Wireless communication method and wireless communication device

Abstract

The present disclosure provides a wireless communication method. The method comprises: a user equipment 120 sends to a base station radio link failure (RLF) prediction information predicted on the basis of an artificial intelligence / machine learning (AI / ML) model. The RLF prediction information comprises at least one of the following: a model identifier (ID), an RLF type, an RLF time, prediction accuracy, an ID corresponding to a predicted RLF, and a radio resource management (RRM) measurement result of a serving cell predicted prior to RLF occurrence. On one hand, the probability of a successful handover is increased, and on the other hand, the base station is enabled to better anticipate radio link failure of the user equipment 120, thereby preventing RLF and improving user experience.

Description

Wireless communication method and wireless communication device Technical Field

[0001] The present disclosure relates to the field of wireless communications, and in particular to a wireless communication method and a wireless communication device. Background Art

[0002] In existing technologies, artificial intelligence / machine learning (AI / ML) is a system that can replace human labor through computational learning. AI / ML can be used to solve various problems, such as natural human language processing, computing, and graphics processing. In recent years, AI / ML has been applied in the communications field. However, the application of AI / ML in the communications field remains a challenge in enhancing wireless resource allocation and mobility management. Therefore, a wireless communication method and wireless communication device are needed to improve existing technologies.

[0003] Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a wireless communication method in view of the above-mentioned defects of the prior art, aiming to solve the problems existing in the prior art.

[0005] According to one aspect of the present disclosure, a wireless communication method is provided, which is executed by a user equipment 120, and the method includes:

[0006] Send radio link failure (RLF) prediction information based on artificial intelligence (AI) / machine learning (ML) model predictions, where the RLF prediction information includes at least one of the following: model ID, RLF type, RLF time, prediction accuracy, an identification ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result before the RLF occurs.

[0007] According to one aspect of the present disclosure, a wireless communication method is provided, which is executed by a first base station, and the method includes:

[0008] Receive radio link failure (RLF) prediction information based on an artificial intelligence / machine learning (AI / ML) model, where the RLF prediction information includes at least one of the following: a model ID, an RLF type, an RLF time, a prediction accuracy, an identification ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result before the RLF occurs.

[0009] According to one aspect of the present disclosure, a wireless communication device is provided, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the steps in the data processing method as described in any one of the above items.

[0010] Beneficial effects of the present invention: In the present disclosure, the user equipment 120 sends wireless link failure RLF prediction information based on artificial intelligence / machine learning AI / ML model prediction to the base station, which on the one hand improves the probability of successful switching, and on the other hand enables the base station to better predict the wireless link failure of the user equipment 120, avoid RLF, and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present disclosure or related technologies, the following drawings will be briefly introduced in the embodiments. Obviously, the drawings are only some embodiments of the present disclosure, and ordinary technicians in this field can derive other drawings based on these drawings without inventive work.

[0012] FIG1 is a schematic diagram illustrating a framework of a wireless communication system provided by the present disclosure.

[0013] FIG2 illustrates a schematic diagram of a user equipment provided by the present disclosure being covered by multiple cells.

[0014] FIG3 illustrates one of the flow charts of the wireless communication method provided by the present disclosure.

[0015] FIG4 illustrates a second flowchart of the wireless communication method provided by the present disclosure.

[0016] FIG5 illustrates one of the signaling interaction schematic diagrams of a wireless communication method provided by the present disclosure.

[0017] FIG6 illustrates a second signaling interaction diagram of a wireless communication method provided by the present disclosure.

[0018] FIG7 illustrates a third signaling interaction diagram of a wireless communication method provided by the present disclosure.

[0019] FIG8 illustrates a fourth signaling interaction diagram of a wireless communication method provided by the present disclosure.

[0020] FIG9 illustrates a fifth signaling interaction diagram of a wireless communication method provided by the present disclosure.

[0021] FIG10 illustrates one of the flow charts of performance reporting for radio link failure prediction provided by the present disclosure.

[0022] FIG11 illustrates another flowchart of performance reporting for wireless link failure prediction provided by the present disclosure.

[0023] FIG12 illustrates a third flowchart of another performance reporting method for wireless link failure prediction provided by the present disclosure.

[0024] FIG13 illustrates a fourth flowchart of another performance reporting method for wireless link failure prediction provided by the present disclosure.

[0025] FIG14 illustrates an exemplary block diagram of a wireless communication system provided by the present disclosure. DETAILED DESCRIPTION

[0026] The embodiments of the present disclosure describe technical matters, structural features, objectives and effects in detail with reference to the accompanying drawings, as described below. Specifically, the terms in the embodiments of the present disclosure are only used to describe the purpose of specific embodiments, rather than to limit the present disclosure.

[0027] In this disclosure, "A or B" may mean "only A," "only B," or "both A and B."

[0028] In other words, in the present disclosure, "A or B" may be interpreted as "A and / or B." For example, in the present disclosure, "A, B or C" may mean "only A," "only B," "only C," or "any combination of A, B, and C."

[0029] As used in this disclosure, a slash ( / ) or a comma may mean "and / or". For example, "A / B" may mean "A and / or B". Thus, "A / B" may mean "only A", "only B", or "both A and B". For example, "A, B, C" may mean "A, B, or C".

[0030] In the present disclosure, “at least one of A and B” may mean “only A”, “only B”, or “both A and B”. In addition, in the present disclosure, the expression “at least one of A or B” or “at least one of A and / or B” may be interpreted as “at least one of A and B”.

[0031] In addition, in the present disclosure, “at least one of A, B, and C” may mean “only A,” “only B,” “only C,” or “any combination of A, B, and C.” In addition, “at least one of A, B, or C” or “at least one of A, B, and / or C” may mean “at least one of A, B, and C.”

[0032] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the described features. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0033] Those skilled in the art will recognize and appreciate that the details of the described examples are merely illustrative of some embodiments and that the teachings set forth herein are applicable to various alternative arrangements.

[0034] The technical solution disclosed herein can be applied to various wireless communication systems, such as: Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, 5G communication system or future wireless communication systems, etc.

[0035] Exemplarily, a wireless communication system 100 applied in the present disclosure is shown in FIG1 . The wireless communication system 100 may include a first base station 110 and a second base station 140, and the first base station 110 / the second base station 140 may be a device for communicating with a user equipment 120 (UE). The first base station 110 / the second base station 140 may provide communication coverage for a specific geographical area and may communicate with the user equipment 120 located within the coverage area. Optionally, the first base station 110 / the second base station 140 may be an evolved Node B (eNB or eNodeB) in an LTE system, or the base station may be a mobile switching center, a relay station, an access point, an in-vehicle device, a wearable device, a hub, a switch, a bridge, a router, a network-side device in a 5G network, or a base station in a future communication system.

[0036] The wireless communication system 100 also includes at least one user equipment 120 located within the coverage area of ​​the first base station 110 / the second base station 140. As used herein, "user equipment" includes, but is not limited to, a device configured to receive / send communication signals via a wired connection, such as a Public Switched Telephone Network (PSTN), a Digital Subscriber Line (DSL), a digital cable, a direct cable connection, and / or another data connection / network, and / or via a wireless interface, such as a cellular network, a Wireless Local Area Network (WLAN), a digital television network such as a DVB-H network, a satellite network, an AM-FM broadcast transmitter, and / or another user equipment 120, and / or an Internet of Things (IoT) device. A user equipment 120 configured to communicate via a wireless interface may be referred to as a "wireless communication terminal," "wireless terminal," or "mobile terminal." Examples of mobile terminals include, but are not limited to, satellite or cellular telephones; Personal Communications System (PCS) terminals that can combine cellular radiotelephones with data processing, fax, and data communications capabilities; PDAs that can include radiotelephones, pagers, Internet / Intranet access, web browsers, organizers, calendars, and / or Global Positioning System (GPS) receivers; and conventional laptop and / or palmtop receivers or other electronic devices that include radiotelephone transceivers. User equipment 120 can be referred to as an access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote user equipment 120, mobile device, wireless communication device, or user agent. The access terminal can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a user device 120 in a 5G network, or a user device 120 in a future evolved PLMN, etc.

[0037] Optionally, the user equipments 120 may perform device-to-device (D2D) communication with each other.

[0038] Optionally, the 5G communication system or 5G network may also be referred to as a New Radio (NR) system or NR network.

[0039] The wireless communication system 100 also includes a core network 130. Core network 130 may be an IP mobile communication network operated by a mobile communication operator. For example, core network 130 may be a core network used by a mobile communication operator that operates and manages the wireless communication system 100, or may be a core network used by a virtual mobile communication operator such as an MVNO (Mobile Virtual Network Operator).

[0040] The core network 130 can be connected to the first base station 110 / the second base station 140 as a relay device for transmitting user data. The user equipment 120 sends and receives user data via the core network 130. It should be noted that the communication of user data is not limited to IP communication and can also be non-IP communication.

[0041] Figure 1 exemplarily shows a first base station 110 and a second base station 140, two user equipments 120 and a core network 130. Optionally, the wireless communication system 100 may include multiple base stations and each base station may include another number of user equipments 120 within its coverage area, which is not limited in the present disclosure.

[0042] Optionally, the wireless communication system 100 may further include other network entities such as a network controller, a mobility management entity, and a network element, which is not limited in this disclosure. For example, the core network 130 may include other network entities such as a network controller, a mobility management entity, and a network element, which is not limited in this disclosure.

[0043] It should be understood that in the present disclosure, a device with wireless communication capabilities in a network / system may be referred to as a wireless communication device. Taking the wireless communication system 100 shown in Figure 1 as an example, the wireless communication device may include a first base station 110 and a second base station 140 with communication capabilities, a user device 120, and a core network 130. The first base station 110 / the second base station 140 and the user device 120 may be the specific devices described above and will not be repeated here. The wireless communication device may also include other devices (core network 130) in the wireless communication system 100. For example, the core network 130 may include other network entities such as a network controller and a mobility management entity, which is not limited in the present disclosure.

[0044] After the introduction of the artificial intelligence / machine learning AI / ML model, the user equipment 120 will use the artificial intelligence / machine learning AI / ML model to perform inference, which can predict future mobility parameters (inference output). Therefore, it is possible to modify the signaling related to the user equipment 120 reporting future mobility parameters. Existing mechanisms do not support inference results.

[0045] The reporting of Radio Link Failure (RLF) prediction can help the network side (e.g., the first base station 110) predict RLF in advance, so that the network side (e.g., the first base station 110) can make a more accurate handover (HO) decision based on the RLF type provided by the user equipment 120, thereby avoiding the recurrence of RLF.

[0046] The information sending method provided by the embodiment of the present application is described in detail below through some embodiments and their application scenarios in combination with the accompanying drawings.

[0047] Figure 2 illustrates a schematic diagram of a user device 120 provided by the present disclosure being covered by multiple cells. As shown in Figure 2, in a real-world network deployment, a region is typically covered by multiple cells. In this scenario, user device 120 is covered by cells 1, 2, and 3. Furthermore, user device 120 is located at the center of cells 1, 2, and 3, and there is no possibility of handover due to a drop in signal quality in the serving cell at the cell edge.

[0048] However, if a coverage hole suddenly appears while UE 120 is within the coverage of serving cell 1, handover cannot be used to maintain optimal network connectivity and signal quality for UE 120. Therefore, AI / ML can be introduced. If UE 120 can predict the coverage hole in advance, it can be handed over to another cell, such as cell 2, to avoid RLF.

[0049] When UE 120 performs RRC re-establishment to gNB2 where cell 2 is located, UE 120 may include information / parameters of the last radio resource management (RRM) measurement result before the occurrence of RLF in the radio resource control (RRC) re-establishment message. This parameter can guide gNB1 when to preemptively handover UE 120 to another cell, such as cell 2.

[0050] FIG3 illustrates one of the flow charts of the wireless communication method provided by the present disclosure. As shown in FIG3 , the method can be applied to the user equipment 120. The method includes:

[0051] Step S300: Send radio link failure RLF prediction information based on artificial intelligence / machine learning AI / ML model prediction, wherein the RLF prediction information includes at least one of the following: model ID, RLF type, RLF time, prediction accuracy, identification ID corresponding to the predicted RLF, and serving cell radio resource management RRM measurement result predicted before the RLF occurs.

[0052] FIG4 illustrates one of the flow charts of the wireless communication method provided by the present disclosure. As shown in FIG4 , the method can be applied to the first base station 110. The method includes:

[0053] Step S400: Receive radio link failure (RLF) prediction information based on an artificial intelligence / machine learning (AI / ML) model, wherein the RLF prediction information includes at least one of the following: a model ID, an RLF type, an RLF time, a prediction accuracy, an identification ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result before the RLF occurs.

[0054] Specifically, the RLF type refers to a predicted RLF type, such as a random access problem, a T310 / T312 timeout, an RLC reaching a maximum number of retransmissions, a listen-before-talk failure (LBT failure), and the like.

[0055] RLF time: It indicates how long it is likely to occur RLF. The time can be a range, such as 10s-20ms.

[0056] Prediction accuracy refers to the precision of the prediction results, such as the time error of RLF occurrence.

[0057] The predicted serving cell radio resource management (RRM) measurement result before the RLF occurs can help the gNB determine in advance whether the user equipment 120 has an RLF, so that a handover can be made at the most appropriate time to hand over the user equipment 120 to a cell where the RLF will not occur.

[0058] The identification ID corresponding to the predicted RLF corresponds to the predicted RLF and is used to identify the RLF prediction information obtained by a specific prediction.

[0059] In the embodiment of the present disclosure, the user equipment 120 sends radio link failure RLF prediction information predicted based on the artificial intelligence / machine learning AI / ML model to the first base station 110, which on the one hand improves the probability of successful switching, and on the other hand enables the first base station 110 to better predict the radio link failure of the user equipment 120, avoid RLF, and improve user experience.

[0060] In order to prevent the user equipment 120 from failing when the RLF is imminent, the first base station 110 may configure the user equipment 120 to report a measurement result when reporting the RLF prediction information.

[0061] In some embodiments, before the user equipment 120 sends the radio link failure RLF prediction information predicted based on the artificial intelligence / machine learning AI / ML model to the first base station 110, the user equipment 120 also receives configuration information sent by the first base station 110.

[0062] Specifically, the configuration information includes at least one of the following:

[0063] (1) Time intervals and / or user equipment 120 reporting measurement results of several cells;

[0064] Specifically, the first base station 110 configures the user equipment 120 to report the time interval T1 and / or measurement results of several cells. For example, the first base station 110 can configure the user equipment 120 to report the serving cell and the measurement results of other cells, and let the user equipment 120 carry these measurement values ​​in the RLF prediction information. The user equipment 120 can report the RLF prediction information of these measurement values ​​to the first base station 110 at a time interval T1 before the occurrence of the RLF.

[0065] (2) reporting RLF prediction information at a time interval and / or when a measurement event is satisfied; wherein the measurement event is used to trigger the sending of the RLF prediction information, wherein the measurement event includes at least one of the following: A1 event, A2 event, A3 event, A4 event, A5 event, A6 event, B1 event, and B2 event.

[0066] Specifically, the first base station 110 configures the user equipment 120 to report RLF prediction information only after a specific measurement event is met. In one implementation, the user equipment 120 may report the RLF prediction information carrying these measurement values ​​to the first base station 110 at a time interval T1 before the occurrence of the RLF. The measurement event adopts an existing measurement event, and a specific measurement event is configured as a triggering condition for reporting RLF prediction information. Event A1 is when the serving cell measurement result is above the threshold, event A2 is when the serving cell measurement result is below the threshold, event A3 is when the neighboring cell measurement result is higher than the serving cell measurement result + offset, event A4 is when the neighboring cell measurement result is above the threshold, event A5 is when the serving cell measurement result is below the threshold and the neighboring cell measurement result is above the threshold, event A6 is when the neighboring cell measurement result is higher than the Scell ​​measurement result + offset, event B1 is when the inter-system cell measurement result is above the threshold, and event B2 is when the inter-system cell measurement result is above the threshold and the special cell (SPcell) measurement result is below the threshold.

[0067] (3) Time interval and / or indication of N cells reported, where N is greater than or equal to 1.

[0068] Specifically, the first base station 110 configures the user equipment 120 to report RLF prediction information T1 in advance and allows the user equipment 120 to report a number of target cells (target cell(s)). In this implementation, the gNB's measurement configuration does not trigger RRM measurement reporting for the user equipment 120. However, if the user equipment 120 predicts an imminent RLF, it may wish for the network-side equipment (e.g., the first base station 110) to quickly handover it to another cell. In this case, a measurement report can be configured such that, when the user equipment 120 predicts an RLF, the predicted RLF time is advanced by T1. This allows the N cells with the best signals to be selected as candidate cells for handover. This allows the gNB to handover the user equipment to the candidate cells after reporting the RLF prediction information.

[0069] In some embodiments, the user equipment 120 receives configuration information sent by the first base station 110, and the configuration information includes measurement results of several cells reported by the user equipment 120. Then, the radio link failure RLF prediction information sent by the user equipment 120 based on artificial intelligence / machine learning AI / ML model prediction also includes predicted neighboring cell RRM measurement results.

[0070] Specifically, the predicted neighboring cell RRM measurement result refers to the RRM of the neighboring cell at the current moment. Which neighboring cells are specifically reported depends on the configuration information, such as cell 1 (cell1) and cell 2 (cell2). Figure 5 is a schematic diagram of signaling interaction of a wireless communication method provided by the present disclosure. As shown in Figure 5, the method may include:

[0071] Step S501: The gNB sends configuration information (e.g., RLF prediction configuration: RLF prediction config (cell1, cell2)). The configuration information includes the user equipment 120 reporting measurement results of several cells, such as the RRM measurement results of the serving cell, neighbor cell 1 (cell1), and neighbor cell 2 (cell2) as one of the configuration parameters reported in the RLF prediction information.

[0072] Step S502: The user equipment 120 sends RLF prediction information to the gNB. The RLF prediction information includes any one of the following: RLF type, RLF time, prediction accuracy, an identifier ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result and a predicted neighboring cell RRM measurement result before the RLF occurs.

[0073] In an embodiment of the present disclosure, the user equipment 120 reports measurement results of several cells based on the user equipment 120 configured by the first base station 110, and sends radio link failure RLF prediction information including predicted neighboring cell RRM measurement results predicted based on an artificial intelligence / machine learning AI / ML model to the first base station 110. The first base station 110 can switch to a neighboring cell with better RRM measurement results before RLF occurs, thereby avoiding RLF and improving user experience.

[0074] It should be noted that FIG5 may be part of the steps of signaling interaction between the first base station 110 and the user equipment 120 in the wireless communication method, or may be an independent solution.

[0075] In some embodiments, the user equipment 120 receives configuration information sent by the first base station 110, and the configuration information includes reporting RLF prediction information when a measurement event is met. Then, the radio link failure RLF prediction information based on artificial intelligence / machine learning AI / ML model prediction sent by the user equipment 120 also includes RRM measurement results of the serving cell and / or neighboring cell.

[0076] Specifically, the RRM at the current moment may be the RRM of the neighboring cell and / or the RRM of the serving cell at the current moment, depending on the configuration of the first base station 110. Which RRM measurement events the user equipment 120 reports depends on the configuration information. For example, the configuration information is an A4 measurement event, so when the A4 measurement event is met, RLF prediction information is reported. FIG6 is a schematic diagram of signaling interaction of a wireless communication method provided by the present disclosure. As shown in FIG6, the method includes:

[0077] Step S601: The first base station 110 sends configuration information to the user equipment 120. For example, an A4 measurement event is configured as a trigger condition. The gNB configures the reference signal receiving power (RSRP) threshold of cell 1 to be higher than -26dBm. In this case, the user equipment 120 will report RLF prediction information only when the RSRP of cell 1 is higher than -26dBm.

[0078] Step S602 : The user equipment 120 sends RLF prediction information to the first base station 110 .

[0079] In an embodiment of the present disclosure, the user equipment 120 reports RLF prediction information when the user equipment 120 reports a measurement event based on the configuration of the first base station 110, and sends radio link failure RLF prediction information including the RRM measurement result at the current moment predicted based on the artificial intelligence / machine learning AI / ML model to the first base station 110. The first base station 110 can switch to a neighboring area with a better RRM measurement result before the measurement event that causes the RLF occurs, thereby avoiding RLF and improving user experience.

[0080] It should be noted that FIG6 may be part of the steps of signaling interaction between the first base station 110 and the user equipment 120 in the wireless communication method, or may be an independent solution.

[0081] In some embodiments, the user equipment 120 receives configuration information sent by the first base station 110, where the configuration information includes a time interval and / or an indication of N cells to be reported, where N is greater than or equal to 1; then, the radio link failure RLF prediction information based on artificial intelligence / machine learning AI / ML model prediction sent by the user equipment 120 also includes the RRM measurement result of the best candidate neighboring cell before the radio link failure occurs.

[0082] Specifically, the RRM measurement result of the best candidate neighboring cell before the radio link failure occurs refers to the N cells indicated for reporting in the configuration information. The N cells indicated for reporting are the N neighboring cells with the best signal quality (BestNeighNo) in the embodiment of the present disclosure. For example, if N is 3, the user equipment 120 will report the three neighboring cells with the best signal quality to the first base station 110. In this way, the user equipment 120 can switch from the serving cell to the neighboring cell in advance, thereby preparing to avoid RLF. Figure 7 is a signaling interaction diagram of a wireless communication method provided by the present disclosure. As shown in Figure 7, the method includes:

[0083] Step S701: the first base station 110 may configure N (N is 3, for example) to the user equipment 120.

[0084] Step S702 : The user equipment 120 sends RLF prediction information to the first base station 110 .

[0085] In an embodiment of the present disclosure, the user equipment 120 sends radio link failure RLF prediction information including the RRM measurement result of the best candidate neighboring cell before the radio link failure occurs, which is predicted based on the artificial intelligence / machine learning AI / ML model, based on the reporting time interval of the user equipment 120 configured by the first base station 110 and / or the N cells indicated for reporting. The first base station 110 can switch to the neighboring cell with the best signal quality before the RLF, thereby avoiding the RLF and improving the user experience.

[0086] It should be noted that FIG. 7 may be part of the steps of signaling interaction between the first base station 110 and the user equipment 120 in the wireless communication method, or may be an independent solution.

[0087] In some embodiments, the method comprises:

[0088] Step C1 (i.e., step S801): the user equipment 120 reports auxiliary information to the first base station 110, wherein the auxiliary information includes a constant list and a timer list; the constant list and the timer list are determined based on the AI / ML model;

[0089] Step C2: The user equipment 120 receives the configuration information sent by the first base station 110;

[0090] Step C3: The user equipment 120 sends radio link failure (RLF) prediction information based on the artificial intelligence / machine learning (AI / ML) model prediction to the first base station 110 .

[0091] Specifically, the user equipment 120 reports the auxiliary information to the first base station 110 (ie, step S801), as shown in Figure 8. Since the parameters related to RLF detection include the following:

[0092] As can be seen from the above parameters related to RLF detection, T310, T311, N310, and N311 are parameters that the network configures for the user equipment 120 to perform RLF and RLF recovery. The user equipment 120 can generate a timer list (preferred timer list) and a constant list (preferred counter list) based on the AI / ML model and provide them to the network (e.g., the first base station 110) so that the network can better train the mobility management model. The preferred timer list includes one or more of the above timers T310 and T311, and the preferred counter list includes one or more of the above constants N310 and N311.

[0093] In some embodiments, the method comprises:

[0094] Step D1 (i.e., step S901): the user equipment 120 reports capability information to the first base station 110, where the capability information is used to indicate the ability of the user equipment 120 to support RLF prediction based on the AI / ML model;

[0095] Step D2: The user equipment 120 receives the configuration information sent by the first base station 110;

[0096] Step D3: The user equipment 120 sends radio link failure (RLF) prediction information based on the artificial intelligence / machine learning (AI / ML) model prediction to the first base station 110 .

[0097] Specifically, the user equipment 120 reports capability information to the first base station 110, i.e., step S901, as shown in FIG9 . Because the AI / ML model requires computing resources on the user equipment 120 side, some user equipment 120 on the network side (e.g., the first base station 110) may support RLF prediction information obtained based on the AI / ML model, while some user equipment 120 may not. Alternatively, different user equipment 120 may have significantly different capabilities for supporting RLF prediction information obtained based on the AI / ML model. Therefore, to support RLF prediction information, the gNB needs to know whether the user equipment 120 is capable of supporting RLF prediction information obtained based on the AI / ML model. This allows the gNB to provide appropriate configurations to the user equipment 120. The capability information based on RLF prediction information reported by the user equipment 120 to the network side equipment (gNB, core network element, third-party equipment, etc.) includes at least one or more of the following information:

[0098] RLF prediction support: describes the ability of the user equipment 120 to support handover failure prediction, including whether the user equipment 120 supports the ability to predict when the RLF prediction information appears. The information may further include node information and / or resource information and / or AI / ML model information, wherein the node information is used to describe that the ability to predict RLF only supports the prediction capability for specific nodes, and the resource information is used to describe that the ability to predict RLF only supports the prediction capability for specific resources. It should be noted that the node information described here may include cell identifiers (Cell ID), transmission and receiving point identifiers (TRP ID), tracking area identifiers (TAID), scenario identifiers (Scenario ID), area identifiers (Area ID), etc. The node may include at least one of the following: cell (Cell), transmission and receiving point (Transmission and Receiving Point), tracking area (TA), scenario (Scenario), area (Area); resource information may include beam information, bandwidth information, frequency information, etc.

[0099] It should be noted that all of the above capabilities may further include predicting time, that is, the ability to predict the start time and end time of the time range of an event.

[0100] It should be noted that all of the above capabilities may further include accuracy, that is, the probability of predicting an event, 10%, 20%, 30%...

[0101] It should be noted that for all the above capabilities, if they include both area ID and cell ID, it means that the supported capability is valid in a specific area ID or for a specific cell ID.

[0102] It should be noted that, before receiving the configuration information sent by the first base station 110 , the user equipment 120 may receive the auxiliary information and the capability information simultaneously.

[0103] On the other hand, when RLF occurs, the user equipment 120 can send the RLF event as a key performance indicator (KPI) to the network side device (such as the first base station 110), so as to better train the model.

[0104] In some embodiments, in addition to the steps described above, the wireless communication method may also include the following steps: the user equipment 120 reports a report on performance monitoring of the RLF prediction information to the first base station 110, wherein the report on performance monitoring of the RLF prediction information includes at least one of the following: service interruption time, time from predicted RLF to occurrence of RLF, RLF cause, identification ID corresponding to the predicted RLF, and information that RLF did not occur.

[0105] Specifically, the service interruption time refers to the service interruption time from the occurrence of RLF to the successful re-establishment of RRC. The identifier ID corresponding to the predicted RLF corresponds to the predicted RLF and is used to identify the RLF prediction information obtained from a specific prediction. The information that no RLF occurred indicates that no RLF occurred. The RLF cause includes at least one of the following: listen-before-talk failure, multiple out-of-sync states, and RLC reaching the maximum number of retransmissions.

[0106] In some embodiments, in addition to the steps described above, the wireless communication method may further include a step of receiving a first trigger condition indicator, where the first trigger condition indicator is used to instruct the first base station 110 to reestablish a connection after the user equipment 120 has an RLF.

[0107] Optionally, the first base station 110 to which the user equipment 120 reestablishes a connection after an RLF occurs is the first base station 110 to which the user equipment 120 was connected before the RLF occurs.

[0108] Optionally, the configuration information further includes a first timer, and the method further includes starting the first timer.

[0109] Optionally, the report for performing performance monitoring on the RLF prediction information is a report for performing performance monitoring on the RLF prediction information when RLF occurs in the first timer.

[0110] Because TS38.331 only defines the conditions for user equipment 120 to detect RLF, first base station 110 cannot promptly detect when user equipment 120 has experienced RLF. From an implementation perspective, first base station 110 can only determine when user equipment 120 has experienced RLF based on retransmissions in Radio Link Control Reliable Mode (RLC AM). Therefore, the time when first base station 110 determines that user equipment 120 has experienced RLF is not accurate. Therefore, even if RLF occurs, user equipment 120 must report a performance monitoring report (key performance indicator (KPI)) of the RLF prediction information to the network.

[0111] Taking scenario 1 (user equipment 120 ultimately fails to avoid RLF and RLF still occurs) as an example, the steps in the above wireless communication method (as shown in FIG10 ) are described:

[0112] Step S1001: The first base station 110 configures a first timer T11 for the user equipment 120;

[0113] Step S1002: The user equipment 120 reports RLF prediction information and starts a first timer T11;

[0114] Step S1003: If RLF occurs in the user equipment 120 before the first timer T11 expires, the user equipment 120 reports a performance monitoring report on the RLF prediction information (service interruption time, time from predicted RLF to occurrence of RLF, RLF cause, and identification ID corresponding to the predicted RLF), where the identification ID corresponding to the predicted RLF is used to identify the predicted RLF corresponding to the information that no RLF has occurred.

[0115] It should be noted that FIG10 may be part of the steps of signaling interaction between the first base station 110 and the user equipment 120 in the wireless communication method, or may be an independent solution.

[0116] Optionally, the first base station 110 with which the user equipment 120 reestablishes the connection after the RLF occurs is a neighboring base station corresponding to the user equipment 120 before the RLF occurs.

[0117] Optionally, the report of performance monitoring of the RLF prediction information further includes an RRM measurement result when RLF occurs.

[0118] If UE 120 is capable of predicting RLF, this is a UE 120-side model. UE 120 expects to receive feedback from the network to update and retrain its own model. UE 120 itself knows whether RLF has occurred, so there is no need to notify UE 120 of the RLF event.

[0119] To ensure that the gNB can preemptively handover the user equipment 120 before an RLF occurs, the gNB should be aware of the RRM result before the RLF occurs. This allows the gNB to handover the user equipment 120 before the RLF occurs the next time the user equipment 120 is encountered. However, based on a normal measurement event, since the user equipment 120 is not at the cell edge, the location where the RLF occurs is a coverage hole. Therefore, the user equipment 120 must report the RRM result at the time of the RLF.

[0120] Now, taking scenario 1 (user equipment 120 ultimately fails to avoid RLF and RLF still occurs) as an example, the steps in the above wireless communication method are described (as shown in FIG11 ):

[0121] Step S1101: The user equipment 120 re-establishes the radio resource control (RRC) with the second base station (i.e., the base station after the handover) (service interruption time, time from predicted RLF to occurrence of RLF, RLF cause, radio resource management (RRM) when the RLF occurs, and an identifier ID corresponding to the predicted RLF). The identifier ID corresponding to the predicted RLF is used to identify the predicted RLF corresponding to the information that the RLF did not occur.

[0122] Step S1102: The second base station 140 sends an Xn message (user equipment 120 identification ID, time from predicted RLF to occurrence of RLF, RLF cause, radio resource management RRM when RLF occurs, service interruption time and identification ID corresponding to the predicted RLF) to the first base station 110 (i.e., the source base station before switching).

[0123] It should be noted that FIG11 only shows some steps of signaling interaction between the base station and the user equipment 120 in the wireless communication method.

[0124] In some embodiments, in addition to the steps described above, the wireless communication method further includes receiving a second trigger condition indicator, where the second trigger condition indicator is used to indicate whether handover occurs during the process of the user equipment 120 avoiding RLF.

[0125] Optionally, the method further includes receiving a second trigger condition indicator, where the second trigger condition indicator is used to indicate whether handover occurs in the process of the user equipment 120 avoiding RLF.

[0126] Optionally, when the second trigger condition indicator indicates that no handover occurs in the process of the user equipment 120 avoiding RLF (that is, no RLF event occurs and the RLF is successfully avoided), the configuration information further includes a second timer.

[0127] Optionally, the report for performance monitoring of the RLF prediction information is a report for performance monitoring of the RLF prediction information when the second timer times out and RLF does not occur. If RLF does not occur in the second timer, it is determined that RLF does not occur, and the user equipment 120 reports a report for performance monitoring of the RLF prediction information (performance KPI that RLF does not occur) to the network, and the user equipment 120 does not have to wait for whether RLF occurs.

[0128] Taking scenario 2 (if the user equipment 120 successfully predicts RLF and avoids RLF by early switching; or RLF does not occur in the current cell) as an example, the steps in the above wireless communication method are described (as shown in FIG12 ):

[0129] Step S1201: The first base station 110 configures a second timer (T12 timer) for the user equipment 120 as a condition for the terminal to report a performance monitoring report on the RLF prediction information (RLF prediction performance);

[0130] Step S1202: The user equipment 120 reports RLF prediction information;

[0131] Step S1203: When RLF still does not occur after T1 times out, the user equipment 120 reports a performance monitoring report on the RLF prediction information (RLF prediction performance report and an identifier ID corresponding to the predicted RLF) to the first base station 110, indicating that RLF has not occurred, wherein the identifier ID corresponding to the predicted RLF is used to identify the predicted RLF corresponding to the information that RLF has not occurred.

[0132] It should be noted that FIG12 may be part of the steps of signaling interaction between the first base station 110 and the user equipment 120 in the wireless communication method, or may be an independent solution.

[0133] Optionally, when the second trigger condition indicator instructs the user equipment 120 to avoid handover during the RLF process, the report on the performance monitoring of the RLF prediction information further includes a source cell ID.

[0134] When user equipment 120 reports RLF prediction information to first base station 110 (serving base station), but RLF does not occur, and instead first base station 110 (serving base station) hands over user equipment 120 to second base station 140 (neighboring base station), user equipment 120 should report a performance monitoring report on the RLF prediction information to the network (performance KPI for no RLF). However, at this time, user equipment 120 has already handed over to second base station 140 (neighboring base station), so a performance monitoring report on the RLF prediction information (RLF avoided due to handover) should be reported to second base station 140 (neighboring base station). Then, second base station 140 (neighboring base station) reports a performance monitoring report on the RLF prediction information (RLF avoided due to handover) to first base station 110 (serving base station).

[0135] Now, the steps in the above wireless communication method are described as follows (as shown in FIG13 ) using scenario 2 (if the user equipment 120 successfully predicts RLF and avoids RLF by early switching; or if RLF does not occur in the current cell):

[0136] Step S1301: The user equipment 120 carries information that no RLF has occurred, an identifier corresponding to the predicted RLF, and a source cell ID in a radio resource control (RRC) message, so that the second base station 140 knows that the user equipment 120 has not experienced the RLF corresponding to the identifier corresponding to the predicted RLF.

[0137] Step S1302: After receiving the report sent by the user equipment 120 that no RLF has occurred, the second base station 140 forwards the user equipment 120 identifier (UE ID), the information that no RLF has occurred, and the identifier ID corresponding to the predicted RLF in an Xn message, wherein the identifier ID corresponding to the predicted RLF is used to identify the predicted RLF corresponding to the information that no RLF has occurred, so that the base station can make adjustments.

[0138] It should be noted that FIG13 may be part of the steps of signaling interaction between the base station and the user equipment 120 in the wireless communication method, or may be an independent solution.

[0139] Described herein is a method for wireless communication, applicable, for example, to communication between user equipment 120 and a base station. However, these inventive concepts, methods, apparatuses, devices, computer-readable storage media, chips, and computer program products are not limited to 5G NR communication but can be extended to other communication scenarios to achieve the same technical benefits and effects.

[0140] In these scalable communication scenarios, user equipment 120 (UE) refers to a device used for communication at the user end, such as a mobile phone. It can also be called a terminal, mobile station, or mobile terminal. UE can be a variety of devices, including but not limited to mobile phones, tablets, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals for industrial control, wireless terminals for autonomous driving, wireless terminals for remote medical surgery, wireless terminals for smart grids, wireless terminals for environmental monitoring, wireless terminals for smart cities, and wireless terminals for smart homes.

[0141] Furthermore, UEs and base stations can be deployed in different environments, including but not limited to indoors, outdoors, as handheld devices, in vehicles, or even on water, in the air, on airplanes, drones, or satellites.

[0142] Therefore, although this document describes methods and devices for wireless communication, the inventive concepts and technologies contained therein can be extended to other communication scenarios and are expected to achieve the same technical benefits and effects. It is easy to understand that these inventive concepts have broad applicability and scalability, whether in communication between different types of base stations and user equipment 120, or in communication in different deployment environments.

[0143] It should be noted that the above steps are merely examples and do not limit the scope of the present invention. Various modifications and variations can be made to the steps without departing from the spirit and scope of the present invention.

[0144] The order of the described steps (signaling / boxes) is not intended to be construed as a limitation, and any number of the described steps (signaling / boxes) may be skipped or combined in any order to implement a method or an alternative method.

[0145] The present disclosure describes examples of communication between terminals and network element components in a network architecture in the above embodiments, which are mainly for illustrative purposes and not restrictive.

[0146] The order of the steps (signaling / boxes) described is not intended to be interpreted as limiting, and any number of the steps (signaling / boxes) described can be skipped or combined in any order to implement a method or alternative method. Typically, any of the components, modules, methods, and operations described herein can be implemented using software, firmware, hardware (e.g., fixed logic circuitry), manual processing, or any combination thereof. Some operations of the example methods can be described in the general context of executable instructions stored on a computer-readable memory locally and / or remotely on a computer processing system, and implementation methods can include software applications, programs, functions, and the like. Alternatively or in addition, any function described herein can be performed, at least in part, by one or more hardware logic components, such as, but not limited to, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), an application specific standard product (ASSP), a system on a chip (SoC), a complex programmable logic device (CPLD), and the like.

[0147] In addition, the signaling described in the embodiments of the present disclosure can be implemented in any manner known in the art. For example, the signaling can be explicit and / or implicit. In addition, the steps (signaling / frames) shown are for illustrative purposes only and are not intended to limit the present application.

[0148] FIG14 is a schematic structural diagram of a wireless communication device 900 provided by the present disclosure. The wireless communication device includes: a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory, and perform the following operations:

[0149] Send radio link failure (RLF) prediction information based on artificial intelligence (AI) / machine learning (ML) model predictions, where the RLF prediction information includes at least one of the following: model ID, RLF type, RLF time, prediction accuracy, an identification ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result before the RLF occurs.

[0150] and

[0151] Receive radio link failure (RLF) prediction information based on an artificial intelligence / machine learning (AI / ML) model, where the RLF prediction information includes at least one of the following: a model ID, an RLF type, an RLF time, a prediction accuracy, an identification ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result before the RLF occurs.

[0152] The wireless communication device may be a user device 120, a base station, or a network element. The wireless communication device 900 shown in FIG14 includes a processor 910. The processor 910 may call and run a computer program from a memory to implement the method in an embodiment of the present application.

[0153] Optionally, as shown in FIG14 , the wireless communication device 900 may further include a memory 920. The processor 910 may call and execute a computer program from the memory 920 to implement the method in the embodiment of the present application. The memory 920 may be a separate device independent of the processor 910 or may be integrated into the processor 910.

[0154] Optionally, as shown in FIG14 , the wireless communication device 900 may further include a transceiver 930. The processor 910 may control the transceiver 930 to communicate with other devices. Specifically, the transceiver 930 may send information or data to other devices or receive information or data sent by other devices. The transceiver 930 may include a transmitter and a receiver. The transceiver 930 may further include one or more antennas.

[0155] Optionally, the wireless communication device 900 may specifically be a base station in an embodiment of the present application, and the wireless communication device 900 may implement the corresponding processes implemented by the base station in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0156] Optionally, the wireless communication device 900 may specifically be the mobile user device 120 / user device 120 of an embodiment of the present application, and the wireless communication device 900 may implement the corresponding processes implemented by the mobile user device 120 / user device 120 in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0157] Optionally, the wireless communication device 900 may specifically be a network element in an embodiment of the present application, and the wireless communication device 900 may implement the corresponding processes implemented by the network element in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0158] According to an example embodiment, a chip is provided, comprising: a processor for calling and running a computer program from a memory, so that a device equipped with the chip executes a method according to any one of the above embodiments, examples, or exemplary embodiments.

[0159] According to an example embodiment, there is provided a computer-readable storage medium for storing a computer program, wherein the computer program causes a computer to execute a method according to any one of the above-mentioned embodiments, examples, or exemplary embodiments.

[0160] According to an example embodiment, a computer program product is provided, comprising a computer program / instruction, which, when executed by a processor (e.g., by the processor or an apparatus, device, computer or machine including the processor), implements a method according to any one of the above-mentioned embodiments, examples, or example embodiments.

[0161] The embodiments of the present disclosure are a combination of techniques / processes that may be employed in 3GPP specifications to create a final product.

[0162] While the present disclosure has been described in connection with what is considered to be the most practical and preferred embodiment, it is to be understood that the disclosure is not limited to the disclosed embodiment, but is intended to cover various arrangements embodied within the broadest interpretation of the appended claims.

Claims

1. A wireless communication method, executed by a user equipment, the method comprising: Send radio link failure (RLF) prediction information based on artificial intelligence (AI) / machine learning (ML) model predictions, where the RLF prediction information includes at least one of the following: model ID, RLF type, RLF time, prediction accuracy, an identification ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result before the RLF occurs.

2. The method according to claim 1, wherein The model ID is used to identify the AI / ML model used to obtain the RLF prediction information; the RLF type refers to the predicted RLF type; the RLF time refers to how long it is predicted to take for the RLF to occur; the prediction accuracy refers to the accuracy of the prediction result; the identification ID corresponding to the predicted RLF is used to identify the RLF prediction information obtained from a specific prediction.

3. The method according to claim 1 or 2, wherein: The method further comprises: Receive configuration information.

4. The method according to claim 3, wherein: The configuration information includes a time interval and / or measurement results of several cells reported by the user equipment, and the RLF prediction information also includes a predicted neighboring cell RRM measurement result, where the predicted neighboring cell RRM measurement result refers to the RRM of the neighboring cell at the current moment.

5. The method according to claim 3, wherein The configuration information includes reporting RLF prediction information at a time interval and / or when a measurement event is met, wherein the measurement event is used to trigger the sending of the RLF prediction information, wherein the measurement event includes at least one of the following: an A1 event, an A2 event, an A3 event, an A4 event, an A5 event, an A6 event, a B1 event, and a B2 event.

6. The method according to claim 5, wherein: The RLF prediction information also includes the RRM measurement result at the current moment.

7. The method according to claim 3, wherein: The configuration information includes a time interval and / or indicates N cells to be reported, wherein N is greater than or equal to 1, and the N cells are N cells with the best signal quality.

8. The method according to claim 7, wherein: The RLF prediction information also includes RRM measurement results of the N best candidate neighboring cells before the radio link failure occurs.

9. The method according to any one of claims 1 to 8, wherein: The method further comprises: Reporting auxiliary information, wherein the auxiliary information includes a constant list and a timer list suggested by the user equipment; the constant list and the timer list are determined based on the AI / ML model.

10. The method according to claim 9, wherein: The timer list includes one or more of T310 and T311; the constant list includes one or more of N310 and N311.

11. The method according to any one of claims 1 to 10, wherein: The method further comprises: Report capability information, where the capability information is used to characterize the user equipment's ability to support RLF prediction based on AI / ML models.

12. The method according to claim 11, wherein The capability information includes at least one of the following: node information, resource information, and AI / ML model information. The node information is used to describe that the ability to predict RLF only supports prediction capabilities for specific nodes; the resource information is used to describe that the ability to predict RLF only supports prediction capabilities for specific resources; the AI / ML model information is a model ID, and the node includes at least one of the following: cell, sending and receiving point, tracking area, scene, and area.

13. The method according to any one of claims 1 to 12, wherein: The method further includes: reporting a report on performance monitoring of the RLF prediction information, wherein the report on performance monitoring of the RLF prediction information includes at least one of the following: service interruption time, time from predicted RLF to occurrence of RLF, RLF cause, an identification ID corresponding to the predicted RLF, and information that RLF did not occur, wherein the service interruption time refers to the service interruption time from the occurrence of RLF to the successful re-establishment of RRC.

14. The method according to claim 13, wherein: The RLF reason includes at least one of the following: listen-before-talk failure, several out-of-sync states, and RLC reaching the maximum number of retransmissions.

15. The method according to any one of claims 13 to 14, wherein: The method further includes: reporting a performance monitoring report on the RLF prediction information based on a first trigger condition, wherein the first trigger condition is that the user equipment successfully reestablishes to the first base station or the second base station after RLF occurs.

16. The method according to claim 15, wherein The first base station is a base station to which the user equipment is connected before the RLF occurs, the configuration information further includes a first timer, and the method further includes starting the first timer.

17. The method according to claim 16, wherein The method further includes submitting a report for performance monitoring of the RLF prediction information if RLF occurs before the first timer expires.

18. The method according to claim 15, wherein The second base station is a neighboring base station corresponding to the user equipment before the RLF occurs.

19. The method according to claim 18, wherein The report on the performance monitoring of the RLF prediction information also includes RRM measurement results when RLF occurs.

20. The method according to any one of claims 13-14, wherein: The method further includes: reporting a performance monitoring report on the RLF prediction information based on a second trigger condition, wherein the second trigger condition is that the user equipment does not switch and avoids RLF or the user equipment switches and avoids RLF through switching.

21. The method according to claim 20, wherein When the second trigger condition is that the user equipment does not undergo handover and RLF is avoided, the configuration information further includes a second timer.

22. The method according to claim 21, wherein The method further includes reporting information that no RLF has occurred when the second timer times out and no RLF has occurred.

23. The method according to claim 20, wherein When the second trigger condition is that handover occurs to the user equipment and RLF is avoided through handover, the source cell ID and / or the information that no RLF occurs is reported.

24. A wireless communication device, wherein: The wireless communication device includes: a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method according to any one of claims 1 to 23.

25. A wireless communication method, performed by a first base station, the method comprising: Receive radio link failure (RLF) prediction information based on an artificial intelligence / machine learning (AI / ML) model, where the RLF prediction information includes at least one of the following: a model ID, an RLF type, an RLF time, a prediction accuracy, an identification ID corresponding to the predicted RLF, and a predicted serving cell radio resource management (RRM) measurement result before the RLF occurs.

26. The method according to claim 25, wherein The model ID is used to identify the AI / ML model used to obtain the RLF prediction information; the RLF type refers to the predicted RLF type; the RLF time refers to how long it is predicted to take for the RLF to occur; the prediction accuracy refers to the accuracy of the prediction result; the identification ID corresponding to the predicted RLF is used to identify the RLF prediction information obtained from a specific prediction.

27. The method according to claim 25 or 26, wherein The method further comprises: Send configuration information.

28. The method according to claim 27, wherein The configuration information includes a time interval and / or measurement results of several cells reported by the user equipment, and the RLF prediction information also includes a predicted neighboring cell RRM measurement result, where the predicted neighboring cell RRM measurement result refers to the RRM of the neighboring cell at the current moment.

29. The method according to claim 27, wherein The configuration information includes reporting RLF prediction information at a time interval and / or when a measurement event is met, wherein the measurement event is used to trigger the sending of the RLF prediction information, wherein the measurement event includes at least one of the following: an A1 event, an A2 event, an A3 event, an A4 event, an A5 event, an A6 event, a B1 event, and a B2 event.

30. The method according to claim 29, wherein The RLF prediction information also includes the RRM measurement result at the current moment.

31. The method of claim 27, wherein: The configuration information includes a time interval and / or indicates N cells to be reported, wherein N is greater than or equal to 1, and the N cells are N cells with the best signal quality.

32. The method according to claim 31, wherein The RLF prediction information also includes RRM measurement results of the N best candidate neighboring cells before the radio link failure occurs.

33. The method according to any one of claims 25 to 32, wherein: The method further comprises: Receive auxiliary information, wherein the auxiliary information includes a constant list and a timer list suggested by a user equipment; the constant list and the timer list are determined based on an AI / ML model.

34. The method according to claim 33, wherein The timer list includes one or more of T310 and T311; the constant list includes one or more of N310 and N311.

35. The method according to any one of claims 25 to 34, wherein: The method further comprises: Receive capability information, where the capability information is used to characterize an ability of the user equipment to support RLF prediction based on an AI / ML model.

36. The method according to claim 35, wherein The capability information includes at least one of the following: node information, resource information, and AI / ML model information. The node information is used to describe that the ability to predict RLF only supports prediction capabilities for specific nodes; the resource information is used to describe that the ability to predict RLF only supports prediction capabilities for specific resources; the AI / ML model information is a model ID, and the node includes at least one of the following: cell, sending and receiving point, tracking area, scene, and area.

37. The method according to any one of claims 25 to 36, wherein: The method also includes: receiving a report on performance monitoring of the RLF prediction information, wherein the report on performance monitoring of the RLF prediction information includes at least one of the following: service interruption time, time from predicted RLF to occurrence of RLF, RLF cause, an identification ID corresponding to the predicted RLF, and information that RLF did not occur, wherein the service interruption time refers to the service interruption time from the occurrence of RLF to the successful re-establishment of RRC.

38. The method of claim 37, wherein: The RLF reason includes at least one of the following: listen-before-talk failure, several out-of-sync states, and RLC reaching the maximum number of retransmissions.

39. The method according to any one of claims 37-38, wherein: The method further includes: receiving a report on performance monitoring of the RLF prediction information based on a first trigger condition, wherein the first trigger condition is that the user equipment successfully reestablishes to the first base station or the second base station after RLF occurs.

40. The method of claim 39, wherein The first base station is a base station to which the user equipment is connected before the RLF occurs, the configuration information further includes a first timer, and the method further includes starting the first timer.

41. The method according to claim 40, wherein The method further includes receiving a report of performance monitoring of the RLF prediction information if RLF occurs before the first timer expires.

42. The method according to claim 41, wherein The second base station is a neighboring base station corresponding to the user equipment before the RLF occurs.

43. The method according to claim 42, wherein The report on performance monitoring of the RLF prediction information also includes an RRM measurement result when RLF occurs, and the method also includes receiving a first message based on the Xn interface sent by the second base station, the first message based on the Xn interface including an identification ID of the user equipment, a service interruption time, a time from the predicted RLF to the occurrence of the RLF, an RLF cause, an identification ID corresponding to the predicted RLF, and an RRM measurement result when the RLF occurs, wherein the identification ID of the user equipment is used to identify the user equipment that predicts the RLF prediction information.

44. The method according to any one of claims 37-38, wherein The method further includes: receiving a report on performance monitoring of the RLF prediction information based on a second trigger condition, wherein the second trigger condition is that the user equipment does not undergo handover and avoids RLF or that the user equipment undergoes handover and avoids RLF through handover.

45. The method of claim 44, wherein: When the second trigger condition is that the user equipment does not undergo handover and RLF is avoided, the configuration information further includes a second timer.

46. ​​The method of claim 45, wherein The method further includes, when the second timer times out and RLF does not occur, receiving an identification ID corresponding to the predicted RLF and / or information that the RLF does not occur.

47. The method according to claim 43 or 44, wherein When the second trigger condition is that the user equipment switches and RLF is avoided by switching, a second message based on the Xn interface sent by the second base station is received, and the second message includes at least one of the following: an identification ID of the user equipment, an identification ID corresponding to the predicted RLF, and the information that the RLF did not occur.

48. A wireless communication device, wherein: The wireless communication device includes: a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method according to any one of claims 25 to 47.

Images