIG. 17, the management of the inference function of the plurality of base stations is completed by the RAN domain management function 1703, that is, data interaction is performed with the RAN domain MnS (Management Service, management service) consumer / cross-domain management 1701 (as shown by the dashed arrow 1708 in FIG. 17).

[0889] Optionally, the management of the inference function can also be completed by the base station itself, that is, each base station can independently interact with the RAN domain MnS consumer / cross-domain management 1701.

[0890] It should be noted that embodiment 17 is only a non-limiting implementation; optionally, the training function of the RAN domain can also be deployed in the base station; or optionally, part of the base stations deploy the inference function and the training function of the RAN domain, and part of the base stations only deploy the inference function.

[0891] As an embodiment, one gNB (or base station) in embodiment 17 is the base station of the present application.

[0892] As an embodiment, one inference function in FIG. 17 performs RLF prediction.

[0893] Embodiment 18

[0894] Embodiment 18 shows a schematic diagram of UE intelligent function deployment according to one embodiment of the present application; as shown in FIG. 18. The training function 1805 of the RAN domain in FIG. 18 is optional.

[0895] The UE intelligent function 1804 is deployed in the terminal of the present application, and the UE intelligent function 1804 includes an inference function 1806; the inference function 1806 uses an intelligent model (also known as an AI model, or an ML model, or an AI / ML model) for inference; one intelligent model usually needs to be trained before being used for AI / ML inference.

[0896] As an embodiment, the UE intelligent function 1804 includes a training function 1805 of the RAN domain, which runs training data through an intelligent model to derive relevant loss, and adjusts the parameters of the intelligent model based on the calculated loss; the training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0897] The above embodiments can reduce the complexity of the base station, or save the air interface resources caused by the reporting of training data; however, the above embodiments put higher requirements on the processing capability of the UE side.

[0898] Optionally, the UE intelligent function 1804 further includes a training function of the CN domain (not included in FIG. 18).

[0899] Optionally, the UE intelligent function 1804 further includes an intelligent deployment function (not included in FIG. 18), which is used to load intelligent models and data.

[0900] As an embodiment, the terminal indicates whether it supports the training function (RAN domain or CN domain) through capability reporting, and the capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0901] As an embodiment, the intelligent model, and related metadata, is loaded by the terminal from a network device or a remote server.

[0902] Optionally, the UE intelligent function 1804 is a MnS producer providing data for management or analytics to the CN domain MnF 1801, and / or the RAN domain MnF 1802, and / or the cross-domain management system 1803 (as indicated by double-headed arrow 1507).

[0903] Optionally, the UE intelligent function 1804 is a MnS consumer loading data from the CN domain MnF 1801, and / or the RAN domain MnF 1802, and / or the cross-domain management system 1803 for AI / ML related management, such as management data requests, intelligent model activation, and / or intelligent model training, etc. (as indicated by double-headed arrow 1807).

[0904] As an embodiment, the intelligent model is based on a neural network.

[0905] As an embodiment, the intelligent model is based on a CNN (Conventional Neural Networks).

[0906] As an embodiment, the intelligent model is based on a Transformer architecture.

[0907] As an embodiment, the terminal in the present application comprises the inference function 1806 in FIG. 18.

[0908] As an embodiment, the first processor in the present application comprises the inference function 1806 in FIG. 18.

[0909] As an embodiment, the UE 201 in FIG. 2 comprises the inference function 1806 in FIG. 18.

[0910] As an embodiment, the first communication device 450 in FIG. 4 comprises the inference function 1806 in FIG. 18.

[0911] As an embodiment, the first processor 1202 in FIG. 12 comprises the inference function 1806 in FIG. 18.

[0912] As one example, the smart module 1501 in FIG. 15 includes the inference function 1806 in FIG. 18.

[0913] As one example, the third module in FIG. 16 includes the inference function 1806 in FIG. 18.

[0914] As one example, the inference function 1806 in FIG. 18 performs RLF prediction.

[0915] As one example, the inference function 1806 in FIG. 18 indicates relevant information of the predicted RLF.

[0916] Embodiment 19

[0917] Embodiment 19 illustrates a flowchart of AI / ML based process according to an embodiment of the present application; as shown in FIG. 19. FIG. 19 includes a third operation, a fourth operation, a fifth operation, a sixth operation, and a seventh operation. In Embodiment 19, the third operation and the fourth operation belong to a first phase, the fifth operation belongs to a second phase, the sixth operation belongs to a third phase, and the seventh operation belongs to a fourth phase. In FIG. 19, the line with arrow indicates the order of the flow.

[0918] As one example, the third operation includes AI / ML training, the fourth operation includes AI / ML testing, the fifth operation includes AI / ML emulation, the sixth operation includes AI / ML entity loading, and the seventh operation includes AI / ML inference.

[0919] As one example, the first phase includes a training phase, the second phase includes an emulation phase, the third phase includes a deployment phase, and the fourth phase includes an inference phase.

[0920] As one example, the first phase includes AI / ML model training.

[0921] As one example, the first phase includes AI / ML model training and AI / ML testing.

[0922] As one example, the AI / ML model training includes initial training and re-training of one or a set of AI / ML entities.

[0923] As one embodiment, the AI / ML model training relies on training data.

[0924] As one embodiment, the AI / ML model training includes AI / ML entity validation.

[0925] As one embodiment, the AI / ML entity validation is used to evaluate the performance of the AI / ML entity.

[0926] As one embodiment, the AI / ML entity validation relies on validation data.

[0927] As one embodiment, if the result of AI / ML entity validation does not meet the expectation, the AI / ML model will be retrained.

[0928] As one embodiment, the AI / ML testing includes testing the validated AI / ML entity to evaluate the performance of the trained AI / ML model.

[0929] As one embodiment, if the result of AI / ML testing meets the expectation, the AI / ML entity proceeds to the next stage; otherwise, the AI / ML model will be retrained.

[0930] As one embodiment, the AI / ML testing relies on testing data.

[0931] As one embodiment, the second stage includes AI / ML simulation, which simulates the inference of the AI / ML entity in a simulation environment.

[0932] As one embodiment, the AI / ML simulation is to evaluate the performance of the inference of the AI / ML entity in a simulation environment before the AI / ML entity is used.

[0933] As one embodiment, the second stage is optional.

[0934] As one embodiment, the third stage includes AI / ML entity loading, which is to obtain the trained AI / ML entity to obtain the desired AI / ML inference function.

[0935] As one embodiment, the third stage is optional.

[0936] As one embodiment, the third stage is not needed when the training function and the inference function are co-located.

[0937] As one embodiment, the fourth stage includes AI / ML inference.

[0938] Those skilled in the art can understand that all or part of the steps in the foregoing method can be instructed by programs to the relevant hardware to complete, and the programs can be stored in a computer readable storage medium, such as a read-only memory, a hard disk, an optical disk or the like. Alternatively, all or part of the steps of the foregoing embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module unit in the foregoing embodiments can be implemented in the form of hardware or in the form of a software function module, and the present application is not limited to any specific form of combination of software and hardware. The user equipment, terminal and UE in the present application include but are not limited to unmanned aerial vehicles, communication modules on unmanned aerial vehicles, remote control aircraft, aircraft, small aircraft, mobile phones, tablet computers, notebooks, vehicle-mounted communication devices, wireless sensors, network cards, Internet of Things terminals, RFID terminals, NB-IOT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, network cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablet computers and other wireless communication devices. The base station or system device in the present application includes but is not limited to macro cellular base stations, micro cellular base stations, home base stations, relay base stations, gNB (NR NodeB) NR NodeB, TRP (Transmitter Receiver Point) and other wireless communication devices.

[0939] The above only describes the preferred embodiments of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting wireless link failures, characterized in that, include: Receive a first signaling instruction; wherein the first signaling instruction indicates a first threshold; if a first counter reaches the first threshold, start a first timer; if the first timer expires, determine an RLF; If the first counter reaches the second threshold, RLF prediction is performed; the first threshold and the second threshold are different.

2. The method according to claim 1, characterized in that, The method includes: When the first counter reaches the second threshold, a first notification is sent; the first notification is received. The first notification triggers the execution of RLF prediction.

3. The method according to claim 1 or 2, characterized in that, The method includes: As a response to the first condition being met, the RLF prediction is aborted; The first condition depends on at least one of measurement or prediction.

4. The method according to claim 3, characterized in that, The method includes: When the first condition is met, send a second notification; receive the second notification; The second notification triggers the termination of the RLF prediction.

5. The method according to any one of claims 1-4, characterized in that, The method includes: In response to the prediction of RLF, operate at least one of the first counter or the first timer.

6. The method according to any one of claims 1-4, characterized in that, The method includes: In response to the predicted RLF, RRC connection reconstruction is initiated.

7. The method according to any one of claims 1-4, characterized in that, The method includes: In response to a predicted RLF, either operating the first counter or the first timer, or initiating RRC connection reconstruction, depends on the predicted occurrence time of the RLF.

8. The method according to any one of claims 1-7, characterized in that, The method includes: Receive at least the first reference signal; The RLF prediction depends on the at least first reference signal.

9. The method according to claim 8, characterized in that, The predicted RLF depends on at least one of the number of predicted synchronization indicators or the number of predicted out-of-synchronization indicators within a first time window; the predicted synchronization indicator or the predicted out-of-synchronization indicator depends on the at least first reference signal.

10. 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 1-9.

11. A method for predicting wireless link failures, characterized in that, include: Send a first signaling instruction; wherein the first signaling instruction indicates a first threshold; if a first counter reaches the first threshold, the receiver of the first signaling instruction starts a first timer; if the first timer expires, the receiver of the first signaling instruction determines an RLF; If the first counter reaches the second threshold, RLF prediction is performed; the first threshold and the second threshold are different.

12. The method according to claim 11, characterized in that, When the first counter reaches the second threshold, the receiver of the first signaling sends a first notification; the receiver of the first signaling receives the first notification; wherein the first notification triggers the execution of RLF prediction.

13. The method according to claim 11 or 12, characterized in that, In response to the fulfillment of the first condition, the receiver of the first signaling suspends the RLF prediction; wherein the first condition depends on at least one of measurement or prediction.

14. The method according to claim 13, characterized in that, When the first condition is met, the receiver of the first signaling sends a second notification; the receiver of the first signaling receives the second notification; wherein the second notification triggers the termination of the RLF prediction.

15. The method according to any one of claims 11-14, characterized in that, In response to the prediction of RLF, the receiver of the first signaling operates at least one of the first counter or the first timer.

16. The method according to any one of claims 11-14, characterized in that, In response to the predicted RLF, the receiver of the first signaling initiates an RRC connection reconstruction.

17. The method according to any one of claims 11-16, characterized in that, Send at least the first reference signal; The RLF prediction depends on the at least first reference signal.

18. The method according to any one of claims 11-17, characterized in that, The first signaling indicates the second threshold.

19. The method according to claim 13 or 14, characterized in that, The first condition includes the first counter reaching a third threshold; the first signaling indicating the third threshold.

20. A base station, characterized in that, 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 11-19.

Images