Channel state adjustment method, and terminal device and network device
By training the model to predict RLF events and adjusting the channel state of the terminal device, the problem of long service interruption time caused by RLF in the communication system is solved, and the effect of reducing service interruption time is achieved.
Patent Information
- Application Number
- PCT/CN2023/097623
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-31
- Publication Date
- 2024-12-05
AI Technical Summary
In the communication system, if the channel status of the serving cell is not good, it may lead to RLF events, resulting in a long connection re-establishment process time and a long service interruption time. The prior art is difficult to effectively reduce the service interruption time caused by RLF.
By training a model based on RLF event-related, the RLF information at the current moment is predicted, and when the prediction information meets specific conditions, the channel state of the terminal device is adjusted, for example, through cell handover or adjustment of the motion trajectory, to avoid the occurrence of RLF events.
Accurate prediction of RLF events and channel state adjustment are realized, effectively reducing the number of RLF events and service interruption time.
Smart Images

Figure CN2023097623_05122024_PF_FP_ABST
Abstract
Description
Method for adjusting channel state, terminal device and network device Technical Field
[0001] The present application relates to the field of communications, and more specifically, to a method for adjusting channel status, a terminal device, a network device, a chip, a computer-readable storage medium, a computer program product, and a computer program. Background Art
[0002] In a communication system, if the channel status of the serving cell is poor, a Radio Link Failure (RLF) event may occur. This RLF event triggers a connection re-establishment. This connection re-establishment process takes a long time, resulting in a prolonged service interruption. Consideration should be given to reducing the service interruption caused by RLF.
[0003] Summary of the Invention
[0004] This embodiment of the present application provides a method for adjusting a channel state, including:
[0005] When the RLF prediction information satisfies a first condition, the terminal device performs a first process;
[0006] Among them, the RLF prediction information is obtained by processing the RLF associated data related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event; and the first processing is used to adjust the channel state of the terminal device.
[0007] This embodiment of the present application provides a method for adjusting a channel state, including:
[0008] When the RLF prediction information satisfies a first condition, the network device performs a first process;
[0009] Among them, the RLF prediction information is obtained by processing the RLF associated data of the terminal device related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event of the terminal device; the first processing is used to adjust the channel state of the terminal device.
[0010] An embodiment of the present application provides a terminal device, including:
[0011] A first processing module, configured to perform a first process when the RLF prediction information satisfies a first condition;
[0012] Among them, the RLF prediction information is obtained by processing the RLF associated data related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event; and the first processing is used to adjust the channel state of the terminal device.
[0013] An embodiment of the present application provides a network device, including:
[0014] A second processing module, configured to perform a first process when the RLF prediction information satisfies a first condition;
[0015] Among them, the RLF prediction information is obtained by processing the RLF associated data of the terminal device related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event of the terminal device; the first processing is used to adjust the channel state of the terminal device.
[0016] An embodiment of the present application provides a terminal device, 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, so that the terminal device executes the above-mentioned method for adjusting the channel state.
[0017] An embodiment of the present application provides a network device, 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, so that the network device executes the above-mentioned method for adjusting the channel state.
[0018] An embodiment of the present application provides a chip for implementing the above-mentioned method for adjusting the channel state.
[0019] Specifically, the chip includes: a processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned method for adjusting the channel state.
[0020] An embodiment of the present application provides a computer-readable storage medium for storing a computer program. When the computer program is executed by a device, the device executes the above-mentioned method for adjusting the channel state.
[0021] An embodiment of the present application provides a computer program product, including computer program instructions, which enable a computer to execute the above-mentioned method for adjusting the channel state.
[0022] An embodiment of the present application provides a computer program, which, when executed on a computer, enables the computer to execute the above-mentioned method for adjusting the channel state.
[0023] In this embodiment of the present application, a first model is trained using RLF-related data associated with a first RLF event, enabling the first model to learn the data characteristics of actual RLF events. Therefore, by processing the RLF-related data associated with the current moment using the first model, accurate RLF prediction information for the current moment can be obtained. When this RLF prediction information meets predetermined conditions, the channel state of the terminal device is adjusted by executing the first processing. By accurately predicting RLF events and adjusting the channel state based on the accurate prediction, the number of RLF events can be effectively reduced, thereby shortening the service interruption duration caused by RLF. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application.
[0025] FIG2 is a schematic diagram of a wireless link monitoring process.
[0026] FIG3 is a schematic diagram of traditional conditional switching.
[0027] FIG4 is a schematic flowchart of a method for adjusting channel status according to an embodiment of the present application.
[0028] FIG5 is a schematic flowchart of a method for adjusting channel status according to another embodiment of the present application.
[0029] FIG6A is a schematic diagram of conditional switching in an embodiment of the present application.
[0030] FIG6B is another schematic diagram of conditional switching in an embodiment of the present application.
[0031] FIG7 is a schematic block diagram of a terminal device according to an embodiment of the present application.
[0032] FIG8 is a schematic block diagram of a terminal device according to another embodiment of the present application.
[0033] FIG9 is a schematic block diagram of a terminal device according to another embodiment of the present application.
[0034] FIG10 is a schematic block diagram of a terminal device according to another embodiment of the present application.
[0035] FIG11 is a schematic block diagram of a terminal device according to another embodiment of the present application.
[0036] FIG12 is a schematic block diagram of a network device according to an embodiment of the present application.
[0037] FIG13 is a schematic block diagram of a network device according to another embodiment of the present application.
[0038] FIG14 is a schematic block diagram of a network device according to yet another embodiment of the present application.
[0039] FIG15 is a schematic block diagram of a network device according to another embodiment of the present application.
[0040] FIG16 is a schematic block diagram of a network device according to yet another embodiment of the present application.
[0041] FIG17 is a schematic structural diagram of a communication device according to an embodiment of the present application.
[0042] FIG18 is a schematic structural diagram of a chip according to an embodiment of the present application.
[0043] FIG19 is a schematic block diagram of a communication system according to an embodiment of the present application. DETAILED DESCRIPTION
[0044] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0045] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity) system. Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system or other communication systems, etc.
[0046] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) and other terminal-to-terminal direct communications, and the embodiments of the present application can also be applied to these communication systems.
[0047] In one embodiment, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, and a standalone (SA) networking scenario.
[0048] In one embodiment, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, wherein the authorized spectrum can also be considered as an unshared spectrum.
[0049] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.
[0050] The terminal device can be a station (STATION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.
[0051] In the embodiments of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.) or underwater (such as submarines, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).
[0052] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a terminal device in the personal internet of things (PIoT), a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.
[0053] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.
[0054] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.
[0055] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.
[0056] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
[0057] FIG1 exemplarily illustrates a communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one possible implementation, the communication system 100 may include multiple network devices 110, and each network device 110 may include a different number of terminal devices 120 within its coverage area, which is not limited in this embodiment of the present application.
[0058] In one possible implementation, the communication system 100 may further include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which is not limited in this embodiment of the present application.
[0059] Among them, the network equipment may include access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks for communicating with the access network equipment. The access network equipment can be an evolutionary base station (evolutional node B, abbreviated as eNB or e-NodeB) macro base station, micro base station (also called "small base station"), pico base station, access point (AP), transmission point (TP) or new generation base station (new generation Node B, gNodeB), etc. in a long-term evolution (LTE) system, a next-generation (mobile communication system) (next radio, NR) system or an authorized auxiliary access long-term evolution (LAA-LTE) system.
[0060] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system shown in Figure 1 as an example, the communication device may include a network device and a terminal device having a communication function. The network device and the terminal device may be specific devices in the embodiments of the present application and will not be described in detail here. The communication device may also include other devices in the communication system, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.
[0061] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.
[0062] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.
[0063] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.
[0064] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.
[0065] (1) RLF
[0066] A UE in the RRC (Radio Resource Control) connected state (i.e., RRC_CONNECTED state) will continuously monitor the downlink radio link quality of the serving cell during mobility. The network will determine the synchronization and desynchronization status of the channel based on the signal quality of the SSB (Synchronization Signal Block) or CSI-RS (Channel State Information Reference Signal).
[0067] Figure 2 shows a schematic diagram of the radio link monitoring process. During the radio problem detection phase, when the BLER (block error rate) of N310 consecutively monitored PDCCHs (Physical Downlink Control Channels) is greater than 10%, it is considered that a desynchronization has occurred. As shown in Figure 2, the T310 timer is started, where N310 is a set value configured by the network. Before the T310 timer expires, if the BLER of N311 consecutively detected PDCCHs is less than 2%, it is considered that the signal has been resynchronized, the T310 timer is stopped, and the UE's radio link is restored, where N311 is a set value configured by the network. Otherwise, when the T310 timer expires, it is determined that a radio link failure has occurred, triggering the UE's RLF declaration and the connection re-establishment process.
[0068] (2) Reporting of Failure Events
[0069] When the UE encounters RLF, the UE will record the RLF-related information in the RLF report (VarRLF-Report). The RLF report includes RLF-Report-r16 and PLMN-IdentityList2-r16. The RLF-Report-r16 includes the global cell ID and tracking area code of the serving cell, the RSRP (Reference Signal Receiving Power) of the serving / neighboring cell, RSRQ (Reference Signal Receiving Quality), SINR (Signal to Interference plus Noise Ratio) information, the time from failure to reconnection, and location information. This information will be uploaded to the network side to help the network optimize switching parameters and detect coverage issues. The VarRLF-Report on the UE side will be released 48 hours after the RLF occurs.
[0070] (3) CHO (Conditional Handover)
[0071] Figure 3 is a schematic diagram of traditional conditional handover. Conditional handover is a handover mechanism. In conditional handover, the serving cell determines one or more candidate cells for conditional handover based on measurement reports (reported when RSRP falls below a preset threshold). After sending a handover request to the candidate cell and obtaining the candidate cell configuration information, the serving cell sends a conditional handover command to the UE. The UE determines whether the conditional handover triggering conditions (contained in the conditional handover command) are met based on the measurement results of the candidate cell. If a candidate cell is found to meet the handover conditions, it performs a subsequent random access procedure on that cell.
[0072] The triggering conditions for conditional switching can include one or more of the following five conditions:
[0073] Conditional event A3 (CondEvent A3): The measurement result of the conditional handover candidate cell is better than the measurement result of the PCell (Primary Cell) / PSCell (Primary Secondary Cell) by more than the set offset value;
[0074] Conditional event A4 (CondEvent A4): The measurement result of the conditional handover candidate cell is better than the set threshold;
[0075] Conditional event A5 (CondEvent A5): The measurement result of the PCell / PSCell is worse than the set threshold 1, and the measurement result of the conditional handover candidate cell is better than the set threshold 2;
[0076] Conditional event D1 (CondEvent D1): The distance between the UE and the reference location referenceLocation1 becomes greater than the configured threshold distance ThreshFromReference1, and the distance between the UE and the reference location referenceLocation2 of the conditional handover candidate cell becomes less than the configured threshold distance ThreshFromReference2;
[0077] Condition event T1 (CondEvent T1): The time measured by the UE is greater than the threshold t1 but less than (threshold t1 + duration).
[0078] CondEvent A3 and CondEvent A5 are applicable to all types of conditional handover. CondEvent A4, CondEvent D1, and CondEvent T1 are currently only applicable in NTN (Non-Terrestrial Networks) and CPC (Conditional PSCell Change) scenarios. In NTN, conditional handover can be configured with one or two trigger conditions. CondEvent T1 and CondEvent D1 must be configured together with one of CondEvent A3, A4, or A5. When two trigger conditions are configured, they must both be met to trigger the UE's random access procedure.
[0079] When conditional handover is configured with multiple candidate cells, the UE attempts to access one of them. However, if access fails due to channel deterioration, load balancing, or other reasons, the UE can reselect a candidate cell to attempt access. If it fails again, the conditional handover process fails, and the UE needs to perform a connection re-establishment process. Only two attempts are made because the candidate cell for conditional handover was configured some time ago based on the RSRP reported by the measurement. As the UE moves or the channel changes, the CHO configuration may become outdated. Frequent use of the candidate cell in the conditional handover command for random access may increase the service interruption time.
[0080] FIG4 is a schematic flow chart of a method for adjusting channel status according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes:
[0081] S410. When the RLF prediction information satisfies a first condition, the terminal device performs a first process.
[0082] Among them, the RLF prediction information is obtained by processing the RLF associated data related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event; and the first processing is used to adjust the channel state of the terminal device.
[0083] In an embodiment of the present application, the first model is an AI (Artificial Intelligence) model. For example, the first model can be a model that predicts the second RLF event by extracting data features from the first RLF event, such as a data feature extraction model. Alternatively, the first model can be a model trained through supervised training using data from the first RLF event and data from a period without RLF events, such as a time series prediction model. For example, the time series prediction model can include an LSTM (Long Short-Term Memory) model.
[0084] In an embodiment of the present application, the first model is trained and inferred using RLF-related data. RLF-related data represents a specific type of data used to predict RLF events. For example, RLF-related data may be data of a measurement result type, and the RLF-related data associated with the first RLF event may refer to the most recent measurement result of the reference signal when the first RLF event occurs (or the most recent measurement result of the reference signal obtained before the first RLF event occurs); the RLF data associated with the current moment may refer to the measurement result of the reference signal obtained at the current moment. The first RLF event is an RLF event that has actually occurred.
[0085] In the embodiment of the present application, the input information of the first model is RLF-related data, and the output information is RLF prediction information. The RLF prediction information may include any prediction information related to the RLF event, such as whether a second RLF event will occur, the probability of the second RLF event occurring, and the time of occurrence.
[0086] Exemplarily, the RLF prediction information may include: whether a second RLF event occurs within a first time window after the current moment; or the probability of a second RLF event occurring within the first time window. The length of the first time window may be predefined or configured by the network device. Optionally, the length of the first time window may be associated with the length of a second time window corresponding to the training data of the first model. For example, the RLF-related data associated with the first RLF event may be RLF-related data acquired within a second time window before the first RLF event occurs, where the length of the second time window is the same as the length of the first time window.
[0087] In an embodiment of the present application, the RLF prediction information may be obtained by the terminal device using the first model, or may be obtained by the network device using the first model.
[0088] In an embodiment of the present application, whether the RLF prediction information satisfies the first condition can be determined by the terminal device or by the network device. If the determination of whether the RLF prediction information satisfies the first condition is made by the network device, the network device can trigger the terminal device to perform the first processing. For example, the network device sends a determination result to the terminal device to trigger the terminal device to perform the first processing, or the network device schedules the terminal device to perform the first processing.
[0089] In an embodiment of the present application, the first processing may be any processing method for adjusting the channel state of the terminal device. Exemplarily, the first processing may include cell switching or adjusting the mobile mode. For example, in a case where the RLF prediction information indicates that a second RLF event will occur, the terminal device performs cell switching. In this way, by actively performing cell switching before the second RLF event occurs, the channel state of the terminal device can be adjusted to avoid the need to perform a more time-consuming connection re-establishment after the second RLF event occurs. For another example, in a case where the RLF prediction information indicates that a second RLF event will occur, for mobile terminal devices, such as UAVs (Unmanned Aerial Vehicles), etc., better channel conditions can be obtained by adjusting the motion trajectory.
[0090] In the method provided in the above embodiment, a first model is trained using RLF-related data associated with a first RLF event, enabling the first model to learn the characteristics of the RLF-related data corresponding to an actual RLF event. Therefore, by processing the RLF-related data relevant to the current moment using the first model, accurate RLF prediction information can be obtained for the current moment. When this RLF prediction information meets predetermined conditions, the terminal device adjusts its channel state by executing the first processing. By accurately predicting the RLF event and adjusting the channel state based on the accurate prediction, RLF events can be effectively avoided, reducing service interruptions caused by RLF.
[0091] In some embodiments, the RLF-related data includes at least one of the following:
[0092] Measurement results of the serving cell;
[0093] The identification of the serving cell;
[0094] Measurement results of neighboring cells;
[0095] Identification of adjacent cells;
[0096] Location-related information of the terminal device.
[0097] Accordingly, the RLF associated data related to the current moment includes at least one of the following: the measurement result of the service cell related to the current moment; the identifier of the service cell related to the current moment; the measurement result of the adjacent cell related to the current moment; the identifier of the adjacent cell related to the current moment; and the location-related information of the terminal device related to the current moment.
[0098] Similarly, the RLF-associated data related to the first RLF event includes at least one of the following: measurement results of the serving cell related to the first RLF event; an identifier of the serving cell related to the first RLF event; measurement results of the neighboring cell related to the first RLF event; an identifier of the neighboring cell related to the first RLF event; and location-related information of the terminal device related to the first RLF event.
[0099] In one embodiment, the RLF-associated data includes the measurement results of the serving cell and the identifier of the serving cell. The identifier may be a PCI (Physical Cell Identifier). In another embodiment, the RLF-associated data may further include the measurement results of neighboring cells and the location information of the terminal device. It should be noted that the setting of the RLF-associated data may not be limited to the above embodiment. For example, the RLF-associated data may also include only the measurement results of the serving cell. In specific implementation, it may be set according to the effect of the model, system requirements, or protocol agreements, etc., which are not exhaustively listed here.
[0100] In some embodiments, the above-mentioned measurement results may include at least one of RSRP, RSRQ and SINR. Exemplarily, the measurement result of the serving cell may include at least one of the RSRP of the serving cell, the RSRQ of the serving cell and the SINR of the serving cell, for example, including the RSRP of the serving cell and the RSRQ of the serving cell, or including the RSRP of the serving cell and the SINR of the serving cell. Similarly, the measurement result of the adjacent cell may include at least one of the RSRP of the adjacent cell, the RSRQ of the adjacent cell and the SINR of the adjacent cell, for example, including the RSRQ of the adjacent cell and the SINR of the serving cell, or including the RSRP of the serving cell and the SINR of the serving cell. In specific implementation, the measurement result may be set to include one or more of the above information according to the effect of the model, system requirements or protocol agreements, etc., and is not exhaustively listed here.
[0101] In some embodiments, the above-mentioned location-related information may include at least one of the location collection time, longitude and latitude information, and movement speed estimation information.
[0102] In some embodiments, the RLF-related data related to the current moment includes RLF-related data acquired at the current moment and / or RLF-related data acquired within a second time window before the current moment, where the second time window represents a time window with a predetermined duration.
[0103] Exemplarily, the RLF-related data obtained at the current moment may include at least one of the following: the measurement result of the service cell obtained at the current moment, the identifier of the service cell where the terminal device is located at the current moment, the measurement result of the adjacent cell obtained at the current moment, the identifier of the adjacent cell at the current moment, and the location-related information of the terminal device at the current moment.
[0104] Exemplarily, the RLF-related data obtained within the second time window before the current moment may include at least one of the following: measurement results of the serving cell obtained within the second time window before the current moment; identification of the serving cell within the second time window before the current moment; measurement results of the adjacent cell obtained within the second time window before the current moment; identification of the adjacent cell within the second time window before the current moment; and location-related information of the terminal device obtained within the second time window before the current moment.
[0105] It should be noted that, when the RLF associated data related to the current moment includes both the RLF associated data obtained at the current moment and the RLF associated data obtained within the second time window before the current moment, the RLF associated data obtained at the current moment and the RLF associated data obtained within the second time window before the current moment may be data of the same type or data of different types. For example, the RLF associated data related to the current moment includes the measurement result of the service cell obtained at the current moment, and the RLF associated data obtained within the second time window before the current moment includes the location-related information of the terminal device obtained within the second time window.
[0106] In one application example, the RLF-associated data includes a measurement result of a serving cell and location information of a terminal device. Accordingly, the RLF-associated data related to the current moment may include the measurement result of the serving cell and the location information of the terminal device at the current moment, or the measurement result of the serving cell and the location information of the terminal device within a second time window before the current moment, or the measurement result of the serving cell at the current moment and the location information of the terminal device within the second time window before the current moment.
[0107] In some embodiments, the RLF-related data related to the first RLF event includes the RLF-related data most recently acquired before the first RLF event occurs, and / or the RLF-related data acquired within a second time window before the first RLF event occurs.
[0108] Exemplarily, the RLF-related data most recently acquired before the occurrence of the first RLF event may include at least one of the following: the measurement result of the service cell most recently acquired before the occurrence of the first RLF event, the identifier of the service cell most recently acquired before the occurrence of the first RLF event, the measurement result of the adjacent cell most recently acquired before the occurrence of the first RLF event, the identifier of the adjacent cell most recently acquired before the occurrence of the first RLF event, and the location-related information of the terminal device most recently acquired before the occurrence of the first RLF event.
[0109] Exemplarily, the RLF-associated data obtained within the second time window before the first RLF event occurs may include at least one of the following: measurement results of the serving cell obtained within the second time window before the first RLF event occurs; identifier of the serving cell within the second time window before the first RLF event occurs; measurement results of the adjacent cell obtained within the second time window before the first RLF event occurs; identifier of the adjacent cell obtained within the second time window before the first RLF event occurs; location-related information of the terminal device obtained within the second time window before the first RLF event occurs.
[0110] It should be noted that, when the RLF-related data related to the first RLF event includes both the RLF-related data most recently acquired before the occurrence of the first RLF event and the RLF-related data acquired within the second time window before the occurrence of the first RLF event, the RLF-related data most recently acquired before the occurrence of the first RLF event and the RLF-related data acquired within the second time window before the occurrence of the first RLF event may be data of the same type or data of different types. For example, the RLF-related data most recently acquired before the occurrence of the first RLF event includes the measurement result of the service cell most recently acquired before the occurrence of the first RLF event, and the RLF-related data acquired within the second time window before the occurrence of the first RLF event includes the location-related information of the terminal device acquired within the second time window.
[0111] In one application example, the RLF data includes measurement results of the serving cell and location information of the terminal device. Accordingly, the RLF-associated data associated with the first RLF event may include the most recently acquired measurement results of the serving cell and the location information of the terminal device before the occurrence of the first RLF event, or the most recently acquired measurement results of the serving cell and the location information of the terminal device within the second time window, or the most recently acquired measurement results of the serving cell before the occurrence of the first RLF event and the location information of the terminal device within the second time window.
[0112] It should be noted that the measurement result of the serving cell and / or the measurement result of the neighboring cell within the second time window may include one or more measurement results of the reference signal, wherein the number of measurements is determined by the length of the second time window.
[0113] Optionally, the length of the second time window is configured by the network device. Further, the network device may send configuration information of the length of the second time window to the terminal device, so that the terminal device can determine the length and extract the RLF-related data within the second time window according to the length.
[0114] It should be noted that the network device can configure the same or different time window lengths for different terminal devices. Exemplarily, the length of the second time window is related to the speed of the terminal device and / or a preset number of location samples. Exemplarily, the length of the second time window can be determined based on the speed of the terminal device and / or the preset number of location samples. For example, the faster the terminal device, the shorter the second time window. For another example, the second time window should contain at least five location samples. For another example, when the speed of the terminal device is less than a preset threshold, the second time window contains five location samples; when the speed of the terminal device is greater than or equal to the preset threshold, the second time window contains eight location samples. In practical applications, the configuration information for the first time window can be explicitly provided in the form of an enumerated IE (Information Element). For example, the configuration information can refer to the following settings, indicating that the length of the first time window MeasWindow can be one of 2000ms (milliseconds), 5000ms, and 10000ms.
[0115] MeasWindow::=ENUMERATED{2000ms,5000ms,10000ms,spare1},
[0116] Among them, spare1 indicates the space reserved for future expansion.
[0117] Corresponding to the above embodiment, the present application also provides a prediction information processing method performed by a network device. FIG5 is a schematic flow chart of a method for adjusting channel status according to another embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes:
[0118] S510: When the RLF prediction information satisfies a first condition, the network device performs a first process;
[0119] Among them, the RLF prediction information is obtained by processing the RLF associated data of the terminal device related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event of the terminal device; the first processing is used to adjust the channel state of the terminal device.
[0120] Optionally, the network device performs the first processing, which may be completed by the network device and the terminal device through interaction. For example, the first processing may be cell switching or adjusting the mobility mode of the terminal device.
[0121] Optionally, the setting and processing of relevant information such as RLF prediction information, the first model, RLF associated data, etc. can refer to the corresponding description of the method executed by the terminal device in the aforementioned embodiment, and will not be repeated here.
[0122] In order to more clearly understand the technical solution of the present application, corresponding embodiments are provided below for the training process of the first model, the determination of RLF prediction information (ie, the reasoning process of the first model), and the processing method based on the RLF prediction information.
[0123] In some embodiments, the above method may further include: the terminal device sends first reporting information; wherein the first reporting information includes RLF associated data related to the first RLF event, and the RLF associated data related to the first RLF event is used for network device training to obtain a first model.
[0124] Accordingly, on the network side, the method may further include: the network device receiving first reporting information from the terminal device. In some embodiments, the method may further include: the network device training a first model based on RLF association data related to the first RLF event.
[0125] That is, the terminal device reports the RLF-related data before the first RLF event occurs to the network device, and then the network device uses the data reported by the terminal device to train and obtain the first model.
[0126] In some embodiments, the terminal device sends the first reporting information, which may include at least one of the following:
[0127] When the connection re-establishment triggered by the first RLF event is completed, the terminal device sends the first reporting information;
[0128] The terminal device sends the first reporting information when the channel is idle;
[0129] The terminal device periodically sends the first reporting information.
[0130] Accordingly, the network device receives the first reporting information from the terminal device, which may include at least one of the following:
[0131] The network device receives first reporting information when the connection re-establishment triggered by the first RLF event is completed;
[0132] The network device receives the first reporting information when the channel of the terminal device is idle;
[0133] The network device periodically sends the first reporting information.
[0134] That is to say, the terminal device reports the RLF-related data related to the first RLF event to the network device, which can be an event-based report. Since the terminal device can store 48 hours of RLF information, the terminal device can also report autonomously when the channel is idle, or report periodically. In actual applications, the terminal device can use one or more methods to report the RLF-related data related to the first RLF event. For example, the terminal device can send the first reporting information when the connection is re-established, and send the first reporting information periodically, so that the network device can receive the first reporting information in time when the connection is re-established, and can periodically receive the first reporting information summarized within the period, thereby improving the reliability of data reporting. In specific implementation, the reporting method can be set according to system requirements or protocol agreements, etc., which are not exhaustively listed here.
[0135] For example, autonomous reporting during channel idle time can specifically involve the terminal device requesting uplink scheduling resources from the network device when the channel is idle, and reporting based on the network device's scheduling. Because RLF events are sporadic, reporting after connection reestablishment or during channel idle time provides greater scheduling flexibility.
[0136] In some embodiments, the first reporting information is carried by an RRC message, a MAC CE (MAC Control Element, a control unit of media access control) or an UCI (Uplink Control Information, uplink control information).
[0137] Optionally, the first reporting information may be carried in a newly defined or dedicated RRC message, MAC CE or UCI, or may be multiplexed with other RRC messages, MAC CE or UCI.
[0138] Exemplarily, the first reporting information may be carried by an RLF report. The RLF report may refer to a VarRLF-Report included in an RRC message UEInformationResponse. In other words, RLF-related data related to the first RLF event may be reported together with the original data in the RLF report. Optionally, the first reporting information may also be reported in other RRC messages, such as UEAssistanceInformation, which is not limited in this application.
[0139] According to the above embodiment, the terminal device reports RLF-related data related to actual RLF events, and the network side trains the model. In this way, the network side's stronger computing power and RLF-related data related to RLF events from multiple terminal devices can be used to train a highly accurate first model.
[0140] In some embodiments, the network device trains a first model based on RLF association data related to the first RLF event, including: the network device extracts feature information from the RLF association data related to the first RLF event, and trains the first model based on the feature information.
[0141] Exemplarily, the first model may be a data feature extraction model.
[0142] Since the network device can collect a large amount of RLF-related data related to actual RLF events from multiple terminal devices, the training of the first model is achieved by extracting feature information from real data, which has the advantage of low implementation difficulty and ensures the prediction accuracy of the first model to a certain extent.
[0143] In some embodiments, the network device trains the first model based on RLF-related data related to the first RLF event, including: the network device trains the first model based on the RLF-related data and non-RLF-related data related to the first RLF event.
[0144] The non-RLF related data includes at least one of the following:
[0145] a measurement result of the serving cell within a third time window during a period in which no RLF event occurs;
[0146] The identification of the serving cell;
[0147] Measurement results of neighboring cells within a third time window during a period in which no RLF event occurs;
[0148] Identification of adjacent cells;
[0149] The location-related information of the terminal device within a third time window in a period in which no RLF event occurs.
[0150] Optionally, the length of the third time window may be the same as the length of the second time window in the aforementioned embodiment.
[0151] In one embodiment, the non-RLF-related data may include measurement results of the serving cell and an identifier of the serving cell within the third time window. In another embodiment, the non-RLF-related data may also include at least one of measurement results of neighboring cells within the third time window during a period in which no RLF event occurred, the identifier of the neighboring cell, and information related to the location of the terminal device within the third time window.
[0152] It should be noted that the configuration of non-RLF-related data may not be limited to the above implementations. For example, the non-RLF-related data may also include only the measurement results of the serving cell within the third time window. In specific implementations, the configuration may be based on model effects, system requirements, or protocol agreements, and is not exhaustive here.
[0153] According to the above embodiment, the network device can use the measurement results, cell identifiers, location-related information, and other data before the first RLF event occurs, as well as the measurement results, cell identifiers, location-related information, and other data during a period in which no RLF event occurs, to perform supervised training to obtain a first model. This embodiment uses positive and negative data to help improve the classification capabilities of the first model, thereby improving prediction accuracy.
[0154] In some embodiments, the network device may include an access network device and / or a core network element.
[0155] Exemplarily, the network device may include an access network device, which receives the first reporting information and performs the above-mentioned model training steps.
[0156] Exemplarily, the training and management of the first model may occur at different locations on the network side. Specifically, the network device may include an access network device and a core network element, wherein the access network device is used to receive the first reported information, i.e., collect training data, and the core network element is used to train the first model.
[0157] Correspondingly, the above method may further include: the access network device sends first reporting information to the core network network element, and the first reporting information is used for training the core network network element to obtain a first model.
[0158] Optionally, the core network element may be an NWDAF (Network Data Analytics Function) element. The NWDAF element has strong computing power and can help improve the accuracy of the first model.
[0159] Optionally, the access network device may also be used to manage the first model, such as model monitoring, model activation, model deactivation, etc.
[0160] As the amount of data associated with RLF events increases, the parameters of the first model will continue to change, and the predictive ability of the first model will continue to improve. Considering the low frequency of RLF, the first model can be trained offline, that is, the model is deployed and inferred after training.
[0161] In the embodiment of the present application, the reasoning process of the first model can be implemented on the network side or the terminal side. Accordingly, the first model can be deployed in the network device or in the terminal device.
[0162] In some embodiments, the reasoning process of the first model is implemented on the terminal side, that is, the RLF prediction information is determined by the terminal device. The above method also includes: the network device sends first configuration information to the terminal device; wherein the first configuration information is used by the terminal device to configure the first model.
[0163] Accordingly, on the terminal side, the method further includes: the terminal device receiving first configuration information, the first configuration information including relevant information of the first model; and the terminal device configuring the first model based on the first configuration information. Exemplarily, the relevant information of the first model may include information such as the type and parameters of the first model.
[0164] That is, the network device can send the configuration information of the trained first model to the terminal device, so that the terminal device can configure the first model and use the first model to process the RLF associated data related to the current moment to obtain RLF prediction information.
[0165] In some embodiments, the first process for adjusting the channel state of the terminal device may be triggered by a network device. Based on this, the terminal device may report the RLF prediction information to the network device after obtaining it. Specifically, the method further includes: the terminal device sending second reporting information; the second reporting information is used to indicate the RLF prediction information. Correspondingly, on the network side, the method further includes: the network device receiving the second reporting information from the terminal device.
[0166] Exemplarily, the second reporting information may include RLF prediction information, and may also include indication information of the RLF prediction information. For example, when the RLF prediction information includes the probability of the second RLF event occurring, the second reporting information may include the probability value. For another example, when the RLF prediction information includes whether the second RLF event occurs, the second reporting information may include 1-bit indication information, where a value of the bit is 1 indicates the occurrence of the second RLF event, and a value of the bit is 0 indicates the non-occurrence of the second RLF event; alternatively, the second reporting information may indicate the occurrence of the second RLF event by carrying a specific field, and when the field is empty, indicates the non-occurrence of the second RLF event.
[0167] In some embodiments, the reasoning process of the first model is implemented on the network side, that is, the RLF prediction information is determined by the network device. The above method may also include: the terminal device sending third reporting information; wherein the third reporting information includes RLF-related data related to the current moment, and the RLF-related data related to the current moment is used by the network device to process using the first model to obtain RLF prediction information.
[0168] Correspondingly, on the network side, the above method may also include: the network device receives third reporting information from the terminal device, the third reporting information includes RLF associated data related to the current moment; the network device uses the first model to process the RLF associated data related to the current moment to obtain RLF prediction information.
[0169] As described in the preceding embodiments, when the RLF prediction information satisfies the first condition, the terminal device and the network device will perform the first process. The first condition may be a condition for predicting the occurrence of an RLF event. For example, the first condition may include: the RLF prediction information indicating that a second RLF event will occur within a first time window after the current moment; or the RLF prediction information indicating that the probability of a second RLF event occurring within the first time window is greater than a first threshold.
[0170] The first threshold may be pre-set, configured by a network device, or configured by a terminal device. For example, the network device or the terminal device may adjust the first threshold based on the effect of the first model to further reduce the number of RLF events or the number of executions of the first process.
[0171] In some embodiments, the RLF prediction information may further include:
[0172] A first time interval; wherein the first time interval is a time interval between the current moment and a second RLF event after the current moment;
[0173] The identifier of the candidate cell;
[0174] Recommended value of candidate cell.
[0175] Exemplarily, the RLF prediction information may include a first time interval, and the terminal device may perform the first processing according to the first time interval, for example, determine relevant parameters in the first processing according to the first time interval.
[0176] Exemplarily, the RLF prediction information may include the identifier of the candidate cell and the recommended value of the candidate cell. In this way, when the first processing is cell switching, the terminal device can determine the candidate cell to be accessed based on the identifier of the candidate cell and the recommended value of the candidate cell, thereby improving the success rate of the cell switching.
[0177] As described in the above embodiments, the first process may include cell switching or adjusting the mobility mode. In some embodiments, the cell switching may include conditional switching.
[0178] The conditional handover process includes downlink synchronization, uplink synchronization, and resource allocation, while the connection re-establishment process after an RLF event includes cell search, downlink synchronization, system information acquisition, uplink synchronization, and resource allocation. In comparison, connection re-establishment requires two steps: cell search and system information acquisition. Generally speaking, the time required for cell search and system information acquisition exceeds the time required for uplink / downlink synchronization and resource allocation. Therefore, performing conditional handover before a radio link failure occurs, or when an RLF is predicted, can effectively reduce service interruption time.
[0179] Figure 6A shows a schematic diagram of conditional switching in an embodiment of the present application. As shown in Figure 6A, conditional switching performed based on the prediction result can skip the wireless problem detection and T310 timer stages, while avoiding the connection re-establishment process, thereby significantly reducing service interruption time.
[0180] In related technologies, when performing conditional handover, the network device needs to send a conditional handover command to the terminal device after obtaining the candidate cell configuration information. The conditional handover command may carry relevant information about the candidate cell and indication information of one or more conditional events. In some embodiments of the present application, the conditional event carried in the conditional handover command may be conditional event A4 (CondEventA4).
[0181] Specifically, the above method may also include: the network device performs a first processing, including: the network device sends a conditional switching command to the terminal device; wherein the conditional switching command is used to indicate relevant information of N candidate cells and a first conditional event, so that the terminal device selects the first candidate cell from the N candidate cells for access when the first conditional event occurs; the first conditional event includes conditional event A4, and N is an integer greater than or equal to 1.
[0182] Accordingly, on the terminal side, the terminal device performs the first processing, which may include:
[0183] The terminal device receives a conditional handover command from the network device; wherein the conditional handover command is used to indicate relevant information of N candidate cells and a first conditional event; wherein the first conditional event includes conditional event A4, and N is an integer greater than or equal to 1;
[0184] When the first condition event occurs, the terminal device selects the first candidate cell from N candidate cells for access.
[0185] Since the channel condition of the serving cell (or source cell) may still be good when conditional handover is adopted to actively avoid RLF, selecting conditional event A4 as the trigger condition for accessing the candidate cell can improve the success rate of handover.
[0186] In some embodiments, the first conditional event further includes a conditional event T1 (CondEvent T1), wherein the second threshold and / or duration in the conditional event T1 is determined by the network device based on the first time interval in the RLF prediction information. The second threshold refers to a threshold-type parameter in the conditional event T1, such as t1-Threshold.
[0187] Optionally, if the RLF prediction information includes a first time interval, that is, a time interval between the current moment and the predicted occurrence of the second RLF event, the first conditional event includes the conditional event T1.
[0188] It should be noted that when the first conditional event includes conditional event A4 and conditional event T1, the terminal device needs to select the first candidate cell for access from the N candidate cells when conditional event A4 and conditional event T1 are simultaneously met. When conditional event T1 is configured as empty, that is, when the first conditional event only includes conditional event A4, the terminal device can select the first candidate cell for access when conditional event A4 is met, without waiting for the measurement time to exceed the first threshold.
[0189] In the above embodiment, if the terminal device successfully accesses the first candidate cell, the conditional handover process is completed. If the terminal device fails to access the first candidate cell, the terminal device may select the second candidate cell for access.
[0190] In some embodiments, the terminal device may use the CHO mechanism in the aforementioned related art to trigger a connection re-establishment process when access to the second candidate cell fails, that is, only try to access the candidate cell twice.
[0191] In some embodiments, the terminal device performs the first process, further comprising:
[0192] In the case of failure to access the first candidate cell, the terminal device selects a second candidate cell from other candidate cells except the first candidate cell among the N candidate cells for access;
[0193] When the second condition is met, the terminal device reestablishes the connection; wherein, the second condition includes: access to each of the N candidate cells fails, or the access duration exceeds a third threshold, and the third threshold is determined based on relevant parameters in the first condition event.
[0194] That is to say, the terminal device can reselect another candidate cell in the conditional switching command for access until the access is successful, or trigger the connection re-establishment process when access to each candidate cell fails or the access duration exceeds the third threshold.
[0195] In some embodiments, the third threshold may be determined based on the second threshold and / or duration in the first conditional event. Exemplarily, the third threshold is the sum of the second threshold and the duration.
[0196] Since AI technology can provide one or more candidate cells based on historical access conditions, it can reflect the connectivity status of the candidate cells in the future to a certain extent. These candidate cells can be considered trustworthy, that is, the terminal device can establish a connection with them to obtain services. Therefore, the candidate cells given by the first model can be tried as much as possible to avoid the connection re-establishment process and reduce service interruption.
[0197] FIG6B shows another schematic diagram of conditional switching in an embodiment of the present application. As shown in FIG6B , the conditional switching triggered by RLF prediction information in an embodiment of the present application includes the following steps:
[0198] 1. The serving cell receives RLF-related data or RLF prediction information. If the serving cell receives RLF-related data, the serving cell processes the RLF-related data using the first model to obtain RLF prediction information.
[0199] 2. The serving cell sends a handover request to the candidate cell.
[0200] 3. After the candidate cell accepts the handover and establishes the RRC configuration, the serving cell receives the handover confirmation information, which includes the RRC configuration information of the candidate cell.
[0201] 4. The serving cell sends a conditional handover command to the terminal device. Considering that the channel conditions of the source serving cell may still be good when conditional handover is used to actively avoid RLF, the conditional handover command should select condEventA4.
[0202] Optionally, if the RLF prediction information includes the time from the current moment to the occurrence of RLF, the conditional switching command also includes condEventT1. The specific values of "t1-Threshold" and duration are configured by the network based on the time from the current moment to the occurrence of RLF. (If this configuration is empty, the terminal device can directly enable the condEventA4 condition judgment without waiting for the t1-Threshold moment to enable it; if it is not empty, the candidate cell must meet both condEventA4 and condEventT1 before attempting to access the cell.)
[0203] 5. When the measurement meets the switching condition (i.e., condition event A4 / T1), the terminal device triggers conditional switching and performs synchronization and random access to the candidate cell.
[0204] If the access is successful, the handover process is completed. If the access fails, the terminal device can reselect another candidate cell for access attempt. If the access still fails, the terminal device can trigger the connection re-establishment process, or continue to select other candidate cells for access until there are no other untried candidate cells or the access attempt time exceeds the third threshold. It can be seen that the difference between the conditional handover in the embodiment of the present application and the traditional conditional handover is:
[0205] It should be noted that the above provides an embodiment of cell handover based on RLF prediction information using conditional handover as an example, but in some embodiments of the present application, traditional cell handover can also be used as the first process. Since it is an active handover based on AI prediction, the radio problem detection and T310 timer stages can be skipped, and the reconnection process can be avoided, thereby reducing service interruption time.
[0206] It can be seen that the embodiment of the present application provides an AI-based RLF event data collection, prediction and processing method, which mainly considers the use of AI technology to learn the behavioral characteristics of UE failure events, combined with the UE's current channel measurement results, location and other information, to predict possible RLF events, and by preparing active switching in advance, reduce UE service interruption time and improve user experience.
[0207] It should be noted that the cell in the embodiment of the present application can be a PCell, a PSCell, or an SCell (Secondary Cell), that is, the embodiment of the present application can support carrier aggregation scenarios and dual connectivity scenarios.
[0208] FIG7 is a schematic block diagram of a terminal device 700 according to an embodiment of the present application. The terminal device 700 may include:
[0209] A first processing module 710 is configured to perform a first process when the radio link failure (RLF) prediction information satisfies a first condition;
[0210] Among them, the RLF prediction information is obtained by processing the RLF associated data related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event; and the first processing is used to adjust the channel state of the terminal device.
[0211] In one embodiment, the RLF prediction information includes:
[0212] Whether a second RLF event occurs within a first time window after the current moment; or,
[0213] The probability of a second RLF event occurring within the first time window.
[0214] In one embodiment, the RLF association data related to the current moment includes the RLF association data acquired at the current moment and / or the RLF association data acquired within a second time window before the current moment.
[0215] In one embodiment, the RLF-related data related to the first RLF event includes the RLF-related data most recently acquired before the first RLF event occurs, and / or the RLF-related data acquired within a second time window before the first RLF event occurs.
[0216] In one embodiment, the length of the second time window is configured by the network device.
[0217] In one embodiment, the length of the second time window is related to the speed of the terminal device and / or a preset number of position samples.
[0218] In one embodiment, the RLF-related data includes at least one of the following:
[0219] Measurement results of the serving cell;
[0220] The identification of the serving cell;
[0221] Measurement results of neighboring cells;
[0222] Identification of adjacent cells;
[0223] Location-related information of the terminal device.
[0224] In one embodiment, the measurement result includes at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a signal to interference plus noise ratio (SINR).
[0225] In one embodiment, the location-related information includes at least one of the location collection time, longitude and latitude information, and movement speed estimation information.
[0226] In one embodiment, as shown in FIG8 , the terminal device 700 further includes a first communication module 810 configured to:
[0227] Sending first reporting information; wherein the first reporting information includes RLF associated data related to the first RLF event, and the RLF associated data related to the first RLF event is used for network equipment training to obtain a first model.
[0228] In one embodiment, the first communication module 810 is configured to perform at least one of the following:
[0229] When the connection re-establishment triggered by the first RLF event is completed, sending first reporting information;
[0230] Sending first reporting information when the channel is idle;
[0231] The first reporting information is sent periodically.
[0232] In one implementation, the first reporting information is carried by an RRC message, a MAC CE, or a UCI.
[0233] In one implementation, the first reporting information is carried by an RLF report.
[0234] In one embodiment, the RLF prediction information is determined by the terminal device;
[0235] As shown in FIG9 , the terminal device 700 further includes a second communication module 910 for receiving first configuration information; wherein the first configuration information includes relevant information of the first model;
[0236] The first processing module 710 is further configured to configure the first model based on the first configuration information.
[0237] In one embodiment, the second communication module 910 is further configured to:
[0238] Send second reporting information; the second reporting information is used to indicate RLF prediction information.
[0239] In one embodiment, as shown in FIG10 , the terminal device 700 further includes a third communication module 1010 configured to:
[0240] Sending third reporting information; wherein, the third reporting information includes RLF associated data related to the current moment, and the RLF associated data related to the current moment is used by the network device to obtain RLF prediction information using the first model.
[0241] In one embodiment, the first condition includes:
[0242] The RLF prediction information indicates that a second RLF event occurs within a first time window after the current moment; or,
[0243] The RLF prediction information indicates that a probability of a second RLF event occurring within the first time window is greater than a first threshold.
[0244] In one embodiment, the RLF prediction information further includes at least one of the following:
[0245] A first time interval; wherein the first time interval is a time interval between the current moment and a second RLF event after the current moment;
[0246] The identifier of the candidate cell;
[0247] Recommended value of candidate cell.
[0248] In one embodiment, the first process includes cell switching or adjusting a mobility pattern.
[0249] In one embodiment, the cell handover includes conditional handover.
[0250] In one embodiment, as shown in FIG11 , the terminal device 700 further includes a fourth communication module 1110 configured to:
[0251] Receiving a conditional handover command from a network device; wherein the conditional handover command is used to indicate relevant information of N candidate cells and a first conditional event; wherein the first conditional event includes conditional event A4, and N is an integer greater than or equal to 1;
[0252] The first processing module 710 is further configured to select a first candidate cell from the N candidate cells for access when a first condition event occurs.
[0253] In one embodiment, the first conditional event further includes a conditional event T1, and the second threshold and / or duration in the conditional event T1 is determined by the network device based on the first time interval in the RLF prediction information.
[0254] In one embodiment, the first processing module 710 is further configured to:
[0255] In the case of failure to access the first candidate cell, selecting a second candidate cell for access from other candidate cells except the first candidate cell among the N candidate cells;
[0256] When the second condition is met, the connection is re-established; wherein the second condition includes: access to each of the N candidate cells fails, or the access duration exceeds a third threshold, and the third threshold is determined based on relevant parameters in the first condition event.
[0257] The terminal device 700 of the embodiment of the present application can implement the corresponding functions of the terminal device in the aforementioned method embodiment. The processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the terminal device 700 can be found in the corresponding descriptions in the above-mentioned method embodiments, and will not be repeated here. It should be noted that the functions described by the various modules (sub-modules, units or components, etc.) in the terminal device 700 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.) or by the same module (sub-module, unit or component, etc.).
[0258] FIG12 is a schematic block diagram of a network device 1200 according to an embodiment of the present application. The network device 1200 may include:
[0259] The second processing module 1210 is configured to perform a first process when the radio link failure (RLF) prediction information satisfies a first condition;
[0260] Among them, the RLF prediction information is obtained by processing the RLF associated data of the terminal device related to the current moment using the first model; the first model is trained based on the RLF associated data related to the first RLF event of the terminal device; the first processing is used to adjust the channel state of the terminal device.
[0261] In one embodiment, the RLF prediction information includes:
[0262] Whether a second RLF event occurs within a first time window after the current moment; or,
[0263] The probability of a second RLF event occurring within the first time window.
[0264] In one implementation, the RLF association data related to the current moment includes the RLF association data acquired at the current moment and / or the RLF association data acquired within a second time window before the current moment.
[0265] In one embodiment, the RLF association data related to the first RLF event of the terminal device includes the RLF association data most recently acquired before the first RLF event occurs, and / or the RLF association data acquired within a second time window before the first RLF event occurs.
[0266] In one embodiment, the length of the second time window is configured by the network device.
[0267] In one embodiment, the length of the second time window is related to the speed of the terminal device and / or a preset number of position samples.
[0268] In one embodiment, the RLF-related data includes at least one of the following:
[0269] Measurement results of the serving cell;
[0270] The identification of the serving cell;
[0271] Measurement results of neighboring cells;
[0272] Identification of adjacent cells;
[0273] Location-related information of the terminal device.
[0274] In one embodiment, the measurement result includes at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), and a signal to interference plus noise ratio (SINR).
[0275] In one embodiment, the location-related information includes at least one of the location collection time, longitude and latitude information, and movement speed estimation information.
[0276] In one embodiment, as shown in FIG13 , the network device 1200 further includes a fifth communication module 1310 configured to:
[0277] Receive first reporting information from a terminal device; wherein the first reporting information includes RLF-related data related to a first RLF event.
[0278] In one embodiment, the second processing module 1210 is further configured to:
[0279] A first model is trained based on RLF-related data related to the first RLF event.
[0280] In one embodiment, the second processing module 1210 is further configured to:
[0281] Feature information in RLF-related data related to the first RLF event is extracted, and a first model is obtained through training based on the feature information.
[0282] In one embodiment, the second processing module 1210 is further configured to:
[0283] Training a first model based on RLF-related data and non-RLF-related data related to the first RLF event;
[0284] The non-RLF related data includes at least one of the following:
[0285] a measurement result of the serving cell within a third time window during a period in which no RLF event occurs;
[0286] The identification of the serving cell;
[0287] Measurement results of neighboring cells within a third time window during a period in which no RLF event occurs;
[0288] Identification of adjacent cells;
[0289] The location-related information of the terminal device within a third time window in a period in which no RLF event occurs.
[0290] In one embodiment, the network device is an access network device, and the fifth communication module 1310 is further configured to:
[0291] The access network device sends first reporting information to the core network network element, and the first reporting information is used for training the core network network element to obtain a first model.
[0292] In one embodiment, the fifth communication module 1310 is configured to perform at least one of the following:
[0293] When the connection re-establishment triggered by the first RLF event is completed, receiving first reporting information;
[0294] Receiving first reporting information when the channel of the terminal device is idle;
[0295] The first reporting information is sent periodically.
[0296] In one implementation, the first reporting information is carried by an RRC message, a MAC CE, or a UCI.
[0297] In one implementation, the first reporting information is carried by an RLF report.
[0298] In one embodiment, as shown in FIG14 , the network device 1200 further includes a sixth communication module 1410 configured to:
[0299] Sending first configuration information to the terminal device; wherein the first configuration information is used to configure the first model for the terminal device.
[0300] In one embodiment, the sixth communication module 1410 is further configured to:
[0301] Receive second reporting information from the terminal device; the second reporting information is used to indicate RLF prediction information.
[0302] In one embodiment, as shown in FIG15 , the network device 1200 further includes a seventh communication module 1510 configured to:
[0303] receiving third reporting information from the terminal device; wherein the third reporting information includes RLF-related data related to the current moment;
[0304] The second processing module 1210 is further configured to process the RLF associated data related to the current moment using the first model to obtain RLF prediction information.
[0305] In one embodiment, the first condition includes:
[0306] The RLF prediction information indicates that a second RLF event occurs within a first time window after the current moment; or,
[0307] The RLF prediction information indicates that a probability of a second RLF event occurring within the first time window is greater than a first threshold.
[0308] In one embodiment, the RLF prediction information further includes at least one of the following:
[0309] A first time interval; wherein the first time interval is a time interval between the current moment and a second RLF event after the current moment;
[0310] The identifier of the candidate cell;
[0311] Recommended value of candidate cell.
[0312] In one embodiment, the first process includes cell switching or adjusting a mobility pattern.
[0313] In one embodiment, the cell handover includes conditional handover.
[0314] In one embodiment, as shown in FIG16 , the network device 1200 further includes an eighth communication module 1610 configured to:
[0315] A conditional switching command is sent to the terminal device; wherein the conditional switching command is used to indicate relevant information of N candidate cells and a first conditional event, so that the terminal device selects the first candidate cell from the N candidate cells for access when the first conditional event occurs; the first conditional event includes conditional event A4, and N is an integer greater than or equal to 1.
[0316] In one embodiment, the first conditional event further includes a conditional event T1, and the second threshold and / or duration in the conditional event T1 is determined based on the first time interval in the RLF prediction information.
[0317] The network device 1200 of the embodiment of the present application can implement the corresponding functions of the network device in the aforementioned method embodiment. The processes, functions, implementation methods and beneficial effects corresponding to each module (sub-module, unit or component, etc.) in the network device 1200 can be found in the corresponding description in the above method embodiment, and will not be repeated here. It should be noted that the functions described in the various modules (sub-module, unit or component, etc.) in the network device 1200 of the embodiment of the application can be implemented by different modules (sub-module, unit or component, etc.) or by the same module (sub-module, unit or component, etc.).
[0318] Figure 17 is a schematic structural diagram of a communication device 1700 according to an embodiment of the present application. The communication device 1700 includes a processor 1710, which can call and execute a computer program from a memory to enable the communication device 1700 to implement the method according to the embodiment of the present application.
[0319] In one embodiment, the communication device 1700 may further include a memory 1720. The processor 1710 may call and execute a computer program from the memory 1720 to enable the communication device 1700 to implement the method in the embodiment of the present application.
[0320] The memory 1720 may be a separate device independent of the processor 1710 , or may be integrated into the processor 1710 .
[0321] In one embodiment, the communication device 1700 may further include a transceiver 1730 , and the processor 1710 may control the transceiver 1730 to communicate with other devices. Specifically, the transceiver 1730 may send information or data to other devices, or receive information or data sent by other devices.
[0322] The transceiver 1730 may include a transmitter and a receiver. The transceiver 1730 may further include an antenna, and the number of antennas may be one or more.
[0323] In one embodiment, the communication device 1700 may be a terminal device of an embodiment of the present application, and the communication device 1700 may implement the corresponding processes implemented by the terminal device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.
[0324] In one embodiment, the communication device 1700 may be a network device of an embodiment of the present application, and the communication device 1700 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.
[0325] 18 is a schematic structural diagram of a chip 1800 according to an embodiment of the present application. The chip 1800 includes a processor 1810, which can call and execute a computer program from a memory to implement the method according to the embodiment of the present application.
[0326] In one embodiment, the chip 1800 may further include a memory 1820. The processor 1810 may call and execute a computer program from the memory 1820 to implement the method executed by the terminal device in the embodiment of the present application.
[0327] The memory 1820 may be a separate device independent of the processor 1810 , or may be integrated into the processor 1810 .
[0328] In one embodiment, the chip 1800 may further include an input interface 1830. The processor 1810 may control the input interface 1830 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.
[0329] In one embodiment, the chip 1800 may further include an output interface 1840. The processor 1810 may control the output interface 1840 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.
[0330] In one embodiment, the chip can be applied to the terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the terminal device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
[0331] In one embodiment, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
[0332] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0333] The processor mentioned above may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. The general-purpose processor mentioned above may be a microprocessor or any conventional processor, etc.
[0334] The memory mentioned above may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM).
[0335] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.
[0336] FIG19 is a schematic block diagram of a communication system 1900 according to an embodiment of the present application. The communication system 1900 includes a terminal device 700 and a network device 1200 .
[0337] Among them, the terminal device 700 and the network device 1200 are used to perform a first processing when the radio link failure RLF prediction information meets the first condition; wherein the RLF prediction information is obtained by processing the RLF associated data related to the current moment using a first model; the first model is trained based on the RLF associated data related to the first RLF event; the first processing is used to adjust the channel state of the terminal device.
[0338] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function in accordance with the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).
[0339] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0340] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0341] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
Claims
1. A method for adjusting a channel state, include: When the radio link failure RLF prediction information satisfies the first condition, the terminal device performs a first process; Among them, the RLF prediction information is obtained by processing the RLF associated data related to the current moment using a first model; the first model is trained based on the RLF associated data related to the first RLF event; and the first processing is used to adjust the channel state of the terminal device.
2. The method according to claim 1, in, The RLF prediction information includes: whether a second RLF event occurs within a first time window after the current moment; or, A probability of the second RLF event occurring within the first time window.
3. The method according to claim 1 or 2, in, The RLF associated data related to the current moment includes the RLF associated data acquired at the current moment and / or the RLF associated data acquired within a second time window before the current moment.
4. The method according to any one of claims 1 to 3, in, The RLF-related data related to the first RLF event includes the RLF-related data most recently acquired before the first RLF event occurs, and / or the RLF-related data acquired within a second time window before the first RLF event occurs.
5. The method according to claim 3 or 4, in, The length of the second time window is configured by the network device.
6. The method according to any one of claims 3 to 5, in, The length of the second time window is related to the speed of the terminal device and / or a preset number of position samplings.
7. The method according to any one of claims 1 to 6, in, The RLF associated data includes at least one of the following: Measurement results of the serving cell; an identifier of the serving cell; Measurement results of neighboring cells; The identifier of the neighboring cell; The location-related information of the terminal device.
8. The method according to claim 7, in, The measurement result includes at least one of a reference signal received power RSRP, a reference signal received quality RSRQ and a signal to interference plus noise ratio SINR.
9. The method according to claim 7 or 8, in, The location-related information includes at least one of location collection time, longitude and latitude information, and moving speed estimation information.
10. The method according to any one of claims 1 to 9, in, The method further comprises: The terminal device sends first reporting information; wherein, the first reporting information includes the RLF associated data related to the first RLF event, and the RLF associated data related to the first RLF event is used for network equipment training to obtain the first model.
11. The method according to claim 10, in, The terminal device sends first reporting information, including at least one of the following: When the connection re-establishment triggered by the first RLF event is completed, the terminal device sends the first reporting information; The terminal device sends the first reporting information when the channel is idle; The terminal device periodically sends the first reporting information.
12. The method according to claim 10 or 11, in, The first reporting information is carried by a radio resource control RRC message, a media access control control unit MAC CE or uplink control information UCI.
13. The method according to any one of claims 10 to 12, in, The first reporting information is carried by the RLF report.
14. The method according to any one of claims 1 to 13, in, The RLF prediction information is determined by the terminal device; The method further comprises: The terminal device receives first configuration information; wherein the first configuration information includes relevant information of the first model; The terminal device configures the first model based on the first configuration information.
15. The method according to claim 14, in, The method further comprises: The terminal device sends second reporting information; the second reporting information is used to indicate the RLF prediction information.
16. The method according to any one of claims 1 to 13, in, The method further comprises: The terminal device sends third reporting information; wherein, the third reporting information includes the RLF associated data related to the current moment, and the RLF associated data related to the current moment is used by the network device to obtain the RLF prediction information using the first model.
17. The method according to any one of claims 1 to 16, in, The first condition includes: The RLF prediction information indicates that a second RLF event occurs within a first time window after the current moment; or, The RLF prediction information indicates that a probability of the second RLF event occurring within the first time window is greater than a first threshold.
18. The method according to any one of claims 1 to 17, in, The RLF prediction information also includes at least one of the following: The first time interval is the time interval between the current time and the second RLF event after the current time. the time interval between The identification of the candidate cell; Recommended value for candidate cells.
19. The method according to any one of claims 1 to 18, in, The first process includes cell switching or adjusting a mobility mode.
20. The method according to claim 19, in, The cell switching includes conditional switching.
21. The method according to any one of claims 1 to 20, in, The terminal device performs the first process, including: The terminal device receives a conditional switching command from a network device; wherein the conditional switching command is used to indicate relevant information of N candidate cells and a first conditional event; wherein the first conditional event includes a conditional event A4, and N is an integer greater than or equal to 1; When the first condition event occurs, the terminal device selects a first candidate cell from the N candidate cells for access.
22. The method according to claim 21, in, The first conditional event also includes a conditional event T1, and the second threshold and / or duration in the conditional event T1 is determined by the network device based on the first time interval in the RLF prediction information.
23. The method according to claim 21 or 22, in, The terminal device performs the first process, further comprising: In the case of failure to access the first candidate cell, the terminal device selects a second candidate cell for access from other candidate cells except the first candidate cell among the N candidate cells; When the second condition is met, the terminal device reestablishes the connection; wherein, the second condition includes: access to each of the N candidate cells fails, or the access duration exceeds a third threshold, and the third threshold is determined based on relevant parameters in the first condition event.
24. A method for adjusting a channel state, include: When the RLF prediction information satisfies the first condition, the network device performs a first process; Among them, the RLF prediction information is obtained by processing the RLF associated data of the terminal device related to the current moment using a first model; the first model is trained based on the RLF associated data related to the first RLF event of the terminal device; and the first processing is used to adjust the channel state of the terminal device.
25. The method according to claim 24, in, The RLF prediction information includes: whether a second RLF event occurs within a first time window after the current moment; or, A probability of the second RLF event occurring within the first time window.
26. The method according to claim 24 or 25, in, The RLF associated data related to the current moment includes the RLF associated data acquired at the current moment and / or the RLF associated data acquired within a second time window before the current moment.
27. The method according to any one of claims 24 to 26, in, The RLF-associated data related to the first RLF event of the terminal device includes the RLF-associated data most recently acquired before the first RLF event occurs, and / or the RLF-associated data acquired within a second time window before the first RLF event occurs.
28. The method according to claim 26 or 27, in, The length of the second time window is configured by the network device.
29. The method according to any one of claims 26 to 28, in, The length of the second time window is related to the speed of the terminal device and / or a preset number of position samplings.
30. The method according to any one of claims 24 to 29, in, The RLF associated data includes at least one of the following: Measurement results of the serving cell; an identifier of the serving cell; Measurement results of neighboring cells; The identifier of the neighboring cell; The location-related information of the terminal device.
31. The method according to claim 30, in, The measurement result includes at least one of RSRP, RSRQ and SINR.
32. The method according to claim 30 or 31, in, The location-related information includes at least one of location collection time, longitude and latitude information, and moving speed estimation information.
33. The method according to any one of claims 24 to 32, in, The method further comprises: The network device receives first reporting information from the terminal device; wherein the first reporting information includes RLF associated data related to the first RLF event.
34. The method according to claim 33, in, The method further comprises: The network device trains the first model based on RLF association data related to the first RLF event.
35. The method according to claim 34, in, The network device trains the first model based on the RLF association data related to the first RLF event, including: The network device extracts feature information from RLF associated data related to the first RLF event, and obtains the first model through training based on the feature information.
36. The method according to claim 34, in, The network device trains the first model based on the RLF association data related to the first RLF event, including: The network device trains the first model based on RLF-related data and non-RLF-related data related to the first RLF event; The non-RLF associated data includes at least one of the following: A measurement result of the serving cell in a third time window during a period in which no RLF event occurs; an identifier of the serving cell; The measurement results of the neighboring cells in the third time window in the period when the RLF event does not occur; The identifier of the neighboring cell; The location-related information of the terminal device within a third time window in a period when no RLF event occurs.
37. The method according to claim 33, in, The network device is an access network device, and the method further includes: The access network device sends the first reporting information to the core network network element, and the first reporting information is used by the core network network element to train the first model.
38. The method according to any one of claims 33 to 37, in, The network device receives first reporting information from the terminal device, including at least one of the following: The network device receives the first reporting information when the connection re-establishment triggered by the first RLF event is completed; The network device receives the first reporting information when the channel of the terminal device is idle; The network device periodically sends the first reporting information.
39. The method according to any one of claims 33 to 38, in, The first reporting information is carried by an RRC message, a MAC CE or a UCI.
40. The method according to any one of claims 33 to 39, in, The first reporting information is carried by the RLF report.
41. The method according to any one of claims 24 to 40, in, The method further comprises: The network device sends first configuration information to the terminal device; wherein the first configuration information is used by the terminal device to configure the first model.
42. The method according to claim 41, in, The method further comprises: The network device receives second reporting information from the terminal device; the second reporting information is used to indicate the RLF prediction information.
43. The method according to any one of claims 24 to 40, in, The method further comprises: The network device receives third reporting information from the terminal device; wherein the third reporting information includes the RLF associated data related to the current moment; The network device processes the RLF associated data related to the current moment using the first model to obtain the RLF prediction information.
44. The method according to any one of claims 24 to 43, in, The first condition includes: The RLF prediction information indicates that a second RLF event occurs within a first time window after the current moment; or, The RLF prediction information indicates that a probability of the second RLF event occurring within the first time window is greater than a first threshold.
45. The method according to any one of claims 24 to 44, in, The RLF prediction information also includes at least one of the following: A first time interval; wherein the first time interval is a time interval between the current moment and a second RLF event after the current moment; The identification of the candidate cell; Recommended value for candidate cells.
46. The method according to any one of claims 24 to 45, in, The first process includes cell switching or adjusting a mobility mode.
47. The method according to claim 46, in, The cell switching includes conditional switching.
48. The method according to any one of claims 24 to 47, in, The network device performs the first process, including: The network device sends a conditional switching command to the terminal device; wherein the conditional switching command is used to indicate relevant information of N candidate cells and a first conditional event, so that the terminal device selects a first candidate cell from the N candidate cells for access when the first conditional event occurs; the first conditional event includes conditional event A4, and N is an integer greater than or equal to 1.
49. The method according to claim 48, in, The first conditional event also includes a conditional event T1, and the second threshold and / or duration in the conditional event T1 is determined by the network device based on the first time interval in the RLF prediction information.
50. A terminal device, include: A first processing module, configured to perform a first process when the RLF prediction information satisfies a first condition; The RLF prediction information is obtained by processing the RLF associated data related to the current moment using a first model; the first model is obtained by training the RLF associated data related to the first RLF event; the first processing is used to adjust the terminal Channel status of the device.
51. The terminal device according to claim 50, in, The RLF prediction information includes: whether a second RLF event occurs within a first time window after the current moment; or, A probability of the second RLF event occurring within the first time window.
52. The terminal device according to claim 50 or 51, in, The RLF associated data related to the current moment includes the RLF associated data acquired at the current moment and / or the RLF associated data acquired within a second time window before the current moment.
53. The terminal device according to any one of claims 50 to 52, in, The RLF-related data related to the first RLF event includes the RLF-related data most recently acquired before the first RLF event occurs, and / or the RLF-related data acquired within a second time window before the first RLF event occurs.
54. The terminal device according to claim 52 or 53, in, The length of the second time window is configured by the network device.
55. The terminal device according to any one of claims 52 to 54, in, The length of the second time window is related to the speed of the terminal device and / or a preset number of position samplings.
56. The terminal device according to any one of claims 50 to 55, in, The RLF associated data includes at least one of the following: Measurement results of the serving cell; an identifier of the serving cell; Measurement results of neighboring cells; The identifier of the neighboring cell; The location-related information of the terminal device.
57. The terminal device according to claim 56, in, The measurement result includes at least one of RSRP, RSRQ and SINR.
58. The terminal device according to claim 56 or 57, in, The location-related information includes at least one of location collection time, longitude and latitude information, and moving speed estimation information.
59. The terminal device according to any one of claims 50 to 58, in, The terminal device further includes a first communication module, configured to: Sending first reporting information; wherein the first reporting information includes the RLF associated data related to the first RLF event, and the RLF associated data related to the first RLF event is used for network equipment training to obtain the first model.
60. The terminal device according to claim 59, in, The first communication module is used to perform at least one of the following: When the connection re-establishment triggered by the first RLF event is completed, sending the first reporting information; Sending the first reporting information when the channel is idle; The first reporting information is sent periodically.
61. The terminal device according to claim 59 or 60, in, The first reporting information is carried by an RRC message, a MAC CE or a UCI.
62. The terminal device according to any one of claims 59 to 61, in, The first reporting information is carried by the RLF report.
63. The terminal device according to any one of claims 50 to 62, in, The RLF prediction information is determined by the terminal device; The terminal device further includes a second communication module, configured to receive first configuration information; wherein the first configuration information includes relevant information of the first model; The first processing module is further used to configure the first model based on the first configuration information.
64. The terminal device according to claim 63, in, The second communication module is also used for: Sending second reporting information; the second reporting information is used to indicate the RLF prediction information.
65. The terminal device according to any one of claims 50 to 62, in, The terminal device further includes a third communication module, configured to: Sending third reporting information; wherein, the third reporting information includes the RLF associated data related to the current moment, and the RLF associated data related to the current moment is used by the network device to obtain the RLF prediction information using the first model.
66. The terminal device according to any one of claims 50 to 65, in, The first condition includes: The RLF prediction information indicates that a second RLF event occurs within a first time window after the current moment; or, The RLF prediction information indicates that a probability of the second RLF event occurring within the first time window is greater than a first threshold.
67. The terminal device according to any one of claims 50 to 66, in, The RLF prediction information also includes at least one of the following: A first time interval; wherein the first time interval is a time interval between the current moment and a second RLF event after the current moment; The identification of the candidate cell; Recommended value for candidate cells.
68. The terminal device according to any one of claims 50 to 67, in, The first process includes cell switching or adjusting a mobility mode.
69. The terminal device according to claim 68, in, The cell switching includes conditional switching.
70. The terminal device according to any one of claims 50 to 69, in, The terminal device includes a fourth communication module, which is used to receive a conditional switching command from a network device; wherein the conditional switching command is used to indicate relevant information of N candidate cells and a first conditional event; wherein the first conditional event includes a conditional event A4, and N is an integer greater than or equal to 1; The first processing module is further configured to select a first candidate cell for access from among the N candidate cells when the first condition event occurs.
71. The terminal device according to claim 70, in, The first conditional event also includes a conditional event T1, and the second threshold and / or duration in the conditional event T1 is determined by the network device based on the first time interval in the RLF prediction information.
72. The terminal device according to claim 70 or 71, in, The first processing module is also used for: In the case of failure to access the first candidate cell, selecting a second candidate cell for access from other candidate cells except the first candidate cell among the N candidate cells; When the second condition is met, the connection is reestablished; wherein the second condition includes: access to each of the N candidate cells fails, or the access duration exceeds a third threshold, and the third threshold is determined based on relevant parameters in the first condition event.
73. A network device, include: A second processing module, configured to perform a first process when the RLF prediction information satisfies a first condition; Among them, the RLF prediction information is obtained by processing the RLF associated data of the terminal device related to the current moment using a first model; the first model is trained based on the RLF associated data related to the first RLF event of the terminal device; and the first processing is used to adjust the channel state of the terminal device.
74. The network device according to claim 73, in, The RLF prediction information includes: whether a second RLF event occurs within a first time window after the current moment; or, A probability of the second RLF event occurring within the first time window.
75. The network device according to claim 73 or 74, in, The RLF associated data related to the current moment includes the RLF associated data acquired at the current moment and / or the RLF associated data acquired within a second time window before the current moment.
76. The network device according to any one of claims 73 to 75, in, The RLF-associated data related to the first RLF event of the terminal device includes the RLF-associated data most recently acquired before the first RLF event occurs, and / or the RLF-associated data acquired within a second time window before the first RLF event occurs.
77. The network device according to claim 75 or 76, in, The length of the second time window is configured by the network device.
78. The network device according to any one of claims 75 to 77, in, The length of the second time window is related to the speed of the terminal device and / or a preset number of position samplings.
79. The network device according to any one of claims 73 to 78, in, The RLF associated data includes at least one of the following: Measurement results of the serving cell; an identifier of the serving cell; Measurement results of neighboring cells; The identifier of the neighboring cell; The location-related information of the terminal device.
80. The network device according to claim 79, in, The measurement result includes at least one of RSRP, RSRQ and SINR.
81. The network device according to claim 79 or 80, in, The location-related information includes at least one of location collection time, longitude and latitude information, and moving speed estimation information.
82. The network device according to any one of claims 73 to 81, in, The network device further includes a fifth communication module, configured to: Receive first reporting information from the terminal device; wherein the first reporting information includes RLF associated data related to the first RLF event.
83. The network device according to claim 82, in, The second processing module is also used for: The first model is trained based on RLF association data related to the first RLF event.
84. The network device according to claim 83, in, The second processing module is also used for: Feature information in RLF associated data related to the first RLF event is extracted, and the first model is obtained by training based on the feature information.
85. The network device according to claim 83, in, The second processing module is also used for: The first model is obtained by training based on RLF-related data and non-RLF-related data related to the first RLF event; The non-RLF associated data includes at least one of the following: A measurement result of the serving cell in a third time window during a period in which no RLF event occurs; an identifier of the serving cell; The measurement results of the neighboring cells in the third time window in the period when the RLF event does not occur; The identifier of the neighboring cell; The location-related information of the terminal device within a third time window in a period when no RLF event occurs.
86. The network device according to claim 82, in, The network device is an access network device, and the fifth communication module is further used for: The access network device sends the first reporting information to the core network network element, and the first reporting information is used by the core network network element to train the first model.
87. The network device according to any one of claims 82 to 86, in, The fifth communication module is further configured to perform at least one of the following: When the connection reestablishment triggered by the first RLF event is completed, receiving the first reporting information; Receiving the first reporting information when the channel of the terminal device is idle; The first reporting information is sent periodically.
88. The network device according to any one of claims 82 to 87, in, The first reporting information is carried by an RRC message, a MAC CE or a UCI.
89. The network device according to any one of claims 82 to 88, in, The first reporting information is carried by the RLF report.
90. The network device according to any one of claims 73 to 89, in, The network device further includes a sixth communication module, configured to: Sending first configuration information to the terminal device; wherein the first configuration information is used for the terminal device to configure the first model.
91. The network device according to claim 90, in, The sixth communication module is also used for: Receive second reporting information from the terminal device; the second reporting information is used to indicate the RLF prediction information.
92. The network device according to any one of claims 73 to 89, in, The network device further includes a seventh communication module, configured to receive third reporting information from the terminal device; wherein the third reporting information includes the RLF associated data related to the current moment; The second processing module is further configured to process the RLF associated data related to the current moment using the first model to obtain the RLF prediction information.
93. The network device according to any one of claims 73 to 92, in, The first condition includes: The RLF prediction information indicates that a second RLF event occurs within a first time window after the current moment; or, The RLF prediction information indicates that a probability of the second RLF event occurring within the first time window is greater than a first threshold.
94. The network device according to any one of claims 73 to 93, in, The RLF prediction information also includes at least one of the following: A first time interval; wherein the first time interval is a time interval between the current moment and a second RLF event after the current moment; The identification of the candidate cell; Recommended value for candidate cells.
95. The network device according to any one of claims 73 to 94, in, The first process includes cell switching or adjusting a mobility mode.
96. The network device according to claim 95, in, The cell switching includes conditional switching.
97. The network device according to any one of claims 73 to 96, in, The network device further includes an eighth communication module, configured to: Send a conditional switching command to the terminal device; wherein the conditional switching command is used to indicate relevant information of N candidate cells and a first conditional event, so that the terminal device selects a first candidate cell from the N candidate cells for access when the first conditional event occurs; the first conditional event includes conditional event A4, and N is an integer greater than or equal to 1.
98. The network device according to claim 97, in, The first conditional event also includes a conditional event T1, and the second threshold and / or duration in the conditional event T1 is determined based on the first time interval in the RLF prediction information.
99. A terminal device, include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory so that the terminal device executes the method as claimed in any one of claims 1 to 23.
100. A network device, include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory so that the network device executes the method as claimed in any one of claims 24 to 49.
101. A chip, include: A processor, configured to call and run a computer program from a memory so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 49.
102. A computer-readable storage medium, used for storing a computer program, which, when executed by a device, causes the device to perform the method according to any one of claims 1 to 49.
103. A computer program product comprising computer program instructions, the computer program instructions causing a computer to perform the method of any one of claims 1 to 49.
104. A computer program, the computer program causing a computer to execute the method as claimed in any one of claims 1 to 49.
105. A communication system, include: A terminal device, configured to execute the method according to any one of claims 1 to 23; A network device, configured to execute the method according to any one of claims 24 to 49.
Citation Information
Patent Citations
Communication method and device
CN114143799A
Information transmission method and device, communication equipment and storage medium
CN115836545A
Method, UE and network node for fault prediction
CN116034599A
Signalling data for training machine learning based predictive handover
EP3962153A1
Prediction and proactive handling of radio link failures
WO2023014258A1
Cited By
Method and apparatus used in wireless communication
WO2026137881A1
